检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Wang, Jindong Chen, Yiqiang Hao, Shuji Feng, Wenjie Shenk, Zhiqi Beijing Key Laboratory of Mobile Computing and Pervasive Device CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Institute of High Performance Computing A*STAR School of Computer Science and Engineering Nanyang Technological University Singapore Singapore

Transfer learning has achieved promising results by leveraging knowledge from the source domain to annotate the target domain which has few or none labels. Existing methods often seek to minimize the distribution divergence between domains, such as the marginal distribution, the conditional distribution or both. However, these two distances are often treated equally in existing algorithms, which will result in poor performance in real applications. Moreover, existing methods usually assume that the dataset is balanced, which also limits their performances on imbalanced tasks that are quite common in real problems. To tackle the distribution adaptation problem, in this paper, we propose a novel transfer learning approach, named as Balanced Distribution Adaptation (BDA), which can adaptively leverage the importance of the marginal and conditional distribution discrepancies, and several existing methods can be treated as special cases of BDA. Based on BDA, we also propose a novel Weighted Balanced Distribution Adaptation (W-BDA) algorithm to tackle the class imbalance issue in transfer learning. W-BDA not only considers the distribution adaptation between domains but also adaptively changes the weight of each class. To evaluate the proposed methods, we conduct extensive experiments on several transfer learning tasks, which demonstrate the effectiveness of our proposed algorithms over several state-of-the-art methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

User Behavior Analysis of Location-Based Social Network

User Behavior Analysis of Location-Based Social Network

引用

IIAI International Conference on Advanced Applied Informatics (IIAIAAI)

作者： Jun Zeng Xin He Yingbo Wu Sachio Hirokawa Key Laboratory of Dependable Service Computing in Cyber Physical Society School of Big Data and Software Engineering Chongqing China School of Big Data and Software Engineering Chongqing China Research Institute for Information Technology Kyushu University Fukuoka Japan

ISBN: (纸本)9781538674482;9781538674475

User behavior changes over time under the influence of their activities. We contend that these activities are non-random behavior and have a desire to explore the underlying information behind these changes. In this paper, we analyze user behavior by using the check-in data in Location Based Social Networks (LBSNs), and examine whether they have the features of trend, periodicity and surprise or not. We explore some dynamics behaviors of people through their check-in times, and divide time into annually, monthly and even weekly analysis to find out the pattern of their behavior. Eventually, we found the check-in data do exhibit these three features by analyzing them deeply. The analytical work lays the foundation for the further recommendation research.

关键词： Market research Social networking (online) Big data Software engineering Accidents Trajectory Motion pictures

来源：评论

学校读者我要写书评

暂无评论

Self-Evolutionary Neuron Model for Fast-Response Spiking Neural Networks

TechRxiv

引用

TechRxiv 2019年

作者： Zhang, Anguo Han, Ying Hu, Jing Niu, Yuzhen Gao, Yueming Chen, Zhizhang Zhao, Kai College of Physics and Information Engineering Fuzhou University Fujian350108 China The Key Laboratory of Medical Instrumentation Pharmaceutical Technology of Fujian Province Fuzhou350116 China Research Institute of Ruijie Ruijie Networks Co. Ltd Fujian350002 China School of Public Health Xiamen University Xiamen361102 China College of Information and Intelligent Transportation Fujian Chuanzheng Communications College Fuzhou350007 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing College of Mathematics and Computer Science Fuzhou University The Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fujian350108 China College of Physics and information Engineering Fuzhou University the Key Laboratory of Medical Instrumentation Pharmaceutical Technology of Fujian Province Fujian350108 China College of Physics and Information Engineering Fuzhou University 350108 China Faculty of Science and Technology University of Macau 999078 China

We propose two simple and effective spiking neuron models to improve the response time of the conventional spiking neural network. The proposed neuron models adaptively tune the presynaptic input current depending on the input received from its presynapses and subsequent neuron firing events. We analyze and derive the firing activity homeostatic convergence of the proposed models. We experimentally verify and compare the models on MNIST handwritten digits and FashionMNIST classification tasks. We show that the proposed neuron models significantly increase the response speed to the input signal. Experiment codes are available at https://***/anvien/Evol-SNN. © 2019, CC0.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

PSGAN: A generative adversarial network for remote sensing image pan-sharpening

arXiv

引用

arXiv 2018年

作者： Liu, Xiangyu Wang, Yunhong Liu, Qingjie Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang University Beijing100191 China

