cs papers | Gist.Science

Class-Aware Semantic Hybrid Data Augmentation for Imbalanced Sentiment Classification Using Multiple Transformer Models

This paper proposes a Class-Aware Semantic Hybrid Data Augmentation (CSHDA) framework that selectively applies diverse, semantically validated augmentation techniques to minority classes, effectively mitigating class imbalance and significantly improving the performance and robustness of multiple transformer-based models on imbalanced sentiment classification tasks.

Prashant Upadhyaya, G.L. Saini, Atul Makrariya2026-08-27

💻 computer science

A Prior-Regularized Framework for Knowledge-Guided Differentiable Causal Discovery

This paper proposes a universal prior-regularized framework that integrates curated biological knowledge into differentiable causal discovery algorithms, significantly improving graph recovery accuracy in high-dimensional, small-sample transcriptomic data by leveraging existing domain priors to stabilize learning where baseline methods struggle.

Shuaidong Gao2026-08-27✓ Author reviewed ⓘ

💻 computer science

GPU-Accelerated BM4D Volumetric Denoising for Python: A Toolchain- Free, Pip-Installable CuPy Implementation

This paper introduces a fully open-source, pip-installable CuPy implementation of the complete BM4D volumetric denoising algorithm that eliminates the need for a CUDA Toolkit or build steps while achieving up to 36.6x speedups over the CPU reference and maintaining exact numerical fidelity to the original method.

Matin Mahzad2026-08-27

💻 computer science

XGBoost Optimization using Single Lead ECG based on Multi-feature of ECG Morphologies for Automatic Sleep Disorder Classification

This study presents an automatic sleep disorder classification system that utilizes a regularized XGBoost algorithm to analyze multi-feature morphologies from single-lead ECG signals, achieving high accuracy (96.1%), specificity (100%), and sensitivity (92.1%) in distinguishing apnea events.

Iman Fahruzi, Muhamad Haikal Akmal, Ridwan Ridwan, Abdurahman Dwijotomo2026-08-27

💻 computer science

Statistically Guided Hybrid Local–Global Learning for Compressed Deepfake Video Detection

This paper proposes a statistically guided hybrid local–global learning framework that fuses optimized YCbCr features with a novel 3SH–VSS architecture to effectively detect compressed deepfake videos by simultaneously modeling local compression artifacts and global forgery dependencies, achieving superior performance and generalization across datasets.

Tianyu Shi, Shichao Ouyang, Juan Li, Guodong Ye, Xingxing Jia2026-08-27

💻 computer science

A reusable benchmark for machine-learning prediction of concrete placement productivity loss

This paper introduces a reusable, synthetic benchmark for evaluating machine-learning models predicting concrete placement productivity loss, revealing that current competent models fail to adequately capture severe losses and highlighting the need for standardized, field-validated evaluation protocols.

Mohamed Ali, Saher Elsayed, TS. DR. Khairi Azhar Aziz2026-08-27

💻 computer science

Early Detection of Schizophrenia Using EEG Signals Based on CNN and CNN–LSTM Deep Learning Models

This study demonstrates that a hybrid CNN–LSTM deep learning model significantly outperforms a standalone CNN in detecting schizophrenia from resting-state EEG signals, achieving 92.03% accuracy and highlighting the value of integrating temporal sequence learning for objective diagnosis.

Hussein Aly Elsayed, Arief Ruhullah Harris, Tian Swee Tan2026-08-27

💻 computer science

Tri-Modal Contrastive Binary Analysis via Opcode Transformers, Control Flow Graph Isomorphism Networks, and System Call Embeddings: A Systematic Review of Zero-Day Malware Detection Frameworks

This systematic review synthesizes recent advancements in zero-day malware detection by proposing a Tri-Modal Contrastive Binary Analysis framework that unifies opcode Transformers, Control Flow Graph Isomorphism Networks, and System Call embeddings to achieve robust detection accuracy exceeding 98.5% despite sophisticated code obfuscation.

Harish Parshuram Bhabad, Atmeshkumar Subhashbhai Patel, Vijay M. Rakhade, Rupesh Kohli, Nandini S. Patil2026-08-27

💻 computer science

TPCT: Topology-aware Point Cloud Transformer for Geometrically Complex Feature Recognition

This paper proposes TPCT, a novel topology-aware Transformer framework that integrates geometric and dual-graph topological features with area-adaptive sampling to achieve state-of-the-art accuracy in recognizing complex geometric features within B-rep CAD models.

Ruohan Wang, Ruixi Liang, Longtao Guo, Jiacheng Hao, Yilei Shi2026-08-27

💻 computer science

Grey Wolf Optimizer-Based Feature Selection with Mutual Information Refinement for Machine Learning-Based Bot Detection on Social Media

This study proposes a Grey Wolf Optimizer-based feature selection framework refined by Mutual Information to effectively reduce the feature space for social media bot detection, achieving a 98.87% classification accuracy with XGBoost on a dataset of 8,386 accounts.

Aditya Vardhan, Mohit Yadav, Amarjeet Singh Chauhan, Sanjay Saini2026-08-27

← Previous Next →