Search

Advanced machine learning (ML) models are utilized for accurate shear strength prediction of reinforced concrete beams (RCB), but their lack of interpretability makes it unclear how models make specific predictions, reducing their reliability and applicability. Mainstream model-agnostic interpretation methods require numerous additional computing procedures, limiting the interpretation efficiency, and the model prediction process remains unknown. This study proposes an inherently interpretable shear strength prediction model for RCB with stirrups based on Explainable Boosting Machine (EBM) and Bayesian optimization. The EBM algorithm decomposes the predicted shear strength into individual shape functions, thus thoroughly revealing the prediction process. Besides, the ML tasks of selecting a model with optimal hyperparameters are automatically performed by Bayesian optimization to reduce computational cost. The developed model is validated on a database including 372 specimens. Compared with shear design codes, empirical models and prominent ML models, the EBM model obtains most accurate predictions for the test set with R2, MAE, and RMSE of 0.9293, 35.42 kN, and 50.99 kN, respectively. The accuracy of EBM is robust to varying input variables through trend analysis. Its interpretability fully discloses the contribution of individual features to the shear strength, and the model rationality is verified by comparing feature contribution with existing mechanisms. The proposed EBM model achieves inherently interpretable shear strength predictions while maintaining high accuracy, which promotes the model applicability in structural assessment.

Component identification and depth estimation are important for detecting the integrity of post-disaster structures. However, traditional manual methods might be time-consuming, labor-intensive, and influenced by subjective judgments of inspectors. Deep-learning-based image visual inspection is a new approach to overcome these problems, but repeated modeling is required for different inspection tasks, which limits inspection accuracy and practical deployment efficiency. In this study, it is observed that the matched ratios of pixel pairs between component identification and depth estimation reach a high value, which indicates the dual tasks are highly related. Therefore, the Multi-Scale Task Interaction Network (MTI-Net) is proposed for structural images to simultaneously accomplish both tasks for accurate and efficient structural inspection. It propagates distilled task information from lower to higher scales. Then, it aggregates the refined task features from all scales to produce the final per-task predictions. Experiments show that MTI-Net delivers the full potential of multi-task learning, with a smaller memory footprint and higher efficiency compared to single-task learning. For the evaluation metrics of model performance, the mean Intersection over Union (mIoU) of component identification improves by 2.30, and root mean square error (RMSE) drops by 0.36 m with the aid of the multi-task strategy. The multi-task deep learning framework has great potential value in engineering applications.

IntroductionIn December 2021, a large-scale epidemic broke out in Xi’an, China, due to SARS-CoV-2 infection. This study reports the effect of vaccination on COVID-19 and evaluates the impact of different vaccine doses on routine laboratory markers.MethodsThe laboratory data upon admission, of 231 cases with COVID-19 hospitalized from December 8, 2021 to January 20, 2022 in Xi’an, including blood routine, lymphocyte subtypes, coagulative function tests, virus specific antibodies and blood biochemical tests were collected and analyzed.ResultsOf the 231 patients, 21 were not vaccinated, 158 were vaccinated with two doses and 52 with three doses. Unvaccinated patients had a higher proportion of moderate and severe symptoms than vaccinated patients, while two-dose vaccinated patients had a higher proportion than three-dose vaccinated patients. SARS-CoV-2 specific IgG levels were significantly elevated in vaccinated patients compared with unvaccinated patients. Particularly, unvaccinated patients had lower counts and percentages of lymphocytes, eosinophils and CD8+ T-lymphocytes, and elevated coagulation-related markers. In addition, vaccination had no effect on liver and kidney function.ConclusionsVaccination against SARS-CoV-2, inducing high IgG level and increased CD8+ T cells and eosinophils, and regulating coagulation function, can significantly attenuate symptoms of COVID-19, suggesting that the vaccine remains protective against SARS-CoV-2.

The storage of medical images is one of the challenges in the medical imaging field. There are variable works that use implicit neural representation (INR) to compress volumetric medical images. However, there is room to improve the compression rate for volumetric medical images. Most of the INR techniques need a huge amount of GPU memory and a long training time for high-quality medical volume rendering. In this paper, we present a novel implicit neural representation to compress volume data using our proposed architecture, that is, the Lanczos downsampling scheme, SIREN deep network, and SRDenseNet high-resolution scheme. Our architecture can effectively reduce training time, and gain a high compression rate while retaining the final rendering quality. Moreover, it can save GPU memory in comparison with the existing works. The experiments show that the quality of reconstructed images and training speed using our architecture is higher than current works which use the SIREN only. Besides, the GPU memory cost is evidently decreased.

"Missing markers problem", that is, missing markers during a motion capture session, has been raised for many years in Motion Capture field. We propose the locally weighted principal component analysis (PCA) regression method to deal with this challenge. The main merit is to introduce the sparsity of observation datasets through the multivariate tapering approach into traditional least square methods and develop it into a new kind of least square methods with the sparsity constraints. To the best of our knowledge, it is the first least square method with the sparsity constraints. Our experiments show that the proposed regression method can reach high estimation accuracy and has a good numerical stability.

Human motion tracking is a prevalent technique in many fields. A common difficulty encountered in motion tracking is the corrupted data is caused by detachment of markers in 3D motion data or occlusion in 2D tracking data. Most methods for missing markers problem may quickly become ineffective when gaps exist in the trajectories of multiple markers for an extended duration. In this paper, we propose the principal component eigenspace based gap filling methods that leverage a training sample set for estimation. The proposed method is especially beneficial in the scenario of motion data with less predictable or repeated movement patterns, and that of even missing entire frames within an interval of a sequence. To highlight algorithm robustness, we perform algorithms on twenty test samples for comparison. The experimental results show that our methods are numerical stable and fast to work.