Remote sensing image fusion (also known as pan-sharpening) aims to generate a high resolution multi-spectral image from inputs of a high spatial resolution single band panchromatic (PAN) image and a low spatial resolution multi-spectral (MS) image. In this paper, we propose PSGAN, a generative adversarial network (GAN) for remote sensing image pan-sharpening. To the best of our knowledge, this is the first attempt at producing high quality pan-sharpened images with GANs. The PSGAN consists of two parts. Firstly, a two-stream fusion architecture is designed to generate the desired high resolution multi-spectral images, then a fully convolutional network serving as a discriminator is applied to distinct "real" or "pan-sharpened" MS images. Experiments on images acquired by Quickbird and GaoFen-1 satellites demonstrate that the proposed PSGAN can fuse PAN and MS images effectively and significantly improve the results over the state of the art traditional and CNN based pan-sharpening methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Improved Cryptanalysis of an ISO Standard Lightweight Block Cipher with Refined MILP Modelling 13th

Improved Cryptanalysis of an ISO Standard Lightweight Block ...

引用

13th International Conference on Information Securityand Cryptology, Inscrypt 2017

作者： Yin, Jun Ma, Chuyan Lyu, Lijun Song, Jian Zeng, Guang Ma, Chuangui Wei, Fushan State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450001 China State Key Laboratory of Cryptology P.O. Box 5159 Beijing100878 China Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China Data Assurance and Communication Security Research Center Chinese Academy of Sciences Beijing100093 China School of Cyber Security University of Chinese Academy of Sciences Beijing100049 China National University of Defense Technology Changsha410073 China Army Aviation Institute Beijing101116 China

ISBN: (纸本)9783319751597

Differential and linear cryptanalysis are two of the most effective attacks on block ciphers. Searching for (near) optimal differential or linear trails is not only useful for the security evaluation of block ciphers against these attacks, but also indispensable to the cryptanalysts who want to attack a cipher with these techniques. In recent years, searching for trails automatically with Mixed-Integer Linear Programming (MILP) gets a lot of attention. At first, Mouha et al. translated the problem of counting the minimum number of differentially active S-boxes into an MILP problem for word-oriented block ciphers. Subsequently, in Asiacrypt 2014, Sun et al. extended Mouha et al.’s method, and presented a technique which can find actual differential or linear characteristics of a block cipher in both the single-key and related-key models. In this paper, we refine the constraints of the 2-XOR operation in order to reduce the overall number of variables and constraints. Experimental results show that MILP models with the refined constraints can be solved more efficiently. We apply our method to HIGHT (an ISO standard), and we find differential (covering 11 rounds) or linear trails (covering 10 rounds) with higher probability or correlation. Moreover, we find so far the longest differential and linear distinguishers of HIGHT. © Springer International Publishing AG, part of Springer Nature 2018.

关键词： ISO Standards

来源：评论

学校读者我要写书评

暂无评论

Radiomics based on dual-energy CT for noninvasive prediction of cervical lymph node metastases in patients with nasopharyngeal carcinoma

引用

Radiography (London, England : 1995) 2025年第4期31卷 102989页

作者： L Li D Yang Y Wu R Sun Y Qin M Kang X Deng M Bu Z Li Z Zeng X Zeng M Jiang B T Chen Department of Radiology First Affiliated Hospital of Guangxi Medical University Nanning 530021 Guangxi PR China. Department of Radiology Guizhou Provincial People Hospital No.83 East Zhongshan Road Nanming District Guizhou Province 550000 Guiyang PR China Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University No. 2870 Huaxi Avenue South Guiyang 550025 Guizhou PR China. Department of Radiology Guizhou Provincial People Hospital No.83 East Zhongshan Road Nanming District Guizhou Province 550000 Guiyang PR China. Department of Nuclear Medicine First Affiliated Hospital of Guangxi Medical University Nanning 530021 Guangxi PR China. Department of Radiation Oncology First Affiliated Hospital of Guangxi Medical University Nanning 530021 Guangxi PR China. Department of Radiology Guizhou Provincial People Hospital No.83 East Zhongshan Road Nanming District Guizhou Province 550000 Guiyang PR China. Electronic address: zengxianchun04@***. Department of Radiology First Affiliated Hospital of Guangxi Medical University Nanning 530021 Guangxi PR China. Electronic address: jmlgxmu@***. Department of Diagnostic Radiology City of Hope National Medical Center Duarte CA USA.

