Purpose: Rapid developments in social networks and their usage in everyday life have caused an explosion in the amount of short electronic documents. Thus, the need to classify this type of document based on their content has a significant implication in many applications. The need to classify these documents in relevant classes according to their text contents should be interested in many practical reasons. Short-text classification is an essential step in many applications, such as spam filtering, sentiment analysis, Twitter personalization, customer review and many other applications related to social networks. Reviews on short text and its application are limited. Thus, this paper aims to discuss the characteristics of short text, its challenges and difficulties in classification. The paper attempt to introduce all stages in principle classification, the technique used in each stage and the possible development trend in each stage.Design/methodology/approach: The paper as a review of the main aspect of short-text classification. The paper is structured based on the classification task stage.Findings: This paper discusses related issues and approaches to these problems. Further research could be conducted to address the challenges in short texts and avoid poor accuracy in classification. Problems in low performance can be solved by using optimized solutions, such as genetic algorithms that are powerful in enhancing the quality of selected features. Soft computing solution has a fuzzy logic that makes short-text problems a promising area of research.Originality/value: Using a powerful short-text classification method significantly affects many applications in terms of efficiency enhancement. Current solutions still have low performance, implying the need for improvement. This paper discusses related issues and approaches to these problems.

Respiratory disease diagnosis remains challenging in resource-constrained settings, where limited specialist expertise contributes to diagnostic uncertainties affecting over 300 million people worldwide. This study presents E-RespiNet, a novel multi-modal deep learning architecture that integrates ELECTRA’s discriminative pre-training with a triple-stream convolutional neural network framework, enhanced through Harmony Search with Opposition-Based Learning optimization for automated respiratory sound classification. The architecture simultaneously processes mel-frequency cepstral coefficients, discrete wavelet transforms, and mel-spectrograms through parallel CNN streams, with features integrated through hierarchical fusion and ELECTRA-based contextual enhancement. Comprehensive evaluations on two independent clinical datasets—the Asthma Detection Dataset Version 2 (1,211 recordings across five conditions) and King Abdullah University Hospital dataset (940 samples from 81 subjects across four conditions)—demonstrated exceptional performance with 98.9% and 98.8% accuracy respectively, representing 5.0% and 4.3% improvements over baseline configurations. Cross-institutional validation revealed 75.7% average accuracy with a 23.3% generalization gap, substantially better than typical medical AI cross-domain performance. Gradient-weighted class activation mapping provided clinically relevant interpretability, while the Harmony Search optimization framework enhanced both performance and cross-institutional robustness. These results demonstrate significant advances in automated respiratory sound analysis through discriminative language model integration and metaheuristic optimization, establishing important benchmarks for deployable respiratory diagnostic tools in diverse healthcare settings.

Rapid urbanization necessitates innovative traffic monitoring solutions. Traditional methods (fixed sensors/CCTV) face limitations in coverage, adaptability, and real-time processing. This review examines advancements (2015–2024) in vision-based unmanned aerial vehicle (UAV) traffic monitoring systems, evaluating their effectiveness in vehicle detection, traffic analysis, and congestion management. A systematic preferred reporting items for systematic reviews and meta-analyses (PRISMA)-guided analysis of 2,895 articles from IEEE Xplore, Scopus, Web of Science, and ACM Digital Library identified 49 eligible studies. Quantitative performance metrics (detection accuracy and latency) were standardized for cross-study comparison. Modern systems achieve 94% detection accuracy and 40 ms latency through edge computing and deep learning (e.g., you look only once (YOLO) and Faster region-based convolutional neural network (Faster R-CNN)). Multi-sensor fusion improves robustness by 35% in challenging conditions. However, battery life (reduced by 40% under processing load) and regulatory barriers remain critical constraints. Artificial intelligence (AI)-driven UAV systems enable real-time, high-accuracy traffic monitoring but require solutions for power efficiency and scalability. Future integration of 5G/6G and swarm intelligence holds promise for next-generation smart traffic management.

The proliferation of sophisticated malware variants necessitates detection frameworks that balance accuracy with interpretability. This paper proposes a hybrid framework integrating global whale optimization, quantum support vector machine (QSVM), and transformer architectures with explainable artificial intelligence (XAI) components. The approach addresses feature selection, quantum-enhanced classification, and sequential pattern recognition through a unified optimization strategy. Evaluated on EMBER 2018 (1.1M samples) and UGRansome (207 K samples), the framework achieves 99.95% and 99.99% accuracy respectively, with ablation studies confirming synergistic performance gains. Statistical validation through 5-fold stratified cross-validation, 95% bootstrap confidence intervals, and McNemar's significance tests confirms that improvements over every baseline are statistically robust (p