Pub Date : 2016-12-01DOI: 10.1109/SSCI.2016.7849991
I. M. C. Albuquerque, J. M. Filho, Fernando Buarque de Lima-Neto, A. Silva
Assembly lines constitute the main production paradigm of the contemporary manufacturing industry. Thus, many optimization problems have been studied aiming to improve the efficacy of its use. In this context, the problem of balancing an assembly line plays a key role. This problem is of combinatorial nature and also NP-Hard. For this reason, many researchers on computational intelligence and industrial engineering have been conceiving algorithms for tackling many versions of assembly line balancing problems using different procedures. In this paper, the Fish School Search algorithm and a variation of it that incorporates a routine to avoid stagnation of the search process were applied in order to solve the Simple Assembly Line Balancing Problem-type 1. The results were compared with an exact solution procedure named SALOME and also with the Particle Swarm Optimization algorithm. Both proposed procedures were able to achieve good results and the stagnation avoidance routine incorporated to FSS allowed more uniform distributions of tasks among workstations in the assembly line and converged faster to optimal solutions.
{"title":"Solving Assembly Line Balancing Problems with Fish School Search algorithm","authors":"I. M. C. Albuquerque, J. M. Filho, Fernando Buarque de Lima-Neto, A. Silva","doi":"10.1109/SSCI.2016.7849991","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7849991","url":null,"abstract":"Assembly lines constitute the main production paradigm of the contemporary manufacturing industry. Thus, many optimization problems have been studied aiming to improve the efficacy of its use. In this context, the problem of balancing an assembly line plays a key role. This problem is of combinatorial nature and also NP-Hard. For this reason, many researchers on computational intelligence and industrial engineering have been conceiving algorithms for tackling many versions of assembly line balancing problems using different procedures. In this paper, the Fish School Search algorithm and a variation of it that incorporates a routine to avoid stagnation of the search process were applied in order to solve the Simple Assembly Line Balancing Problem-type 1. The results were compared with an exact solution procedure named SALOME and also with the Particle Swarm Optimization algorithm. Both proposed procedures were able to achieve good results and the stagnation avoidance routine incorporated to FSS allowed more uniform distributions of tasks among workstations in the assembly line and converged faster to optimal solutions.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129943294","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 : 2016-12-01DOI: 10.1109/SSCI.2016.7850074
J. Rhinelander
Side-scan sonar technology has been used over the last three decades for underwater surveying and imaging. Application areas of side-scan sonar include archaeology, security and defence, seabed classification, and environmental surveying. In recent years the use of autonomous underwater systems has allowed for automatic collection of data. Along with automatic collection of data comes the need to automatically detect what information is important. Automatic target recognition can allow for efficient task planning and autonomous system deployment for security and defence applications. Support Vector Machines (SVMs) are proven general purpose methods for pattern classification. They provide maximum margin classification that does not over fit to training data. It is generally accepted that the choice of kernel function allows for domain specific information to be leveraged in the classification system. In this paper it is shown that for target classification in side-scan sonar, extra feature extraction and data engineering can result in better classification performance compared to parameter optimization alone.
{"title":"Feature extraction and target classification of side-scan sonar images","authors":"J. Rhinelander","doi":"10.1109/SSCI.2016.7850074","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7850074","url":null,"abstract":"Side-scan sonar technology has been used over the last three decades for underwater surveying and imaging. Application areas of side-scan sonar include archaeology, security and defence, seabed classification, and environmental surveying. In recent years the use of autonomous underwater systems has allowed for automatic collection of data. Along with automatic collection of data comes the need to automatically detect what information is important. Automatic target recognition can allow for efficient task planning and autonomous system deployment for security and defence applications. Support Vector Machines (SVMs) are proven general purpose methods for pattern classification. They provide maximum margin classification that does not over fit to training data. It is generally accepted that the choice of kernel function allows for domain specific information to be leveraged in the classification system. In this paper it is shown that for target classification in side-scan sonar, extra feature extraction and data engineering can result in better classification performance compared to parameter optimization alone.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128522207","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 : 2016-12-01DOI: 10.1109/SSCI.2016.7850220
Jussi Hakanen, Tinkle Chugh, Karthik Sindhya, Yaochu Jin, K. Miettinen
We study how different types of preference information coming from a human decision maker can be utilized in an interactive multiobjective evolutionary optimization algorithm (MOEA). The idea is to convert different types of preference information into a unified format which can then be utilized in an interactive MOEA to guide the search towards the most preferred solution(s). The format chosen here is a set of reference vectors which is used within the interactive version of the reference vector guided evolutionary algorithm (RVEA). The proposed interactive RVEA is then applied to the multiple-disk clutch brake design problem with five objectives to demonstrate the potential of the idea in supporting decision making in optimization problems involving more than three objectives.
