检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Zhang, Lingling Chang, Xiaojun Liu, Jun Luo, Minnan Wang, Sen Ge, Zongyuan Hauptmann, Alexander School of Computer Science and Technology Xian Jiaotong University Xian China Ministry of Education Key Lab For Intelligent Networks and Network Security Xian China Faculty of Information Technology Monash University Australia National Engineering Lab for Big Data Analytics Xian Jiaotong University Xian China School of Information Technology and Electrical Engineering University of Queensland Australia School of Computer Science Carnegie Mellon University United States

An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos. Currently, the most effective methods of temporal activity detection are based on deep learning, and they typically perform very well with large scale annotated videos for training. However, these methods are limited in real applications due to the unavailable videos about certain activity classes and the time-consuming data annotation. To solve this challenging problem, we propose a novel task setting called zero-shot temporal activity detection (ZSTAD), where activities that have never been seen in training can still be detected. We design an end-to-end deep network based on R-C3D as the architecture for this solution. The proposed network is optimized with an innovative loss function that considers the embeddings of activity labels and their super-classes while learning the common semantics of seen and unseen activities. Experiments on both the THUMOS14 and the Charades datasets show promising performance in terms of detecting unseen activities. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Minimizing Overheads of Checkpoints in Distributed Stream Processing Systems 7

Minimizing Overheads of Checkpoints in Distributed Stream Pr...

引用

7th IEEE International Conference on Cloud Networking, CloudNet 2018

作者： Muhammad Abrar Akber, Syed Chen, Hanhua Wang, Yonghui Jin, Hai School of Computer Science and Technology Huazhong University of Science and Technology Cluster and Grid Computing Lab Services Computing Technology and System Lab Big Data Technology and System Lab Wuhan430074 China

ISBN: (纸本)9781538668313

Failure occurrence in large-scale systems is inevitable, which makes the resilience a key challenge for modern systems. Checkpoints with rollback recovery is a well-known approach to provide fault tolerance in distributed systems. The checkpoint based fault tolerance approach periodically persists the application state to reliable storage, which serves as a recovery point in case of failure. These periodic checkpoints are not inline with the failure rate of the systems as many studies conclude that failure occurrence is not periodic. The optimal size of checkpoint interval is a crucial decision, which directly determines the checkpoint overheads. To minimize the checkpoint overheads, we propose to reduce the number of checkpoints during the application execution. We suggest reducing the number of checkpoints by successively increasing the checkpoint intervals. We consider the failure probability of the underlying infrastructure and iteratively increase the checkpoint intervals. The proposed checkpoint approach tailors the checkpoint initializing based on the failure probability. If failure probability is low, it increases the checkpoint interval, and eventually reduces the total number of checkpoints triggered during application timespan. Reducing the total number of checkpoints during application execution results in decreasing the checkpoint overheads. The experiment results show that the proposed checkpoint policy considerably reduces the checkpoint overheads as compared to periodic checkpoints. © 2018 IEEE.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

FLoc: Fingerprint-Based Indoor Localization System under a Federated Learning Updating Framework

FLoc: Fingerprint-Based Indoor Localization System under a F...

引用

International Conference on Mobile Ad-hoc and Sensor Networks, MSN

作者： Yuxiang Liu Huichuwu Li Jiang Xiao Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781728152127

ISBN: (纸本)9781728152134

Fingerprinting-based indoor localization via WiFi has achieved a great breakthrough in the past decade. However, it suffers from an inherent problem that the localization accuracy declines sharply over time due to the dynamic environment and unstable WiFi devices. Researchers have designed many methods to update the localization model, e.g., crowdsourcing-based model updating, in order to maintain the localization accuracy. Unfortunately, they have not taken the privacy into consideration during the updating process. This will lead to a threat that the eavesdroppers could guess the location providers' private information according to the updating model. For the goal of maintaining the localization accuracy without the risk of privacy breaching, we proposed FLoc, a fingerprinting-based indoor localization system which updates the localization model via a federated learning framework. In FLoc, every provider maintains a local localization model in their own device. They will regularly encrypt the updating parameters and share them to a common model server. At the model server, it aggregates the encrypted information of the local models to maintain a general model, which will be sent back to the local devices for next updating iteration. We evaluate FLoc in an APs unknown laboratory corridor. The experiment results show that FLoc has a comparable localization performance. Moreover, it can successfully protect the providers' privacy, since the information transferred is all encrypted.

