arXiv subjects

Beyazit Bestami Yuksel

Publications and source records attributed to Beyazit Bestami Yuksel.

5 recordsLinked to original sources

arXiv2026

Hardware-Aware Federated Learning for Speech Emotion Recognition

Federated learning (FL) enables privacy-preserving collaborative training across distributed edge devices, but real deployments involve heterogeneous clients with different processing power, memory capacity, and communication latency, which often increase round duration and system cost. This paper proposes a hardware-aware federated learning framework for emotion recognition on session-partitioned IEMOCAP that integrates hardware profiling, top-K client selection, and adaptive local epochs within a unified training loop. We compare the method against FedAvg, FedProx, and random top-K selection under a non-IID setup and show that, across 50 federated rounds and 5 independent trials, the proposed approach achieves competitive validation accuracy (0.352), reduces total training time by about 36.5% compared to FedAvg, and lowers cumulative communication cost by 40%.

cs.LG↗

arXiv2025

Monitoring Real-Time ECG Signals on Mobile Systems

This study focuses on the connection of a development kit that enables real-time monitoring of electrocardiogram (ECG) signals using a mobile system. A software developed on the Visual Studio .NET platform reads real-time ECG signals from the human body through non invasive methods and displays them graphically on the mobile system. ECG electrodes placed on specific areas of the body using the method known as Einthoven's triangle. Subsequently, the software initiates data flow through the serial port, and these data displayed as signal values on the mobile device's screen via a graphical interface. When the monitored ECG signals fall below a certain threshold or reach a critical value, the system provides feedback with an alert based on medical data. The developed system is fully portable. Additionally, the implemented system has the potential to form the basis for a multi-purpose system in the future, such as online patient monitoring, patient location tracking, and even initial intervention using the defibrillation method.

eess.SP↗

arXiv2025

Data-Driven Breakthroughs and Future Directions in AI Infrastructure: A Comprehensive Review

This paper presents a comprehensive synthesis of major breakthroughs in artificial intelligence (AI) over the past fifteen years, integrating historical, theoretical, and technological perspectives. It identifies key inflection points in AI' s evolution by tracing the convergence of computational resources, data access, and algorithmic innovation. The analysis highlights how researchers enabled GPU based model training, triggered a data centric shift with ImageNet, simplified architectures through the Transformer, and expanded modeling capabilities with the GPT series. Rather than treating these advances as isolated milestones, the paper frames them as indicators of deeper paradigm shifts. By applying concepts from statistical learning theory such as sample complexity and data efficiency, the paper explains how researchers translated breakthroughs into scalable solutions and why the field must now embrace data centric approaches. In response to rising privacy concerns and tightening regulations, the paper evaluates emerging solutions like federated learning, privacy enhancing technologies (PETs), and the data site paradigm, which reframe data access and security. In cases where real world data remains inaccessible, the paper also assesses the utility and constraints of mock and synthetic data generation. By aligning technical insights with evolving data infrastructure, this study offers strategic guidance for future AI research and policy development.

cs.AI↗

arXiv2024

ECG-PPS: Privacy Preserving Disease Diagnosis and Monitoring System for Real-Time ECG Signal

This study introduces the development of a state of the art, real time ECG monitoring and analysis system, incorporating cutting edge medical technology and innovative data security measures. Our system performs three distinct functions thaat real time ECG monitoring and disease detection, encrypted storage and synchronized visualization, and statistical analysis on encrypted data. At its core, the system uses a three lead ECG preamplifier connected through a serial port to capture, display, and record real time ECG data. These signals are securely stored in the cloud using robust encryption methods. Authorized medical personnel can access and decrypt this data on their computers, with AES encryption ensuring synchronized real time data tracking and visualization. Furthermore, the system performs statistical operations on the ECG data stored in the cloud without decrypting it, using Fully Homomorphic Encryption (FHE). This enables privacy preserving data analysis while ensuring the security and confidentiality of patient information. By integrating these independent functions, our system significantly enhances the security and efficiency of health monitoring. It supports critical tasks such as disease detection, patient monitoring, and preliminary intervention, all while upholding stringent data privacy standards. We provided detailed discussions on the system's architecture, hardware configuration, software implementation, and clinical performance. The results highlight the potential of this system to improve patient care through secure and efficient ECG monitoring and analysis. This work represents a significant leap forward in medical technology. By incorporating FHE into both data transmission and storage processes, we ensure continuous encryption of data throughout its lifecycle while enabling real time disease diagnosis.

cs.CR↗

arXiv2024

Advancing Biomedical Signal Security: Real-Time ECG Monitoring with Chaotic Encryption

The real time analysis and secure transmission of electrocardiogram (ECG) signals are critical for ensuring both effective medical diagnosis and patient data privacy. In this study, we developed a real time ECG monitoring system that integrates chaotic encryption to protect the integrity and confidentiality of ECG signals during acquisition, transmission, and storage. By leveraging the logistic map as the chaotic function for encryption, our system offers a highly secure framework that dynamically encrypts ECG signals without adding significant latency. To validate the system's reliability, we applied a series of security tests. The results demonstrate that chaotic encryption is effective in enhancing data security, as evidenced by high entropy values and strong key sensitivity, ensuring protection against common cryptographic attacks. Additionally, the system's real time disease detection model, based on deep learning, operates seamlessly with encrypted data, providing accurate diagnosis without compromising security. Our findings indicate that chaotic encryption, paired with real time analysis, is a powerful method for protecting sensitive medical data, making this approach particularly relevant for telemedicine and remote patient monitoring applications. The success of this system highlights its potential for broader application to other biomedical signals, providing a secure infrastructure for the future of digital health.

cs.CR↗