Accurately identifying B-lines and pleural line (P-line) in lung ultrasound (LUS) videos is valuable for evaluating certain lung conditions. However, manual interpretation remains subjective and highly dependenton operator expertise. Existing deep learning methods often suffer from performance degradation due to speckle noise and motion artifacts. Moreover, the limited availability of LUS video data annotated for multiple diagnostic features such as B-lines and the P-line limits model development. Therefore, this paper introduces ILD-LUS, a new clinical LUS database designed based on interstitial lung disease (ILD) analysis by category labeling, comprising 2,149 ultrasound videos (193,410 frames). Also, we construct an external test set based on the public Covid-BLUES dataset for the evaluation of B-lines and P-line recognition in different pulmonary pathologies. Then, we propose a novel video analysis framework that integrates wavelet enhancement with temporal attention modeling. Specifically, we employ a dual-component frequency feature enhancement method using the Discrete Wavelet Transform (DWT), which effectively suppresses noise while preserving important landmarks. Subsequently, an adaptive attention module is introduced to model long-range temporal dependencies and improve dynamic feature representation across consecutive frames. Experimental results show that the proposed method achieves over 94% AUC and 82% ACC for both B-lines and P-line classification on both the ILD-LUS and Covid-BLUES datasets, outperforming existing methods. These findings demonstrate the robustness and generalizability of our approach across different pathological conditions. Overall, the proposed framework shows strong potential for supporting clinical decision-making in LUS analysis.

Glomerulus detection is a critical component of renal histopathology assessment, essential for diagnosing glomerulonephritis. To mitigate the increasing workload on pathologists, AI-assisted diagnostic methods based on high-resolution digital pathology whole slide images have been developed. However, these current AI-assisted approaches are limited to high-resolution whole slide images, necessitating expensive digital scanner equipment, high image storage costs, and significant computational complexity. To address this limitation, this paper pioneers a method for facilitating glomerulus detection in low-resolution human kidney pathology images. Specifically, we propose a novel multi-step hybrid knowledge distillation method. Our method distills both the global features and the semantic information through a hybrid knowledge distillation strategy that integrates offline and online knowledge distillation, where the information from high-resolution pathological images is successively transferred to student model from the global features in the shallow network layers to the semantic information of the back-end through a multi-step training strategy. Experimental results on two datasets show that the proposed method achieves effective detection outcomes for low-resolution kidney pathology images. Compared to other state-of-the-art detection techniques, our method achieves an ${AP}_{0.5:0.95}$ improvement of 23.1% on the private LN dataset and 15.9% on the public HUBMAP dataset.

Deep convolutional neural networks (DCNNs) are vulnerable to small perturbations. Currently, first-order optimization-based adversarial attack methods are the mainstream methods for generating perturbations, such as PGD. It is known that, the second-order optimization method can converge faster than the first-order methods. Therefore, it is natural to expect the performance of second-order optimization-based attack methods should be better than that of first-order methods. However, the existing second-order attack methods do not demonstrate superior performance compared to first-order attack methods. The reason behind is that, these second-order attack methods employ the same sign function as first-order methods to generate pixel perturbations. Hence, in this article, we propose a second-order optimization-based adaptive attack method, and at its core, an adaptive perturbation generation strategy is designed. We evaluate the proposed method on multiple datasets and various models. The experimental results demonstrate that the proposed second-order optimization-based adaptive attack method is able to generate adversarial examples that cause misclassification of DCNNs in fewer iterations than existing second-order attack methods and PGD, and has competitive time complexity.

Domain Generalizable Person Re-identification (DG ReID) is a practical task that generalizes the model trained on multiple source domains to unseen target domains without fine-tuning. Existing methods usually combine diverse normalization techniques to remove style information while retaining discriminative features. However, they overlook the absence of the target domain while training. In this work, we propose a Latent Distribution Alignment (LDA) method to indirectly align source and target domains through the dynamically constructed latent distribution without any added learnable parameters. Specifically, we design an expert network to dynamically construct a latent distribution and store the domain-specific representation information by fully utilizing batch-wise statistical parameters. Subsequently, one source domain, acting as the mimical target domain of the remaining source domains, explicitly aligns with the latent distribution through an instance-wise domain alignment network through Anti-Normalization (AN). Extensive experiments show that our method is simple yet effective in enhancing the generalizable capability.

