Synthetic Aperture Radar (SAR) ship target detection has been extensively researched. However, most methods use the same dataset division for both training and validation. In practical applications, it is often necessary to quickly adapt to new loads, new modes, and new data to detect targets effectively. This presents a cross-domain detection problem that requires further study. This paper proposes a method for detecting SAR ships in complex backgrounds using fusion tensor and cross-domain adversarial learning. The method is designed to address the cross-domain detection problem of SAR ships with large differences between the training and test sets. Specifically, it can be used for the cross-domain detection task from the fully-polarised medium-resolution ship dataset (source domain) to the high-resolution single-polarised dataset (target domain). This method proposes a Channel Fusion Module (CFM) based on the YOLOV5s model. The CFM utilises the correlation between polarised channel images during training to enrich the feature information of single-polarised images extracted by the model during inference. The article proposes a module called Cross-Domain Adversarial Learning Module (CALM) to reduce overfitting and achieve adaptation between domains. Additionally, the paper introduces the Anti-Interference Head (AIH) which decouples the detection head to reduce the conflict of classification and localization problems. This improves the anti-interference and generalization ability in complex backgrounds. This paper conducts cross-domain experiments using the constructed medium-resolution SAR full polarization dataset (SFPD) as the source domain and the high-resolution single-polarised ship detection dataset (HRSID) as the target domain. Compared to the best-performing YOLOV8s model among typical mainstream models, this model improves Precision by 4.9%, Recall by 3.3%, AP by 2.4%, and F1 by 3.9%. This verifies the effectiveness of the method and provides a useful reference for improving cross-domain learning and model generalization capability in the field of target detection.

Keywords: domain adversarial; channel reconstruction; transfer learning; fault diagnosis

With the rapid development of Internet and the widely usage of smart devices, massive multimedia data are generated, collected, stored and shared on the Internet. This trend makes cross-modal retrieval problem become a hot issue in this years. Many existing works pay attentions on correlation learning to generate a common subspace for cross-modal correlation measurement, and others uses adversarial learning technique to abate the heterogeneity of multi-modal data. However, very few works combine correlation learning and adversarial learning to bridge the inter-modal semantic gap and diminish cross-modal heterogeneity. This paper propose a novel cross-modal retrieval method, named ALSCOR, which is an end-to-end framework to integrate cross-modal representation learning, correlation learning and adversarial. CCA model, accompanied by two representation model, VisNet and TxtNet is proposed to capture non-linear correlation. Beside, intra-modal classifier and modality classifier are used to learn intra-modal discrimination and minimize the inter-modal heterogeneity. Comprehensive experiments are conducted on three benchmark datasets. The results demonstrate that the proposed ALSCOR has better performance than the state-of-the-arts.

Many fundamental molecular techniques (PCR, Microarray, Southern and northern hybridization, siRNA, CRISPR/Cas9 etc.) developed so far shows errors. I wish to highlight these molecular techniques are developed on basis of Watson-Crick DNA model, ignoring the concept of parallel stranded DNA. Through this opinion article, I wish to highlight specificity and accuracy of these molecular techniques can be enhanced by considering both parallel and anti parallel hybridization of DNA. Hopefully my views will also solve issue of irreproducibility in life science research.

Background: The effect of velamentous cord insertion (VCI) on perinatal outcomes in twin pregnancies is unclear due to conflicting findings. This retrospective study aimed to examine VCI prevalence and related risk factors in twin pregnancies and its association with adverse perinatal outcomes. Methods: Women with twin pregnancies who delivered between January 2012 and December 2021 in a single tertiary hospital were included. The participants were divided into dichorionic (DC) and monochorionic diamniotic (MCDA) groups, and their maternal and fetal characteristics and VCI rates were compared. Logistic regression models were used to identify risk factors for VCI and VCI-related perinatal outcomes. Results: Among the 694 twin pregnancies included in this study, the VCI rate was significantly higher in MCDA than in DC twins. Body mass index and MCDA twins were significant risk factors for VCI, whereas assisted reproductive technology pregnancy was a significant protective factor against VCI. In DC twins, VCI did not affect perinatal outcomes. Conclusion: In MCDA twins, VCI was a significant risk factor for fetal growth restriction, twin-to-twin transfusion syndrome, and preterm birth at

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

Background. The Stanford Health Assessment Questionnaire-Disability Index (HAQ) is widely used to measure functional ability in persons with Rheumatoid Arthritis (RA). The instrument was developed with limited involvement from persons with RA, and their perception of the instrument has not been studied in depth. The aim of this study was to explore how persons with RA experience the use of the HAQ in care. Methods. Forty persons with RA were purposefully recruited to participate in semi-structured interviews. The interviews were then analyzed qualitatively using thematic analysis. Results. The participants questioned the relevance of the HAQ but nevertheless experienced that the instrument had a profound effect on their understanding of health and how care is delivered. The analysis resulted in three themes: Problems with individual items, meaning of the summative score, and effects on care and health perceptions. Conclusions. To make the HAQ relevant to persons with RA, it needs to be revised or to include an option to select items most meaningful to the respondent. To ensure relevance, the HAQ update should preferably be co-created by researchers, clinicians and persons with RA.

Background Community infections of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) have increased rapidly since the emergence of the Omicron strain. During the eighth and ninth pandemic waves—when movement restrictions in the community were eased—the all-case registration system was changed, and the actual status of infection became uncertain. Methods We conducted regular rapid antigen tests (R-RAT) once or twice a week to examine the actual state of coronavirus disease (COVID-19) diagnosis among healthcare employees. Results Overall, 320 (1.42/day) and 299 (1.76/day) employees were infected in the eighth and ninth pandemic waves. During both periods, 59/263 doctors (22.4%), 335/806 nurses (41.6%), 92/194 administrative employees (47.4%), and 129/218 clinical laboratory technicians (59.2%) were infected. In the eighth wave, 56 of 195 employees were infected through close contact; in the ninth wave, 26 of 62 employees were infected. No significant difference was observed in the number of vaccinations between infected and non-infected employees. The positivity rate of R-RAT was 0.41% and 0.45% in the eighth and ninth waves. R-RAT detected infection in 212 and 229 employees during the eighth and ninth waves, respectively; the ratio of R-RAT-detected positive employees to those who reported infection was significantly higher during the ninth wave (odds ratio: 1.67, 95% confidence interval: 1.17–2.37, p

The present grievous situation of the tuberculosis disease can be improved by efficient case management and timely follow-up evaluations. With the advent of digital technology this can be achieved by quick summarization of the patient-centric data. The aim of our study was to assess the effectiveness of the ODK Scan paper-to-digital system during testing period of three months. A sequential, explanatory mixed-method research approach was employed to elucidate technology use. Training, smartphones, application and 3G enabled SIMs were provided to the four field workers. At the beginning, baseline measures of the data management aspects were recorded and compared with endline measures to see the impact of ODK Scan. Additionally, at the end, users’ feedback was collected regarding app usability, user interface design and workflow changes. 122 patients’ records were retrieved from the server and analysed for quality. It was found that ODK Scan recognized 99.2% of multiple choice bubble responses and 79.4% of numerical digit responses correctly. However, the overall quality of the digital data was decreased in comparison to manually entered data. Using ODK Scan, a significant time reduction is observed in data aggregation and data transfer activities, however, data verification and form filling activities took more time. Interviews revealed that field workers saw value in using ODK Scan, however, they were more concerned about the time consuming aspects of the use of ODK Scan. Therefore, it is concluded that minimal disturbance in the existing workflow, continuous feedback and value additions are the important considerations for the implementing organization to ensure technology adoption and workflow improvements.

Macrophages as a source and target of GDF-15

This research presents the Cross-Cultural Intelligent Language Learning System (CILS), a novel approach integrating Artificial Intelligence (AI) into language education to enhance cross-cultural communication. CILS utilizes advanced AI technologies to provide adaptive, personalized learning experiences that cater to the unique linguistic and cultural backgrounds of each learner. By dynamically adjusting content and methodology, CILS significantly improves linguistic proficiency and cultural understanding, essential for effective global interactions. The implementation of CILS in platforms such as Busuu and HelloTalk has demonstrated marked improvements in engagement and communication skills among learners. Empirical studies validate the system's effectiveness in real-world settings, showing enhanced learner performance and increased intercultural competence. Additionally, the Technology Acceptance Model (TAM) applied confirms that the usability and perceived usefulness of AI-driven systems strongly influence learner acceptance and sustained use. This study not only underscores the potential of AI in transforming language education but also highlights the critical role of cultural sensitivity in designing educational technologies.

This research investigates the application of Fused Filament Fabrication (FFF) in producing WC-10Co hardmetals, focusing binder formulations and understanding its influence on extrusion force and the influence of printing variables on green density of the samples. By examining the interplay between different binder compositions and backbone contents, the study aims to enhance the mechanical properties of the sintered parts while reducing defects inherent in the printing process. Evidence suggested that formulated feedstocks influenced the hardness of the sintered hardmetal, not due to microstructural changes but to macrostructural responses like macro defects introduced during printing, debinding and sintering of the samples. The results demonstrate the critical role of PP-MA content in improving part density and sintered hardness, suggesting the need for specific thermal debinding protocols tailored to each feedstock. The study provides insights into the formulation of feedstocks for hardmetal FFF, proposing a path toward refining manufacturing processes for better quality and performance of 3D printed hardmetal components.

This study examines the contribution of early executive functions (EFs) in the association between fluency in reading and arithmetic. Kindergarten children (N = 1,185) were assessed on Executive Functions skills and on reading and arithmetic fluency in Grade 1 and Grade 3. The analysis revealed that beyond the connection within each domain there is a unidirectional effect between fluency measures, with Grade 1 reading fluency significantly influencing the development of arithmetic fluency in Grade 3. Furthermore, the findings indicate that kindergarten EFs significantly contribute to arithmetic fluency at both time points and to reading fluency in the first grade. Early EF skills also emerged as a mediator of associations between fluency performance in reading and arithmetic, suggesting that the influence of EFs extends beyond individual academic domains. These findings have implications for understanding the cognitive mechanisms that underlie the relations between these academic skills.

The lack of defect image data is one of the main factors affecting the accuracy of supervised deep learning-based defect detection models. In response to the insufficient training data of defect images with complex backgrounds such as rust and surface oil leakage in substation equipment, leading to poor performance of the detection model, this paper proposed a novel adversarial deep learning model for substation defect generation: ADD-GAN. In comparison to existing generative adversarial networks, this model generates defect images based on effectively segmented local areas of substation equipment images, avoiding image distortion caused by global style changes. Additionally, the model utilizes a joint discriminator for overall image and defect image to address the issue of low attention to local defect areas, thereby improving the loss of image features. This enhances the overall quality of generated images as well as locally generated defect images, ultimately improving image realism. Experimental results demonstrate that the YOLOV7 object detection model trained on the dataset generated using the ADD-GAN method achieves an mAP of 81.5% on the test dataset, representing an improvement of 9.6% over the original dataset, 5.7% over traditional augmentation methods, and 7% over typical adversarial deep learning methods. This confirms that the ADD-GAN method can generate a high-fidelity dataset of substation equipment defects.

Bartonella species, intracellular parasitic zoonotic pathogens, has drawn increasing attention for their diverse host range and associated human diseases. This study investigates Bartonella infection in small mammals in Yunnan Province, China, focusing on tissue tropism. 333 small mammals were sampled from 13 species, 3 orders, 4 families, and 4 genera in Heqing and Gongshan Counties. Conventional PCR and real-time quantitative PCR (qPCR) were utilized for detection and quantification, followed by bioinformatic analysis of obtained DNA sequences. Results show a 31.5% detection rate, varying across species. Notably, Apodemus chevrieri, Eothenomys eleusis, Niviventer fulvescens, Rattus tanezumi, Episoriculus leucops, Anourosorex squamipes, and Ochotona Thibetana exhibited infection rates of 44.4%, 27.7%, 100.0%, 6.3%, 60.0%, 23.5%, and 22.2%, respectively. Genetic analysis identified 30, 10, and 5 strains based on ssrA, rpoB, and gltA genes, with nucleotide identities ranging from 92.1% to 100.0%. Bartonella strains were assigned to B. grahamii, B. rochalimae, B. sendai, B. koshimizu, B. phoceensis, B. taylorii, and a new species identified in the Episoriculus leucops (GS136). Tissue distribution analysis revealed varied copy numbers across different tissues, with the highest load in spleen. These findings underscore Bartonella's diverse species and host range in Yunnan Province, highlighting its broad tissue tropism in small mammals.

