This paper introduces a novel framework for zero-shot learning (ZSL), i.e., to recognize new categories that are unseen during training, by distilling knowledge from foundation models. Specifically, we first employ ChatGPT and DALL-E to synthesize reference images of unseen categories from text prompts. Then, the test image is aligned with text and reference images using CLIP and DINO. Finally, the predicted logits are aggregated according to their confidence to produce the final prediction.Experiments are conducted on multiple datasets, including CIFAR-10, CIFAR-100, and TinyImageNet. The results demonstrate that our model can significantly improve classification accuracy compared to previous approaches, achieving AUROC scores above 96\% across all test datasets. Our code is available at https://github.com/1134112149/MICW-ZIC.

The pursuit of Artificial Intelligence (AI) that emulates human cognitive processes is a cornerstone of ethical AI development, ensuring that emerging technologies can integrate seamlessly into societal frameworks requiring nuanced understanding and decision-making. Zero-Shot Instance Retrieval (ZSIR) stands at the forefront of this endeavour, potentially providing a robust platform for AI systems, particularly large visual language models, to demonstrate and refine cognition-aligned learning without the need for direct experience. In this paper, we critically evaluate current cognition alignment methodologies within traditional zero-shot learning paradigms, using visual attributes and word embedding generated by large AI models. We propose a unified similarity function that quantifies the cognitive alignment level, bridging the gap between AI processes and human-like understanding. Through extensive experimentation, our findings illustrate that this similarity function can effectively mirror the visual-semantic gap, steering the model towards enhanced performance in zero-shot instance retrieval. This work not only benchmarks the cognition alignment of AI, but also sets a new precedent for the development of visual language models attuned to the complexities of human cognition.}

Zero-shot learning ability robotics enables robots to generalize their knowledge and perform tasks for which they have not been explicitly trained. This ability is extremely helpful because in classic learning approaches, robots are trained on specific tasks and require extensive data and labeled examples to perform accurately. However, in real-world scenarios, robots often encounter new or unseen tasks that were not part of their training data. We briefly survey works in this area to give the reader a perspective about progresses in this area.

This paper explores the potential of using the SAM segmentator to enhance the segmentation capability of known methods. SAM is a promptable segmentation system that offers zero-shot generalization to unfamiliar objects and images, eliminating the need for additional training. The open-source nature of SAM on GitHub allows for easy access and implementation. In our experiments, we aim to improve the segmentation performance by providing SAM with checkpoints extracted from the masks produced by DeepLabv3+, then merging the segmentation masks provided by these two networks. Additionally, we examine the \enquote{oracle} method (as upper bound baseline performance), where segmentation masks are inferred only by SAM with checkpoints extracted from ground truth. In addition, we tested in the CAMO datasets an ensemble of PVTv2 transformers; combining the ensemble and SAM yields state-of-the-art performance in that dataset. The results of our study provide valuable insights into the potential of incorporating the SAM segmentator into existing segmentation techniques. We release with this paper the open-source implementation of our method.

Recently, the focus of entity linking research has centered on the zero-shot scenario, where the entity mention to be labeled at the time of testing was never observed during the training phase or may belong to a different domain than the source domain. Current studies have used BERT as the base encoder as it effectively establishes distributional links between source and target domains. The currently available negative sampling methods all use an extractive approach, which makes it difficult for the models to learn diverse and more challenging negative samples. To address this problem, we propose a generative negative sampling method, Adaptive_mixup_hard, which generates more difficult negative entities by fusing the features of both positive and negative samples on top of hard negative sampling and introduces a transformable adaptive parameter W to increase the diversity of negative samples. Next, we fuse our method with the Biencoder architecture and evaluate its performance under three different score functions. Ultimately, experimental results on the standard benchmark dataset Zeshel demonstrate the effectiveness of our method.

Reemergence of deep Neural Networks (CNNs) has lead to high-performance supervised learning algorithms for the Electro-Optical (EO) domain classification and detection problems. This success is possible because generating huge labeled datasets has become possible using modern crowdsourcing labeling platforms such as Amazon Mechanical Turk that recruit ordinary people to label data. Unlike the EO domain, labeling the Synthetic Aperture Radar (SAR) domain data can be a lot more challenging and for various reasons using crowdsourcing platforms is not feasible for labeling the SAR domain data. As a result, training deep networks using supervised learning is more challenging in the SAR domain. In the paper,we present a new framework to train a deep neural network for classifying Synthetic Aperture Radar (SAR) images by eliminating the need for huge labeled dataset. Our idea is based on transferring knowledge from a related EO domain problem, where labeled data is easy to obtain. We transfer knowledge from the EO domain through learning a shared invariant cross-domain embedding space that is also discriminative for classification. To this end, we train two deep encoders that are coupled through their last year to map data points from the EO and the SAR domains to the shared embedding space such that the distance between the distributions of the two domains is minimized in the latent embedding space. We use the Sliced Wasserstein Distance (SWD) to measure and minimize the distance between these two distributions and use a limited number of SAR label data points to match the distributions class-conditionally. As a result of this training procedure, a classifier trained from the embedding space to the label space using mostly the EO data would generalize well on the SAR domain. We provide theoretical analysis to demonstrate why our approach is effective and validate our algorithm on the problem of ship classification in the SAR domain by comparing against several other learning competing approaches.

CNN-based methods have dominated the field of aerial scene classification for the past few years. While achieving remarkable success, CNN-based methods suffer from excessive parameters and notoriously rely on large amounts of training data. In this work, we introduce few-shot learning to the aerial scene classification problem. Few-shot learning aims to learn a model on base-set that can quickly adapt to unseen categories in novel-set, using only a few labeled samples. To this end, we proposed a meta-learning method for few-shot classification of aerial scene images. First, we train a feature extractor on all base categories to learn a representation of inputs. Then in the meta-training stage, the classifier is optimized in the metric space by cosine distance with a learnable scale parameter. At last, in the meta-testing stage, the query sample in the unseen category is predicted by the adapted classifier given a few support samples. We conduct extensive experiments on two challenging datasets: NWPU-RESISC45 and RSD46-WHU. The experimental results show that our method yields state-of-the-art performance. Furthermore, several ablation experiments are conducted to investigate the effects of dataset scale, the impact of different metrics and the number of support shots; the experiment results confirm that our model is specifically effective in few-shot settings.

Few-shot classification is challenging since the goal is to classify unlabeled samples with very few labeled samples provided. It has been shown that cross attention helps generate more discriminative features for few-shot learning. This paper extends the idea and proposes two cross attention modules, namely the cross scaled attention (CSA) and the cross aligned attention (CAA). Specifically, CSA scales different feature maps to make them better matched, and CAA adopts the principal component analysis to further align features from different images. Experiments showed that both CSA and CAA achieve consistent improvements over state-of-the-art methods on four widely used few-shot classification benchmark datasets, miniImageNet, tieredImageNet, CIFAR-FS, and CUB-200-2011, while CSA is slightly faster and CAA achieves higher accuracies.

With the increasing utilization of intelligent mobile devices for online inspection of electrical equipment in smart grids, the limited computing power and storage capacity of these devices pose challenges for deploying large algorithm models and it’s hard to obtain a substantial number of images of electrical equipment in public. In this paper, we propose a novel distillation method that compresses the knowledge of teacher networks into a compact few-shot classification network, employing a global and local knowledge distillation strategy. Central to our method is exploiting the global and local relationship between the features exacted by the backbone of the teacher network and student network. We compare our method with recent state-of-the-art (SOTA) methods on three public datasets and achieve superior performance. Additionally, we contribute a new dataset, namely EEI-100, which is specifically designed for classification of electrical equipment. We validate our method on this dataset and demonstrate its exceptional prediction accuracy of 94.12% when utilizing only 5-shot images.

Generalized zero-shot learning (GZSL) aims to simultaneously recognize both seen classes and unseen classes by training only on seen class samples and auxiliary semantic descriptions. Recent state-of-the-art methods infer unseen classes based on semantic information or synthesize unseen classes using generative models based on semantic information, all of which rely on the correct alignment of visual-semantic features. However, they often overlook the inconsistency between original visual features and semantic attributes. Additionally, due to the existence of cross-modal dataset biases, the visual features extracted and synthesized by the model may also mismatch with some semantic features, which could hinder the model from properly aligning visual-semantic features. To address this issue, this paper proposes a GZSL framework that enhances the consistency of visual-semantic features using self-distillation and disentanglement network (SDDN). The aim is to utilize self-distillation and disentanglement network to obtain semantically consistent refined visual features and non-redundant semantic features to enhance the consistency of visual-semantic features. Firstly, SDDN utilizes self-distillation technology to refine the extracted and synthesized visual features of the model. Subsequently, the visual-semantic features are then disentangled and aligned using a disentanglement network to enhance the consistency of the visual-semantic features. Finally, the consistent visual-semantic features are fused to jointly train a GZSL classifier. Extensive experiments demonstrate that the proposed method achieves more competitive results on four challenging benchmark datasets (AWA2, CUB, FLO, and SUN).

As a member of smart materials, electrorheological elastomers (EREs) formed by pre-treating active electrorheological particles are attracting more and more attention. In this work, four Mg-doped strontium titanate particles with spherical, dendritic, flake-like and pinecone-like morphorlogies were obtained by hydrothermal and low-temperature co-precipitation. XRD, SEM, Raman and FT-IR were used to characterize the obtained products. The results showed that the sizes of Mg-doped strontium titanates are about 1.5‒2.0 μm, and the phase structure are dominated by cubic crystal. These Mg-doped strontium titanates were dispersed in a hydrogel composite elastic medium. Then, Mg-doped strontium titanate/glycerol/gelatin electrorheological composite hydrophilic elastomers were obtained with or without electric field. The electric field response properties of Mg-doped strontium titanate composite elastomers were investigated. It concluded that dendritic Mg-doped strontium titanate composite elastomers is high-performance EREs. And the maximum value of energy storage modulus of Mg-doped strontium titanate composite elastomers has achieved 8.70 MPa. This high electrorheological performance of the products is helpful for their applications in vibration control, force transducers, smart structures, dampers, and other fields.

Accurate crop diseases classification is crucial for ensuring food security and enhancing agricultural productivity. However, existing crop disease classification algorithms primarily focus on a single image modality and typically require a large number of samples. Our research counters these issues by using pre-trained Vision-Language Models (VLMs), which enhances multimodal synergy for better crop disease classification than traditional unimodal approaches. Firstly, we apply the multimodal model Qwen-VL to generate meticulous textual descriptions for representative disease images selected through clustering from the training set, which will serve as prompt text for generating classifier weights. Compared to using solely the language model for prompt text generation, this approach better captures and conveys fine-grained and image-specific information, thereby enhancing prompt quality. Secondly, we integrate the cross-attention and the SE (Squeeze-and-Excitation) attention into the training-free mode VLCD (Vision-Language model for Crop Diseases classification) and the training-required mode VLCD-T (VLCD-Training) respectively for prompt text processing, enhancing classifier weights by emphasizing key text features. Experimental outcomes conclusively prove our method’s heightened classification effectiveness in few-shot crop disease scenarios, tackling data limitations and intricate disease recognition issues. It offers a pragmatic tool for agricultural pathology and reinforces the smart farming surveillance infrastructure.

Few-shot fine-grained image classification (FSFGIC) methods refer to machine learning methods which aim to classify images (e.g., bird species, flowers, and airplanes) belonging to subordinate object categories of the same entry-level category with only a few samples. It is worth to note that feature representation learning is used not only to represent training samples, but also to construct classifiers for performing various FSFGIC tasks. In this paper, starting from the definition of FSFGIC, a taxonomy of feature representation learning for FSFGIC is proposed. According to this taxonomy, we discuss key issues on FSFGIC (including data augmentation, local or/and global deep feature representation learning, class representation learning, and task specific feature representation learning). The existing popular datasets and evaluation standards are introduced. Furthermore, a novel classification performance evaluation mechanism is designed with a 0.95 confidence interval for judging whether the classification accuracy obtained by a certain specified method is good or bad. Moreover, current challenges and future trends of feature representation learning on FSFGIC are elaborated.

Leveraging the open-world understanding capacity of large-scale visual-language pre-trained models has become a hot-spot in point cloud classification. Recent approaches rely on transferable visual-language pre-trained models, classifying point clouds by projecting them into 2D images and evaluating consistency with textual prompts. These methods benefit from the robust open-world understanding capabilities of visual-language pre-trained models and require no additional training. However, they face several challenges summarized as prompt ambiguity, image domain gap, view weights confusion, and feature deviation. In response to these challenges, we propose PointBLIP, a zero-training point cloud classification network based on the recently introduced BLIP-2 visual-language model. PointBLIP is adept at processing similarities between multi-images and multi-prompts. We separately introduce a novel method for point cloud zero-shot and few-shot classification, which involves comparing multiple features to achieve effective classification. Simultaneously, we enhance the input data quality for both the image and text sides of PointBLIP. In point cloud zero-shot classification tasks, we outperform state-of-the-art methods on three benchmark datasets. For few-shot classification tasks, to the best of our knowledge, we present the first zero-training few-shot point cloud method, surpassing previous works under the same conditions and showcasing comparable performance to full-training methods.

