检索结果-内蒙古大学图书馆

Iranian Conference on intelligent Systems (ICIS)

作者： Shermin Khosravi T. Mohammad-R. Akbarzadeh Department of Artificial Intelligence Islamic Azad University of Mashhad Mashhad Iran Center of Excellence on Soft Computing and Intelligent Information Processing Ferdowsi University of Mashhad Iran

This paper proposes the Real-parameter compact supervision for the Particle Swarm Optimization (RCSPSO) in order to optimize problems with continuous parameters. RCSPSO uses the evolutionary configuration of the Real-valued Compact Genetic Algorithm (RCGA) and the search philosophy of the Particle Swarm Optimization (PSO). As a Compact Evolutionary Algorithms (CEA), RCGA rather than operating on a population of individuals processes a statistical representation of that population. Thus, it shows a very explorative behavior. In contrast, PSO despite having access to several solutions only uses the best solution in order to explore the search space. Although it hardly consumes any additional memory, it provides great insight on the potential exploration areas to the particles. Moreover, to improve the update operation of the probability vector in RCGA, it uses an algorithm that prevents inaccurate influence of particle's fitness on its gene's fitness by evaluating each gene separately. Furthermore, to improve sampling the search space, the algorithm uses a combination of Cauchy and Gaussian distributions. To show the algorithm's viability, we use Differential Evolution (DE), CEAs and PSO on some well-known benchmark functions under identical initial conditions. The results show that the proposed method outperforms the aforementioned algorithms in majority of simulation scenarios.

关键词： Sociology Statistics Vectors Genetic algorithms Particle swarm optimization Convergence Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Dynamic agent-based reward shaping for multi-agent systems

Dynamic agent-based reward shaping for multi-agent systems

引用

Iranian Conference on intelligent Systems (ICIS)

作者： Maryam Sadeghlou Mohammad Reza Akbarzadeh-T Mohammad Bagher Naghibi-S Center of Excellence on Soft Computing and Intelligent Information Processing Ferdowsi University of Mashhad Mashhad Iran Department of Electrical Engineering Ferdowsi University of Mashhad Mashhad Iran

Earlier works have reported that reward shaping accelerates the convergence of reinforcement learning algorithms. It also helps to make better use of existing information. In this article we propose the use to modify Q-learning in multiagent systems by the use of reward shaping depending on agent state regarding other agents. We study this method with different choices, which indicate different effects of this method on the maze problem. The results indicate the directional search, reduces the number of steps to reach the target in the proposed modified approach if appropriate parameters are utilized.

关键词： Complexity theory Multi-agent systems Convergence Educational institutions Learning (artificial intelligence) information processing

来源：评论

学校读者我要写书评

暂无评论

Wind power forecasting using emotional neural networks

Wind power forecasting using emotional neural networks

引用

2014 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2014

作者： Lotfi, Ehsan Khosravi, Abbas Akbarzadeh, M.-R. Nahavandi, Saeid Department of Computer Engineering Torbat-e-Jam Branch Islamic Azad University Torbat-e-Jam Iran Center for Intelligence Systems Research Deakin University Geelong3217 Australia Departments of Electrical and Computer Engineering Center of Excellence on Soft Computing and Intelligent Information Processing Ferdowsi University of Mashhad Iran Centre for Intelligent Systems Research Deakin University 75 Pigdons Road Waurn PondsVIC3216 Australia

ISBN: (纸本)9781479938407

Emotional neural network (ENN) is a recently developed methodology that uses simulated emotions aiding its learning process. ENN is motivated by neurophysiological knowledge of the human's emotional brain. In this paper, ENNs are developed and examined for prediction tasks. Genetic algorithm is applied for optimal tuning of crisp numerical parameters of ENN. The performance of the proposed ENN is examined using data sets for a couple of synthetic (with constant and variable noise) and real world (wind farm power generation data) case studies. A traditional artificial neural network (ANN) is also implemented for comparison purposes. Numerical results indicate the superiority of ENN over ANN in terms of accuracy and stability. © 2014 IEEE.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

A bio-inspired model for emergence of cooperation among nanothings

A bio-inspired model for emergence of cooperation among nano...

