Pub Date : 2020-01-01DOI: 10.1109/CEC48606.2020.9185578
Okkes Tolga Altinöz
{"title":"Modeling of synchronous weapon target assignment problem for howitzer based defense line","authors":"Okkes Tolga Altinöz","doi":"10.1109/CEC48606.2020.9185578","DOIUrl":"https://doi.org/10.1109/CEC48606.2020.9185578","url":null,"abstract":"","PeriodicalId":6344,"journal":{"name":"2009 IEEE Congress on Evolutionary Computation","volume":"21 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81559467","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}
Pub Date : 2020-01-01DOI: 10.1109/CEC48606.2020.9185903
Nicolas Poiron-Guidoni, P. Bisgambiglia
{"title":"A probabilistic optimization approach to deal with uncertainties in model calibration","authors":"Nicolas Poiron-Guidoni, P. Bisgambiglia","doi":"10.1109/CEC48606.2020.9185903","DOIUrl":"https://doi.org/10.1109/CEC48606.2020.9185903","url":null,"abstract":"","PeriodicalId":6344,"journal":{"name":"2009 IEEE Congress on Evolutionary Computation","volume":"34 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85404843","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}
Pub Date : 2019-06-10DOI: 10.1109/CEC.2019.8790262
Zhang Yushan, Huang Han, Hao Zhifeng, Hong Zhou
The pigeon-inspired optimization (PIO) algorithm is a novel swarm intelligence optimizer inspired by the homing behaviors of pigeons. Although PIO has demonstrated effectiveness and superiority in numerous fields, there are few results about the theoretical foundation of PIO. This paper employs the average gain model to estimate the upper bound for the expected first hitting time of PIO in continuous optimization. The case study and experiment result indicate that our theoretical analysis is applicable to the general case where the population size and problem size are both larger than 1, which is close to the practical situation.
{"title":"Runtime Analysis of Pigeon-Inspired Optimizer Based on Average Gain Model","authors":"Zhang Yushan, Huang Han, Hao Zhifeng, Hong Zhou","doi":"10.1109/CEC.2019.8790262","DOIUrl":"https://doi.org/10.1109/CEC.2019.8790262","url":null,"abstract":"The pigeon-inspired optimization (PIO) algorithm is a novel swarm intelligence optimizer inspired by the homing behaviors of pigeons. Although PIO has demonstrated effectiveness and superiority in numerous fields, there are few results about the theoretical foundation of PIO. This paper employs the average gain model to estimate the upper bound for the expected first hitting time of PIO in continuous optimization. The case study and experiment result indicate that our theoretical analysis is applicable to the general case where the population size and problem size are both larger than 1, which is close to the practical situation.","PeriodicalId":6344,"journal":{"name":"2009 IEEE Congress on Evolutionary Computation","volume":"33 1","pages":"1165-1169"},"PeriodicalIF":0.0,"publicationDate":"2019-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89978716","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}
Pub Date : 2019-06-01DOI: 10.1109/CEC.2019.8789956
Douglas Winston Ribeiro Soares, G. Laureano, C. Camilo-Junior
Endmember Extraction is a critical step in hyper-spectral unmixing and classification providing the basis to applications such as identification of minerals [1], vegetation analysis [2], geographical survey [3] and others [4] [5]. It determines the basic constituent materials contained in the image while providing the requirements to the abundance inversion process, used to obtain the percentage of several endmembers in each pixel. Nevertheless, low spatial resolution and computing time are two major difficulties, the first due to the spatial interactions of different fractions of mixed endmembers and the second due to the strict and extensive search utilized in state-of-the-art methods. In this paper, we propose a novel endmember extractor, so-called GAEEII, based on a multi epochs genetic algorithm with enhancements to the naive genetic algorithm endmember extractor (GAEE). We introduce the following additions to the GAEE: a two-dimensional gene initialization, a permutation crossover, a 2D step Gaussian mutation, and an epoch ensemble. To demonstrate the superiority of our proposed method, we conduct extensive experiments on several well-known real and synthetic datasets, as well as a possible relation to the spectral angle distance (SAD) and the volume of the simplex. The results confirm that the proposed method considerably improves the performance in accuracy and computing time compared to the state-of-the-art techniques in the literature including recent developments.
