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 introduces the self-supervised pretext task of rare visual token enhancement: given an image, the model is trained to push the rarest visual tokens far from all the others. This pretext task slightly-but-consistently improves baseline performances for both registration and few-shot change detection on OSCD, LEVIR-CD and S2looking.

With prosperous development and successful application of deep learning technologies in the field of remote sensing, numerous deep-learning based methods have emerged for synthetic aperture radar (SAR) automatic target recognition (ATR) tasks over the past few years. Generally, most deep-learning based methods can achieve outstanding recognition performance in condition that an abundant of labeled samples are available to train the model. However, in real application scenarios, it is difficult and costly to acquire and to annotate abundant SAR images due to the imaging mechanism of SAR, which poses a big challenge to existing SAR ATR methods. Thereby, SAR target recognition under the situation of few-shot, where only a scarcely few of labeled samples are available, is a fundamental problem that needs to be solved. In this paper, we put forward a new method named enhanced prototypical network with customized region-aware convolution (CRCEPN) to specially tackle the few-shot SAR ATR tasks. To be specific, We first develop a feature extraction network based on a customized and region-aware convolution, which can adaptively adjust convolutional kernels and their receptive fields according to each SAR image’s own characteristics as well as the semantical similarity among spatial regions, thus augmenting its capability to extract more informative and discriminative features. To achieve accurate and robust target identity prediction under the few-shot condition, we then propose an enhanced prototypical network which can improve the representation ability of the class prototype by properly making use of training and test samples together, thus effectively raising the classification accuracy. Meanwhile, a new hybrid loss is designed to learn a feature space with both inter-class separability and intra-class tightness as much as possible, which can further upgrade the recognition performance of the proposed method. Experiments performed on the moving and stationary target acquisition and recognition (MSTAR) dataset and the OpenSARShip dataset demonstrate that the proposed method is competitive with some state-of-the-art methods for few-shot SAR ATR tasks.

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.

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.

N-shot learning has emerge in recent year as potential learning approach to solve the problem of data scarcity by learning underlying pattern from a few training sample. Despite recent state-of-the-art research on model-agnostic metal learning, transfer learning, and optimization strategy to rapidly learn valid information from few sample, there remains a big challenge on an actual out-of-distribution zero-day without any similarity to previously known malware family or new variant of an existing malware family. This ultimately questions the effectiveness of current state-of-the-art few-shot learning approach. In this research, we did an in-depth investigation into the performance of state-of-the-art Zero-shot, Single-shot, and few-shot learning approaches on zero-day out-of-distribution malware attack detection based on their static properties using Malimg and Malevis malware dataset. We ensure our model was aware of an out-of-distribution class during training while varying the number of samples in the out-of-distribution class accordingly zero-shot(no sample), single-shot (1 sample), few-shot(5 samples) while using confusion matrix to get the actual number of correct prediction on out-of-distribution malware validation samples. we assert that the model should be smart enough to detect and classify previously unseen data into an empty family as an out-of-distribution considering that the model was made to be aware of the existence of such distribution during training. Result shows 0, 0, and 3 correct out-of-distribution predictions on Zero-shot, single-shot, and few-shot experiments respectively, thereby showing limitation of the current state-of-the-art N-shot approaches on out-of-distribution attack.

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.

With advancements in digital technologies such as 5G communications, big data, and cloud computing, the components of network operation systems have become increasingly complex, significantly complicating system monitoring and maintenance. Correspondingly, automated log anomaly detection has become a crucial means to ensure stable network operation and protect them from malicious attacks or failures. Conventional machine learning and deep learning methods assume consistent distributions between the training and testing data, adhering to a closed-set recognition paradigm. Nevertheless, in realistic scenarios, systems may encounter new anomalies that were not present in the training data, especially in log anomaly detection. Inspired by evidential learning, we propose a novel anomaly detector called LogEDL, which supervises training of the model through an evidential loss function. Unlike traditional loss functions, the evidential loss function not only focuses on correct classification, but also quantifies the uncertainty of predictions. This enhances the robustness and accuracy of the model in handling anomaly detection tasks, while achieving functionality similar to open-set recognition. To evaluate the proposed LogEDL method, we conduct extensive experiments on three datasets, i.e., HDFS, BGL, and Thunderbird, to detect anomalous log sequences. Experimental results demonstrate that our proposed LogEDL achieves state-of-the-art performance in anomaly detection.

Public safety and intelligent surveillance systems critically depend on anomaly behavior detection for effective monitoring. In real-world pedestrian detection scenarios, prevalent challenges such as missed detections, complex background interference, and small target sizes hinder accurate anomaly identification. To address these issues, this study introduces YOLO-ABD, a lightweight method for anomaly behavior detection that integrates small target detection and channel shuffling. This method employs YOLOv8n as the baseline model, incorporating a small target detection mechanism in the Head part and utilizing GSConv convolution in the Backbone to enhance perceptual capability. Additionally, the SimAM attention mechanism is integrated to mitigate complex background interference, thereby improving target detection performance. Evaluation on the IITB-Corridor dataset demonstrated mAP50 and mAP50-95 scores of 89.3% and 60.6%, respectively. Generalization testing on the street-view-gdogo dataset further highlighted the superiority of YOLO-ABD over advanced detection algorithms, underscoring its effectiveness and generalizability. With a relatively small parameter count, YOLO-ABD presents an excellent lightweight solution for pedestrian anomaly behavior detection.

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.

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.

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.

Agriculture is pivotal in national economies, with pest detection significantly influencing food quality and quantity. Pest classification remains challenging in automated agriculture monitoring systems, exacerbated by the non-uniform pest scales and the scarcity of high-quality datasets. In this study, we constructed a pest dataset by acquiring domain-agnostic images from the Internet and resizing them to a standardized 299x299 pixel format. Additionally, we employed diffusion models to generate supplementary data. While Convolutional Neural Networks (CNNs) are prevalent for prediction and classification, they often lack effective global information integration and discriminative feature representation. To address these limitations, we propose the RS Transformer, an innovative model that combines elements like the Region Proposal Network, Swin Transformer, and ROI Align. Additionally, we introduce the Randomly Generated Stable Diffusion Dataset (RGSDD) to augment the availability of high-quality pest datasets. Extensive experimental evaluations demonstrate the superiority of our approach compared to both two-stage models (SSD and Faster R-CNN) and one-stage models (YOLOv3, YOLOv4, YOLOv5m, YOLOv8, and DETR). We rigorously assess performance using metrics such as mean Average Precision (mAP), F1Score, Recall, and mean Detection Time (mDT). Our research contributes to advancing pest detection methodologies in automated agriculture systems, promising improved food production and quality.

With increasing research focus on industrial anomaly detection, numerous methods have emerged in this domain. Notably, memory bank-based approaches, coupled with kNN distance metrics, have demonstrated remarkable performance in anomaly detection (AD) and anomaly segmentation (AS). However, upon examination of the Back to the Feature (BTF) method applied to the Mvtec-3D AD dataset, it was observed that while it exhibited exceptional segmentation performance, its detection performance was lacking. To address this discrepancy, this study base improves the implementation of BTF, especially the improvement of the anomaly score metric. It posits that different "clusters" necessitate distinct k values in kNN distance metrics. For simplify, this assumption is distilled into the proposition that AD and AS tasks impose differing requirements on the k value in kNN distance metrics. Consequently, the paper introduces the BTM method, which utilizes distinct distance metrics for AD and AS tasks. This innovative approach yields superior AD and AS performance (I-AUROC 93.0%, AURPO 96.9%, P-AUROC 99.5%), representing a substantial enhancement over the BTF method (I-AUROC 5.7% ↑, AURPO 0.5% ↑, P-AUROC 0.2% ↑).

Against the background of the sky, imaging and perception of aircraft are cru- cial. Among these, the location of aircrafts is not a very difficult problem in general, because that deep learning algorithms and object detection models based on convolutional neural network(CNN) are ever-evolving. In order to have a better identification of various aircrafts, or to accurately locate different types of flying targets in the sky, it becomes significant to distinguish and recognize different types of aircrafts. One question is that, distinguishing and recognizing between sub-categories of aircrafts pose great challenges. Although fine-grained recognition focuses on exploring and studying such problems, aircrafts under different sub-categories and granularities lead us to rethink the application of features. We noticed that features in swin-transformer demonstrates the under- standing and processing of images, fully showcasing the encoding and indexing of information. Through this research and proposed approach, we discovered a better understanding of features encoding and use, which are inspired by the feature encoding and computation in swin-transformer. In our paper, our ap- proach has achieved effects on features encoded graphically, manifested from the architecture design and convolutional neural network computation, and outper- forms other famous fine-graiend classification models on this issue. Not only approach we proposed has demonstrated superior performance in fine-grained aicraft classification, but also the mechanisms of the feature encoding under different sample space partitions is revealed for this issue, which provides a re- search for the representation of aircraft fineness characteristics. The relationship between representation orientation of aircraft feature information under various grained divisions, shows that the recognition of different categories according to man-made, such as aircraft, can be achieved by means of the feature represen- tations studied in this paper, for more specific defined classification tasks and various man-made targets partition criteria, which may influences the princi- ple of design for calculation and feature extraction in fine-grained classification models.

