This paper proposes an adaptive grouping-based hybrid PSO-GA algorithm to address PSO's premature convergence and GA's slow convergence. The algorithm dynamically partitions the population into elite/regular subgroups, applying PSO for local exploitation and GA for global exploration. Key innovations include adaptive grouping, dynamic weight adjustment, bidirectional elite migration, and stagnation-triggered multi-phase optimization. Experiments on 7 benchmarks show superior convergence accuracy, speed, and stability over standalone PSO/GA (especially for multimodal problems). Further validation on highdimensional $(\mathbf{D}=\mathbf{5 0} / \mathbf{1 0 0})$ CEC 2017 benchmarks, constrained engineering designs, and sensitivity analysis confirms its scalability, robustness, and practical applicability.
Dieyan Liang, Jun-Hang Du, Jun Zhou et al.· 2026 3rd World Conference on...· 0 citations
This paper presents a novel approach to hand gesture recognition based on machine learning techniques applied to data collected from wearable sensors. The proposed system aims to accurately identify intuitive hand gestures to facilitate the development of contactless user interfaces. To achieve robust and reliable recognition performance, various feature extraction methods were systematically employed, and an ensemble learning strategy was developed using Support Vector Machines (SVM), Random Forests (RF), Gradient Boosting (GB), and a Voting Classifier (VC). The gesture dataset utilized in this study consists of over 4,000 samples collected from multiple individuals, capturing diverse gesture classes and conditions. Rigorous experimental evaluation demonstrates that the proposed ensemble approach attains superior accuracy and robustness compared to traditional single-model methods. This research contributes valuable methodological insights and provides an accessible, scalable framework that enhances the practical applicability of sensor-based gesture recognition systems in diverse real-world applications.
Jia-Di Zhang, Zexiao Liang, Shiting Wu et al.· 2026 3rd World Conference on...· 0 citations
The Flexible Job Shop Scheduling Problem (FJSP) is a critical combinatorial optimization problem in modern manufacturing systems, characterized by multiple constraints, dynamic requirements, and NP-hard complexity. This paper presents an improved Ant Colony Optimization (ACO) algorithm specifically designed to address the FJSP by minimizing makespan. The proposed algorithm incorporates enhanced pheromone update mechanisms, dual-level solution encoding for operation sequencing and machine assignment, and adaptive search strategies. Experimental results on a benchmark problem with 4 jobs, 3 processes per job, and 6 machines demonstrate that the improved ACO achieves superior performance compared to traditional metaheuristics, reducing makespan by approximately 8.7% compared to genetic algorithms. The convergence analysis shows stable optimization behavior within 40 iterations, validating the effectiveness and practical applicability of the proposed approach.
Jia-Di Zhang, Zexiao Liang, Shiting Wu et al.· 2026 3rd World Conference on...· 0 citations