{"title":"GAEEII: An Optimised Genetic Algorithm Endmember Extractor for Hyperspectral Unmixing","authors":"Douglas Winston Ribeiro Soares, G. Laureano, C. Camilo-Junior","doi":"10.1109/CEC.2019.8789956","DOIUrl":"https://doi.org/10.1109/CEC.2019.8789956","url":null,"abstract":"Endmember Extraction is a critical step in hyper-spectral unmixing and classification providing the basis to applications such as identification of minerals [1], vegetation analysis [2], geographical survey [3] and others [4] [5]. It determines the basic constituent materials contained in the image while providing the requirements to the abundance inversion process, used to obtain the percentage of several endmembers in each pixel. Nevertheless, low spatial resolution and computing time are two major difficulties, the first due to the spatial interactions of different fractions of mixed endmembers and the second due to the strict and extensive search utilized in state-of-the-art methods. In this paper, we propose a novel endmember extractor, so-called GAEEII, based on a multi epochs genetic algorithm with enhancements to the naive genetic algorithm endmember extractor (GAEE). We introduce the following additions to the GAEE: a two-dimensional gene initialization, a permutation crossover, a 2D step Gaussian mutation, and an epoch ensemble. To demonstrate the superiority of our proposed method, we conduct extensive experiments on several well-known real and synthetic datasets, as well as a possible relation to the spectral angle distance (SAD) and the volume of the simplex. The results confirm that the proposed method considerably improves the performance in accuracy and computing time compared to the state-of-the-art techniques in the literature including recent developments.","PeriodicalId":6344,"journal":{"name":"2009 IEEE Congress on Evolutionary Computation","volume":"7 1","pages":"2386-2393"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82069141","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}
Pub Date : 2019-06-01DOI: 10.1109/CEC.2019.8790034
Huynh Thi Thanh Binh, N. Q. Tuan, Doan Cao Thanh Long
In recent years, multi-task optimization is one of the emerging topics among evolutionary computation researchers. Multi-Factorial Evolutionary Algorithm (MFEA) is developed based on that individuals, from various cultures, exchange their underlying similarities to improve the convergence characteristic. However, in terms of Multi-Objective Multi-Factorial Optimization (MOMFO), current algorithms employing nondominated front ranking and crowding distance still meet difficulties when the number of objective functions arises. In this paper, we propose a Muli-Objective Multi-Factorial Evolutionary Algorithm (MO-MFEA) with reference-point-based approach to improve the multitasking framework. Rather than using crowding distance to compute individual ranking in the context of MOMFO, we employ a set of reference points to determine the diversity of current population. On the other hand, we improve the guided method that automatically adapt the Random Mating Probability (RMP) in order to exploit shared knowledge among high similar task. Further improvement on genetic operators with JADE crossover and NSLS. The conducted experiments demonstrate our approach performs better than the baseline results.
{"title":"A multi-objective multi-factorial evolutionary algorithm with reference-point-based approach","authors":"Huynh Thi Thanh Binh, N. Q. Tuan, Doan Cao Thanh Long","doi":"10.1109/CEC.2019.8790034","DOIUrl":"https://doi.org/10.1109/CEC.2019.8790034","url":null,"abstract":"In recent years, multi-task optimization is one of the emerging topics among evolutionary computation researchers. Multi-Factorial Evolutionary Algorithm (MFEA) is developed based on that individuals, from various cultures, exchange their underlying similarities to improve the convergence characteristic. However, in terms of Multi-Objective Multi-Factorial Optimization (MOMFO), current algorithms employing nondominated front ranking and crowding distance still meet difficulties when the number of objective functions arises. In this paper, we propose a Muli-Objective Multi-Factorial Evolutionary Algorithm (MO-MFEA) with reference-point-based approach to improve the multitasking framework. Rather than using crowding distance to compute individual ranking in the context of MOMFO, we employ a set of reference points to determine the diversity of current population. On the other hand, we improve the guided method that automatically adapt the Random Mating Probability (RMP) in order to exploit shared knowledge among high similar task. Further improvement on genetic operators with JADE crossover and NSLS. The conducted experiments demonstrate our approach performs better than the baseline results.","PeriodicalId":6344,"journal":{"name":"2009 IEEE Congress on Evolutionary Computation","volume":"65 1","pages":"2824-2831"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86029798","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}
Pub Date : 2018-07-08DOI: 10.1109/CEC.2018.8477912
Huynh Thi Thanh Binh, Pham Dinh Thanh, Tran Ba Trung, Le Phuong Thao
Arising from the need of all time for optimization of irrigation systems, distribution network and cable network, the Cluster Shortest Path Tree Problem (CSTP) has been attracting a lot of attention and interest from the research community. For such an NP-Hard problem with a great dimensionality, the approximation approach is usually taken. Evolutionary Algorithms, based on biological evolution, has been proved to be effective in finding approximate solutions to problems of various fields. The multifactorial evolutionary algorithm (MFEA) is one of the most recently exploited realms of EAs and its performance in solving optimization problems has been very promising. The main difference between the MFEA and the traditional Genetic Algorithm (GA) is that the former can solve multiple tasks at the same time and take advantage of implicit genetic transfer in a multitasking problem, while the latter solves one problem and exploit one search space at a time. Considering these characteristics, this paper proposes a MFEA for CSTP tasks, together with novel genetic operators: population initialization, crossover, and mutation operators. Furthermore, a novel decoding scheme for deriving factorial solutions from the unified representation in the MFEA, which is the key factor to the performance of any variant of the MFEA, is also introduced in this paper. For examining the efficiency of the proposed techniques, experiments on a wide range of diverse sets of instances were implemented and the results showed that the proposed algorithms outperformed an existing heuristic algorithm for most of the testing cases. In the experimental results section, we also pointed out which cases allowed for a good performance of the proposed algorithm.
