2661 papers
This study proposes a KPI-based project health assessment model that integrates multiple performance indicators into a composite score and risk calculation to enhance visibility, identify risks early, and improve service reliability in agile IT operations.
This study presents a psychometrically validated Human Digital Twin framework for software developers that utilizes survey data from 605 female participants to model stress–resilience states, identify distinct behavioral clusters, and simulate personalized, explainable interventions that effectively predict and enhance resilience outcomes.
This paper introduces FEDRA, an autonomous framework that leverages transformer-based embeddings, clustering, and graph analysis to extract and prioritize decision factors from large-scale scientific text without expert intervention, demonstrating high accuracy and semantic consistency in a wastewater treatment site selection case study.
This paper proposes a performance-aware, phased migration framework for securing AI workloads on heterogeneous platforms against quantum threats, demonstrating that while key exchange overhead is negligible, the primary engineering challenge lies in managing the larger signatures and extended trust lifecycles required by NIST's finalized post-quantum algorithms.
This paper surveys and experimentally compares five widely used API rate-limiting algorithms—token bucket, leaky bucket, fixed window, sliding window log, and sliding window counter—to evaluate their trade-offs in burst tolerance and precision, ultimately providing guidance for selecting the most appropriate algorithm based on specific traffic characteristics and system constraints.
This paper proposes the Residual Biomechanical Transformer Network (RBTNet), a deep learning framework that combines YOLOv8m-Pose keypoint detection with a Transformer-based temporal analysis to achieve 98% accuracy in classifying eight yoga postures and generating corrective feedback based on biomechanical joint angle deviations without requiring user-specific data.
This paper introduces SentinelBI AI, a deployable business intelligence platform that integrates Isolation Forest and LSTM Autoencoder models to detect anomalous e-commerce revenue patterns, fusing their outputs into a three-tier alert system accessible via an interactive Streamlit dashboard for actionable decision support.
This study presents ChurnGuard AI, a deployed machine learning pipeline utilizing a Logistic Regression model to predict telecom customer churn with high recall, integrated into an interactive Streamlit dashboard to facilitate data-driven retention strategies.
This paper proposes a reasoning-aware framework that dynamically combines error-bounded KV-cache compression and sparse attention to significantly reduce memory, computation, and latency in long-context LLM inference while formally guaranteeing attention-output accuracy through a calibrated dropped-mass bound.
This paper demonstrates that optimizing reinforcement learning agents for emotion-related tasks naturally gives rise to internal reward signals that align with the core characteristics of biological emotions, supporting the principle that emotions evolve to alter actions in pursuit of intangible goals.