INTRODUCTION:To develop and validate a machine learning model based on dual-energy computed tomography (DECT) for predicting cervical lymph node metastases (CLNM) in patients diagnosed with nasopharyngeal carcinoma (NPC). METHODS:This prospective single-center study enrolled patients with NPC and the study assessment included both DECT and 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT). Radiomics features were extracted from each region of interest (ROI) for cervical lymph nodes using arterial and venous phase images at 100 keV and 150 keV, either individually as non-fusion models or combined as fusion models on the DECT images. The performance of the random forest (RF) models, combined with radiomics features, was evaluated by area under the receiver operating characteristic curve (AUC) analysis. DeLong's test was employed to compare model performances, while decision curve analysis (DCA) assessed the clinical utility of the predictive models. RESULTS:Sixty-six patients with NPC were included for analysis, which was divided into a training set (n = 42) and a validation set (n = 22). A total of 13 radiomic models were constructed (4 non-fusion models and 9 fusion models). In the non-fusion models, when the threshold value exceeded 0.4, the venous phase at 100 keV (V100) (AUC, 0.9667; 95 % confidence interval [95 % CI], 0.9363-0.9901) model exhibited a higher net benefit than other non-fusion models. The V100 + V150 fusion model achieved the best performance, with an AUC of 0.9697 (95 % CI, 0.9393-0.9907). CONCLUSION:DECT-based radiomics effectively diagnosed CLNM in patients with NPC and may potentially be a valuable tool for clinical decision-making. IMPLICATIONS FOR PRACTICE:This study improved pre-operative evaluation, treatment strategy selection, and prognostic evaluation for patients with nasopharyngeal carcinoma by combining DECT and radiomics to predict cervical lymph node status prior to treatment.

关键词： Cervical lymph node metastases (CLNM) Dual-energy computed tomography (DECT) Machine learning model Nasopharyngeal carcinoma (NPC) Radiomics

来源：评论

学校读者我要写书评

暂无评论

Predicting ICU mortality by supervised bidirectional LSTM networks 1

Predicting ICU mortality by supervised bidirectional LSTM ne...

引用

1st Joint Workshop on AI in Health, AIH 2018

作者： Zhu, Yao Fan, Xiaoliang Wu, Jinzhun Liu, Xiao Shi, Jia Wang, Cheng Fujian Key Laboratory of Sensing and Computing for Smart Cities Xiamen University Xiamen China First Affiliated Hospital Xiamen University Xiamen China School of Information Technology Deakin University Melbourne Australia Digital Fujian Institute of Healthcare and Biomedical Big Data Research Xiamen University Xiamen China School of Information Science and Engineering Lanzhou University Lanzhou China

Mortality prediction in the Intensive Care Unit (ICU) is considered as one of critical steps for the treatment of patients in serious condition. It is a big challenge to model time-series variables for mortality prediction in ICU, because physiological variables such as heart rate and blood pressure are sampled with inconsistent time frequencies. In addition, it is difficult to capture the timing changes of clinical data and to interpret the prediction result of ICU mortality. To deal with these challenges, in this paper, we propose a novel ICU mortality prediction algorithm combining bidirectional LSTM (Long Short-Term Memory) model with supervised learning. First, we preprocess 37 time-series variables related to patients’ signs. Second, we construct the Bidirectional LSTM model with supervision technique to accurately reflect significant changes in patients’ signs. Finally, we train and evaluate our model using a real-world dataset containing 4,000 ICU patients. Experimental results show that our proposed method can significantly outperform many baseline methods. © CEUR-WS. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Deep Multi-Metric Learning for Person Re-Identification

Deep Multi-Metric Learning for Person Re-Identification

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yongxin Ge Xinqian Gu Min Chen Hongxing Wang Dan Yang Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education (Chongqing University) Chongqing China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China School of Big Data & Software Engineering Chongqing University Chongqing China

In this paper, to exploit more discriminative information of the global-body and body-parts features, we present a novel deep multi-metric learning (DMML) network for person re-identification under the triplet framework. The main novelty of our learning framework lies in two aspects: 1) Unlike most existing metric learning-based approaches, which learn only one distance metric for comparison, our DMM-L method aims to learn different metrics for the global-body and body-parts features respectively by using convolutional neural network (CNN); 2) A new multi-metric loss function is proposed to train the DMML network, under which the distance of each negative pair is greater than that of each positive pair by a predefined margin, and the correlations of different metrics are maximized. Compared with the previous person re-identification methods that have shown state-of-the-art performances, our DMML approach can achieve competitive results on the challenging CUHK03, CUHKOl, VIPeR and iLIDS datasets.