Machine learning (ML) systems that use sensors obtain observations from sensors and use them to recognize and interpret the current situation. These systems are susceptible to sensor-based adversarial example attacks (AEs); if some sensors are vulnerable and can be compromised by an attacker, the attacker can change the output of the system by changing the values of the sensors. The detection of compromised sensors is important to defend the system against sensor-based AEs, because we can check the sensors and replace them by detecting the sensors used by the attacker. In this paper, we propose a method to detect the sensors used in sensor-based AEs by utilizing the features of the attack that cannot be avoided. In this method, we introduced a model called the feature-removable model (FRM), which allows us to select the features used as inputs into the model. Our method detects the sensors used in sensor-based AEs by finding the inconsistencies between the outputs of the FRM obtained by changing the selected features. We evaluated our method using a human activity recognition model with sensors attached to the user’s chest, wrist, and ankle. We demonstrate that our method can accurately detect sensors used by the attacker and achieves an average Recall of Detection of 0.92, and the average Precision of Detection is 0.72.

Segmentation is an important step in medical imaging. In particular, machine learning, especially deep learning, has been widely used to efficiently improve and speed up the segmentation process in clinical practice. Despite the acceptable segmentation results of multi-stage models, little attention was paid to the use of deep learning algorithms for brain image segmentation, which could be due to the lack of training data. Therefore, in this paper, we propose a Generative Adversarial Network (GAN) model that performs transfer learning to segment MRI brain images.Our model enables the generation of more labeled brain images from existing labeled and unlabeled images. Our segmentation targets brain tissue images, including white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). We evaluate the performance of our GAN model using a commonly used evaluation metric, which is Dice Coefficient (DC). Our experimental results reveal that our proposed model significantly improves segmentation results compared to the standard GAN model. We observe that our model is 2.1–10.83 minutes faster than stat-of-the-art-models.

Zanthoxylum armatum is an forest tree with apomixis characteristic, and RWP-RKs are plant-specific transcription factors known to regulate nitrogen response and embryonic development. However, the genome-wide analysis of RWP-RK family genes in Z.armatum is unclear. In this study, 36 ZaRWP-RK transcription factors were identified in the genome of Z.armatum, among which 15 genes were belonged to the RKD subfamily and 21 belonged to the NLP subfamily. Duplication events of ZaRWP-RK genes were mainly segmental duplication, and synteny analysis revealed close phylogenetic relationship between Z.armatum and Arabidopsis. The analysis of cis-elements indicated that ZaRWP-RK genes may be involved in the regulation of embryonic development of Z.armatum by responding to plant hormones such as abscisic acid, auxin, and gibberellin. Real-time PCR showed that the expression levels of most ZaRWP-RK genes were significantly increased from flowers to young fruits. Protein-protein interaction network analysis further revealed the potential roles of the ZaRWP-RK proteins in apomixis. Collectively, this study provide a theoretical basis for future investigations into the ZaRWP-RK genes and their regulatory mechanisms in the apomixis process of Z.armatum.

Data sets for medical images are generally imbalanced and limited in sample size because of high data collection costs, time-consuming annotations, and patient privacy concerns. The training of deep neural network classification models on these data sets to improve the generalization ability does not produce the desired results for classifying the medical condition accurately and often overfit the data on the majority of class samples. To address the issue, we propose a framework for improving the classification performance metrics of deep neural network classification models using transfer learning: pre-trained models, such as Xception, InceptionResNet, DenseNet along with the Generative Adversarial Network (GAN) – based data augmentation. Then, we trained the network by combining traditional data augmentation techniques, such as randomly flipping the image left to right and GAN-based data augmentation, and then fine-tuned the hyper-parameters of the transfer learning models, such as the learning rate, batch size, and the number of epochs. With these configurations, the Xception model outperformed all other pre-trained models achieving a test accuracy of 98.7%, the precision of 99%, recall of 99.3%, f1-score of 99.1%, receiver operating characteristic (ROC) - area under the curve (AUC) of 98.2%.

Intelligent fault diagnosis techniques have replaced the time-consuming and unreliable human analysis, increasing the efficiency of fault diagnosis. Deep learning model can improve the accuracy of intelligent fault diagnosis with the help of its multilayer nonlinear mapping ability. This paper has proposed a novel method named Deep Convolutional Neural Networks with Wide First-layer Kernels (WDCNN). The proposed method uses raw vibration signals as input (data augmentation is used to generate more inputs), and uses the wide kernels in first convolutional layer for extracting feature and suppressing high frequency noise. Small convolutional kernels in the preceding layers are used for multilayer nonlinear mapping. AdaBN is implemented to improve the domain adaptation ability of the model. The proposed model addresses the problem that currently, the accuracy of CNN applied to fault diagnosis is not very high. WDCNN can not only achieve 100% classification accuracy on normal signals, but also outperform state of the art DNN model which is based on frequency features under different working load and noisy environment.

Due to the rising dependency on digital technology, cybersecurity has emerged as a more prominent field of research and application that typically focuses on securing devices, networks, systems, data and other resources from various cyber-attacks, threats, risks, damages, or unauthorized access. Artificial Intelligence (AI), also referred to as a crucial technology of the current Fourth Industrial Revolution (Industry 4.0 or 4IR), could be the key to intelligently dealing with these cyber issues. Various forms of AI methodologies, such as analytical, functional, interactive, textual as well as visual AI can be employed to get the desired cyber solutions according to their computational capabilities. However, the dynamic nature and complexity of real-world situations and data gathered from various cyber sources make it challenging nowadays to build an effective AI-based security model. Moreover, defending robustly against adversarial attacks is still an open question in the area. In this paper, we provide a comprehensive view on "Cybersecurity Intelligence and Robustness", emphasizing multi-aspects AI-based modeling and adversarial learning that could lead to addressing diverse issues in various cyber applications areas such as detecting malware or intrusions, zero-day attacks, phishing, data breach, cyberbullying and other cybercrimes. Thus the eventual security modeling process could be automated, intelligent, and robust compared to traditional security systems. We also emphasize and draw attention to the future aspects of cybersecurity intelligence and robustness along with the research direction within the context of our study. Overall, our goal is not only to explore AI-based modeling and pertinent methodologies but also to focus on the resulting model's applicability for securing our digital systems and society.

Fine-tuning is an important technique in transfer learning that has achieved significant success in tasks that lack training data. However, as it is difficult to extract effective features for single-source domain fine-tuning when the data distribution difference between the source and the target domain is large, we propose a transfer learning framework based on multi-source domain called adaptive multi-source domain collaborative fine-tuning to address this issue. This approach utilizes multiple source domain models for collaborative fine-tuning, thereby improving the model's feature extraction capability in the target task. Specifically, this approach employs an adaptive multi-source domain layer selection strategy to customize appropriate layer fine-tuning schemes for the target task among multiple source domain models. The objective is to extract more efficient features. Furthermore, a novel multi-source domain collaborative loss function is designed to facilitate the precise extraction of target data features by each source domain model. Simultaneously, it works towards minimizing the output difference among various source domain models, thereby enhancing the adaptability of the source domain model to the target data. In order to validate the effectiveness of the proposed the adaptive multi-source domain collaborative fine-tuning framework, it is analyzed and compared with the most widely used fine-tuning methods by applying them to seven publicly available visual categorization datasets commonly employed in transfer learning. Experimental results demonstrate that, in comparison with the existing fine-tuning approaches, our method not only enhances the accuracy of feature extraction in the model but also provides precise layer fine-tuning schemes for the target task, resulting in state-of-the-art performance.

Machine learning has become widely adopted as a strategy for dealing with a variety of cybersecurity issues, ranging from insider threat detection to intrusion and malware detection. However, by their very nature, machine learning systems can introduce vulnerabilities to a security defence whereby a learnt model is unaware of so-called adversarial examples that may intentionally result in mis-classification and therefore bypass a system. Adversarial machine learning has been a research topic for over a decade and is now an accepted but open problem. Much of the early research on adversarial examples has addressed issues related to computer vision, yet as machine learning continues to be adopted in other domains, then likewise it is important to assess the potential vulnerabilities that may occur. A key part of transferring to new domains relates to functionality-preservation, such that any crafted attack can still execute the original intended functionality when inspected by a human and/or a machine. In this literature survey, our main objective is to address the domain of adversarial machine learning attacks and examine the robustness of machine learning models in the cybersecurity and intrusion detection domains. We identify the key trends in current work observed in the literature, and explore how these relate to the research challenges that remain open for future works. Inclusion criteria were: articles related to functionality-preservation in adversarial machine learning for cybersecurity or intrusion detection with insight into robust classification. Generally, we excluded works that are not yet peer-reviewed; however, the authors include some significant papers that make a clear contribution to the domain. There is a risk of subjective bias in the selection of non-peer reviewed articles; however, this is mitigated by co-author review. We selected the following databases with a sizeable computer science element to search and retrieve literature: IEEE Xplore, ACM Digital Library, ScienceDirect, Scopus, SpringerLink,Google Scholar. The literature search was conducted upto January 2022. We have striven to ensure a comprehensive coverage of the domain to the best of our knowledge. We have performed systematic searches of the literature, noting our search terms and results, and following up on all materials that appear relevant and fit within the topic domains of this review. This research was funded by the Partnership PhD scheme at the University of the West of England in collaboration with Techmodal Ltd.

A common challenge in real-world classification scenarios with sequentially appending target domain data is insufficient training datasets during the training phase. Therefore, conventional deep learning and transfer learning classifiers are not applicable especially when individual classes are not represented or are severely underrepresented at the outset. Domain Generalization approaches reach their limits when domain shifts become too large, making them occasionally unsuitable as well. In many (technical) domains, however, it is only the defect/ worn/ reject classes that are insufficiently represented, while the non-defect class is often available from the beginning. The proposed classification approach addresses such conditions and is based on a CNN encoder. Following a contrastive learning approach, it is trained with a modified triplet loss function using two datasets: Besides the non-defective target domain class (= 1st dataset), a state-of-the-art labeled source domain dataset that contains highly related classes (e.g., a related manufacturing error or wear defect) but originates from a (highly) different domain (e.g., different product, material, or appearance) (= 2nd dataset) is utilized. The approach learns the classification features from the source domain dataset while at the same time learning the differences between the source and the target domain in a single training step, aiming to transfer the relevant features to the target domain. The classifier becomes sensitive to the classification features and – by architecture – robust against the highly domain-specific context. The approach is benchmarked in a technical and a non-technical domain and shows convincing classification results. In particular, it is shown that the domain generalization capabilities and classification results are improved by the proposed architecture, allowing for larger domain shifts between source and target domains.

ABC-OCT, Affordable B-scan Camera-based Optical Coherence Tomography, implements Fourier-Domain Optical Coherence Tomography with real-time display using cross-platform C++ and the OpenCV framework. The software can be compiled using current versions of GCC for *nix/Mac and Microsoft^® Visual Studio for Windows. Full functionality of ABC-OCT needs the camera SDK from QHYCCD and a QHYCCD camera to be connected; but the code can be easily modified to support other camera drivers, as is shown by an included demo version which can use any installed webcam. The code is made available under the MIT license. The software is available from GitHub (https://github.com/hn-88/FDOCT).

For the generation of representative volume elements a statistical description of the relevant parameters is necessary. These parameters usually describe the geometric structure of a single grain. Commonly, parameters like area, aspect ratio and slope of the grain relative to the rolling direction are applied. However, usually simple distribution functions like log normal or gamma distribution are used. Yet, these do not take the interdependencies between the microstructural parameters into account. To fully describe any metallic microstructure though, these interdependencies between the singular parameters need to be accounted for. To accomplish this representation, a machine learning approach was applied in this study. By implementing a Wasserstein generative adversarial network, the distribution, as well as the interdependencies could accurately be described. A validation scheme was applied to verify the excellent match between microstructure input data and synthetically generated output data.

Generative models have recently gained popularity in Remote Sensing, offering substantial benefits for interpreting and utilizing satellite imagery across diverse applications such as climate monitoring, urban planning, and wildfire detection. These models are particularly adept at addressing the challenges posed by satellite images, which often exhibit domain variability due to seasonal changes, sensor characteristics, and especially variations in spectral bands. Such variability can significantly impact model performance across various tasks. In response to these challenges, our work introduces a novel approach that harnesses the capabilities of Generative Adversarial Networks (GANs), augmented with Contrastive Learning, to generate target domain images that account for multi-spectral band variations effectively. By maximizing mutual information between corresponding patches and leveraging the power of GANs, our model aims to generate realistic-looking images across different multi-spectral domains. We present a comparative analysis of our model against other well-established generative models, demonstrating its efficacy in generating high-quality satellite images while effectively managing domain variations inherent to multi-spectral diversity.