The central goal of few-shot scene classification is to learn a model that can generalize well to a novel scene category (UNSEEN) from only one or a few labeled examples. Recent works in the remote sensing (RS) community tackle this challenge by developing algorithms in a meta-learning manner. However, most prior approaches have either focused on rapidly optimizing a meta-learner or aimed at finding good similarity metrics while overlooking the embedding power. Here we propose a novel Task-Adaptive Embedding Learning (TAEL) framework that complements the existing methods by giving full play to feature embedding’s dual roles in few-shot scene classification - representing images and constructing classifiers in the embedding space. First, we design a lightweight network that enriches the diversity and expressive capacity of embeddings by dynamically fusing information from multiple kernels. Second, we present a task-adaptive strategy that helps to generate more discriminative representations by transforming the universal embeddings into task-specific embeddings via a self-attention mechanism. We evaluate our model in the standard few-shot learning setting on two challenging datasets: NWPU-RESISC4 and RSD46-WHU. Experimental results demonstrate that, on all tasks, our method achieves state-of-the-art performance by a significant margin.

Ransomware attacks have rapidly proliferated, inflicting severe financial damages on businesses and individuals. Machine learning approaches to automate ransomware detection have shown promise but grapple with challenges like limited training data. This study introduces a novel deep learning model for few-shot ransomware classification. The model employs entropy features derived directly from malware binaries coupled with a twin neural network architecture utilizing transfer learning. Tests on over 1000 samples across 11 families demonstrate a weighted F1-score of 85.8\%, surpassing existing methods. The approach mitigates biases in limited training data and preserves intricacies lost in image-based features. It exhibits precise classification capabilities even with sparse samples of new ransomware variants. The research highlights the potential of entropy-driven deep learning to equip defenses against emerging zero-day ransomware strains.

The global agricultural sector is increasingly pressured to adopt sustainable practices and reduce its environmental impact. In this context, greenhouses play a crucial role in enabling year-round crop production, ensuring food security, and minimizing reliance on traditional open-field farming. However, the energy consumption associated with greenhouse operations poses a significant challenge to achieving sustainability goals. As a result, there is a growing emphasis on transitioning greenhouses towards near-zero energy consumption. Near-zero energy consumption in greenhouses refers to the ambitious objective of minimizing energy usage to the greatest extent possible while maintaining optimal growing conditions for crops. This goal encompasses reducing energy consumption for heating, cooling, lighting, and other operational needs, as well as exploring renewable energy sources to power greenhouse operations. This review article offers a comprehensive overview of greenhouse energy consumption, with the main goal of analyzing the present situation, identifying key challenges, exploring potential opportunities, and proposing future perspectives for decreasing energy usage in greenhouse environments. As the focus on sustainable agricultural practices grows, the need to reduce energy consumption in greenhouses becomes increasingly important. The review critically examines current technological models and strategies applied in smart greenhouse applications, as well as the monitoring of microclimatic conditions inside the greenhouse, encompassing factors such as temperature, humidity, CO2 levels, soil quality, and crop cultivation. Moreover, it aims to present existing literature that investigates the advancement of greenhouses toward achieving significant reductions in energy consumption.

Few-shot object detection (FSOD) aims to address the challenge of requiring a substantial amount of annotations for training in conventional object detection, which is very labor-intensive. However, existing few-shot methods achieve high precision with the sacrifice of time-consuming for exhaustive fine-tuning, or take poor performance in novel-class adaptation. We presume the major reason is that the valuable correlation feature among different categories is insufficiently exploited, hindering the generalization of knowledge from base to novel categories for object detection. In this paper, we propose Few-Shot object detection via Correlation-RPN and Transformer Encoder-Decoder (CRTED), a novel training network to learn object-relevant features of inter-class correlation and intra-class compactness while suppressing object-agnostic features in the background with limited annotated samples. And we also introduce a 4-way tuple-contrast training strategy to positively activate the training progress of our object detector. Experiments over two few-shot benchmarks (Pascal VOC, MS-COCO) demonstrate that, our proposed CRTED without further fine-tuning can achieve comparable performance with current state-of-the-art fine-tuned works. The codes and pre-trained models will be released.

This paper presents the results of an experimental study of the patterns of steel and lead shot transformation under the impact of environmental factors (two types of shot exposed alone and in combination with each other). The analyzed environmental factors include atmospheric precipitation of various acidity and soil solutions with a higher content of organic acids. This research demonstrated that steel shot is characterized by a high transformation rate that is an order of magnitude higher on average than the transformation rate of lead under the same conditions. The prevalence of the suspended iron form (excluding the interaction with organic acids) presents risks for such environmental components as soils and sediments and may be hazardous to the ambient air and natural waters in case of wind erosion and surface runoff from the catchment area. Furthermore, the joint presence of steel and lead shot mutually accelerates the corrosion of both metals, thus increasing the environmental risks.

The modern supply chain (SC) is growing in terms of data, devices, users, and stakeholders, which introduced new security challenges and threats, especially with the reliance on centralized servers or cloud platforms. In addition, increased trust among system participants exposes the SC to a higher risk of vulnerabilities which require strong security measures. This article proposes a hybrid security framework for SC systems, BC-DRLzSC, that integrates Blockchain (BC) and Deep Reinforcement Learning (DRL) designed to operate in a zero trust (ZT) environment. In particular, we propose a decentralized BC-based approach integrated with smart contracts to manage system participant registration and authentication and to control access to system resources. BC-DRLzSC adopts a ZT architecture to reinforce SC security, which can be achieved with an advocate to verify each entity’s trustworthiness before granting or retaining access to system resources. Incorporating the ZT architecture, with BC and DRL, can potentially and significantly bolster SC system security. DRL is employed to develop a proactive attack detection model that continuously monitors the incoming traffic from authenticated nodes within the network and predicts any malicious actions. Finally, we evaluate the performance of our proposed DRL solution using the NSL-KDD dataset.

We generate numerically on a lattice an ensemble of stationary metrics, with spherical symmetry, which have Einstein action S_E « ħ. This is obtained through a Metropolis algorithm with weight exp(-β²S_E²) and β » ħ^-1. The squared action in the exponential allows to circumvene the problem of the non-positivity of S_E. The discretized metrics obtained exhibit a spontaneous polarization in regions of positive and negative scalar curvature. We compare this ensemble with a class of continuous metrics previously found, which satisfy the condition S_E=0 exactly, or in certain cases even the stronger condition R(x)=0 for any x. All these gravitational field configurations are of considerable interest in quantum gravity, because they represent possible vacuum fluctuations and are markedly different from Wheeler's ''spacetime foam''.

The decarbonization of the built environment, both in new construction and renovation, is crucial to mitigate its relevant impact on climate change and achieve the Paris agreement goals. This study presents a systematic LCA-based methodology to assess the whole life carbon emissions of buildings, applied to a proposal for the regeneration of one of Milan’s disused railway yards. As an entry for the 2020 Reinventing Cities competition, Scalo Lambrate is a project for a mainly residential neighborhood with a public park. Strategies to reduce carbon emissions deriving both from the operational energy and construction and maintenance were evaluated and their effects compared to a reference scenario over a time horizon of 100 years. The results show that, while the opportunities to reduce carbon emissions during the use phase are somehow limited due to the already stringent performance requirements for new builds, the use of fast-growing biogenic materials for construction materials, even if mixed with more traditional ones, can provide a significant reduction of the global warming potential over the whole life cycle, with a reduction of 70% over the baseline. The remaining emissions can be offset with afforestation initiatives that, however, must be assessed against land use issues.

Multimodal remote sensing data classification can enhance the model’s ability to distinguish land features through multimodal data fusion. In this context, how to help models understand the relationship between multimodal data and target tasks is the focus of researchers. Inspired by human feedback learning mechanisms, causal reasoning mechanisms, and knowledge induction mechanisms, this paper integrates causal learning, reinforcement learning, and meta learning into a unified remote sensing data classification framework and proposed the causal meta-reinforcement learning (CMRL). First, based on feedback learning mechanisms, we have overcome the limitations of traditional implicit optimization of fusion features and customized a reinforcement learning environment for multimodal remote sensing data classification tasks. Through feedback interactive learning between agents and the environment, we help them understand the complex relationships between multimodal data and labels, thereby achieving full mining of multimodal complementary information. Second, based on the causal inference mechanism we designed causal distribution prediction action, classification reward, and causal intervention reward, capturing pure causal factors in multimodal data and cutting off false statistical associations between non-causal factors and class labels. Finally, based on the knowledge induction mechanism, we designed a bi-layer optimization mechanism based on meta-learning. By constructing a meta training task and meta validation task simulation model in the generalization scenario of unseen data, we helped the model induce cross-task shared knowledge, thereby improving its generalization ability for unseen multimodal data. The experimental results on multiple sets of multimodal datasets show that the proposed method achieved state-of-the-art performance in multimodal remote sensing data classification tasks.

Highly-doped graphene samples show the conductance reduced and the shot-noise power enhanced compared to standard ballistic systems in two-dimensional electron gas. These features can be understood within a model assuming incoherent scattering of Dirac electrons between two interfaces separating the sample and the leads. Here we find, by adopting the above-mentioned model for the edge-free (Corbino) geometry and by means of the computer simulation of quantum transport, that another graphene-specific feature should be observable when the current flow through a doped disk is blocked by high magnetic field. In case the conductance drops to zero, the Fano factor approaches the value of $F\approx{}0.56$, with a very weak dependence on the disk radii ratio. The role of finite source-drain voltages and the system behavior upon tuning the electrostatic potential barrier from a rectangular to parabolic shape are also discussed.

Over the years, the need for autonomous systems such as drones, also known as unmanned aerial vehicles (UAVs), has significantly increased in popularity across several industries, including the military. The Internet of Battlefield Things (IoBT) represents a modern technological advancement that significantly enhances the operational efficacy of defense systems. It establishes an integrated military force by connecting individuals to intelligent technology in drones, radios, equipment, antennas and ground stations. This is achieved through the utilization of cloud and edge computing, sensors, mobile devices, embedded systems, and IoT-based systems. However, IoBT security is significantly compromised by enemies that exploit the vulnerabilities and malicious intrusions that specifically target the external environment or to obtain sensitive data. In addition, a comprehensive understanding of cyberattacks and countermeasures is essential for assuring the security of IoBT. On the other hand, as cyber threats get more complicated, trust becomes increasingly important for the security of digital systems. Within this context, the zero trust architecture contends that the security of a complex network is inherently vulnerable to internal and external threats. In defense, UAV security system applications, for example, the primary purpose of the zero trust architecture is to limit the vulnerability of military UAV systems to cyberattacks, hence reducing the possibility of data breaches and illegal entry. This study conducts a systematic review aimed at identifying different aspects of cybersecurity strategies for protecting UAV systems within the IoBT domain. Furthermore, zero trust architecture is presented in the study as an effective prospective solution to the security issues that develop in defense UAV systems.

Motion related human activity recognition using wearable sensors can potentially enable various useful daily applications. So far, most studies view it as a stand-alone mathematical classification problem without considering the physical nature of human motions. Consequently, they suffer from data dependencies and encounter the dimension disaster problem and the over-fitting issue, and their models are never human-readable. In this study, we start from a deep analysis on natural physical properties of human motions, and then propose a useful feature selection method to quantify each feature's classification contribution capability. On one hand, the "dimension disaster" problem can be avoid to some extent, due to the affined dimension of key features; On the other hand, over-fitting issue can be depressed since the knowledge implied in human motions are nearly invariant, which compensates the possible data inadequacy. The experiment results indicate that the proposed method performs superior to those adopted in related works, such as decision tree, k-NN, SVM, neural networks.

This work is driven by a practical question, corrections of Artificial Intelligence (AI) errors. Systematic re-training of a large AI system is hardly possible. To solve this problem, special external devices, correctors, are developed. They should provide quick and non-iterative system fix without modification of a legacy AI system. A common universal part of the AI corrector is a classifier that should separate undesired and erroneous behavior from normal operation. Training of such classifiers is a grand challenge at the heart of the one- and few-shot learning methods. Effectiveness of one- and few-short methods is based on either significant dimensionality reductions or the blessing of dimensionality effects. Stochastic separability is a blessing of dimensionality phenomenon that allows one-and few-shot error correction: in high-dimensional datasets under broad assumptions each point can be separated from the rest of the set by simple and robust linear discriminant. The hierarchical structure of data universe is introduced where each data cluster has a granular internal structure, etc. New stochastic separation theorems for the data distributions with fine-grained structure are formulated and proved. Separation theorems in infinite-dimensional limits are proven under assumptions of compact embedding of patterns into data space. New multi-correctors of AI systems are presented and illustrated with examples of predicting errors and learning new classes of objects by a deep convolutional neural network.

