2787 papers
This paper proposes a graph-based decomposition framework that enhances the computational efficiency and scalability of solving flow-based charging station location problems on large-scale transportation networks by partitioning the network into smaller subproblems, solving them individually, and refining the aggregated results.
This paper presents a Rust-Python hybrid SPV verification engine for IoT that achieves a 4.35× throughput increase and up to 75% energy reduction on resource-constrained devices by mitigating garbage collection latency and memory risks through a memory-mapped streaming architecture.
The paper proposes ZBA-SU, a novel framework integrating zero-knowledge proofs, blockchain, and ciphertext-policy attribute-based encryption to deliver secure, privacy-preserving, and scalable software updates for IoT devices while mitigating centralized trust dependencies and attribute leakage.
This paper evaluates selective risk control for LLM decision agents under uncertainty, finding that while binding adversarial critique acts as an effective conservative gate for high-risk cases when abstention is cheap, it does not inherently improve active decision quality and should be viewed as a tunable deferral layer rather than a superior replacement for simpler policies.
This paper proposes an imbalance-resilient network intrusion detection framework that combines optimized feature selection, TVAE-based data augmentation for minority classes, and a stacked ensemble learning strategy to achieve high accuracy and robustness in detecting both common and rare cyber attacks on the CSE-CIC-IDS2018 dataset.
This paper proposes FuMO-Edge, an online mobile edge computing orchestrator that integrates Interval Type-2 fuzzy logic with NSGA-II to optimize task placement under uncertainty, demonstrating significant reductions in service time and failure rates compared to existing type-1 baselines, particularly in high-density device scenarios.
This study demonstrates that a heterogeneous ANN–LightGBM stacking model utilizing 23 pre-encryption Windows API indicators can achieve high accuracy (95.20%) in classifying ransomware families and benign software, offering a proactive defense mechanism that outperforms standalone neural architectures while highlighting the need for further external validation.
This paper proposes ST-GAIN+, a hybrid spatiotemporal generative adversarial network that integrates temporal convolutional networks, dual attention mechanisms, and Bayesian uncertainty estimation to achieve robust and accurate imputation of missing solar irradiance data across various missing rates and real-world datasets.
This paper proposes an Explainable Machine Learning and IoT framework that integrates real-time sensor data with ensemble algorithms and XAI techniques to accurately predict middle school students' academic performance and generate transparent, personalized learning interventions.
This preregistered study demonstrates that large language models can reliably infer Big Five personality traits from live conversations with high internal consistency and convergent validity, particularly for neuroticism and agreeableness, though performance varies by trait observability and prompting strategy.