cs papers | Gist.Science

A Robust and Lightweight Intrusion Detection Framework for IoMT Networks with Cross-Domain Evaluation

This study proposes a robust and lightweight intrusion detection framework for IoMT networks using CICIoMT2024, CICIoT2023, and Edge-IIoTset datasets, demonstrating that while ensemble models like XGBoost excel in same-domain scenarios, careful model selection such as Logistic Regression is crucial for maintaining stability and effectiveness in cross-domain environments despite challenges in feature compatibility.

Umair Maqsood, NZ Jhanjhi, Fatima Iftikhar, Raja Majid Mehmood2026-08-25

💻 computer science

Artificial Intelligence Enhanced Threat Intelligence for Cyber Resilience in Zero Trust Cloud Infrastructures

This study proposes an AI-enhanced threat intelligence framework that integrates machine learning with Zero Trust principles to significantly improve real-time threat detection, reduce false positives, and strengthen cyber resilience against sophisticated attacks in dynamic cloud environments.

Md Imran Khan, Md. Mokhlesur Rahman, Md Mahbubul Alam, Md Sultanul Arefin Sourav, Jafrin Reza2026-08-25

💻 computer science

SciSchema.org: A Multidisciplinary Collection of Schemas for Structured Scientific Process Descriptions

This paper introduces SciSchema.org, the first multidisciplinary collection of 16 expert-annotated schemas designed to standardize the description of scientific processes across diverse fields, thereby enabling structured annotation, reproducibility, and cross-study comparison through a human-in-the-loop development workflow.

Jennifer D'Souza, Sameer Sadruddin, Anisa Rula, Ana Bossler, Andres Fullana, Enric Bas, Syed Ather, Defne Circi, Anlan C (…)2026-08-25

💻 computer science

Epistemic Function Diagnosis in AI-Aided Design: Connecting Established Frameworks and Rapidly Evolving Practice

This paper proposes Epistemic Function Diagnosis (EFD) as a unifying reference layer to analyze and intervene in the complex, co-occurring hazards of AI-aided design by integrating established frameworks through a 2×2 diagnostic-intervention architecture and a Belief-Means-Method-Justification (BMMJ) grammar, while acknowledging the need for future empirical validation.

Masahiko MATSUHASHI2026-08-25

💻 computer science

AMORL: A Training-Aware, Adaptive, Multi-Objective RL-CNN Framework for Dynamic DNN Mapping on Networks-on-Chip

This paper introduces AMORL, a training-aware, adaptive framework combining reinforcement learning and convolutional neural networks to dynamically map diverse DNN workloads onto heterogeneous Networks-on-Chip, achieving significant reductions in communication cost, load imbalance, and latency while maintaining high throughput and energy efficiency.

Md Farhadur Reza2026-08-25

💻 computer science

Automating the triage of rheumatology outpatient referrals: a comparative evaluation of 23 large language models under simple and advanced prompting

This study demonstrates that contemporary large language models, particularly when guided by advanced prompting techniques, can automate rheumatology referral triage with accuracy comparable to or exceeding human experts, effectively eliminating the need for expensive, large-scale models.

Lynden Roberts2026-08-25

💻 computer science

Federated Hybrid Deep Learning Framework for IoT Intrusion Detection Using N-BaIoT, CICIoT2023, and BoT-IoT Datasets

This paper presents an end-to-end federated hybrid deep learning framework for IoT intrusion detection that preprocesses and trains diverse models (including CNN, LSTM, and XGBoost) on N-BaIoT, CICIoT2023, and BoT-IoT datasets to achieve strong performance while addressing privacy and resource constraints, with results highlighting the particular challenge of the multiclass CICIoT2023 dataset.

Sonali Mishra^, R. Venkata Siva2026-08-25

💻 computer science

A Patch-Routed Mixture-of-Experts for Continual MOBA Draft Recommendation

This paper proposes a patch-routed mixture-of-Experts architecture for continual MOBA draft recommendation that leverages versioned patch identities to isolate adaptation, achieving zero forgetting and significantly faster convergence with reduced storage compared to independent models, though its speed advantage diminishes as the stream of patches lengthens.

Mohammadreza Mohammadnejad, Morteza Dorrigiv, Farzin Yaghmaee2026-08-25

💻 computer science

An Attention-Enhanced MobileViT Framework for Multi-Task Skin Lesion Classification and Segmentation

This paper proposes an attention-enhanced, lightweight MobileViT-XS framework that effectively balances computational efficiency and diagnostic reliability for joint skin lesion classification and segmentation, achieving competitive performance on the ISIC 2019 dataset with significantly fewer parameters than heavyweight models.

Yanqiang Ge, Bingqian Lu, Haoyu Wang, Zixu Yang, Zhan Zhang2026-08-25

💻 computer science

A multi-scale neuralized Markov random field architecture for ECG arrhythmia recognition

This paper proposes a multi-scale neuralized Markov random field (MSMRF) framework that integrates multi-scale feature extraction, information bottleneck regularization, and physiological constraints to achieve accurate and clinically plausible recognition of cardiac arrhythmias, outperforming existing baselines on public ECG databases.

Jibin Wang, Chen Wei, Lexuan Ma, Bo Shi2026-08-25

← Previous Next →