Convolutional Neural Networks (CNNs) present drawbacks for modeling geometric transformations, such as scaling and rotation, caused by the convolution operation’s locality. Deformable convolution (DCON), a mechanism that substitutes standard convolution, increasing the receptive field to capture relevant features, is a promising approach to solve this drawback and improve the robustness of CNNs. However, the optimal way to replace the standard convolution with its deformable counterpart in a CNN model is unclear. In this study, we clarify this aseveration by conducting several experiments using deformable convolutions applied in the layers that conform a small four-layer CNN model. We also use deformable convolutions on the four-layers of several ResNet CNNs with depths 18, 34, 50, and 101. The models were tested in binary balanced classes with 2D data for image classification: Cats & Dogs, EyesPACS, Spyders & Chickens, and Shapes. After this testing, we evaluated DCON in 3D data for action recognition: UCF101 and Human2 (a dataset we compiled to control movement, clothing and background). The contribution of this research lies in a guideline to use DCON. It can be summarized as follows: if DCON is used on the first layers of the proposal of model (with simple features), the computational resources expressed as the quantity of Flops will tend to increase and produce bigger misclassification than the standard CNN. However, if the DCON is used at the end layers, the quantity of Flops used in the training and testing will decrease, and the classification accuracy will improve by up to 20% about the base model. Moreover, it gains robustness when using deformable convolutions because it can adapt to the region of interest. Also, the best kernel size of the DCON is three. It showed better results than size five. In the last case, the quantity of Flops increase quadratically, but their performance does not increase significantly. With these results, we propose a guideline to use the DCON and contribute to understanding the impact of DCON on the robustness of CNNs.

Cloud-induced atmospheric extinction and occlusion have a major effect on the effectiveness and quality of telescope observations. Real-time cloud cover distribution and long-term statistical data are essential for astronomical siting and telescope operations. At ground-based astronomical telescope sites, cloud cover distribution is currently analyzed using manual observation methods. However, the main disadvantages of manual observation methods are human subjective, heavy workloads and poor real-time performance. Therefore, a real-time automatic cloud images classification method is desperately needed. This paper presents a new cloud identification method, which is named PSO+XGBoost model by combining eXtreme Gradient Boosting (XGBoost) and Particle Swarm Optimization (PSO). The entire cloud image is divided into 37 sub-regions in order to more precisely identify the distribution of the clouds. 19 features are then extracted, including the sky background, star density, lighting conditions, and subregion grayscale values. The experimental results have shown that the overall classification accuracy of 96.91% and our model is able to outperform several state-of-the-art baseline methods. Our approach achieves high accuracy in comparison with the manual observation methods. Moreover, this method meets telescope real-time scheduling requirements.

This paper highlights the importance of one-shot learning from prototype SKU images for efficient product recognition in retail and inventory management. Traditional methods require large supervised datasets to train deep neural networks, which can be costly and impractical. One-shot learning techniques mitigate this issue by enabling classification from a single prototype image per product class, thus reducing data annotation efforts. We introduce the variational prototyping-encoder (VPE), a novel deep neural network for one-shot classification. Utilizing a support set of prototype SKU images, VPE learns to classify query images by capturing image similarity and prototypical concepts. Unlike metric learning-based approaches, VPE pre-learns image translation from real-world object images to prototype images as a meta-task, facilitating efficient one-shot classification with minimal supervision. Our research demonstrates that VPE can significantly reduce the need for large datasets while accurately classifying query images into their respective categories, providing a practical solution for product classification tasks.

Many types of banana (Musa spp.)—one of the most economically important horticultural crops—exist, and their ploidy (diploid, triploid, and tetraploid, usually) and genome types (containing A or/and B genome in most cases) differ. At present, observation and genome type detection are commonly used to identify banana germplasm resources. However, the former is tedious, while the latter cannot distinguish categories below genome types. It is therefore urgent that a simple and effective method for identifying banana germplasm resources is established. We sequenced and analyzed the ribosomal DNA internal transcribed spacer (ITS) sequences of 62 banana germplasm and found that the sequencing peaks, especially the 20 bp region near the 420 bp position (referred to as the “420 bp region”), exhibited relatively recognizable and repeatable polymorphism characteristics. Using the “420 bp region” as a marker, we were able to quickly distinguish bananas belonging to different genome type groups (comprising the AA, AB, AAA, ABB, AAB, ABBB, AAAB, and AAAA groups) or different subgroups in the same genome type group (for example, the Cavendish, Gros Michel, Red, Lakatan, and Ibota Bota subgroups in the AAA group; and the Pisang Raja, Plantain, Pome and Silk subgroups in the AAB group). Moreover, it appeared that Sanger sequencing of ITS could be used for identifying banana hybrid offspring. These results demonstrated that the banana ITS region contains rich genetic information that is useful for genotyping. In general, ITS sequencing simplifies the classification of banana germplasm resources and has potential application in several areas of Musa improvement.

With the development of deep learning, several Graph Neural Networks (GNN)-based approaches have been utilized for text classification. However, GNNs encounter challenges in capturing contextual text information within a document sequence. To address this, a novel text classification model RB-GAT is proposed by combining RoBERTa-BiGRU embedding and a multi-head Graph ATtention Network (GAT). First, the pre-trained RoBERTa model is exploited to learn word and text embeddings in different contexts. Second, the Bidirectional Gated Recurrent Unit (BiGRU) is employed to capture long-term dependencies and bidirectional sentence information from the text context. Next, the multi-head graph attention network is applied to analyze this information, which serves as a node feature for the document. Finally, the classification results are generated through a Softmax layer. Experimental results on three benchmark datasets demonstrate that our method can achieve an accuracy of 71.48%, 98.45%, and 80.32% on Ohsumed, R8, and MR, which is superior to the existing nine text classification approaches.

This paper is motivated by spatio-temporal pattern in the occurrence of Leishmaniasis in Afghanistan and the relatively high number of zero counts. We hold the view that correlations that arise from spatial and temporal sources are inherently distinct. Our method decouples these two sources of correlations, there are at least two advantages in taking this approach. First, it circumvents the need to inverting a large correlation matrix, which is a commonly encountered problem in spatio-temporal analyses. Second, it simplifies the modelling of complex relationships such as anisotropy, which would have been extremely difficult or impossible if spatio-temporal correlations were simultaneously considered. We identify three challenges in the modelling of a spatio-temporal process: (1) accommodation of covariances that arise from spatial and temporal sources; (2) choosing the correct covariance structure and (3) extending to situations where a covariance is not the natural measure of association. Moreover, because the data covers a period that overlaps with the US invasion of Afghanistan, the high number of zero counts may be the result of no disease incidence or lapse of data collection. To resolve this issue, a model truncated at zero built on a foundation of the generalized estimating equations was proposed.

In this paper, we propose an imagined speech-based brain wave pattern recognition using deep learning. Multiple features were extracted concurrently from eight-channel Electroencephalography (EEG) signals. To obtain classifiable EEG data with fewer number of sensors, we placed the EEG sensors on carefully selected spots on the scalp. To decrease the dimensions and complexity of the EEG dataset and to avoid overfitting during the deep learning algorithm, we utilized the wavelet scattering transformation. A low-cost 8-channel EEG headset was used with MATLAB 2023a to acquire the EEG data. The Long-Short Term Memory Recurrent Neural Network (LSTM-RNN) was used to decode the identified EEG signals into four audio commands: Up, Down, Left, and Right. Wavelet scattering transformation was applied to extract the most stable features by passing the EEG dataset through a series of filtration processes. Filtration has been implemented for each individual command in the EEG datasets. The proposed imagined speech-based brain wave pattern recognition approach achieved a 92.50% overall classification accuracy. This accuracy is promising for designing a trustworthy imagined speech-based Brain-Computer Interface (BCI) future real-time systems. For better evaluation of the classification performance, other metrics were considered, and we obtained 92.74%, 92.50% and 92.62% for precision, recall, and F1-score, respectively.

The Energy Performance of Buildings Directive 2010 calls for the Nearly Zero Energy Standard for new buildings from 2021 onwards: Buildings using “almost no energy” are powered by renewable sources or energy produced by the building itself. For residential buildings, this ambitious new standard has already been reached. But for other building types this goal is still far away. The potential of these buildings to meet a Nearly Zero Energy Standard was investigated by analyzing ten case studies representing non-residential buildings with different uses. The analysis shows that the primary characteristics common to critical building types are a dense building context with a very high degree of technical installation (such as hospital, research and laboratory buildings). The large primary energy demand of these types of buildings cannot be compensated by building and property-related energy generation including off-site renewables. If the future Nearly Zero Energy Standard were to be defined with lower requirements because of this, the state related properties of Bavaria suggest that the real potential energy savings available in at least 85% of all new buildings would be insufficiently exploited. Therefore, it would be useful to instead individualize the legal energy verification process for new buildings to distinguish critical building types such as laboratories and hospitals.

While the knowledge about the development of understanding positive integers is rapidly growing, the development of understanding zero is not well-known. Here we tested several components of preschoolers’ understanding zero: whether they can use empty sets in numerical tasks, whether they can use empty sets soon after they understand the cardinality principle, whether they know what the word “zero” refers to, and whether they categorize zero as a number. The results show that preschoolers can handle empty sets in numerical tasks as soon as they understand the cardinality principle or even earlier, and some of them know that these sets are labeled as “zero.” However, they are unsure whether zero is a number. These results identify three components of knowledge about zero: operational knowledge, linguistic knowledge, and meta knowledge. To account for these results we propose that preschoolers might understand numbers as the properties of items or objects in a set. In this view, zero cannot be a number, because an empty set does not include any items, and the missing items cannot have any property, excluding also the number property. This model might explain why zero is handled correctly in numerical tasks, while it is not regarded to be a number.

Gastric cancer is the fifth most common and fourth deadliest cancer worldwide, with a bleak 5-year survival rate of about 20%. Despite significant research into its pathobiology, prognostic predictability remains insufficient due to pathologists’ heavy workloads and the potential for diagnostic errors. Consequently, there is a pressing need for automated and precise histopathological diagnostic tools. This study leverages Machine Learning and Deep Learning techniques to classify histopathological images into healthy and cancerous categories. By utilizing both handcrafted and deep features and shallow learning classifiers on the GasHisSDB dataset, we conduct a comparative analysis to identify the most effective combinations of features and classifiers for differentiating normal from abnormal histopathological images without employing fine-tuning strategies. Our methodology achieves an accuracy of 95% with the SVM classifier, underscoring the effectiveness of feature fusion strategies. Additionally, cross-magnification experiments produced promising results with accuracies close to 80% and 90% when testing the models on unseen testing images with different resolutions.

The rapid growth of smartphone financial services raises the need for secure mobile authentication. Continuous authentication is a user-friendly way to strengthen the security of smartphones by implicitly monitoring a user’s identity through sessions. Mobile continuous authentication can be viewed as an anomaly detection problem in which models discriminate between one genuine user and the rest of the imposters (anomalies). In practice, complete imposter profiles are hardly available due to the time and monetary cost, while leveraging genuine data alone yields poor generalized models due to the lack of knowledge about imposters. To address this challenge, we recast continuous mobile authentication as a few-shot anomaly detection problem, aiming to enhance the inference robustness of unseen imposters by using partial knowledge of available imposter profiles. Specifically, we propose a novel deep learning-based model, namely Local Feature Pooling based Temporal Convolution Network (LFP-TCN), which directly models raw sequential mobile data, aggregating global and local feature information. In addition, we introduce a random pattern mixing augmentation to generate class-unconstrained imposter data for the training. The augmented pool enables characterizing various imposter patterns from limited imposter data. Finally, we demonstrate practical continuous authentication using score-level fusion, which prevents long-term dependency or increased model complexity due to extended re-authentication time. Experiments on two public benchmark datasets show the effectiveness of our method and its state-of-the-art performance.

Despite the importance of few-shot learning, the lack of labeled training data in the real world, makes it extremely challenging for existing machine learning methods as this limited data set does not represent the data variance well. In this research, we suggest employing a generative approach using variational autoencoders (VAEs), which can be used specifically to optimize few-shot learning tasks by generating new samples with more intra-class variations. The purpose of our research is to increase the size of the training data set using various methods to improve the accuracy and robustness of the few-shot face recognition. Specifically, we employ the VAE generator to increase the size of the training data set, including the basic and the novel sets while utilizing transfer learning as the backend. Based on extensive experimental research, we analyze various data augmentation methods to observe how each method affects the accuracy of face recognition. We conclude that the face generation method we proposed can effectively improve the recognition accuracy rate to 96.47% using both the base and the novel sets.

Incorrect sitting posture, characterized by asymmetrical or uneven positioning of the body, often leads to spinal misalignment and muscle tone imbalance. Prolonged maintenance of such postures can adversely impact well-being and contribute to the development of spinal deformities and musculoskeletal disorders. In response, smart-sensing chairs equipped with cutting-edge sensor technologies have been introduced as a viable solution for real-time detection, classification, and monitoring of sitting postures, aiming to mitigate the risk of musculoskeletal disorders and promote overall health. This comprehensive literature review evaluates the current body of research on smart-sensing chairs, with a specific focus on the strategies used for posture detection and classification, as well as the effectiveness of different sensor technologies. A meticulous search across MDPI, IEEE, and Google Scholar databases yielded 34 pertinent studies that utilize non-invasive methods for posture monitoring. The analysis reveals that Force Sensing Resistors (FSR) are the predominant sensors utilized for posture detection, whereas Convolutional Neural Networks (CNN) and Artificial Neural Networks (ANN) are the leading machine learning models for posture classification. However, it was observed that CNNs and ANNs do not outperform traditional statistical models in terms of classification accuracy, due to constrained size and lack of diversity within training datasets. These datasets often fail to comprehensively represent the array of human body shapes and musculoskeletal configurations. Moreover, this review identifies a significant gap in the evaluation of user feedback mechanisms, essential for alerting users to their sitting posture and facilitating corrective adjustments.