Image classification systems are known to be vulnerable to adversarial attacks, which are imperceptibly perturbed but lead to spectacularly disgraceful classification. Adversarial training is one of the most effective defenses for improving the robustness of classifiers. We introduce an enhanced adversarial training approach in this work. Motivated by human's consistently accurate perception of surroundings, we explore the artificial attention of deep neural networks in the context of adversarial classification. We begin with an empirical analysis of how the attention of artificial systems will change as the model undergoes adversarial attacks. Observation is that the class-specific attention gets diverted and subsequently induces wrong prediction. To that end, we propose a regularizer encouraging the consistency in the artificial attention on the clean image and its adversarial counterpart. Our method shows improved empirical robustness over the state-of-the-art, secures 55.74% adversarial accuracy on CIFAR-10 with perturbation budget of 8/255 under the challenging untargeted attack in white-box settings. Further evaluations on CIFAR-100 also show our potential for a desirable boost in adversarial robustness for deep neural networks. Code and trained models of our work are available at: https://github.com/lizhuorong/Towards-Adversarial-Robustness-via-Feature-matching.

Abstract MicroRNA-21 (miR-21), probably one of the most studied miRNAs to date, is found pleiotropic in various biological events. Its emerging role in pulmonary remodeling has attracted extensive attention. This review summarizes the genomic information of its primary transcript and various transcriptional regulations on its promoter. In addition, the role of miR-21 in pulmonary remodeling related signaling such as transforming growth factor β (TGF-β), bone morphogenetic protein (BMP), epidermal growth factor receptor (EGFR) and Notch signaling is discussed. Various validated miR-21 target genes participate in controlling of the overactive cell accumulation, smooth muscle contraction, inflammatory stress (trigger for lung epithelium damage), extracellular matrix deposition and hypoxia-induced disorders. Moreover, we focus on its particular implication in events including inflammatory stress-driven epithelium damage, epithelial-to-mesenchymal transition (EMT), transdifferentiation of fibroblasts into myofibroblasts, hypoxia stimuli and ROS response, as well as some other pulmonary remodeling related events such as overactive fibroblast (myofibroblast) accumulation, extracellular matrix deposition, and angiogenesis. Here, we summarize the strong potential of miR-21 in pulmonary remodeling and provide novel clues for further research in this area.

Benefiting from the joint consideration of geometric structures and low-rank constraint, graph low-rank representation (GLRR) method has led to the state-of-the-art results in many applications. However, it faces the limitations that the structure of errors should be known a prior, the isolated construction of graph Laplacian matrix, and the over shrinkage of the leading rank components. To improve GLRR in these regards, this paper proposes a new LRR model, namely iterative reconstrained LRR via weighted nonconvex regularization, using three distinguished properties on the concerned representation matrix. The first characterizes various distributions of the errors into an adaptively learned weight factor for more flexibility of noise suppression. The second generates an accurate graph matrix from weighted observations for less afflicted by noisy features. The third employs a parameterized rational function to reveal the importance of different rank components for better approximation to the intrinsic subspace structure. Following a deep exploration of automatic thresholding, parallel update, and partial SVD operation, we derive a computationally efficient low-rank representation algorithm using an iterative reconstrained framework and accelerated proximal gradient method. Comprehensive experiments are conducted on synthetic data, image clustering, and background subtraction to achieve several quantitative benchmarks as clustering accuracy, normalized mutual information, and execution time. Results demonstrate the robustness and efficiency of IRWNR compared with other state-of-the-art models.

Matrilin-1 (Matn1), a cartilage-specific peri-cellular and extracellular matrix (ECM) protein, has been hypothesized to regulate ECM interactions and transmit mechanical signals in cartilage. Since Matn1 knock-out (Matn1-/-) mice exhibit a normal skeleton, its function in vivo is unclear. In this study, we found that the anabolic Acan and Col2a transcript levels were significantly higher in wildtype (Matn1+/+) mouse cartilage than that of MATN1-/- mice in vivo. However, such difference was not observed between Matn1+/+ and MATN1-/- chondrocytes cultured under stationary conditions in vitro. Cyclic loading significantly stimulated Acan and Col2a transcript levels in Matn1+/+ but not in MATN1-/- chondrocytes. This suggests that, while Matn1+/+ chondrocytes increase their anabolic gene expression in response to mechanical loading, the MATN1-/- chondrocytes fail to do so because of the deficiency in mechanotransduction. We also found that altered elastic modulus of cartilage matrix in Matn1-/- mice, suggesting the mechanotransduction has changed due to the deficiency of Matn1. To understand the impact of such deficiency on joint disease, mechanical loading was altered in vivo by destabilization of medial meniscus. While Matn1+/+ mice exhibited superficial fissures and clefts consistent with mechanical damage to the articular joint, Matn1-/- mice presented more severe cartilage lesions characterized by proteoglycan loss and disorganization of cells and ECM. This suggests that Matn1 deficiency affects pathogenesis of post-traumatic osteoarthritis by failing to up-regulate anabolic gene expression. This is the first demonstration of Matn1 function in vivo, which suggests its protective role in cartilage degeneration under altered mechanical environment.