Yinghong Zhou

Glass-insulated terminals (GITs) are widely used in high-reliability microelectronic systems, where glass fall-offs in the sealing region may seriously degrade the reliability of the microelectronic component and further degrade the device reliability. Automatic inspection of such defects is challenging due to strong light reflection, irregular defect appearances, and limited defective samples. To address these issues, a coarse-to-fine machine-learning framework is proposed for glass fall-off detection in GIT images. By exploiting the circular-ring geometric prior of GITs, an adaptive sector partition scheme is introduced to divide the region of interest into sectors. Four categories of sector features, including color statistics, gray-level variations, reflective properties, and gradient distributions, are designed for coarse classification using a gradient boosting decision tree (GBDT). Furthermore, a sector neighbor (SN) feature vector is constructed from adjacent sectors to enhance fine classification. Experiments on real industrial GIT images show that the proposed method outperforms several representative inspection approaches, achieving an average IoU of 96.85%, an F1-score of 0.984, a pixel-level false alarm rate of 0.55%, and a pixel-level missed alarm rate of 35.62% at a practical inspection speed of 32.18 s per image.

Small space object detection (SSOD) plays a crucial role in orbital debris monitoring and spacecraft defense, providing critical support for space situational awareness (SSA). To adapt complex background interference and lightweight deployment, a Mamba-driven multi-level feature fusion network is designed based on YOLO architecture. Specifically, an adaptive feature enhancement module (AFEM) is introduced to effectively incorporate multi-level information. To consolidate valid information while suppressing redundant noise, a Mamba-driven dual-branch feature extraction module (DFEM) is developed for spatial-aware and channel-aware selective scanning and merging. Comparative experiments demonstrate that the proposed SSOD-YOLO achieves superior performance on a public small space object dataset, with 95.21% Recall, 97.94% mAP50, and 96.12% F1-score, outperforming both the YOLO series models and the space object detection methods.

Accurate predictions of the state of health (SOH) and remaining useful life (RUL) of lithium-ion batteries are crucial to ensure their efficient and safe operations. Existing deep learning methods are hindered by the limited quantity and diversity of datasets, leading to model overfitting and poor generalization. To this end, a bimodal large-small model collaborative network (BLSCN) is designed in this paper, which seamlessly combines a pretrained large vision model (LVM) with a designed small model (SM) for joint prediction of SOH and RUL of lithium-ion batteries. Specifically, the BLSCN utilizes the LVM to extract features from the bimodal images generated by the battery data, followed by a SM for feature fusion and prediction. To promote the generalization ability of LVM on the battery data, an attention mask strategy is proposed to guide the LVM to focus on more features of interest in the images. In the SM, an elaborately-designed cross fusion module (CFM) is employed to interactively fuse bimodal image features for subsequent joint prediction of SOH and RUL. Experimental results on the public dataset demonstrate the superiority of the proposed BLSCN on joint prediction of SOH and RUL, with coefficients of determination (R²) of 0.983 and 0.942 for SOH and RUL prediction tasks, respectively.

Infrared tiny target detection is faced with difficulty that tiny-sized targets are easily drowned out in complex backgrounds. To address this problem, this paper presents an end-to-end deep learning framework, which consists of an anchor-free U-shaped backbone for extracting image features and a detection head block for target attributes regression. To capture fine-grained details and semantic information, a multi-hop and multiscale fusion block is designed in the backbone for effective progressive feature fusion. Moreover, to adaptively adjust the constraints for the localization and shape description of the targets, a tolerance-adjustable measure is proposed in the detection head to provide a reliable means for determining the authenticity of targets. Extensive experiments indicate that our trained model can simultaneously detect infrared targets with various sizes, especially achieve an excellent detection performance for point targets with 98.2% F1-score, 3.1% error rate and 0.5% omission rate. Comparative experiments indicate that the proposed method is superior to SOTA deep learning based methods, especially for tiny targets.

Online inspection of flexographic printing labels (FPLs) is significant for preventing batch misprints to ensure mass production quality. In this paper, an online inspection system is designed for fabric FPLs, in which a multi-scale generative adversarial network (GAN) framework with several region adaptive schemes is proposed to inspect the fabric FPL images acquired by the designed hardware system. To address the scarcity of defective samples in real production, the framework only employs qualified FPL samples to train the GAN template generators for generating the templates. Different from previous template generators, the framework incorporates skip connections and a multi-scale architecture to improve the template representation ability. To deal with tensions in the FPL substrates and to capture subtle defects, several region adaptive schemes are designed for the inspection stage, involving statistical region subtracter (SRS), region adaptive thresholding (RAT) and region defect assessment (RDA). Specifically, during inspection, the inspected FPL is adaptively divided into the character and background regions, which are dealt with these region adaptive schemes. Experimental results demonstrate that the proposed framework achieves the fabric FPL inspection performance of 0.1% omission rate and 1.8% error rate at a reasonable speed of 45ms per sample, which can meet with the online inspection requirements for real production.

