Search

Advances in the early detection of breast cancer and treatment improvements have significantly increased survival rates. Traditional screening methods, including mammography, MRI, ultrasound, and biopsies, while effective, often come with high costs and risks. Recently, thermal imaging has gained attention due to its minimal risks compared to mammography, although it is not widely adopted as a primary detection tool since it depends on identifying skin temperature changes and lesions. The advent of machine learning (ML) and deep learning (DL) has enhanced the effectiveness of breast cancer detection and diagnosis using this technology. In this study, a novel interpretable computer aided diagnosis (CAD) system for breast cancer detection is proposed, leveraging Explainable Artificial Intelligence (XAI) throughout its various phases. To achieve these goals, we proposed a new multi-objective optimization approach named the Hybrid Particle Swarm Optimization algorithm (HPSO) and Hybrid Spider Monkey Optimization algorithm (HSMO). These algorithms simultaneously combined the continuous and binary representations of PSO and SMO to effectively manage trade-offs between accuracy, feature selection, and hyperparameter tuning. We evaluated several CAD models and investigated the impact of handcrafted methods such as Local Binary Patterns (LBP), Histogram of Oriented Gradients (HOG), Gabor Filters, and Edge Detection. We further shed light on the effect of feature selection and optimization on feature attribution and model decision-making processes using the SHapley Additive exPlanations (SHAP) framework, with a particular emphasis on cancer classification using the DMR-IR dataset. The results of our experiments demonstrate in all trials that the performance of the model is improved. With HSMO, our models achieved an accuracy of 98.27% and F1-score of 98.15% while selecting only 25.78% of the HOG features. This approach not only boosts the performance of CAD models but also ensures comprehensive interpretability. This method emerges as a promising and transparent tool for early breast cancer diagnosis. [ABSTRACT FROM AUTHOR]

This paper presents a multi-agent license plate recognition system, specifically designed to address the diverse and challenging nature of license plates. Utilizing a multi-agent architecture with agents operating in individual Docker containers and orchestrated by Kubernetes, the system demonstrates remarkable adaptability and scalability. It leverages advanced neural networks, trained on a comprehensive dataset, to accurately identify various license plate types under dynamic conditions. The system's efficacy is showcased through its threelayered approach, encompassing data collection, processing, and result compilation, significantly outperforming traditional license plate recognition (LPR) systems. This innovation not only marks a technological leap in license plate recognition but also offers strategic solutions for enhancing traffic management and smart city infrastructure globally. [ABSTRACT FROM AUTHOR]

Abstract—This paper investigates the integration of Zero-Knowledge Proofs (ZKP) and OAuth 2.0 to enhance anonymity and security in multi-agent distributed systems. We propose an approach that allows agents to authenticate and prove possession of specific data without revealing the underlying details. Additionally, we outline a potential access control strategy using ZKP for anonymity, allowing agents to validate their access rights without identity exposure. When combined with OAuth 2.0, this mechanism provides a framework for secure data access. While the proposed methods offer promising solutions to security, privacy, and anonymity challenges in multi-agent systems, they also highlight the need for further research and validation to confirm their effectiveness.

Multimorbidity is one of the major problems in recent health care systems, the more conditions the patients suffer from, the worst psychological pressures are put upon these patients. We formulate Multimorbidity detection as a hypergraph learning problem. Then we propose an implementation of a multimorbidity pattern detection using Multimorbidity coefficient score. This pairwise based algorithm can be considered as a baseline to which other data-driven and machine learning techniques for multimorbidity pattern detection can be evaluated. We illustrate this algorithm by building a co-occurrence model for comorbid diseases over psycho-social profiles present in a real dataset. Based on the comorbidity network of diseases, we conducted mesoscopic analysis using centrality analysis of network disease/nodes and determined potential components of the network using community detection algorithms. The patterns detected in this work by the used algorithms reveal first, that the proposed algorithm can be used as a baseline to other approaches. Second, that aging does not influence the risk of developing Multimorbidity diseases just in quantity, but also in complexity.