检索结果-内蒙古大学图书馆

36th Chinese Control Conference, CCC 2017

作者： Liu, Tianfeng Ding, Yongsheng Cai, Xin Zhu, Yifeng Zhang, Xiangfei Engineering Research Center of Digitized Textile and Apparel Technology Ministry of Education College of Information Sciences and Technology Donghua University Shanghai 201620 China Shanghai Agricultural IOT Engineering Technology Research Center Shanghai China Information Center Shanghai Agricultural Committee Shanghai 200335 China

Reference evapotranspiration (ET0) plays an important role in water resources scheduling of irrigation systems. This paper proposes a novel extreme learning machine (ELM) method optimized by particle swarm optimizatio... 详细信息

ISBN: (纸本)9781538629185

Reference evapotranspiration (ET₀) plays an important role in water resources scheduling of irrigation systems. This paper proposes a novel extreme learning machine (ELM) method optimized by particle swarm optimization (PSO) algorithm (PSO-SWELM) to realize more accurate evapotranspiration estimation with limited environmental and meteorological data. The weights and thresholds between input and hidden layers of ELM is optimized by PSO algorithm and a function based on the two-wave superposition is selected as the activation function of ELM, which both enhances the accuracy of estimation. The Penman-Monteith model (FAO-56 PM) is used as the standard model to estimate ET₀. The root of mean squared error (RMSE) and coefficient of determination (R²) are set as the two evaluation criteria to compare the performances of BP, PSO-BP, SVM, ELM, PSO-ELM and PSO-SWELM in estimating ET₀. The simulation results show that the PSO-SWELM method has better performance in predicting the ET0 than the currently prevailing methods. © 2017 Technical Committee on Control Theory, CAA.

关键词： Activation function Extreme Learning Machine Particle Swarm Optimization Penman-Monteith model Reference Evapotranspiration

来源：评论

学校读者我要写书评

暂无评论

TVWS Network AP Placement in Indoor 3D Space Based on Path Loss Model

TVWS Network AP Placement in Indoor 3D Space Based on Path L...

引用

2017中国智能物联系统会议

作者： YANG Zhengjian ZHANG Guanglin LI Demin College of Information Science and Technology Donghua UniversityShanghai 201620China Engineering Research Center of Digitized Textile and Apparel Technology Ministry of EducationShangh

The increasing demand of wireless communication would lead to the scarcity of spectrum resources and many countries and institutions have begun to release rules to use of TV white space(TVWS).Most of existing studies focused on exploring TVWS in outdoor environments and there are few researched on indoor TVWS *** this paper,we presented an indoor three-dimensional TV white space network *** is the first white space network design built in indoor 3D *** the indoor environment seriously influences the wireless signal strength,we applied the path loss *** proposed the 3D distance system and determined the AP placement based on path loss *** built an experiment platform to communicate in TVWS and we optimized spectrum allocation in *** results shows that this is an effectual architecture and might work in real *** system satisfied the demand traffic rate,reduced system cost and achieved fairness among users.

关键词： Indoor 3D Network AP placement in TVWS Wireless Communicate in TVWS Path Loss Model

来源：评论

学校读者我要写书评

暂无评论

A rule-driven multi-path routing algorithm with dynamic immune clustering for event-driven wireless sensor networks

引用

Neurocomputing 2016年 203卷 139-149页

作者： Ding, Yongsheng Chen, Rui Hao, Kuangrong Engineering Research Center of Digitized Textile and Apparel Technology College of Information Science and Technology Donghua University Shanghai 201620 China

In order to save energy for event-driven wireless sensor networks (WSNs) applied to emergency monitoring, a rule-driven multi-path routing algorithm with dynamic immune clustering (RDICMR) is proposed. The RDICMR algorithm is executed under the driven of condition rules and implementation rules. By applying the working mechanism of the biological immune system to the event-driven dynamic clustering algorithm for WSNs, where event as antigen, the records of clusters and routing paths of past events in the node[U+05F3]s memory as antibodies, antibodies have the function of collecting and preserving memories, as such it is convenient to response to antigens that are similar to the previous antigen timely. When similar events happen and satisfy the affinity and energy rules, the sensor nodes can directly call antibodies in the memory to build clusters of events and transfer data quickly. Besides, we change the cycle of the network dynamically according to the updating cluster cycle rule. The proposed RDICMR algorithm saves a lot of energy in the process of building clusters and data transmission, increases the amount of data transmission and prolongs the lifetime of the network. © 2016 Elsevier B.V..

