检索结果-内蒙古大学图书馆

IEEE International Conference on Image Processing

作者： Haifeng Zhao Jun Cheng Jun Jiang Dacheng Tao Sci. & Tech. on Information System Engineering Laboratory Nanjing 210007 China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology CAS Shenzhen 518055 China Center for Quantum Computation and Intelligent Systems University of Technology Sydney 2007 Australia

ISBN: (纸本)9781479923427

Multiple Instance Learning (MIL) has been widely applied in practice, such as drug activity prediction, content-based image retrieval. In MIL, a sample, comprised of a set of instances, is called a bag. Labels are assigned to bags instead of instances. The uncertainty of labels on instances makes MIL different from conventional supervised single instance learning (SIL) tasks. Therefore, it is critical to learn an effective mapping to convert an MIL task to an SIL task. In this paper, we present OptMILES by learning the optimal transformation on the bag-to-instance similarity measure, exploring the optimal distance metric between instances, by an alternating minimization training procedure. We thoroughly evaluate the proposed method on both a synthetic dataset and real world datasets by comparing with representative MIL algorithms. The experimental results suggest the effectiveness of OptMILES.

关键词： Multiple instance learning distance metric learning MILES image classification alternating minimization MILES Image classification distance metric Squamous Intraepithelial Lesions Learning

来源：评论

学校读者我要写书评

暂无评论

Incommensurate order fractional optimal control: Application to treatment of psychiatric disorders

Incommensurate order fractional optimal control: Application...

引用

Iranian Conference on Electrical Engineering (ICEE)

作者： S. S. Tabatabaei M. J. Yazdanpanah M. S. Tavazoei Department of Electrical Engineering Amirkabir University of Technology Tehran Iran Advanced Control Systems Laboratory Control and Intelligent Processing Center of Excellence School of Electrical and Computer Tehran Iran Electrical Engineering Department Sharif University of Technology Tehran Iran

ISBN: (纸本)9781467356329

The main point of this paper is to present a time domain strategy for drug dosage to treat psychiatric disorders. A time domain model of emotion is obtained from an extension of a recently developed fractional nonlinear dynamic model of happiness. First, the Fractional Optimal Control law for incommensurate multi state systems is obtained. It will be then applied as an optimal drug administration procedure in the line of psychiatric disorders treatment. Results of this paper show that optimal control scheme is a proper approach to face the difficulties of analysis and control the incommensurate systems. It can be also clearly seen from the simulation results that this approach is very effective in the case that control methods are used as treatment techniques.

关键词： Mathematical model Drugs Optimal control Numerical models Differential equations Equations

来源：评论

学校读者我要写书评

暂无评论

A HIERARCHICAL REINFORCEMENT LEARNING-BASED APPROACH TO MULTI-ROBOT COOPERATION FOR TARGET SEARCHING IN UNKNOWN ENVIRONMENTS

引用

CONTROL AND intelligent systems 2013年第4期41卷 1-1页

作者： Cai, Yifan Yang, Simon X. Xu, Xin Advanced Robotics and Intelligent Systems (ARIS) Laboratory School of Engineering University of Guelph Guelph ON N1G 2W1 Canada College of Mechatronics and Automation National University of Defense Technology Changsha Hunan Province 410073 China

Effective cooperation of multi-robots in unknown environments is essential in many robotic applications, such as environment exploration and target searching. In this paper, a MAXQ and Option combined hierarchical reinforcement learning approach, together with a multi-agent cooperation strategy, are proposed for the real-time cooperation of multi-robots in completely unknown environments. Unlike other algorithms that need an explicit environment model or selected parameters by trial and error, the proposed cooperation method obtains all the required parameters automatically through learning. By integrating segmental options with the MAXQ algorithm, a multi-agent cooperation strategy is designed. In new tasks, the designed cooperation method can control the multi-robot system to complete the task effectively. The simulation results demonstrate that the proposed scheme is able to effectively and efficiently guide a team of robots to cooperatively accomplish target searching tasks in completely unknown environments.