引用

Iranian Conference on intelligent Systems (ICIS)

作者： Nasibeh Rady Raz Mohammad-R. Akbarzadeh-T Young Researchers and Elite Club Mashhad Branch Islamic Azad University Mashhad Iran Center of Excellence on Soft Computing and Intelligent Information Processing Ferdowsi University of Mashhad Mashhad Iran

In the not too distant future, all the objects of various scales can be connected and build a new kind of Internet. This Internet-like structure can put an end to many problems such as early detection of diseases, drug delivery, pollution, extinction of organisms. The Internet of macro/nano things is an infrastructure-less network and communication range limitation is one of its challenges. Intermediate nano-nodes could be used to overcome this problem. However, intermediate nano-nodes may act selfish and refuse to cooperate due to limited resources. To overcome this problem, we propose a bio-inspired distributed model using a trust and a voronoi-based cooperation strategy with teams of neighbors. Using both cell membrane inspiration for making a flexible joining and parting and two metrics of trust and distance, we make a mechanism to promote cooperation in the Internet of macro/nano things. In this architecture, a good reputation encourages each nano-node to cooperate and gain trust of others in a team of neighbors. A nano-node that is located on the shortest path and has high level of trust will be selected to maintain cooperation. In contrast, a nano-node with a low level of trust parts from the team of neighbors and cannot send information. We compare the proposed work with the state-of-the-art incentive cooperation models like DECADE. Results show that the proposed model is completely distributed, adapts to fast changing conditions (dynamic joining/ parting) and achieves good cooperation value.

关键词： Games Biomembranes Internet Sociology Statistics Nanobioscience Biological system modeling

来源：评论

学校读者我要写书评

暂无评论

Rule selection by Guided Elitism genetic algorithm in Fuzzy Min-Max classifier

Rule selection by Guided Elitism genetic algorithm in Fuzzy ...

引用

Iranian Conference on intelligent Systems (ICIS)

作者： Hadis Jalesiyan Mahdi Yaghubi T. Mohammad R. Akbarzadeh Department of Computer Engineering Islamic Azad University Mashhad Iran Center of Excellence on Soft Computing and Intelligent Information Processing Ferdowsi University of Mashhad Iran Ferdowsi University of Mashhad Mashhad Razavi Khorasan IR

Rule-based classification with Neural Networks has high acceptance ability for noisy data, high accuracy and is preferable in data mining. In this paper, we use Fuzzy Min-Max (FMM) Neural Network. Nevertheless the - Curse of Dimensionality - problem also exists in this classifier. As a possible solution, in this paper the modified GA is adopted to minimize the number of features in the extracted rules. “Guided Elitism” strategy is used to create elitism in the population, based on information extracted from good individuals of previous generations. The main advantage of this data structure is that it maintains partial information of good solutions, which may otherwise be lost in the selection process. Five well-known benchmark problems are used to evaluate the performance of the proposed GEGA system; Results shows comparatively high accuracy and generally lower computational time.

关键词： Genetic algorithms Sociology Statistics Accuracy Neural networks Glass Biological cells

来源：评论

学校读者我要写书评

暂无评论

A time-delay parallel cascade identification system for predicting jaw movements

A time-delay parallel cascade identification system for pred...

引用

Iranian Conference of Biomedical Engineering (ICBME)

作者： Nazanin Goharian Hadi Kalani Sanar Moghimi Electrical Engineering Dept Ferdowsi University of Mashhad Mashhad Iran Mechanical Engineering Dept Ferdowsi University of Mashhad Mashhad Iran Electrical Engineering Dept Center of Excellence on Soft Computing and Intelligent Information Processing Mashhad Iran

The relationship between muscles' electrical activity and body movements is of special importance in many medical applications. In this study, for the first time, we plan to evaluate the efficiency of time-delay parallel cascade identification (TDPCI) to predict jaw motion using Electromyography (EMG) signals recorded from two masticatory muscles, namely masseter and temporalis. The Obtained results demonstrate the efficiency of TDPCI in predicting time-varying mastication kinematic parameters based on EMG signals recorded from the two aforementioned muscles. The proposed model has the potential to be employed for controlling masticatory robots controlled by remotely recorded EMG signals.