Several disruptive attacks against companies in the maritime industry have led experts to consider the increased risk imposed by cyber threats as a major obstacle to undergoing digitization. The industry is heading toward increased automation and connectivity, leading to reduced human involvement in the different navigational functions and increased reliance on sensor data and software for more autonomous modes of operations. To meet the objectives of increased automation under the threat of cyber attacks, the different software modules that are expected to be involved in different navigational functions need to be prepared to detect such attacks utilizing suitable detection techniques. Therefore, we propose a systematic approach for analyzing the navigational NMEA messages carrying the data of the different sensors, their possible anomalies, malicious causes of such anomalies as well as the appropriate detection algorithms. The proposed approach is evaluated through two use cases, traditional Integrated Navigation System (INS) and Autonomous Passenger Ship (APS). The results reflect the utility of specification and frequency-based detection in detecting the identified anomalies with high confidence. Also, the analysis is found to facilitate the communication of threats through indicating the possible impact of the identified anomalies against the navigational operations. Moreover, we have developed a testing environment that facilitates conducting the analysis. The environment includes a developed tool, NMEA−Manipulator that enables the invocation of the identified anomalies through a group of cyber attacks on sensor data. Our work paves the way for future work in the analysis of NMEA anomalies toward the development of an NMEA intrusion detection system.

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.

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.

Increasing concerns on animal welfare in commercial pig industry include aggression between pigs as it affects their health and growth. Early detection of aggressive behaviors is essential for optimizing their living environment. A major challenge for detection is that these behaviors are observed occasionally in normal conditions. Under this circumstance, a limited amount of aggressive behavior data will lead to class imbalance issue, making it difficult to develop an effective classification model for the detection of aggressive behaviors. To overcome this problem, we approach the aggressive behavior detection problem as a case of anomaly detection rather than classification and propose a model based on anomaly detection, which can better handle unbalanced class distribution and effectively detect the infrequent, aggressive episodes of pigs. The model consists of a convolutional neural network (CNN) and a variational long short-term memory (LSTM) autoencoder. Additionally, we adopted a training method similar to weakly supervised anomaly detection and included a few aggressive behavior data in the training set for prior learning. To effectively utilize the aggressive behavior data, we created Reconstruction Loss Inversion, a novel objective function, to train the autoencoder-based model to increase the reconstruction error of aggressive behaviors by inverting the loss function. Our anomaly detection approach significantly outperforms traditional classification-based methods, effectively identifying aggressive behaviors in a natural farming environment. This method offers a robust solution for detecting aggressive animal behaviors and contributes to improving their welfare.

Existing methods of hyperspectral anomaly detection still face several challenges: 1) Due to the limitations of self-supervision, avoiding the identity mapping of anomalies remains difficult; 2) The ineffective interaction between spatial and spectral features leads to the insufficient utilization of spatial information; 3) Current methods are not adaptable to the detection of multi-scale anomaly targets. To address the aforementioned challenges, we proposed a blind spot network based on multi-scale blind spot convolution for HAD. The multi-scale mask convolution module is employed to adapt to diverse scales of anomaly targets, while the dynamic fusion module is introduced to integrate the advantages of mask convolutions at different scales. The proposed approach includes a spatial-spectral joint module and a background feature attention mechanism to enhance the interaction between spatial-spectral features, with a specific emphasis on highlighting the significance of background features within the network. Furthermore, we propose a preprocessing technique that integrates pixel shuffle down-sampling (PD) operation with spatial spectral joint screening to address the issue of anomalous identity map-ping and facilitate finite-scale mask convolution to adapt to the detection of more scale targets. The proposed approach was assessed on four real hyperspectral datasets comprising anomaly targets of different scales. The experimental results demonstrate the effectiveness and superior performance of the proposed methodology compared with nine state-of-the art methods.

The emergence of few-shot learning as a potential approach to address the problem of data scarcity by learning underlying pattern from a few training sample had so far given a mix-result especially on the suitability of model-agnostic meta learning, transfer learning, and optimization strategy to rapidly learn valid information from few sample. In this research, we did an in-depth evaluation of meta- learning to determine their plausibility and suitability for previously unknown cyberattack detection by first retrieving the original research artifacts of current state of the art meta learning to repeat the experiment with original dataset before replicating the experiment with two different malware dataset which had not been previously done with meta-transfer learning. On each of the experiments, meta-transfer learning gave good results on digital character recognition dataset but abysmal result on Malimg and Malevis malware images datasets thereby indicating its unreliability for detecting cyberattacks and the need for an improvement to the state-of-the-art meta transfer learning towards a better attack detection. Transfer learning performance is independent on imbalance and hence does not influence its performance since both malware dataset used for this experiment result in high validation loss and balancing the dataset doesn't result in reduced validation loss,the successful learning transfer seen on digital character recognition dataset is not unconnected to the fact that several languages have similar characters and digits thereby enhancing the successful learning transfer unlike malware datasets, and more importantly the finding that current meta-learning transfer approach doesn't generalize well on malware dataset and hence not suitable for detecting previously unseen out-of-distribution attack.

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.

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.

The anomaly detection task is very important in computer science. And there are a lot of anomaly detection methods. Different from some thresholding methods, some unsupervised methods could make us get more accurate and faster result, which is the object of the project. In this paper, I tried to use EWMA and some other methods in two datasets: Webank time consuming indicators dataset and AIOps Challenge dataset. The paper consists nine parts: background of the project, related work, description of algorithms, implementation details, experimental setup and data sets used, experimental results and discussion, future directions, reference and meeting notes.

This study discusses the application of deep learning technology in network intrusion detection systems (IDS) and focuses on a new model named CNN-Focal. First, through the review of traditional IDS technology, it analyzes its limitations in dealing with complex network traffic. Then, the design principle of the CNN-Focal model is described in detail, which uses threshold convolution and SoftMax multi-class classification technology to effectively improve abnormal traffic detection's accuracy and efficiency. The experimental results show that CNN-Focal performs well on the open data set, demonstrating the potential and advantages of its application in the natural network environment and providing a new perspective and method for further research of deep learning in the field of network security in the future.

This study explores fault-tolerant consensus in leader-following heterogeneous multi-agent systems, focusing on actuator failures in uncrewed aerial vehicles (UAVs) and uncrewed ground vehicles (UGVs). An optimization-based fault-tolerant consensus algorithm is proposed. The algorithm utilizes the Euler-Lagrange formula to ensure system consistency under actuator failures, with the Lyapunov stability theory proving the asymptotic stability of the consistency error. The algorithm is applied to heterogeneous multi-agent systems of UAVs and UGVs to derive optimal fault-tolerant consensus control laws for each vehicle type. Simulation experiments give evidence for the feasibility of the proposed control strategy.

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.

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.

By shifting the focus from aggregate-level analysis to individual-level analysis, we believe that the DAD model can contribute to a more comprehensive understanding of driving behavior. Combing DAD with a conflict identification (CIM) model can potentially enhance the effectiveness of Advanced Driver Assistance Systems (ADAS) in terms of crash evasion capabilities. This paper is part of our research titled Automatic Safety Diagnosis in Connected Vehicle Environment, which received funding from the Southeastern Transportation Research, Innovation, Development, and Education Center.

Hyperspectral anomaly detection is to recognize anomalies from complex scene in an unsupervised way. Currently, many spectral-spatial detection methods have been proposed with a cascaded manner. However, they often neglect complementary characteristics between spectral and spatial dimensions, which easily leads to yield high false alarm rate. To alleviate this issue, a spectral-spatial information fusion (SSIF) method is designed for hyperspectral anomaly detection. First, an isolation forest is exploited to obtain spectral anomaly map, in which the object-level feature is constructed with entropy rate segmentation algorithm. Then, a local spatial saliency detection scheme is proposed to produce spatial anomaly result. Finally, the spectral and spatial anomaly scores are integrated together followed by a domain transform recursive filtering to generate the final detection result. Experiments on five hyperspectral datasets prove that the proposed SSIF produces superior detection result over other state-of-the-art detection techniques.

Pipeline integrity is an important area of concern for the oil and gas, refining, chemical, hydrogen, carbon sequestration, and electric-power industries, due to the safety risks associated with pipeline failures. Regular monitoring, inspection, and maintenance of these facilities is therefore required for safe operation. Large standoff magnetometry (LSM) is a non-intrusive, passive magnetometer-based mea- surement technology that has shown promise in detecting defects (anomalies) in regions of elevated mechanical stresses. However, analyzing the noisy multi-sensor LSM data to clearly identify regions of anomalies is a significant challenge. This is mainly due to the high frequency of the data collection, mis-alignment between consecutive inspections and sensors, as well as the number of sensor measurements recorded. In this paper we present LSM defect identification approach based on ma- chine learning (ML). We show that this ML approach is able to successfully detect anomalous readings using a series of methods with increasing model complexity and capacity. The methods start from unsupervised learning with "point" methods and eventually increase complexity to supervised learning with sequence methods and multi-output predictions. We observe data leakage issues for some methods with randomized train/test splitting and resolve them by specific non-randomized splitting of training and validation data. We also achieve a 200x acceleration of support-vector classifier (SVC) method by porting computations from CPU to GPU leveraging the cuML RAPIDS AI library. For sequence methods, we develop a customized Convolutional Neural Network (CNN) architecture based on 1D convolutional filters to identify and characterize multiple properties of these defects. In the end, we report the scalability of the best-performing methods and compare them, for viability in field trials.

The rapid evolution of information and communication technologies, notably the Internet, has yielded substantial benefits while posing challenges to information system security. With an increasing frequency of cyber threats—from unauthorized access to data breaches—the digital landscape's vulnerability is evident. Addressing the financial impact of cybercrime, this study delves into the role of Artificial Intelligence (AI) and Machine Learning (ML) technologies in cybersecurity. Analyzing advancements and outcomes, the research explores practical techniques for anomaly detection, threat prediction, and automated response. By investigating prior research and real-world implementations, the study provides valuable insights into the potential of AI/ML, uncovering current trends, challenges, and prospects in enhancing cybersecurity tactics amid a dynamically changing threat landscape.