关键词： Hierarchical reinforcement learning multi-robot cooperation com-pletely unknown environment target searching

来源：评论

学校读者我要写书评

暂无评论

Humanoid robot as an evaluator of assistive devices

Humanoid robot as an evaluator of assistive devices

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Kanako Miura Eiichi Yoshida Yoshiyuki Kobayashi Yui Endo Fumio Kanehioro Keiko Homma Isamu Kajitani Yoshio Matsumoto Takayuki Tanaka CNRS-AIST JRL (Joint Robotics Laboratory) Intelligent Systems Research Institute National Institute of Advanced Industrial Science and Technology Japan Digital Human Research Center DHRC-AIST AIST Japan IS-AIST Japan Hokkaido University Japan

This paper presents a basic study on feasibility of usage of humanoid robots as an evaluator of assistive devices, by taking advantage of its anthropomorphic shape. In this new application humanoid are expected to help evaluation through quantitative measures, which is difficult with human subjects, and also to reduce the burden coming from ethical concerns with costly tests by human subjects. Taking a passive supportive wear “Smart Suit Lite” designed to relieve the load at lower back as an example, we have conducted pilot experiments by using the humanoid robot HRP-4C. The motion to be performed by the humanoid is obtained through retargeting technique from measured human lifting motion. The supportive effect is first estimated by simulation taking into account the mechanism of the supportive device. The experimentation of humanoid hardware brought us encouraging results on the basic feasibility of this application, as we observed a clear decrease of the torque for lifting when wearing the device as expected by the simulation.

关键词： Joints Torque Assistive devices Hip Humanoid robots Torso

来源：评论

学校读者我要写书评

暂无评论

Finding Objects with Segmentation Strategy based Multi Robot Exploration in Unknown Environment

引用

Procedia - Social and Behavioral Sciences 2013年 97卷 580-586页

作者： Reza Arezoumand Syamsiah Mashohor Mohammad Hamiruce Marhaban Intelligent System and Robotics Laboratory Institute of Advanced Technology Universiti Putra Malaysia 43400 Serdang Selangor Malaysia Department of Computer & Communication Systems Faculty of Engineering Universiti Putra Malaysia 43400 Serdang Selangor Malaysia Department of Electrical and Electronic Engineering University Putra Malaysia 43400 Serdang Selangor Malaysia

In this paper we address exploration algorithm in flat experimental environment with colored objects for multi robots system. The aim of exploration in unknown environment is finding target points like mine detection in outdoor environment without any positioning device. Two algorithms were investigated in this paper one is frontier based random search algorithm and the second is efficient algorithm based on segmentation strategy. To improve efficiency, each robot had to go to different regions to avoid cumulating robots in one region. Constructed maps for all four regions could be shared and navigation could be done more effectively. For constructing map robot can use on built range finder sensor or using vision based systems. Also the algorithm using segmentation strategy is using frontier base algorithm for exploring divided area. Both algorithm implemented and analyzed in Player/Stage simulation. The result was compared and showed the efficiency of the designed algorithm based segmentation strategy. In simulation this algorithm is tested with different number of robots to achieve better view of efficiency for proposed algorithm in different type of environment like harsh environment as possibility of losing some robots.

关键词： Multi-robot exploration Flocking Exploration ratio Trajectory prediction

来源：评论

学校读者我要写书评

暂无评论

GPS/INS integration based on dynamic ANFIS network

International Journal of Control and Automation

引用

International Journal of Control and Automation 2012年第3期5卷 1-22页

作者： Hasan, Ahmed Mudheher Samsudin, Khairulmizam Ramli, Abdul Rahman Computer Systems Research Group Department of Computer and Communication Systems Universiti Putra Malaysia 43400 UPM-Serdang Malaysia Intelligent Systems and Robotics Laboratory Institute of Advanced Technology Universiti Putra Malaysia 43400 UPM-Serdang Malaysia

This article presents a new structure for solving global positioning system (GPS) outages for long periods without requiring any prior information about the characteristics of the inertial navigation system (INS) and GPS. Kalman filter (KF) is widely used in INS and GPS integration to present a forceful navigation solution by overcoming the GPS outage problems. However, KF is usually criticized for working under predefined models and for its observability problem of hidden state variables, sensor dependency, and linearization dependency. Therefore, this article proposes a dynamic adaptive neuro-fuzzy inference system (DANFIS) to predict the INS error during GPS outages based on the current and previous raw INS data. The proposed integrated system is evaluated using a real field test data. The performance of the proposed technique is also compared with the traditional artificial intelligence (AI) technique and KF. The results showed great improvements in positioning and especially in velocity for MEMS grade IMU and for different length of GPS outages.