关键词： Dynamic immune clustering Event-driven Multi-path routing Rule-driven Wireless sensor network

来源：评论

学校读者我要写书评

暂无评论

Exposing Image Forgery with Inconsistent Reflection Line Midpoint

引用

Journal of Donghua University(English Edition) 2017年第1期34卷 44-48页

作者：葛华勇 MALIK Hafiz 蒋学芹房树娟 College oflnformation Sciences and Technology Donghua University Shanghai 201620 China Engineering Research Center of Digitized Textile & Fashion Technology Ministry of Education Donghua University Shanghai 201620 China Department of Electrical and Computer Engineering University of Michigan-Dearborn M148128 USA

In recent years,there has been a backlash of sorts and the authenticity of images has been routinely *** is no longer *** is an urgent need for robust image forensic techniques to expose photo *** paper proposed a novel and effective technique to expose image forgery using inconsistent *** specifically,a new technique was presented to calculate reflection line midpoint,the definition of midpoint ratio was given,and three standards were proposed and employed to detect image *** and effectiveness of the proposed technique were evaluated using a data set consisting of 200 authentic and forged *** results indicate that the proposed method can detect image forgery with very high success rate.

关键词： image forgery inconsistent reflection midpoint ratio image forensics

来源：评论

学校读者我要写书评

暂无评论

Real-time Cost Minimizing Energy Allocation in Microgrids with Electric Vehicles

Real-time Cost Minimizing Energy Allocation in Microgrids wi...

引用

2017中国智能物联系统会议

作者： WU Changle ZHANG Guanglin LI Demin CAO Yongsheng College of Information Science and Technology Donghua UniversityShanghai201620.P.R.China Engineering Research Center of Digitized Textile and Apparel Technology Ministry of EducationShangh

In this paper,we consider a microgrid scenario that consists of electric vehicles(EVs),aggregator,renewable energy generation,combined heat and power(CHP)generation,power grid,and thermal energy storage *** aggregator operates power grid,CHP generation and EVs to provide energy balancing service between supply and *** aim to use EVs and water tank as energy storage devices to minimize the time-average system cost by jointly considering the uncertainty of real-time electricity price,renewable energy generation,demands,*** propose an real-time energy allocation algorithm by employing the Lyapunov optimization technique,which does not need any statistical information about the system *** demonstrate that our proposed algorithm accommodates a wide spectrum of vital system characteristics,including the self charging/discharging of EV,limited battery size of EV,battery degradation cost of *** the cost of purchasing electncity from power grid and using natural *** further compare our proposed algorithm with two alternatives through simulation and demonstrate its performance is better.

关键词： Electric Vehicles (EVs) combined heat and power (CHP) generation renewable energy generation microgrid real-time algorithm

来源：评论

学校读者我要写书评

暂无评论

An Immune System-Inspired Information Diffusion Model 36

An Immune System-Inspired Information Diffusion Model

引用

Chinese Control Conference

作者： Yanjun Liu Yongsheng Ding Kuangrong Hao Lei Chen Engineering Research Center of Digitized Textile & Fashion Technology Ministry of Education College of Information Sciences and Technology Donghua University Shanghai P. R. China

ISBN: (纸本)9781538629185

Though there are a lot of common characteristics between epidemic spreading and information diffusion, but it has a significant difference in nature. Individual spreading behavior is closely related to user activity, user neighbor and network features. At present, most of research on information diffusion is based on epidemic spreading where the probability that the user is infected by the information is regarded as a constant, which has a less ability to reduce the information diffusion in the real network. In this paper, we analyze the process of immune response and propose an information diffusion model based on immune mechanism, where the information tolerance, social reinforcement and memory enhancement is taken into account. Experiments show that the model can more accurately describe the process of information diffusion and reflect the trend of information diffusion, as such helps to better describe the actual diffusion process.

关键词： Immune system Social network services Analytical models Diseases Silicon Diffusion processes Media

来源：评论

学校读者我要写书评

暂无评论

Forgery Detection Using Inconsistent Reflection Vanishing Point

引用

Journal of Donghua University(English Edition) 2017年第5期34卷 666-669页

作者：葛华勇 HAFIZ Malik 蒋学芹 College of lnformation Sciences and Technology Donghua UniversityShanghai 201620China Engineering Research Center of Digitized Textile&Fashion Technology Ministry of EducationDonghua UniversityShanghai 201620China Department of Electrical and Computer Engineering University of Michigan-DearbornM148128USA

The rapid development of image processing techniques has made it extremely easy to alter the content of images or create *** photographs,which appear in magazines,social media,and political attacks,can no longer be trusted.A novel and effective technique is proposed in this paper to expose image forgery using inconsistent reflection vanishing point(RVP).More specifically,the definition of error distance is given,sin^2()-based function is proposed to normalize error distance,and a reasonable threshold value is set to detect image *** experimental data and results are presented to demonstrate the accuracy and effectiveness of the technique.