This study aimed to learn disturbance information to effectively control multiple small unmanned surface vehicles (USVs) for marine research purposes at sea. The learned disturbance information was used to investigate the control of multiple USV swarms based on the leading–following formation technique. Numerous studies have already been conducted on swarm control using drones in the air; however, there has been a paucity of studies on swarm control in the sea. Contrary to swarm control in aviation, the fluid density of the sea is high, and the environment is constantly changing; thus, a robot system would be significantly affected by disturbances. This ultimately influences the maintenance of swarm formations and the accomplishment of missions [1,2]. Therefore, it is difficult to control numerous moving objects while maintaining a formation at sea by using the existing aerial drone swarm control technology. To solve this problem, we learned a long short-term memory (LSTM) model with time-series marine environmental data to predict maritime disturbances. Thereafter, the model was applied to a mission-based position control algorithm of each USV constituting the swarm to design a marine unmanned floating vessel swarm control system that can be applied to various marine environments. Specifically, to effectively control numerous small USVs for marine research purposes, ocean currents are learned using the LSTM algorithm, and the predicted ocean currents are used to generate a swarm USV control system for USV formations. In this study, a control system model of several small USVs equipped with two rear thrusters and a front lateral thruster was designed. The LSTM algorithm was learned using the previous ocean current data, and the velocity of the following ocean currents was predicted. The predictions were then used as a system disturbance to determine the thrust of the controller. To measure ocean currents in the sea when each USV moves, the velocity, azimuth, and position (latitude, longitude) data from the GPS mounted on the USV were used to measure the velocity and direction of the hull's movement. Further, the flow rate was measured using a flow rate sensor on a small USV. The USV movement and position were controlled using an artificial neural network-PID (ANN-PID) controller. This study entailed a comparative analysis of the designed USV model results and those generated by the simulator, including the behavior control rule of the USV swarm and the path of the actual USV swarm at sea. It was verified that the effectiveness of the USV mathematical model and behavior control rules. By comparing the movement path of the swarm USV with and without the disturbance learning algorithm and ANN-PID control algorithm applied to the designed simulator, the position error and maintenance performance of the swarm formation were analyzed, and the application results were compared.

This work introduces a new architecture for a time-domain feedback-based beamformer designed to meet real-time processing demands. The primary goal of this design is to locate reflective sources by estimating their direction of arrival (DOA) and signal range. Incorporating a feedback mechanism in this architecture is a unique aspect that refines localization precision. We conduct an in-depth analysis highlighting their respective benefits and limitations to compare the effectiveness of time-domain feedback beamforming against conventional time-domain methods. Our evaluation of the proposed architecture, based on critical performance indicators such as peak-to-sidelobe ratio, mainlobe width, and directivity factor, demonstrates its ability to improve beamformer effectiveness significantly.

Prompt removal of misfolded membrane proteins and misassembled membrane protein complexes is essential for membrane homeostasis. However, the elimination of these toxic proteins from the hydrophobic membrane environment has high energetic barriers. Transmembrane FtsH is the only known ATP-dependent protease responsible for this task, unlike other well-studied soluble ATP-dependent proteases. The mechanisms by which FtsH recognizes, unfolds, translocates, and proteolyzes its substrates remain unclear. Here, we report the crystal structures of the Thermotoga maritima FtsH periplasmic domain (PD) in an associative trimeric state at a 1.5-1.95 Å resolution. We also describe the pH-dependent oligomerization states of the isolated PD using dynamic light scattering. These observations help us understand how FtsH recognizes membrane-anchored misfolded proteins.

Natural vegetation restoration can take decades to achieve and requires information on species composition and trend to inform management strategies. Here we demonstrate the potential and portability of drone, dove and Sentinel-2 imagery for species level classification and trajectory monitoring using three study sites with different revegetation histories. Drone imagery (4 cm) was classified using random forests. Dove (3 m) and Sentinel-2 (10 m) images were acquired close to the anniversary of the drone flights and converted into fractional cover maps showing the proportion of exotics, natives and other land covers using ordinary least squares (OLS) and geographically weighted regression (GWR). The time series of fractional cover maps were converted into positive and negative slope and second-order curvature and summarised as one RGB composite to illustrate trend and observe exotic expansion. Drone classification accuracies ranged from 73%-76% when applied to the full plant species list and between 93% and 97% when grouped into natives, exotics, and other land covers. GWR outperformed OLS for all fractional cover mapping and GWR with dove imagery was more accurate than with Sentinel imagery. The combination of very high-resolution drone acquired imagery with the versatility of dove acquired imagery arms land managers with highly accurate species composition and their spatio-temporal dynamics to promote timely intervention.

Manual material handling (MMH) significantly impacts worker health and productivity, often leading to musculoskeletal disorders (MSDs) primarily in the lower back. As a novel assistive technology, exoskeletons may serve as ergonomic tools to mitigate these work-related MSDs. It is essential to examine exoskeletons from the users’ perspectives before their widespread implementation in occupational settings. This study investigates the effectiveness of a passive back-support exoskeleton (BExo) in reducing perceived physical exertion and improving ergonomic safety in manufacturing context. Twenty-two college students were recruited to perform MMH tasks in a controlled lab environment, both with and without the BExo, followed by completing a survey questionnaire on various aspects of the BExo. Using ANOVA, the study analyzed biomechanical exertion across various body parts and tasks. The findings indicate that the BExo substantially alleviates discomfort in the low back, shoulders and knees, thereby, enhancing ergonomic posture and reducing fatigue. These results underscore the potential of passive exoskeletons to boost workers’ safety and efficiency, providing valuable insights for future ergonomic strategies in industrial setting.

Introduction and Purpose: Nurses are expected to be competent in practice based on the domain of standards and interpersonal soft skills (ISS). Nurses are faced with inadequate physical assessment 28%, formulating diagnoses 56%, plans 34%, implementation 31%, evaluation 37,5%, and communication skills 41%. Aims to develop an ISS learning model based on transformative learning theory and digitalization (TLTD) to improve nurses’ competencies. Method: Used Explanatory cross-sectional involved 190 practitioner nurses. Variables of individual characters (X1), facilities (X2), Social environment support/SES (X3), TLTD (X4), ISS (X5), and nursing competencies (Y) were measured. Data was collected using a checklist questionnaire, conducted on 6 June to 10 August 2022 at Dili, Baucau, and Maliana hospitals. Used descriptive and inferential analysis with SEM-PLS. Result: Five of the 11 hypotheses of statistical p-value < 0,05 and T-Test > 1,96, including X2>X4, X3>X5, X4>X5, and X5>y, to form ISS learning model. The characteristic of respondents were 81,8% young adults, 67,9% women, 57,8% undergraduates, judging the previous training 35% was unsuccessful, and 45,8% did not meet expectations. Learning facilities that are still lacking include policies 23,7%, curriculum 23,4%, guideline 22,7%, modules 27,9%, infrastructure 20,3%, social environment support 24,2% low, organizational support, 30,0% low peer support and 26,3% low family support. The average TLTD is 25,3% to 34,2%, ISS 22,1% to 30,5%, and nurse competence 25,3% to 30,5%.Suggestion: Result of the study become base to improve nurse’s competencies. Conclusion: Learning model was formed by facilities, SES, TLTD, ISS, and nurses’ competencies.

Abstract Introduction: Poor structural quality of health facilities for tuberculosis (TB) diagnosis and treatment contributes to unfavorable health outcomes among TB patients. Improving the quality of healthcare services helps to avert TB-related morbidity. Despite these facts, the level of structural quality of health facilitieSs to deliver TB services is not in line with what the national TB and leprosy program (NTLP) recommends. Hence, the present study was conducted to assess the structural quality of health facilities to deliver quality TB services to TB patients among public health facilities in the Sidama region.Objectives: To determine the quality of the structural domain of TB services at public health facilities in the Sidama region of southern Ethiopia.Methods: An institution-based cross-sectional study was conducted from June to July 2023 among randomly selected public health facilities in the Sidama region. We included 40 randomly selected public health facilities that delivered TB services in the study area. Data was collected by experienced data collectors using facility audits, clinical observation checklists, structured questionnaires, and in-depth interviews. An Open Kit Mobile (ODK) application was used to collect data and exported to SPSS version 26. All statistical analysis was done using SPSS version 26.Results: The overall mean quality score for the structural dimension was 50.25 among the 40 health facilities audited in the study area.Conclusion: The quality of TB services regarding structural dimensions was poor in the study area. Therefore, any strategies must give careful attention to increasing the comprehensive structural dimension of quality TB services.

Adversarial Classification (AC) is a major subfield within the increasingly important domain of adversarial machine learning (AML). Most approaches to AC so far have followed a classical game-theoretic framework. This requires unrealistic common knowledge conditions untenable in the security settings typical of the AML realm. After reviewing such approaches, we present alternative perspectives on AC based on Adversarial Risk Analysis.

The many limitations of implementing anticancer strategies under the term “precision oncology” have been extensively discussed. While some authors propose promising future directions, others are less optimistic and use phrases such as illusion, hype and false hypotheses. The reality is revealed by practicing clinicians and cancer patients in various online publications, one of which has stated that “in the quest for the next cancer cure, few researchers bother to look back at the graveyard of failed medicines to figure out what went wrong.” The message is clear: novel therapeutic strategies with catchy names (e.g., synthetic “lethality”) have not fulfilled their promises despite decades of extensive research and clinical trials. The main purpose of this review is to discuss key challenges in solid tumor therapy that surprisingly continue to be overlooked by the nomenclature committee on cell death and numerous other authors. These challenges include: the impact of chemotherapy-induced genome chaos (e.g., multinucleation) on resistance and relapse, oncogenic function of caspase 3, cancer cell anastasis (recovery from late stages of apoptosis), and pitfalls of ubiquitously used preclinical chemosensitivity assays (e.g., cell “viability” and tumor growth delay studies in live animals) that score such pro-survival responses as “lethal” events. Studies outline herein underscore the need for new direction in the management of solid tumors.

Numerous approaches address over-fitting in neural networks: by imposing a penalty on the parameters of the network (L1, L2, etc); by changing the network stochastically (drop-out, Gaussian noise, etc.); or by transforming the input data (batch normalization, etc.). In contrast, we aim to ensure that a minimum amount of supporting evidence is present when fitting the model parameters to the training data. This, at the single neuron level, is equivalent to ensuring that both sides of the separating hyperplane (for a standard artificial neuron) have a minimum number of data points — noting that these points need not belong to the same class for the inner layers. We firstly benchmark the results of this approach on the standard Fashion-MINST dataset, comparing it to various regularization techniques. Interestingly, we note that by nudging each neuron to divide, at least in part, its input data, the resulting networks make use of each neuron, avoiding a hyperplane completely on one side of its input data (which is equivalent to a constant into the next layers). To illustrate this point, we study the prevalence of saturated nodes throughout training, showing that neurons are activated more frequently and earlier in training when using this regularization approach. A direct consequence of the improved neuron activation is that deep networks are now easier to train. This is crucially important when the network topology is not known a priori and fitting often remains stuck in a suboptimal local minima. We demonstrate this property by training a network of increasing depth (and constant width): most regularization approaches will result in increasingly frequent training failures (over different random seeds) whilst the proposed evidence-based regularization significantly outperforms in its ability to train deep networks.

Underwater image often exhibit detail blurring and color distortion due to light scattering, impurities, and other influences, obscuring essential textures and details. This presents a challenge for existing super-resolution techniques in identifying and extracting effective features, making high-quality reconstruction difficult. This research aims to innovate underwater image super-resolution technology to tackle this challenge. Initially, an underwater image degradation model was created by integrating random subsampling, Gaussian blur, mixed noise, and suspended particle simulation to generate a highly realistic synthetic dataset, thereby training the network to adapt to various degradation factors. Subsequently, to enhance the network's capability to extract key features, improvements were made based on the symmetrically structured Blind Super-Resolution Generative Adversarial Network (BSRGAN) model architecture. An attention mechanism based on energy functions was introduced within the generator to assess the importance of each pixel, and a weighted fusion strategy of adversarial loss, reconstruction loss, and perceptual loss was utilized to improve the quality of image reconstruction. Experimental results demonstrate that the proposed method achieved significant improvements in Peak Signal-to-Noise Ratio (PSNR) and Underwater Image Quality Measure (UIQM) by 0.85 dB and 0.19, respectively, significantly enhancing the visual perception quality and indicating its feasibility in super-resolution applications.

