arXiv subjects

Yaser M. Banad

Publications and source records attributed to Yaser M. Banad.

9 recordsLinked to original sources

arXiv2026

Adaptive Ecological Momentary Assessment with a Hybrid Language Model: Formative Expert Review and Retrospective Evaluation

Ecological momentary assessment (EMA) measures experience in daily life, but fixed questionnaires and schedules collect information of uneven value and can interrupt participants. We present and retrospectively evaluate EMA-E4B, a hybrid framework for question selection and prompt timing. Separate ridge models propose an item set and delay; a supervised Gemma 4 E4B language layer produces the final structured response and explanation. Evaluation distinguishes proxy action performance, output conformity, and formative judgments of response quality. The data contain 4,372 records from 79 participants and yield 3,516 sequential cases under a participant separated split. One involved domain expert preferred the complete hybrid response in 15 of 20 decisive comparisons, with two ties among 22 reviews. On 75 reused development cases, hybrid question utility and timing similarity were 0.832 and 0.818; the head alone reached 0.852 and 0.818. A separate 60 case comparison with untouched E4B under the same head gave action differences of -0.0031 and -0.0105. Thus, the language layer produced structured responses with action scores comparable to or slightly below the reference configurations, while the expert feedback favored the complete hybrid response. These observations establish a concrete, inspectable framework and clarify the distinct roles of action scoring and response review. Repeated adaptive administration and practical effects on measurement and participant burden remain future research.

cs.HC↗

arXiv2026

Machine Learning Framework for Magnetic Candidate Discovery in Cerium-Based Compounds

Cerium (Ce), the most abundant lanthanide, offers significant potential for addressing shortages in high-performance magnetic materials, particularly through the discovery of compounds suitable for gap magnets. However, predicting Ce-based ferromagnets with uniaxial magnetic anisotropy remains challenging because their magnetic behavior depends strongly on crystal structure, exchange geometry, and electronic interactions. Here, we present a physics-guided computational framework to screen known Ce-based crystal structures and identify promising Ising ferromagnets for future synthesis. A Random Forest classifier uses seven structural and SOAP descriptors, including unit-cell volume, density, atomic sites, space group, atomic density, Ce SOAP overlap, and transition-metal SOAP overlap, to prioritize candidate compounds. Selected crystallographic structures are then analyzed using Ising-model Monte Carlo simulations to characterize phase behavior and critical properties. Critical exponents extracted from simulated phase transitions provide quantitative insight into magnetic regimes and anisotropy-related effects. We further employ autoencoders trained on affinity-based features from simulated spin configurations to identify latent signatures of phase evolution and transition behavior. Together, this framework integrates structural screening, statistical-mechanical simulation, and machine learning to accelerate the identification of promising Ce-based magnetic materials and provide candidates for experimental synthesis and validation.

cond-mat.mtrl-sci↗

arXiv2026

MCP Bridge: A Lightweight, LLM-Agnostic RESTful Proxy for Model Context Protocol Servers

Large Language Models (LLMs) are increasingly augmented with external tools through standardized interfaces like the Model Context Protocol (MCP). However, current MCP implementations face critical limitations: they typically require local process execution through STDIO transports, making them impractical for resource-constrained environments like mobile devices, web browsers, and edge computing. We present MCP Bridge, a lightweight RESTful proxy that connects to multiple MCP servers and exposes their capabilities through a unified API. Unlike existing solutions, MCP Bridge is fully LLM-agnostic, supporting any backend regardless of vendor. The system implements a risk-based execution model with three security levels-standard execution, confirmation workflow, and Docker isolation-while maintaining backward compatibility with standard MCP clients. However, reliable execution within this framework requires models that can strictly adhere to protocol schemas. To this end, we also fine-tuned the Qwen3 4B and 8B model family on the Agent-Ark/Toucan-1.5M dataset using four Reinforcement Learning techniques: Group Relative Policy Optimization (GRPO), Dr. GRPO, Beta Normalization Policy Optimization (BNPO), and Decoupled Clip and Dynamic sAmpling Policy Optimization (DAPO). Evaluated on the MCPToolBench++ benchmark, our optimized model achieves an F1 score of 73.0% that outperforms GPT-OSS-120B (62.17%) and remains competitive with the 70B+ parameter baselines. Evaluation demonstrates that MCP Bridge successfully addresses the constraints of direct MCP connections while providing enhanced security controls and cross-platform compatibility, enabling sophisticated LLM-powered applications in previously inaccessible environments.