{"title":"Connections of reference vectors and different types of preference information in interactive multiobjective evolutionary algorithms","authors":"Jussi Hakanen, Tinkle Chugh, Karthik Sindhya, Yaochu Jin, K. Miettinen","doi":"10.1109/SSCI.2016.7850220","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7850220","url":null,"abstract":"We study how different types of preference information coming from a human decision maker can be utilized in an interactive multiobjective evolutionary optimization algorithm (MOEA). The idea is to convert different types of preference information into a unified format which can then be utilized in an interactive MOEA to guide the search towards the most preferred solution(s). The format chosen here is a set of reference vectors which is used within the interactive version of the reference vector guided evolutionary algorithm (RVEA). The proposed interactive RVEA is then applied to the multiple-disk clutch brake design problem with five objectives to demonstrate the potential of the idea in supporting decision making in optimization problems involving more than three objectives.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124700198","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 : 2016-12-01DOI: 10.1109/SSCI.2016.7850159
Franz Pieper, Sanaz Mostaghim
This paper presents Evolutionary Spatial Games in dynamic environments. This game is a concept based on Evolutionary Game Theory (EGT) and Evolutionary Algorithms (EAs). The main goal is to study the implicit influence of dynamic environments on the behavior of agents in EGT. The paper considers three different types of populations which interact using a modifiable and individualized payoff matrix for their agents. As each agent of a certain type can have a different payoff value than the rest of the population, the populations evolve towards a diverse set of agents. In order to study the diversity in each population, we propose a model based on EAs and study the impact of dynamic environments on the populations and their diversities. The main question to answer is that whether diversity can help to obtain a stable strategy and if the dynamics in a certain environment can influence the Spatial Game. The experiments on three different environments show that the stable strategies can contain a diverse set of agents particularly in dynamic environments.
{"title":"Influence of dynamic environments on agent strategies","authors":"Franz Pieper, Sanaz Mostaghim","doi":"10.1109/SSCI.2016.7850159","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7850159","url":null,"abstract":"This paper presents Evolutionary Spatial Games in dynamic environments. This game is a concept based on Evolutionary Game Theory (EGT) and Evolutionary Algorithms (EAs). The main goal is to study the implicit influence of dynamic environments on the behavior of agents in EGT. The paper considers three different types of populations which interact using a modifiable and individualized payoff matrix for their agents. As each agent of a certain type can have a different payoff value than the rest of the population, the populations evolve towards a diverse set of agents. In order to study the diversity in each population, we propose a model based on EAs and study the impact of dynamic environments on the populations and their diversities. The main question to answer is that whether diversity can help to obtain a stable strategy and if the dynamics in a certain environment can influence the Spatial Game. The experiments on three different environments show that the stable strategies can contain a diverse set of agents particularly in dynamic environments.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130503096","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 : 2016-12-01DOI: 10.1109/SSCI.2016.7850112
Zongqing Lu, Wenjian Zhang, Q. Liao
Deep learning is greatly successful when used for pedestrian detection. However, we find that this method is barely satisfactory for multi-scale detection. Meanwhile, various solutions such as multi-scale classifiers have been developed (based on traditional methods) to handle this situation. Considering this, we propose a scale-discriminative classifier layer (SDC) that contains numerous classifiers to cope with different scales. To expand the capacity for small-scale pedestrian detection, we construct a full-scale layer that converges both high-level semantic features and low-level features. From the analysis above, a scale-discriminative network (SDN) for pedestrian detection was born. We apply this network to the Caltech pedestrian dataset, and the experimental results show that the SDN achieves state-of-the-art performance.