Foundational and state-of-the-art anomaly detection methods through power system state estimation are reviewed. The traditional components for bad data detection such as chi-square testing, residual-based methods, and hypothesis testing are discussed to explain the motivations for recent anomaly detection methods given the increasing complexity of power grids, energy management systems, and cyber-threats. In particular, state estimation anomaly detection based on data-driven quickest change detection and artificial intelligence are discussed and directions for research are suggested with particular emphasis on considerations of the future smart grid.

In recent years, video anomaly detection technology , which can intelligently analyze massive video and quickly find abnormal phenomena, has attracted extensive attention with the wide application of video surveillance technology . To address the complex and diverse problem of abnormal human behavior detection in surveillance videos, a surveillance video abnormal behavior detection and localization supervised method based on the deep network model and the traditional method is proposed. Specifically, we combined AGMM and YOLACT methods to obtain more accurate foreground information by fusing the foreground maps extracted by each technique. To further improve the accuracy , we use the PWC-Net technique to extract features of the foreground images and input them into an anomaly classification model for classification. The proposed method effectively detects and locates the abnormal behavior in the monitoring scene. In addition to the aforementioned methods, this paper also employs YOLOV5 and DeepSORT networks for object detection and tracking in the video, which allows us to track the detected objects for better understanding of the scene in the video. Experiments on the UCSD benchmark dataset and the comparison with state-of-the-art schemes prove the advantages of our method.

Anomaly Detection in real time data is accepted as a vital research area. Clustering has effectively been tried for this purpose. As the datasets are real time, the time of generating of the data is also important. In this article, we introduce a mixture of partitioning and agglomerative hierarchical approach to detect anomalies from such datasets. It is a two-phase method which follows partitioning approach first and then agglomerative hierarchical approach. The dataset can have mixed attributes. In phase-1, a unified metric defined on mixed attributes is used. The same is also used for merging of similar clusters in phase-2. Also, we have kept the track of time attribute of each data instance which produces the clusters with their lifetimes in phase-1. Then in phase-2, we merge the similar clusters. While merging, the similar clusters, the lifetimes of the corresponding clusters with overlapping cores are to be superimposed producing fuzzy time intervals. This way, each cluster will have an associated fuzzy lifetime. The data instances either belonging sparse clusters or not belonging to any of the clusters can be treated as anomalies. The efficacy of the algorithms can be established using both complexity analysis as well as experimental studies.

Anomaly detection is an active area of research with numerous methods and applications. This survey reviews the state-of-the-art of data-driven anomaly detection techniques and their application to the the aviation domain. After a brief introduction to the main traditional data-driven methods for anomaly detection, we review the recent advances in the area of neural networks, deep learning and temporal-logic based learning. We cover especially unsupervised techniques applicable to time series data because of their relevance to the aviation domain, where the lack of labeled data is the most usual case, and the nature of flight trajectories and sensor data is sequential, or temporal. The advantages and disadvantages of each method are presented in terms of computational efficiency and detection efficacy. The second part of the survey explores the application of anomaly detection techniques to aviation and their contributions to the improvement of the safety and performance of flight operations and aviation systems. As far as we know, some of the presented methods have not yet found an application in the aviation domain. We review applications ranging from the identification of significant operational events in air traffic operations to the prediction of potential aviation system failures for predictive maintenance.

The challenging issues of Computer Network and Databases are not only the intrusion detection but also the reduction of false positive and increase of detection rate. In any intrusion detection system, anomaly detection mainly focuses on modeling the normal behavior of the users and detecting the deviations from normal behavior which are assumed to be potential intrusions or treat. Several techniques have already been successfully tried for this purpose. However, the normal and suspicious behavior are hard to predict as there is no precise boundary differentiat-ing one from another. Here rough set theory and fuzzy set theory come into the picture. In this article, a hybrid approach based on rough set theory and intuitionistic fuzzy set theory is pro-posed for the detection of anomaly. The proposed approach is a classification approach which takes the advantages of softness properties both rough and fuzzy set theory to deal with uncer-tainty in the dataset. The algorithm classifies the data instances in such a way that they can be expressed using natural language. The experimental results with a real world dataset and a syn-thetic dataset show that the proposed algorithm has normal true positive rates of 91.989% and 96.99% and attack true positive rates of 91.289% and 96.29% respectively

Machine learning methods have widely been applied to detect anomalies in machine and cutting tool behavior during lathe or milling. However, detecting anomalies in the workpiece itself did not get the same attention by researchers. That is why in this article, the authors present a pub-licly available multivariate time series dataset which was recorded during milling of 16MnCr5. Due to artificially introduced, though realistic anomalies in the workpiece the dataset can be ap-plied for anomaly detection. By using a convolutional autoencoder as a first model good results in detecting the location of the anomalies in the workpiece were achieved. Furthermore, milling tools with two different diameters where used which led to a dataset eligible for transfer learn-ing. The objective of this article is to provide researchers with a real-world time series dataset of the milling process which is suitable for modern machine learning research topics like anomaly detection and transfer learning.

The rapid industrial growth in solar energy is gaining increasing interest in renewable power from smart grids and plants. Anomaly detection in photovoltaic (PV) systems is a demanding task. In this sense, it is vital to utilize recent advances in machine learning to accurately and timely detect different anomalies and condition monitoring. This paper addresses this issue by evaluating different machine learning techniques and schemes and showing how to apply these approaches to solve anomaly detection and detect faults on photovoltaic components. For this, we apply distinct state-of-the-art machine learning techniques (AutoEncoder Long Short-Term Memory (AE-LSTM), Facebook-Prophet, and Isolation Forest) to detect faults/anomalies and evaluate their performance. These models shall identify the PV system's healthy and abnormal actual behaviors. Our results provide clear insights to make an informed decision, especially with experimental trade-offs for such complex solution space.

Critical Infrastructures and associated real time Informational systems need some security protection mechanisms that will be able to detect and respond to possible attacks. For this reason, Anomaly Detection Systems (ADS), as part of a Security Information and Event Management (SIEM) system, are needed for constantly monitoring and identifying potential threats inside an Information Technology (IT) System. Typically, ADS collect information from various sources within a CI system using security sensors or agents and correlate those information so as to identify anomaly events. Such sensors though in a CI setting (factories, power plants, remote locations) may be placed in open areas and left unattended thus becoming targets themselves of security attacks. They can be tampering and malicious manipulated so that they provide false data that may lead an ADS or SIEM system to falsely comprehend the CI current security status. In this paper, we describe existing approaches on security monitoring in critical infrastructures and focus on how to collect security sensor - agent information in a secure and trusted way. We then introduce the concept of hardware assisted security sensor information collection that improve the level if trust (by hardware means) and also increase the responsiveness of the sensor. Thus, we propose a Hardware Security Token (HST) that when connected to a CI Host, it acts as a secure anchor for security agent information collection. We describe the HST functionality, its association with a host device, its expected role and its log monitoring mechanism. We also provide information on how security can be established between the Host device and the HST.Then, we introduce and describe the necessary Host components that need to be established in order to guarantee a high security level and correct HST functionality. We, also provide a realization-implementation of the HST overall concept in a FPGA SoC evaluation board and describe how the HST implementation can controlled. Finally, we provide indicative use case scenarios of how the HST can be used in practice to provide a variety of different security services beyond acting as a secure ADS sensor.

In the ambitiously evolving construction industry of Kuwait, characterized by its vision 2035 and rapid technological integration, there exists a pressing need for advanced analytical frameworks. This research paper introduces a groundbreaking deep learning approach utilising an autoencoder neural network to analyse the complexities of the Kuwait Construction Market and identify data irregularities. The construction sector’s significant investment influx and project expansion make it an ideal candidate for deploying sophisticated analytical techniques to detect anomalous patterns indicating inefficiencies or unveiling potential opportunities. Our approach leverages the capabilities of autoencoder architectures to delve into and understand the prevalent patterns in market behaviours. This meticulous analysis allows for the detection of deviations that may lead to operational or financial consequences. We elucidate the mathematical foundations of autoencoders, highlighting their proficiency in managing the complex, multidimensional data typical of the construction industry. Through training on an extensive dataset—comprising variables like market sizes, investment distributions, and project completions—our model demonstrates its ability to pinpoint subtle yet significant anomalies. The outcomes of this study enhance our understanding of deep learning’s pivotal role in construction and building management. Additionally, our findings proactively sketch the future market trajectory and facilitate anomaly detection, thereby contributing substantially to the academic discussion on integrating machine learning into construction management. This research offers valuable insights for professionals within Kuwait, aiming to harness deep learning techniques to boost operational efficiency and strategic foresight in the construction sector.

Recent SDN advances address traditional network management challenges through centralized control and plane separation. SDN prevents breaches using a centralized controller but introduces risks. The controller can be a single point of failure. Thus, an OpenFlow Controller's flow-based anomaly detection enhances SDN security. Our research explored two OpenFlow intrusion detection methods. The first employed machine learning, NSL-KDD dataset, and feature selection, yielding 82% accuracy with random forest. The second combined deep neural networks with GRU-LSTM, achieving 88% accuracy using ANOVA F-Test and feature elimination. Experiments highlighted deep learning as superior for OpenFlow intrusion detection.

