Search

Background: In the field of mobile health, portable dynamic electrocardiogram (ECG) monitoring devices often have a limited number of lead electrodes due to considerations, such as portability and battery life. This situation leads to a contradiction between the demand for standard 12‑lead ECG information and the limited number of leads collected by portable devices., Methods: This study introduces a composite ECG vector reconstruction network architecture based on convolutional neural network (CNN) combined with recurrent neural network by using leads I, II, and V2. This network is designed to reconstruct three‑lead ECG signals into 12‑lead ECG signals. A 1D CNN abstracts and extracts features from the spatial domain of the ECG signals, and a bidirectional long short-term memory network analyzes the temporal trends in the signals. Then, the ECG signals are inputted into the model in a multilead, single-channel manner., Results: Under inter-patient conditions, the mean reconstructed Root mean squared error (RMSE) for precordial leads V1, V3, V4, V5, and V6 were 28.7, 17.3, 24.2, 36.5, and 25.5 μV, respectively. The mean overall RMSE and reconstructed Correlation coefficient (CC) were 26.44 μV and 0.9562, respectively., Conclusion: This paper presents a solution and innovative approach for recovering 12‑lead ECG information when only three‑lead information is available. After supplementing with comprehensive leads, we can analyze the cardiac health status more comprehensively across 12 dimensions., (Copyright © 2024 Elsevier Inc. All rights reserved.)

As one of the important components of Earth observation technology, land use and land cover (LULC) image classification plays an essential role. It uses remote sensing techniques to classify specific categories of ground cover as a means of analyzing and understanding the natural attributes of the Earth's surface and the state of land use. It provides important information for applications in environmental protection, urban planning, and land resource management. However, remote sensing images are usually high-dimensional data and have limited available labeled samples, so performing the LULC classification task faces great challenges. In recent years, due to the emergence of deep learning technology, remote sensing data processing methods based on deep learning have achieved remarkable results, bringing new possibilities for the research and development of LULC classification. In this paper, we present a systematic review of deep-learning-based LULC classification, mainly covering the following five aspects: (1) introduction of the main components of five typical deep learning networks, how they work, and their unique benefits; (2) summary of two baseline datasets for LULC classification (pixel-level, patch-level) and performance metrics for evaluating different models (OA, AA, F1, and MIOU); (3) review of deep learning strategies in LULC classification studies, including convolutional neural networks (CNNs), autoencoders (AEs), generative adversarial networks (GANs), and recurrent neural networks (RNNs); (4) challenges faced by LULC classification and processing schemes under limited training samples; (5) outlooks on the future development of deep-learning-based LULC classification. [ABSTRACT FROM AUTHOR]

Lung cancer is mainly caused by malignant lung nodules. Early detection and diagnosis of lung nodules can diagnose the disease in time and significantly improve the survival rate of the patients. With the rapid development of deep learning networks in the field of medical aid diagnosis, many deep networks have been applied to lung nodule detection. Statistical distribution shows that most of the lung nodule radii are too small to be well detected. Therefore, 3D feature pyramid network (FPN) for single‐stage pulmonary nodule detection is proposed to solve this problem by combining the 3D characteristics of computed tomography (CT) image data. In addition, the squeeze‐and‐excitation (SE)‐attention module is added to improve detection performance. The validity of the network is verified on the public pulmonary nodule dataset LUNA16. The competition performance metric (CPM) value reaches 0.8934. Compared with other pulmonary nodule detection networks, the detection performance of this network improved by 2%. [ABSTRACT FROM AUTHOR]

Single-image super-resolution (SISR) is an important task in image processing, aiming to achieve enhanced image resolution. With the development of deep learning, SISR based on convolutional neural networks has also gained great progress, but as the network deepens and the task of SISR becomes more complex, SISR networks become difficult to train, which hinders SISR from achieving greater success. Therefore, to further promote SISR, many challenges have emerged in recent years. In this review, we briefly review the SISR challenges organized from 2017 to 2022 and focus on the in-depth classification of these challenges, the datasets employed, the evaluation methods used, and the powerful network architectures proposed or accepted by the winners. First, depending on the tasks of the challenges, the SISR challenges can be broadly classified into four categories: classic SISR, efficient SISR, perceptual extreme SISR, and real-world SISR. Second, we introduce the datasets commonly used in the challenges in recent years and describe their characteristics. Third, we present the image evaluation methods commonly used in SISR challenges in recent years. Fourth, we introduce the network architectures used by the winners, mainly to explore in depth where the advantages of their network architectures lie and to compare the results of previous years' winners. Finally, we summarize the methods that have been widely used in SISR in recent years and suggest several possible promising directions for future SISR. [ABSTRACT FROM AUTHOR]