Tuning tensor program generation involves navigating a vast search space to find optimal program transformations and measurements for a program on target hardware. The complexity of this process is further amplified by the exponential combinations of transformations, especially in heterogeneous environments. This research addresses these challenges by introducing a novel approach that learns the joint neural network and hardware features space, facilitating knowledge transfer to new, unseen target hardware. A comprehensive analysis is conducted on the existing state-of-the-art dataset, TenSet, including a thorough examination of test split strategies and the proposal of methodologies for dataset pruning. Leveraging an attention-inspired technique, we tailor the tuning of tensor programs to embed both neural network and hardware-specific features. Notably, our approach substantially reduces the dataset size by up to 53% compared to the baseline without compromising Pairwise Comparison Accuracy (PCA). Furthermore, our proposed methodology demonstrates competitive or improved mean inference times with only 25%40% of the baseline tuning time across various networks and target hardware. The attention-based tuner can effectively utilize schedules learned from previous hardware program measurements to optimize tensor program tuning on previously unseen hardware, achieving a top-5 accuracy exceeding 90%. This research introduces a significant advancement in auto-tuning tensor program generation, addressing the complexities associated with heterogeneous environments and showcasing promising results regarding efficiency and accuracy.

Purpose. This paper aims to present a unique perspective that emphasizes the intricate interplay between energy, dietary proteins, and amino acid composition, underscoring their mutual dependence for health-related considerations. Energy and protein synthesis are fundamental to biological processes, crucial for the sustenance of life and growth of organisms. Methods and Results. We explore the intricate relationship between energy metabolism, protein synthesis, regulatory mechanisms, protein sources, amino acid availability, and autophagy, in order to elucidate how these elements collectively maintain cellular homeostasis. We underscore the vital role this dynamic interplay has in preserving cell life. Conclusion. A deeper understanding of the link between energy and protein synthesis is essential to comprehend fundamental cellular processes. This insight could have wide-ranging impact in several medical fields, such as nutrition, metabolism, and disease management.

The field of domain adaptation, particularly in cross-domain sentiment classification, leverages labeled data from a source domain alongside unlabeled or sparsely labeled data from a target domain. The objective is to enhance performance in the target domain by mitigating the discrepancies in data distributions. Traditional methods in this area have focused on identifying and differentiating between pivotal sentiment words (shared across domains) and domain-specific sentiment words. In our work, we introduce a novel framework called Sentiment Domain Adapter (SDA), which incorporates a Category Attention Network (CAN) alongside a Convolutional Neural Network (CNN). This approach treats pivotal and domain-specific words as part of a collective category of attributes, which SDA learns to discern automatically, thereby enhancing domain adaptation. Additionally, SDA seeks to provide interpretative insights by learning these category attributes. Our model's optimization targets three main goals: (1) supervised classification accuracy, (2) minimizing the disparity in category feature distribution, and (3) maintaining domain invariance. Evaluations on three benchmark datasets for sentiment analysis affirm that SDA surpasses several established baselines.

Highly-skilled migrants and refugees finding employment in low-skill vocations, despite professional qualifications and educational background, has become a global tendency, mainly due to the language barrier. Employment prospects for displaced communities are mostly decided by their knowledge of the sublanguage of the vocational domain they are interested in working. Common vocational domains include agriculture, cooking, crafting, construction, and hospitality. The increasing amount of user-generated content in wikis and social networks provides a valuable source of data for data mining, Natural Language Processing and machine learning applications. This paper extends the contribution of the authors’ previous research on automatic vocational domain identification by further analyzing the results of the machine learning experiments with the domain-specific textual data set, considering 2 research directions: a. predictions analysis and b. data balancing. Wrong predictions analysis and the features that contributed to misclassification, along with correct predictions analysis and the features that were the most dominant, contributed to the identification of a primary set of terms for the vocational domains. Data balancing techniques were applied on the data set to observe their impact on the performance of the classification model. A novel 4-step methodology is proposed in this paper for the first time, consisting of successive applications of SMOTE oversampling on imbalanced data. Data oversampling obtains better results than data undersampling in imbalanced data sets, while hybrid approaches perform reasonably well.

The digital era has significantly amplified the volume of online reviews, presenting both opportunities and challenges in harnessing insights from consumer feedback. Aspect-Based Sentiment Analysis (ABSA) has emerged as a crucial tool for distilling sentiments from these reviews, providing valuable data for enhancing product and service quality. This study introduces an advanced hybrid model, AdvSentiNet, which integrates adversarial training into the state-of-the-art framework to elevate the precision of sentiment detection at the aspect level. By employing an adversarial network, where a generative model competes against a classifier by crafting highly realistic synthetic samples, we aim to bolster the model's resilience against varied data samples. This innovative approach, unexplored in its entirety within the realm of ABSA, demonstrated remarkable performance improvements on benchmark datasets. For instance, accuracy on the SemEval 2015 dataset escalated from 81.7% to 82.5%, and for the SemEval 2016 dataset, it surged from 84.4% to 87.3%.

We present a method to improve the reconstruction and generation performance of variational autoencoder (VAE) by injecting an adversarial learning. On the other hand, instead of comparing the reconstructed with the original data to calculate the reconstruction loss, we use a consistency principle for deep features. The training process of the VAE is then divided into two steps, training the encoder and then training the decoder. By using this two-step learning process, our method can be more widely used in applications other than image processing. While training the encoder, the label information is integrated to better structure the latent space in a supervised way. The adversarial constraints allow the decoder to generate data with better authenticity and more realistic than the conventional VAE. We present experimental results to show that our method gives better performance than the original VAE.

Motivated by diffraction experiments on the $\left(2\sqrt{3}\times \sqrt{3}\right)\mathrm{R}{30}^{\circ }$ reconstructed Si(111) due to deposition of rare earth elements (Dy, Tb) and silicide formation we analyse the splitting and non-splitting of superstructure spots. For this purpose, we model diffraction patterns for one dimensional structures generated by the binary surface technique and use supercell models to keep the analysis simple. Diffraction pattern are calculated in the framework of the kinematical diffraction theory and they are analyzed as a function of the domains and domain boundaries. Basic properties of the diffraction pattern are analyzed for model systems of a two-fold and a three-fold periodicity. The rules derived from these calculations are applied to the "real-world" system of Si(111)-($\left(2\sqrt{3}\times \sqrt{3}\right)\mathrm{R}{30}^{\circ }$)-RESi$2_{}$ (RE = Dy or Tb). Depending on the combination of domains and domain boundaries of different types a plethora of different features are observed in the diffraction patterns. These are analyzed to determine the sizes of both domain boundaries and domains from experimentally observed splitting of specific superstructure spots.

Structural health monitoring has been studied by a number of researchers as well as various industries to keep up with the increasing demand for preventive maintenance routines. This work presents a novel method for reconstruct prompt, informed strain/stress responses at the hot spots of the structures based on strain measurements at remote locations. The structural responses measured from usage monitoring system at available locations are decomposed into modal responses using empirical mode decomposition. Transformation equations based on finite element modeling are derived to extrapolate the modal responses from the measured locations to critical locations where direct sensor measurements are not available. Then, two numerical examples (a two-span beam and a 19956-degree of freedom simplified airfoil) are used to demonstrate the overall reconstruction method. Finally, the present work investigates the effectiveness and accuracy of the method through a set of experiments conducted on an aluminium alloy cantilever beam commonly used in air vehicle and spacecraft. The experiments collect the vibration strain signals of the beam via optical fiber sensors. Reconstruction results are compared with theoretical solutions and a detailed error analysis is also provided.

(1) Background: We aimed to identify factors associated with the presence of apical lesions (AL) on panoramic radiographs and to evaluate the predictive value of the identified factors. (2) Methodology: Panoramic radiographs from 1071 patients (age: 11-93 a, mean: 50.6 a ± 19.7 a) with 27532 teeth were included. Each radiograph was independently assessed by five experienced dentists for AL. A range of shallow machine learning algorithms (logistic regression, k-nearest neighbor, decision tree, random forest, support vector machine, adaptive and gradient boosting) were employed to identify factors on patient and tooth level associated with AL and to predict AL. (3) Results: AL were detected in 522 patients (48.7%) and 1133 teeth (4.1%), whereas males showed a significantly higher prevalence than females (52.5%/44.8%; p<0.05). Logistic regression found that an existing root canal treatment was the most important risk factor (adjusted Odds Ratio 16.89; 95% CI: 13.98-20.41), followed by the tooth type ‘molar’ (2.54; 2.1-3.08) and the restoration with a crown (2.1; 1.67-2.63). Associations between factors and AL were stronger and accuracy higher when using less complex models like decision tree (F1 score: 0.9 (0.89-0.9)). (4) Conclusions: The presence of AL was higher in root-canal treated teeth, those with crowns and molars. More complex machine learning models did not outperform less complex ones.

Over the past decade, research in the field of Deep Learning has brought about novel improvements in image generation and feature learning; one such example being a Generative Adversarial Network. However, these improvements have been coupled with an increasing demand on mathematical literacy and previous knowledge in the field. Therefore, in this literature review, I seek to introduce Generative Adversarial Networks (GANs) to a broader audience by explaining their background and intuition at a more foundational level. I begin by discussing the mathematical background of this architecture, specifically topics in linear algebra and probability theory. I then proceed to introduce GANs in a more theoretical framework, along with some of the literature on GANs, including their architectural improvements and image-generation capabilities. Finally, I cover state-of-the-art image generation through style-based methods, as well as their implications on society.

Background: The practice of self-medication is common worldwide and is an important component of medical self-care. However, the practice can be dangerous and is linked to various risks for the patients and the entire community. This study aimed to estimate the prevalence and factors associated with self-medication among Bangladeshi adults. Methods: A cross-sectional survey was conducted between April and June 2021 among Bangladeshi adults (aged &gt;19 years) using convenient sampling. A total of 1320 data were collected through face-to-face interviews using a standardized questionnaire. Multivariable logistic regression analysis was used to identify factors associated with self-medication practice (SMP). Results: Overall, 41% of adults in our survey reported SMP. The most common illnesses that prompted SMP were common cold/flu (66.4%), gastric problems (65%), and headache (64.4%). The most frequent reasons for SMP were to get better services (30.59%), perceive SMP without side effects (23.28%), and save time with effectiveness (14.56%). Potential risk factors included 10 years (AOR = 1.91; 95% CI: 1.04 - 3.50) and &gt;12 years of schooling (AOR = 5.03; 95% CI: 2.27 - 11.15), being a businessman (AOR = 4.64; 95% CI: 1.74 - 12.37), having ≤6 family members (AOR = 2.13; 95% CI: 1.40 - 3.24), being a member of a social group (AOR = 1.53; 95% CI: 1.10 - 2.12), a health status check after every six months (AOR = 1.52; 95% CI: 1.08 - 2.13), and current ill-health (AOR = 1.41; 95% CI: 1.06 - 1.87). Protective factors identified included ≤30 years of age (AOR = 0.40; 95% CI: 0.17 - 0.93), and practice of modern (AOR = 0.39; 95% CI: 0.22- 0.69) and herbal (AOR = 0.45; 95% CI: 0.21- 0.97) healing types. Conclusion: More than one-third of the study participants reported practicing self-medication. Increasing the community’s awareness of the extreme consequences of SMP and not just the average experience might sway individuals away from SMP, and implementing strict jurisdiction could be a way to minimize the SMP.

Virus taxonomy uses a Linnaean-like subsumption hierarchy to classify viruses into taxonomic units at species and higher rank levels. Virus species are considered monophyletic groups of mobile genetic elements (MGEs) often delimited by phylogenetic analysis of aligned genomic or metagenomic sequences. Taxonomic units are assumed independent organizational, functional and evolutionary units that follow a ‘natural’ historical rationale. Here, I use phylogenomic and other arguments to show that viruses are not self-standing genetically-driven biological systems. Instead, they are crucial components of holobionts, units of biological organization that dynamically integrate the genetics, epigenetic, physiological and functional properties of their co-evolving members. Remarkably, phylogenomic analyses show viruses share protein domain and loop structures with cells throughout history via massive processes of reticulate evolution, helping spread evolutionary innovations across a wider taxonomic spectrum. Thus, viruses are not merely MGEs or microbes. Instead, their genomes and proteomes conduct cellularly integrated processes akin to those cataloged by the GO Consortium. This prompts the generation of compositional hierarchies that replace the ‘is-a-kind-of’ by a ‘is-a-part-of’ logic to better describe the mereology of integrated cellular and viral makeup. My analysis demands a new paradigm that integrates virus taxonomy into a modern evolutionarily centered taxonomy of organisms.