Disease surveillance is critical to monitor ongoing control activities, detect early outbreaks and to inform intervention priorities and policies. Unfortunately, most data from disease surveillance remain under-utilised to support decision-making in real-time. Using the Brazilian Amazon malaria surveillance data as a case study, we explore unsupervised anomaly detection machine learning techniques to analyse and discover potential anomalies. We found that our models are able to detect early outbreaks, peak of outbreaks as well as change points in the proportion of positive malaria cases. Specifically, the sustained rise in malaria in the Brazilian Amazon in 2016 was flagged by several models. We also found that no single model detects all the anomalies across all health regions. The approaches using Clustering-based local outlier algorithm ranked first before Principal component analysis and Stochastic outlier selection in maximising the number of anomalies detected in local health regions. Because of this, we also provide the minimum number of machine learning models (top-k models) to maximise the number of anomalies detected across different health regions. We discovered that the top-3 models that maximise the coverage of the number and types of anomalies detected across the 13 health regions are: Principal component analysis, Stochastic outlier selection and Multi-covariance determinant. Anomaly detection approaches provide interesting solutions to discover patterns of epidemiological importance when confronted with a large volume of data across space and time. Our exploratory approach can be replicated for other diseases and locations to inform timely interventions and actions toward endemic disease control.

To detect aberrant human behaviors from large volume of passive data collected by smartphones in real time, we propose an online anomaly detection method using Hotelling’s T-squared test. The test statistic is a weighted average, with more weight on the between-individual component when there are little data available for the individual and more weight on the within-individual component when the data are adequate. The algorithm takes only O(1) run time in each update and the required memory usage is fixed after a pre-specified number of updates. The performance of the proposed method, in terms of accuracy, sensitivity and specificity, is consistently better than or equal to the offline method that it builds upon depending on the sample size of the individual data.

Sentinel eggs used to monitor field parasitism of stink bug pests (Hemiptera: Pentatomidae) can only be deployed for a few days to avoid releasing the pest in the monitored area. Using sterile eggs removes the risk of accidental pest introduction and extends deployment time. Freezing the eggs before deployment is one common method for sterilizing sentinel eggs. However, some egg parasitoid species have lower to no parasitism on frozen eggs. In this study, x-ray irradiation was used to sterilize Bagrada hilaris sentinel eggs intended for monitoring parasitism by Gryon aetherium (Hymenoptera: Scelionidae), the most promising biological control candidate. In this case, freezing sentinel eggs is not recommended because G. aetherium has low levels of parasitism on frozen eggs. Doses as low as 10 Gy induced 100% sterility. Irradiated eggs successfully sustained the development of G. aetherium and Ooencyrtus californicus (Hymenoptera: Encyrtidae), another egg parasitoid attacking B. hilaris, and parasitism levels were comparable to fresh eggs up to seven days. In addition, G. aetherium showed no preference for fresh non-irradiated over seven-day-old irradiated eggs. Our results indicate that x-ray irradiation is a suitable alternative to produce safe and reliable sentinel eggs to monitor egg parasitism of B. hilaris and possibly other species.

The log data generated during the operation of a software system contains information about the system, and using logs for anomaly detection can detect system failures in a timely manner. Most of the existing log anomaly detection methods are specific to a particular system, have cold start problems, and are sensitive to updates in log format. In this paper, we propose a log anomaly detection method LogBD based on pre-training model and domain adaptation, which uses the pre-training model BERT to learn the semantic information of logs, and can solve the problems caused by multiple meaning words and log statement updates. An anomaly detection method LogBD based on distance to determine anomalies is constructed based on domain adaptation, using TCN networks to extract common features of different system logs and map them to the same hypersphere space. Finally, experiments are conducted on two publicly available datasets to evaluate the method, and the experimental results show that the method can better solve the log instability problem and has some improvement in the cross-system log anomaly detection effect.

Recently, the availability of many omics data source has given the rise of modelling biological networks for each individual or patient. Such networks are able to represent individual-specific characteristics, providing insights into the condition of each person. Given a set of networks of individuals, a network representing a particular condition (e.g., an individual with a specific disease) may be seen as an anomaly network. Consequently, the use of Graph Anomaly Detection techniques may support such analysis. Among the others, Generative Adversarial Networks present optimal per- formances in anomaly detection. This paper presents ADIN (Anomaly Detection in Individual Networks), a framework based on Generative Adversarial Attributed Networks (GAANs) for anomaly detection in convergence/divergence patients at- tributed networks. Preliminary results on networks generated from computational biology gene expression data demonstrate the effectiveness of our approach in detecting and explaining bladder cancer patients.

The production of cheese, a beloved culinary delight worldwide, faces challenges in maintaining consistent product quality and operational efficiency. One crucial stage in this process is determining the precise cutting time during curd formation, which significantly impacts the quality of the cheese. Misjudging this timing can lead to the production of inferior products, harming a company's reputation and revenue. Conventional methods often fall short of accurately assessing variations in coagulation conditions due to the inherent potential for human error. To address this issue, we propose an anomaly detection-based approach. In this approach, we treat the class representing curd formation as the anomaly to be identified. Our proposed solution involves utilizing a one-class, fully convolutional data description network, which we compared against several state-of-the-art methods to detect deviations from the standard coagulation patterns. Encouragingly, our results show F1 scores of up to 0.92, indicating the effectiveness of our approach.

Nowadays, the Internet of Things (IoT) devices and applications have rapidly expanded worldwide due to their benefits in improving the business environment, industrial environment, and people's daily lives. However, the IoT devices are not immune to malicious network traffic, which causes potential negative consequences and sabotages IoT operating devices. Therefore, developing a method for screening network traffic is necessary to detect and classify malicious activity to mitigate its negative impacts. Therefore, this research proposes a predictive machine learning model to detect and classify network activity in an IoT system. Specifically, our model distinguishes between normal and anomaly network activity. Furthermore, it classifies network traffic into five categories, normal, Mirai attack, denial of service (DoS) attack, Scan attack, and man-in-the-middle (MITM) attack. Five supervised learning models were implemented to characterize their performance in detecting and classifying network activities for IoT systems. This includes models shallow neural networks (SNN), decision trees (DT), bagging trees (BT), support vector machine (SVM), and k-nearest neighbor (kNN). The learning models were evaluated on a new and broad dataset for IoT attacks, the IoTID20 dataset. Besides, a deep feature engineering process was applied to the dataset to improve the accuracy of the learning models. Our experimental evaluation exhibited an accuracy of 100% recorded for the detection using all implemented models and an accuracy of 99.4%-99.9% recorded for the classification process.

World Health Organization (WHO) provides the guideline for managing the Particulate Matter (PM) level because when the PM level is higher, it threats the human health. For managing PM level, the procedure for measuring PM value is needed firstly. We use Tapered Element Oscillating Microbalance (TEOM)-based PM measuring sensors because it shows higher cost-effectiveness than Beta Attenuation Monitor (BAM)-based sensor. However, TEOM-based sensor has higher probability of malfunctioning than BAM-based sensor. In this paper, we call the overall malfunction as an anomaly, and we aim to detect anomalies for the maintenance of PM measuring sensors. We propose a novel architecture for solving the above aim that named as Hypothesis Pruning Generative Adversarial Network (HP-GAN). We experimentally compare the several anomaly detection architectures to certify ours performing better.

Anomaly detection plays a significant role in helping gas turbines run reliably and economically. Considering collective anomalous data and both sensitivity and robustness of the anomaly detection model, a sequential symbolic anomaly detection method is proposed and applied to the gas turbine fuel system. A structural Finite State Machine is to evaluate posterior probabilities of observing symbolic sequences and most probable state sequences they may locate. Hence an estimating based model and a decoding based model are used to identify anomalies in two different ways. Experimental results indicates that these two models have both ideal performance overall, and estimating based model has a strong ability in robustness, while decoding based model has a strong ability in accuracy, particularly in a certain range of length of sequence. Therefore, the proposed method can well facilitate existing symbolic dynamic analysis based anomaly detection methods especially in gas turbine domain.

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.

In today's technologically advanced landscape, sensors feed critical data for accurate decision-making and actions. Ensuring the integrity and reliability of sensor data is paramount to system performance and security. This paper introduces an innovative approach utilizing discrete wavelet transforms (DWT) embedded within microcontrollers to scrutinize sensor data meticulously. Our methodology aims to detect and isolate malfunctions, misuse, or any anomalies before they permeate the system, potentially causing widespread disruption. By leveraging the power of wavelet-based analysis, we embed computational intelligence directly into the microcontrollers, enabling them to monitor and validate their outputs in real-time. This proactive anomaly detection framework is designed to distinguish between normal and aberrant sensor behaviors, thereby safeguarding the system from erroneous data propagation. Our approach significantly enhances the reliability of embedded systems, providing a robust defense against false data injection attacks and contributing to overall cybersecurity.

This work focused on the evaluation of some machine learning (ML) models and their application in e-health, using intermediate nodes within an Internet of Things (IoT) platform used for heartbeat anomaly detection. For the evaluation of ML models, a set of statistical validation metrics was selected. These metrics were applied in the training, testing and validation phases of the models. The results obtained can determine relevant factors for the selection of ML models, either based on the statistical and intrinsic efficiency of the ML models, or on their suitability to be implemented in intermediate nodes within an IoT platform. the more Lightweight models such as Simple Linear Regression, Logistic Regression, and K Nearest Neighbors, could easily operate in intermediate nodes, and they are models that require low processing and storage to work. In conclusion, the approach for intermediate nodes of Internet of Things platforms using cognitive networks decreases the processing cost in cloud computing and transfers it to the fog layer.

