检索结果-内蒙古大学图书馆

XCloud-VIP: Virtual Peak Enables Highly Accelerated NMR Spectroscopy and Faithful Quantitative Measures

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Guo, Di Tu, Zhangren Guo, Yi Zhou, Yirong Wang, Jian Wang, Zi Qiu, Tianyu Xiao, Min Chen, Yinran Feng, Liubin Huang, Yuqing Lin, Donghai Hong, Qing Goldbourt, Amir Lin, Meijin Qu, Xiaobo The School of Computer and Information Engineering Fujian Engineering Research Center for Medical Data Mining and Application Xiamen University of Technology Xiamen361024 China Department of Electronic Science Biomedical Intelligent Cloud R&D Center Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance Xiamen University Xiamen361102 China School of Opto-Electronic and Communication Engineering Xiamen University of Technology Xiamen361024 China Department of Computer Science School of Information Xiamen University Xiamen361102 China College of Chemistry and Chemical Engineering Key Laboratory for Chemical Biology of Fujian Province High-field NMR Center Xiamen University Xiamen361005 China China Mobile Group Xiamen361005 China School of Chemistry Tel Aviv University Tel Aviv6997801 Israel Department of Applied Marine Physics and Engineering College of Ocean and Earth Sciences Xiamen University Xiamen361102 China

—Nuclear Magnetic Resonance (NMR) spectroscopy is an important bio-engineering tool to determine the metabolic concentrations, molecule structures and so on. The data acquisition time, however, is very long in multi-dimensional NMR. To accelerate data acquisition, non-uniformly sampling is an effective way but may encounter severe spectral distortions and unfaithful quantitative measures when the acceleration factor is high. By modelling the acquired signal as the superimposed exponentials, we proposed a virtual peak (VIP) approach to self-adapt the prior spectral information, such as the resonance frequency and peak lineshape, and then feed these information into the reconstruction. The proposed method is further implemented with cloud computing to facilitate online, open, and easy access. Results on simulated and experimental data demonstrate that, compared with the low-rank Hankel matrix method, the new approach reconstructs high-fidelity NMR spectra from highly undersampled data and achieves more accurate quantification. The maximum quantitative errors of distances between nuclear pairs and concentrations of metabolites in mixtures have been reduced by 61.1% and 57.7%, respectively. Copyright © 2021, The Authors. All rights reserved.

关键词： Nuclear magnetic resonance spectroscopy

Micro-supervised disturbance learning: A perspective of representation probability distribution

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Chu, Jielei Liu, Jing Wang, Hongjun Meng, Hua Gong, Zhiguo Li, Tianrui The School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China The School of Business Sichuan University Sichuan Chengdu610065 China The State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science University of Macau China

The instability is shown in the existing methods of representation learning based on Euclidean distance under a broad set of conditions. Furthermore, the scarcity and high cost of labels prompt us to explore more expressive representation learning methods which depends on the labels as few as possible. To address these issues, the small-perturbation ideology is firstly introduced on the representation learning model based on the representation probability distribution. The positive small-perturbation information (SPI) which only depend on two labels of each cluster is used to stimulate the representation probability distribution and then two variant models are proposed to fine-tune the expected representation distribution of RBM, namely, Micro-supervised Disturbance GRBM (Micro-DGRBM) and Micro-supervised Disturbance RBM (Micro-DRBM) models. The Kullback-Leibler (KL) divergence of SPI is minimized in the same cluster to promote the representation probability distributions to become more similar in Contrastive Divergence (CD) learning. In contrast, the KL divergence of SPI is maximized in the different clusters to enforce the representation probability distributions to become more dissimilar in CD learning. To explore the representation learning capability under the continuous stimulation of the SPI, we present a deep Micro-supervised Disturbance Learning (Micro-DL) framework based on the Micro-DGRBM and Micro-DRBM models and compare it with a similar deep structure which has not any external stimulation. Experimental results demonstrate that the proposed deep Micro-DL architecture shows better performance in comparison to the baseline method, the most related shallow models and deep frameworks for clustering. © 2020, CC0.

关键词： Probability distributions

How Powerful are Shallow Neural Networks with Bandlimited Random Weights?