关键词： Electromyography Muscles Biomedical engineering Educational institutions Kinematics Robots Neural networks

来源：评论

学校读者我要写书评

暂无评论

Initial free self-organizing map by aggregation

International Journal of Control and Automation

引用

International Journal of Control and Automation 2013年第2期6卷 81-98页

作者： Allahyar, Amin Yazdi, Hadi Sadoghi Department of Computer Engineering Ferdowsi University of Mashhad Mashhad Iran Center of Excellence on Soft Computing and Intelligent Information Processing Ferdowsi University of Mashhad Iran

Initialization parameters of Self-organizing map networks (SOM) have a great influence in their final result. This is the only known problem of SOM networks. The uncertainty of solution is resolved with the fusion methods in many machine learning algorithms. Motivated by this application, we aim to reduce the uncertainty in SOM final result and provide a more robust solution. This is done by aggregating the results obtained from several run of SOM network. The objective in uniting several SOM run is to reduce the effect of two above factors and reach a more appropriate solution. To achieve this, a number of methods for integration of SOM solutions have been proposed and their characteristics are discussed in detail. Finally, these approaches are experimentally compared with some recently proposed SOM networks and their effectiveness are investigated.

关键词： Self organizing maps

来源：评论

学校读者我要写书评

暂无评论

A probabilistic model for assessing the reliability of wind farms in a power system

引用

Journal of Zhejiang University-Science C(Computers and Electronics) 2013年第6期14卷 464-474页

作者： Mostafa HOSSEINPOUR Habib RAJABI MASHHADI Mohammad Ebrahim HAJIABAD Faculty of Engineering Department of Electrical EngineeringFerdowsi University of MashhadMashhadIran Center of Excellence on Soft Computing and Intelligent Information Processing Ferdowsi University of MashhadMashhadIran

Modeling the generation of a wind farm and its effect on power system reliability is a challenging task,largely due to the random behavior of the output *** this paper,we propose a new probabilistic model for assessing the reliability of wind farms in a power system at hierarchical level II(HLII),using a Monte Carlo *** proposed model shows the effect of correlation between wind and load on reliability *** can also be used for identifying the priority of various points of the network for installing new wind farms,to promote the reliability of the whole system.A simple grid at hierarchical level I(HLI) and a network in the north-eastern region of Iran are *** results showed that the correlation between wind and load significantly affects the reliability.

关键词： Wind farm Reliability Priority Probabilistic model

来源：评论

学校读者我要写书评

暂无评论

Wind power forecasting using emotional neural networks

Wind power forecasting using emotional neural networks

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Ehsan Lotfi Abbas Khosravi M-R. Akbarzadeh-T Saeid Nahavandi Department of Computer Engineering Islamic Azad University Torbat-e-Jam Iran Center for Intelligence Systems Research Deakin University Geelong Australia Center of Excellence on Soft Computing and Intelligent Information Processing Ferdowsi University of Mashhad Iran Alfred Deakin Professor Deakin University Waurn Ponds Victoria Australia

关键词： Wind power generation Forecasting Artificial neural networks Brain models Genetic algorithms Biological cells

来源：评论

学校读者我要写书评

暂无评论

Cooperation Tuning in MANETs: A fuzzy approach Fuzzy behaviors of node in the presence of conflict

Cooperation Tuning in MANETs: A fuzzy approach Fuzzy behavio...

引用

13th Iranian Conference on Fuzzy Systems, IFSC 2013

作者： Rady Raz, Nasibeh Akbarzadeh -T, Mohammad-R. Department of Artificial Intelligent Islamic Azad University Mashhad Branch Mashhad Iran Center of Excellence on Soft Computing and Intelligent Information Processing Ferdowsi University of Mashhad Mashhad Iran

ISBN: (纸本)9781479912285

One of the challenging concepts in mobile ad hoc networks (MANETs) is cooperation maintenance. It is important to know when and how long to do the cooperation among nodes. In this paper we introduce a new concept called 'Cooperation Tuning'. A distributed system based on a fuzzy inference system (FIS) with two inputs 'cooperativeness' and 'assertiveness' and an output 'conflict' is proposed. Considering a degree of conflict, each node decides whether to send a packet or save its energy. We classify nodes' behaviors into five types: Collaborating, Competing, Compromising, Avoiding and Accommodating. Results show that conflict is a good 'Cooperation Tuning' tool and some degrees of conflict have a good influence on network throughput and decreasing selfishness among nodes. We compare our work with the state-of-the-art incentive cooperation models like DECADE. © 2013 IEEE.

关键词： Fuzzy systems

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：