2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI)最新文献_第4页

Playing the game of snake with limited knowledge: Unsupervised neuro-controllers trained using particle swarm optimization 用有限的知识玩蛇的游戏:使用粒子群优化训练的无监督神经控制器

2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI) Pub Date : 2017-11-01 DOI: 10.1109/ISCMI.2017.8279602

Cornelius J. van Rooyen, Willem S. van Heerden, C. Cleghorn

{"title":"Playing the game of snake with limited knowledge: Unsupervised neuro-controllers trained using particle swarm optimization","authors":"Cornelius J. van Rooyen, Willem S. van Heerden, C. Cleghorn","doi":"10.1109/ISCMI.2017.8279602","DOIUrl":"https://doi.org/10.1109/ISCMI.2017.8279602","url":null,"abstract":"Methods in the domain of artificial intelligence (AI) have been applied to develop agents capable of playing a variety of games. The single-player variant of Snake is a well-known and popular video game that requires a player to navigate a line-based representation of a snake through a two-dimensional playing area, while avoiding collisions with the walls of the playing area and the body of the snake itself. A score and the snake length are increased whenever the snake is moved through items representing food. The game thus becomes more challenging as the score increases. The application of AI techniques to playing the game of Snake has not been very well explored. This paper proposes a novel technique that uses particle swarm optimization for the unsupervised training of neuro-controllers in order to play the game of Snake. The proposed technique assumes nothing about effective game playing strategies, and thus works with limited knowledge. Sensory input is also minimal. Due to the lack of similar AI-based approaches for playing Snake, the proposed technique is empirically compared against three hand-designed Snake playing agents in terms of several performance measures. The performance of the proposed technique demonstrates the feasibility of the approach, and suggests that future research into AI-based controllers for Snake will be fruitful.","PeriodicalId":119111,"journal":{"name":"2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115306548","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: 0

Analysis and comparison of two task models in a partially observable Markov decision process based assistive system 基于部分可观察马尔可夫决策过程的辅助系统两种任务模型的分析与比较

2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI) Pub Date : 2017-11-01 DOI: 10.1109/ISCMI.2017.8279623

E. Jean-Baptiste, Alex Mihailidis

引用次数: 5

Change reaction strategies for DNSGA-II solving dynamic multi-objective optimization problems DNSGA-II求解动态多目标优化问题的变化反应策略

2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI) Pub Date : 2017-11-01 DOI: 10.1109/ISCMI.2017.8279596

Mardé Helbig

{"title":"Change reaction strategies for DNSGA-II solving dynamic multi-objective optimization problems","authors":"Mardé Helbig","doi":"10.1109/ISCMI.2017.8279596","DOIUrl":"https://doi.org/10.1109/ISCMI.2017.8279596","url":null,"abstract":"Many real world optimization problems have multiple objectives that typically are in conflict with one another. Furthermore, at least one objective can even be dynamic. If all of these traits are present, the problem is called a dynamic multi-objective optimisation problems (DMOOPs). The non-dominated sorting genetic algorithm II (NSGA-II) is a standard or benchmark algorithm for static multi-objective optimization problems (MOOPs) that has been extended to solve DMOOPs. Once a change has been detected, an algorithm has to react appropriately, to ensure enough diversity in the population to search for new optimal solutions after the change has occurred. However, the algorithm still has to balance exploration and exploitation. Therefore, this paper investigates four change reaction strategies that introduce new diversity into the population of the dynamic non-dominated sorting genetic algorithm II (DNSGA-II) after a change in the environment has occurred. The results indicate that all strategies that only inject diversity through changing a portion of the population (and not the entire population) performed well. When the whole population was changed, the performance of DNSGA-II deteriorated.","PeriodicalId":119111,"journal":{"name":"2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"88 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131578840","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

Adaptive SSP forecast and memory reclamation using belief nets 基于信念网的自适应SSP预测与记忆回收

2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI) Pub Date : 2017-11-01 DOI: 10.1109/ISCMI.2017.8279621

Hemant Tiwari, Vanraj Vala

引用次数: 1

Applying machine learning to big data streams : An overview of challenges 将机器学习应用于大数据流:挑战概述

2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI) Pub Date : 2017-11-01 DOI: 10.1109/ISCMI.2017.8279592

Christoph Augenstein, N. Spangenberg, Bogdan Franczyk

引用次数: 15

Research articles suggestion using topic modelling 研究文章建议采用主题建模

2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI) Pub Date : 2017-11-01 DOI: 10.1109/ISCMI.2017.8279622

V. Chaitanya, P. Singh

{"title":"Research articles suggestion using topic modelling","authors":"V. Chaitanya, P. Singh","doi":"10.1109/ISCMI.2017.8279622","DOIUrl":"https://doi.org/10.1109/ISCMI.2017.8279622","url":null,"abstract":"Searching research articles effectively is significantly important to researchers. Currently, researchers use search engines like Google Scholar and search by keywords. The typical search result includes a lot of articles which match the keywords exactly; however, they are on many different topics. It is very time and effort consuming to go through the articles manually and select desirable ones. We propose a method to search articles by topics. Our method trains on a large set of articles and analyzes every article in it to generate its distribution over topics. The method recommends articles to the researcher by analyzing the input given by her/him and comparing with the topic distribution of all articles in the training set. The articles with most similar distributions are recommended to the researcher. In this way, articles are recommended by matching by topics rather than keywords. Our experimental results are analyzed using Mean average precision (MAP) and Normalized Discounted Cumulative Gain (NDCG). The obtained results demonstrate that our method successfully extracts the topics beneath the words of an article and recommend closely related ones.","PeriodicalId":119111,"journal":{"name":"2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131536697","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: 3

Variation of ant colony optimization parameters for solving the travelling salesman problem 求解旅行商问题的蚁群优化参数变化

2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI) Pub Date : 2017-11-01 DOI: 10.1109/ISCMI.2017.8279598

Pui Yue Cheong, Deepak Aggarwal, T. Hanne, Rolf Dornberger

引用次数: 11

A large-scale filter method for feature selection based on spark 一种基于spark的大规模特征选择滤波方法

2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI) Pub Date : 2017-11-01 DOI: 10.1109/ISCMI.2017.8279590

Reine Marie Ndéla Marone, Fodé Camara, S. Ndiaye

引用次数: 1

Printed thai character segmentation and recognition 打印的泰文字符分割和识别

2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI) Pub Date : 2017-11-01 DOI: 10.1109/ISCMI.2017.8279611

P. Chomphuwiset

引用次数: 5

Feature selection for an SVM based webpage classifier 基于SVM的网页分类器特征选择

2017 IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI) Pub Date : 2017-11-01 DOI: 10.1109/ISCMI.2017.8279603

Nhamo Mtetwa, M. Yousefi, V. Reddy

引用次数: 6