Institution
Xiamen University
Education•Amoy, Fujian, China•
About: Xiamen University is a education organization based out in Amoy, Fujian, China. It is known for research contribution in the topics: Catalysis & Population. The organization has 50472 authors who have published 54480 publications receiving 1058239 citations. The organization is also known as: Amoy University & Xiàmén Dàxué.
Topics: Catalysis, Population, Graphene, Raman spectroscopy, Anode
Papers published on a yearly basis
Papers
More filters
••
TL;DR: New knowledge is added to the literature on factors that affect blockchain adoption among Small-Medium Enterprises in Malaysia that covers the technological dimensions of relative advantage and complexity, organisational dimensions of upper management support and cost and environmental dimensions of market dynamics, competitive pressure and regulatory support.
314 citations
••
TL;DR: The potentials of different optical probes as PAT contrast agents were elucidated and the instrumental embodiments and the measured functional parameters, then focus on emerging contrast agent-based PAT applications, and finally discuss the challenges and prospects.
Abstract: Photoacoustic tomography (PAT) can offer structural, functional and molecular contrasts at scalable observation level. By ultrasonically overcoming the strong optical scattering, this imaging technology can reach centimeters penetration depth while retaining high spatial resolution in biological tissue. Recent extensive research has been focused on developing new contrast agents to improve the imaging sensitivity, specificity and efficiency. These emerging materials have substantially accelerated PAT applications in signal sensing, functional imaging, biomarker labeling and therapy monitoring etc. Here, the potentials of different optical probes as PAT contrast agents were elucidated. We first describe the instrumental embodiments and the measured functional parameters, then focus on emerging contrast agent-based PAT applications, and finally discuss the challenges and prospects.
313 citations
••
TL;DR: It is validated that the proposed CNN classifier using ECG spectrograms as input can achieve improved classification accuracy without additional manual pre-processing of the ECG signals.
Abstract: The classification of electrocardiogram (ECG) signals is very important for the automatic diagnosis of heart disease. Traditionally, it is divided into two steps, including the step of feature extraction and the step of pattern classification. Owing to recent advances in artificial intelligence, it has been demonstrated that deep neural network, which trained on a huge amount of data, can carry out the task of feature extraction directly from the data and recognize cardiac arrhythmias better than professional cardiologists. This paper proposes an ECG arrhythmia classification method using two-dimensional (2D) deep convolutional neural network (CNN). The time domain signals of ECG, belonging to five heart beat types including normal beat (NOR), left bundle branch block beat (LBB), right bundle branch block beat (RBB), premature ventricular contraction beat (PVC), and atrial premature contraction beat (APC), were first transformed into time-frequency spectrograms by short-time Fourier transform. Subsequently, the spectrograms of the five arrhythmia types were utilized as input to the 2D-CNN such that the ECG arrhythmia types were identified and classified finally. Using ECG recordings from the MIT-BIH arrhythmia database as the training and testing data, the classification results show that the proposed 2D-CNN model can reach an averaged accuracy of 99.00%. On the other hand, in order to achieve optimal classification performances, the model parameter optimization was investigated. It was found when the learning rate is 0.001 and the batch size parameter is 2500, the classifier achieved the highest accuracy and the lowest loss. We also compared the proposed 2D-CNN model with a conventional one-dimensional CNN model. Comparison results show that the 1D-CNN classifier can achieve an averaged accuracy of 90.93%. Therefore, it is validated that the proposed CNN classifier using ECG spectrograms as input can achieve improved classification accuracy without additional manual pre-processing of the ECG signals.
312 citations
••
TL;DR: It is found that C-dots are efficiently and rapidly excreted from the body after all three injection routes, an important step forward toward safety and efficacy analysis of nanoparticles.
Abstract: The emergence of photoluminescent carbon-based nanomaterials has shown exciting potential in the development of benign nanoprobes. However, the in vivo kinetic behaviors of these particles that are necessary for clinical translation are poorly understood to date. In this study, fluorescent carbon dots (C-dots) were synthesized and the effect of three injection routes on their fate in vivo was explored by using both near-infrared fluorescence and positron emission tomography imaging techniques. We found that C-dots are efficiently and rapidly excreted from the body after all three injection routes. The clearance rate of C-dots is ranked as intravenous > intramuscular > subcutaneous. The particles had relatively low retention in the reticuloendothelial system and showed high tumor-to-background contrast. Furthermore, different injection routes also resulted in different blood clearance patterns and tumor uptakes of C-dots. These results satisfy the need for clinical translation and should promote efforts to...
311 citations
••
01 Jun 2021TL;DR: Wu et al. as discussed by the authors proposed a contrastive regularization (CR) based on contrastive learning to exploit both the information of hazy images and clear images as negative and positive samples, respectively.
Abstract: Single image dehazing is a challenging ill-posed problem due to the severe information degeneration. However, existing deep learning based dehazing methods only adopt clear images as positive samples to guide the training of dehazing network while negative information is unexploited. Moreover, most of them focus on strengthening the dehazing network with an increase of depth and width, leading to a significant requirement of computation and memory. In this paper, we propose a novel contrastive regularization (CR) built upon contrastive learning to exploit both the information of hazy images and clear images as negative and positive samples, respectively. CR ensures that the restored image is pulled to closer to the clear image and pushed to far away from the hazy image in the representation space.Furthermore, considering trade-off between performance and memory storage, we develop a compact dehazing network based on autoencoder-like (AE) framework. It involves an adaptive mixup operation and a dynamic feature enhancement module, which can benefit from preserving information flow adaptively and expanding the receptive field to improve the network’s transformation capability, respectively. We term our dehazing network with autoencoder and contrastive regularization as AECR-Net. The extensive experiments on synthetic and real-world datasets demonstrate that our AECR-Net surpass the state-of-the-art approaches. The code is released in https://github.com/GlassyWu/AECR-Net.
311 citations
Authors
Showing all 50945 results
Name | H-index | Papers | Citations |
---|---|---|---|
Zhong Lin Wang | 245 | 2529 | 259003 |
Lei Jiang | 170 | 2244 | 135205 |
Yang Gao | 168 | 2047 | 146301 |
William A. Goddard | 151 | 1653 | 123322 |
Rui Zhang | 151 | 2625 | 107917 |
Xiaoyuan Chen | 149 | 994 | 89870 |
Fuqiang Wang | 145 | 1518 | 95014 |
Galen D. Stucky | 144 | 958 | 101796 |
Shu-Hong Yu | 144 | 799 | 70853 |
Wei Huang | 139 | 2417 | 93522 |
Bin Liu | 138 | 2181 | 87085 |
Jie Liu | 131 | 1531 | 68891 |
Han Zhang | 130 | 970 | 58863 |
Lei Zhang | 130 | 2312 | 86950 |
Jian Zhou | 128 | 3007 | 91402 |