Nowadays, technological advancement has transformed traditional vehicles into Au-tonomous Vehicles (A.V.s). In addition, in our daily lives, A.V.s play an important role since they are considered an essential component of smart cities. A.V. is an intelligent vehicle capable of main-taining safe driving by avoiding crashes caused by drivers. Unlike traditional vehicles, which are fully controlled and operated by humans, A.V.s collect information about the outside environment using sensors to ensure safe navigation. Furthermore, A.V.s reduce environmental impact because they usually use electricity to operate instead of fossil fuel, thus decreasing the greenhouse gasses. However, A.V.s could be threatened by cyberattacks, posing risks to human life. For example, re-searchers reported that Wi-Fi technology could be vulnerable to cyberattacks through Tesla and BMW AVs. Therefore, more research is needed to detect cyberattacks targeting the components of A.V.s to mitigate their negative consequences. This research will contribute to the security of A.V.s by detecting cyberattacks at the early stages. First, we inject False Data Injection (FDI) attacks into an A.V. simulation-based system developed by MathWorks. Inc. Second, we collect the dataset generated from the simulation model after integrating the cyberattack. Third, we implement an intelligent symmetrical anomaly detection method to identify FDI attacks targeting the control system of the A.V. through a compromised sensor. We use long short-term memory (LSTM) deep networks to detect FDI attacks in the early stage to ensure the stability of the operation of A.V.s. Our method classifies the collected dataset into two classifications: normal and anomaly data. The ex-perimental result shows that our proposed model's accuracy is 99.95%. To this end, the proposed model outperforms other state-of-the-art models in the same study area.

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.

: Mistrust, amplified by numerous artificial intelligence (AI) related incidents, has caused the energy and industrial sectors to be amongst the slowest adopter of AI methods. Central to this issue is the black-box problem of AI, which impedes investments and fast becoming a legal hazard for users. Explainable AI (XAI) is a recent paradigm to tackle this challenge. Being the backbone of the industry, the prognostic and health management (PHM) domain has recently been introduced to XAI. However, many deficiencies, particularly lack of explanation assessment methods and uncertainty quantification, plague this young field. In this paper, we elaborate a framework on explainable anomaly detection and failure prognostic employing a Bayesian deep learning model to generate local and global explanations from the PHM tasks. An uncertainty measure of the Bayesian model is utilized as marker for anomalies expanding the prognostic explanation scope to include model’s confidence. Also, the global explanation is used to improve prognostic performance, an aspect neglected from the handful of PHM-XAI publications. The quality of the explanation is finally examined employing local accuracy and consistency properties. The method is tested on real-world gas turbine anomalies and synthetic turbofan data failure prediction. Seven out of eight of the tested anomalies were successfully identified. Additionally, the prognostic outcome showed 19% improvement in statistical terms and achieved the highest prognostic score amongst best published results on the topic.

The CAN protocol is widely adopted for in-vehicle networks due to its cost efficiency and reliable transmission. However, despite its popularity, the protocol lacks built-in security mechanisms, making it vulnerable to various attacks such as flooding, fuzzing, and DoS. These attacks can exploit vulnerabilities and disrupt the normal behavior of the in-vehicle network. One of the main reasons for these security concerns is that the protocol relies on broadcast frames for communication between ECUs within the network. To tackle this issue, this paper presents an intrusion detection system that leverages multiple LSTM-Autoencoders. The proposed system utilizes diverse features, including transmission interval and payload value changes, to capture various characteristics of normal network behavior. By analyzing different types of features separately using the LSTM-Autoencoder model, the system effectively detects anomalies. In our evaluation, we conducted experiments using real vehicle network traffic, and the results demonstrated the system's high precision with a 99% detection rate in identifying anomalies.

Wind energy is becoming an essential source of power for countries which have the aim to reduce greenhouse gases emission and mitigate the effects of global warming. The Wind Turbines (WTs) installed around the globe is increasing significantly every year. The dramatic increase in wind power has encountered quite a few challenges, among which the major issues are availability and reliability. The unexpected failure in WTs Gearbox (GB) ultimately increases the Operation and Maintenance (O&M) cost. The identification of faults in the earlier stages before it turns to catastrophic damage to other components of WT is crucial. This research deals with the prediction of WT failures by using a Supervisory Control and Data Acquisition (SCADA) system. The main aim is to forecast the temperature of the WTs GB to predict the impending overheating of the GB at an early stage. The earlier prediction will help to optimize the maintenance period and to save maintenance expenses and, even more important, generate warnings in due time to avoid major damages or even technical disasters. In the proposed method we compared six different machine learning (ML) models based on error and accuracy of prediction. The bagging regressor is the best ML model, which results in the mean square error of 0.33 and R of 99.8 on training data. The bagging regressor is then used to predict the fault in the WT GB, which detected the anomalous behavior of WT GB 59 days earlier than the actual failure. This model also detects the extremely unusual behavior of the GB 9 days earlier than a complete failure.

Recent advancements in Software Defined Networking (SDN) makes it possible to overcome the management challenges of traditional network by logically centralizing control plane and decoupling it from forwarding plane. Through centralized controllers, SDN can prevent security breach, but it also brings in new threats and vulnerabilities. Central controller can be a single point of failure. Hence, flow-based anomaly detection system in OpenFlow Controller can secure SDN to a great extent. In this paper, we investigated two different approaches of flow-based intrusion detection system in OpenFlow Controller. The first of which is based on machine-learning algorithm where NSL-KDD dataset with feature selection ensures the accuracy of 82% with Random Forest classifier using Gain Ratio feature selection evaluator. In the later phase, the second approach is combined with Gated Recurrent Unit Long Short-Term Memory based intrusion detection model based on Deep Neural Network (DNN) where we applied an appropriate ANOVA F-Test and Recursive Feature Elimination feature selection method to improve the classifier performance and achieved an accuracy of 88%. Substantial experiments with comparative analysis clearly show that, deep learning would be a better choice for intrusion detection in OpenFlow Controller.

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 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.}

The Smart Energy Research Lab (SERL) Observatory dataset described here comprises half-hourly and daily electricity and gas data, SERL survey data, Energy Performance Certificate (EPC) input data and 24 local hourly climate reanalysis variables from the European Centre for Medium-Range Weather Forecasts (ECMWF) for over 13,000 households in Great Britain (GB). Participants were recruited in September 2019, September 2020 and January 2021 and their smart meter data are collected from up to one year prior to sign up. Data collection will continue until at least August 2022, and longer if funding allows. Survey data relating to the dwelling, appliances, household demographics and attitudes was collected at sign up. Data are linked at the household level and UK-based academic researchers can apply for access within a secure virtual environment for research projects in the public interest. This is a data descriptor paper describing how the data was collected, the variables available and the representativeness of the sample compared to national estimates. It is intended as a guide for researchers working with or considering using the SERL Observatory dataset, or simply looking to learn more about it.

Corona virus disease (COVID-19) has infected over more than 10 million people around the globe and killed at least 500K worldwide by the end of June 2020. As this disease continues to evolve and scientists and researchers around the world now trying to find out the way to combat this disease in most effective way. Chest X-rays are widely available modality for immediate care in diagnosing COVID-19. Precise detection and diagnosis of COVID-19 from these chest X-rays would be practical for the current situation. This paper proposes one shot cluster based approach for the accurate detection of COVID-19 chest x-rays. The main objective of one shot learning (OSL) is to mimic the way humans learn in order to make classification or prediction on a wide range of similar but novel problems. The core constraint of this type of task is that the algorithm should decide on the class of a test instance after seeing just one test example. For this purpose we have experimented with widely known Generalized Regression and Probabilistic Neural Networks. Experiments conducted with publicly available chest x-ray images demonstrate that the method can detect COVID-19 accurately with high precision. The obtained results have outperformed many of the convolutional neural network based existing methods proposed in the literature.

Imitation learning, also known as programming by demonstration, has been shown to be a promising paradigm for intuitive robot programming by non-expert users. However, the classical kinesthetic approach with physical hand guidance suffers from generalizability across different robot types and is impractical for demonstrating tasks with long horizons. Visual imitation learning enables the recording of multi-step tasks as a single continuous video, allowing non-experts to demonstrate tasks naturally. Existing approaches typically require a large amount of data to develop end-to-end deep learning models that map raw pixels to robot actions. This paper explores the application of visual imitation learning from one-shot demonstration, significantly reducing the data requirements and simplifying the programming process. To achieve this target, a framework is proposed to map hand trajectories to the robot end-effector, consisting of four essential components: hand detection; object detection; segmentation of the trajectories into elemental skills; and learning the skills. Methods are developed for each component and evaluated on recorded videos to demonstrate the effectiveness of the proposed framework.

Lamb wave-based structural health monitoring is widely acknowledged as a reliable 11 method for damage identification, classification, localization and quantification. However, due to 12 the complexity of Lamb wave signals, especially after interacting with structural components and 13 defects, interpreting these waves and extracting useful information about the structure's health is 14 still a major challenge. However, deep learning-based strategy offers a great opportunity to address 15 such challenges as the algorithm can operate directly on raw discrete time-domain signals. Unlike 16 traditional methods, which often require careful feature engineering and preprocessing, deep learn-17 ing can automatically extract relevant features from the raw data. This paper proposes an autoen-18 coder based on a bidirectional long short-term memory network with maximal overlap discrete 19 wavelet transform layer to detect the signal anomaly and determine the location of the damage in 20 the composite structure. This approach has the potential to greatly enhance our ability to detect and 21 locate structural damage in composite structures, thereby increasing safety and efficiency.

