检索结果-内蒙古大学图书馆

BENCHIP： Benchmarking Intelligence Processors

Journal of Computer Science & Technology 2018年第1期33卷 1-23页

作者： Jin-Hua Tao Zi-Dong Du Qi Guo Hui-Ying Lan Lei Zhang Sheng-Yuan Zhou Ling-Jie Xu Cong Liu Hai-Feng Liu Shah Tang Allen Rush Willian Chen Shao-Li Liu Yun-Ji Chen Tian-Shi Chen State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing 100049 China Intelligent Processor Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Cambricon Ltd. Beijing 100190 China A libaba Infrastructure Service A libaba Group Hangzhou 311121 China Iflytek Co. Ltd. Hefei 230088 China Beijing Jingdong Century Trading Co. Ltd. Beijing 100176 China RDA Microdectronics Inc. Shanghai 201203 China Advanced Micro Devices Inc. Sunnyvale CA 94085 U.S.A.

The increasing attention on deep learning has tremendously spurred the design of intelligence processing hardware. The variety of emerging intelligence processors requires standard benchmarks for fair comparison and system optimization （in both software and hardware）. However, existing benchmarks are unsuitable for benchmarking intelligence processors due to their non-diversity and nonrepresentativeness. Also, the lack of a standard benchmarking methodology further exacerbates this problem. In this paper, we propose BENCHIP, a benchmark suite and benchmarking methodology for intelligence processors. The benchmark suite in BENCHIP consists of two sets of benchmarks： microbenchmarks and macrobenchmarks. The microbenchmarks consist of single-layer networks, They are mainly designed for bottleneck analysis and system optimization. The macrobenchmarks contain state-of-the-art industrial networks, so as to offer a realistic comparison of different platforms. We also propose a standard benchmarking methodology built upon an industrial software stack and evaluation metrics that comprehensively reflect various characteristics of the evaluated intelligence processors, BENCHIP is utilized for evaluating various hardware platforms, including CPUs, GPUs, and accelerators. BENCHIP will be open-sourced soon.

关键词： deep learning intelligence processor benchmark

来源：评论

学校读者我要写书评

暂无评论

An Image Encryption Algorithm Based on Chaos System and DNA Strand Displacement Model

An Image Encryption Algorithm Based on Chaos System and DNA ...

引用

2017 2nd International Conference on Artificial Intelligence: Techniques and Applications (AITA 2017)

作者： Ze-jun ZHANG Bo-xiang XIAO Xue-dong ZHENG Chang-jun ZHOU Key Laboratory of Advanced Design and Intelligent Computing(Dalian University) Ministry of Education

In this paper,we proposed a novel algorithm for image *** the scheme,three chaotic sequences are generated by Lorenz chaos *** chaotic sequences are used to permutation and diffusion the digital ***,the algorithm introduce the DNA strand displacement reaction model to extract the secret key and then encrypt the image with a combination of XOR *** simulation results and security analysis show that our algorithm can successfully encrypts and decrypts the input image and gets a better encryption ***,the method also has a good ability of resisting attacks.

关键词： Image encryption Chaos system DNA strand displacement XOR operation

来源：评论

学校读者我要写书评

暂无评论

Protein-coding genes combined with long noncoding RNA as a novel transcriptome molecular staging model to predict the survival of patients with esophageal squamous cell carcinoma

引用

Cancer Communications 2018年第1期38卷 50-62页

作者： Jin-Cheng Guo Yang Wu Yang Chen Feng Pan Zhi-Yong Wu Jia-Sheng Zhang Jian-Yi Wu Xiu-E Xu Jian-Mei Zhao En-Min Li Yi Zhao Li-Yan Xu Key Laboratory of Molecular Biology in High Cancer Incidence Coastal Chaoshan Area of Guangdong Higher Education Institutes Shantou University Medical CollegeShantouGuangdong 515041P.R.China Department of Biochemistry and Molecular Biology Shantou University Medical CollegeShantouGuangdong 515041P.R.China Departments of Oncology Surgery Shantou Central HospitalAffiliated Shantou Hospital of Sun Yat-Sen UniversityShantouGuangdong 515041P.R.China Institute of Oncologic Pathology Shantou University Medical CollegeShantouGuangdong 515041P.R.China Key Laboratory of Intelligent Information Processing Advanced Computer Research CenterState Key Laboratory of Computer ArchitectureInstitute of Computing TechnologyChinese Academy of SciencesBeijing 100190P.R.China