{"title":"Effective Multifactorial Evolutionary Algorithm for Solving the Cluster Shortest Path Tree Problem","authors":"Huynh Thi Thanh Binh, Pham Dinh Thanh, Tran Ba Trung, Le Phuong Thao","doi":"10.1109/CEC.2018.8477912","DOIUrl":"https://doi.org/10.1109/CEC.2018.8477912","url":null,"abstract":"Arising from the need of all time for optimization of irrigation systems, distribution network and cable network, the Cluster Shortest Path Tree Problem (CSTP) has been attracting a lot of attention and interest from the research community. For such an NP-Hard problem with a great dimensionality, the approximation approach is usually taken. Evolutionary Algorithms, based on biological evolution, has been proved to be effective in finding approximate solutions to problems of various fields. The multifactorial evolutionary algorithm (MFEA) is one of the most recently exploited realms of EAs and its performance in solving optimization problems has been very promising. The main difference between the MFEA and the traditional Genetic Algorithm (GA) is that the former can solve multiple tasks at the same time and take advantage of implicit genetic transfer in a multitasking problem, while the latter solves one problem and exploit one search space at a time. Considering these characteristics, this paper proposes a MFEA for CSTP tasks, together with novel genetic operators: population initialization, crossover, and mutation operators. Furthermore, a novel decoding scheme for deriving factorial solutions from the unified representation in the MFEA, which is the key factor to the performance of any variant of the MFEA, is also introduced in this paper. For examining the efficiency of the proposed techniques, experiments on a wide range of diverse sets of instances were implemented and the results showed that the proposed algorithms outperformed an existing heuristic algorithm for most of the testing cases. In the experimental results section, we also pointed out which cases allowed for a good performance of the proposed algorithm.","PeriodicalId":6344,"journal":{"name":"2009 IEEE Congress on Evolutionary Computation","volume":"21 4 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2018-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78450763","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}
Pub Date : 2018-07-01DOI: 10.1109/CEC.2018.8477841
M. M. P. Silva, C. S. Magalhães
Beehive Hidato is a fill-in logic puzzle, similar to Sudoku, with hexagonal grid cells. Some hexagons are pre-filled with fixed numbers, while the remaining has to be filled by the player such that consecutive numbers stay connected to form a “path”, from 1 to n, the largest number in the grid. Each Hidato problem has only one correct answer and, despite its simple rules, finding the solution for these problems can be quite challenging. In this work, we analyzed the importance of diversity preservation, as well as, the influence of commonly used permutation genetic operators in a simple genetic algorithm (GA) for solving Beehive Hidato problems. The algorithm was evaluated on 21 instances of Beehive Hidato problems, with different complexity levels, divided into two classes according to its size. We found PMX crossover and swap mutation as the best operators among the ones tested. Apart from that, the results indicate that the use of a diversity preservation technique has a significant role in GA performance, mainly for solving larger problem instances.