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Ming Sonoda, Sho Cao, Feilong Wang, Yu Guang Liang, Jiye Key Laboratory of Intelligent Education Technology Application of Zhejiang Province Zhejiang Normal University Jinhua China Deep Learning Theory Team RIKEN AIP Tokyo Japan College of Sciences China Jiliang University Hangzhou China Institute of Natural Sciences Shanghai Jiao Tong University Shanghai China School of Mathematical Sciences Shanghai Jiao Tong University Shanghai China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education School of Computer and Information Technology Shanxi University Taiyuan China

We investigate the expressive power of depth-2 bandlimited random neural networks. A random net is a neural network where the hidden layer parameters are frozen with random assignment, and only the output layer parameters are trained by loss minimization. Using random weights for a hidden layer is an effective method to avoid non-convex optimization in standard gradient descent learning. It has also been adopted in recent deep learning theories. Despite the well-known fact that a neural network is a universal approximator, in this study, we mathematically show that when hidden parameters are distributed in a bounded domain, the network may not achieve zero approximation error. In particular, we derive a new nontrivial approximation error lower bound. The proof utilizes the technique of ridgelet analysis, a harmonic analysis method designed for neural networks. This method is inspired by fundamental principles in classical signal processing, specifically the idea that signals with limited bandwidth may not always be able to perfectly reconstruct the original signal. We corroborate our theoretical results with various simulation studies, and generally, two main take-home messages are offered: (i) Not any distribution for selecting random weights is feasible to build a universal approximator;(ii) A suitable assignment of random weights exists but to some degree is associated with the complexity of the target function. © 2020, CC BY.

关键词： Convex optimization

A Research on the Control System of High-Speed Homopolar Motor with Solid Rotor Based on Flywheel Energy Storage

学校读者我要写书评

暂无评论

Complexity 2020年 2020卷

作者： Jing, Lili Yu, Yandong Xue, Xiaochuan Key Laboratory of High Speed Signal Processing and Internet of Things Technology Application Jining Normal University Ulanqab Inner Mongolia 012000 China Department of Computer Science Jining Normal University Ulanqab Inner Mongolia 012000 China Systems Engineering Research Institute of China State Shipbuilding Corporation Beijing 100191 China

In view of the defects of the motors used for flywheel energy storage such as great iron loss in rotation, poor rotor strength, and robustness, a new type of motor called electrically excited homopolar motor is adopted in this paper for flywheel energy storage. Compared to general motors, this motor has the advantages of simple structure, high rotor strength, and low iron loss in rotation. A double closed-loop PI governing system of the new motor was designed, modeled, and simulated with this motor as the controlled object on simulation platform. The simulation result shows that the PI-controlled electrically excited homopolar motor system realized fast speed governing and good system performance, achieved the purpose of quick charge by flywheel energy storage, verified the correctness and effectiveness of the design scheme, and provided data reference and theoretical basis for the practice of future flywheel energy storage experiments. © 2020 Lili Jing et al.

关键词： Digital storage

QuesNet: A unified representation for heterogeneous test questions

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yin, Yu Liu, Qi Huang, Zhenya Chen, Enhong Tong, Wei Wang, Shijin Su, Yu Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology School of Data Science University of Science and Technology of China IFLYTEK Research IFLYTEK CO. LTD. State Key Laboratory of Cognitive Intelligence

Understanding learning materials (e.g. test questions) is a crucial issue in online learning systems, which can promote many applications in education domain. Unfortunately, many supervised approaches suffer from the problem of scarce human labeled data, whereas abundant unlabeled resources are highly underutilized. To alleviate this problem, an effective solution is to use pre-trained representations for question understanding. However, existing pretraining methods in NLP area are infeasible to learn test question representations due to several domain-specific characteristics in education. First, questions usually comprise of heterogeneous data including content text, images and side information. Second, there exists both basic linguistic information as well as domain logic and knowledge. To this end, in this paper, we propose a novel pre-training method, namely QuesNet, for comprehensively learning question representations. Specifically, we first design a unified framework to aggregate question information with its heterogeneous inputs into a comprehensive vector. Then we propose a two-level hierarchical pre-training algorithm to learn better understanding of test questions in an unsupervised way. Here, a novel holed language model objective is developed to extract low-level linguistic features, and a domain-oriented objective is proposed to learn high-level logic and knowledge. Moreover,we showthat Ques- Net has good capability of being fine-tuned in many question-based tasks. We conduct extensive experiments on large-scale real-world question data, where the experimental results clearly demonstrate the effectiveness of QuesNet for question understanding as well as its superior applicability. Copyright © 2019, The Authors. All rights reserved.