关键词： Inertial navigation systems

来源：评论

学校读者我要写书评

暂无评论

A highly efficient clustering algorithm for analyzing gene sequences

A highly efficient clustering algorithm for analyzing gene s...

引用

数学、计算机与生命科学交叉研究青年学者研讨会

作者： Dan Wei Qingshan Jiang Yanjie Wei Shengrui Wang Shenzhen Key Lab for High Performance Data Mining Shenzhen Institutes of Advanced TechnologyChinese Academy of SciencesShenzhenChina Shenzhen Key Lab for High Performance Data MiningShenzhen Institutes of Advanced TechnologyChinese Academy of SciencesShenzhenChina Department of Computer SciencesUniversity of SherbrookeSherbrookeQCCanada Cognitive Science Department & Fujian Key Laboratory of the Brain-like Intelligent Systems Xiamen UniversityXiamenChina

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial: intelligent Information technology in Agriculture

引用

intelligent Automation & Soft Computing 2013年第3期19卷 227-229页

作者： Dong Ren[a] Chunjiang Zhao[b] & Simon X. Yang[c] [a] College of Computer and Information Technology China Three Gorges University Yichang 443002 P.R. China [b] Beijing Research Center for Information Technology in Agriculture Beijing Academy of Agriculture and Forestry Sciences Beijing 100097 P.R. China [c] Advanced Robotics and Intelligent Systems (ARIS) Laboratory School of Engineering University of Guelph Guelph Ontario N1G 2W1 Canada

Click to increase image sizeClick to decrease image size

关键词：

来源：评论

学校读者我要写书评

暂无评论

Differently implicational α-universal triple I restriction method of (1, 2, 2) type

引用

Journal of systems Engineering and Electronics 2012年第4期23卷 560-573页

作者： Yiming Tang Fuji Ren Yanxiang Chen Information and Communication Engineering Postdoctoral Research Station Hefei University of TechnologyHefei 230009P.R.China State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191P.R.China Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of TechnologyHefei 230009P.R.China Institute of Technology and Science The University of TokushimaMinami Josanjima770-8506Japan

From the viewpoints of both fuzzy system and fuzzy reasoning, a new fuzzy reasoning method which contains the α- triple I restriction method as its particular case is proposed. The previous α-triple I restriction principles are improved, and then the optimal restriction solutions of this new method are achieved, especially for seven familiar implications. As its special case, the corresponding results of α-triple I restriction method are obtained and improved. Lastly, it is found by examples that this new method is more reasonable than the α-triple I restriction method.

关键词： fuzzy reasoning fuzzy system triple I method triple Irestriction method compositional rule of inference method.

来源：评论

学校读者我要写书评

暂无评论

A new classification method for human gene splice site prediction

引用

1st International Conference on Health Information Science, HIS 2012

作者： Wei, Dan Zhuang, Weiwei Jiang, Qingshan Wei, Yanjie Cognitive Science Department Fujian Key Laboratory of the Brain-like Intelligent Systems Xiamen University Xiamen China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China

ISBN: (纸本)9783642293603

Human splicing site prediction is important for identifying the complete structure of genes in Human genomes. Machine learning method is capable of distinguishing the different splice sites in genes. For machine learning method, feature extraction is a key step in dealing with the problem of splicing site identification. Encoding schema is a widely used method to encode gene sequences by feature vectors. However, this method ignores the information of the period-3 behavior of the splice sites and sequential information in the sequence. In this paper, a new feature extraction method, based on orthogonal encoding, codon usage and the sequential information, is proposed to map splice site sequences into feature vectors. Classification is performed using a Support Vector Machine (SVM) method. The experimental results show that the new method can predict human splice sites with high classification accuracy. © 2012 Springer-Verlag.

关键词： Feature extraction

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：