cs papers | Gist.Science

IPEK: Intelligent Priority-Aware Event-Based Trust with Asymmetric Knowledge for Resilient Vehicular Ad-Hoc Networks

This paper proposes IPEK, an intelligent trust management framework for Vehicular Ad-Hoc Networks that leverages asymmetric knowledge, event severity awareness, and Yager's DST-based fusion to effectively detect strategic attackers who exploit homogeneous trust models, achieving significantly higher recall and lower false positive rates than existing centralized schemes.

İpek Abasıkeleş-Turgut2026-09-19

💻 computer science

Beyond direct AI exposure: Measuring network-mediated labor risk through multilayer occupational networks

This paper introduces a Multilayer Occupational Network (MONET) and a Relation-Aware Multilayer Graph Neural Network (RAM-GNN) to identify labor risks beyond direct AI exposure by analyzing structural associations within occupational neighborhoods, offering a policy screening tool that balances detection accuracy with socioeconomic vulnerability while cautioning against individual-level misapplication.

Soyoung Park, Junghyun Oh, Minkyung Song, Jin-woo Lee, Jincheul Jang, Sungsu Lim2026-09-19

💻 computer science

Development and Evaluation of Target-Specific Machine-Learning Scoring Functions for Monoamine Oxidase B

This study demonstrates that while target-specific machine-learning scoring functions for MAO-B, particularly tuned regression models with combined features, significantly outperform generic scoring functions on independent test sets, their early-recognition performance is heavily influenced by structural similarity to known actives, underscoring the critical need for rigorous benchmark design and prospective validation to ensure generalization to novel chemical space.

Sherif Adel Arafa Elsabbagh2026-09-19

💻 computer science

Dissecting ADDQN: An Ablation Study for Deadline-Aware Task Scheduling in Fog Computing

This paper presents a systematic ablation study demonstrating that the superior performance of the Attention-Enhanced Double Deep Q-Network (ADDQN) for deadline-aware task scheduling in fog computing relies critically on the synergistic interplay of its components, with reward shaping and dual-path fusion identified as the most significant contributors to robust scheduling.

Nagwa Elmobark, Sara Elhishi, Alshaimaa M. Mohammed2026-09-19

💻 computer science

Differentially and Integrally Attentive Convolutional-Based Real-Time Photoplethysmographic Signal Quality Classification

This paper proposes a real-time, Convolutional Neural Network-based framework enhanced with differential and integral attention mechanisms to robustly classify photoplethysmographic signal quality across diverse wearable devices, achieving high accuracy and F1-scores while balancing model size and performance.

Rafael Lima, Italo Sandoval, Arthur Valencio, Maíssa Maniezzo, Pedro Garcia2026-09-18

💻 computer science

The Imposed and Emergent Pieces of Convolution Under an Energy Budget

This paper uses an evolutionary search under an energy budget to decompose convolutional neural networks into imposed priors and emergent structures, revealing that sparse connectivity and weight sharing arise naturally while compact filters require specific mutation mechanisms and composition on the channel axis hits a capacity wall without supervision.

Vasili Gavrilov2026-09-18

💻 computer science

Real-Time Acoustic Keylogging: A Convolutional Neural Network Based Approach

This paper presents a novel real-time acoustic keylogging system that utilizes a convolutional neural network trained on log-mel spectrograms to achieve high-accuracy keystroke inference with low latency (0.35 seconds) and robust performance even under limited training data conditions.

Joshua Edgley, Aikaterini Kanta, Athanasios Paraskelidis2026-09-18

💻 computer science

Cross-Age Real-Time Kannada Sign Language Recognition using Curvilinear Geometric Features and CNN-LSTM Models

This study introduces a robust, real-time framework for cross-age Kannada Sign Language recognition that integrates curvilinear geometric feature extraction with a hybrid CNN-LSTM architecture, achieving 94.6% accuracy on a newly curated dataset of 5,000 annotated samples to facilitate effective sign-to-text translation for assistive communication.

Ramesh M. Kagalkar, Bahubali Shiragapur, Praveen B M2026-09-18

💻 computer science

MAT-3: A Bounded Averaged-Projection Operator for Pre-Inference Cognitive-Affective Guidance

This paper introduces MAT-3, a bounded, non-expansive pre-inference operator that guides language model affective behavior through averaged projections onto a local covariance-defined affine set while incorporating safety mechanisms for selective abstention, though its practical efficacy on downstream language models remains to be empirically validated.

Tiago Aguioncio Vieira2026-09-18

💻 computer science

A Dynamic Adaptive Fusion Transformer for Zero-Inflated Intermittent Spare Parts Demand Forecasting

This paper proposes a Dynamic Adaptive Fusion Transformer (DAF-Transformer) that decomposes zero-inflated intermittent spare parts demand forecasting into occurrence probability and conditional size estimation, utilizing a dynamic adaptive fusion mechanism to significantly reduce forecasting errors and suppress spurious positive predictions during zero-demand periods.

Weiqi Chen, Yujiao Wen, Bin Ni, XuFeng Wang, Hongya Zhou, XiaoLin Liu2026-09-18

← Previous Next →