关键词： image forensics reflection vanishing point(RVP) error distance reflection consistency threshold value

来源：评论

学校读者我要写书评

暂无评论

Multi-State Self-Learning Template Library Updating Approach for Multi-Camera Human Tracking in Complex Scenes

引用

International Journal of Pattern Recognition and Artificial Intelligence 2017年第12期31卷 1755016-1755016页

作者： Liu, Jian Hao, Kuangrong Ding, Yongsheng Yang, Shiyu Gao, Lei Engineering Research Center of Digitized Textile and Apparel Technology Ministry of Education College of Information Science and Technology Donghua University Shanghai201620 China CSIRO Private Mail Bag 2 Glen-OsmondSA Australia

In multi-camera video tracking, the tracking scene and tracking-target appearance can become complex, and current tracking methods use entirely different databases and evaluation criteria. Herein, for the first time to our knowledge, we present a universally applicable template library updating approach for multi-camera human tracking called multi-state self-learning template library updating (RS-TLU), which can be applied in different multi-camera tracking algorithms. In RS-TLU, self-learning divides tracking results into three states, namely steady state, gradually changing state, and suddenly changing state, by using the similarity of objects with historical templates and instantaneous templates because every state requires a different decision strategy. Subsequently, the tracking results for each state are judged and learned with motion and occlusion information. Finally, the correct template is chosen in the robust template library. We investigate the effectiveness of the proposed method using three databases and 42 test videos, and calculate the number of false positives, false matches, and missing tracking targets. Experimental results demonstrate that, in comparison with the state-of-the-art algorithms for 15 complex scenes, our RS-TLU approach effectively improves the number of correct target templates and reduces the number of similar templates and error templates in the template library. © 2017 World Scientific Publishing Company.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

research and Application of Smart Hanger Based on Airbag Inflation Model and Multi-object Collaborative Optimization Algorithm

Research and Application of Smart Hanger Based on Airbag Inf...

引用

2nd International Conference on Computer engineering,Information Science & Application technology(ICCIA 2017)

作者： Yihong Zhang Xi Jin Zhijie Wang College of Information Science & Technology DongHua University Engineering Research Center of Digitized Textile and Fashion Technology Ministry of Education

ISBN: (纸本)9781510845008

This paper presents a smart hanger based on airbag inflation and muti-object collaborative optimization algorithm for intelligent garment inspecting system. To fully extend the garment to a proper position, one fuzzy Self-adaptive PID method is given to control the pneumatic motor by comparing the feedback value of the flexible pressure sensor with the threshold value. Flexible sensor arrays were embedded on the surface of the smart hanger;the pressure value detected shows appropriate degree between cloths and the smart hanger, and it's an important standard for garment inspection. One multi-objective optimization algorithm is proposed for the various targets control on the smart hanger in order to achieve the optimal value.

关键词： Smart Hanger Garment defect detecting Flexible pressure sensor Adaptive fuzzy control Airbag inflation model Multi objective optimization

来源：评论

学校读者我要写书评

暂无评论

research and Application of Smart Hanger Based on Airbag Inflation Model and Fuzzy Self-adaptive PID Method

Research and Application of Smart Hanger Based on Airbag Inf...

引用

2017 2nd International Conference on Control, Automation and Artificial Intelligence(CAAI2017)

作者： Yihong Zhang Xi Jin Zhijie Wang College of Information Science &Technology DongHua University Engineering Research Center of Digitized Textile and Fashion Technology Ministry of Education

ISBN: (纸本)9781510845541

This paper demonstrates one smart hanger based on airbag inflation and fuzzy Self-adaptive PID method for intelligent garment inspecting system. To fully extend the garment to a proper position, one fuzzy Self-adaptive PID method is given to control the pneumatic motor by comparing the feedback value of the flexible pressure sensor with the threshold value. Flexible sensor arrays were embedded on the surface of the smart hanger;the pressure value detected shows appropriate degree between cloths and the smart hanger, and it's an important standard for garment inspection. The adaptive fuzzy control algorithm is proposed to control the whole process.

关键词： smart hanger garment defect detecting flexible pressure sensor adaptive fuzzy PID contro airbag inflation model

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：