cs.CR↗

arXiv2025

Brain Tumor Detection Through Diverse CNN Architectures in IoT Healthcare Industries: Fast R-CNN, U-Net, Transfer Learning-Based CNN, and Fully Connected CNN

Artificial intelligence (AI)-powered deep learning has advanced brain tumor diagnosis in Internet of Things (IoT)-healthcare systems, achieving high accuracy with large datasets. Brain health is critical to human life, and accurate diagnosis is essential for effective treatment. Magnetic Resonance Imaging (MRI) provides key data for brain tumor detection, serving as a major source of big data for AI-driven image classification. In this study, we classified glioma, meningioma, and pituitary tumors from MRI images using Region-based Convolutional Neural Network (R-CNN) and UNet architectures. We also applied Convolutional Neural Networks (CNN) and CNN-based transfer learning models such as Inception-V3, EfficientNetB4, and VGG19. Model performance was assessed using F-score, recall, precision, and accuracy. The Fast R-CNN achieved the best results with 99% accuracy, 98.5% F-score, 99.5% Area Under the Curve (AUC), 99.4% recall, and 98.5% precision. Combining R-CNN, UNet, and transfer learning enables earlier diagnosis and more effective treatment in IoT-healthcare systems, improving patient outcomes. IoT devices such as wearable monitors and smart imaging systems continuously collect real-time data, which AI algorithms analyze to provide immediate insights for timely interventions and personalized care. For external cohort cross-dataset validation, EfficientNetB2 achieved the strongest performance among fine-tuned EfficientNet models, with 92.11% precision, 92.11% recall/sensitivity, 95.96% specificity, 92.02% F1-score, and 92.23% accuracy. These findings underscore the robustness and reliability of AI models in handling diverse datasets, reinforcing their potential to enhance brain tumor classification and patient care in IoT healthcare environments.

eess.IV↗

arXiv2025

Dual Micro-Ring Resonators with Angular GST Modulation: Enabling Ultra-Fast Nonlinear Activation for Neuromorphic Photonics

Photonic technologies are emerging as powerful enablers for neuromorphic computing by delivering ultrafast and energy efficient neural functionalities. In this work, we propose and demonstrate a novel all-optical dual micro ring resonator architecture incorporating the phase change material Ge2Sb2Te5 (GST) to implement highly precise nonlinear activation functions (NLAFs). Our approach introduces angular positioning of GST segments within the rings, enabling fine-grained control over optical transmission dynamics. Through a systematic evaluation of sixteen distinct phase configurations, we identify an optimal GST placement 180 deg in the first ring and 90 deg in the second that achieves ultra narrowband transmission with a full width at half maximum (FWHM) of just 0.47 nm. This dual ring configuration provides two distinct resonant wavelengths, facilitating enhanced nonlinear modulation and multi level optical signal processing that closely mimics biological neuron behavior. Notably, the device achieves high contrast transmission, 0 to 0.85, across a 4 nm spectral window while operating at significantly reduced temperatures (100 deg C), outperforming traditional GST based designs. Furthermore, the dual-ring architecture enables independent optimization of spectral selectivity and switching contrast capabilities previously unattainable with single ring structures. These results establish a promising pathway toward scalable, high speed neuromorphic photonic systems, offering both the precision and switching speed required for practical on chip neural processing.

physics.optics↗

arXiv2025

Accelerated Discovery of Vanadium Oxide Compositions: A WGAN-VAE Framework for Materials Design

The discovery of novel materials with tailored electronic properties is crucial for modern device technologies, but time-consuming empirical methods hamper progress. We present an inverse design framework combining an enhanced Wasserstein Generative Adversarial Network (WGAN) with a specialized Variational Autoencoder (VAE) to accelerate the discovery of stable vanadium oxide (V-O) compositions. Our approach features (1) a WGAN with integrated stability constraints and formation energy predictions, enabling direct generation of thermodynamically feasible structures, and (2) a refined VAE capturing atomic positions and lattice parameters while maintaining chemical validity. Applying this framework, we generated 451 unique V-O compositions, with 91 stable and 44 metastable under rigorous thermodynamic criteria. Notably, we uncovered several novel V2O3 configurations with formation energies below the Materials Project convex hull, revealing previously unknown stable phases. Detailed spin-polarized DFT+U calculations showed distinct electronic behaviors, including promising half-metallic characteristics. Our approach outperforms existing methods in both quality and stability, demonstrating about a 20 percent stability rate under strict criteria compared to earlier benchmarks. Additionally, phonon calculations performed on selected compositions confirm dynamic stability: minor imaginary modes at 0 K likely stem from finite-size effects or known phase transitions, suggesting that these materials remain stable or metastable in practical conditions. These findings establish our framework as a powerful tool for accelerated materials discovery and highlight promising V-O candidates for next-generation electronic devices.