In recent years, with the rapid development of technology, artificial intelligence(AI) security issues represented by adversarial sample attack have aroused widespread concern in society. Adversarial samples are often generated by surrogate models and then transfer to attack the target model, and most AI models in real-world scenarios belong to black boxes, thus transferability becomes a key factor to measure the quality of adversarial samples. The traditional method relies on the decision boundary of the classifier and takes the boundary crossing as the only judgment metric without considering the probability distribution of the sample itself, which results in an irregular way of adding perturbations to the adversarial sample, an unclear path of generation, and a lack of transferability and interpretability. In the probabilistic generative model, after learning the probability distribution of the samples, a random term can be added to the sampling to gradually transform the noise into a new independent and identically distributed sample. Inspired by this idea, we believe that by removing the random term, the adversarial sample generation process can be regarded as static sampling of the probabilistic generative model, which guides the adversarial samples out of the original probability distribution and into the target probability distribution, and helps to improve transferability and interpretability. Therefore, we propose a Score Matching-Based Attack(SMBA) method to perform the adversarial sample attacks by manipulating the probability distribution of the samples, which can show good transferability in the face of different datasets and models, and give reasonable explanations from the perspective of mathematical theory and feature space. In conclusion, our research establishes a bridge between probabilistic generative models and adversarial samples, provides a new entry angle for the study of adversarial samples, and brings new thinking to AI security.

Current VAT rules for cross-border e-commerce companies in the EU are not sustainable, because they are extremely complex and often opaque, due to the lack of tax harmonization. The aim of the research is to explore, using a qualitative method, what kind of harmonization would make the current legislation more uniform, simpler, more transparent, and easier to understand, without conflicting with the rules of any Member State. To this end, the aspects of the new platform regulation introduced on 1 July 2021 and its potential for expansion are assessed through information from possible sales models. The research suggests that the rules on platforms do not cover all possible sales models, which in our view imposes an unnecessary extra administrative burden on some businesses and makes their tax activities less transparent. In the light of the results of the research, we propose that the current EU platform regulation should be extended to cover B2B, B2C transactions and services. As a result of this suggested harmonization, a simpler, more transparent, uniform and sustainable tax system would contribute to the whitening of the economy, generating additional tax revenue for Member States.

Generative artificial intelligence (GenAI) has been developing with many incredible achievements like ChatGPT and Bard. Deep generative model (DGM) is a branch of GenAI, which is preeminent in generating raster data such as image and sound due to strong points of deep neural network (DNN) in inference and recognition. The built-in inference mechanism of DNN, which simulates and aims to synaptic plasticity of human neuron network, fosters generation ability of DGM which produces surprised results with support of statistical flexibility. Two popular approaches in DGM are Variational Autoencoders (VAE) and Generative Adversarial Network (GAN). Both VAE and GAN have their own strong points although they share and imply underline theory of statistics as well as incredible complex via hidden layers of DNN when DNN becomes effective encoding/decoding functions without concrete specifications. In this research, VAE and GAN is unified into a consistent and consolidated model called Adversarial Variational Autoencoders (AVA) in which VAE and GAN complement each other, for instance, VAE is good at generator by encoding data via excellent ideology of Kullback-Leibler divergence and GAN is a significantly important method to assess reliability of data which is realistic or fake. In other words, AVA aims to improve accuracy of generative models, besides AVA extends function of simple generative models. In methodology this research focuses on combination of applied mathematical concepts and skillful techniques of computer programming in order to implement and solve complicated problems as simply as possible.

In the face of escalating cybercriminal sophistication, an innovative approach to network anomaly detection has been pursued in this longitudinal study, integrating computational data analytics in a geographic, organizational, and behavioral context. A data-driven scoring mechanism was employed to systematically analyze and correlate source countries of IP addresses and organization-associated Autonomous System (AS) Numbers (ASN) with network anomalies. Significant correlations between certain countries, specific organizations, and high behavior scores were identified through the data analytics. An increase in connection requests was also found to be linked with elevated behavior scores. Validated by cross-validation techniques, these findings emphasize the necessity for continuous model recalibration. The transformative role of integrative data analytics in cybersecurity is underscored, paving the way for the development of more sophisticated, context-aware anomaly detection systems. Specifically, the analysis underscores the need for organizations to adopt a proactive and adaptive approach to cybersecurity that can keep pace with the evolving threat landscape.

：Non-Euclidean data, such as social networks, and citation relationships between documents, has node information and structural information. Graph Convolutional Network(GCN) can automatically learn node features and association information between nodes. The core ideology of the graph convolutional network is to aggregate node information by using edge information, thereby generating a new node feature. In the process of updating node features, there are two core influencing factors. One is the number of neighboring nodes of the central node, the other is the contribution of the neighboring nodes to the central node. Due to the previous GCN methods not simultaneously considering the numbers and different contributions of neighboring nodes to the central node, we design the Adaptive Attention Mechanism(AAM). To further enhance the representational capability of the model, we utilize Multi-Head Graph Convolution(MHGC). Finally, we adopt cross-entropy(CE) loss function to describe the difference between the predicted results of node categories and the ground truth (GT). Combined with backpropagation, this ultimately achieves accurate node classification. Based on AAM, MHGC and CE, we contrive the novel Graph Adaptive Attention Network (GAAN). Experiments show that the classification accuracy has achieved outstanding performances on Cora, Citeseer and Pubmed datasets.

Microscopic and ultra-microscopic vascular sutures are indispensable in the surgical procedures such as arm transplantation and finger reattachment. The state of the blood vessels after suturing, such as vascular patency, narrow, and blocked, determines the success rate of the operation. If we can grasp the golden window period after blood vessel suture and before muscle tissue suture to achieve accurate and objective assessment of blood vessel status, it can not only reduce medical costs but also improve social benefits. Doppler optical coherence tomography enables high-speed, high-resolution imaging of biological tissues, especially microscopic and ultra-microscopic blood vessels. Using Doppler optical coherence tomography to image the sutured blood vessels, not only the three-dimensional structure of the blood vessels, but also the blood flow information can be obtained. By extracting the contour of blood vessel wall and the contour of blood flow area, the three-dimensional shape of blood vessel can be reconstructed in three dimensions, which provides parameter support for the assessment of blood vessel status. In this work, we propose a neural network-based multi-classification deep learning model that can simultaneously and automatically extract blood vessel boundaries from Doppler OCT vessel intensity images and the contours of blood flow regions from corresponding Doppler OCT vessel phase images. Compared with the traditional random walk segmentation algorithm and cascade neural network method, the proposed model has better performance. This method is easier to realize system integration and has great potential for clinical evaluation. It is expected to be applied to the evaluation of microscopic and ultra-microscopic vascular status in microvascular anastomosis.

Machine Learning is increasingly and ubiquitously being used in the medical domain. Evaluation metrics like accuracy, precision, and recall may indicate the performance of the models but not necessarily the reliability of their outcomes. This paper assesses the effectiveness of a number of machine learning algorithms applied to an important dataset in the medical domain, specifically, mental health, by employing explainability methodologies. Using multiple machine learning algorithms and model explainability techniques, the project provides insights into the model workings to help determine the reliability of the machine learning algorithm predictions. The results are not intuitive. It was found that the models were focusing significantly on less relevant features and at times, unsound ranking of the features to make the predictions. The paper therefore argues that it is important for research in applied machine learning to provide insights into explainability of the models in addition to other performance metrics like accuracy. This is particularly important for applications in critical domains such as healthcare. A future direction is to investigate methods to quantify the effectiveness of the machine learning models in terms of the insights from their explainability.

L-gulonolactone oxidase enzyme (GULO) catalyzes the last step of L-ascorbic acid (vitamin C) biosynthesis. This enzymatic activity is lost in primates. The full-length rat GULO has been previously produced in plants and demonstrated to be active. In this study, we compare activity of two variants of GULO produced in Escheriachia coli cells, full-length rat GULO (fGULO) and its C-terminal catalytic domain (cGULO). The expression and purification of the recombinant proteins were optimised and their biological activity was confirmed by two methods, the GULO activity assay in the protein extracts and the ‘in-gel’ staining for GULO activity. Both variants of recombinant GULO were biologically active in both assays. However, cGULO is more promising than fGULO for ascorbic acid production because it is more efficiently produced by bacteria.

In the remote sensing domain, it is crucial to complete semantic segmentation on the raster images, e.g., river, building, forest, etc, on raster images. A deep convolutional encoder--decoder (DCED) network is the state-of-the-art semantic segmentation method for remotely sensed images. However, the accuracy is still limited, since the network is not designed for remotely sensed images and the training data in this domain is deficient. In this paper, we aim to propose a novel CNN for semantic segmentation particularly for remote sensing corpora with three main contributions. First, we propose applying a recent CNN called a global convolutional network (GCN), since it can capture different resolutions by extracting multi-scale features from different stages of the network. Additionally, we further enhance the network by improving its backbone using larger numbers of layers, which is suitable for medium resolution remotely sensed images. Second, "channel attention'' is presented in our network in order to select the most discriminative filters (features). Third, "domain-specific transfer learning'' is introduced to alleviate the scarcity issue by utilizing other remotely sensed corpora with different resolutions as pre-trained data. The experiment was then conducted on two given datasets: (i) medium resolution data collected from Landsat-8 satellite and (ii) very high resolution data called the ISPRS Vaihingen Challenge Dataset. The results show that our networks outperformed DCED in terms of $F1$ for 17.48% and 2.49% on medium and very high resolution corpora, respectively.

Safe water is a global public health concern amid increasing scarcity and pollution. Bottled water production and consumption contribute to these problems. This study examines tap water consumption in Italy, assessing associated sociodemographic factors and related health outcomes such as obesity and self-perceived health status. Data from the Italian National Statistics Institute's "Aspects of daily life" survey (N=45,597) were analyzed. Covariates included education, age, gender, economic status, region, concerns about waste and climate change, consumption of carbonated drinks excluding water, alcohol consumption, consumption of vegetables, consumption of snacks, body mass index, and self-perceived health status. Bivariate analyses and mixed-effect logistic regression models explored the associations. People who drink tap water were 19,674 with a higher prevalence in people aged 45 to 59 old, people with a graduate/post-graduate degree diploma, with optimal economic resources, and concerned about waste production and climate change, coming from the North-East regions of Italy. Underweight people showed a higher prevalence of TW assumption as well as those who drink less than occasionally carbonated drinks, drink alcohol, consume vegetables more than once a day, and snacks less than once a week with a satisfying level perceived health status. Regressions showed that all age classes are less likely to drink tap water than people younger than 20 years old. The category with “inadequate” economic resources is more likely to consume tap water. Low educational classes show a low likelihood of consuming tap water as well as Islands. A concern about waste production and climate change is associated with an increased likelihood of assuming tap water. Tap water consumption was negatively associate with obesity but not with a satisfactory Self-perceived health status. Insights from this study can inform public health strategies.

The BET family of proteins is characterized by the presence of two tandem bromodomains and an extra-terminal domain. The mammalian BET family of proteins comprises Brd2, Brd3, Brd4, and Brdt, which are encoded by paralogous genes that may have been generated by repeated duplication of an ancestral gene during evolution. Bromodomains that can specifically bind acetylated lysine residues in histones serve as chromatin-targeting modules that decipher the histone acetylation code. BET proteins play a crucial role in regulating gene transcription through epigenetic interactions between bromodomains and acetylated histones during cellular proliferation and differentiation processes. On the other hand, BET proteins have been reported to mediate latent viral infection in host cells and be involved in oncogenesis. Human BRD4 is involved in multiple processes of the DNA virus life cycle, including viral replication, genome maintenance, and gene transcription through interaction with viral proteins. Aberrant BRD4 expression contributes to carcinogenesis by mediating hyperacetylation of the chromatin containing the cell proliferation-promoting genes. BET bromodomain blockade using small-molecule inhibitors gives rise to selective repression of the transcriptional network driven by c-Myc. These inhibitors are expected to be potential therapeutic drugs for a wide range of cancers. This review presents an overview of the basic roles of BET proteins and highlights the pathological functions of BET and the recent developments in cancer therapy targeting BET proteins in animal models.

In this research paper, design and development of pyramidal horn antenna for J-band application is reported. It is particularly designed for 17 dB gain and half beam width about 25 degrees at 6.93 GHz. Horn aperture, horn axial length and distance from the throat of the antenna to aperture are the main design constraints which are calculated and used for the antenna design and simulation. Beam width in E-plane and H-plane horn is calculated and it is 19.18 dB and 22.86 dB respectively. The reported antenna design shows good performance for J-band in radiometry, satellite, and radar applications.