In the paper the verification of forecasts of precipitation conditions measured by the standardized precipitation index SPI is presented. For the verification of categorical forecasts a contingency table was used. Standard verification measures were used for the SPI value forecast. The 30 day SPI moved every 10 days by 10 days was calculated in 2013-2015 from April to September on the basis of precipitation data from 35 meteorological stations in Poland. Predictions of the 30 day SPI were created in which precipitation was forecasted in the next 10 days (the SPI 10-day forecast) and 20 days (the SPI 20-day forecast). Both for the 10 and 20 days, the forecasts were skewed towards drier categories at the expense of wet categories. There was a good agreement between observed and 10-day forecast categories of precipitation. Less agreement is obtained for 20-day forecasts – these forecasts evidently “over-dry” the assessment of precipitation anomalies. The 10-day SPI value forecast accuracy is acceptable, whereas for the 20-day forecast is unsatisfactory. Both for the SPI categorical and the SPI value forecast, the 10-day SPI forecast is reliable and the 20-day forecast should be accepted with reservation and used with caution.

This paper presents a theoretical framework aimed at improving IoT network cybersecurity by AI-driven anomaly detection in the context of rapid urbanization and the development of smart cities. The framework draws upon the Complex Adaptive Systems Theory, Theory of Planned Behavior, the Technology Acceptance Model, and the Socio-Technical Systems Theory, and intri-cately examines how AI might be integrated into the intricate ecosystem of smart cities to detect and mitigate cyber threats. It emphasizes AI-driven anomaly detection methods as pivotal in-struments that impact cybersecurity enhancement in smart city infrastructures. The proposed framework also highlights the crucial role that human-related factors, including user behavior and adoption, play in determining how effective AI applications are in enhancing cybersecurity in smart cities. It also recognizes the important moderating roles played by outside factors like legislative frameworks, environmental contexts, and technological breakthroughs in the relationship between AI-enabled anomaly detection and enhanced cybersecurity. The goal of this research is to shed light on the interactions between technology and socio-technical dynamics by offering a thorough theoretical understanding of AI's potential in smart city cybersecurity. It highlights the significance of taking into account a variety of contextual aspects when employing AI to strengthen the digital security of urban areas, and provides a strategic direction for future research and practical implementation.

The optimal functionality and dependability of mechanical systems are important for the sustained productivity and operational reliability of industrial machinery which has direct impact on it’s longevity and profitability. Therefore, failure of a mechanical system or any of it component would be detrimental to production continuity and availability. Consequently,this study proposes a robust diagnostic framework for analyzing the blade conditions of shot blast industrial machinery. The framework involves analyzing the spectral characteristics of the vibration signals generated by Industrial Shot Blast. Additionally, a peak detection algorithms is introduced to identify and extract the unique features present in the peak magnitudes of each signal spectrum. A feature importance algorithm is then deployed as the feature selection tool, and these selected features are fed into 10 machine learning classifier, with Extreme gradient boosting (XGB) as the core classifier. Results show that the XGB classifier achieved the best accuracy of 98.05%, with a cost-efficient computational cost of 0.83 seconds. Other global assessment metrics were also implemented in the study to further validate the model.

Anomaly detection in equipment processes plays an important role in the oil and gas sector. Algorithms for detecting anomalies in measured data are best understood in computer science and mathematics. Therefore, a possible transfer of knowledge from the latter knowledge area to the former can play a significant role. This paper addresses such a task by analyzing bibliometric data of Computer Science and Mathematics papers published in MDPI journals and publications found on the SPE search platform. It is shown that the main algorithms both extensively studied in MDPI publications and found in SPE publications and reflecting the anomaly detection problem are Random Forest, Support Vector Machine, Long-term Memory Method and Recurrent Neural Network. The main advantages and disadvantages of these methods are briefly described. Examples of classical, highly cited publications describing the work of these algorithms are given. Examples of papers describing their application in the oil and gas industry are given. The sections of SPE disciplines with the largest number of publications using the above algorithms that are frequently used for anomaly detection are presented.

With the development of artificial intelligence, the ability of capturing the background characteristics of hyperspectral imagery (HSI) is improved and promising performance in hyperspectral anomaly detection (HAD) tasks is yielded. However, existing methods proposed in recent years still suffer from certain limitations: 1) constraints are lacking in the deep feature learning process in terms of the issue for absence of prior background and anomaly information. 2) hyperspectral anomaly detectors with traditional self-supervised deep learning methods fail to ensure prioritized reconstruction of the background. 3) architectures of fully connected deep network in hyperspectral anomaly detectors lead to low utilization of spatial information and destruction for original spatial relationship of hyperspectral imagery, and disregard spectral correlation between adjacent pixels. 4) hypotheses or assumptions for background and anomaly distributions restrict the performance of many hyperspectral anomaly detectors because the distributions of background land covers are usually complex and not assumable in real-world hyperspectral imagery. With the consideration of above problems, in this paper, we propose a novel fully convolutional auto-encoder based on dual clustering and latent feature adversarial consistency (FCAE-DCAC) for HAD which is carried out in a self-supervised learning-based processing. Firstly, the density-based spatial clustering of applications with noise algorithm and connected component analysis are utilized for successive spectral and spatial clustering to obtain more precise prior background and anomaly information, which facilitates the separation between background and anomaly samples during the training of our method. Subsequently, a novel fully convolutional auto-encoder (FCAE) integrated with spatial-spectral joint attention (SSJA) is proposed to enhance the utilization of spatial information and augment feature expression. In addition, a latent feature adversarial consistency network is proposed to achieve pure background reconstruction with the ability of learning actual background distribution in hyperspectral imagery. Finally, a triplet loss is introduced to enhance the separability between background and anomaly, and the reconstruction residual serves as the anomaly detection result. We evaluate the proposed method on seven groups of real-world hyperspectral datasets, and the experimental results confirmed the effectiveness and superior performance of the proposed method versus nine state-of-the-art methods.

While the importance of continuous monitoring of electrocardiographic (ECG) or photoplethysmographic (PPG) signals to detect cardiac anomalies is generally accepted in preventative medicine, there remain major barriers to its actual widespread adoption. Most notably, current approaches tend to lack real-time capability, exhibit high computational cost, and be based on restrictive modeling assumptions or require large amounts of training data. We propose a lightweight and model-free approach for the online detection of cardiac anomalies such as ectopic beats in ECG or PPG signals based on the change detection capabilities of Singular Spectrum Analysis (SSA) and nonparametric rank-based cumulative sum (CUSUM) control charts. The procedure is able to quickly detect anomalies without requiring the identification of fiducial points such as R-peaks and is computationally significantly less demanding than previously proposed SSA-based approaches. Therefore, the proposed procedure is equally well suited for standalone use and as an add-on to complement existing (e.g. heart rate (HR) estimation) procedures.

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.

In the field of 2-D image processing and computer vision, accurately detecting and segmenting objects in scenarios where they overlap or are obscured remains a challenge. This difficulty is worse in the analysis of shoeprints used in forensic investigations because they are embedded in noisy environments such as the ground and can be indistinct. Traditional Convolutional Neural Networks (CNNs), despite their success in various image analysis tasks, struggle with accurately delineating overlapping objects due to the complexity of segmenting intertwined textures and boundaries against a background of noise. This study introduces employs the YOLO (You Only Look Once) model enhanced by edge detection and image segmentation techniques to improve the detection of overlapping shoeprints. By focusing on the critical boundary information between shoeprint textures and the ground, our method demonstrates improvements in sensitivity and precision, achieving confidence levels above 85% for minimally overlapped images and maintaining above 70% for extensively overlapped instances. Heatmaps of convolution layers were generated to show how the network converges towards successful detection using these enhancements. This research may provide a potential methodology for addressing the broader challenge of detecting multiple overlapping objects against noisy backgrounds.

We have repeated the experiment performed recently by Krasznahorkay et al., (Phys. Rev. Lett. 116, 042501 (2016)), which may indicate a new particle called X17 in the literature. In order to get a reliable, and independent result, we used a different type of electron-positron pair spectrometer which have a more simple acceptance/efficiency as a function of the correlation angle, but the other conditions of the experiment were very similar to the published ones. We could confirm the presence of the anomaly measured at the Ex=18.15 MeV resonance, and also confirm their absence at the Ex=17.6 MeV resonance, and at Ep= 800 keV off resonance energies.

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.

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.

Anomaly detection and segmentation aim at distinguishing abnormal images from normal images and further localizing the anomalous regions. Feature reconstruction based method has become one of the mainstream methods for this task. This kind of method has two assumptions: (1) The features extracted by neural network is a good representation of the image. (2) The autoencoder solely trained on the features of normal images cannot reconstruct the features of anomalous regions well. But these two assumptions are hard to meet. In this paper, we propose a new anomaly segmentation method based on feature reconstruction. Our approach mainly consists of two parts: (1) We use a pretrained vision transformer (ViT) to extract the features of the input image. (2) We design a self-attention autoencoder to reconstruct the features. We regard that the self-attention operation which has a global receptive field is beneficial to the methods based on feature reconstruction both in feature extraction and reconstruction. The experiments show that our method outperforms the state-of-the-art approaches for anomaly segmentation on the MVTec dataset. It is both effective and time-efficient.