In this paper, a seamless connection between sensor technology and machine learning (ML) has been presented which has wide applicability in rehabilitation and physical medicine. The intent is to identify an ML algorithm which has a better performance, easy to deploy, and has less training time and consumes less computational resources. In short, we propose an algorithm which maximizes the synergy between a sensor and ML by maximizing classification performance and easy to do implementation, which is robust in computational power and lower in resource consumption. The premise of the work is to show the important considerations for evaluating ML algorithms for Upper-limb activity recognition for Physical medicine and rehabilitation field.

Hyperspectral images (HSI) contain abundant spectral information. Efficient extraction and utilization of this information for image classification remain prominent research topics. Previously, hyperspectral classification techniques primarily relied on statistical attributes and mathematical models of spectral data. Deep learning classification techniques have recently been extensively utilized for hyperspectral data classification, yielding promising outcomes. This study proposes a deep learning approach that uses polarization feature maps for classification. Initially, the polar coordinate transformation method is employed to convert the spectral information of all pixels in the image into spectral feature maps. Subsequently, the proposed Deep Context Feature Fusion Network (DCFF-NET) is utilized to classify these feature maps. The model is validated using three open-source hyperspectral datasets: Indian Pines, Pavia University, and Salinas. The experimental results indicated that DCFF-NET achieves excellent classification performance. Experimental results on three public HSI datasets demonstrate that the proposed method accurately recognizes different objects with an overall accuracy (OA) of 86.68%, 94.73%, and 95.14% based on the pixel method, and 98.15%, 99.86%, and 99.98% based on the pixel-patch method.

The ability to detect the presence as well as classify the activities of individuals behind visually obscuring structures is of significant benefit to police, security and emergency services in many situations. This paper presents the analysis from a series of experimental results generated using a through-the-wall (TTW) Frequency Modulated Continuous Wave (FMCW) C-Band radar system named Soprano. The objective of this analysis was to classify whether an individual was carrying an item in both hands or not using micro-Doppler information from a FMCW sensor. The radar was deployed at a standoff distance, of approximately 0.5 m, outside a residential building and used to detect multiple people walking within a room. Through the application of digital filtering, it was shown that significant suppression of the primary wall reflection is possible, significantly enhancing the target signal to clutter ratio. Singular Value Decomposition (SVD) signal processing techniques were then applied to the micro-Doppler signatures from different individuals. Features from the SVD information have been used to classify whether the person was carrying an item or walking free handed. Excellent performance of the classifier was achieved in this challenging scenario with accuracies up to 94%, suggesting that future through wall radar sensors may have the ability to reliably recognize many different types of activities in TTW scenarios using these techniques.

The energy efficiency of existing buildings is a crucial factor in addressing Europe’s energy con-sumption challenges, accounting for nearly 40% of the total energy usage. The ongoing energy crisis, driven by the reliance on fossil fuels and increasing prices, has underscored the urgency of adopting sustainable and energy efficient practices especially to the existing building stock. Cyprus is par-ticularly vulnerable due to its heavy dependence on imported fuels for electricity generation and faces significant challenges in transforming its existing building stock into energy-efficient and sustainable structures. Extensive focus has been made by the government on the energy-efficient retrofit of non-residential public buildings. This study examines an existing cultural hall. The case study of the Cultural Hall represents the building stock before 2010 which is lacking thermal in-sulation, double glazing and any energy efficient element. It then offers an ideal case study to ex-plore sustainable solutions which can be easily adopted from the construction industry and from the building owners. The primary objective of this research is twofold: first, to develop a comprehensive retrofit plan to transform the cultural hall into a net-zero energy building; and second, to explore how this transformation can give value back to the local community. After running two simulation scenarios and providing two energy performance certificates, one with at the existing state and one with the intended retrofit measures, it is clear that the building can be a net zero energy consump-tion building. Some interesting results derived, present also how this building can provide value back to the community i.e. through solar carports for EV charging.

Domain generalization has led to remarkable achievements in Hyperspectral Image (HSI) classification. Inspired by contrastive language-image pre-training (CLIP), the language-aware domain generalization method has been explored to learn cross-domain-invariant representation. However, existing methods face some challenges: 1) The weak capacity to extract long-range contextual information and inter-class correlation. 2) Due to the inadequacies of the large-scale pre-training for HSI data, the spatial-spectral features of HSI and linguistic features can not be straightforwardly alignment. To address the above problems, a novel network has been proposed with a CLIP framework, which consists of an image encoder, based on an encoder-only transformer to obtain the global contextual information and inter-class correlation, a frozen text encoder, and a cross-attention mechanism, named Linguistic-Interact-with-Visual Engager (LIVE), enhances the interaction between two modalities. Extensive experiments demonstrating superior performance over state-of-the-art methods in HSI Domain Generalization with a CLIP framework.

Sentiment analysis plays a crucial role in understanding customer feedback, guiding product development, and informing business decisions. This paper introduces term sentiment entropy (TSE), a novel weighting method that leverages the distribution of sentiment labels associated with words to enhance text classification accuracy. TSE complements traditional TF-IDF techniques by capturing the nuances of sentiment variation across different contexts. Experiments across diverse public datasets demonstrate TSE's potential to improve sentiment analysis performance, especially in capturing subtle sentiment shifts and adapting to specific domains. While computational cost and label quality pose challenges, TSE offers a promising avenue for refining sentiment analysis and opening new research frontiers.

Highly diverse agroecosystems are increasingly of interest as the realization of farms' invaluable ecosystem services grows. Simultaneously there has been an increased use of uncrewed aerial systems (UAS) in remote sensing as drones offer a finer spatial resolution and faster revisit rate than traditional satellites. With the combined utility of UAS and the attention on agroecosystems, there exists an opportunity to assess UAS practicality in highly biodiverse settings.  In this study, we utilized UAS to collect fine-resolution 10-band multispectral imagery of coffee agroecosystems in Puerto Rico. We created land cover maps through a pixel-based supervised classification of each farm and assembled accuracy assessments for each classification. To bolster our understanding of the classifications, we interviewed farmers to understand their thoughts on how these maps may be best used to support their land management. The average overall accuracy (53.9%), though relatively low, was expected for such a diverse landscape with fine-resolution data. After sharing imagery and land cover classifications with farmers, we found that while the prints were often a point of pride or curiosity for farmers, integrating the maps into farm management was perceived as impractical. These findings highlight that while remote sensing of diverse agroecosystems may provide a detailed way of estimating land cover classes and ecosystem services for researchers and government agencies for example these maps may be of limited use to land managers without additional interpretation.

Abstract This study delved into the application of various machine learning (ML) models for the classification of lung cancer levels. Through meticulous monitoring of parameters such as minimum child weight and learning rate, efforts were made to mitigate overfitting while optimizing model performance. The Deep Neural Network (DNN) emerged as a standout performer, showcasing robust performance across training, validation, and testing stages. Ensemble methods like voting and bagging also demonstrated promising results. However, Support Vector Machine (SVM) models with the Sigmoid kernel faced challenges in achieving satisfactory performance. Overall, the investigation sheds light on the efficacy of different ML models in lung cancer level classification and underscores the importance of parameter tuning to address overfitting concerns.

In order to achieve the elimination of the negative impacts of transport on road safety, the European Union is taking various measures resulting from its commitment to improve road safety. One of the instruments for achieving the objectives set is social legislation for the work of drivers in road freight and passenger transport. In line with the objective of improving the quality of working conditions for road transport drivers and road safety, the European Union applies Regulation (EC) No 561/2006 on the harmonisation of certain social legislation relating to road transport, which lays down rules on driving times, breaks and rest periods for drivers operating in road freight and passenger transport. The main objective of the paper is to assess the impact of social legislation on road transport safety by means of real research and to identify the factors influencing the violation of the legislation depending on the type of transports carried out in domestic or international road freight transport.

Detection of subsurface archaeological remains using a range of remote sensing methods, poses several challenges until today. Recent studies regarding the detection of archaeological proxies like those of cropmarks highlight the complexity of the phenomenon. In this work we present three different methods, and associated indices, for identifying stressed reflectance signatures indicating buried archaeological remains, based on a dataset of measured ground spectroradiometric reflectance. Several spectral profiles between the visible and near infrared part of the spectrum, were taken over a controlled environment in Cyprus during the 2011-2012 and are re-used in this study. The first two (spectral) methods are based on a suitable analysis of the spectral signatures in (1) the visible part of the spectrum, and in particular in the neighborhood of 570 nm, and (2) the red edge-near infrared part of the spectrum, in the neighborhood of 730 nm. Machine learning (decision trees) allows for the deduction of suitable wavelengths to focus on, in order to formulate the proposed indices and the associated classification criteria (decision boundaries) that can enhance the detection probability of stressed vegetation. Noise in the signal is taken into account by simulating reflectance signatures perturbed by white noise. Applying decision tree classification on the ensemble of simulations and basic statistical analysis we refine the formulation of the indices and criteria for the noisy signatures. The success rate of the proposed methods is over 90%. The third method rests on the estimation of vegetation/canopy reflectance parameters through inversion of the physical-based PROSAIL reflectance model and the associated classification through machine learning methods. The obtained results provide further insights into the formation of stress vegetation that occurred due to the presence of shallow buried archaeological remains, which are well aligned with physical-based models and existing empirical knowledge. To the best of the authors' knowledge, this is the first study demonstrating the usefulness of radiative transfer models such as PROSAIL for understanding the formation of cropmarks. Similar studies can support future research directions towards the development of regional remote sensing methods and algorithms if systematic observations are adequately dispersed in space and time.

Timely and accurate information on tree species is crucial for the sustainable management of natural resources, forest inventory, biodiversity detection, and carbon stock calculation. The advancement of remote sensing technology and artificial intelligence has facilitated the acquisition and analysis of remote sensing data, resulting in more precise and effective classification of tree species. Multimodal remote sensing data and deep learning seem to be the current tree species classification research mainstream, whether or not. The current review on the remote sensing data and deep learning tree species classification methods perspectives to analyze the unimodal and multimodal remote sensing data and classification methods in this realm is missing. To bridge the gap, we search for major trends in the remote sensing data and tree species classification methods, provide a detailed overview of classic deep learning-based methods for tree species classification, and discuss the limitations.

The application of artificial intelligence to point-of-care testing (POCT) disease detection has become a hot research field, in which breath detection which detects the patient's exhaled VOCs combined with sensor arrays of Convolutional Neural Network (CNN) algorithms as a new lung cancer detection is attracting more researchers' attention. However, due to low accuracy, high complexity computation and large number of parameters make the CNN algorithms difficult transplant to the embedded system of POCT devices. A lightweight neural network (LTNet) in this work is proposed to deal with this problem, and meanwhile, achieve high-precision classification of acetone and ethanol gases, which are respiratory markers for lung cancer patients. Compared to currently popular lightweight CNN models such as EfficientNet, LTNet has fewer parameters (32K) and its training weight size is only 0.155 MB. LTNet achieved an overall classification accuracy of 99.06% and 99.14% in the own mixed gas dataset and the University of California (UCI) dataset, which are both higher than that of the five existing models’, and it also offers the shortest training (844.38s and 584.67s) and inference time (23s and 14s) in the same validation set. Compared to the existing CNN models, LTNet is more suitable for resource-limited POCT devices.

Cardiopulmonary resuscitation (CPR) is a widely practiced lifesaving skill. Conventional CPR is based on manual chest compressions and delivering mouth-to-mouth breaths. There has been advancement in biomedical technology over the last few decades which has led to the introduction of new techniques and devices in CPR as well. In light of these advancements, we propose SMEAR (Standard, Mechanical, ECMO Assisted, Augmented virtual and Remote) classification system to provide structured overview from traditional to novel methods and devices. The standard or Manual CPR, widely practiced by the general public during out-of-hospital cardiac arrests, combines active chest compressions with or without mouth breathing. However, to enhance CPR’s efficacy, various mechanical devices have been developed, encompassing Active Chest Compression, Passive Decompression, and those integrated with Automated External Defibrillators. Feedback sensor-equipped devices, include the Metronome, Accelerometer, Barometer, and Triaxial Field Induction. Mechanical devices, classified by their compression mechanisms, can be isolated – like the Piston-driven, Load-distributing, and Active Compression-Decompression (ACD) – or combined, as in ACD-ITV (Impedance Threshold Device), ACD-IAC (Interposed Abdominal Compression), and ACD-ITV-EECP (Enhanced External Counter Pulsation). Beyond mechanics, Extracorporeal CPR offers veno-arterial Extracorporeal Membrane Oxygenation in refractory cardiac arrest and can improve outcomes. Augmented Virtual Reality usage in training and provision of CPR is at the early stages. It has the potential of expanded usage in training public to provide high-quality CPR. A provider can be remotely guided step by step via telephone or smartphone applications, ensuring continuous support until professional assistance arrives.