{"title":"Pedestrian detection aided by scale-discriminative network","authors":"Zongqing Lu, Wenjian Zhang, Q. Liao","doi":"10.1109/SSCI.2016.7850112","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7850112","url":null,"abstract":"Deep learning is greatly successful when used for pedestrian detection. However, we find that this method is barely satisfactory for multi-scale detection. Meanwhile, various solutions such as multi-scale classifiers have been developed (based on traditional methods) to handle this situation. Considering this, we propose a scale-discriminative classifier layer (SDC) that contains numerous classifiers to cope with different scales. To expand the capacity for small-scale pedestrian detection, we construct a full-scale layer that converges both high-level semantic features and low-level features. From the analysis above, a scale-discriminative network (SDN) for pedestrian detection was born. We apply this network to the Caltech pedestrian dataset, and the experimental results show that the SDN achieves state-of-the-art performance.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126911070","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 : 2016-12-01DOI: 10.1109/SSCI.2016.7849843
Roberto Bonfigli, E. Principi, S. Squartini, Marco Fagiani, M. Severini, F. Piazza
In the area of Non-Intrusive Load Monitoring (NILM), many approaches need a supervised procedure of appliance modelling, in order to provide the informations about the appliances to the disaggregation algorithm and to obtain the disaggregated consumptions related to each one of them. In many approaches, the appliance modelling relies on the consumption footprint, which is a typical working cycle of the appliance. Since the NILM system has only the aggregated power consumption available, the recorded footprint might be corrupted by other appliances, which can not be turned off during this period, i.e., the fridge and freezer in the household. Furthermore, the user needs a facilitated procedure, in order to obtain a clean footprint from the aggregated power signal in real scenario. Therefore, a user-aided footprint extraction procedure is needed. In this work, this procedure is defined as a NILM problem with two sources, i.e., the desired appliance and the fridge-freezer combination. One of the resulting disaggregated profiles of the algorithm corresponds to the extracted footprint. Then, this is used for the appliance modelling stage to create te corresponding Hidden Markov Model (HMM), suitable for the Additive Factorial Approximate Maximum a Posteriori (AFAMAP) algorithm. The effectiveness of the footprint extraction procedure is evaluated through the confidence of the disaggregation output of a real problem, using a span of 30 days data taken from two different datasets (AMPds, ECO). The experiments are conducted using the HMM from the extracted footprint, compared to the confidence of the same problem using the HMM from the true footprint, as appliance level consumption. The results show that the performance are comparable, with the worst relative F1 loss of 3.83%, demonstrating the effectiveness of the footprint extraction procedure.
{"title":"User-aided footprint extraction for appliance modelling in Non-Intrusive Load Monitoring","authors":"Roberto Bonfigli, E. Principi, S. Squartini, Marco Fagiani, M. Severini, F. Piazza","doi":"10.1109/SSCI.2016.7849843","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7849843","url":null,"abstract":"In the area of Non-Intrusive Load Monitoring (NILM), many approaches need a supervised procedure of appliance modelling, in order to provide the informations about the appliances to the disaggregation algorithm and to obtain the disaggregated consumptions related to each one of them. In many approaches, the appliance modelling relies on the consumption footprint, which is a typical working cycle of the appliance. Since the NILM system has only the aggregated power consumption available, the recorded footprint might be corrupted by other appliances, which can not be turned off during this period, i.e., the fridge and freezer in the household. Furthermore, the user needs a facilitated procedure, in order to obtain a clean footprint from the aggregated power signal in real scenario. Therefore, a user-aided footprint extraction procedure is needed. In this work, this procedure is defined as a NILM problem with two sources, i.e., the desired appliance and the fridge-freezer combination. One of the resulting disaggregated profiles of the algorithm corresponds to the extracted footprint. Then, this is used for the appliance modelling stage to create te corresponding Hidden Markov Model (HMM), suitable for the Additive Factorial Approximate Maximum a Posteriori (AFAMAP) algorithm. The effectiveness of the footprint extraction procedure is evaluated through the confidence of the disaggregation output of a real problem, using a span of 30 days data taken from two different datasets (AMPds, ECO). The experiments are conducted using the HMM from the extracted footprint, compared to the confidence of the same problem using the HMM from the true footprint, as appliance level consumption. The results show that the performance are comparable, with the worst relative F1 loss of 3.83%, demonstrating the effectiveness of the footprint extraction procedure.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123678790","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 : 2016-12-01DOI: 10.1109/SSCI.2016.7849867
T. Pham
This paper presents a method for computing entropy rates of images by modeling a stationary Markov chain constructed from a weighted graph. The proposed method was applied to the quantification of the complex behavior of the growing rates of physiological aging of Caenorhabditis elegans (C. elegans) on microscopic images, which has been considered as one of the most challenging problems in the search for metrics that can be used for identifying differences among stages in high-throughput and high-content images of physiological aging.
{"title":"Entropy rates of physiological aging on microscopy","authors":"T. Pham","doi":"10.1109/SSCI.2016.7849867","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7849867","url":null,"abstract":"This paper presents a method for computing entropy rates of images by modeling a stationary Markov chain constructed from a weighted graph. The proposed method was applied to the quantification of the complex behavior of the growing rates of physiological aging of Caenorhabditis elegans (C. elegans) on microscopic images, which has been considered as one of the most challenging problems in the search for metrics that can be used for identifying differences among stages in high-throughput and high-content images of physiological aging.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121426381","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 analyze a variety of influence factors for the spreading pattern of forest fires. Rules of these crucial factors are expressed with cellular automata (CA), which has powerful simulation capacity. Specifically, we analyze the influence of combustible materials, wind, temperature, and terrain. We implement a CA Forest Fire Forecast System based on the Matlab development platform. Simulation results demonstrate that this model can be used to effectively simulate and forecast the spreading trend of forest fire in various conditions.