Background:Esophageal squamous cell carcinoma(ESCC)is the predominant subtype of esophageal carcinoma in *** study was to develop a staging model to predict outcomes of patients with ***:Using Cox regression analysis,principal component analysis(PCA),partitioning clustering,Kaplan-Meier analysis,receiver operating characteristic(ROC)curve analysis,and classification and regression tree(CART)analysis,we mined the Gene Expression Omnibus database to determine the expression profiles of genes in 179 patients with ESCC from GSE63624 and GSE63622 ***:Univariate cox regression analysis of the GSE63624 dataset revealed that 2404 protein-coding genes(PCGs)and 635 long non-coding RNAs(lncRNAs)were associated with the survival of patients with *** categorized these PCGs and lncRNAs into three principal components(PCs),which were used to cluster the patients into three *** analysis demonstrated that the predictive ability of PCG-lncRNA PCs when applied to new patients was better than that of the tumor-node-metastasis staging(area under ROC curve[AUC]:0.69 vs.0.65,P<0.05).Accord-ingly,we constructed a molecular disaggregated model comprising one lncRNA and two PCGs,which we desig-nated as the LSB staging model using CART analysis in the GSE63624 *** LSB staging model classified the GSE63622 dataset of patients into three different groups,and its effectiveness was validated by analysis of another cohort of 105 ***:The LSB staging model has clinical significance for the prognosis prediction of patients with ESCC and may serve as a three-gene staging microarray.

关键词： Long non-coding RNA Protein-coding gene Esophageal squamous cell carcinoma Overall survival Staging model Transcriptome

来源：评论

学校读者我要写书评

暂无评论

Exploring risk factors and predicting UPDRS score based on Parkinson's speech signals 19

Exploring risk factors and predicting UPDRS score based on P...

引用

19th IEEE International Conference on e-Health Networking, Applications and Services, Healthcom 2017

作者： Zhang, Jianxin Xu, Weifeng Zhang, Qiang Jin, Bo Wei, Xiaopeng Key Lab of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian China Dalian University of Technology School of Computer Science Dalian China

ISBN: (纸本)9781509067046

The unified Parkinson's disease rating scale (UPDRS) is the most widely employed scale for tracking Parkinson's disease (PD) symptom progression. However, conventional way to achieve UPDRS, mainly based on the physical examinations of clinic patients performed by the trained medical staffs, involves the disadvantages of inconvenience and high medical expense. Hence, in this study, we try to explore some risk factors and accurately predict the UPDRS for PD, using the speech signals of PD patients published on UCI machine-learning archive. More specifically, inspired by the idea of ensemble learning, we firstly construct a framework of ensemble feature selection (EFS) to select a suitable subset of features among numerous speech signals. Subsequently, a personalized predictive model, trained by adopting information from similar patients, is developed to be customized for an individual PD patient. Finally, we employ the personalized predictive model to predict UPDRS score combined with various classical regression algorithms. Compared to conventional models, our study has a potential to capture more relevant risk factors and produces more accurate UPDRS score for individual patient. Experimental results on real-world dataset from UCI machine-learning archive show that our personalized predictive model gets a promising performance. © 2017 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

The Temperature Control of Blackbody Radiation Source Based on ADRC

The Temperature Control of Blackbody Radiation Source Based ...