Much of the debate on Plan S seems to concentrate on how to make toll access journals open access, taking for granted that existing open access journals are Plan S compliant. We suspected this was not so, and set out to explore this using DOAJ's journal metadata. We conclude that an overwhelmingly large majority of open access journals are not Plan S compliant, and that it is small HSS publishers not charging APCs that are least compliant and will face major challenges with becoming compliant. Plan S need to give special considerations to smaller publishers and/or non-APC-based journals.

Relatively little research attention has been paid to sex issues in late life suicidal behaviour. The aim was to compare clinical characteristics of women and men aged 70+ who were hospitalized after a suicide attempt. We hypothesized higher depression and anxiety scores in women, and we expected to find that men would more often attribute the attempt to health problems and compromised autonomy. Participants (56 women and 47 men, mean age 80) were interviewed by a psychologist. In addition to psychiatric and somatic health assessments, participants responded to an open-ended question concerning attributions of the attempt. There were no sex differences in depression and anxiety, but women were more likely to report that they found their situation hopeless (67.9% vs. 43.8%, p = 0.02). At least one serious physical disability was noted in 60.7% of the women and 53.2% of the men (p = 0.55). Proportions attributing their attempt to somatic illness did not differ (women, 14.5% vs. men 17.4%, p = 0.79), and similar proportions attributed the attempt to reduced autonomy (women, 21.8% vs. men, 26.1 %, p = 0.64). The unexpected lack of sex differences might be influenced by cultural context in which sex norms play a part.

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.

Predicting anomalies in manufacturing assembly lines is crucial for reducing time and labor costs and improving processes. For instance, in rocket assembly, premature part failures can lead to significant financial losses and labor inefficiencies. With the abundance of sensor data in the Industry 4.0 era, machine learning (ML) offers potential for early anomaly detection. However, current ML methods for anomaly prediction have limitations, with F1-measure scores of only 50% and 66% for prediction and detection, respectively. This is due to challenges like the rarity of anomalous events, scarcity of high-fidelity simulation data (actual data is expensive), and the complex relationships between anomalies not easily captured by traditional ML approaches. Specifically, these challenges relate to two dimensions of anomaly prediction: predicting when anomalies will occur and understanding the dependencies between them. This paper introduces a new method called Robust and Interpretable 2D Anomaly Prediction (RI2AP) designed to address both dimensions effectively. RI2AP is demonstrated on a rocket assembly simulation, showing up to a 30-point improvement in F1 measure compared to current ML methods. This highlights its potential to enhance automated anomaly prediction in manufacturing. Additionally, RI2AP includes a novel interpretation mechanism inspired by a causal-influence framework, providing domain experts with valuable insights into sensor readings and their impact on predictions. Finally, the RI2AP model is deployed in a real manufacturing setting for assembling rocket parts. Results and insights from this deployment demonstrate the promise of RI2AP for anomaly prediction in manufacturing assembly pipelines.

Glaucoma secondary to Peters' anomaly (PA) is an important factor affecting visual prognosis, but there are few reports on it. This study aimed to investigate the characteristics of glaucoma asso-ciated with PA and glaucoma surgery outcomes. This retrospective study included 31 eyes of 20 patients with PA. PA was classified into three stages: Stage 1, with a posterior corneal defect only; Stage 2, a corneal defect with iridocorneal adhesion; and Stage 3, a corneal defect with lens ab-normalities. The associations between glaucoma and anterior segment dysgenesis severity, visual prognosis, and glaucoma surgery outcomes were analyzed. Sixteen eyes of 10 patients developed glaucoma. Stage 1 PA had no glaucoma, 52% of Stage 2 had glaucoma, and 75% of Stage 3 had glaucoma. Of the 16 eyes with glaucoma, 11 underwent surgery. Eight of these 11 eyes achieved intraocular pressure (IOP) control. Five of the nine eyes that underwent trabeculotomy (TLO) succeeded, and none had corneal staphyloma. Three of the four eyes for which TLO was ineffective had corneal staphyloma (P=0.0331). Patients with PA are more likely to develop glaucoma as anterior segment dysgenesis progresses, and the effect of TLO is limited if corneal staphyloma is present.

The properties of the dark matter, dark energy, graviton and photon are discussed in terms of the new three-dimensional quantized space model. Three new particles (bastons) with the electric charges (EC) are proposed as the dark matters. It is proposed that the EC, LC and CC charges are aligned along the time axes but not along the space axes. The photon is confined on its corresponding three-dimensional quantized space. However, the graviton can be evaporated into other three-dimensional quantized spaces. The rest mass of the electron neutrino (n_e) of 3.494·10⁻³ eV/c² is obtained from the experimental vacuum energy density in terms of quantum field theory (QFT). The rest mass and force range of the massive g(0,0,0) graviton with the Planck size are m_g = 3.1872·10⁻³¹ eV/c² and x_r = 3.0955·10²³ m = 10.0 Mpc, respectively, based on the experimental rest mass and rms charge radius of the proton. The possible diameter (10 Mpc) of the largest galaxy cluster is remarkably consistent with the gravitational force range (10 Mpc). Then, the diameter of the largest dark matter distribution related to the largest galaxy cluster is 9.2865·10²³ m = 30 Mpc equal to the force range of the massive g(0) graviton with the rest mass of 1.0624·10⁻³¹ eV/c². Because of the huge number (N) of the evaporated gravitons, the very small Coulomb’s constant of about 10⁻⁴⁸k and large gravitation constant of 10⁶G_N are expected for the charged dark matters. Therefore, F_c(mm) > F_g(dd) > F_g(mm) > F_g(dm) > F_c(dd) > F_c(dm) = 0 for the proton-like particle. The proposed weak gravitational force between the dark matters and normal matters explains the observed dark matter distributions of the bullet cluster, Abell 1689 cluster and Abell 520 cluster. The transition from the galaxy without the dark matters to the galaxy with the dark matters are explained. Also, the accelerated space expansion is caused by the new space quanta created by the evaporated gravitons into the x1x2x3 space and repulsive electromagnetic force between dark matters corresponding to the dark energy. The decreasing coupling constant of the strong force, neutron lifetime anomaly and the pressure distribution inside the proton are explained by the unobservable proton and hadronization. And the rest mass of 1.4 TeV/c² is assigned to the Le particle with the EC charge of −2e. The proposed rest mass (26.12 eV/c²) of the B1 dark matter is indirectly confirmed from the supernova 1987A data. Also, the gravitation constant has been changing with the time because of the graviton evaporation.

The paper presents an analysis of the latest developments in the field of stereo vision in the low-cost segment, both for prototypes and for industrial designs. We described the theory of stereo vision and presented information about cameras and data transfer protocols and their compatibility with various devices. The theory in the field of image processing for stereo vision processes is considered and the calibration process is described in detail. Ultimately, we presented the developed stereo vision system and provided the main points that need to be considered when developing such systems. The final, we presented software for adjusting stereo vision parameters in real-time in the python language in the Windows operating system.

We fabricate large-area atomically thin MoS₂ layers through the direct transformation of crystalline molybdenum trioxide (MoO₃) by sulfurization at relatively low temperatures. The obtained MoS₂ sheets are polycrystalline (~10-20 nm single-crystal domain size) with areas of up to 300×300 µm² with 2-4 layers in thickness and show a marked p-type behaviour. The synthesized films are characterized by a combination of complementary techniques: Raman spectroscopy, X-ray diffraction, transmission electron microscopy and electronic transport measurements.

Automating pruning tasks entails overcoming several challenges, encompassing not only robotic manipulation but also environment perception and detection. To achieve efficient pruning, robotic systems must accurately identify the correct cutting points. A possible method to define these points is to choose the cutting location based on the number of nodes present on the targeted cane. For this purpose, in grapevine pruning, it is required to correctly identify the nodes present on the primary canes of the grapevines. In this paper, a novel method of node detection in grapevines is proposed with four distinct state-of-the-art versions of the YOLO detection model: YOLOv7, YOLOv8, YOLOv9 and YOLOv10. These models were trained on a public dataset with images containing artificial backgrounds and afterwards validated on different cultivars of grapevines from two distinct Portuguese viticulture regions with cluttered backgrounds. This allowed to evaluate the robustness of the algorithms on the detection of nodes in diverse environments, compare the performance of the YOLO models used, as well as create a publicly available dataset of grapevines obtained in Portuguese vineyards for node detection. Overall, all used models were capable of achieving correct node detection on images of grapevines from the three distinct datasets. Considering the trade-off between accuracy and inference speed, the YOLOv7 model demonstrated to be the most robust in detecting nodes in 2D images of grapevines, achieving F1-Score values between 70 % and 86.5 % with inference times of around 89 ms for an input size of 1280×1280 px. Considering these results, this work contributes with an efficient approach for real-time node detection for further implementation on an autonomous robotic pruning system.