A simple design of an ultrathin six-band polarization-insensitive terahertz perfect metamaterial absorber (PMMA) composed of a metal cross-cave-patch resonator (CCPR) placed over a ground plane was proposed and investigated numerically. The numerical simulation results demonstrate that the average absorption peaks are up to 95% at six resonance frequencies with high quality-factors (>65). In addition, the absorption properties can be kept stability for both normal incident transverse magnetic (TM) and transverse electric (TE) waves. The physical mechanism behind the observed high level absorption is illustrated by the electric and power loss density distributions. The different absorption mainly originates from the higher order multipolar and multipolar plasmon resonance of the structure, which are sharp different to the most previous studies of the PMMAs. Furthermore, the resonance absorption of the PMMA can be tunable by varying the geometric parameters of the unit cell.

A simple design of an ultrathin six-band polarization-insensitive terahertz perfect metamaterial absorber (PMMA) composed of a metal cross-cave-patch resonator (CCPR) placed over a ground plane was proposed and investigated numerically. The numerical simulation results demonstrate that the average absorption peaks are up to 95% at six resonance frequencies with high quality-factors (>65). In addition, the absorption properties can be kept stability for both normal incident transverse magnetic (TM) and transverse electric (TE) waves. The physical mechanism behind the observed high level absorption is illustrated by the electric and power loss density distributions. The different absorption mainly originates from the higher order multipolar and multipolar plasmon resonance of the structure, which are sharp different to the most previous studies of the PMMAs. Furthermore, the resonance absorption of the PMMA can be tunable by varying the geometric parameters of the unit cell.

Globally, over the past several months millions of persons contracted the coronavirus disease 2019 (COVID-19) resulting in significant mortality. Health care systems are negatively impacted including the care of individuals with cancers and other chronic diseases such as chronic active hepatitis, cirrhosis and hepatocellular carcinoma. There are various probable pathogenic mechanisms that have been presented to account for liver injury in COVID-19 patients such as hepatotoxicity cause by therapeutic drugs, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection of the bile duct cells and hepatocytes, hypoxia and systemic inflammatory response. Liver biochemistry tests such as AST, ALT, GGT and ALP are deranged in COVID-19 patients with liver injury. Hepatocellular damage results in the elevation of serum AST and ALT levels in early onset disease while a cholestatic pattern that develops as the disease progress causes higher levels of ALP, GGT, direct and total bilirubin. These liver biochemistry tests are prognostic markers of disease severity and should be carefully monitored in COVID-19 patients. We conducted a systematic review of abnormal liver biochemistry tests in COVID-19 and the possible pathogenesis involved. Significant findings regarding the severity, hepatocellular pattern, incidence and related clinical outcomes in COVID-19 patients are highlighted.

Background: The electroretinogram is a clinical test used to assess the function of the photoreceptors and retinal circuits of various cells in the eye, with the recorded waveform being the result of the summated response of neural generators across the retina. Methods: The present investigation involved an analysis of the electroretinogram waveform in both the time and time-frequency domain through the utilization of the discrete wavelet transform and continuous wavelet transform techniques. The primary aim of this study was to monitor and evaluate the effects of treatment in a New Zealand rabbit model of endophthalmitis via electroretinogram waveform analysis and to compare these with normal human electroretinograms Results: The wavelet scalograms were analyzed using various mother wavelets, including the Daubechies, Ricker, Wavelet Biorthogonal 3.1 (bior3.1), Morlet, Haar, and Gaussian wavelets. Distinctive variances were identified in the wavelet scalograms between rabbit and human electroretinograms. The wavelet scalograms in the rabbit model of endophthalmitis showed recovery with treatment in parallel with the time -domain features. Conclusions: The study compared Adult, Child, and Rabbit electroretinogram responses using DWT and CWT, finding that Adult signals had higher power than Child signals, and Rabbit signals showed differences in a-wave and b-wave depending on the type of response tested, while Haar Wavelet was found to be superior in visualizing frequency components in electrophysiological signals in following the treatment of endophthalmitis and may give additional outcome measures for the management of retinal disease.

Despite the impressive performance of deep neural networks on many different vision tasks, they have been known to be vulnerable to intentionally added noise to input images. To combat these adversarial examples (AEs), improving the adversarial robustness of models has emerged as an important research topic, and research has been conducted in various directions including adversarial training, image denoising, and adversarial purification. Among them, this paper focuses on adversarial purification, which is a kind of pre-processing that removes noise before AEs enter a classification model. The advantage of adversarial purification is that it can improve robustness without affecting the model’s nature, while another defense techniques like adversarial training suffer from a decrease in model accuracy. Our proposed purification framework utilizes a Convolutional Autoencoder as a base model to capture the features of images and their spatial structure. We further aim to improve the adversarial robustness of our purification model by distilling the knowledge from teacher models. To this end, we train two Convolutional Autoencoders (teachers), one with adversarial training and the other with normal training. Then, through ensemble knowledge distillation, we transfer the ability of denoising and restoring of original images to the student model (purification model). Our extensive experiments confirm that our student model achieves high purification performance(i.e., how accurately a pre-trained classification model classifies purified images). The ablation study confirms the positive effect of our idea of ensemble knowledge distillation from two teachers on performance.

In traditional databases, the entity resolution problem (which is also known as deduplication), refers to the task of mapping multiple manifestations of virtual objects to its corresponding real-world entity. When addressing this problem, in both theory and practice, it is widely assumed that such sets of virtual object appear as the result of clerical errors, transliterations, missing or updated attributes, abbreviations, and so forth. In this paper, we address this problem under the assumption that this situation is caused by malicious actors operating in domains in which they do not wish to be identified, such as hacker forums and markets in which the participants are motivated to remain semi-anonymous (though they wish to keep their true identities secret, they find it useful for customers to identify their products and services). We are therefore in the presence of a different, even more challenging problem that we refer to as adversarial deduplication. In this paper, we study this problem via examples that arise from real-world data on malicious hacker forums and markets arising from collaborations with a cyber threat intelligence company focusing on understanding this kind of behavior. We argue that it is very difficult---if not impossible---to find ground truth data on which to build solutions to this problem, and develop a set of preliminary experiments based on training machine learning classifiers that leverage text analysis to detect potential cases of duplicate entities. Our results are encouraging as a first step towards building tools that human analysts can use to enhance their capabilities towards fighting cyber threats.

Traditional image steganography conceals secret messages into unprocessed natural images by modifying the pixel value, causing the obtained stego different from the original image in terms of statistical distribution, thereby could be detected by a well-trained classifier for steganalysis. To ensure the steganography is imperceptible and in line with the trend of art images produced by Artificial Intelligence Generated Content (AIGC) becoming popular in social networks, this paper proposes to embed hidden information throughout the process of the generation of an art-style image by designing an image style transformation neural network with steganography function. The proposed scheme takes a content image, an art-style image, and messages to be embedded as inputs, processing them with an encoder-decoder model, and finally generates a styled image containing the secret messages at the same time. An adversarial training technique is applied to enhance the imperceptibility of the generated art-styled stego image with from plain style-transferred images. The lack of the original cover image makes it difficult for the opponent learning a steganalyzer to identify the stego. The recommended approach can successfully withstand existing steganalysis techniques and attain the embedding capacity of 3 bits per pixel for a color image, according to experimental results.

We study the brain segmentation by dividing the brain into multiple tissues. Given possible brain segmentation by deep, machine learning can be efficiently exploited to expedite the segmentation process in the clinical practice. To accomplish segmentation process, a MRI and tissues transfer using generative adversarial networks is proposed. Given the better result, we propose the transfer model using GAN. For the case of the brain tissues, white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF) are segmented. Empirical results show that this proposed model significantly improved segmentation results compared to the stat-of-the-art results. Furthermore, a dice coefficient (DC) metric is used to evaluate the model performance.

Background: Ultraviolet (UV) radiation from the sunlight can harm skin cells, causing short-term effects, such as sunburns and long-term effects, such as pigmentation changes, changes in the skin's immune responses, and increased risk of skin cancer. These conditions can be largely prevented with proper sun protection measures and behavioural changes. This study aims to assess the knowledge on sun protection behaviour and baseline knowledge of medical students from the “Carol Davila” University of Medicine and Pharmacy, Bucharest, Romania. Methods: Data in this cross-sectional study were collected through a Google Forms questionnaire, which was distributed from November 2023 to December 2023 via digital communication channels to students across all academic years. STROBE guidelines were consulted for data synthesis; Results: A total of 668 stu-dents responded. The student cohort demonstrated a commendable level of awareness of the risks associated with sun exposure and the advantages of employing sun protection factor (SPF); how-ever, the incidence of sunburns remained notably elevated (72.3%). Further analysis revealed cor-relations among gender, academic year, presence of photosensitizing conditions, and adherence to SPF application. Additionally, there is a need to improve understanding of the appropriate appli-cation techniques for SPF, as only 11.5% of the students exhibited proficiency in this regard; Con-clusions: As future healthcare providers, medical students hold significance in promoting healthy behaviours in the broader community. This study indicates that while their knowledge about sun protection is satisfactory, there is scope for enhancement.

The Eurasian grapevine (Vitis vinifera L.) is the most widely grown horticultural crop in the world and is important for the economy of many countries. In the wine production chain, grape varieties play an important role as they directly influence the authenticity and classification of the product. Identifying the different grape varieties is therefore fundamental for quality control and inspection activities, as well as for regulating production. Currently, ampelography and molecular analysis are the main approaches to identifying grape varieties. However, both methods have limitations. Ampelography is subjective and prone to errors and is experiencing enormous difficulties as ampelographers are increasingly scarce. On the other hand, molecular analyses are very demanding in terms of cost and time. In this scenario, Deep Learning (DL) and Machine Learning (ML) methods have emerged as a classification alternative to deal with the scarcity of ampelographs and avoid molecular analyses. In this study, the most recent and current methods for identifying grapevine varieties using DL classification-based approaches are presented through a systematic literature review. The classification pipeline of the 31 studies found in the literature was described, highlighting its pros and cons. Most of the studies used DL-based models trained with leaf images acquired in a controlled environment at a maximum distance of 1.2 metres to classify grape varieties. In addition, there is a large gap between practical applications and the datasets used: a great lack of varieties, limited data acquired in the field and a lack of tests on plants under adverse conditions. Potential directions for improving this area of research were also presented.

A multiscale model that enables quantitative understanding and prediction of the size effect on scattering properties of micro- and nanostructures is crucial for the design of LED surface textures optimized for high light extraction efficiency (LEE). In this paper, a hybrid process for combining full-wave finite-difference time-domain simulation and a ray-tracing technique based on a bidirectional scattering distribution function model is proposed. We apply this method to study the influence of different pattern sizes of a patterned sapphire substrate on GaN-based LED light extraction from the microscale to the nanoscale. The results show that near-wavelength–scaled patterns with strong diffraction are not expected to enhance LEE. By contrast, microscaled patterns with optical diffusion behavior have the highest LEE at a specific aspect ratio, and subwavelength-scaled patterns that have antireflection properties show marked enhancement of LEE for a wide range of aspect ratios.

Background: Studies have tried to identify predictors of functional markers of keratoconus progression, whereas structural outcomes of collagen cross-linking have not been properly investigated. Objective: find and set up a combination of diagnostic modalities and measurements to reliably reflect CXL efficiency. Material and methods: We retrospectively reviewed the medical histories of 107 KC patients (131 eyes) who underwent CXL in a medical center from January 2018 to December 2022. The dataset included preoperative examinations and follow-up results, which provided a total of 796 observations. The cases of other corneal diseases, repeated CXL, pregnancy, and observations without follow-up examinations were excluded. Results: The study findings revealed a significant drop in the central and corneal thickness during 14.01±9.98 months of observations. Linear and polynomial equations suggested different trends in pachymetry change after CXL. The linear model showed corneal thinning, and according to the polynomials, pachymetry findings return to baseline values two years after CXL. Conclusion: The most reliable prognosis of postoperative corneal thickness is achieved with the models trained on keratometry readings and topography indices. BAD indices are also reliable predictors of the corneal thickness after CXL. A combination of the aforementioned structural parameters and their derivatives can reliably predict CXL efficiency.