Two austenitic stainless steel (ASS) plates, 304L and 316L, were cold-rolled (304R and 316R) with a 10 % reduction in thickness then subjected to laser welding. Cold-rolling caused a slight surface hardening and introduced residual tensile stress into the ASS plates. The susceptibility to stress corrosion cracking (SCC) of the welds (304RW and 316RW) was determined using the U-bend test pieces in a salt spray. To highlight the stress concentration at the weld’s fusion boundary (FB), the top weld reinforcement was not ground off before bending. Moreover, micro-shot peening (MSP) was performed to mitigate the SCC of the welds by imposing high residual compressive stress and forming a fine-grained structure. Cold-rolling increased the susceptibility of the 304R specimen to pitting corrosion (PTC) and intergranular (IG) microcracking. Moreover, PTC and SCC were found more often at the FBs of the 304RW. The corrosion pits of the peened 304RW (304RWSP) were finer but greater in amount than the un-peened one. The results also indicated that the 316L ASS welds with MSP was resistant to the incidence of PTC and SCC in a salt spray. The better reliability and longer service life of dry storage canister could be achieved by using 316L ASS for construction and application of MSP on it.

Lung cancer remains a pervasive global health challenge, necessitating precise and efficient classification methods to inform optimal treatment strategies. In this study, we investigate the potential of machine learning algorithms in developing a computer-aided diagnostic tool for early and accurate lung cancer classification, leveraging essential protein biomarkers as predictive features. Our investigation reveals the superiority of Deep Neural Networks (DNNs) in lung cancer classification, achieving an impressive accuracy of 96.91%. This highlights the transformative potential of DNNs in facilitating real-world clinical applications, offering clinicians a powerful tool for accurate diagnosis and prognosis. Additionally, we analyze the performance of Ensemble Methods, including Voting (91.75%) and Bagging (93.81%), as viable alternatives to DNNs. These ensemble techniques demonstrate robust performance, further underlining their utility in lung cancer classification tasks. Furthermore, our study underscores the critical role of hyperparameter tuning, particularly in adjusting parameters such as min child weights and learning rates, in mitigating overfitting and enhancing the generalizability of diverse machine learning models. For instance, Support Vector Machines (SVM) exhibit varying accuracies ranging from 74.23% to 95.88% across different hyperparameter configurations, emphasizing the importance of hyperparameter optimization in maximizing model performance. In summary, our comprehensive comparative analysis sheds light on the efficacy of different machine learning approaches in lung cancer classification. By leveraging advanced algorithms and optimizing model parameters, researchers and clinicians can harness the power of machine learning to advance early detection and personalized treatment strategies for lung cancer patients.

Zero-emission trucks for regional and long haul missions are an option for fossil-free freight. The viability of such powertrains and system solutions was studied conceptually in project ESCALATE for trucks with GVW of 40 tonnes and beyond through various prime mover combinations. The study covers battery and fuel cell power sources with different degrees of battery electric as well as H2 and fuel cell operation. As a design basis, two different missions with a single-charge/H2 refill were analysed. The first mission was the VECTO long haul profile repeated up to 750 km, whereas the second was a real 520 km on-road mission in Finland. Based on the simulated energy consumption on the driving cycle, on-board energy demand was estimated, and the initial single-charge operational scenarios were analysed with five different power source topologies. The traction motors of the tractor were dimensioned so that a secondary mission of GVW up to 76 tons on a shorter route can be operated. Based on the powertrain and vehicle model, various infrastructure options for charging and H2 refuelling strategy as well as various operative scenarios with indicative total cost of ownership (TCO) were analysed.

Identifying punch types as part of punch kinematic analysis is a key component for both coaches and players, providing critical insights into the variety and effectiveness of punches, which are essential for refining overall performance. Existing research indicates that punch type classification typically relies on data from either wearables or video data. Both approaches have their merits and demerits but require a significant amount of labeled data for modeling the classification algorithm. In this work, we propose a novel approach that significantly reduces the labeling effort by one-sixth by leveraging video data to enhance the training information of sensor data. This enriched training phase enables more accurate punch classification with reduced labeled data. Subsequently, the real-time punch identification and classification use only the wearable data. On a real dataset, with 15% of the labeling efforts, our approach achieved an accuracy rate of 91.41% for rear hand punch recognition and 91.91% for lead hand punch recognition, along with 92.33% and 94.56% for punch classification, respectively. Through the development of our Smart Boxer system, we aim to revolutionize punch analytics in boxing, providing comprehensive insights while enhancing the overall training and competitive experience for athletes and enriching fan engagement with the sport.

This paper focuses on optimal sensor positioning for monitoring activities of daily living and investigates different combinations of features and models on different sensor positions, i.e., the side of the waist, front of the waist, chest, thigh, head, upper arm, wrist, and ankle. Sixteen features are extracted and the feature importance is measured by using the Relief-F feature selection algorithm. Eight classification algorithms are evaluated on a dataset collected from young subjects and that collected from elderly subjects, with two different experimental settings. To deal with different sampling rates, signals with a high data rate are down-sampled and a transformation matrix is used for aligning signals to the same coordinate system. The thigh, chest, side of the waist, and front of the waist are the best four sensor positions for the first dataset (young subjects), with average accuracy values being greater than 95%. The best model obtained from the first dataset for the side of the waist is validated on the second dataset (elderly subjects). The most appropriate number of features for each sensor position is reported. The results provide a reference for building activity recognition models for different sensor positions, as well as for data acquired from different hardware platforms and subject groups.

Surface water distribution extracted from remote sensing data has been used in water resource assessment, coastal management, and environmental change studies. Traditional manual methods for extracting water bodies cannot satisfy the requirements for mass processing of remote sensing data; therefore, accurate automated extraction of such water bodies has remained a challenge. The histogram bimodal method (HBM) is a frequently used objective tool for threshold selection in image segmentation. The threshold is determined by seeking twin peaks, and the valley values between them; however, automatically calculating the threshold is difficult because complex surfaces and image noise which lead to not perfect twin peaks (single or multiple peaks). We developed an operational automated water extraction method, the modified histogram bimodal method (MHBM). The MHBM defines the threshold range of water extraction through mass static data; therefore, it does not require the identification of twin histogram peaks. It then seeks the minimum values in the threshold range to achieve automated threshold. We calibrated the MHBM for many lakes in China using Landsat 8 Operational Land Imager (OLI) images, for which the relative error (RE) and squared correlation coefficient (R2) for threshold accuracy were found to be 2.1% and 0.96, respectively. The RE and root-mean-square error (RMSE) for the area accuracy of MHBM were 0.59% and 7.4 km2. The results show that the MHBM could easily be applied to mass time-series remote sensing data to calculate water thresholds within water index images and successfully extract the spatial distribution of large water bodies automatically.

New setting is introduced to study failed zero-forcing number and failed zero-forcing neutrosophic-number. Leaf-like is a key term to have these notions. Forcing a vertex to change its color is a type of approach to force that vertex to be zero-like. Forcing a vertex which is only neighbor for zero-like vertex to be zero-like vertex but now reverse approach is on demand which is finding biggest set which doesn’t force. LetNTG : (V,E,σ,μ) be a neutrosophic graph. Then failed zero-forcing number Z(NTG) for a neutrosophic graph NTG : (V,E,σ,μ) is maximal cardinality of a set S of black vertices (whereas vertices in V (G) \ S are colored white) such that V (G) isn’t turned black after finitely many applications of “the color-change rule”: a white vertex is converted to a black vertex if it is the only white neighbor of a black vertex. Failed zero-forcing neutrosophic-number Zn(NTG) for a neutrosophic graphNTG : (V,E,σ,μ) is maximal neutrosophic cardinality of a set S of black vertices (whereas vertices in V (G) \ S are colored white) such that V (G) isn’t turned black afterfinitely many applications of “the color-change rule”: a white vertex is converted to a black vertex if it is the only white neighbor of a black vertex. Failed zero-forcing number and failed zero-forcing neutrosophic-number are about a set of vertices which are applied into the setting of neutrosophic graphs. The structure of set is studied and general results are obtained. Also, some classes of neutrosophic graphs namely path-neutrosophic graphs, cycle-neutrosophic graphs, complete-neutrosophic graphs, star-neutrosophic graphs, bipartite-neutrosophic graphs, and t-partite-neutrosophic graphs are investigated in the terms of maximal set which forms both of failed zero-forcing number and failed zero-forcing neutrosophic-number. Neutrosophic number is reused in this way. It’s applied to use the type of neutrosophic number in the way that, three values of a vertex are used and they’ve same share to construct this number to compare with other vertices. Summation of three values of vertex makes one number and applying it to a comparison. This approach facilitates identifying vertices which form failed zero-forcing number and failed zero-forcing neutrosophic-number. In path-neutrosophic graphs, the set of vertices such that every given two vertices in the set, have distance at least two, forms maximal set but with slightly differences, in cycle-neutrosophic graphs, the set of vertices such that every given two vertices in the set, have distance at least two, forms maximal set. Other classes have same approaches. In complete-neutrosophic graphs, a set of vertices excluding two vertices leads us to failed zero-forcing number and failed zero-forcing neutrosophic-number. In star-neutrosophic graphs, a set of vertices excluding only two vertices and containing center, makes maximal set. In complete-bipartite-neutrosophic graphs, a set of vertices excluding two vertices from same parts makes intended set but with slightly differences, in complete-t-partite-neutrosophic graphs, a set of vertices excluding two vertices from same parts makes intended set. In both settings, some classes of well-known neutrosophic graphs are studied. Some clarifications for each result and each definition are provided. Using basic set not to extend this set to set of all vertices has key role to have these notions in the form of failed zero-forcing number and failed zero-forcing neutrosophic-number. The cardinality of a set has eligibility to form failed zero-forcing number but the neutrosophic cardinality of a set has eligibility to call failed zero-forcing neutrosophic-number. Some results get more frameworks and perspective about these definitions. The way in that, two vertices don’t have unique connection together, opens the way to do some approaches. A vertex could affect on other vertex but there’s no usage of edges. These notions are applied into neutrosophic graphs as individuals but not family of them as drawbacks for these notions. Finding special neutrosophic graphs which are well-known, is an open way to pursue this study. Some problems are proposed to pursue this study. Basic familiarities with graph theory and neutrosophic graph theory are proposed for this article.

Myelin protein zero (P0), a type I transmembrane protein, is the most abundant protein in peripheral nervous system (PNS) myelin – the lipid-rich, periodic structure that concentrically encloses long axonal segments. Schwann cells, the myelinating glia of the PNS, express P0 throughout their development until the formation of mature myelin. In the intramyelinic compartment, the immunoglobulin-like domain of P0 bridges apposing membranes together via homophilic adhesion, forming a dense, macroscopic ultrastructure known as the intraperiod line. The C-terminal tail of P0 adheres apposing membranes together in the narrow cytoplasmic compartment of compact myelin, much like myelin basic protein (MBP). In mouse models, the absence of P0, unlike that of MBP or P2, severely disturbs the formation of myelin. Therefore, P0 is the executive molecule of PNS myelin maturation. How and when is P0 trafficked and modified to enable myelin compaction, and how disease mutations that give rise to incurable peripheral neuropathies alter the function of P0, are currently open questions. The potential mechanisms of P0 function in myelination are discussed, providing a foundation for the understanding of mature myelin development and how it derails in peripheral neuropathies.

ACL instability poses a significant challenge in traumatology and orthopedic medicine, often requiring accurate diagnosis for appropriate treatment. While the pivot-shift test offers a crucial means of assessment, its reliance on subjective interpretation underscores the need for supplementary imaging studies. This study aims to address this limitation by developing a Bayesian classification algorithm tailored for integration into a mobile application. Using the built-in inertial sensors of smartphones, this new approach aims to dynamically evaluate rotational stability during knee examinations. Orthopedic specialists conducted knee evaluations on 52 subjects, with subsequent analysis revealing interesting insights. Intraobserver and interobserver analyses, as measured by ICC, demonstrated strong agreement both in terms of timing between maneuvers (ICC = 0.94) and signal amplitude (ICC = 0.71-0.66). Notably, the Bayesian algorithm successfully classified 95% of joint hypermobility cases, with an additional 7 cases of hyperlaxity identified by the Pivot-Shift Meter (PSM). These findings highlight the practicality and effectiveness of implementing a Bayesian classification algorithm within a mobile application for assessing and categorizing signals captured by smartphone inertial sensors during the pivot-shift test.

By using a two-stage physiologically based extraction test (PBET) and (W-PBET), the authors of this paper have estimated the bioaccessibility of metals (Pb and Fe) and their compounds in the GI tract of waterfowl and mammals. It has been shown that the metals (Pb and Fe) have low bioaccessibility; combined with the short time of shot exposition at the GI tract, this eliminates the risk of toxic effects in the case of shot ingestion by waterfowl. It has also been discovered that there is a significant difference in the bioaccessibility of metals and their compounds. A model was proposed and tested to predict the toxic effects of lead on biological objects depending on the threshold mass of consumption. This model takes into account data on the bioavailability of lead and regulatory values indicating dangerous concentrations of lead.

