cs papers | Gist.Science

Solver-Informed Evolution of Interpretable Dispatching Rules for the Stochastic Team Orienteering Problem with Time Windows

This paper proposes SI-GP, a solver-informed genetic programming hyper-heuristic that enhances interpretable dispatching rules for the stochastic team orienteering problem with time windows by extracting and selecting instance-specific heuristic features from high-quality reference solutions, thereby outperforming existing baselines while maintaining rule readability and stability.

Augusto Magalhães Pinto de Mendonça, Filipe Pessôa Sousa, Laura Silva de Assis, Igor Machado Coelho2026-09-07

💻 computer science

Multi-Objective Path Optimization for Truck–Drone Collaborative Delivery Based on Subspace Contribution-Driven Adaptive Resource Allocation

This paper proposes RC-NSGA-II, a novel multi-objective optimization algorithm that integrates K-means-based subspace contribution-driven resource allocation, random-key encoding, and adaptive local search to effectively solve the complex three-objective truck-drone collaborative delivery problem, demonstrating superior performance in solution quality and efficiency across various benchmark instances.

yuehua liao, jia zhao2026-09-07

💻 computer science

Hardware-Coupled Bayesian Optimization for Self-Tuning Lightweight Cryptographic Parameters in Resource-Constrained Decision Support Systems

This paper presents a self-tuning framework that utilizes hardware-coupled Bayesian optimization, transfer learning, and drift-aware feedback to dynamically optimize lightweight cryptographic parameters for resource-constrained decision support systems, thereby balancing security, energy efficiency, and performance without manual intervention.

Seema Joshi, Neelu Singh, Deepshikha Arya, Virendra Kumar Tiwari2026-09-07

💻 computer science

Optimal Feature Extraction and Prediction for Air Quality Using a Swarm-Refined Hybrid System

This study proposes a hybrid air quality prediction model that integrates SARIMA for trend extraction, TCN for capturing nonlinear dynamics, and SCSO for hyperparameter optimization, demonstrating significantly improved accuracy and robustness over traditional methods.

Jiahao Guo, Yingfang Zhu, Huihua Huang, Juyang Liao, Hao Huang2026-09-07

💻 computer science

Robust Non-Invasive Melanoma Early Detection Through Lightweight Self-Supervision and Lesion-Focused Representation Learning

This paper presents a lightweight, robust YOLOv11-based framework that leverages lesion-focused self-supervised pretraining and a hierarchical two-stage classifier to achieve high-accuracy, non-invasive melanoma detection on the HAM10000 dataset while maintaining resilience against image degradation typical of mobile devices.

Chen-Hao Peng, Tzu-Kun Lo, Da-Chuan Cheng2026-09-07

💻 computer science

Smart Cities AVNs: Transparent and Privacy-Preserving Cyber Attack Prediction with Explainable Federated Feature Selection

This paper proposes a transparent and privacy-preserving Explainable Federated Learning framework for Autonomous Vehicular Networks that integrates distributed feature selection and interpretable AI to achieve high-accuracy, multiclass cyber-attack prediction while maintaining data locality and decision trustworthiness.

Hussein A. Al-Hashimi2026-09-07

💻 computer science

Extended Compositional Learning Algorithm for Synchronous Parallel Automata

This paper presents an extended compositional learning algorithm for synchronous parallel automata that relaxes the restrictive global uniqueness assumption on synchronizing actions, thereby enabling the scalable and correct extraction of component models from realistic black-box systems with significantly fewer resources than monolithic approaches.

Mahboubeh Samadi, Aryan Bastany, Hossein Hojjat2026-09-07

💻 computer science

TAH-GAN: Time-Aware Hybrid Generative Adversarial Network for Robust Android Malware Evasion

This paper introduces TAH-GAN, a time-aware hybrid generative adversarial network that integrates Fourier temporal encoding and dual-gate quality control to generate future-aligned Android malware samples, effectively addressing temporal concept drift and achieving superior evasion rates and temporal coherence compared to existing non-temporal baselines.

Daniel Jeremiah, Jalil Md D, Husnain Rafiq2026-09-07

💻 computer science

A 2-Level Stacking Ensemble Framework for Multi-Class Alzheimer’s Disease Diagnosis Using CNN Feature Extractors and SVM-XGBoost Classifiers

This study proposes a two-level stacking ensemble framework that integrates features from ResNet152, DenseNet121, and a custom CNN, processed through PCA and classified by SVM and XGBoost, to achieve near-perfect accuracy (0.9997) in four-class Alzheimer's disease diagnosis using MRI scans, significantly outperforming existing state-of-the-art baselines.

Shashi Kant Mourya, Ajit Kr. Singh Yadav2026-09-07

💻 computer science

Disentangling Mechanism, Budget, and Coverage in Data Augmentation for Imbalanced Malware Family Classification

This paper disentangles the effects of generation mechanism, augmentation budget, and coverage in deep generative models for imbalanced malware classification, finding that while most factors yield negligible performance gains, increasing the augmentation budget provides a small but reproducible improvement for RBF-SVM classifiers, highlighting the critical importance of experimental design in evaluating data augmentation strategies.

Kiana Bakrani Balani, Fabio Di Troia2026-09-07

← Previous Next →