Self-sustained learning (SSL) is considered a crucial factor in promoting students’ long-term learning and development in a sustainable society. To deepen the understanding of SSL, especially in the context of learning English as a second language, the current study examined the influence of intercultural communicative skills, language mindset, and positive L2 self on SSL in English learning among 1,238 college students in China. The results showed that students not only had a strong language mindset, positive L2 self, and intercultural communicative skills but also scored higher in long-term self-sustained English learning. Findings from the Structural Equation Modeling indicated that both language mindset and intercultural communicative skills positively predicted positive L2 self and self-sustained English learning. Furthermore, language mindset and intercultural communicative skills had an indirect impact on self-sustained English learning through positive L2 self. These findings suggest that to promote English learners’ SSL, instructors should help facilitate students’ intercultural communicative skills and foster a growth language mindset, as well as positive language learning beliefs.

Object recognition is an essential element of machine intelligence tasks. However, one model cannot practically be trained to identify all the possible objects it encounters. An ensemble of models may be needed to cater to a broader range of objects. Building a mathematical understanding of the relationship between various objects that share comparable outlined features is envisaged as an effective method of improving the model ensemble through a pre-processing stage, where these objects' features are grouped under a broader classification umbrella. This paper proposes a mechanism to train an ensemble of recognition models coupled with a model selection scheme to scale-up object recognition in a multi-model system. An algorithmic relationship between the learnt parameters of a trained classification model and the features of input images is presented in the paper for the system to learn the model selection scheme. The multiple models are built with a CNN structure, whereas the image features are extracted using a CNN/VGG16 architecture. Based on the models' excitation weights, a neural network model selection algorithm, which links a new object with the models and decides how close the features of the object are to the trained models for selecting a particular model for object recognition is developed and tested on a five-model neural network platform. The experiment results show the proposed model selection scheme is highly effective and accurate in selecting an appropriate model for a network of multiple models.

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.

Recent years have witnessed significant advances in reinforcement learning (RL), which has registered remarkable success in solving various sequential decision-making problems in machine learning. Most of the successful RL applications, e.g., the games of Go and Poker, robotics, and autonomous driving, involve the participation of more than one single agent, which naturally fall into the realm of multi-agent RL (MARL), a domain with a relatively long history, and has recently re-emerged due to advances in single-agent RL techniques. Although, typically, the communication protocol between agents is manually specified and not altered during training, recently, some papers have shown signs of trying to emerge a communication between agents on the one hand and, on the other hand, to understand what is exchanged between agents. So, there is a growing body of literature on this topic which includes qualitative and quantitative studies and the ones that apply mixed methods. This study presents the scoping review of the methodological strategies undertaken in a total of 16 research articles. The results present the critical appraisal of quantitative methods in terms of validity and reliability and for qualitative methods considering four trustworthiness factors. In the end, relevant insights are further explored with implications and reflections on how they can benefit one's research in the field.

This research investigates entrepreneurial attitudes among 415 students in the academic sports domain. Utilizing a 15-item questionnaire, participants were categorized into four groups based on their sports background: individual and team sports with competitive history, amateur athletes, and non-practitioners. The questionnaire exhibited good internal consistency (Cronbach's alpha coefficient = 0.755). Statistical analysis using the Chi-Square Test of Homogeneity across criteria such as gender, competitive sports involvement, type of competitive sports, and engagement in amateur sports revealed significant differences in nine out of 60 comparisons. Furthermore, this study employs an explanatory approach to elucidate the distinctions among athletes, amateur, and non-athlete students in academic sports programs regarding assumption of responsibilities, proactive initiative, determination to establish their own businesses, perception of the comfort zone, and the perception of post-sports career adaptation. Additionally, a gender comparison is conducted concerning the perception of business risk, comfort and security in a stable workplace, and the applicability of sports-oriented approaches in business. These results provide valuable insights into how sports backgrounds shape entrepreneurial perspectives, thereby contributing to the development of customized entrepreneurial programs. Moreover, the study seeks to offer a nuanced comprehension of the diverse factors influencing the entrepreneurial attitudes and perceptions of students in sports academic programs.

In this paper, we continue the research cycle on the properties of convolutional neural network-based image recognition systems and ways to improve noise immunity and robustness [1]. Currently, a popular research area related to artificial neural networks is adversarial attacks. The effect of adversarial attacks on the image is not highly perceptible to the human eye, also it drastically reduces the neural network accuracy. Image perception by a machine is highly dependent on the propagation of high frequency distortions throughout the network. At the same time, a human efficiently ignores high-frequency distortions, perceiving the shape of objects as a whole. The approach proposed in this paper can improve the image recognition accuracy in the presence of high-frequency distortions, in particular, caused by adversarial attacks. The proposed technique makes it possible to measure up the logic of artificial neural network to that of a human, for whom high-frequency distortions are not decisive in object recognition.

Accurate seasonal weather forecasts are vital across a broad spectrum of applications, bearing significant environmental and socioeconomic implications. This importance renders the subject a matter of primary interest to a wide range of stakeholders, including the general public, agricultural sector, emergency responders, financial institutions, and policy strategists. The need for precision in long-term predictive models necessitates the development of innovative methodologies. These methodologies should be capable of deciphering atmospheric patterns and mechanisms with detail, especially at a local level, without the resource constraints that dynamical downscaling imposes. In response to this expanding demand, this study presents a novel solution, combining a stochastic deep learning methodology, specifically Generative Adversarial Networks (GANs), with a Digital Elevation Model (DEM). The cornerstone of the proposed model is the enhancement of gridded temperature fields from seasonal forecasts. The area of focus was the Hellenic region, wherein the spatial resolution is amplified from a coarse 1° x 1° grid to an impressively detailed 0.1° x 0.1° grid. This offers a transformative perspective for interpreting and employing this crucial meteorological data. The results suggest that the downscaled fields adequately approximate the actual spatial distribution, although the predicted values tend to slightly overestimate and in some cases underestimate the original ones. This study underlines the potential of this approach to significantly enhance the resolution and utility of weather forecasts, thereby contributing to a variety of sectors dependent on reliable meteorological data.

Conditional generative adversarial networks (CGANs) learn a mapping from conditional input to observed image and perform tasks in image generation, manipulation and translation. In-situ monitoring uses sensors to obtain real-time information of additive manufacturing (AM) processes that relate to process stability and part quality. Understanding the correlations between process inputs and in-situ process signatures through machine learning can enable experimental-driven predictions of future process inputs. In this research, in-situ data obtained during a metallic powder bed fusion AM process is mapped with a CGAN. A single build of two turbine blades is monitored using EOSTATE Exposure OT, a near-infrared optical tomography system of the EOS M290 system. Layerwise images generated from the in-situ monitoring system were paired with a conditional image that labeled the specimen cross-section, laser-scan stripe overlap and z-distance to part surfaces. A CGAN was trained using the turbine blade data set and employed to generate new in-situ layerwise images for unseen conditional inputs.

Hepatitis B surface antigen (HBsAg) is not only the biomarker of hepatitis B virus (HBV) infection and expression activity in hepatocytes, but also contributes to viral specific T cell exhaustion and HBV persistent infection. Therefore, anti-HBV therapies targeting HBsAg to achieve HBsAg loss are key approaches for HBV functional cure. In this study, we found that YZH-106, a rupestonic acid derivative, inhibited HBsAg secretion and viral replication. Further investigation demonstrated that YZH-106 promoted the lysosomal degradation of viral L- and M-HBs proteins. Mechanistic study by Biacore and docking analysis revealed that YZH-106 bound directly to PreS2 domain of L- and M-HBsAg, thereby blocking their entry to the endoplasmic reticulum (ER) and promoting their degradation in cytoplasm. Our work thereby provide basis for design of novel compound therapy to target HBsAg against HBV infection.

The potential of quantum computing for scientific and industrial breakthroughs is immense, however, we are still in the Noisy Intermediate-Scale Quantum (NISQ) era, where the currently available quantum devices contain small numbers of qubits, are very sensitive to environmental conditions and prone to quantum decoherence. Even so, existing NISQ computers have already been shown to outperform conventional computers on specific problems and the key question is how to make use of today’s NISQ devices to achieve quantum advantage in the field of computational science and engineering (CSE). In this direction, this work proposes a hybrid computing formulation by combining quantum computing with machine learning for accelerating the solution of parameterized linear systems in NISQ devices. In particular, it focuses on the Variational Quantum Linear Solver (VQLS), which is a hybrid quantum- classical algorithm for solving linear systems of equations. VQLS employs a short-depth quantum circuit to efficiently evaluate a cost function related to the system solution. The algorithm’s circuit consists of a quantum gate sequence (unitary operators) that involves a set of tunable parameters. Then, well-established classical optimizers are utilized to tune the parameters of the sequence in order to minimize the cost function, which is equivalent to finding the system solution at an acceptable level of accuracy. In this work, it is demonstrated that machine learning tools such as feed-forward neural networks and nearest-neighbor interpolation techniques can be successfully employed to accelerate the convergence of the VQLS algorithm towards the optimal values for the circuit parameters when applied to parameterized linear systems that need to be solved for multiple parameter instances.

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

This letter presents a dual-frequency terahertz amplitude modulator based on a cross-shaped structure and U-shaped metal patches. Its structural unit is a typical metal-substrate structure. The top metal consists of a cross-shaped structure and U-shaped metal patches, and the bottom substrate layer is made of quartz. Amplitude modulation is achieved by adjusting the temperature of the vanadium dioxide (VO2) patches. The modulation depth can be approximately 75%. The mechanism of the resonance frequency is explained by the equivalent circuit model. The proposed structure shows good amplitude modulation capability at different incidence and azimuth angles by changing the location of the VO2 patches. The dual-frequency terahertz amplitude modulator can be used in terahertz communication, imaging, etc.

Understanding the dynamics of teamwork and communication among healthcare professionals is crucial in the face of evolving healthcare challenges. This study assessed relational coordination among healthcare professionals in the South Tyrolean healthcare system in Italy, focusing on communication and teamwork dynamics in a cross-sectional survey. Using the validated Relational Coordination Survey (RCS) instrument and 525 completed online responses, the questionnaire aimed to understand the implications of different levels of relational coordination ratings by general practitioners, hospital physicians, nurses, and administrative personnel (response rate 26%). The demographics of the participants revealed a predominance of female professionals (64%), with an average age of 50 and 18 years of service. The resulting RCS scores varied significantly across professional groups, with nurses reporting the highest within-group scores, indicating moderate coordination, and administrators reporting the lowest scores, reflecting areas of weak coordination. Between-group relational coordination was generally perceived as weak across professional groups, with the least weakness observed between general practitioners and nurses. German or Italian language and health district affiliation emerged as significant factors influencing relational coordination ratings, highlighting the need for differentiated understanding and strategies in multilingual and diverse regional settings. Assessments of interdisciplinary feedback and referral practices highlight the variation in teamwork and communication weaknesses and underscore the need for targeted interventions to improve relational coordination. This study provides insights into the complexity of relational dynamics in health care settings. It suggests that improving relational coordination through tailored strategies could significantly improve team effectiveness, quality of patient care, and overall system efficiency.

In the context of sustainable development, integrating the work aspect into health promotion systems is essential, ensuring that employees maintain a healthy balance between their professional and personal lives, which respects and amplifies the potential of every individual. Lately, there has been a noticeable shift of medical professionals from the public to the private sector. This trend paints a bleak picture, highlighting the vulnerabilities of a system teetering on the brink of failure, with significant impacts on patient care. Among the myriad reasons behind this shift, burnout stands out prominently. Medical professionals face increasing pressures due to understaffing, limited organizational support, and insufficient resources, leading to feelings of cynicism, exhaustion, and detachment from their roles. Utilizing the Maslach et al. questionnaire, we assessed the risk of burnout among physicians in public hospitals to identify and underscore preventive measures and improvements, correlating our findings with key aspects of organizational empowerment. Our research indicates that enhancing interpersonal relationships and resources—both within teams and between the organization and its physicians—is crucial for the revival of the healthcare system. This approach aims at improving the delivery of healthcare services and offering appropriate recognition to healthcare professionals, aligning with the principles of sustainable employment.

In Korea, the underground silo structure for low- and intermediate-level radioactive waste disposal facilities has been constructed and operated since 2014. Large-scale earthquakes occurred in 2016 and 2017, respectively, in Gyeongju and Pohang areas near the underground silo structures, and interest in the stability of the underground silo increased significantly. In this paper, one-dimensional free field analyses have been carried out before the three-dimensional silo dynamic analyses subjected to earthquake loadings. As an additional study, a new form of finite element equilibrium equation is derived in terms of relative motions, which is essentially the same equation as that expressed in terms of total motions where the base shear force is applied for earthquake load. The accuracy of conventional finite element solutions is evaluated by directly comparing them with closed-form solutions by frequency domain analysis such as SHAKE91.

