This paper presents the research results found for the utilization of a Genetic Algorithm (GA) technique in evolving a set of Artificial Neural Networks (ANNs) weights which functions as controller in deciding what type of unit that should be spawned for winning against the opponent in a RTS game called War craft 3 (custom map). The elitism concept is applied during the optimization processes in order to avoid losing good solutions. The experimentation results show clearly a group of mixed randomized opponent can be defeated by the generated AI army. Hence, it is proof that GA is capable to act as a tuning technique in generating the required controllers in RTS game. Furthermore, the neural controllers generated are able to decide the best group of army used in defeating the opponent.
{"title":"Evolving Neural Controllers Using GA for Warcraft 3-Real Time Strategy Game","authors":"Chang Kee Tong, C. K. On, J. Teo, A. Kiring","doi":"10.1109/BIC-TA.2011.70","DOIUrl":"https://doi.org/10.1109/BIC-TA.2011.70","url":null,"abstract":"This paper presents the research results found for the utilization of a Genetic Algorithm (GA) technique in evolving a set of Artificial Neural Networks (ANNs) weights which functions as controller in deciding what type of unit that should be spawned for winning against the opponent in a RTS game called War craft 3 (custom map). The elitism concept is applied during the optimization processes in order to avoid losing good solutions. The experimentation results show clearly a group of mixed randomized opponent can be defeated by the generated AI army. Hence, it is proof that GA is capable to act as a tuning technique in generating the required controllers in RTS game. Furthermore, the neural controllers generated are able to decide the best group of army used in defeating the opponent.","PeriodicalId":211822,"journal":{"name":"2011 Sixth International Conference on Bio-Inspired Computing: Theories and Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130007904","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}
Global Positioning System technology has been widely utilized for various applications. Nevertheless, it only performs accurately in outdoor environment. Thus, Local Positioning System has been introduced specifically to determine position in indoor environment. The aim of this research is to evaluate the performance of a Local Positioning System structure with the implementation of Cosine Correlation Similarity Measure. The area use for this research is at floor level 1, Kolej Teknologi 5 building, German Malaysian Institute (GMI), Malaysia. Similarity measure is implemented to act as a decision support system for the positioning system. The performance of the system will be evaluated in term of its accuracy, level of complexity, scalability and cost. The online testing of this research reveals that 73% accuracy achieved within 7 meter of the system. The complexity is at medium level compared with previous research. The scalability level is low, while the setup cost is consider very low. As a conclusion, this research has successfully introduced and evaluates the performance of the Cosine Correlation Similarity Measure as a decision support system for Local Positioning System.
{"title":"Local Positioning System Performance Evaluation with Cosine Correlation Similarity Measure","authors":"S. Ali, R. Hassan","doi":"10.1109/BIC-TA.2011.20","DOIUrl":"https://doi.org/10.1109/BIC-TA.2011.20","url":null,"abstract":"Global Positioning System technology has been widely utilized for various applications. Nevertheless, it only performs accurately in outdoor environment. Thus, Local Positioning System has been introduced specifically to determine position in indoor environment. The aim of this research is to evaluate the performance of a Local Positioning System structure with the implementation of Cosine Correlation Similarity Measure. The area use for this research is at floor level 1, Kolej Teknologi 5 building, German Malaysian Institute (GMI), Malaysia. Similarity measure is implemented to act as a decision support system for the positioning system. The performance of the system will be evaluated in term of its accuracy, level of complexity, scalability and cost. The online testing of this research reveals that 73% accuracy achieved within 7 meter of the system. The complexity is at medium level compared with previous research. The scalability level is low, while the setup cost is consider very low. As a conclusion, this research has successfully introduced and evaluates the performance of the Cosine Correlation Similarity Measure as a decision support system for Local Positioning System.","PeriodicalId":211822,"journal":{"name":"2011 Sixth International Conference on Bio-Inspired Computing: Theories and Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120961841","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}
Multi-robot foraging systems can assist human beings to collect crops or minerals, efficiently. As being wider searching spaces, the robot control system demands scalability and reliability. For handling this limitation, in particular, swarm robotics has been considered due to its strengths such as self-organization, robustness and flexibility. However, it stipulates high initial, operating cost as employing the multi-robot foraging system. To address these drawbacks, this paper presents a novel distributed foraging mechanism. The aim is to adopt a new behavioral model regarding role division and search space division for improving energy efficiency. Simulation results demonstrate that the proposed approach outperforms an existing foraging robot system.
