Tiny defect detection is a knotty task in industrial electronics production. Existing traditional and deep learning methods have achieved satisfactory performance, however, they still face challenges in accuracy, generalization ability, and computational complexity. Therefore, this study designs a tiny defect detection-based you only look once (TDD-YOLO) model and proposes an innovative compression training strategy to train on low-resolution images and test on original images. First, a four-ME layers structure is adopted to the backbone network, to integrate more underlying information and extract effective features. In addition, a miniature detection head is incorporated into the head network to improve the accuracy and generalization performance of you only look once (YOLO). Meanwhile, TDD-YOLO introduces wise intersection over union (W-IoU) to reevaluate the loss of bounding box regression (BBR) and reduce false negatives by fitting the model well to regular quality anchor boxes. Finally, an image compression method at different ratios is applied in the proposed compression training strategy, to reduce computational complexity and surprisingly further improve accuracy. Comprehensive experiments on several variable compressed datasets which are based on a public printed circuit board (PCB) defect dataset validate the effectiveness of our theoretical approach and illustrate that our proposed method outperforms state-of-the-art methods.

Feature selection (FS) is a classic and challenging optimization task in most machine learning and data mining projects. Recently, researchers have attempted to develop more effective methods by using metaheuristic methods in FS. To increase population diversity and further improve the effectiveness of the beluga whale optimization (BWO) algorithm, in this paper, we propose a multi-strategies improved BWO (MSBWO), which incorporates improved circle mapping and dynamic opposition-based learning (ICMDOBL) population initialization as well as elite pool (EP), step-adaptive Lévy flight and spiral updating position (SLFSUP), and golden sine algorithm (Gold-SA) strategies. Among them, ICMDOBL contributes to increasing the diversity during the search process and reducing the risk of falling into local optima. The EP technique also enhances the algorithm′s ability to escape from local optima. The SLFSUP, which is distinguished from the original BWO, aims to increase the rigor and accuracy of the development of local spaces. Gold-SA is introduced to improve the quality of the solutions. The hybrid performance of MSBWO was evaluated comprehensively on IEEE CEC2005 test functions, including a qualitative analysis and comparisons with other conventional methods as well as state-of-the-art (SOTA) metaheuristic approaches that were introduced in 2024. The results demonstrate that MSBWO is superior to other algorithms in terms of accuracy and maintains a better balance between exploration and exploitation. Moreover, according to the proposed continuous MSBWO, the binary MSBWO variant (BMSBWO) and other binary optimizers obtained by the mapping function were evaluated on ten UCI datasets with a random forest (RF) classifier. Consequently, BMSBWO has proven very competitive in terms of classification precision and feature reduction.

In this article, we propose an effective grasp detection network based on an improved deformable convolution and spatial feature center mechanism (DCSFC-Grasp) to precisely grasp unidentified objects. DCSFC-Grasp includes three key procedures as follows. First, improved deformable convolution is introduced to adaptively adjust receptive fields for multiscale feature information extraction. Then, an efficient spatial feature center (SFC) layer is explored to capture the global remote dependencies through a lightweight multilayer perceptron (MLP) architecture. Furthermore, a learnable feature center (LFC) mechanism is reported to gather local regional features and preserve the local corner region. Finally, a lightweight CARAFE operator is developed to upsample the features. Experimental results show that DCSFC-Grasp achieves a high accuracy (99.3% and 96.1% for the Cornell and Jacquard grasp datasets, respectively) and even outperforms the existing state-of-the-art grasp detection models. The results of real-world experiments on the six-DoF Realman RM65 robotic arm further demonstrate that our DCSFC-Grasp is effective and robust for the grasping of unknown targets.

Facial expression plays an important role in human–computer interaction and affective computing. However, existing expression recognition methods cannot effectively capture multi-scale structural details contained in facial expressions, leading to a decline in recognition accuracy. Inspired by the multi-scale processing mechanism of the biological visual system, this paper proposes a wavelet-guided global–local feature aggregation network (WGGLFA) for facial expression recognition (FER). Our WGGLFA network consists of three main modules: the scale-aware expansion (SAE) module, which combines dilated convolution and wavelet transform to capture multi-scale contextual features; the structured local feature aggregation (SLFA) module based on facial keypoints to extract structured local features; and the expression-guided region refinement (ExGR) module, which enhances features from high-response expression areas to improve the collaborative modeling between local details and key expression regions. All three modules utilize the spatial frequency locality of the wavelet transform to achieve high-/low-frequency feature separation, thereby enhancing fine-grained expression representation under frequency domain guidance. Experimental results show that our WGGLFA achieves accuracies of 90.32%, 91.24%, and 71.90% on the RAF-DB, FERPlus, and FED-RO datasets, respectively, demonstrating that our WGGLFA is effective and has more capability of robustness and generalization than state-of-the-art (SOTA) expression recognition methods.

Metaheuristic algorithms are widely used to solve complex optimization problems, but the trade-off between exploration and exploitation often limits their performance. The Crested Porcupine Optimizer (CPO) employs four bio-inspired defense mechanisms and achieves competitive performance, but it still tends to converge prematurely, initialize populations poorly, and rely on static parameters that cannot adapt to different phases. This paper proposes a Multi-Strategy Enhanced Crested Porcupine Optimizer (MSCPO) with four phase-targeted enhancement strategies: (1) Kent Chaos Opposition-Based Learning Initialization (KCOL) improves the initial population distribution through chaotic-weighted reflection; (2) Arctic Puffin Optimization (APO)-Inspired Dual-Modal Evasion (APO-DME) reduces dependence on the global best solution and increases population diversity through dual-mode differential perturbation; (3) Adaptive Dual-Differential Perturbation (ADDP) refines the search by combining population diversity and elite guidance information; (4) Periodic Dynamic Adaptive Perturbation (PDAP) enhances exploitation through periodic trigonometric perturbation and a fitness-conditioned update rule. These strategies interact across the optimization process to strengthen each defense mechanism at the appropriate phase. On the CEC 2017 and CEC 2022 benchmark suites, MSCPO achieves the best overall mean rank among all compared algorithms, with an overall rank of 2.638 on CEC 2017 and 2.375 on CEC 2022. A full-factorial ablation over all 16 strategy combinations confirms that each strategy contributes positively: removing any single strategy degrades the overall mean rank, and the complete MSCPO achieves the best mean rank (3.34), significantly outperforming all single-strategy variants (Wilcoxon signed-rank test, p < 0.001). To verify the practical applicability of MSCPO, the algorithm is further applied to three engineering design problems: step-cone pulley design, hydrostatic thrust bearing design, and robotic gripper design. MSCPO ranks first on the hydrostatic thrust bearing problem, second on the step-cone pulley problem, and third on the robotic gripper problem. Future work will explore adaptive population sizing to further improve the scalability of MSCPO on very high-dimensional problems.