关键词： Mobile handsets Privacy Fingerprint recognition Servers Wireless fidelity databases Computational modeling

来源：评论

学校读者我要写书评

暂无评论

HiNUMA: NUMA-Aware data Placement and Migration in Hybrid Memory Systems

HiNUMA: NUMA-Aware Data Placement and Migration in Hybrid Me...

引用

IEEE International Conference on Computer Design: VLSI in Computers and Processors, (ICCD)

作者： Zhuohui Duan Haikun Liu Xiaofei Liao Hai Jin Wenbin Jiang Yu Zhang National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Non-uniform memory access (NUMA) architectures feature asymmetrical memory access latencies on different CPU nodes. Hybrid memory systems composed of non-volatile memory (NVM) and DRAM further diversify memory access latencies due to the relatively large performance gap between NVM and DRAM. Traditional NUMA memory management policies fail to manage hybrid memories effectively and may even hurt application performance. In this paper, we present HiNUMA, a new NUMA abstraction for memory allocation and migration in hybrid memory systems. HiNUMA advocates NUMA topologyaware hybrid memory allocation policies for the initial data placement. HiNUMA also proposes a new NUMA balancing mechanism called HANB for memory migration at runtime. HANB considers both data access frequency and memory bandwidth utilization to reduce the cost of memory accesses in hybrid memory systems. We evaluate the performance of HiNUMA with several typical workloads. Experimental results show that HiNUMA can effectively utilize hybrid memories, and deliver much higher application performance than conventional NUMA memory management policies and other state-of-the-art work.

关键词： Nonvolatile memory Random access memory Bandwidth Memory management Resource management Task analysis Memory architecture

来源：评论

学校读者我要写书评

暂无评论

Analysis of bivariate time series of magnetoencephalography for depression Based on Granger Kernel Method 3

Analysis of bivariate time series of magnetoencephalography ...

引用

3rd International Conference on Biological Information and Biomedical Engineering, BIBE 2019

作者： Hu, Jialin Yan, Wei Wang, Jun Li, Jin Hou, Fengzhen Smart Health Big Data Analysis and Location Services Engineering Lab of Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing China Department of Psychiatry Affiliated Brain Hospital of Nanjing Medical University Nanjing China College of Physics and Information Technology Shaanxi Normal University Xi'an China School of Science China Pharmaceutical University Nanjing China

ISBN: (纸本)9783800750269

Granger causality is widely used to analyze dynamic systems, among which the linear granger causality method is a very popular method to analyze the causality between bivariate time series. In this paper, an improved granger causality method, kernel granger causality method, is adopted to analyze the causality of the time series of symmetrical channels in the left and right frontal areas of magnetoencephalography (MEG) in normal people and depressed patients by specifically using the inhomogeneous polynomial(IP) kernel method and Gaussian kernel. The results showed that both methods showed that the causality index from the right frontal area to the left frontal area is greater than in the opposite direction in both healthy subjects and depressed patients. Different from Gaussian kernel method, the results of Inhomogeneous polynomial kernel also showed that the causality index of depressed patients was more susceptible to stimulation. Specifically, the causality index of both directions for depressed patients was higher than that of normal people under negative and neutral stimulation. By comparing the two different kernel methods, we found that the inhomogeneous polynomial kernel is a more appropriate method to distinguish depressed patients from normal people than the Gaussian kernel in our study. © VDE VERLAG GMBH · Berlin · Offenbach.

关键词： Magnetoencephalography

来源：评论

学校读者我要写书评

暂无评论

Prediction of pregnancy diabetes based on machine learning 3

Prediction of pregnancy diabetes based on machine learning

引用

3rd International Conference on Biological Information and Biomedical Engineering, BIBE 2019

作者： Du, Fan Zhong, Weiyang Wu, Wei Peng, Danhong Xu, Tian Wang, Jun Wang, Gongdao Hou, Fengzhen Smart Health Big Data Analysis and Location Services Engineering Lab of Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing China Department of Psychiatry Affiliated Brain Hospital of Nanjing Medical University Nanjing China Department of Obstetrics and Gynecology Zhongda Hospital Southeast University Nanjing China School of Science China Pharmaceutical University Nanjing China