This study describes a novel method for grading pathological sections of gliomas. Our own integrated hyperspectral imaging system was employed to characterize 270 bands of cancerous tissue samples from microarray slides of gliomas. These samples were then classified according to the guidelines developed by the World Health Organization, which define the subtypes and grades of diffuse gliomas. We explored a hyperspectral feature extraction model called SMLME-Resnet using microscopic hyperspectral images of brain gliomas of different malignancy grades. The model combines the channel attention mechanism and multi-scale image features to automatically learn the pathological organization of gliomas and obtain hierarchical feature representations, effectively removing the interference of redundant information. It also completes multi-modal, multi-scale spatial and spectral feature extraction to improve the automatic classification of glioma subtypes. The proposed classification method demonstrated high average classification accuracy (>97.3\%) and Kappa coefficient (0.954), indicating its effectiveness in improving the automatic classification of hyperspectral gliomas. The method is readily applicable in a wide range of clinical settings, offering valuable assistance in alleviating the workload of clinical pathologists. Furthermore, the study contributes to the development of more personalized and refined treatment plans, as well as subsequent follow-up and adjustment of treatment, by providing physicians with insights into the underlying pathological organization of gliomas.

This study examines the feasibility of using event-related potentials (ERPs) obtained from electroencephalographic (EEG) recordings as biomarkers for long-term memory item classification. Previous studies have identified old/new effects in memory paradigms associated with explicit long-term memory and familiarity. Recent advancements in convolutional neural networks (CNNs) have enabled the classification of ERP trials under different conditions and identification of features related to neural processes at the single-trial level. We employed this approach to compare three CNN models with distinct architectures using experimental data. Participants (N = 25) performed an association memory task while recording ERPs that were used for training and validation of the CNN models. The EEGNET-based model achieved the most reliable performance in terms of precision, recall, and specificity compared with the shallow and deep convolutional approaches. The classification accuracy of this model reached 70% for known items and 62% for unknown items. Good overall accuracy requires a trade-off between recall and specificity and depends on the architecture of the model and the dataset size. These results suggest the possibility of integrating ERP and CNN into online learning tools and identifying the underlying processes related to long-term memorization.

Object detection is a popular image processing technique, widely used in numerous applications for detecting and locating objects in images or videos. While being one of the fastest algorithms for object detection, Single-Shot Multibox Detection (SSD) networks are also computationally very demanding, which limits their usage in real-time edge applications. Even though the SSD post-processing algorithm is not the most complex segment of the overall SSD object detection network, it is still computationally demanding and can become a bottleneck with respect to processing latency and power consumption, especially in edge applications with limited resources. When using hardware accelerators to accelerate backbone CNN processing, the SSD post-processing step implemented in software can become critical for high-end applications where high frame rates are required, as this paper shows. To overcome this problem, we propose Puppis, an architecture for hardware acceleration of SSD post-processing algorithm. As experiments will show, our solution will lead to an average SSD post-processing speedup of 34.42 when compared with a software implementation. Furthermore, execution of a complete SSD network will be on average 45.39 times faster than software implementation when the proposed Puppis SSD hardware accelerator is used together with some existing CNN accelerators.

Deep learning has achieved lots of successes in many fields, but when trainable sample are extremely limited, deep learning often under or overfitting to few samples. Meta-learning was proposed to solve difficulties in few-shot learning and fast adaptive areas. Meta-learner learns to remember some common knowledge by training on large scale tasks sampled from a certain data distribution to equip generalization when facing unseen new tasks. Due to the limitation of samples, most approaches only use shallow neural network to avoid overfitting and reduce the difficulty of training process, that causes the waste of many extra information when adapting to unseen tasks. Euclidean space-based gradient descent also make meta-learner's update inaccurate. These issues cause many meta-learning model hard to extract feature from samples and update network parameters. In this paper, we propose a novel method by using multi-stage joint training approach to post the bottleneck during adapting process. To accelerate adapt procedure, we also constraint network to Stiefel manifold, thus meta-learner could perform more stable gradient descent in limited steps. Experiment on mini-ImageNet shows that our method reaches better accuracy under 5-way 1-shot and 5-way 5-shot conditions.

Zero-dose children, or children who have not received any routine vaccination, are a priority population for global health policy makers as these children are at high risk of mortality from vaccine-preventable illnesses. We conducted a narrative review to identify potential interventions, both within and outside of the health sector, to reach zero-dose children. We reviewed peer-reviewed and grey literature and identified 59 relevant resources. Additionally, we interviewed six key informants to enhance synthesis of our findings. Data were organized into three priority settings: (1) urban slums, (2) remote or rural communities, and (3) conflict settings. We found that zero-dose children in the three-priority settings face differing barriers to vaccina-tion and, therefore, require context-specific interventions, such as leveraging slum health commit-tees for urban slums or integrating with existing humanitarian response services for conflict set-tings. Three predominant themes emerged for grouping the various interventions: (1) community engagement, (2) health systems strengthening and integration, and (3) technological innovations. The barriers to reaching zero-dose children are multifaceted and nuanced to each setting, there-fore, no one intervention is enough. Technological interventions especially must be coupled with community engagement and health systems strengthening efforts. Evaluations of the suggested interventions are needed to guide scale up, as the evidence-base around these interventions is rel-atively small.

The purpose of this project was to demonstrate the potential of converting an existing internal combustion engine for hydrogen operation at relatively low cost and to optimize the combustion process for ultra-low NOx emissions. The conversion has been carried out on a 450cc naturally aspirated single cylinder engine. The first baseline measurements and setup have shown lower NOx emissions than the baseline gasoline engine (without catalytic converter) for similar power output and engine efficiency. Further optimization of the combustion process allowed to achieve Euro VI and (latest European Commission proposal) Euro VII heavy-duty NOx limits without exhaust gas aftertreatment system (EATS) in steady state conditions. The concept is very promising and the knowledge gained should allow for further optimization to achieve near zero NOx emissions at high engine efficiency and power output with supercharging. It should also allow an efficient conversion of other engine types for different applications. In particular, a project with the aim to convert a heavy duty 6 cylinder engine intended for public transport buses has started. It follows a feasibility study which has shown the competitiveness of the hydrogen engine for this application.

Aiming at solving difficulties related to aero-engine classification and identification, the infrared spectra of aero-engine hot jets are measured by telemetry Fourier transform infrared spectrometer, and a six types aero-engine hot jet spectrum data set is generated. The spectrum data set were randomly sampled at a ratio of 8:1:1 to generate training set, validation set and prediction set. In this paper, a Peak Finding Siamese Convolutional Neural Network (PF-SCNN) is designed to match and classify spectrum data. In the first place, the matching pairs of training set and validation set are made independently with the labels of positive and negative samples creating. The spectrum feature extraction and distance similarity calculation are carried out by the Siamese convolutional neural network (SCNN). When entering the prediction phase, the prediction set and training set are integrated to predict in the trained model. The prediction set labels are ultimately determined by matching them with the training set labels having the highest similarities to ensure accurate predictions. To improve the operation efficiency of the SCNN, a peak finding method is introduced to extract the spectrum peaks. Peak positions of high frequency are counted, while the peak data are extracted. The peak data are used to take the place of the original data for training and prediction. The performance measures are defined as Accuracy, Precision, Recall, Confusion matrix and F1-score, and the prediction accuracy was up to 99%. The experimental results indicate that the proposed PF-SCNN is suitable for our spectral dataset and can complete the task of infrared spectrum classification of aero-engine hot jets.

Aerial image classification has become popular and has attracted extensive research efforts in recent decades. The main challenge lies in its very high spatial resolution but relatively insufficient spectral information. To this end, spatial-spectral feature extraction is a popular strategy for classification. However, parameter determination for that feature extraction is usually time-consuming and depends excessively on experience. In this paper, an automatic spatial feature extraction approach based on image raster and segmental vector data cross-analysis is proposed for the classification of very high spatial resolution (VHSR) aerial imagery. First, multi-resolution segmentation is used to generate strongly homogeneous image objects and extract corresponding vectors. Then, to automatically explore the region of a ground target, two rules, which are derived from Tobler’s First Law of Geography (TFL) and a topological relationship of vector data, are integrated to constrain the extension of a region around a central object. Third, the shape and size of the extended region are described. A final classification map is achieved through a supervised classifier using shape, size, and spectral features. Experiments on three real aerial images of VHSR (0.1 to 0.32 m) are done to evaluate effectiveness and robustness of the proposed approach. Comparisons to state-of-the-art methods demonstrate the superiority of the proposed method in VHSR image classification.

Coded aperture 3D imaging techniques have been rapidly evolving in the recent years. The two main directions of evolution are in aperture engineering to generate the optimal optical field and in development of computational reconstruction to reconstruct the object’s image from the intensity distribution with a minimal noise. The goal is to find the ideal aperture-reconstruction method pair and if not, to optimize one to match the other for designing an imaging system with required 3D imaging characteristics. Lucy-Richardson-Rosen algorithm (LR²A), a recently developed computational reconstruction method was found to perform better than its predecessors such as matched filter, Weiner filter, phase-only filter, Lucy-Richardson algorithm and non-linear reconstruction (NLR) for certain apertures when the point spread function (PSF) is a real and symmetric function. For other cases of PSF, NLR performed better than the rest of the methods. In this tutorial, LR²A has been presented as a generalized approach for any optical field along with MATLAB codes for reconstruction of any image when the PSF is known. The common problems and pitfalls in using LR²A has been discussed. Simulation and experimental studies for common optical fields such as spherical, Bessel, vortex beams and exotic optical fields such as Airy, scattered and self-rotating beams have been presented. From this study, it can be seen that it is possible to transfer the 3D imaging characteristics from non-imaging type exotic fields to indirect imaging systems faithfully using LR²A. The application of LR²A to medical images such as colonoscopy images and cone beam computed tomography images with synthetic PSF has been demonstrated. We believe that the tutorial will provide a deeper understanding of computational reconstruction using LR²A.

This study investigated the relationship between wrist flexion and the dynamics of the swing of a croquet mallet. Twenty seven subjects participated in a study which used 3D motion capture equipment and high speed and high-definition video to determine if there is a correlation between the lateral twist of a croquet player’s swing and the flexion of the wrist during that swing. The study found a significant correlation between the amount of flexion of the wrist from the start of the stroke to the top of the backswing and the twist of the mallet head at the top of the backswing (r=0.330, p<0.01). The methodology and findings are relevant to all sports where minimising wrist flexion is favourable for improving consistency of stroke making. Additionally, reducing wrist motion in stroke-making may reduce the incidence of wrist pain and injury in croquet, further supporting recommendations to reduce the amount of wrist flexion during the croquet swing.

In Indonesia, types of meat are still identified manually due to increasing prices for beef and buf-falo ahead of Idul Fitri. Traders mix beef with pork to thwart the beef scam. Haar wavelet and GLCM, GLCM with angles of 0°, 45°, 90°, and 135°, as well as matrices using contrast, correlation, energy, homogeneity, and entropy, are used in feature extraction. The following are the results of meat image classification testing using k-NN, Haar wavelet, and GLCM: The k-NN algorithm shows superiority in identifying fresh (99%), frozen (99%), and rotten (96%) meat texture images with the most fantastic accuracy results in every situation. Meanwhile, GLCM routinely provides good results, especially regarding the texture image of fresh meat (183.21) and rotten meat (115.79). However, despite delivering less throughput than k-NN and GLCM, Haar wavelets are still helpful, especially when dealing with fresh meat texture images (89,96).

The advent of deep learning (DL) has revolutionized medical imaging, offering unprecedented avenues for accurate disease classification and diagnosis. DL models have shown remarkable promise for classifying brain tumor from Magnetic Resonance Imaging (MRI) scans. However, despite their impressive performance, the opaque nature of DL models poses challenges in understanding their decision-making processes, particularly crucial in medical contexts where interpretability is essential. This paper explores the intersection of medical image analysis and DL interpretability, aiming to elucidate the decision-making rationale of DL models in brain tumor classification. Leveraging state-of-the-art DL frameworks with transfer learning, we conduct a comprehensive evaluation encompassing both classification accuracy and interpretability. Using state-of-the-art DL frameworks with transfer learning, we conduct a thorough evaluation covering both classification accuracy and interpretability. We employ adaptive path-based techniques to understand the underlying decision-making mechanisms of these models. Grad-CAM and Grad-CAM++ highlight critical image regions where the tumors are located.

Accurately predicting drug-drug interactions (DDIs) is crucial for preventing adverse drug events in clinical settings. However, existing methodologies often rely on complex models built from diverse data sources, posing challenges in computational drug discovery. To address the need for precise computational methods in predicting unknown DDIs, this study introduces a novel Deep Neural Network (DNN)-based approach. By leveraging a wide range of drug-related information, including substructure, targets, side effects, pathways, and indications, our method calculates multiple drug similarities. These similarities are then synthesized using a nonlinear fusion method to extract high-level features. Subsequently, a tailored neural network is deployed for interaction prediction. Comparative evaluation against three prominent machine learning classifiers—Extreme Gradient Boosting (XGBoost), Adaptive Gradient Boosting (AdaBoost), and Light Gradient-Boosting Machine (LGBM)—using three benchmark datasets demonstrates the superior performance of DNN. It achieves outstanding accuracy, precision, recall, and F1-score metrics, all reaching 94.6% in cross-validation. Additionally, case studies involving numerous drug pairs confirm the reliability of DNN in accurately predicting unknown DDIs. These findings underscore DNN as a potent and reliable method for DDI prediction, with promising implications for drug discovery and healthcare applications.