As a critical preprocessing technique, low-illumination image enhancement has a wide range of practical applications. It aims to improve the visual perception of a given image captured without sufficient illumination. Conventional low-illumination image enhancement methods are typically implemented by improving image brightness, enhancing image contrast, and suppressing image noise simultaneously. Nevertheless, recent advances in this area are dominated by deep-learning-based solutions, and consequently, various deep neural networks have been proposed and applied to this field. Therefore, this paper briefly reviews the latest low-illumination image enhancement, ranging from its related algorithms to its unsolved open issues. Specifically, current low-illumination image enhancement methods based on deep learning are first sorted out and divided into four categories: supervised learning methods, unsupervised learning methods, semi-supervised learning methods, and zero-shot learning methods. Then, existing low-light image datasets are summarized and analyzed. In addition, various quality assessment indices for low-light image enhancement are introduced in detail. We also compare 14 representative algorithms in terms of both objective evaluation and subjective evaluation. Finally, the future development trend of low-illumination image enhancement and its open issues are summarized and prospected. [ABSTRACT FROM AUTHOR]

With the development of deep learning, considerable progress has been made in image restoration. Notably, many state-of-the-art single image super-resolution (SR) methods have been proposed. However, most of them contain many parameters, which leads to a significant amount of calculation consumption in the inference phase. To make current SR networks more lightweight and resource-friendly, we present a convolution neural network with the proposed selective channel processing strategy (SCPN). Specifically, the selective channel processing module (SCPM) is first designed to dynamically learn the significance of each channel in the feature map using a channel selection matrix in the training phase. Correspondingly, in the inference phase, only the essential channels indicated by the channel selection matrixes need to be further processed. By doing so, we can significantly reduce the parameters and the calculation consumption. Moreover, the differential channel attention (DCA) block is proposed, which takes into consideration the data distribution of the channels in feature maps to restore more high-frequency information. Extensive experiments are performed on the natural image super-resolution benchmarks (i.e., Set5, Set14, B100, Urban100, Manga109) and remote-sensing benchmarks (i.e., UCTest and RESISCTest), and our method achieves superior results to other state-of-the-art methods. Furthermore, our method keeps a slim size with fewer than 1 M parameters, which proves the superiority of our method. Owing to the proposed SCPM and DCA, our SCPN model achieves a better trade-off between calculation cost and performance in both general and remote-sensing SR applications, and our proposed method can be extended to other computer vision tasks for further research. [ABSTRACT FROM AUTHOR]

Due to the influence of the environment and the limit of optical equipment, low-light images produce problems such as low brightness, high noise, low contrast, and color distortion, which have a great impact on their visual perception and the following image understanding tasks. In this paper, we take advantage of the independent nature of YCbCr color channels and incorporate RetinexNet into the brightness channel (Y) to reduce color distortion in the enhanced images. Meanwhile, to suppress the image noise generated during the enhancement, the enhanced image is also denoised. Finally, the original color and the enhanced brightness are recombined in the channel direction, converted back to the RGB color space, and adjusted to generate an enhanced result. The proposed algorithm is compared with other recently published counterparts on the LOL dataset. The experimental results demonstrate that the proposed algorithm achieved better performance in terms of both quantitative metrics and visual quality. [ABSTRACT FROM AUTHOR]

Deep learning techniques and deep networks have recently been extensively studied and widely applied to single image super‐resolution (SR). Among them, channel attention has garnered the most focus owing to its significant boost in the presentational power of a convolutional neural network. However, the original channel attention neglects the critical importance of the positional information, thus imposing performance limitations. Here, a novel perspective, namely, a coordinate attention mechanism, is explored to alleviate the aforementioned problem, and accordingly result in an enhanced SR performance. Specifically, a deep residual coordinate attention SR network (COSR) is proposed, which mainly incorporates the presented coordinate attention blocks into a deep nested residual structure. The coordinate attention captures the positional information by computing the average value vector from the two spatial directions, thus aggregating the features in different coordinates. The nested residual blocks pass low‐frequency information from the top to the end through the skip connection lines, allowing convolution filters to concentrate more on high‐frequency textures and edges, thereby reducing the difficulty of reconstruction. Extensive experiments demonstrate that our proposed COSR achieves a better performance and exceeds many state‐of‐the‐art SR methods in terms of both quantitative metrics and visual quality. [ABSTRACT FROM AUTHOR]

Driver action recognition aims to distinguish normal driver action and some abnormal driver actions such as leaving the wheel, talking on the phone, diving with smoking, etc. For the purpose of traffic safety, studies on the computer vision technologies for driver action recognition have become especially meaningful. However, this issue is far from being solved, mainly due to the subtle variations between different driver action classes. In this paper, we present a new video-based driver action recognition approach based on the hybrid spatial–temporal deep learning framework. Specifically, we first design an encoder–decoder spatial–temporal convolutional neural network (EDSTCNN) to capture short-term spatial–temporal representation of driver actions jointly with optical flow prediction. Second, we exploit the feature refinement network (FRN) to refine the short-term driver action feature. Then, convolutional long short-term memory network (ConvLSTM) is employed for long-term spatial–temporal fusion. Finally, the fully connected neural network (FCNN) is used for final driver action recognition. In our experiment, we validate the performance of the proposed framework on our self-created datasets, including a simulated driving dataset and a real driving dataset. Extensive experimental results illustrate that the proposed hybrid spatial–temporal deep learning framework obtains the highest accuracy in multiple driver action recognition datasets (98.9% on SEU-DAR-V1 dataset and 97.0% on SEU-DAR-V2 dataset). [ABSTRACT FROM AUTHOR]