As an important device for high-speed railway (HSR) to obtain electrical energy from outside, the structure of pantograph will directly affect the safety and stability of HSR operation. The current pantograph structure detection algorithm has a low accuracy rate, which cannot effectively cope with various complex scenarios and external disturbances during the actual operation of HSR and is difficult to achieve real-time detection of the pantograph structure. In order to solve the current problems in pantograph structure detection, the rigid target subregion longest common sub-sequence (RTS-LCSS) is proposed, which is a new method for real-time pantograph structure detection. This paper realizes the positioning of pantograph region by you only look once (YOLO) V7, then the pantograph characteristic curve is fitted according to the pantograph feature points, and finally compares the fitted pantograph characteristic curve with the normal pantograph characteristic curve to achieve the accurate evaluation of the pantograph structure. Meanwhile, in order to improve the accuracy of YOLO, this paper adopts deep convolution generative adversarial nets (DCGAN) to expand the training samples in conjunction with the real situation of HSR. The method proposed in this paper can realize the real-time detection of pantograph structure in addition to the specific localization of structural abnormal regions. The experimental results show that the proposed method has higher robustness and stronger environmental adaptation. The algorithm accuracy and real-time performance meet the actual operation requirements of HSR, and it continues to function well under the influence of complex scenes and external environment interference.

Artificial intelligence (AI) offers opportunities but also challenges for biomedical research and healthcare. This position paper shares the results of the international conference "Fair medicine and AI" (online 3-5 March 2021). Scholars from science and technology studies (STS), gender studies, and ethics of science and technology formulated opportunities, challenges, and research and development desiderata for AI in healthcare. AI systems and solutions, which are being rapidly developed and applied, may have undesirable and unintended consequences including the risk of perpetuating health inequalities for marginalized groups. Socially robust development and implications of AI in healthcare require urgent investigation. There is a particular dearth of studies in human-AI interaction and how this may best be configured to dependably deliver safe, effective and equitable healthcare. To address these challenges, we need to establish diverse and interdisciplinary teams equipped to develop and apply medical AI in a fair, accountable and transparent manner. We formulate the importance of including social science perspectives in the development of intersectionally beneficent and equitable AI for biomedical research and healthcare, in part by strengthening AI health evaluation.

Unsupervised domain adaptive (UDA) person re-identification (ReID) has gained increasing attention for its effectiveness on the target domain without manual annotations. Most fine-tuning based UDA person ReID methods focus on encoding global features for pseudo labels generation, neglecting the local feature that can provide for the fine-grained information. To handle this issue, we propose a Learning Feature Fusion (LF2) framework for adaptively learning to fuse global and local features to obtain a more comprehensive fusion feature representation. Specifically, we first pre-train our model within a source domain, then fine-tune the model on unlabeled target domain based on the teacher-student training strategy. The average weighting teacher network is designed to encode global features, while the student network updating at each iteration is responsible for fine-grained local features. By fusing these multi-view features, multi-level clustering is adopted to generate diverse pseudo labels. In particular, a learnable Fusion Module (FM) for giving prominence to fine-grained local information within the global feature is also proposed to avoid obscure learning of multiple pseudo labels. Experiments show that our proposed LF2framework outperforms the state-of-the-art with 73.5% mAP and 83.7% Rank1 on Market1501 to DukeMTMC-ReID, and achieves 83.2% mAP and 92.8% Rank1 on DukeMTMC-ReID to Market1501. The source code is available at: https://github.com/DJEddyking/LF2.

