Search

With the widespread application of mobile edge computing (MEC), MEC is serving as a bridge to narrow the gaps between medical staff and patients. Relatedly, MEC is also moving toward supervising individual health in an automatic and intelligent manner. One of the main MEC technologies in healthcare monitoring systems is human activity recognition (HAR). Built-in multifunctional sensors make smartphones a ubiquitous platform for acquiring and analyzing data, thus making it possible for smartphones to perform HAR. The task of recognizing human activity using a smartphone's built-in accelerometer has been well resolved, but in practice, with the multimodal and high-dimensional sensor data, these traditional methods fail to identify complicated and real-time human activities. This paper designs a smartphone inertial accelerometer-based architecture for HAR. When the participants perform typical daily activities, the smartphone collects the sensory data sequence, extracts the high-efficiency features from the original data, and then obtains the user's physical behavior data through multiple three-axis accelerometers. The data are preprocessed by denoising, normalization and segmentation to extract valuable feature vectors. In addition, a real-time human activity classification method based on a convolutional neural network (CNN) is proposed, which uses a CNN for local feature extraction. Finally, CNN, LSTM, BLSTM, MLP and SVM models are utilized on the UCI and Pamap2 datasets. We explore how to train deep learning methods and demonstrate how the proposed method outperforms the others on two large public datasets: UCI and Pamap2. [ABSTRACT FROM AUTHOR]

In order to increase the automatic quality control level in the textile industry, depending on the big data collected by the Internet of things of the textile factories, this paper proposes a novel visual saliency–based defect detection algorithm, which has the capability of automatically detecting defect in both nonpatterned and patterned fabrics. The algorithm employs the histogram features extracted from the saliency maps to detect the fabric defects. The algorithm involves three main steps: (1) saliency map generation to highlight the defective regions and suppress the defect‐free regions, (2) saliency histogram features extraction and selection to obtain the feature vectors that can effectively discriminate between the defective and defect‐free fabric images, and (3) fabric defect detection using a two‐class support vector machine classifier that has been trained using sets of feature vectors extracted from defective and defect‐free fabric samples. Experimental results show that our method yields accurate detections, outperforming other state‐of‐the‐art algorithms. [ABSTRACT FROM AUTHOR]

Deep learning has brought a significant progress in medical image analysis. However, their lack of interpretability might bring high risk for wrong diagnosis with limited clinical knowledge embedding. In other words, we believe it's crucial for humans to interpret how deep learning work for medical analysis, thus appropriately adding knowledge constraints to correct the bias of wrong results. With such purpose, we propose Representation Group-Disentangling Network (RGD-Net) to explain the process of feature extraction and decision making inside deep learning framework, where we completely disentangle feature space of input X-ray images into independent feature groups, and each group would contribute to diagnose of a specific disease. Specifically, we first state problem definition for interpretable prediction with auto-encoder structure. Then, group-disentangled representations are extracted from input X-ray images with the proposed Group-Disentangle Module, which constructs semantic latent space by enforcing semantic consistency of attributes. Afterwards, adversarial constricts on mapping from features to diseases are proposed to prevent model collapse during training. Finally, a novel design of local tuning medical application is proposed based on RGB-Net, which is capable to aid clinicians for reasonable diagnosis. By conducting quantity of experiments on public datasets, RGD-Net have been superior to comparative studies by leveraging potential factors contributing to different diseases. We believe our work could bring interpretability in digging inherent patterns of deep learning on medical image analysis. • RGD-Net extracts fine-grained, group-disentangled disease representations for better interpretation and prediction. • Adversarial constraint avoids shortcut problems and promotes global minimum convergence in RGD-Net. • RGD-Net significantly improves classification accuracy and disentangles information in experiments. [ABSTRACT FROM AUTHOR]

• CDText detect texts of arbitrary shapes by encoding context information. • Feature extractor refines feature map with dilated context encoding blocks. • Transformer aggregates text features of detection boxes for instance segmentation. Scene text detection task aims to precisely locate text regions in natural scenes. However, the existing methods still face challenges in detecting arbitrary-shaped text, due to their limited feature representation capability. To alleviate this problem, we propose a scene text detector, i.e., CDText, based on structure of context-aware deformable transformer. Specifically, CDText firstly adopts different convolution kernel designs for feature extraction, which designs receptive fields with different size for multi-scale feature perception and fusion. Meanwhile, multi-head self-attention mechanism is used to strengthen the reasoning ability of CDText in a global sense, thus enhancing feature maps with abundant context information by extracting implicit relationship between multi-scale text features. Moreover, CDText designs a segmentation head to segment text instances of arbitrary shapes from rectangular detection boxes. Experiments show that CDText is superior to comparative methods in detection accuracy, achieving F -scores of 92.7, 81.9, and 82.9 on ICDAR2013, Total Text, and CTW-1500 datasets, respectively. [ABSTRACT FROM AUTHOR]

Point cloud representation is a challenge to extracting sufficient semantic information while ensuring that the sparsely point cloud spatial structure is complete. Benefiting from the Transformer network, recent studies have promoted the development of point cloud representation by extracting refined attention features based on global context. However, there is still undesired semantic information loss in the feature extraction stage. Hence, this paper proposes a novel architecture for 3D point cloud representation, namely Relation-Shape Transformer Network (RS-TNet), to address above problem while maintaining the merits of relation-shape embedding mechanism so as to generate rich and robust local semantic features. Specifically, RS-TNet can achieve coarse-to-fine grained semantic information coverage by integrating the global multi-head self-attention and local Relation-Feature extraction module simultaneously. Moreover, theoretical analysis demonstrates that RS-TNet can explicitly introduce the spatial relation of points by learning underlying shapes. In this way, extracted features are of more shape awareness and robustness. As a result, the proposed RS-TNet achieves 90.9% class accuracy and 85.6% Intersection-over-Union on ModelNet40 and ShapeNet datasets, respectively. Further, ablation experiments verify the effectiveness of our RS-TNet in point cloud classification and part segmentation tasks. [ABSTRACT FROM AUTHOR]

• Propose a Group-Disentangled Representation Learning framework (GDRL). • Introduce an implicit group-swap structure. • Extract linking relationship between semantical concepts of pathology and visual features. • Demonstrate that GDRL can significantly improve classification accuracy. Deep learning methods have shown significant performance in medical image analysis tasks. However, they generally act like "black box" without explanations in both feature extraction and decision processes, leading to lack of clinical insights and high risk assessments. To aid deep learning in envisioning diseases with visual clues, we propose a novel Group-Disentangled Representation Learning framework (GDRL). The key contribution is that GDRL completely disentangles latent space into disease concepts with abundant and non-overlapping feature related explanations, thus enhancing interpretability in feature extraction and decision processes. Furthermore, we introduce an implicit group-swap structure by emphasizing the linking relationship between semantical concepts of disease and low-level visual features, other than explicit explanations on general objects and their attributes. We demonstrate our framework on predicting four categories of diseases from chest X-ray images. The AUROC of GDRL on ChestX-ray14 for thoracic pathologic prediction are 0.8630, 0.8980, 0.9269 and 0.8653 respectively, and we showcase the potential of our framework in enhancing interpretability of the factors contributing to different diseases. [ABSTRACT FROM AUTHOR]