ISBN: (纸本)9783800750269

Gestational diabetes (GDM) refers to the normal metabolism of glucose before pregnancy and the occurrence of diabetes during pregnancy. This disease is a serious threat to the health of this pregnant woman and infant, so it is important to accurately predict whether the target is a gestational diabetes patient based on various indicators. Based on the measured data of the hospital, this paper uses decision tree, logistic regression and DenseNet to predict the target when the disease is sick or to be sick in the future, and discuss their prediction accuracy separately, which can help doctors make rapid diagnosis and make timely prevention. In the end, it was found that the DenseNet model can better predict whether the target is gestational diabetes or not, and the model flexibility is better. © VDE VERLAG GMBH · Berlin · Offenbach.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Reasoning Based Workload Performance Prediction in Cloud data Centers

Reasoning Based Workload Performance Prediction in Cloud Dat...

引用

IEEE International Conference on Cloud Computing Technology and science

作者： Adeel Aslam Hanhua Chen Jiang Xiao Hai Jin National Engineering Research Center for Big Data Technology and System Cluster and Grid Computing Lab Services Computing Technology and System Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Cloud computing provides utility-based and scalable services to end-users. In the past decade, the demands for resource management in cloud computing have increased substantially which lead to certain challenges such as optimal resource utilization, power consumption, and service level agreement violations. Workload performance prediction serves as an assistance to address these issues. In this paper, we propose a prediction model based on clustered Case-Based Reasoning (CBR). The proposed model determines the performance metrics for workload prior to the co-operation of autonomic computing characteristics. Thus, CBR provides optimal scheduling of resources and workload monitoring for cloud data centers. In order to validate the proposed CBR-based prediction model, we perform a series of experiments and evaluate the effectiveness in terms of precision, recall, f-measure, and mean square error rate. We generate the cases for CBR using traces from the Google cluster data center. Moreover, we also validate our proposed prediction model against Support Vector Machine (SVM) prediction scheme. Experimental results show that the proposed CBR outperforms the SVM-based approach and yields 10% improvement in terms of precision.

关键词：

来源：评论

学校读者我要写书评

暂无评论

WORD: A large scale dataset, benchmark and clinical applicable study for abdominal organ segmentation from CT image

arXiv

引用

arXiv 2021年

作者： Luo, Xiangde Liao, Wenjun Xiao, Jianghong Chen, Jieneng Song, Tao Zhang, Xiaofan Li, Kang Metaxas, Dimitris N. Wang, Guotai Zhang, Shaoting School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu China Department of Radiation Oncology Sichuan Cancer Hospital and Institute Sichuan Cancer Center Chengdu China Department of Radiation Oncology Cancer Center West China Hospital Sichuan University Chengdu China Shanghai Artificial Intelligence Laboratory Shanghai China School of Medicine University of Electronic Science and Technology of China Chengdu China Department of Computer Science Johns Hopkins University Baltimore United States SenseTime Research Shanghai China West China Hospital-SenseTime Joint Lab West China Biomedical Big Data Center Sichuan University Chengdu China Department of Computer Science Rutgers University PiscatawayNJ United States

Whole abdominal organ segmentation is important in diagnosing abdomen lesions, radiotherapy, and follow-up. However, oncologists’ delineating all abdominal organs from 3D volumes is time-consuming and very expensive. Deep learning-based medical image segmentation has shown the potential to reduce manual delineation efforts, but it still requires a large-scale fine annotated dataset for training, and there is a lack of large-scale datasets covering the whole abdomen region with accurate and detailed annotations for the whole abdominal organ segmentation. In this work, we establish a new large-scale Whole abdominal ORgan dataset (WORD) for algorithm research and clinical application development. This dataset contains 150 abdominal CT volumes (30495 slices). Each volume has 16 organs with fine pixel-level annotations and scribble-based sparse annotations, which may be the largest dataset with whole abdominal organ annotation. Several state-of-the-art segmentation methods are evaluated on this dataset. And we also invited three experienced oncologists to revise the model predictions to measure the gap between the deep learning method and oncologists. Afterwards, we investigate the inference-efficient learning on the WORD, as the high-resolution image requires large GPU memory and a long inference time in the test stage. We further evaluate the scribble-based annotation-efficient learning on this dataset, as the pixel-wise manual annotation is time-consuming and expensive. The work provided a new benchmark for the abdominal multi-organ segmentation task, and these experiments can serve as the baseline for future research and clinical application development. © 2021, CC BY.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Translation and psychometric evaluation of the Chinese version of The Prediction-Related Experiences Questionnaire (PRE-Q-C)