Polarimetric Synthetic Aperture Radar (PolSAR) images encompass valuable information that can facilitate extensive land cover interpretation and generate diverse output products. Extracting meaningful features from PolSAR data poses challenges distinct from those encountered in optical imagery. Deep Learning (DL) methods offer effective solutions for overcoming these challenges in PolSAR feature extraction. Convolutional Neural Networks (CNNs) play a crucial role in capturing PolSAR image characteristics by leveraging kernel capabilities to consider local information and the complex-valued nature of PolSAR data. In this study, a novel three-branch fusion of complex-valued CNN named Shallow to Deep Feature Fusion Network (SDF2Net) is proposed for PolSAR image classification. To validate the performance of the proposed method, classification results are compared against multiple state-of-the-art approaches using the Airborne Synthetic Aperture Radar (AIRSAR) datasets of Flevoland, San Francisco, and ESAR Oberpfaffenhofen dataset. The results indicate that the proposed approach demonstrates improvements in OA, with 1.3% and 0.8% enhancement for the AIRSAR datasets and 0.5% improvement for the ESAR dataset. The analyses conducted on the Flevoland data underscore the effectiveness of the SDF2Net model, revealing a promising OA of 96.01% even with only 1% sampling ratio.

Target detection and segmentation in synthetic aperture radar (SAR) images are vital steps for many remote sensing applications. In the era of data-driven deep learning, this task is extremely challenging due to the limited labeled data. Few-shot Learning has the ability to learn quickly from few samples with supervised information. Inspired by this, a few-shot learning framework named MSG-FN is proposed to solve the segmentation of ship targets in heterologous SAR images with few annotated samples. The proposed MSG-FN adopts a dual-branch network consisting of a support branch and a query branch. The support branch is used to extract features with an encoder, and the query branch uses a U-shaped encoder-decoder structure to segment the target in the query image. The encoder of each branch is composed of well-designed residual blocks combined with filter response normalization to capture robust and domain-independent features. A multi-scale similarity guidance module is proposed to improve the scale adaptability of detection by applying hand-on-hand guidance of support features to query features of various scales. In addition, a SAR dataset named SARShip-4i is built to evaluate the proposed MSG-FN and the experimental results show that the proposed method achieves superior segmentation results compared with the state-of-the-arts.

Mineral prospectivity mapping (MPM), aiming to outline and prioritize mineral exploration targets, has been spurred by data-driven machine learning algorithms. Supervised data-driven MPM is a typical few-shot task, suffering from the scarcity of labeled data, over-fitting of models and uncertainty of predictions. The main objective of this contribution is to propose a robust framework of few-shot learning (FSL) combining data augmentation and transfer learning, which enables generation of prospectivity models with excellent predictive efficiency and low uncertainty. The mineral systems approach was used to transfer a conceptual mineral system into mappable exploration criteria. Synthetic minority over-sampling technique (SMOTE) was employed to augment and balance the labeled dataset, allowing for model pre-training with a large synthetic training dataset of source domain. The knowledge derived from pre-trained models was then transferred to the target domain by fine-tuning, and the prospectivity model was generated in light of over-fitting and uncertainty assessment. The proposed FSL framework was applied to tungsten prospectivity mapping in southern Jiangxi Province. The results indicate that the SMOTE-ed balanced dataset boosts the classification accuracy in the training process. The FSL models yield an arch-shaped prediction point pattern favorable for focusing potential targets with high probability and low uncertainty. The FSL models achieve a high predictive performance (test AUC=0.9172) and the lowest quantitative over-fitting value, compared to the models derived from the benchmark algorithms of random forest and support vector machine. Four levels of potential targeting zones, considering both predictive efficiency and uncertainty, are extracted from the resulting FSL prospectivity map. The final high-potential and low-risk exploration targets only cover 4.27% of the area, but capture 41.53% known tungsten deposits, achieving superior predictive performance. This study highlights the capability of FSL framework for controlling over-fitting and generating high-confidence exploration targets with low uncertainty.

Deep Learning (DL) oriented document processing is widely used in different fields for extraction, recognition, and classification processes from raw corpora of data. The article examines the application of deep learning approaches, based on different neural network methods, including Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), and Convolutional Neural Networks (CNN). The compared models were combined with two different word embedding techniques, namely: Bidirectional Encoder Representations from Transformers BERT and Gensim Word2Vec. The models are designed to evaluate the performance of architectures based on neural network techniques for the classification of CVs of Moroccan engineering students at ENSAK(National School of Applied Sciences of Kenitra, Ibn Tofail University). The used dataset included resumes collected from engineering students at ENSAK in 2023 for a project on the employability of Moroccan engineers in which new approaches were applied, especially machine learning, deep learning, and big data. Accordingly, 867 resumes were collected from five specialties of study (Electrical Engineering, Networks and Systems Telecommunications, Computer Engineering, Automotive Mechatronics Engineering, Industrial Engineering). The results revealed good performance of the proposed models based on the BERT embedding approach compared to models based on the Gensim Word2Vec embedding approach. Accordingly, the CNN-GRU/Bert model achieved slightly better accuracy with 0.9251 compared to other hybrid models.

To enable net zero sustainable thermal building energy this study develops an open-source thermal house model to couple solar photovoltaic (PV) and heat pumps (HP) for grid-connected residential housing. The calculation of both space heating and cooling thermal loads and the selection of HP is accomplished with a validated Python model for air-source heat pumps. The capacity of PV required to supply the HPs is calculated using an System Advisor Model integrated Python model. Self-sufficiency and self-consumption of PV and the energy imported/exported to the grid for a case study are provided, which shows that simulations based on the monthly load profile have a significant reduction of 43% for energy sent to/from the grid compared to the detailed hourly simulation and an increase from 30% to 60% for self-consumption and self-sufficiency. These results show the importance of more granular modeling and also indicate mismatches of PV generation and HP load based on hourly simulation datasets. The back-calculation PV sizing algorithm combined with HP and thermal loads presented in this study exhibited robust performance. The results indicate this approach can be used to accelerate the solar electrification of heating and cooling to offset the use of fossil fuels in northern climates.

Chemical process control relies on a tightly controlled, narrow range of margins for critical variables, ensuring process stability and safeguarding equipment from potential accidents. The availability of historical process data is limited to a specific setpoint of operation. This challenge raises issues for process monitoring in predicting and adjusting to deviations outside of the range of operational parameters. Therefore, this paper proposes simulation-assisted deep transfer learning for predicting and optimizing the final purity and production capacity of the glycerin purification process. The proposed network is trained by the simulation domain to generate a base feature extractor, which is then fine-tuned using few-shot learning techniques on the target learner to extend the working domain of the model beyond the historical practice. The result shows that the proposed model improved prediction performance by 99% in predicting water content and 79.72% in glycerin prediction over the conventional deep learning model. Additionally, the implementation of the proposed model identified the production and product quality improvement for enhancing the glycerin purification process.

Literature review indicates that the basic microstructure of Ti-6Al-4V is bimodal which consist of two phases: α + β, and it occurs after the fabrication in conventional methods such as casting, plastic forming or machining processes. After the additive manufacturing methods, there could be significant changes in the microstructure. Due to the rapid heat exchange during heat-treatment process, bimodal microstructure transforms into lamellar microstructure which consists of two phases α′ + β. Despite applying optimum printing parameters, 3D-printed products exhibit typical surface defects and discontinuities. Recently, two of the primary technologies for the improvement of surface layer properties of titanium alloys are shot peening and electropolishing. Literature review signalizes that shot peening and electropolishing processes have positive impact on the corrosion behaviour, mechanical properties and the condition of the surface layer of titanium alloy. Furthermore, there is a lack of studies about combining shot peening and electropolishing in one hybrid process on titanium alloys, which could synthesize the benefits of both processes. The scope of future investigation is also included in this review.

This paper investigates the effect of shot peening on the strength and corrosion properties of EN AW 6082-T651 aluminium alloy. Surface roughness, microhardness, residual stresses and corrosion performance were investigated and compared with the untreated aluminium alloy. Cracks and delaminations in the surface layer can only be seen on the treated specimens at a working pressure of 4 bar and 8 bar, while no such effect was observed at a working pressure of 1.6 bar. The effect of dislocation densification was confirmed by the microhardness measurement of the hardened layer, where microhardness increased by up to 23 % compared to the untreated aluminium alloy. Shot peening also results in a deeper layer with higher compressive residual stresses compared to untreated specimens. With higher working pressure, surface roughness increases, which can promote localized pitting corrosion. However, all treated specimens improve the corrosion resistance and have a lower degree of anodic dissolution. The current density of the shot peened specimen with the lowest surface roughness was more than twice lower than that of the untreated specimen.

Shot peening is an attractive technique for fatigue enhanced performance of metallic components, because it promotes crack initiation retardation and later crack growth. Engineering design based on fatigue crack propagation predictions applying the principles of fracture mechanics is commonly used in aluminum structures for aerospace engineering. The main purpose of present work was to analyze the effect of shot peening on the fatigue crack propagation of the 7475 aluminum alloy, under both constant amplitude loading and periodical overload blocks. The tests were performed on 4 and 8 mm thickness specimen's with stress ratios of 0.05 and 0.4. The analysis of the shot-peened surface showed a small increase of the micro-hardness values, due to the plastic deformations imposed by shot peening. The beneficial effect of surface peening on fatigue crack growth rates is quite limited to an increasing near the threshold. The specimens’ thickness has only marginal influence on the crack propagation, in opposite to the stress ratio. Periodic overload blocks of 300 cycles promotes a reduction of the fatigue crack growth rate for both intervals of 7,500 and 15,000 cycles.

Many corporations aspire to become Net Zero Carbon Dioxide by 2030-2050. This paper examines what it will take. It requires understanding where energy is produced and consumed, the magnitude of CO2 generation, and the Carbon Cycle. Reviews are provided for prior technologies for reducing CO2 emissions from fossil to focus on their limitations and to show that none offer a complete solution. Both biofuels and CO2 sequestration reduce future CO2 emissions from fossil fuels. They will not remove CO2 already in the atmosphere. Planting trees has been proposed as one solution. Trees are a temporary solution. When they die, they decompose and release their carbon as CO2 to the atmosphere. The only way to permanently remove CO2 already in the atmosphere is to break the Carbon Cycle by growing biomass from atmospheric CO2 and sequestering biomass carbon. Permanent sequestration of leaves is proposed as a solution. Leaves have a short Carbon Cycle time constant. They renew and decompose every year. Theoretically, sequestrating a fraction of the world’s tree leaves can get the world to Net Zero without disturbing the underlying forests. This would be CO2 capture in its simplest and most natural form. Permanent sequestration may be achieved by redesigning landfills to discourage decomposition. In traditional landfills, waste undergoes several stages of decomposition, including rapid initial aerobic decomposition to CO2, followed by slow anaerobic decomposition to methane and CO2. The latter can take hundreds to thousands of years. Understanding landfill chemistry provides clues to disrupting decomposition at each phase.

Coronavirus disease 2019 (COVID-19) continues to cause morbidity and mortality worldwide; therefore, effective treatments remain crucial to controlling it. As interferon-alpha (IFN-α) and -beta (β) have been proposed as COVID-19 treatments, we sought to assess their effectiveness on respiratory, cardiovascular, neurological, and psychiatric signs and symptoms, as well as PASC and death, in hospitalized COVID-19 patients without multiple sclerosis (MS). Using a federated data research network (TriNetX), we performed a retrospective cohort study of hospitalized COVID-19 patients without MS who received IFN-α or -β treatment, comparing them to a similar cohort who did not receive treatment. Following propensity score-matched analyses, we demonstrate that hospitalized COVID-19 patients who were treated with IFN-α or -β had significantly higher odds of death. In contrast, there was no significant difference in any other outcomes between 1-30 days or 1 day to anytime afterward. Overall, hospitalized COVID-19 patients without MS who were treated with IFN-α or -β had similar short- and long-term sequelae (except for mortality) as those who did not receive treatment. The potential benefits of utilizing IFN-α or -β treatment as therapeutics remain to be realized, and our research highlights the need to explore repurposing drugs for COVID-19 using real-world evidence.

