2016 Artificial Intelligence and Robotics (IRANOPEN)最新文献_第3页

Using parametric regression and KNN algorithm with missing handling for software effort prediction 采用参数回归和带缺失处理的KNN算法进行软件工作量预测

2016 Artificial Intelligence and Robotics (IRANOPEN) Pub Date : 2016-04-09 DOI: 10.1109/RIOS.2016.7529494

Fereshteh Soltanveis, S. H. Alizadeh

引用次数: 5

Identify human personality parameters based on handwriting using neural network 基于笔迹的神经网络人格参数识别

2016 Artificial Intelligence and Robotics (IRANOPEN) Pub Date : 2016-04-09 DOI: 10.1109/RIOS.2016.7529501

Behnam Fallah, Hassan Khotanlou

{"title":"Identify human personality parameters based on handwriting using neural network","authors":"Behnam Fallah, Hassan Khotanlou","doi":"10.1109/RIOS.2016.7529501","DOIUrl":"https://doi.org/10.1109/RIOS.2016.7529501","url":null,"abstract":"The survey of person's handwriting and its parameters anatomy will lead the psychologists to investigate the psychological principles of behavior, temperament, character, personality and the nervous and social aspects of a person's brain. The human's handwritings in different psychological states including: anger, calm, happiness, excitement and different emotional states will show one's reaction or behavior at the same situations or same states. Analyzing one's handwriting is one of the scientific methods for evaluating and understanding one's personality. When a person's personality is analyzed, the effect of his personality or character on his/her handwriting is obvious and remarkable. The purpose of this method is to identify a person's personality through his/her handwriting. The literature shows that the identification and verification of human's identity from handwriting is common and relatively useful. Moreover, identification of one's identity from signature is more common. In this paper, in order to identify the character parameters in training stage, The Minnesota Multiphasic Personality Inventory was applied, and for identification of one's personality from his/her handwriting, a hidden Markov model and neural network (MLP) to perform classification was used so that MLP was used to identify those properties which are not related to the writer and a hidden Markov model was used to classify those properties which are related to the target writer. In this stage, in order to select the most similar image to the image of the input context, the image of input context after eliciting its property will be compared with all existing patterns in database. Finally the test output regarding the personality of the image of the target text which is recommended by the system will be introduced as the parameters of the output character.","PeriodicalId":416467,"journal":{"name":"2016 Artificial Intelligence and Robotics (IRANOPEN)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127595506","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 22

License Plate Automatic Recognition based on edge detection 基于边缘检测的车牌自动识别

2016 Artificial Intelligence and Robotics (IRANOPEN) Pub Date : 2016-04-09 DOI: 10.1109/RIOS.2016.7529509

Pooya Sagharichi Ha, M. Shakeri

引用次数: 33

Adaptive search in unstructured peer-to-peer networks based on ant colony and Learning Automata 基于蚁群和学习自动机的非结构化点对点网络自适应搜索

2016 Artificial Intelligence and Robotics (IRANOPEN) Pub Date : 2016-04-09 DOI: 10.1109/RIOS.2016.7529503

A. Ahmadi, M. Meybodi, A. Saghiri

{"title":"Adaptive search in unstructured peer-to-peer networks based on ant colony and Learning Automata","authors":"A. Ahmadi, M. Meybodi, A. Saghiri","doi":"10.1109/RIOS.2016.7529503","DOIUrl":"https://doi.org/10.1109/RIOS.2016.7529503","url":null,"abstract":"An unstructured peer-to-peer network is an overlay network where all nodes play equal roles, and the topology and data location do not follow restrictive rules. So, in a traditional file search mechanism, such as flooding, a peer broadcasts a query to its neighbors through an unstructured peer-to-peer (P2P) network until the time-to-live decreases to zero. A major disadvantage of flooding is that, in a large-scale network, this blind-choice strategy usually incurs an enormous traffic overhead. AntP2PR is a protocol to search based on the ant colony in unstructured peer to peer networks, which faces with some problems such as high communication overhead and low success rate due to the lack of an appropriate decision-making mechanism. In this paper, two adaptive improved version of AntP2PR named DLAntP2P and LAntP2P to improve the search problem in unstructured peer-to-peer networks are proposed. The DLAntP2P and LAntP2P protocols utilize the Distributed Learning Automata (DLA) and Learning Automata (LA), respectively, as an adaptive decision-making mechanism to determine number of ant and enhance the way of selecting the neighbors to forward the query messages. Simulations show the effectiveness of proposed protocols in terms of communication overhead and success rate, compared to AntP2PR and K-walker random walk.","PeriodicalId":416467,"journal":{"name":"2016 Artificial Intelligence and Robotics (IRANOPEN)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124324656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

A new distributed learning automata based algorithm for maximum independent set problem 基于分布式学习自动机的最大独立集问题求解算法

2016 Artificial Intelligence and Robotics (IRANOPEN) Pub Date : 2016-04-09 DOI: 10.1109/RIOS.2016.7529512

M. D. Khomami, Negin Bagherpour, H. Sajedi, M. Meybodi

引用次数: 9

Intelligent and dynamic method to specify chronological order of the games to improve the excitement and fairness of the champions in simulation league 智能和动态的方法来指定比赛的时间顺序，以提高模拟联赛冠军的兴奋和公平

2016 Artificial Intelligence and Robotics (IRANOPEN) Pub Date : 2016-04-09 DOI: 10.1109/RIOS.2016.7529510

Nader Zare, A. Keshavarzi, Hadi Mowla, S. E. Beheshtian

引用次数: 0

An extension of multinomial choice model for customer purchase behavior analysis 顾客购买行为分析中多项选择模型的扩展

2016 Artificial Intelligence and Robotics (IRANOPEN) Pub Date : 2016-04-09 DOI: 10.1109/RIOS.2016.7529491

Parinaz Norouzi, S. H. Alizadeh

引用次数: 6

A hierarchical feature learning for isolated Farsi handwritten digit recognition using sparse autoencoder 基于稀疏自编码器的孤立波斯语手写数字识别的分层特征学习

2016 Artificial Intelligence and Robotics (IRANOPEN) Pub Date : 2016-04-09 DOI: 10.1109/RIOS.2016.7529492

Reza Safdari, M. Moin

引用次数: 11

Particle Swarm Optimization based feature selection with novel fitness function for image steganalysis 基于适应度函数的粒子群特征选择图像隐写分析

2016 Artificial Intelligence and Robotics (IRANOPEN) Pub Date : 2016-04-01 DOI: 10.1109/RIOS.2016.7529499

Vahid Rostami, Azar Shahmoradi Khiavi

引用次数: 11