{"title":"Can Simple GAs Solve Beehive Hidato Logic Puzzles? The Influence of Diversity Preservation and Genetic Operators","authors":"M. M. P. Silva, C. S. Magalhães","doi":"10.1109/CEC.2018.8477841","DOIUrl":"https://doi.org/10.1109/CEC.2018.8477841","url":null,"abstract":"Beehive Hidato is a fill-in logic puzzle, similar to Sudoku, with hexagonal grid cells. Some hexagons are pre-filled with fixed numbers, while the remaining has to be filled by the player such that consecutive numbers stay connected to form a “path”, from 1 to n, the largest number in the grid. Each Hidato problem has only one correct answer and, despite its simple rules, finding the solution for these problems can be quite challenging. In this work, we analyzed the importance of diversity preservation, as well as, the influence of commonly used permutation genetic operators in a simple genetic algorithm (GA) for solving Beehive Hidato problems. The algorithm was evaluated on 21 instances of Beehive Hidato problems, with different complexity levels, divided into two classes according to its size. We found PMX crossover and swap mutation as the best operators among the ones tested. Apart from that, the results indicate that the use of a diversity preservation technique has a significant role in GA performance, mainly for solving larger problem instances.","PeriodicalId":6344,"journal":{"name":"2009 IEEE Congress on Evolutionary Computation","volume":"78 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79992697","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}
Pub Date : 2018-07-01DOI: 10.1109/CEC.2018.8477864
L. M. Pascoal, H. A. D. D. Nascimento, C. Camilo-Junior, Edialma Queiroz da Silva, E. L. Aleixo, Thierson Couto
The analysis of affinity or similarity between people is an important task in the study of social dynamics. Traditional methods for determining similarity depends on considerable amount of data regarding people's preferences and features. Those methods present limitations when the data is scarce and/or changes constantly. This paper introduces a new method for determining people similarity that does not suffer from the same problems. The method can learn a customized similarity function based on social variables of friends that attend the same events (concerts, parties, conferences etc), collected from social networks. Two types of optimization algorithms for learning a similarity function are presented: The universal function approximator modelling, which relays on the relationship of social attributes and a friends' importance ranking; and the populational evolutionary modelling, which linearly combines social variables. Both models were tested in a generalist and in a specialist approach. The results show that the specialist approach exceeded in almost 38 % the generalist approach using populational evolutionary methods and in almost 69 % when using the universal function approximator methods. Among the implemented optimization algorithms employed inside the methods for learning similarity, Genetic Algorithm and Particle Swarm Optimization presented better performance for the populational evolutionary methods and the Artificial Neural Network presented the best performance overall using the universal function approximator modelling.
{"title":"Using Social Information to Compose a Similarity Function Based on Friends Attendance at Events","authors":"L. M. Pascoal, H. A. D. D. Nascimento, C. Camilo-Junior, Edialma Queiroz da Silva, E. L. Aleixo, Thierson Couto","doi":"10.1109/CEC.2018.8477864","DOIUrl":"https://doi.org/10.1109/CEC.2018.8477864","url":null,"abstract":"The analysis of affinity or similarity between people is an important task in the study of social dynamics. Traditional methods for determining similarity depends on considerable amount of data regarding people's preferences and features. Those methods present limitations when the data is scarce and/or changes constantly. This paper introduces a new method for determining people similarity that does not suffer from the same problems. The method can learn a customized similarity function based on social variables of friends that attend the same events (concerts, parties, conferences etc), collected from social networks. Two types of optimization algorithms for learning a similarity function are presented: The universal function approximator modelling, which relays on the relationship of social attributes and a friends' importance ranking; and the populational evolutionary modelling, which linearly combines social variables. Both models were tested in a generalist and in a specialist approach. The results show that the specialist approach exceeded in almost 38 % the generalist approach using populational evolutionary methods and in almost 69 % when using the universal function approximator methods. Among the implemented optimization algorithms employed inside the methods for learning similarity, Genetic Algorithm and Particle Swarm Optimization presented better performance for the populational evolutionary methods and the Artificial Neural Network presented the best performance overall using the universal function approximator modelling.","PeriodicalId":6344,"journal":{"name":"2009 IEEE Congress on Evolutionary Computation","volume":"52 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76654849","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}
Pub Date : 2018-07-01DOI: 10.1109/CEC.2018.8477690
Maicon Douglas Santos Matos, Laurence Rodrigues do Amaral
Genetic Algorithms (GAs) are computational search methods based on Darwin's evolutionary theory. In the present study, the MDRGA (Multiple Disjunctions Rule Genetic Algorithm) is proposed as a tool to induce non-linear IF-THEN classification rules from non-linear datasets, which can be used as a classification system. The main goal of MDRGA is to allow the discovery of concise, yet accurate, non-linear high-level IF-THEN rules balancing prediction precision, comprehensibility and interpretability. The results show that the MDRGA is promising and capable of extracting useful high-level knowledge with good precision values. The classification accuracy of proposed MDRGA was compared with other GA-based methods (CEE and NLCEE) and traditional classification methods (J48, Random Forest, PART, Naive Bayes and IBK) in four non-linear datasets (Sonar, Diabetes, Iris and Breast-W) downloaded from UCI Machine Learning Repository and the MDRGA obtained the best classification accuracy results for all datasets.