Background: Ice formation on power transmission lines presents significant risks, including structural damage and power outages. Traditional methods for detecting ice on these lines have limitations, particularly in challenging environmental conditions. This study aims to enhance ice detection accuracy by introducing a novel image segmentation and edge detection methodology using improved multi-scale Retinex and advanced morphological operations. Method: The proposed method integrates multi-stage image processing techniques, including image enhancement, grayscale conversion, thresholding, segmentation, object isolation, and edge detection. High-resolution binocular cameras were used to capture images of ice formations on transmission lines. The effectiveness of the method was assessed through a series of metrics, including accuracy, sensitivity, specificity, and precision, and compared with existing methodologies. Results: The proposed method demonstrated superior performance in both ice detection and thickness measurement. The method effectively identified and isolated ice formations under various conditions with an average accuracy of 98.35%, sensitivity of 91.63%, specificity of 99.42%, and precision of 96.03%. Additionally, the analysis of ice thickness measurements further highlighted the method’s accuracy, with a notably low root mean squared error (RMSE) of 1.20 mm and mean absolute error (MAE) of 1.10 mm, along with a strong R-squared value of 0.95. These statistical metrics show that the proposed method not only outperforms previous methods in consistency and alignment with manual measurements but also stands out as the most reliable option for tasks requiring precise measurements, offering significant advancements in accuracy and reliability over existing methodologies. Conclusions: The enhanced image segmentation and edge detection approach provides a more accurate and reliable method for monitoring ice formations on power transmission lines.

This paper presents a novel approach to predicting shot accuracy in badminton by analyzing Quiet Eye (QE) metrics such as QE duration, fixation points, and gaze dynamics. We develop a neural network model that combines visual data from eye-tracking devices with biomechanical data such as body posture and shuttlecock trajectory. Our model is designed to predict shot accuracy, providing insights into the role of QE in performance. The study involved 30 badminton players of varying skill levels from the Singapore Swimming Club. Using a combination of eye-tracking technology and motion capture systems, we collected data on QE metrics and biomechanical factors during a series of badminton shots. Key results include: 1. The neural network model achieved 85% accuracy in predicting shot outcomes, demonstrating the potential of integrating QE metrics with biomechanical data. 2. QE duration and onset were identified as the most significant predictors of shot accuracy, followed by racket speed and wrist angle at impact. 3. Elite players exhibited significantly longer QE durations (M = 289.5 ms) compared to intermediate (M = 213.7 ms) and novice players (M = 168.3 ms). 4. A strong positive correlation (r = 0.72) was found between QE duration and shot accuracy across all skill levels. These findings have important implications for badminton training and performance evaluation. The study suggests that QE-based training programs could significantly enhance players' shot accuracy. Furthermore, the predictive model developed in this study offers a framework for real-time performance analysis and personalized training regimens in badminton. By bridging cognitive neuroscience and sports performance through advanced data analytics, this research paves the way for more sophisticated, individualized training approaches in badminton and potentially other fast-paced sports. Future research directions include exploring the temporal dynamics of QE during matches and developing real-time feedback systems based on QE metrics.

The growing expansion of the economy and population has resulted in an increased inclination towards the utilization of groundwater resources. Conducting a geophysical survey is a widely employed method for subsurface mapping and the detection of groundwater. A geophysical study was conducted in Nanshan township, Huarong County, located in the Hunan province of the South-Central region of China. The investigation involved the utilization of a 2D Electrical Resistivity Imaging technique employing forward and inverse pole-dipole electrode array. A total of six survey lines were established, each with an electrode distance from the nearest measuring point to exceeding 800 m. The maximum current electrode separation was utilized in this setup. The spacing between the electrical resistivity sounding points was established at regular intervals. The findings from the exploration indicate the existence of multiple faults within the surveyed region. The study additionally identified two regions of structural failure, which occurred due to the convergence of faults oriented in different directions. This convergence led to the fracturing of rocks, an increase in water content, and a decrease in resistivity. The findings from the exploration were utilized in the formulation of five verification target boreholes. The results of this study offer significant insights that can inform future investigations into groundwater exploration endeavors within the region.

Detecting small objects in images poses significant challenges due to their limited pixel representation and the difficulty in extracting sufficient features, often leading to missed or false detections. To address these challenges and enhance detection accuracy, this paper presents an improved small object detection algorithm, CRL-YOLOv5. The proposed approach integrates the CBAM attention mechanism into the C3 module of the backbone network, which enhances the localization accuracy of small objects. Additionally, the Receptive Field Block (RFB) module is introduced to expand the model's receptive field, thereby fully leveraging contextual information. Furthermore, the network architecture is restructured to include an additional detection layer specifically for small objects, allowing for deeper feature extraction from shallow layers. When tested on the VisDrone2019 small object dataset, CRL-YOLOv5 achieved an mAP50 of 39.2%, representing a 5.4% improvement over the original YOLOv5, effectively boosting the detection precision for small objects in images.

There are many applications of anomaly detection in IoT domain. IoT technology consists of large number of interconnecting digital devices not only generating huge data continuously but also making real-time computations. Since IoT devices are highly exposed due to Internet, they frequently meet with the challenges of illegitimate accesses in the form of intrusions, anomaly, fraud, etc. Identifying these illegitimate accesses in IoT domain can be an exciting research problem. In numerous applications fuzzy clustering and rough set theory have been successfully employed. As the data generated in IoT domains are high-dimensional, the clustering methods used for lower dimensional data cannot be applied efficiently. In this article, mixed approaches consisting of nano topology and fuzzy clustering techniques are proposed for anomaly detection. First of all, the nano topology is generated to find lower dimensional apace and then a couple of well-known fuzzy clustering techniques are employed on it for the efficient anomaly detection. The effectiveness of the proposed approaches is evaluated using time-complexity analysis, experimental studies with a synthetic dataset and a real-life dataset along with comparative studies with traditional fuzzy clustering approaches namely fuzzy c-means clustering (FCM) algorithm, Gustafson-Kessel (GK) Algorithm, Gath-Geva (GG) Algorithm, Mahalanobis Distance based Fuzzy C-Means algorithm (M-FCM), and Common Mahalanobis Distance based Fuzzy C-Means algorithm (CM-FCM). Experimentally, it has been found that the proposed approaches outperform the aforesaid algorithms in terms of detection rates, accuracy rates, false alarm rates and computational times.

Log collection and storage is a crucial process for enterprises around the globe. Log analysis helps identify potential security breaches and, in some cases, is required by law for compliance. However, enterprises often delegate these responsibilities to third-party Cloud Service Providers (CSPs), where the logs are collected and processed for anomaly detection and stored in a data warehouse for archiving. Prevalent schemes rely on plain (unencrypted) data for anomaly detection. More often, these logs can reveal sensitive information about an organization or the customers of that organization. Hence, it is best to keep it encrypted at all times. This paper presents "SigML++," an extension of work done in "SigML." We utilize Fully Homomorphic Encryption (FHE) with the Cheon-Kim-Kim-Song (CKKS) scheme for supervised log anomaly detection on encrypted data. We use an Artificial Neural Network (ANN) based probabilistic polynomial approximations using a Perceptron with linear activation. We probabilistically approximate the Sigmoid activation function (σ(x)) in the encrypted domain for the intervals [−10,10] and [−50,50]. Experiments show better approximations for Logistic Regression (LR) and Support Vector Machine (SVM) for low-order polynomials.

The focus of this work lies in the construction of monitoring system designed in the form of a patch using a long-lasting potentiometric electrolyte concentration sensor from metal electrodes, in a galvanic cell configuration Mg(s)|NaCl(aq)|Cu(s). Initially, a mathematical analysis was conducted on the expected sensor output through the Nernst equation. The experimental phase involved conducting controlled tests in the laboratory using various molar concentrations of sodium chloride (NaCl) in aqueous solution. Results showed that the electrolyte sensor allows for monitoring electrolyte levels in NaCl in the range of 0.02 to 1 M/L, with electrode lifespan exceeding 10 days. On the other hand, when patch is using human sweat during controlled exercise routines, it showed the sensor's capability for monitoring changes in the subjects' hydration levels in real time. The sensor output potential is greater than 1.7 volts when the sensor electrodes are in contact with human sweat, which is equivalent to measuring molar concentrations at normal hydration and moderately high hydration levels. Sensor results indicate that the system can function in a self-powered manner without external batteries. Additionally, the extended lifespan of its electrodes allows for continuous monitoring of imbalances in the human body, showcasing the system capability for long-term health assessment.

The research field of two dimensional (2D) materials strongly relies on optical microscopy characterization tools to identify atomically thin materials and to determine their number of layers. Moreover, optical microscopy-based techniques also opened the door to study the optical properties of these nanomaterials. We present a comprehensive study of the differential reflectance spectra of 2D semiconducting transition metal dichalcogenides (TMDCs), MoS₂, MoSe₂, WS₂ and WSe₂, with thickness ranging from one layer up to six layers. We analyze the thickness-dependent energy of the different excitonic features, indicating the change in the band structure of the different TMDC materials with the number of layers. Our work provides a route to employ differential reflectance spectroscopy for determining the number of layers of MoS₂, MoSe₂, WS₂ and WSe₂.

All types of sports are potential application scenarios for automatic and real-time visual object and event detection. In rink hockey, the popular roller quad skate variant of hockey team sports, it is of great interest to automatically track player’s movements and positions, player’s sticks and, also, making other judgments, such as being able to locate the ball. In this work, we introduce a real-time pipeline composed by an object detection model, created specifically for rink hockey games, followed by a knowledge-based event detection module. Even in the presence of occlusions and quick motions, our deep learning object detection model effectively identifies and tracks, in real-time, important visual elements such as: ball; players; sticks; referees; crowd; goalkeeper; and goal. Using a curated dataset composed by a collection of videos of rink hockey, comprising 2525 annotated frames, we trained and evaluated the algorithm performance and compare it to state of the art object detection techniques. Our object detection model, based on YOLOv7, presents a global accuracy of 80%, and presents a good performance in terms of accuracy and speed, according to our results, making it a good choice for rink hockey applications. In our initial tests, the event detection module successfully detected one important event type in rink hockey games, the occurrence of penalties.