1. Solar energy is central to the global power infrastructure, with photovoltaic (PV) cells serving as the primary technology for converting sunlight into electricity [1–3]. Although modern solar c...

Accurate thickness recognition plays a vital role in safeguarding the structural reliability of critical assets. Pulse eddy current testing (PECT), as a non-destructive method that is both non-contact and insensitive to surface coatings, provides an efficient pathway for this purpose. Nevertheless, the complex, nonstationary, and nonlinear characteristics of PECT signals make it difficult for conventional models to jointly capture localized high-frequency patterns and long-range temporal dependencies, thereby constraining their prediction performance. To overcome these issues, we introduce a novel deep learning framework, multi-scale residual dilated convolution, and bidirectional long short-term memory with a squeeze-and-excitation mechanism (MRDC-BiLSE) for PECT time series analysis. The architecture integrates a multi-scale residual dilated convolution block. By combining dilated convolutions with residual connections at different scales, this block captures structural patterns across multiple temporal resolutions, leading to more comprehensive and discriminative feature extraction. Furthermore, to better exploit temporal dependencies, the BiLSTM-SE module combines bidirectional modeling with a squeeze-and-excitation mechanism, resulting in more discriminative feature representations. Experiments on experimental PECT datasets confirm that MRDC-BiLSE surpasses existing methods, showing applicability for real-world thickness recognition.

Electroencephalogram (EEG)-based motor imagery (MI) decoding is vital in brain–computer interface (BCI) systems. Although convolutional neural networks (CNNs) have achieved promising results, existing methods still face limitations in multi-scale feature extraction. Specifically, some CNN architectures focus primarily on local and global temporal features, while medium temporal information remains underexplored. Moreover, conventional feature integration strategies often overlook the distinct characteristics of features at different scales, limiting their effective utilization. To address these limitations, we propose a multi-perspective attention-based multi-scale CNN, called MPAMCNN. The model extracts local, medium, and global EEG features simultaneously by applying convolution kernels with different receptive fields. In addition, we incorporate different attention mechanisms into the corresponding branches to emphasize discriminative information and reduce feature redundancy before fusion. Extensive experiments on two benchmark datasets, BCI Competition IV-2a and IV-2b, demonstrate that MPAMCNN achieves classification accuracies of 79.71% and 88.02%, respectively, validating its efficacy for EEG motor imagery classification. Visualization analysis also reveals improved feature separability and clearer decision boundaries.

Camera-based visual sensing for classroom behavior detection remains challenging because fine-grained behaviors often differ only in subtle posture and hand–object cues, while dense seating, occlusion, scale variation, and background interference further weaken discriminative visual evidence. To address these issues, this study proposes the Multi-scale Context, Hierarchical Integration, and Memory Enhancement Detector (MCHIME-Det), a lightweight, multi-scale context and memory-enhanced detector built on YOLO26n. The framework introduces three complementary components: C3k2PMM combines multi-scale local modeling with direction-aware selective state-space scanning; CGHFF performs channel-guided hierarchical feature interaction across adjacent feature levels; and C2MECM uses input-dependent memory experts to compensate for ambiguous high-level representations. For evaluation, two public classroom behavior datasets were combined into a corpus containing 11,879 images and 71,657 annotated instances across three categories: hand-raising, reading, and writing. On the curated image-level split, MCHIME-Det achieves 76.3% precision, 74.9% recall, 82.1% mAP${}_{50}$, and 61.4% mAP${}_{50:95}$, improving the YOLO26n baseline by 5.6 and 4.4 percentage points in mAP${}_{50}$ and mAP${}_{50:95}$, respectively. These gains are achieved with only 2.36 M parameters and 5.2 GFLOPs, while maintaining 182 FPS on an RTX 4090 and 17.1 FPS on a Jetson Orin Nano edge device. Ablation, cross-architecture, scale-, density-, and overlap-conditioned analyses, cross-source evaluation, image-corruption robustness tests, and cross-hardware benchmarks characterize model performance on the curated benchmark, three sampled external datasets, specified synthetic corruptions, and tested hardware platforms. These results support hierarchical local–global refinement and memory-assisted compensation as effective strategies for lightweight camera-based visual sensing under the evaluated image datasets and inference settings.