Journal of Intelligent Manufacturing - In droplet-on-demand liquid metal jetting (DoD-LMJ) additive manufacturing, complex physical interactions govern the droplet characteristics, such as size,... 相似文献
The Journal of Supercomputing - This study was to evaluate the performance of magnetic resonance imaging (MRI) reconstruction algorithm based on convolutional neural network (CNN) in the diagnosis... 相似文献
The advantages of a cloud computing service are cost advantages, availability, scalability, flexibility, reduced time to market, and dynamic access to computing resources. Enterprises can improve the successful adoption rate of cloud computing services if they understand the critical factors. To find critical factors, this study first reviewed the literature and established a three-layer hierarchical factor table for adopting a cloud computing service based on the Technology-Organization-Environment framework. Then, a hybrid method that combines two multi-criteria decision-making tools—called the Fuzzy Analytic Network Process method and the concept of VlseKriterijumska Optimizacija I Kompromisno Resenje acceptable advantage—was used to objectively identify critical factors for the adoption of a cloud computing service, replacing the subjective decision of the authors. The results of this study determined five critical factors, namely data access security, information transmission security, senior management support, fallback cloud management, and employee acceptance. Finally, the paper presents the findings and implications of the study. 相似文献
The heavy reliance on data is one of the major reasons that currently limit the development of deep learning. Data quality directly dominates the effect of deep learning models, and the long-tailed distribution is one of the factors affecting data quality. The long-tailed phenomenon is prevalent due to the prevalence of power law in nature. In this case, the performance of deep learning models is often dominated by the head classes while the learning of the tail classes is severely underdeveloped. In order to learn adequately for all classes, many researchers have studied and preliminarily addressed the long-tailed problem. In this survey, we focus on the problems caused by long-tailed data distribution, sort out the representative long-tailed visual recognition datasets and summarize some mainstream long-tailed studies. Specifically, we summarize these studies into ten categories from the perspective of representation learning, and outline the highlights and limitations of each category. Besides, we have studied four quantitative metrics for evaluating the imbalance, and suggest using the Gini coefficient to evaluate the long-tailedness of a dataset. Based on the Gini coefficient, we quantitatively study 20 widely-used and large-scale visual datasets proposed in the last decade, and find that the long-tailed phenomenon is widespread and has not been fully studied. Finally, we provide several future directions for the development of long-tailed learning to provide more ideas for readers.
High-level semantic features and low-level detail features matter for salient object detection in fully convolutional neural networks (FCNs). Further integration of low-level and high-level features increases the ability to map salient object features. In addition, different channels in the same feature are not of equal importance to saliency detection. In this paper, we propose a residual attention learning strategy and a multistage refinement mechanism to gradually refine the coarse prediction in a scale-by-scale manner. First, a global information complementary (GIC) module is designed by integrating low-level detailed features and high-level semantic features. Second, to extract multiscale features of the same layer, a multiscale parallel convolutional (MPC) module is employed. Afterwards, we present a residual attention mechanism module (RAM) to receive the feature maps of adjacent stages, which are from the hybrid feature cascaded aggregation (HFCA) module. The HFCA aims to enhance feature maps, which reduce the loss of spatial details and the impact of varying the shape, scale and position of the object. Finally, we adopt multiscale cross-entropy loss to guide network learning salient features. Experimental results on six benchmark datasets demonstrate that the proposed method significantly outperforms 15 state-of-the-art methods under various evaluation metrics.
Neural Computing and Applications - Medical concept normalization aims to construct a semantic mapping between mentions and concepts and to uniformly represent mentions that belong to the same... 相似文献
To find out the causes of vibration and noise of the trigeminal universal joint which appeared in the installation and use process, the additional moment distribution with the varies of the input shaft angular and the deflection angle was analyzed. Kinematics diagrams of the trigeminal universal joint when the output shaft installed by single radial bearing or twin radial bearing were established. The system coordinates were established under the two installation ways, and the motion equations were established by the direction cosine matrix tools. It indicated that the trigeminal universal joint installed by the single radial bearing was an approximately isometric speed transmission, and was a constant velocity transmission with twin radial bearing installed. Furthermore, the additional moment component on the input shaft and the output shaft was analyzed under the two installation ways. According to the virtual displacement principle, the additional moment on the tripod universal joint when the output shaft installed by twin radial bearing and single radial bearing were determined. When installed by single radial bearing, the deflection moment exists and the vibration frequency of additional moment was three times of the input shaft as a sine curve. The variation trend of the additional moment was straight up with the increase of deflection angle. When installed by twin radial bearing, the deflection moment was zero and the additional moment increased gradually with the increase of deflection angle but did not fluctuate. The analysis revealed that additional moment existed in the trigeminal universal joint system under both installation ways would produce bending vibration. This study is of great significance to study the causes of vibration and determine the nonlinear dynamics of the system. 相似文献