Automatic intention recognition in financial service scenarios faces challenges such as limited corpus size, high colloquialism, and ambiguous intentions. This paper proposes a hybrid intention recognition framework for financial customer service, which involves semi-supervised learning data augmentation, label semantic inference, and text classification. A semi-supervised learning method is designed to augment the limited corpus data obtained from the Chinese financial service scenario, which combines back-translation with BERT models. Then, a K-means-based semantic inference method is introduced to extract label semantic information from categorized corpus data, serving as constraints for subsequent text classification. Finally, a BERT-based text classification network is designed to recognize the intentions in financial customer service, involving a multi-level feature fusion for corpus information and label semantic information. During the multi-level feature fusion, a shallow-to-deep (StD) mechanism is designed to alleviate feature collapse. To validate our hybrid framework, 2977 corpus texts about loan service are provided by a financial company in China. Experimental results demonstrate that our hybrid framework outperforms existing deep learning methods in financial customer service intention recognition, achieving an accuracy of 89.06%, precision of 90.27%, recall of 90.40%, and an F1 score of 90.07%. This study demonstrates the potential of the hybrid framework to automatic intention recognition in financial customer service, which is beneficial for the improvement of the financial service quality.

The three-dimensional (3D) reconstruction of the hepatic duct tree is significant for the minimally invasive surgery of hepatobiliary stone disease, which can be influenced by the quantity of the CT scans of hepatic ducts. If insufficient CT scans with low inter-slice resolution are directly utilized for 3D reconstruction, discontinuities and gaps will emerge in the reconstructed hepatic duct tree. In this paper, a novel end-to-end deep learning framework is designed for the inter-slice super-resolution segmentation of the CT slices of hepatic ducts, which can improve the 3D reconstruction performance in the inter-slice dimension. Specifically, the framework cascades into an inter-slice super-resolution subnetwork and a segmentation subnetwork. A deep learning network is introduced as the inter-slice super-resolution subnetwork to generate an intermediate slice between two adjacent CT slices in the simulated CT scans with low inter-slice resolution. To capture the spatiotemporal correlation existing in the CT scans of hepatic ducts, the ConvLSTM is introduced into the U-Net-like segmentation subnetwork in the high-dimensional feature space. To further suppress the problems of discontinuities and gaps, a structure-aware loss function is proposed by incorporating the structural similarity index measure (SSIM) as a regulator to dynamically assign the contribution of the generated CT slice to the total loss of the designed framework. Experimental results demonstrate that our proposed framework performs better segmentations for hepatic ducts than several existing deep learning networks with the performance of 0.7690 DICE and a 0.7712 F1-score, which is beneficial for the 3D reconstruction of the hepatic duct tree.

To aid the diagnosis of chronic obstructive pulmonary disease (COPD), a local-to-global deep framework with group attentions and slice-aware loss is designed in this paper, which utilizes the chest CT sequences of the patients as the network input. To fully mine the medical hints submerged in the CT slices, two types of group attentions are designed to extract local–global features of the grouped slices. Specifically, in each group, a group local attention block (GLAB) and a group global attention block (GGAB) are designed to extract local features in the CT slices and long-range dependencies among the grouped slices. To alleviate the influence of different numbers of CT slices in the chest CT sequences for different patients, a slice-aware loss is proposed by incorporating a normalized coefficient into the cross-entropy loss. Experimental results indicate that the designed deep model performs a good COPD identification on a real COPD dataset with 96.08% accuracy, 94.12% sensitivity, 97.06% specificity, and 95.32% AUC, which is superior to some existing deep learning methods.

The rapid growth of EVs relies on the development of supporting infrastructure, e.g., charging stations (CSs). The sizing problem of a CS typically involves minimizing the investment costs. Therefore, a flexible and precise sizing strategy is crucial. However, the existing methods suffer from the following issues: (1) they do not consider charging station deployments based on the charging stack; (2) existing sizing strategies based on smart charging technology consider a single scenario and fail to meet the demand for flexible operation under multiple scenarios in real-life situations. This paper proposes a novel CS sizing framework specific for charging stacks to overcome these challenges. Specifically, it first addresses the charging-stack-based CS sizing problem, and then it proposes the corresponding multiscenario constraints, i.e., exclusive and shared, for capacity-setting optimization. In addition, a novel quality of service (QoS) formulation is also proposed to better relate the user QoS levels to the CS sizing problem. Finally, it also explores the relationship between the investment costs and the total power of the needed charging stack under three business models. Extensive experiments show that the proposed framework can offer valuable guidance to CS operators in competitive environments.