2931 papers
This paper presents the first implementation and evaluation of space-efficient BFS and DFS traversal algorithms on succinct de Bruijn graphs, demonstrating significant reductions in auxiliary memory usage (up to 11×) and overall memory footprint (up to 2.36×) on a graph with 800 million edges.
This paper presents a month-long longitudinal study demonstrating that while both persuasive and instructional robot behaviors sustain older adults' engagement in cognitive activities, a persuasive interaction style is more effective at fostering positive responses and emotional connection, suggesting that a hybrid approach may best support long-term motivation.
This paper proposes a Cyberspace Topological Coordinate System (CTCS) model and a corresponding 3D framework that utilize logical, informational, and social relationships to effectively visualize and analyze complex network structures, outperforming traditional methods by integrating diverse data types and revealing node attributes and propagation paths.
This systematic literature review synthesizes research from 2010 to 2026 to demonstrate that cybersecurity incidents stem from the complex interplay of cognitive, social, and organizational factors rather than isolated user errors, ultimately proposing an integrative human-centered framework to address these vulnerabilities.
This paper presents a deep learning-based framework using TensorFlow and MediaPipe to enable real-time, contactless hand gesture recognition for diverse applications such as media control, gaming, and accessibility, offering an accurate and cost-effective alternative to traditional input devices.
This paper proposes a multi-role simulation framework using Large Language Models and Human-in-the-Loop validation to generate a high-quality, expert-verified synthetic dataset of Saudi Family Law divorce cases, effectively overcoming the scarcity of real judicial records caused by privacy constraints.
This study demonstrates that deep transfer learning, particularly using the EfficientNetB7 and ResNet50 models optimized with data augmentation and cross-validation, achieves high-precision classification of oral squamous cell carcinoma histological images, offering a promising solution to improve diagnostic accuracy and address inter-pathologist variability.
This empirical study examines the experiences of creative practitioners in Iran with Generative AI, revealing how geopolitical constraints and technical limitations shape their adoption through dominant director mental models, compensatory labor, and the emergence of bottom-up "Folk Ethics" to navigate systemic inequities.
This paper demonstrates that integrating an automated security-audit skill into the "vibe coding" process drastically improves the security of AI-generated web applications, reducing unmitigated risk by 99% and eliminating all high-severity vulnerabilities in a controlled comparison of two builds of the same e-commerce demo.
This paper proposes GTAN, a Graph-Temporal Attention Network that combines Temporal Convolutional and Graph Attention encoders with a Focal Contrastive Loss to effectively detect rare intrusion attacks in highly imbalanced Cyber-Physical Systems traffic by modeling both temporal sequences and topological relationships.