{"title":"Improving Energy Efficiency in Cooperative Foraging Swarm Robots Using Behavioral Model","authors":"Jong-Hyun Lee, C. Ahn","doi":"10.1109/BIC-TA.2011.69","DOIUrl":"https://doi.org/10.1109/BIC-TA.2011.69","url":null,"abstract":"Multi-robot foraging systems can assist human beings to collect crops or minerals, efficiently. As being wider searching spaces, the robot control system demands scalability and reliability. For handling this limitation, in particular, swarm robotics has been considered due to its strengths such as self-organization, robustness and flexibility. However, it stipulates high initial, operating cost as employing the multi-robot foraging system. To address these drawbacks, this paper presents a novel distributed foraging mechanism. The aim is to adopt a new behavioral model regarding role division and search space division for improving energy efficiency. Simulation results demonstrate that the proposed approach outperforms an existing foraging robot system.","PeriodicalId":211822,"journal":{"name":"2011 Sixth International Conference on Bio-Inspired Computing: Theories and Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121341547","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}
In this paper we introduce an infinite array with diminishing cells and study some of their combinatorial properties. We call this array as Dr array. A code space can be reorganized in an endless variety of amazing geometrical and topological ways to form sets that look like leaves, ferns, cells, flowers and so on. For this we introduce a complete metric in Dr array. We note that this space is in fact compact. Also certain properties of Dr array are obtained.
{"title":"A Study on Diminishing Cells Infinite Array","authors":"N. Jansirani, V. Dare","doi":"10.1109/BIC-TA.2011.48","DOIUrl":"https://doi.org/10.1109/BIC-TA.2011.48","url":null,"abstract":"In this paper we introduce an infinite array with diminishing cells and study some of their combinatorial properties. We call this array as Dr array. A code space can be reorganized in an endless variety of amazing geometrical and topological ways to form sets that look like leaves, ferns, cells, flowers and so on. For this we introduce a complete metric in Dr array. We note that this space is in fact compact. Also certain properties of Dr array are obtained.","PeriodicalId":211822,"journal":{"name":"2011 Sixth International Conference on Bio-Inspired Computing: Theories and Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128055062","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}
S. Bharathi, J. Padmashree, S. Selvi, K. Thiagarajan
Our main result is to correlate the graph splicing scheme of Rudolf Freund with semi graphs introduced by E. Sampathkumar [10]. We get characterization of DNA structure after splicing in terms of semi graph to show some splicing graph properties. In this paper, we introduce semi graph folding for the DNA splicing system and show that any n-cut spliced semi graph (n ? 1) can be folded onto an edge and two semi edges at the maximum of four semi graph folding.
{"title":"Semigraph Structure on DNA Splicing System","authors":"S. Bharathi, J. Padmashree, S. Selvi, K. Thiagarajan","doi":"10.1109/BIC-TA.2011.26","DOIUrl":"https://doi.org/10.1109/BIC-TA.2011.26","url":null,"abstract":"Our main result is to correlate the graph splicing scheme of Rudolf Freund with semi graphs introduced by E. Sampathkumar [10]. We get characterization of DNA structure after splicing in terms of semi graph to show some splicing graph properties. In this paper, we introduce semi graph folding for the DNA splicing system and show that any n-cut spliced semi graph (n ? 1) can be folded onto an edge and two semi edges at the maximum of four semi graph folding.","PeriodicalId":211822,"journal":{"name":"2011 Sixth International Conference on Bio-Inspired Computing: Theories and Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132462442","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}
Research results have confirmed that some reasonable solution for NP-complete problem could be achieved using DNA self-assembly model, in which the ability of molecular computing to perform complicated mathematical operations could be get a full play. In this paper, the DNA self-assembly model for the bin packing problem is constructed. This model is composed of two units: grouping based on binary method and subtraction system. The great advantage of our schema is that it only needs a constant number of DNA tile types and in time linear with the size of the items to solve any bin packing problem. This work demonstrates further evidence for the ability of DNA tiles to solve other NP-complete problems.