The dropper is one of the core components of the high speed railway catenary and dropper failure will lead to serious transportation accidents. It is very important to carry out dropper failure and defect detection. There are a large number of droppers installed in the catenary. The dropper images are collected by the high-definition camera installed on the top of the moving catenary inspection vehicles. The image quality and image consistency are poor, and it is very difficult to identify dropper defects automatically. The railway department and companies lack efficient and intelligent detection methods. This article innovatively proposes a multialgorithm fusion image processing technology, and builds a dropper recognition and failure-defect detection model based on a deep learning algorithm and subpixel level dropper defect detection model, and achieves high accuracy dropper failure and defect detection. The detection model based on the Faster R-CNN algorithm is studied to realize the positioning and recognition of the dropper and the failure detection of bending slack and broken dropper. The subpixel level dropper defect detection algorithm is based on the fusion of the image preprocessing, dropper fine positioning algorithm, edge fitting and bending zoom algorithms, the Hough transform algorithm, and so on. These can be used to realize detection of defects, such as microdeformation, dropper-strands loosened, dropper-strands broken, and foreign body adhesions. The test is verified by the catenary images taken from a practical high speed railway. The detection accuracy, real-time performance, and stability of the algorithm meet the needs of inspection and maintenance for a high speed railway.

This paper investigates a synchronous control method with variable proportion for multi-axis servo system based on sliding mode variable structure to solve the inherent shortcomings of parallel synchronous uncoupled control for multi-servo motors. The method is an improvement of the ring-coupled control strategy and is thus applicable to multi-axis proportional synchronous control. No-salient pole permanent magnet synchronous servo motors are taken as the controlled objects. A sliding mode controller is designed according to the state equation of the mathematical model. The rationality of the designed controller is proven by Lyapunov stability theory, and the method is compared with a parallel synchronous control strategy, which is widely used in the object of this research. Finally, the feasibility and superiority of the method in a multi-axis synchronous control system with variable proportion is confirmed by MATLAB simulation and experimental verification. The method is applied to a three-degree-of-freedom servo system, and makes the theoretical research have the corresponding practical engineering application value.

Community detection finds its applications in the biological networks and social networks, like predicting functional modules of proteins, recommending items to the users based on their interests, and exploring potential relationships among persons. Modularity is a widely-used criterion for evaluating the quality of the detected community structures. Due to modularity maximization is an NP-hard problem, developing the approximate algorithms with good accuracy and computational complexity is challenging and of great significance. In this paper, a novel algorithm based on competitive Hopfield neural network (CHNN for short) for maximizing modularity is proposed, where a new energy function and a two-dimensional topology is designed, and the winner-takes-all strategy for updating the outputs of neurons in each row of CHNN is adopted. Moreover, the convergence of the proposed algorithm is proved. The algorithm is capable of converging fast and achieving good modularity. Experimental results on multiple empirical and synthetic networks show the proposed algorithm can effectively and efficiently identify the community structures of the networks, and has the competitive performance compared to several other baseline algorithms for community detection.

The need to provide remote visualization of large datasets with adequate levels of quality and interactively has become a major impediment to distributed collaboration in Computational Science.Although Image Based Rendering (IBR) techniques based on plenoptic functions have some important advantages over other approaches to this problem, they suffer from an inability to deal with issues of network latency and server load, due to the large size of the IBR databases they generate.Consequently, IBR techniques have been left largely unexplored for this purppose.In this paper we describe strategies for addressing these obstacles using Logistical Networking (LoN), which is a new and highly scalable approach to deploying storage as a shared communication resource.Leveraging LoN technology and infrastructure, we developed a remote visualization system based on concepts of light field rendering, an IBR method using a 4-D plenoptic function.Our system extends existing work on light fields by employing a modified method of parameterization and data organization that supports more efficient prefetching, caching and loss-less compression. Using this approach, we have been able to interactively browse multi-gigabyte, high-resolution light field databases across the wide area network at 30 frames per second.

In this paper, the natures of random and pseudo-random input sequences and their influence on permanent and intermittent fault detecting are analyzed. The aliasing fault coverage between the pseudo-random and random sequences is estimated. The activity probability features of the intermittent faults are considered. The self-test circuits of the intermittent faults are illustrated. The experimental results based on real circuits are obtained through simulation. The mathematical analysis and experimental results show that the quality of the pseudo-random testing is better than that of the random testing for permanent and intermittent faults. The Markov chain models are used in obtaining the input sequence length needed for determining if a circuit fault is intermittent or permanent.