引用

Asian journal of psychiatry 2025年 109卷 104556页

作者： Shuang Ma Xinyi He Xuehua Xu He He Wendian Shi Xudong Zhao School of Psychology Shanghai Normal University Shanghai 200234 China School of Economics and Management Shanghai Polytechnic University Shanghai 201209 China. School of Psychology Shanghai Normal University Shanghai 200234 China. International Institute of Creative Design Shanghai University of Engineering Science Shanghai 201620 China. School of Psychology Shanghai Normal University Shanghai 200234 China. Electronic address: swd_nx@***. Lab for Educational Big Data and Policymaking Ministry of Education Shanghai Normal University Shanghai 200234 China. Electronic address: psyzhao@***.

OBJECTIVE:Prediction is a fundamental cognitive process that facilitates adaptive interactions with the environment. The Prediction-Related Experiences Questionnaire (PRE-Q), a 19-item measure, assesses individuals' everyday predictive abilities. This study aimed to develop and validate a Chinese version (PRE-Q-C) by translating and adapting the original scale and examining its psychometric properties in a large Chinese sample. METHODS:The PRE-Q was translated and back-translated according to standard guidelines, followed by expert review and a comprehensibility test. A total of 2595 participants completed the PRE-Q-C and other related measures. Exploratory graph analysis (EGA) was used to identify the factor structure, confirmed via confirmatory factor analysis (CFA). Item response theory (IRT), internal consistency, test-retest reliability, and convergent validity were also evaluated. RESULTS:EGA suggested a 2-factor structure, comprising Sensory-Social prediction (7 items) and Motor prediction (6 items), which was subsequently supported by CFA. IRT analyses demonstrated that the PRE-Q-C items exhibited appropriate discrimination parameters. The scale showed high internal consistency (Cronbach's α = 0.85) and good test-retest reliability (r = 0.51, p < .001). Additionally, significant correlations with related psychological constructs supported the scale's convergent validity. CONCLUSION:The PRE-Q-C demonstrated strong psychometric properties, supporting its use as a reliable and valid instrument for assessing predictive processing in Chinese-speaking populations. These findings contribute to the understanding of individual differences in predictive abilities and their implications for mental health research.

关键词： Autism spectrum disorder Autistic traits Confirmatory factor analysis Exploratory graph analysis Prediction

来源：评论

学校读者我要写书评

暂无评论

Study on the correlation of microstate sequences of MEG 3

Study on the correlation of microstate sequences of MEG

引用

3rd International Conference on Biological Information and Biomedical Engineering, BIBE 2019

作者： Zhang, Yafei Yan, Wei Wang, Jun Li, Jin Hou, Fengzhen Smart Health Big Data Analysis and Location Services Engineering Lab of Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing China Department of Psychiatry Affiliated Brain Hospital of Nanjing Medical University Nanjing China College of Physics and Information Technology Shaanxi Normal University Xi'an China School of Science China Pharmaceutical University Nanjing China

ISBN: (纸本)9783800750269

Magnetoencephalography(MEG) as a non-inva-sive brain function detection technology has been widely used in the study of depression. We analyze the Hurst exponent to study the correlation of the microstate sequences of MEG between patients with depression and healthy people. We implement four microstate segmentation algorithms, namely modified K-Means, principal component analysis (PCA), fast independent component analysis (Fast-ICA) and Kmedoids, to cluster MEG into microstate sequences, and then calculate Hurst exponent through R/S and DFA method. The experi-mental results show that the correlation of MEG between healthy people and depressed patients has a significant difference, and we also find that the correlation of MEG of depressed patients in the left and right frontal regions of the brain is different distinctly from that of healthy people, which may provide a judgment basis for diagnosis and assessment of the risk of depression. © VDE VERLAG GMBH · Berlin · Offenbach.

关键词： Magnetoencephalography

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：