{"title":"DNA Tile Assembly Model for Bin Packing Problem","authors":"Yanfeng Wang, Weili Lu, Guangzhao Cui","doi":"10.1109/BIC-TA.2011.35","DOIUrl":"https://doi.org/10.1109/BIC-TA.2011.35","url":null,"abstract":"Research results have confirmed that some reasonable solution for NP-complete problem could be achieved using DNA self-assembly model, in which the ability of molecular computing to perform complicated mathematical operations could be get a full play. In this paper, the DNA self-assembly model for the bin packing problem is constructed. This model is composed of two units: grouping based on binary method and subtraction system. The great advantage of our schema is that it only needs a constant number of DNA tile types and in time linear with the size of the items to solve any bin packing problem. This work demonstrates further evidence for the ability of DNA tiles to solve other NP-complete problems.","PeriodicalId":211822,"journal":{"name":"2011 Sixth International Conference on Bio-Inspired Computing: Theories and Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125051262","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}
Yuquan Li, Gexiang Zhang, Xiangxiang Zeng, Jixiang Cheng, M. Gheorghe, Susan Elias
Estimation of distribution algorithms (EDAs) is a class of probabilistic model-building evolutionary algorithms, which is characterized by learning and sampling the probability distribution of the selected individuals. This paper proposes a modified estimation of distribution algorithm (mEDA) for numeric optimization. mEDA uses a novel sampling method, called centro-individual sampling, and a fuzzy c-means clustering technique to improve its performance. Extensive experiments conducted on a set of benchmark functions show that mEDA outperforms HPBILc, CEGDA, CEGNABGe and NichingEDA, reported in the literature, in terms of the quality of solutions.
{"title":"A Modified Estimation of Distribution Algorithm for Numeric Optimization","authors":"Yuquan Li, Gexiang Zhang, Xiangxiang Zeng, Jixiang Cheng, M. Gheorghe, Susan Elias","doi":"10.1109/BIC-TA.2011.14","DOIUrl":"https://doi.org/10.1109/BIC-TA.2011.14","url":null,"abstract":"Estimation of distribution algorithms (EDAs) is a class of probabilistic model-building evolutionary algorithms, which is characterized by learning and sampling the probability distribution of the selected individuals. This paper proposes a modified estimation of distribution algorithm (mEDA) for numeric optimization. mEDA uses a novel sampling method, called centro-individual sampling, and a fuzzy c-means clustering technique to improve its performance. Extensive experiments conducted on a set of benchmark functions show that mEDA outperforms HPBILc, CEGDA, CEGNABGe and NichingEDA, reported in the literature, in terms of the quality of solutions.","PeriodicalId":211822,"journal":{"name":"2011 Sixth International Conference on Bio-Inspired Computing: Theories and Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131104303","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}
Artificial Bee Colony (ABC) algorithm is an optimization algorithm based on the intelligent behaviour of honey bee swarm. ABC can be initialized with either a uniform or a non-uniform distribution. The decision regarding which to use depends on how much is known about the location of the optimum. Generally uniform distributions are preferred since they best reflect the lack of knowledge about the optimum's location. In this paper we have used Halton points for the initial distribution and compared the simulation results with rand (0,1) uniform distribution. Further the algorithm is a used to estimate the cost model parameters and than the performance is compared with the measured efforts on the NASA Software project dataset
{"title":"Halton Based Initial Distribution in Artificial Bee Colony Algorithm and Its Application in Software Effort Estimation","authors":"T. Sharma, M. Pant","doi":"10.4018/jncr.2012040105","DOIUrl":"https://doi.org/10.4018/jncr.2012040105","url":null,"abstract":"Artificial Bee Colony (ABC) algorithm is an optimization algorithm based on the intelligent behaviour of honey bee swarm. ABC can be initialized with either a uniform or a non-uniform distribution. The decision regarding which to use depends on how much is known about the location of the optimum. Generally uniform distributions are preferred since they best reflect the lack of knowledge about the optimum's location. In this paper we have used Halton points for the initial distribution and compared the simulation results with rand (0,1) uniform distribution. Further the algorithm is a used to estimate the cost model parameters and than the performance is compared with the measured efforts on the NASA Software project dataset","PeriodicalId":211822,"journal":{"name":"2011 Sixth International Conference on Bio-Inspired Computing: Theories and Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122222900","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}
M. Awadallah, A. Khader, M. Al-Betar, Asaju La'aro Bolaji
In this research an adaption of Harmony Search Algorithm (HSA) for Nurse Scheduling Problem (NSP) is presented. Nurse scheduling problem is a task of assigning shifts to nurses for the duties that have to carry out. The difficulty of handling this problem is due to the high number of constraints to be satisfied. Thus, we are proposing an adaptation of HSA i.e. a new population-based metaheuristic algorithm that mimics the musical improvisation process which has been successfully applied for wide range of optimisation problems. The performance of HAS is evaluated using datasets established by International Nurse Rostering Competition 2010 (INRC2010). The results obtained were compared with the best results reported in the competition. The results show that the proposed method can compete well in comparison with those reported results.