Driver drowsiness has currently been a severe issue threatening road safety, hence it is vital to develop an effective drowsiness recognition algorithm to avoid traffic accidents. However, recognizing drowsiness is still very challenging, due to the large intra-class variations in facial expression, head pose and illumination condition. In this paper, a new deep learning framework based on the hybrid of 3D conditional generative adversarial network and two-level attention bidirectional long short-term memory network (3DcGAN-TLABiLSTM) has been proposed for robust driver drowsiness recognition. Aiming at extracting short-term spatial-temporal features with abundant drowsiness-related information, we design a 3D encoder-decoder generator with the condition of auxiliary information to generate high-quality fake image sequences and devise a 3D discriminator to learn drowsiness-related representation from spatial-temporal domain. In addition, for long-term spatial-temporal fusion, we investigate the use of two-level attention mechanism to guide the bidirectional long short-term memory learn the saliency of short-term memory information and long-term temporal information. For experiment, we evaluate our 3DcGAN-TLABiLSTM framework on a public NTHU-DDD dataset. Experimental results show that the proposed approach achieves higher precision of drowsiness recognition compared to the state-of-the-art. [ABSTRACT FROM AUTHOR]

With the advance of deep learning, the performance of single image super-resolution (SR) has been notably improved by convolution neural network (CNN)-based methods. However, the increasing depth of CNNs makes them more difficult to train, which hinders the SR networks from achieving greater success. To overcome this, a wide range of related mechanisms has been introduced into the SR networks recently, with the aim of helping them converge more quickly and perform better. This has resulted in many research papers that incorporated a variety of attention mechanisms into the above SR baseline from different perspectives. Thus, this survey focuses on this topic and provides a review of these recently published works by grouping them into three major categories: channel attention, spatial attention, and non-local attention. For each of the groups in the taxonomy, the basic concepts are first explained, and then we delve deep into the detailed insights and contributions. Finally, we conclude this review by highlighting the bottlenecks of the current SR attention mechanisms, and propose a new perspective that can be viewed as a potential way to make a breakthrough. [ABSTRACT FROM AUTHOR]

Illumination normalization is one of the most challenging issues for facial analysis. To be specific, the variation of environmental illumination influences the visual quality of an image and drastically degrades the performance of face recognition, detection, landmark and other related applications. Retinex theory provides an important concept for processing illumination variation, which supposes that a face image can be decomposed into [an invariant reflectance component and a variant illumination component. Enlighten by this theory, in this paper, we put forward a novel deep learning approach which combines self-supervised learning and adversarial training for face illumination normalization (FIN-GAN). The proposed FIN-GAN framework can be implemented by two steps. Firstly, self-supervised learning is employed to decompose the original face image into the illumination component and the illumination-invariant component with Retinex constraint. Then, we employ the conditional generative adversarial network for face image reconstruction. For network optimization, we design the combined loss to ensure visual quality and preserve identity information. Experiments are performed on Extended-YaleB, CAS-PEAL, CMU-PIE and Multi-PIE datasets. Through multiple quantitative criteria, we demonstrate that the proposed FIN-GAN obtains promising performance in face illumination normalization. [ABSTRACT FROM AUTHOR]

In the desert region of northwest China, the frequency of wind-sand disasters is high. All types of concrete buildings built in this area face severe wind erosion due to high wind speed, resulting in varying degrees of wind-erosion damage to concrete. To accomplish intelligent identification of concrete wind-erosion damage, a concrete wind erosion experiment was conducted in the laboratory, and a concrete wind-erosion damage dataset was generated under the interference of water stains, scratches, shooting distance, and background noise. This paper combined with transformer theory to improve YOLO-v4 and proposed an object detection algorithm called MHSA-YOLOv4 suitable for wind-erosion damage of concrete. The results demonstrate that MHSA-YOLOv4 exhibits improved object detection performance than YOLO-v3, improved YOLO-v3, and YOLO-v4. On the test set, ACC, Precision, Recall, and mAP of MHSA-YOLOv4 are 91.30%, 91.52%, 92.31%, and 0.89, respectively. MHSA-YOLOv4 can accurately identify wind-erosion damage of concrete images under different test conditions, which reflects strong robustness. The applicability of computer vision technology to the intelligent identification of wind-erosion damage on concrete has been verified. • The dataset of wind-erosion of concrete was established to simulate the spalling of concrete. • A object detection algorithm called MHSA-YOLOv4 was proposed based on Transformer. • MHSA-YOLOv4 can detect concrete wind-erosion damage with high-precision. [ABSTRACT FROM AUTHOR]