cond-mat.mtrl-sci↗

arXiv2024

On-Chip Learning with Memristor-Based Neural Networks: Assessing Accuracy and Efficiency Under Device Variations, Conductance Errors, and Input Noise

This paper presents a memristor-based compute-in-memory hardware accelerator for on-chip training and inference, focusing on its accuracy and efficiency against device variations, conductance errors, and input noise. Utilizing realistic SPICE models of commercially available silver-based metal self-directed channel (M-SDC) memristors, the study incorporates inherent device non-idealities into the circuit simulations. The hardware, consisting of 30 memristors and 4 neurons, utilizes three different M-SDC structures with tungsten, chromium, and carbon media to perform binary image classification tasks. An on-chip training algorithm precisely tunes memristor conductance to achieve target weights. Results show that incorporating moderate noise (<15%) during training enhances robustness to device variations and noisy input data, achieving up to 97% accuracy despite conductance variations and input noises. The network tolerates a 10% conductance error without significant accuracy loss. Notably, omitting the initial memristor reset pulse during training considerably reduces training time and energy consumption. The hardware designed with chromium-based memristors exhibits superior performance, achieving a training time of 2.4 seconds and an energy consumption of 18.9 mJ. This research provides insights for developing robust and energy-efficient memristor-based neural networks for on-chip learning in edge applications.

cs.NE↗

arXiv2024

A Comparative Study of Sampling Methods with Cross-Validation in the FedHome Framework

This paper presents a comparative study of sampling methods within the FedHome framework, designed for personalized in-home health monitoring. FedHome leverages federated learning (FL) and generative convolutional autoencoders (GCAE) to train models on decentralized edge devices while prioritizing data privacy. A notable challenge in this domain is the class imbalance in health data, where critical events such as falls are underrepresented, adversely affecting model performance. To address this, the research evaluates six oversampling techniques using Stratified K-fold cross-validation: SMOTE, Borderline-SMOTE, Random OverSampler, SMOTE-Tomek, SVM-SMOTE, and SMOTE-ENN. These methods are tested on FedHome's public implementation over 200 training rounds with and without stratified K-fold cross-validation. The findings indicate that SMOTE-ENN achieves the most consistent test accuracy, with a standard deviation range of 0.0167-0.0176, demonstrating stable performance compared to other samplers. In contrast, SMOTE and SVM-SMOTE exhibit higher variability in performance, as reflected by their wider standard deviation ranges of 0.0157-0.0180 and 0.0155-0.0180, respectively. Similarly, the Random OverSampler method shows a significant deviation range of 0.0155-0.0176. SMOTE-Tomek, with a deviation range of 0.0160-0.0175, also shows greater stability but not as much as SMOTE-ENN. This finding highlights the potential of SMOTE-ENN to enhance the reliability and accuracy of personalized health monitoring systems within the FedHome framework.

cs.LG↗

arXiv2023

Optical Properties and Behavior of Whispering Gallery Mode Resonators in Complex Microsphere Configurations: Insights for Sensing and Information Processing Applications

Whispering gallery mode (WGM) resonators are garnering significant attention due to their unique characteristics and remarkable properties. When integrated with optical sensing and processing technology, WGM resonators offer numerous advantages, including compact size, high sensitivity, rapid response, and tunability. This paper comprehensively investigates the optical properties and behavior of WGMs in complex microsphere resonator configurations. The findings underscore the potential of WGMs in sensing applications and their role in advancing future optical information processing. The study explores the impact of configuration, size, excitation, polarization, and coupling effects on the WGMs properties. The paper provides crucial insights and valuable guidance for designing and optimizing microsphere resonator systems, enabling their realization for practical applications.

physics.optics↗