In recent years, with the widespread application of Vision Transformer (ViT) in visual trackers, their robustness has received increasing attention. However, by focusing on global interactions between image patches, ViT reduces sensitivity to local noise, posing new challenges for adversarial attacks. Meanwhile, existing decision-based adversarial attack methods often overlook the differences in noise sensitivity between different patches, further limiting the compression efficiency of adversarial noise, especially in ViT. In visual tracking, existing adversarial attack methods primarily target Siamese network-based trackers, and research on adversarial attacks against Transformer-based trackers, particularly decision-based black-box attacks, is still relatively limited. To implement effective black-box attacks on Transformer-based trackers, this paper innovatively proposes patch-based adversarial noise compression (PANC), a decision-based adversarial attack method. This method effectively compresses adversarial noise patch by patch, significantly improving compression efficiency and attack concealment. PANC also introduces a noise sensitivity matrix that dynamically adds and reduces adversarial noise, optimizing the spatial distribution of noise while decreasing the number of queries. We validated the effectiveness of the proposed PANC attack method on several Transformer-based trackers, including OSTrack, STARK, TransT, and MixformerV2, and three public large-scale benchmark datasets: GOT-10k, TrackingNet, and LaSOT. Experimental results show that compared to the existing state-of-the-art adversarial attack method, the IoU attack, PANC compresses the noise level to 10%, improving the attack effectiveness by 162% with the number of queries of only 45.7%. Furthermore, PANC can serve as an initialization or post-processing optimization strategy for other adversarial attack methods, providing a more flexible and efficient mechanism for adversarial example generation. Our work reveals the vulnerabilities of existing Transformer-based visual trackers and offers new ideas for further improving the efficiency and concealment of adversarial attacks.

Motor rehabilitation for pediatrics with hand injuries often suffers from low engagement due to the repetitive and non-interactive nature of traditional therapy. In addition, fluctuating performance during therapy sessions demands a system capable of adapting to the child’s changing abilities. These challenges, combined with limited access to rehabilitation services in rural or remote areas, frequently lead to boredom, reduced participation, and delayed recovery. To address these issues, this paper presents Mareen, an intelligent rehabilitation system designed to enhance therapy effectiveness by leveraging computer vision techniques and Dynamic Difficulty Adjustment (DDA). The system utilizes computer vision to track finger joint movements during exercises. A total of 6,336 hand movement samples were collected and categorized into three difficulty levels based on performance indicators. Four machine learning models were trained and evaluated, with the Random Forest model achieving the highest accuracy (97.3%) in real-time difficulty prediction. Gamification elements were integrated to increase motivation, and the system automatically generates progress reports to support therapists in monitoring outcomes. Mareen provides an effective, adaptive, and engaging rehabilitation experience suitable for both home and clinical use.

This paper introduces a multi-method explainable artificial intelligence framework designed as a foundational step toward European Union AI Act-compliant automated ICD-10 coding. The framework integrates three complementary explainability methods: label-wise attention, SHAP and case-based reasoning. Unlike existing approaches that typically employ single explanation methods, this new framework creates a comprehensive implementation of multiple explainable techniques while implementing stratified evaluation across different data complexity levels. The architecture leverages a transformer-based model with label-wise attention aggregation. While current performance levels require further development before industry deployment, preliminary results demonstrate competitive performance with micro-F1 score of 0.565 and explanation coverage of 87.1%, establishing critical infrastructure for regulatory-compliant explainable AI in healthcare.

One-class classification (OCC) is a supervised classification problem where the training data is solely one class. OCC cannot execute hyperparameter tuning because its evaluation requires access to other classes; the algorithm will no longer be OCC if the model is updated after accessing other classes. To address this issue, this paper proposes hyperparameter fusion, which is applicable without the evaluation. The fusion process applies ensemble learning techniques, voting, and stacking into OCC models trained on different hyperparameters. The experiments involve 54 OCC problems from 27 imbalanced learn datasets and 115 hyperparameter candidates. The experiment results show that hyperparameter fusion outperformed the average base learners in the area under the receiver operating characteristic (AUC) score. Moreover, removing the worst base learner can improve the AUC score for the ensemble. The discussion section predicts the worst base learner from correlations of normality rankings created by model outputs. The worst base learner has relatively small ranking correlations to the ensemble model compared to other base learners.

In recent years, visual tracking methods based on convolutional neural networks and transformers have achieved remarkable performance and have been successfully applied in fields such as autonomous driving. However, the numerous security issues exposed by deep learning models have gradually affected the reliable application of visual tracking methods in real-world scenarios. Therefore, how to reveal the security vulnerabilities of existing visual trackers through effective adversarial attacks has become a critical problem that needs to be addressed. To this end, we propose an adaptive meta-gradient adversarial attack (AMGA) method for visual tracking. This method integrates multimodel ensemble and meta-learning strategies, combining momentum mechanisms and Gaussian smoothing, which can significantly enhance the transferability and attack effectiveness of adversarial examples. AMGA randomly selects models from a large model repository, constructs diverse tracking scenarios, and iteratively performs both white- and black-box adversarial attacks in each scenario, optimizing the gradient directions of each model. This paradigm minimizes the gap between white- and black-box adversarial attacks, thus achieving excellent attack performance in black-box scenarios. Extensive experimental results on large-scale datasets, such as OTB2015, LaSOT, and GOT-10 k demonstrate that AMGA significantly improves the attack performance, transferability, and deception of adversarial examples.

Abstract Disease diagnosis is an exciting task due to many associated factors. Inaccuracy in the measurement of a patient’s symptoms and the medical expert’s expertise has some limitations capacity to articulate cause affects the diagnosis process when several connected variables contribute to uncertainty in the diagnosis process. In this case, a decision support system that can assist clinicians in developing a more accurate diagnosis has a lot of potentials. This work aims to deploy a fuzzy inference-based decision support system to diagnose various diseases. Our suggested method distinguishes new cases based on illness symptoms. Distinguishing symptomatic disorders becomes a time-consuming task in most cases. It is critical to design a system that can accurately track symptoms to identify diseases using a fuzzy inference system (FIS). Different coefficients were used to predict and compute the severity of the predicted diseases for each sign of disease. This study aims to differentiate and diagnose COVID-19, typhoid, malaria and pneumonia. The FIS approach was utilized in this study to determine the condition correlating with input symptoms. The FIS method demonstrates that afflictive illness can be diagnosed based on the symptoms. Our decision support system’s findings showed that FIS might be used to identify a variety of ailments. Doctors, patients, medical practitioners and other healthcare professionals could benefit from our suggested decision support system for better diagnosis and treatment.