Classifications of AAFD/PCFD have evolved with an increased understanding of the pathology involved. A review of classification systems helps identify deficiencies and respective contributions to the evolution in understanding the classification of AAFD. Using multiple electronic database searches (Medline, PubMed) and Google search, original papers classifying AAFD were identified. Nine original articles were identified that met the inclusion criteria. Johnson's original classification and multiple variants provided a significant leap in understanding and communicating the pathology but remained tibialis posterior tendon focussed. Drawbacks of these classifications include the implication of causality, linearity of progression through stages, an over-simplification of stage 2 deformity and a failure to understand multiple tendons react, not just tibialis posterior. Later classifications, such as the PCFD classification, are deformity-centric. Early instability in non-cavus feet and all stages of cavus feet can present pain and instability with minor/no deformity. These may not be captured in deformity-based classifications biased to planus feet.' The authors developed the 'Triple Classification' (TC) understanding that primary pathology is a progressive ligament failure/instability that presents as tendon reactivity, deformity, and painful impingement. There is a variable manifestation dependent on starting foot morphology. This review has identified deficiencies within classification systems used in AAFD/PCFD and, as a result, was used to help develop a more comprehensive 'Triple classification'. Advantages of the TC include representing foot types with no deformity, defining complex secondary instabilities, delinking of foot types, tendon reactivity/ligament instability and deformity to represent these independently in a more comprehensive classification system.

The ongoing conflict in Syria and Iraq has caused many residents of these countries to flee. This study explored how these refugees cope with traumatic experiences from pre-migration to post-migration phases and how they develop resilience experiences at the individual, familial, and community levels. Data were collected through individual interviews and analyzed using Interpretative Phenomenological Analysis. A discussion of the findings revealed (1) a cumulative effect of prolonged adversity from pre-migration to resettlement phases; (2) the impacts of post-migration context as it facilitates refugees’ adjustment or leads to re-traumatization through increased marginalization; and (3) finally, an overview of refugees’ ongoing survival. Clinical implications are presented along with policy implications and future directions for research.

This study investigates anomaly detection of IoT device traffic using Convolutional Neural Networks (CNN) and Variational Autoencoders (VAE) to enhance the detection capability of security threats in IoT environments. A series of hardware configurations, software environments, and hyperparameters were utilized to optimize the training and testing processes of the models. The CNN model demonstrates robust classification performance, achieving an accuracy rate of 95.85% on the test dataset, effectively distinguishing between different types of IoT device traffic. Meanwhile, the VAE model exhibits proficient anomaly detection capabilities by effectively capturing abnormal patterns in the data using reconstruction loss and KL divergence. The combined use of CNN and VAE models offers a comprehensive solution to cybersecurity challenges in IoT environments. Future research directions include exploring diverse IoT traffic data, practical deployment for validation, and further optimization of model structures and parameters to improve performance and applicability.

This study employs the reflection symmetry decomposition (RSD) method to extract polarization scattering features from ground object images, aiming to determine the optimal data input scheme for deep learning networks in polarimetric synthetic aperture radar classification. Eight distinct polarizing feature combinations are designed, and the classification accuracy of various approaches is evaluated using the classic convolutional neural networks(CNNs) AlexNet and VGG16. The findings reveal that the commonly employed 6-parameter input scheme, favored by many researchers, lacks the comprehensive utilization of polarization information and warrants attention. Intriguingly, leveraging the complete 9-parameter input scheme based on the polarization coherence matrix results in improved classification accuracy. Furthermore, the input scheme incorporating all 21 parameters from the RSD and polarization coherence matrix notably enhances overall accuracy and the Kappa coefficient compared to the other 7 schemes. This comprehensive approach maximizes the utilization of polarization scattering information from ground objects, emerging as the most effective CNN input data scheme in this study. Additionally, the classification performance using the second and third component total power values (P2 and P3) from the RSD surpasses the approach utilizing surface scattering power value (PS) and secondary scattering power value (PD) from the same decomposition.

Timely and accurate acquisition of information on distribution of the crop planting structure in Loess Plateau of eastern Gansu Province, one of the most important agricultural areas in western China, is crucial for promoting fine management of agriculture and ensuring food security. In this study, the Object-Based Image Classification (OBIC), the Random Forest (RF) and Convolutional Neural Network (CNN) models were employed to classify the crop planting structure of four representative test areas in Qingyang City in a precise manner. Firstly, different optimal segmentation scales for various crops were selected using the Estimation of Scale Parameter 2 (ESP2) tool and the Ratio of Mean Difference to Neighbors(ABS) to Standard Deviation (RMAS)model. The images were then segmented through multiresolution segmentation combined with the Canny Edge Detection algorithm. Secondly, the L1 regularized logistic regression model was utilized to select and optimize 39 spatial feature factors including spectral, textural, geometric, and index features, in conjunction with phenological factors. Lastly, under the multi-level classification framework, the Random Forest (RF) classifier and Convolutional Neural Network (CNN) model, combined with object-based multiresolution segmentation, was used to classify the crop planting structure. The findings show that: Thanks to the Canny Edge Detection algorithm, we can obtain a more complete boundary of the segmented objects and improve the separability. The optimal segmentation scales for corn, vegetables, and buckwheat were found to be 55, 70, and 35, respectively, while wheat and apple had optimal segmentation scales of 65. In addition to phenological characteristics, the number of selected spatial features for corn, vegetables, buckwheat, wheat, and apple were 9, 7, 16, 12, and 10, respectively. The CNN model demonstrated high consistency with the RF model in the classification results, but the accuracy of RF model is higher than that of CNN model on the whole. The overall accuracy of classification using RF model in four test areas registered 91.93%, 94.92%, 89.37% and 90.68%, respectively. This paper introduced crop phenological factors, effectively improving the extraction precision of shattered agricultural planting structure in the Loess Plateau of eastern Gansu Province. Its findings have important application value in crop monitoring, management, food security and other related fields.

Automatic target detection of remote sensing images (RSI) plays an important role in military reconnaissance, disaster monitoring, and target rescue. The core task of remote sensing target detection is to judge the target categories and complete precise location. However, the existing target detection algorithms have limited accuracy and weak generalization capability for remote sensing images with complex backgrounds. To achieve accurate detection of different categories targets in remote sensing images, this study presents a novel feature enhancement single shot multibox detector (FESSD) algorithm for remote sensing target detection. The FESSD introduces feature enhancement module and attention mechanism into the convolution neural networks (CNN) model, which can effectively enhance the feature extraction ability and nonlinear relationship between different convolution features. Specifically, the feature enhancement module is used to extract the multi-scale feature information, and enhance the model nonlinear learning ability; the self-learning attention mechanism (SAM) is used to expand the convolution kernel local receptive field, which makes the model extract more valuable features. In addition, the nonlinear relationship between different convolution features is enhanced using the feature pyramid attention mechanism (PAM). The advantage of FESSD over other state-of-the-art target detection methods is validated by experiments on the presented seven-class target detection dataset (SD-RSI) and the public DIOR dataset.

Phase imaging of biochemical samples has been demonstrated for the first time at the Infrared Microspectroscopy (IRM) beamline of the Australian Synchrotron using the usually discarded Near-IR (NIR) region of the synchrotron-IR beam. The synchrotron-IR beam at the Australian Synchrotron IRM beamline has a unique fork shaped intensity distribution as a result of the gold coated extraction mirror shape, which includes a central slit for rejection of the intense X-ray beam. The resulting beam configuration makes any imaging task challenging. For intensity imaging, the fork shaped beam is usually tightly focused to a point on the sample plane followed by a pixel-by-pixel scanning approach to record the image. In this study, a pinhole was aligned with one of the lobes of the fork shaped beam and the Airy diffraction pattern was used to illuminate biochemical samples. The diffracted light from the samples was captured using a NIR sensitive lensless camera. A rapid phase-retrieval algorithm was applied to the recorded intensity distributions to reconstruct the phase information corresponding to different planes. The preliminary results are promising to develop multimodal imaging capabilities at the IRM beamline of the Australian Synchrotron.

This study is follow-up of the steel shot transformation under the influence of environmental factors research (Lisin et al., 2022) and is the initial stage of investigating the iron behavior in soils during steel shot corrosion under a number of factors: the metallic lead in soils, atmospheric precipitation, excess organic matter. The results obtained show that corrosion of steel ammunition is a continuous process, including the formation of a poorly soluble rust crust on the surface of the steel and the mineralization of the metal until it is destroyed. As a result, the metal transformed into rust form, is a constant source of iron ions and dispersed rust particles migrating in soil waters and accumulating in soils. In addition, the aggregation of corrosion products of steel ammunition is the cause of a change in physical and mechanical properties of soils, which leads to a violation of the air and water migration regime of soils and an increase in surface runoff from the territories of shooting activity. The highest environmental risks are observed when steel ammunition is used on shooting areas where metallic lead intensifies steel shot corrosion rate, while the deposited steel shot activates the deterioration of previously encapsulated metal and — if steel and lead ammunition are used at the same time — slows down the encapsulation of newly deposited metallic lead, which catalyses the accumulation and migration of lead in environmental components.

Background/Objectives: This study looks at how a kinematic chain exercise regimen that targets the lower, core, and upper body affects university shot put participants' shoulder muscle strength and throwing efficiency. This study fills an apparent research void on shot put training approaches by presenting a comprehensive kinematic chain workout program. It was anticipated that this method would improve performance the most, considering the complex biomechanical require-ments of the sport. Methodology: Athletes, seventy in age (19.87 ± 1.31 years), were assigned into two groups at random: experimental (n = 35) and control (n = 35). While the control group carried on with their usual training, the experimental group participated in an 8-week kinematic chain training program, pre- and post-training evaluations were carried out to evaluate shot put throwing ability, shoulder muscle strength, and participant satisfaction with the exercise regimen. Results: demonstrated that, when compared to the control group, the athletes in the kinematic chain program had a significantly improved throwing distance (p = 0.01) and shoulder muscle strength (p = 0.01). Furthermore, there was a significant difference (p = 0.005) in the athletes' satisfaction levels with the workout program among those in the experimental group. This implies that a kinematic chain-focused strategy improves performance and emphasizes the significance this type of training is for shot put athlete performance. Conclusion: As an improvement forward in sports science, the study's finding promotes the inclusion of kinematic chain workouts in shot put training programs and calls for more research on kinematic chain-based approaches in a variety of sports.

Hydrogen plays an important role in the implementation of Australia’s Net-Zero Strategy. It competes with lithium-ion rechargeable batteries in the electrification of Australian land transportation sector, and can provide an alternative energy storage medium for the greening of the country’s electrical grid system. This paper reviews the role hydrogen plays in the current government’s Net-Zero strategy, and investigates the potential role of other bioenergy sources. It is found that hydrogen and batteries play essentially complementary roles in reducing transport emissions, and that the former energy source is more suited to the operation of long-distance commercial service vehicles than batteries. It is suggested that bioenergy fuels such as biomethane, second generation biofuels and HVO can provide suitable bridging alternatives in the event that Australia’s EV strategy is unable to meet the 2030 target.

Despite the increase in popularity of Zero Waste (ZW) concept, the successful implementation of this concept in waste management is still facing many challenges. The plastic recycling rate in Australia is currently only about 9.4%, which could leave up to 90.6% of plastic consumption being sent to landfills. The state of Victoria (in Australia) has proposed an ambitious plan to upgrade its waste and recycling system and to divert about 80% of waste from landfills by 2030. The aim of this research is to study Victoria’s current waste management plan and to develop a simulation model to assess the feasibility of it achieving zero plastic waste by 2035. In this direction, a fundamental knowledge of global ZW implementation needs to be acquired in order to understand the challenges, obstacles, and uncertainties in achieving ZW target. A simulation model is established using a method called double baselines. This method was developed as an improvisation to address the limitation of data availability for the model development. The model will run on 4 scenarios including one from Victoria’s current plan. Outcomes from the model are produced in comparative charts covering 6 key considerations including the rates of plastic consumption, waste to landfill, diversion, recycling, relative accumulative cost and effort. The findings of this study pointed out that Victoria’s current plan are feasible for its goal and presented with opportunities for improvement especially towards zero plastic waste. Besides, study results also reveal that the Victoria’s current plan to achieve 80% diversion rate by 2030 is possible but the zero plastic waste target by 2035 is less likely to happen.

Biothermodynamics of viruses is among the youngest, but rapidly developing scientific disciplines. During the COVID-19 pandemic, it has closely followed the results published by molecular biologists. Empirical formulas were published for 50 viruses and thermodynamic properties for multiple viruses and virus variants, including all variants of concern of SARS-CoV-2, SARS-CoV, MERS-COV, Ebola virus, Vaccinia and Monkeypox virus. A review of development of biothermodynamics of viruses during the last several decades and intense development during the last 3 years has been described in this paper.

This study reports an empirical analysis of an all-electric, Net Zero Energy Housing (NZEH) development located in a mixed-humid climate zone (4A, Virginia, USA). Circuit-level energy monitors were used to measure energy consumption and energy production data (solar photovoltaic) at 1-hr intervals in six identical apartments over 24 months. The study employs a multi-step case study methodology to a) empirically evaluate energy consumption and production data, b) identify the temporal variability of energy consumption and production data at different time scales, c) understand the impact(s) of weather and human-building interaction on energy consumption and production, and d) synthesize the study’s “lessons learned” toward data-driven recommendations for future NZEH researchers and practitioners. The study found that the development’s net zero energy goal was achieved in three of six case units and that NZEH housing performance was more influenced by human-building interaction than weather variability. The analysis also found the solar photovoltaic (PV) performance to be reliable across the sampled units over the periods of measurement, suggesting that solar PV could be oversized as an approach to overcome verifiability in HBI and achieve NZEH performance goals.