Visual object tracking is an important technology in camera based sensor networks, which has a wide range of practicability in auto drive system. A transformer is a deep learning model that adopts the mechanism of self-attention, and it differentially weights the significance of each part of the input data. It has been widely applied in the field of visual tracking. Unfortunately, the security of the transformer model is unclear. It makes such transformer-based applications be exposed to security threats. In this work, the security of the transformer model is investigated with the important component of autonomous driving, visual tracking. Such deep-learning-based visual tracking is vulnerable to adversarial attacks, so adversarial attacks are implemented as the security threats to conduct the investigation. First, adversarial examples are generated on top of video sequences to degrade tracking performance, and the frame-by-frame temporal motion is taken into consideration when generating perturbations over the predicted tracking results. Then, the influence of perturbations on performance is sequentially investigated and analyzed. Finally, numerous experiments on OTB100, VOT2018, and GOT-10k data sets demonstrate that the executed adversarial examples are effective on the performance drops of the transformer-based visual tracking.

In this paper, we propose an unsupervised blind restoration model for images in hybrid degradation scenes. The proposed model encodes the content information and degradation information of images and then uses the attention module to disentangle the two kinds of information. It can improve the ability of disentangled presentation learning for a generative adversarial network (GAN) to restore the images in hybrid degradation scenes, enhance the detailed features of restored image and remove the artifact combining the adversarial loss, cycle-consistency loss, and perception loss. The experimental results on the DIV2K dataset and medical images show that the proposed method outperforms existing unsupervised image restoration algorithms in terms of peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and subjective visual evaluation.

The combination of new-generation information technology and manufacturing technology has resulted in major and profound impact on future development paradigm of manufacturing. It is challenging for existing methods to conduct a multidimensional trend exploration related to machine tool domain, which is the basis of virtually everything in manufacturing. In this paper, we proposed an integrating approach framework combined topic models, bibliometric, trend analysis and patent analysis to mine insightful information about future development from multi-source data related to machine tool, such as papers, grants, patents and news. Specifically, papers and grants provided two different perspectives to explore the current focuses and future trends in machine tool research. Furthermore, the future technology development of machine tool was investigated through patents analysis. Finally, news related to machine tool industry in recent years was analyzed to analyze future machine tool business mode. The integration of the above various analytical methods and the multi-dimensional mining of literatures enabled the analysis of the future development of machine tool domain systematically from multi-perspectives which include research, technology development and industry. The conclusions obtained in this paper is beneficial to different communities of machine tool in terms of determining the research directions for researchers, identifying industry opportunities for corporations and developing reasonable industry policy for policy makers.

In recent years there has been a clear increase in bottled water consumption, globally which translates to significant health and environmental concerns. This cross-sectional study aims to understand the attitude and preferences of university students in Qatar towards use of bottled and tap water for drinking purposes using an online survey questionnaire. The number of students who responded to the online survey was 14% of the entire student population within the university (n = 688). Overall, majority of the students reported plastic bottled water as the main source of drinking water they preferred to use on campus (n=468; 68.02%), with a higher proportion of females (72.08%) preferring the use of plastic bottled water. Out of the 468 students who preferred plastic bottled water, safety was the most important factor (43.80%) followed by convenience (16.88%) and taste (15.60%). Cost (15.17%), personal/family habits (5.13%), Environmental concerns (2.14%) and minerals (1.28%) were found to be the least important factors. Among the 45 students who preferred tap water over plastic bottled water, cost (46.67%) was the dominant factor followed by convenience (20.00%) and environmental concerns and safety (13.33% each), taste (4.44%), and personal/family habits (2.22%). This study recommends campaigns to focus on attitude and behavior change and not solely emphasize knowledge; 71.7% believed that plastic water bottles are more harmful to the environment, yet the greater majority still resorted to this source. There is an immediate need to further educate students through environmental and health literacy programs on water consumption and quality. Enabling the population to understand the positive and negative aspects of their choices, may be an effective remedy to ensuring a healthy population and healthy environment.

The increase in the frequency of droughts in Africa has increased the interest in crops with drought escape mechanisms like grain Amaranth (Amaranthus hypochondriacus). However, the white-seeded grain Amaranth is easily cross-pollinated by its black seeded wild relatives such as smooth pigweed (Amaranthus hybridus). A study to investigate a minimum isolation distance enough to prevent seed contamination study was carried out at three sites namely Gweru and Bindura (2020/2021 rainy season) and Shamva (2021/2022 rainy season). Smooth pigweed was planted at distances of 3 to 150 m from pure grain Amaranth. Close monitoring of phenology and measurement of meteorological conditions such as temperature, wind speed and direction were done during the anthesis period. Cross-pollination in grain Amaranth was influenced by distance from the pollen source. A maximum of 12.9 % contamination rate was measured within the 10 m radius from the pollen donor plot and a minimum outcrossing rate of 0.45 % was recorded at the widest distance of 150 m. It can be concluded that complete removal of wild relatives of grain Amaranth is important within the field at as far as 150 m from the crop.

Pulmonary Embolism (PE) is the obstruction of blood arteries in the lungs by a blood clot. The mortality risk for PE is approximately 30%. Detecting pulmonary embolism in the segmental arteries of the lung is more challenging than in the main arteries and is very prone to being missed. A computer-based approach was created in this work to automatically identify pulmonary embolism in the segmental arteries using computed tomography images. The system's infrastructure includes an enhanced Mask R-CNN deep neural network that has been trained with images containing PE. The network accurately identifies the location of the pulmonary embolism on the computed tomography picture and successfully extracts its borders. The investigation was conducted by generating a local dataset. The study's performance was evaluated using pulmonary embolisms identified manually by the expert radiologist. The sensitivity, specificity, accuracy, dice coefficient, and Jaccard index values for 2130 pictures were 96.4%, 93.5%, 96.1%, 0.96, and 0.90, respectively. The improved Mask R-CNN model has demonstrated superior performance when compared to the traditional Mask R-CNN and U-Net models. This high-performance technology is designed to identify pulmonary embolism and will aid professionals in assessing the size of the embolism.

This study presents a detailed computational investigation aimed at identifying and evaluating potential small organic molecular scaffolds as inhibitors targeting the Pks13 protein, a critical enzyme in tuberculosis (TB) drug discovery. Our approach integrates multiple computational techniques, including quantitative structure-activity relationship (QSAR) modelling, compound library generation, molecular docking, biological activity prediction, re-evaluation of screened compounds, molecular dynamics (MD) analysis, and binding free energy estimation using the MM-GBSA approach. We developed a robust QSAR model using multiple linear regression (MLR) techniques, specifically tailored to predict the minimum inhibitory concentration (MIC) values of potential anti-TB agents. This model demonstrated excellent predictive performance, validated through rigorous internal and external validation procedures. Through molecular docking simulations, we identified five promising inhibitors Ethyl (R,Z)-2-(2-((2-chlorobenzyl) oxy)benzylidene)-5-(4-chlorophenyl)-7-methyl-3-oxo-2,3-dihydro-5H-thiazolo [3,2-a] pyrimidine-6-carboxylate (PKD1), (7R,9aR)-7-(2-hydroxyphenyl)-4-(2-methoxyphenyl)-3-methyl-7,8,9,9a-tetrahydroisoxazolo[5,4-b]quinolin-5(6H)-one (PKD2), (7-(4-methoxy phenyl)-2-methyl-3-phenylpyrazolo[1,5-a]pyrimidin-5-yl)(4-(3-(trifluoromethyl)phenyl) piperazin-1-yl)methanone (PKD3), (8S,10S)-10-(((2R,4S,5S,6S)-4-amino-5-hydroxy-6-methyl tetrahydro-2H-pyran-2-yl)oxy)-6,8,11-trihydroxy-8-(2-hydroxyacetyl)-1-methoxy-7,8,9,10-tetra-hydrotetracene-5,12-dione (PKD4), 3-(3,4-dimethylphenyl)-5-((2-(4-fluorophenyl)-2-oxoethyl) thio)-6-phenyl-2-thioxo-2,3,5,7a-tetrahydrothiazolo[4,5-d]pyrimidin-7(6H)-one (PKD5)with high binding affinities, prioritizing them based on their binding energies. These selected compounds were further assessed for their biological activity predictions, guiding the selection of candidates for experimental validation. Subsequent re-evaluation using absolute binding free energy estimation and MD simulations provided insights into the stability and dynamics of the protein-ligand complexes over time. Our findings highlighted the potential of identified compounds as stable binders within the Pks13-TE domain binding pocket, underscoring their viability as drug candidates. Additionally, binding free energy analysis using MM-GBSA reaffirmed the strong affinity of the proposed compounds towards Pks13. Our integrated computational approach offers a systematic and detailed framework for the identification and characterization of potential Pks13 inhibitors with specific relevance to TB drug discovery.

This paper analyses the application of deep learning techniques for predicting wave overtopping events in port environments using sea state and weather forecasts as inputs. The study was conducted in the outer port of Punta Langosteira, A Coruña, Spain. A video recording infrastructure was installed to monitor overtopping events from 2015 to 2022, identifying 3709 overtopping events. The data collected was merged with actual and predicted data for the sea state and weather conditions during the overtopping events, creating three datasets. We used these datasets to create several machine learning models to predict whether an overtopping event would occur based on sea state and weather conditions. The final models achieved a high accuracy level during the training and testing stages: 0.81, 0.73, and 0.84 average accuracy during training and 0.67, 0.48, and 0.86 average accuracy during testing, respectively. The results of this study have significant implications for port safety and efficiency, as wave overtopping events can cause disruptions and potential damage. Using deep learning techniques for overtopping prediction can help port managers take preventative measures and optimize operations, ultimately improving safety and helping to minimize the economic impact that overtopping events have on the port's activities.

DNA Topoisomerase IIa (Top2A) is a nuclear enzyme that is a cancer drug target, and there is interest in identifying novel sites on the enzyme to inhibit cancer cells more selectively and to reduce off-target toxicity. The C-terminal domain (CTD) is one potential target, but it is an intrinsically disordered domain, which prevents structural analysis. Therefore, we set out to analyze the sequence of Top2A from 105 species using bioinformatic analysis including the PSICalc algorithm, entropy analysis, and other approaches. Our results demonstrate that large (10th-order) interdependent clusters are found including non-proximal positions across the major domains of Top2A. Further, CTD-specific clusters of 3rd, 4th, and 5th-order were identified that included positions that had been previously analyzed via mutation and biochemical assays. Some of these clusters coincided with positions that when mutated either increased or decreased relaxation activity. Finally, sites of low entropy (i.e., high information content) were identified and mapped as key positions in the CTD. Included in the low entropy sites are phosphorylation sites and charged positions. Together, these results help to build a clearer picture of the critical positions in the CTD and provide potential sites/regions for further analysis.

Pregnant women (PW) are at a higher risk of diseases and hospitalization from viral respiratory infections, specially influenza, due to cardiopulmonary and immunological changes. This study assessed the impact of viral respiratory infections on PW hospitalized with severe acute respiratory infection (SARI). It´s a cross-sectional study with 42 PW and 85 non-pregnant women (NPW) admitted with SARI to two tertiary hospital between January 2015 and December 2019. The rate of virus prevalence, SARI hospitalization, length of hospital stay, oxygen supplementation, intensive care unit (ICU) admission, and death were comparable between PW and NPW. Multivariate analysis showed that PW had a higher rate of viral SARI hospitalizations (OR = 2.37; 95% CI =1.02 - 5.48) compared to NPW, with influenza virus being the most prevalent (aOR =7.58; 95% CI =1.53 - 37.66). Length of hospital stay (aOR = 0.83; 95% CI = 0.73 – 0.95) and admission to the ICU (aOR=0.028; 95% CI=0.004 - 0.25) were lower in PW compared to hospitalized NPW. Respiratory viruses had a greater impact on the frequency of SARI in the group of PW. Although PW had a higher rate of influenza SARI, they had a better outcome than NPW due to the treatment they received.

Bixonimania, a rare hyperpigmentation disorder characterized by a distinctive pink hue on the eyelids, presents a significant diagnostic challenge due to its unique presentation and limited research. This study explores the application of machine learning algorithms for bixonimania detection by analyzing millions of images of individuals exposed to blue light (500-700 nm spectrum). Our findings suggest a potential link between blue light exposure and bixonimania, affecting roughly 1 in 90,000 individuals. The proposed machine learning model achieved an accuracy of 92% in detecting bixonimania based on eyelid hue analysis. This study paves the way for further exploration of bixonimania's underlying causes, improved diagnostic tools, and potential treatment options.