cs papers | Gist.Science

Enhancing RD-BIBD Key Pre-distribution with Permutation Aware Node Assignment in Fog Computing

This paper proposes a secure, hierarchical key pre-distribution scheme for fog-assisted IoT networks that enhances resilience against physical node capture attacks by integrating Residual Design-based combinatorial structures with a randomized permutation mechanism to obscure the deterministic mapping between cryptographic blocks and physical nodes, all while maintaining low overhead and high connectivity.

Majid Tajeri2026-08-19

💻 computer science

A Context-Aware Machine Learning Framework for Energy Anomaly Detection and Explainability in Hospital Equipment

This paper proposes a context-aware machine learning framework combining Isolation Forests, Random Forests, and SHAP explainability to detect and interpret energy anomalies in hospital equipment, achieving superior accuracy and low false alarm rates validated on real and synthetic datasets.

Jayanthi K, Jayasudha V, Aruna S K, Jothi Arunachalam S, Nagaraj Ashok2026-08-19

💻 computer science

EffiFusion-GAN: Efficient Fusion Generative Adversarial Network for Speech Enhancement

EffiFusion-GAN is a lightweight, time–frequency generative adversarial network that leverages depthwise-separable convolutions, residual Conformer blocks, and unstructured pruning to achieve near-state-of-the-art speech enhancement quality with significantly fewer parameters than existing models.

BIN WEN, Tien-Ping Tan2026-08-19

💻 computer science

Multi model deliberation improves the stability of automated scoring by large language models across genres and assessment contexts

This study demonstrates that a multi-model deliberation framework, where three heterogeneous Chinese large language models iteratively exchange scores and rationales, significantly improves the stability and precision of automated essay scoring across diverse genres and assessment contexts, with any resulting systematic bias being effectively correctable through standard human-anchored calibration.

Xiaoying ZHENG, Benhui CHEN, Yuqing CHEN, Yun YANG2026-08-19

💻 computer science

AI Acceptance and Digital Transformation as Predictive Drivers of University Sustainability Using a Hybrid Machine Learning Model

This study utilizes survey data from 178 Thai university executives and a novel SA-Optuna-Stack hybrid machine learning model to demonstrate that digital transformation and AI acceptance are significant predictive drivers of organizational sustainability in Southeast Asian higher education, identifying personnel skills and external networks as key levers while providing a high-accuracy tool for monitoring institutional outcomes aligned with UN Sustainable Development Goals.

Seerungrat Sudsomboon, Yuthachai Krokaew, Pawarisa Seangkham, Sutana Boonlua2026-08-19

💻 computer science

GADE-YOLO: An Efficient Geometry-Adaptive Network for Industrial Wood Surface Defect Inspection

This paper proposes GADE-YOLO, an efficient geometry-adaptive network based on YOLOv11n that integrates adaptive multi-scale feature enhancement, edge strengthening, and deformable convolution modules to effectively overcome wood-grain interference and irregular defect morphologies, achieving superior accuracy and lightweight performance for real-time industrial wood surface defect inspection.

Mengyang Wu, Huijian Han, Lei Li2026-08-19

💻 computer science

Agri-GAC-CoC: A Domain-Situated Chain-of-Checks Framework for Generative AI Feedback in Higher Agricultural Education

The paper introduces Agri-GAC-CoC, a domain-specific Chain-of-Checks framework for generative AI that significantly outperforms zero-shot, rubric-based, and standard Chain-of-Thought prompting in generating valid, actionable feedback for agricultural writing by prioritizing task-grounded domain checks over surface-level fluency.

Yurun Wang, Moyu Zhong2026-08-19

💻 computer science

Reliability-aware Gradient Decoupling for Partial Label Learning

The paper proposes RGD-PLL, a reliability-aware gradient decoupling framework that enhances partial label learning by estimating instance-dependent candidate reliability, suppressing uncertain supervision via entropy weighting, and removing conflicting gradient components through asymmetric projection to improve optimization stability and robustness.

Zhonghe Wei, Jihang Yin, Fengzhi Zhang, Yan Yan2026-08-19

💻 computer science

Post-Deployment Accountability in AI Governance: A Cross-Regulatory Empirical Analysis of AI Incidents

This empirical study analyzes AI incidents from 2020 to 2026 against major regulatory frameworks to reveal significant post-deployment accountability gaps, particularly in external detection and impact assessments, while proposing the Proactive AI Governance Compliance Framework (PAGCF) to address these systemic failures.

Ummara Mumtaz, Rabi Noor, Summaya Mumtaz2026-08-19

💻 computer science

Predictingthe Trainability of Variational Quantum Circuits: A Data-Driven Model for BarrenPlateaus

This paper presents a data-driven classical machine learning model that accurately predicts the trainability of variational quantum circuits and identifies barren plateaus based solely on architectural features, offering a cost-effective alternative to expensive gradient sampling for screening quantum circuit designs.

Md Habibur Rahman2026-08-19

← Previous Next →