关键词： Learning systems

Optical polarization imaging for underwater target detection with non-scatter background

学校读者我要写书评

暂无评论

Journal of Measurement Science and Instrumentation 2020年第4期11卷 335-342页

作者： GUAN Jin-ge ZHAO Yong ZHENG Yong-qiu MA Miao SUN Peng XUE Chen-yang School of Information and Communication Engineering North University of ChinaTaiyuan 030051China Beijing Institute of Computer Application Technology China North Industries Group Corporation LimitedBeijing 100089China Key Laboratory of Instrumentation Science and Dynamic Measurement(North University of China) Ministry of EducationTaiyuan 030051China Department of Science Taiyuan Institute of TechnologyTaiyuan 030008China

For conventional optical polarization imaging of underwater target,the polarization degree of backscatter should be pre-measured by averaging the pixel intensities in the no target region of the polarization images,and the polarization property of the target is assumed to be completely *** the scattering background is unseen in the field of view or the target is polarized,conventional method is helpless in detecting the *** improvement is to use lots of co-polarization and cross polarization detection *** propose a polarization subtraction method to estimate depolarization property of the scattering noise and target *** experiment in a quartz cuvette container is performed to demonstrate the effectiveness of the proposed *** results show that the proposed method can work without scattering background reference,and further recover the target along with smooth surface for polarization preserving *** study promotes the development of optical polarization imaging systems in underwater environments.

关键词： polarization imaging underwater optical scattering optical information processing target detection

Nonlinear Cross-Domain Feature Representation Learning Method Based on Dual Constraints

学校读者我要写书评

暂无评论

Nonlinear Cross-Domain Feature Representation Learning Metho...

IEEE International Conference on Big Knowledge (ICBK)

作者： Han Ding Yuhong Zhang Shuai Yang Yaojin Lin Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Data Science and Intelligence Application Fujian Province University Zhangzhou China

Feature representation learning is a research focus in domain adaptation. Recently, due to the fast training speed, the marginalized Denoising Autoencoder (mDA) as a standing deep learning model has been widely utilized for feature representation learning. However, the training of mDA suffers from the lack of nonlinear relationship and does not explicitly consider the distribution discrepancy between domains. To address these problems, this paper proposes a novel method for feature representation learning, namely Nonlinear cross-domain Feature learning based Dual Constraints (NFDC), which consists of kernelization and dual constraints. Firstly, we introduce kernelization to effectively extract nonlinear relationship in feature representation learning. Secondly, we design dual constraints including Maximum Mean Discrepancy (MMD) and Manifold Regularization (MR) in order to minimize distribution discrepancy during the training process. Experimental results show that our approach is superior to several state-of-the-art methods in domain adaptation tasks.

关键词： Noise reduction Manifolds Training Adaptation models Kernel Deep learning Feature extraction

FrepJoin:an efficient partition-based algorithm for edit similarity join

学校读者我要写书评

暂无评论

Frontiers of Information technology & Electronic Engineering 2017年第10期18卷 1499-1510页

作者： Ji-zhou LUO Sheng-fei SHI Hong-zhi WANG Jian-zhong LI School of Computer Science and Technology Harbin Institute of Technology Guangdong Key Laboratory of Popular High Performance Computers Key Laboratory of Service Computing and Application

String similarity join(SSJ) is essential for many applications where near-duplicate objects need to be found. This paper targets SSJ with edit distance constraints. The existing algorithms usually adopt the filter-andrefine framework. They cannot catch the dissimilarity between string subsets, and do not fully exploit the statistics such as the frequencies of characters. We investigate to develop a partition-based algorithm by using such *** frequency vectors are used to partition datasets into data chunks with dissimilarity between them being caught easily. A novel algorithm is designed to accelerate SSJ via the partitioned data. A new filter is proposed to leverage the statistics to avoid computing edit distances for a noticeable proportion of candidate pairs which survive the existing filters. Our algorithm outperforms alternative methods notably on real datasets.

关键词： String similarity join Edit distance Filter and refine Data partition Combined frequency vectors

Research and Prospect of Digital Economy Development in Shandong Province

学校读者我要写书评

暂无评论

Research and Prospect of Digital Economy Development in Shan...

2019 5th International Conference on Humanities and Social Science Research (ICHSSR 2019)

作者： Zhengqian Feng Hao Wang Liping Wei Shandong Information Resources Application Association Qilu University of Technology(Shandong Academy of Sciences) Shandong Computer Science Center(National Supercomputer Center in Jinan) Shandong Provincial Key Laboratory of Computer Networks Shandong University of Science and Technology

Digital economy refers to the economic model that takes digital technology as the core to drive the whole economic activity process and create *** the future, all economic links may be driven by digital technology, digital technology will be the main driving force for world economic development, and digital economy will be the new engine for world economic *** great transformation of digital economy is a new opportunity for economic *** development level of digital economy in Shandong province has entered the first echelon in China, but there are still some factors restricting its *** digital economy has become the core force leading the scientific and technological revolution and industrial transformation, and human society is entering a new stage marked by digital *** province must correctly grasp the general trend of the development of digital economy, do a good job in planning and creating momentum and taking advantage of it, accelerate the construction of a strong digital province, make the digital economy become an important starting point to promote the conversion of old and new drives and an important supporting force of "lead the way".

关键词： Digital Economy Development Status Evaluation Index