{"title":"Nurse Scheduling Using Harmony Search","authors":"M. Awadallah, A. Khader, M. Al-Betar, Asaju La'aro Bolaji","doi":"10.1109/BIC-TA.2011.75","DOIUrl":"https://doi.org/10.1109/BIC-TA.2011.75","url":null,"abstract":"In this research an adaption of Harmony Search Algorithm (HSA) for Nurse Scheduling Problem (NSP) is presented. Nurse scheduling problem is a task of assigning shifts to nurses for the duties that have to carry out. The difficulty of handling this problem is due to the high number of constraints to be satisfied. Thus, we are proposing an adaptation of HSA i.e. a new population-based metaheuristic algorithm that mimics the musical improvisation process which has been successfully applied for wide range of optimisation problems. The performance of HAS is evaluated using datasets established by International Nurse Rostering Competition 2010 (INRC2010). The results obtained were compared with the best results reported in the competition. The results show that the proposed method can compete well in comparison with those reported results.","PeriodicalId":211822,"journal":{"name":"2011 Sixth International Conference on Bio-Inspired Computing: Theories and Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115840045","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}
Distillations column control becomes the main subject of control research due to the intensive energy usage in the industry and the nonlinearity behavior in control variables. The growing importance of "green technology" and sustainability has triggered researchers to focus on this matter. Therefore, a method of modeling and controlling of the column is certainly indispensible in this matter. Neural networks are a powerful tool especially in modeling nonlinear and intricate process. Hence, in this paper Feed forward Artificial Neural network (FANN) have been chosen to model the multiple input-single output (MISO) for the distillation column predicting top and bottom composition. The performance and the accuracy of the models have been presented in term of correlation coefficient (R value) and the smallest sum squared error (SSE). It has been found that FANN can model MISO in representing the process. The results obtained also show that the MISO model is suitable to be used to represent the distillation process accurately.
{"title":"Multiple Input-Single Output (MISO) Feedforward Artificial Neural Network (FANN) Models for Pilot Plant Binary Distillation Column","authors":"Z. Abdullah, Z. Ahmad, N. Aziz","doi":"10.1109/BIC-TA.2011.21","DOIUrl":"https://doi.org/10.1109/BIC-TA.2011.21","url":null,"abstract":"Distillations column control becomes the main subject of control research due to the intensive energy usage in the industry and the nonlinearity behavior in control variables. The growing importance of \"green technology\" and sustainability has triggered researchers to focus on this matter. Therefore, a method of modeling and controlling of the column is certainly indispensible in this matter. Neural networks are a powerful tool especially in modeling nonlinear and intricate process. Hence, in this paper Feed forward Artificial Neural network (FANN) have been chosen to model the multiple input-single output (MISO) for the distillation column predicting top and bottom composition. The performance and the accuracy of the models have been presented in term of correlation coefficient (R value) and the smallest sum squared error (SSE). It has been found that FANN can model MISO in representing the process. The results obtained also show that the MISO model is suitable to be used to represent the distillation process accurately.","PeriodicalId":211822,"journal":{"name":"2011 Sixth International Conference on Bio-Inspired Computing: Theories and Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115596456","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：