引用

IEEE International Conference on Mechatronics and Automation

作者： Zhigang Wang Zerong Yun Lingling Wang Jinghui Wang Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin China Natinal Institute of Metrology China Beijing China

Blackbody radiation source is used as a standard device for infrared thermometer, it plays increasingly important roles in the field of calibration. Through experiment discoveries that it is a typical nonlinear system and has a large transport delay when the blackbody is rise temperature or cooling in order to reach set temperature points. Based on the temperature control of blackbody is a kind of typical multi-variable, strong coupling and time-varying nonlinear control system. The paper proposes applying the theory of active disturbance rejection controller (ADRC) to suppress various disturbances and improve the dynamic performance of blackbody radiation source. First of all, describing the working principle of blackbody radiation source and building its mathematical model. Secondly, introducing the control method of ADRC, which is applied to the temperature control system of blackbody radiation source. Finally, through MATLAB/SIMULINK platform to simulate and compare the temperature control performances of blackbody among ADRC, PID and Smith predictor(SP) control strategies. The simulation results show that proposed ADRC algorithm improves the abilities of anti-interference of system and it is without overshoot. In addition, the results also indicated that the control method of ADRC shortens plant stable time and has a strong prospect for practical applications.

关键词： Mathematical model Simulation Temperature measurement Cooling Heating systems Temperature sensors

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Detection Using Regional Proposal Network with Feature Fusion

Pedestrian Detection Using Regional Proposal Network with Fe...

引用

Workshops on Image Processing Theory, Tools and Applications, IPTA

作者： Xiaogang Lv Xiaotao Zhang Yinghua Jiang Jianxin Zhang Key Lab of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian P. R. China Information and Engineering College Dalian University Dalian P. R. China

ISBN: (纸本)9781538664292;9781538664285

Pedestrian detection, which has broad application prospects in video security, robotics and self-driving vehicles etc., is one of the most important research fields in computer vision. Recently, deep learning methods, e.g., Region Proposal Network (RPN), have achieved major performance improvements in pedestrian detection. In order to further utilize the deep pedestrian features of RPN, this paper proposes a novel regional proposal network model based on feature fusion (RPN_FeaFus) for pedestrian detection. RPN_FeaFus adopts an asymmetric dual-path deep model, constructed by VGGNet and ZFNet, to extract pedestrian features in different levels, which are further combined through PCA dimension reduction and feature stacking to provide more discriminant representation. Then, the low-dimensional fusion features are adopted to detect the region proposals and train the classifier. Experimental results on three widely used pedestrian detection databases, i.e, Caltech database, Daimler database and TUD database, illuminate that RPN_FeaFus gains obvious performance improvements over its baseline RPN_BF, which is also competitive with the state-of-the-art methods.

关键词： Feature extraction Databases Proposals Task analysis Training Principal component analysis Detectors

来源：评论

学校读者我要写书评

暂无评论

An Experimental Study on Spatiotemporal Step Characteristics of Individuals Considering the Effect of Ship Heeling and Trim

An Experimental Study on Spatiotemporal Step Characteristics...

引用

Fire Science and Fire Protection Engineering (ICFSFPE), Conference on

作者： Jinlu Sun Shouxiang Lu Jiansheng Wu Ting Sun Kai Shi Shenshi Huang School of Urban Planning and Design Peking University Shenzhen Graduate School Shenzhen China Skate Key Laboratory of Fire Science University of Science and Technology of China Hefei China The Postdoctoral Innovation Base Smart City Research Institute of China Electronics Technology Group Corporation Shenzhen China Smart City Research Institute of China Electronics Technology Group Corporation Shenzhen China Institute of Advanced Computing and Digital Engineering Shenzhen Institute of Advanced Technology Chinese Academy of Science Shenzhen China

ISBN: (数字)9781728153223

ISBN: (纸本)9781728153230

Ship listing and motion affects individual movement pattern on board, thus individual walking behavior would be significantly different from those on level ground. To quantify the correlation between individual walking speed and gait parameters of individuals on board, we designed a ship corridor simulator, where we performed both fast and freely walking experiments considering the effect of ship heeling and trim. Results indicated that both step length and step frequency are positively linearly associated with individual walking speed with different degrees, with one exception that individuals could adopt quick and tiny steps in a much lower walking speed with even larger step frequency to keep balance when the trim-up or trim-down angle exceeds 20°. However, there is no direct relationship that could be observed between step width and individual walking speed, despite that walking with wider steps might weaken individual stability and increase fall risk. Moreover, though individual experimental subjects tend to walk along the right side due to cultural factors, the walking routes are more likely to be close to the handrail arranged on the opposite side for safety purpose when the trim-down angle exceeds 20° even though some of them did not use the handrail actually. This work would be a primary consideration in the development of evacuation models and the design of evacuation facilities on board.