{"title":"Multiple Disjunctions Rule Genetic Algorithm (MDRGA): Inferring Non-Linear IF-THEN Rules in Non-Linear Datasets","authors":"Maicon Douglas Santos Matos, Laurence Rodrigues do Amaral","doi":"10.1109/CEC.2018.8477690","DOIUrl":"https://doi.org/10.1109/CEC.2018.8477690","url":null,"abstract":"Genetic Algorithms (GAs) are computational search methods based on Darwin's evolutionary theory. In the present study, the MDRGA (Multiple Disjunctions Rule Genetic Algorithm) is proposed as a tool to induce non-linear IF-THEN classification rules from non-linear datasets, which can be used as a classification system. The main goal of MDRGA is to allow the discovery of concise, yet accurate, non-linear high-level IF-THEN rules balancing prediction precision, comprehensibility and interpretability. The results show that the MDRGA is promising and capable of extracting useful high-level knowledge with good precision values. The classification accuracy of proposed MDRGA was compared with other GA-based methods (CEE and NLCEE) and traditional classification methods (J48, Random Forest, PART, Naive Bayes and IBK) in four non-linear datasets (Sonar, Diabetes, Iris and Breast-W) downloaded from UCI Machine Learning Repository and the MDRGA obtained the best classification accuracy results for all datasets.","PeriodicalId":6344,"journal":{"name":"2009 IEEE Congress on Evolutionary Computation","volume":"107 4","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72572670","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}
Pub Date : 2018-07-01DOI: 10.1109/CEC.2018.8477951
Guilherme Seidyo Imai Aldeia, F. O. França
Symbolic Regression techniques stand out from other regression analysis tools because of the possibility of generating powerful but yet simple expressions. These simple expressions may be useful in many practical situations in which the practitioner wants to interpret the obtained results, finetune the model, or understand the generating phenomena. Despite this possibility, the current state-of-the-art algorithms for Symbolic Regression usually require a high computational budget while having little guarantees regarding the simplicity of the returned expressions. Recently, a new Data Structure representation for mathematical expressions, called Interaction-Transformation (IT), was introduced together with a search-based algorithm named SymTree that surpassed a subset of the recent Symbolic Regression algorithms and even some state-of-the-art nonlinear regression algorithms, while returning simple expressions as a result. This paper introduces a lightweight tool based on this algorithm, named Lab Assistant. This tool runs on the client-side of any compatible Internet browser with JavaScript. Alongside this tool, two algorithms using the IT representation are introduced. Some experiments are performed in order to show the potential of the Lab Assistant to help practitioners, professors, researchers and students willing to experiment with Symbolic Regression. The results showed that this tool is competent to find the correct expression for many well known Physics and Engineering relations within a reasonable average time frame of a few seconds. This tool opens up lots of possibilities in Symbolic Regression research for low-cost devices to be used in applications where a high-end computer is not available.
{"title":"Lightweight Symbolic Regression with the Interaction - Transformation Representation","authors":"Guilherme Seidyo Imai Aldeia, F. O. França","doi":"10.1109/CEC.2018.8477951","DOIUrl":"https://doi.org/10.1109/CEC.2018.8477951","url":null,"abstract":"Symbolic Regression techniques stand out from other regression analysis tools because of the possibility of generating powerful but yet simple expressions. These simple expressions may be useful in many practical situations in which the practitioner wants to interpret the obtained results, finetune the model, or understand the generating phenomena. Despite this possibility, the current state-of-the-art algorithms for Symbolic Regression usually require a high computational budget while having little guarantees regarding the simplicity of the returned expressions. Recently, a new Data Structure representation for mathematical expressions, called Interaction-Transformation (IT), was introduced together with a search-based algorithm named SymTree that surpassed a subset of the recent Symbolic Regression algorithms and even some state-of-the-art nonlinear regression algorithms, while returning simple expressions as a result. This paper introduces a lightweight tool based on this algorithm, named Lab Assistant. This tool runs on the client-side of any compatible Internet browser with JavaScript. Alongside this tool, two algorithms using the IT representation are introduced. Some experiments are performed in order to show the potential of the Lab Assistant to help practitioners, professors, researchers and students willing to experiment with Symbolic Regression. The results showed that this tool is competent to find the correct expression for many well known Physics and Engineering relations within a reasonable average time frame of a few seconds. This tool opens up lots of possibilities in Symbolic Regression research for low-cost devices to be used in applications where a high-end computer is not available.","PeriodicalId":6344,"journal":{"name":"2009 IEEE Congress on Evolutionary Computation","volume":"15 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78608926","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：