关键词： Measurement Image color analysis Feature extraction Training Machine learning Kernel Learning systems

来源：评论

学校读者我要写书评

暂无评论

Deep learning on image denoising: An overview

arXiv

引用

arXiv 2019年

作者： Tian, Chunwei Fei, Lunke Zheng, Wenxian Xu, Yong Zuo, Wangmeng Lin, Chia-Wen Bio-Computing Research Center Harbin Institute of Technology Shenzhen Shenzhen Guangdong518055 China Shenzhen Key Laboratory of Visual Object Detection and Recognition Shenzhen Guangdong518055 China School of Computers Guangdong University of Technology Guangzhou Guangdong510006 China Tsinghua Shenzhen International Graduate School Shenzhen Guangdong518055 China Peng Cheng Laboratory Shenzhen Guangdong518055 China School of Computer Science and Technology Harbin Institute of Technology Harbin Heilongjiang150001 China Department of Electrical Engineering Institute of Communications Engineering National Tsing Hua University Hsinchu Taiwan

Deep learning techniques have obtained much attention in image denoising. However, deep learning methods of different types deal with the noise have enormous differences. Specifically, discriminative learning based on deep learning can well address the Gaussian noise. Optimization model methods based on deep learning have good effect on estimating of the real noise. So far, there are little related researches to summarize different deep learning techniques for image denoising. In this paper, we make such a comparative study of different deep techniques in image denoising. We first classify the (1) deep convolutional neural networks (CNNs) for additive white noisy images, (2) deep CNNs for real noisy images, (3) deep CNNs for blind denoising and (4) deep CNNs for hybrid noisy images, which is the combination of noisy, blurred and low-resolution images. Then, we analyze the motivations and principles of deep learning methods of different types. Next, we compare and verify the state-of-the-art methods on public denoising datasets in terms of quantitative and qualitative analysis. Finally, we point out some potential challenges and directions of future research. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Adaptive Structure-Constrained Robust Latent Low-Rank Coding for Image Recovery

Adaptive Structure-Constrained Robust Latent Low-Rank Coding...

引用

IEEE International Conference on data Mining (ICDM)

作者： Zhao Zhang Lei Wang Sheng Li Yang Wang Zheng Zhang Zhengjun Zha Meng Wang School of Computer Science and Technology Soochow University Suzhou China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) Hefei University of Technology School of Computer Science and Information Engineering Hefei University of Technology Hefei China Department of Computer Science University of Georgia Athens GA Bio-Computing Research Center Harbin Institute of Technology (Shenzhen) Shenzhen China School of Information Science and Technology University of Science and Technology of China Hefei China

In this paper, we propose a robust representation learning model called Adaptive Structure-constrained Low-Rank Coding (AS-LRC) for the latent representation of data. To recover the underlying subspaces more accurately, AS-LRC seamlessly integrates an adaptive weighting based block-diagonal structure-constrained low-rank representation and the group sparse salient feature extraction into a unified framework. Specifically, AS-LRC performs the latent decomposition of given data into a low-rank reconstruction by a block-diagonal codes matrix, a group sparse locality-adaptive salient feature part and a sparse error part. To enforce the block-diagonal structures adaptive to different real datasets for the low-rank recovery, AS-LRC clearly computes an auto-weighting matrix based on the locality-adaptive features and multiplies by the low-rank coefficients for direct minimization at the same time. This encourages the codes to be block-diagonal and can avoid the tricky issue of choosing optimal neighborhood size or kernel width for the weight assignment, suffered in most local geometrical structures-preserving low-rank coding methods. In addition, our AS-LRC selects the L2, 1-norm on the projection for extracting group sparse features rather than learning low-rank features by Nuclear-norm regularization, which can make learnt features robust to noise and outliers in samples, and can also make the feature coding process efficient. Extensive visualizations and numerical results demonstrate the effectiveness of our AS-LRC for image representation and recovery.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：