💻 Category

cs

4157 papers

💻 computer science

Dual-channel temporal convolutional autoencoder: Multi-scale representation with short-term fluctuation and long-term trend for dynamic process monitoring

To overcome the limitations of traditional static autoencoders in capturing temporal dynamics, this paper proposes a Dual-channel Temporal Convolutional Autoencoder (DTCAE) that utilizes parallel networks with distinct receptive fields to separately extract short-term fluctuations and long-term trends, thereby enhancing dynamic process monitoring through improved feature representation and Bayesian inference.

Jian Huang, Xin Pu, Xu Yang, Kaixiang Peng, Jingjing Gao, Dajian Huang2026-11-10
💻 computer science

Shift-Safe EStream-OPF: Reusable Top-K Forgetting Queries over Order-Preserving Index Streams

This paper introduces Shift-Safe EStream-OPF, a reusable query framework for order-preserving index streams that employs a numerically stable shift-safe factorization to efficiently compute repeated global top-KK rankings under exponential forgetting, demonstrating significant latency improvements over baseline methods when leveraging index reuse and occurrence-equivalent compression.

Khac-Chien Nguyen, Nhut-Minh Bui, Cong-Phat Tran2026-11-10
💻 computer science

Calculus on Clouds: Discretized Integration and Depth-wise Evolution for Point Cloud Segmentation

This paper introduces Calculus on Clouds (COC), a novel geometry-state operator integrated into the OneFormer3D decoder that utilizes discretized integration, state-aware cross-attention, and depth-wise selective scan aggregation to effectively address the challenges of irregular point cloud sampling and achieve superior semantic, instance, and panoptic segmentation performance.

Zhige Ying, Zhe Wu, Huizheng Yuan, Cheng Zhang, Qiangsheng Zhang2026-11-10
💻 computer science

Artificial Intelligence in Safety-Critical Aerospace Systems: Applications, Challenges, and Implications

This paper presents an interdisciplinary analysis of AI's role as an autonomous decision-making agent in high-risk aerospace systems—specifically hypersonic reentry, autonomous satellites, and nuclear propulsion—by examining technical applications, operational challenges, and critical governance issues to establish robust frameworks for reliable and ethical deployment.

Marcos Fernandez-Tous, Ian Werkheiser, Sreejith Vidhyadharan Nair, Michael Dodge, Sai Susmitha Guddanti2026-11-10
💻 computer science

AE-DSP: An Explainable Intrusion Detection Framework for Zero-Day Attacks Based on SHAP Contribution-Space Modeling

This paper proposes AE-DSP, an explainable intrusion detection framework that addresses the challenge of zero-day attack detection by modeling SHAP contribution deviations within a unified space to capture both overall structural anomalies and dimension-wise semantic patterns, achieving high performance and traceability across multiple benchmark datasets.

Yifan Liu, Zheng Liu, Wenlei Chai, Miaolin Wang, Junjie Qiu, Yi Liu2026-11-10
💻 computer science

Selective Foundation-Model Intervention for Vertebral CT Segmentationunder Predictive Uncertainty

This paper proposes an uncertainty-guided selective collaboration framework (UGSCF) that strategically deploys the Segment Anything Model (SAM) only to correct high-uncertainty regions in task-specific vertebral CT segmentations, demonstrating that while unconditional fusion is often harmful, a hierarchical decision process effectively allocates foundation-model resources even if it yields only marginal aggregate accuracy gains.

Xinyu Liu, Xinlu Lv, Yihan Liu, Bingran Wang, Wenchao Du2026-11-10
💻 computer science

Automated Root Cause Analysis of Security Incidents Using Causal Machine Learning

This study validates a reproducible causal machine learning framework for distinguishing root causes from downstream symptoms in security incidents, demonstrating that residual scoring within a structural causal graph significantly outperforms marginal anomaly scoring in identifying mechanism shifts, particularly under low-noise conditions, while explicitly acknowledging limitations regarding real-world deployment and causal discovery.

Rehana Devani2026-11-10