{"title":"A cellular automata model for forest fire spreading simulation","authors":"Xuehua Wang, Chang Liu, Jiaqi Liu, Xuezhi Qin, Ning Wang, Wenjun Zhou","doi":"10.1109/SSCI.2016.7849971","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7849971","url":null,"abstract":"In this paper, we analyze a variety of influence factors for the spreading pattern of forest fires. Rules of these crucial factors are expressed with cellular automata (CA), which has powerful simulation capacity. Specifically, we analyze the influence of combustible materials, wind, temperature, and terrain. We implement a CA Forest Fire Forecast System based on the Matlab development platform. Simulation results demonstrate that this model can be used to effectively simulate and forecast the spreading trend of forest fire in various conditions.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114314656","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 : 2016-12-01DOI: 10.1109/SSCI.2016.7850050
T. Dhivyaprabha, P. Subashini, M. Krishnaveni
In robot control, rule discovery for understanding of data is of critical importance. Basically, understanding of data depends upon logical rules, similarity evaluation and graphical methods. The expert system collects training examples separately by exploring an anonymous environment by using machine learning techniques. In dynamic environments, future actions are determined by sequences of perceptions thus encoded as rule base. This paper is focused on demonstrating the extraction and application of logical rules for image understanding, using newly developed Synergistic Fibroblast Optimization (SFO) algorithm with well-known existing artificial learning methods. The SFO algorithm is tested in two modes: Michigan and Pittsburgh approach. Optimal rule discovery is evaluated by describing continuous data and verifying accuracy and error level at optimization phase. In this work, Monk's problem is solved by discovering optimal rules that enhance the generalization and comprehensibility of a robot classification system in classifying the objects from extracted attributes to effectively categorize its domain.
{"title":"Computational intelligence based machine learning methods for rule-based reasoning in computer vision applications","authors":"T. Dhivyaprabha, P. Subashini, M. Krishnaveni","doi":"10.1109/SSCI.2016.7850050","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7850050","url":null,"abstract":"In robot control, rule discovery for understanding of data is of critical importance. Basically, understanding of data depends upon logical rules, similarity evaluation and graphical methods. The expert system collects training examples separately by exploring an anonymous environment by using machine learning techniques. In dynamic environments, future actions are determined by sequences of perceptions thus encoded as rule base. This paper is focused on demonstrating the extraction and application of logical rules for image understanding, using newly developed Synergistic Fibroblast Optimization (SFO) algorithm with well-known existing artificial learning methods. The SFO algorithm is tested in two modes: Michigan and Pittsburgh approach. Optimal rule discovery is evaluated by describing continuous data and verifying accuracy and error level at optimization phase. In this work, Monk's problem is solved by discovering optimal rules that enhance the generalization and comprehensibility of a robot classification system in classifying the objects from extracted attributes to effectively categorize its domain.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116297737","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 : 2016-12-01DOI: 10.1109/SSCI.2016.7850162
C. A. Severiano, F. Guimarães, Miri Weiss-Cohen
This paper proposes a new multi-agent system to solve very short-term solar forecasting problems. The system organizes the training data into clusters using Part and Select Algorithm. These clusters are used to generate different forecasting models, where each one is performed by a different agent. Finally, another agent is responsible for deciding which model will be applied at each forecasting situation. Results present improvements in forecasting accuracy and training performance if compared to other forecasting methods. A discussion of how to use this architecture for the implementation of a more comprehensive model is also addressed.
{"title":"Very short-term solar forecasting using multi-agent system based on Extreme Learning Machines and data clustering","authors":"C. A. Severiano, F. Guimarães, Miri Weiss-Cohen","doi":"10.1109/SSCI.2016.7850162","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7850162","url":null,"abstract":"This paper proposes a new multi-agent system to solve very short-term solar forecasting problems. The system organizes the training data into clusters using Part and Select Algorithm. These clusters are used to generate different forecasting models, where each one is performed by a different agent. Finally, another agent is responsible for deciding which model will be applied at each forecasting situation. Results present improvements in forecasting accuracy and training performance if compared to other forecasting methods. A discussion of how to use this architecture for the implementation of a more comprehensive model is also addressed.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114785033","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：