关键词： Legged locomotion Marine vehicles Spatiotemporal phenomena Frequency measurement Foot Stability analysis Length measurement

来源：评论

学校读者我要写书评

暂无评论

LSTM based classification model and its application for doctor-patient relationship evaluation 19

LSTM based classification model and its application for doct...

引用

19th IEEE International Conference on e-Health Networking, Applications and Services, Healthcom 2017

作者： Kuang, Hongrui Che, Chao Zhang, Qiang Wei, Xiaopeng Key Lab of Advanced Design and Intelligent Computing Dalian University Ministry of Education Dalian China Dalian University of Technology School of Computer Science and Technology Dalian China

ISBN: (纸本)9781509067046

The emergence of medical social media has made it possible for more and more patients to share their views and experiences on the medical care platform. These subjective texts contains patients' evaluation information for doctors and can be analyzed to provide rich decision-making information for patients and hospitals. Therefore, we propose a LSTM (Long Short Term Memory) based text sentiment classification method to evaluate the relationship between doctors and patients through the comment data from medical social media. The classification model of doctor-patient relationship can also be performed to evaluate the hospital by calculating the praise rate to help people choose hospitals. We perform two experiments on the patients' evaluation data from the website of Haodaifu. The experiment of doctor-patient relationship classification confirms the effectiveness of the classification model. In the experiment of hospital evaluation, we calculate the praise rate of 11 hospitals in Jinan of Shandong province based on the doctor-patient relationship classification results. The consistency between the results obtained by our method and the data of Mingyihui shows that our evaluation method for hospitals is reasonable and effective. © 2017 IEEE.

关键词： Hospitals

来源：评论

学校读者我要写书评

暂无评论

Development of a New Fluid Shearing System for Cell Culture in Vitro

引用

IOP Conference Series: Materials Science and Engineering 2019年第1期626卷

作者： Pengfei Wu Xin Wang Lilan Gao Chunqiu Zhang Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin 300384 China

Cells in organisms are surrounded by fluid environment, and the fluid shear force produced by this fluid affects the morphology and behaviour of cells. The stimulation of cells in a bioreactor is a key area of research in tissue engineering and regenerative medicine. This paper introduces a fluid shear system for cell culture in vitro. The main component of system is a perfusion chamber, which consists of an inoculation room and a perfusion cap. The inoculation room is used for the common laboratory consumables of microorganism or cell culture, such as petri dish, six-well plate and so on. It can realize to six independent experiments of fluid shear; the new type of perfusion cap was designed to obtain a reasonable cavity by hydrodynamic simulation. The cap was produced by casting technology. It not only has the function of cap with nozzles, but also has the function of sealing. With peristaltic pumps, nozzles, liquid storage bottles and so on, the fluid shearing system which can provide uniform, controllable and up to 60 dyn/cm2 shear stress along the bottom surface is constructed, and is easy to operate and can be personalized.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of Influencing Factors on Carbon Monoxide Utilization Rate of Blast Furnace Based on Multi-Timescale Characteristics 36

Analysis of Influencing Factors on Carbon Monoxide Utilizati...

引用

第36届中国控制会议

作者： Jianqi An Yuwan Yang Min Wu Takao Terano School of Automation China University of Geosciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Department of Computer Science School of ComputingTokyo Institute of Technology

ISBN: (纸本)9781538629185

In the blast furnace,due to the different changing frequency of different operations,and the different reaction time of gas,liquid and solid materials,there exists multi-timescale characteristics in the iron-making ***,not enough attention has been paid to this characteristic,most of the analyses on the blast furnace state before are under a fixed time ***,this paper makes a analysis of influencing factors on carbon monoxide utilization rate of blast furnace based on multi-timescale ***,the factors that affect the carbon monoxide utilization rate are analyzed from different time ***,in the short time scale,the individual influencing time scale of the permeability index,total pressure difference and top temperature is found by the support vector machine（SVM） *** in the long time scale,the influencing time scale of burdening is *** the validity of each model is verified by the field data of the blast furnace.

关键词： Multi-time scales Carbon monoxide utilization Support vector machine Blast furnace

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：