Search

It is critical to use scientific methods to track the performance degradation of in-service buildings over time and avoid accidents. In recent years, both supervised and unsupervised learning methods have yielded positive results in structural health monitoring (SHM). Supervised learning approaches require data from the entire structure and various damage scenarios for training. However, it is impractical to obtain adequate training data from various damage situations in service facilities. In addition, most known unsupervised approaches for training only take response data from the entire structure. In these situations, contaminated data containing both undamaged and damaged samples, typical in real-world applications, prevent the models from fitting undamaged data, resulting in performance loss. This work provides an unsupervised technique for detecting structural damage for the reasons stated above. This approach trains on contaminated data, with the anomaly score of the data serving as the model's output. First, we devised a score-guided regularization approach for damage detection to expand the score difference between undamaged and damaged data. Then, multi-task learning is incorporated to make parameter adjustment easier. The experimental phase II of the SHM benchmark data and data from the Qatar University grandstand simulator are used to validate this strategy. The suggested algorithm has the most excellent mean AUC of 0.708 and 0.998 on the two datasets compared to the classical algorithm. [ABSTRACT FROM AUTHOR]

Research on the rectangle packing problems has mainly focused on rectangular raw material sheets without defects, while natural slate has irregular and defective characteristics, and the existing packing method adopts manual packing, which wastes material and is inefficient. In this work, we propose an effective packing optimization method for nature slate; to the best of our knowledge, this is the first attempt to solve the guillotine packing problem of rectangular items in a single irregular and defective slate. This method is modeled by the permutation model, uses the horizontal level (HL) heuristic proposed in this paper to obtain feasible solutions, and then applies the genetic algorithm to optimize the quality of solutions further. The HL heuristic is constructed on the basis of computational geometry and level packing. This heuristic aims to divide the irregular plate into multiple subplates horizontally, calculates the movable positions of the rectangle in the subplates, determines whether or not the rectangle can be packed in the movable positions through computational geometry, and fills the scraps appropriately. Theoretical analysis confirms that the rectangles obtained through the HL heuristic are inside the plate and do not overlap with the defects. In addition, the packed rectangles do not overlap each other and satisfy the guillotine constraint. Accordingly, the packing problem can be solved. Experiments on irregular slates with defects show that the slate utilization through our method is between 89% and 95%. This result is better than manual packing and can satisfy actual production requirements. [ABSTRACT FROM AUTHOR]

The deep-learning steganography of current hotspots can conceal an image secret message in a cover image of the same size. While the steganography secret message is primarily removed via active steganalysis. The document image as the secret message in deep-learning steganography can deliver a considerable amount of effective information in a secret communication process. This study builds and implements deep-learning steganography removal models of document image secret messages based on the idea of adversarial perturbation removal: feed-forward denoising convolutional neural networks (DnCNN) and high-level representation guided denoiser (HGD). Further—considering the large computation cost and storage overheads of the above model—we use the document image-quality assessment (DIQA) as threshold, calculate the importance of filters using geometric median and prune redundant filters as extensively as possible through the overall iterative pruning and artificial bee colony (ABC) automatic pruning algorithms to reduce the size of the network structure of the existing vast and over-parameterized deep-learning steganography removal model, while maintaining the good removal effects of the model in the pruning process. Experiment results showed that the model generated by this method has better adaptability and scalability. Compared with the original deep-learning steganography removal model without pruning in this paper, the classic indicators params and flops are reduced by more than 75%. [ABSTRACT FROM AUTHOR]