💻 Category

cs

863 papers

💻 computer science

A Deep learning framework for early detection of Ransomware communication patterns in encrypted network using transfer learning Case study: Financial Enterprise Networking

This paper presents an LSTM-based deep learning framework that utilizes transfer learning on encrypted network flow features to detect ransomware without payload decryption, demonstrating the critical necessity of 12–18 month retraining cycles to counteract temporal model drift while achieving high detection accuracy through a confidence-based ensemble system integrated with Wazuh SIEM.

Jean chrysostome NDAYISABYE, ICYITEGETSE Theresie, IKUZWE Pascaline2026-07-07
💻 computer science

Immersive Virtual Reality in Education: A Systematic Review of Learning Outcomes, Challenges, and Future Directions

This systematic review of literature from 2020 to 2026 evaluates the impact of immersive virtual reality on diverse educational outcomes, finding that while VR significantly enhances engagement, retention, and conceptual understanding, its widespread adoption is currently hindered by barriers such as cost, cybersickness, and insufficient teacher training, thereby outlining a roadmap for future research in adaptive learning, analytics, and ethical implementation.

Zeynep Yılmaz2026-07-07
💻 computer science

Do-Calculus Interventions in Predictive Coding Networks: Formal Correspondence, Empirical Validation, and Architectural Prescriptions for Clinical Causal AI

This paper establishes a formal correspondence between predictive coding network dynamics and Pearl's do-calculus, demonstrating through theoretical derivation and empirical validation on clinical benchmarks that specific architectural interventions enable these networks to accurately perform causal reasoning and outperform standard associational models in estimating interventional effects.

Hassan Farooq2026-07-07
💻 computer science

A Conceptual AI-Assisted Music Creation Framework for Individuals with Amusia: Neural Pitch Correction and Adaptive Auditory Feedback

This paper proposes the AI-Assisted Music Creation Framework (AAMCF), a conceptual five-layer architecture that leverages neural pitch correction, generative harmonization, and adaptive feedback to enable individuals with amusia to create and perceive music, while outlining its theoretical foundations, evaluation metrics, and ethical considerations for future empirical validation.

Snigdha Saha, Md. Maruf Sharker Munna2026-07-07
💻 computer science

Embedding Formal Worst-Case Latency Proofs and Memory-Safety Certificates into the snn-mlir MLIR Lowering Pipeline for IEC 62304-Compliant Edge Deployment of Spiking Neural Networks

This paper introduces a post-processing MLIR analysis pass for the snn-mlir compiler that generates machine-checkable worst-case latency proofs and memory-safety certificates, thereby enabling the IEC 62304 Class B compliant deployment of spiking neural networks for safety-critical edge medical devices like seizure detectors.

Hassan Farooq2026-07-07
💻 computer science

Twos All the Way Down: A Hidden Condition Every Deployed RoPE Schedule Satisfies

This paper identifies and validates a previously unarticulated "max_cluster = 1" condition, requiring pairwise distinctness of all RoPE frequencies, demonstrating that violating this implicit constraint at inference time causes catastrophic performance degradation in large language models while proving that standard geometric schedules inherently satisfy it due to the transcendental nature of their logarithmic bases.

Sungmin Ryu2026-07-07
💻 computer science

DBHMT: Dynamic Balancing Hybrid Merkle Tree– Design, Optimization and Evaluation in IOTA Tangle for IoT-Enabled Healthcare 4.0

This paper proposes the Dynamic Balancing Hybrid Merkle Tree (DBHMT), an optimized data structure for IOTA Tangle-based Healthcare 4.0 that employs a dynamic pruning mechanism to achieve a fourfold reduction in storage costs while maintaining security for resource-constrained IoT environments.

Basker Palaniswamy, Md Noor-A-Rahim, Paolo Palmieri, Francesco Regazzoni, Ashok Kumar Das, Vivekananda Bhat K2026-07-07
💻 computer science

Mapping Curricula to Occupational Work Activities Using a Shared DWA Ontology: Evidence from the Course-Skill Atlas and O*NET

This study introduces a curriculum analytics framework that maps Computer Science course signals to Data Scientist occupational requirements using a shared Detailed Work Activity ontology, revealing that while the curriculum covers all necessary tasks, it exhibits a significant emphasis gap in their relative weighting.

Hairu Fan, Shiyuan Wang, Ming Liu2026-07-07
💻 computer science

From Prompt to Production: A Case Study of Human-AI Collaborative Software Development Using Claude Code Multi-Agent Orchestration

This paper presents a comprehensive case study of developing a production-grade medical platform using Claude Code's multi-agent orchestration, establishing a human-AI competency framework, quantifying performance gains across different AI configurations, and proposing token optimization strategies to enhance productivity while reducing costs.

Pham Thi Thuong, Nguyen Dang Quang, Ngo Thi Lan Phuong2026-07-07