Pub Date : 2021-01-01DOI: 10.14311/nnw.2021.31.015
Nils Weiss, Enrico Pozzobon, J. Mottok, V. Matousek
Car manufacturers define proprietary protocols to be used inside their vehicular networks, which are kept an industrial secret, therefore impeding independent researchers from extracting information from these networks. This article describes a statistical and a neural network approach that allows reverse engineering proprietary controller area network (CAN)-protocols assuming they were designed using the data base CAN (DBC) file format. The proposed algorithms are tested with CAN traces taken from a real car. We show that our approaches can correctly reverse engineer CAN messages in an automated manner.
{"title":"Automated Reverse Engineering of CAN Protocols","authors":"Nils Weiss, Enrico Pozzobon, J. Mottok, V. Matousek","doi":"10.14311/nnw.2021.31.015","DOIUrl":"https://doi.org/10.14311/nnw.2021.31.015","url":null,"abstract":"Car manufacturers define proprietary protocols to be used inside their vehicular networks, which are kept an industrial secret, therefore impeding independent researchers from extracting information from these networks. This article describes a statistical and a neural network approach that allows reverse engineering proprietary controller area network (CAN)-protocols assuming they were designed using the data base CAN (DBC) file format. The proposed algorithms are tested with CAN traces taken from a real car. We show that our approaches can correctly reverse engineer CAN messages in an automated manner.","PeriodicalId":49765,"journal":{"name":"Neural Network World","volume":"1 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67124521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-01DOI: 10.14311/nnw.2021.31.020
Yaroslav Kerechanin, P. Bobrov, A. Frolov, D. Húsek
Eight methods of decomposition of a multichannel EEG signal are compared in terms of their ability to identify the most physiologically significant components. The criterion for the meaningfulness of a method is its ability to reduce mutual information between components; to create components that can be attributed to the activity of dipoles located in the cerebral cortex; find components that are provided by other methods and for this case; and, at the same time, these components should most contribute to the accuracy of the BCI based on imaginary movement. Independent component analysis methods AMICA, RUNICA and FASTICA outperform others in the first three criteria and are second only to the common spatial patterns method in the fourth criterion. The components created by all methods for 386 experimental sessions of 27 subjects were combined into more than 100 clusters containing more than 10 elements. Additionally, the components of the 12 largest clusters were analyzed. They have proven to be of great importance in controlling BCI, their origins can be modeled using dipoles in the brain, and they have been detected by several degradation methods. Five of the 12 selected components have been identified and described in our previous articles. Even if the physiological and functional origins of the rest of identified components are to be the subject of further research, we have shown that their physiological nature is at least highly probable.
{"title":"Independent EEG components are meaningful (for BCI based on motor imagery)","authors":"Yaroslav Kerechanin, P. Bobrov, A. Frolov, D. Húsek","doi":"10.14311/nnw.2021.31.020","DOIUrl":"https://doi.org/10.14311/nnw.2021.31.020","url":null,"abstract":"Eight methods of decomposition of a multichannel EEG signal are compared in terms of their ability to identify the most physiologically significant components. The criterion for the meaningfulness of a method is its ability to reduce mutual information between components; to create components that can be attributed to the activity of dipoles located in the cerebral cortex; find components that are provided by other methods and for this case; and, at the same time, these components should most contribute to the accuracy of the BCI based on imaginary movement. Independent component analysis methods AMICA, RUNICA and FASTICA outperform others in the first three criteria and are second only to the common spatial patterns method in the fourth criterion. The components created by all methods for 386 experimental sessions of 27 subjects were combined into more than 100 clusters containing more than 10 elements. Additionally, the components of the 12 largest clusters were analyzed. They have proven to be of great importance in controlling BCI, their origins can be modeled using dipoles in the brain, and they have been detected by several degradation methods. Five of the 12 selected components have been identified and described in our previous articles. Even if the physiological and functional origins of the rest of identified components are to be the subject of further research, we have shown that their physiological nature is at least highly probable.","PeriodicalId":49765,"journal":{"name":"Neural Network World","volume":"1 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67125164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-01DOI: 10.14311/nnw.2021.31.011
S. Zheng, A. Jiang, X. Yang
The prediction and analysis of surrounding rock deformation is a primary risk assessment method in tunnel engineering. However, the accurate prediction result is not easy to achieve due to the influence of multiple factors such as rock mass properties, support structure, and the spatial effect of tunnel construction. In this paper, a multivariate time-series model (MTSM) for tunnel displacement prediction is studied based on Gaussian process regression (GPR) optimized by differential evolutionary (DE) strategy, where the spatial effect is intuitively expressed through an extended time-series model. First, building learning samples for GPR, in which the inputs is the displacement data of the previous n days and the output is the data of the day (n + 1). Then, for each sample, an input item is added successively to form an expanded learning sample, which is the “distance between the construction face and monitoring section” on the day (n+ 1). Taking the root mean square error between the regression and measured data as the control index, the GPR model is trained to express the nonlinear mapping relationship between input and output, and the optimal parameters of this model are searched by DE. The displacement multivariate time-series model represented by DE-GPR is known as MTSM. On this basis, the applicability of GPR for tunnel displacement prediction and the necessity of DE optimization are illustrated by comparing the prediction results of several commonly used machine learning models. At the same time, the influence of GPR and DE parameters on the regression result and the computational efficiency of the MTSM model is analyzed, the recommendation for parameter values are given considering both calculation efficiency and accuracy. This method is successfully applied to the Leshanting tunnel of Puyan expressway in Fujian province, China, and the results show that the MTSM based on DE-GPR has a good ability in the deformation prediction of the surrounding rock, which provides a new method for tunnel engineering safety control.
{"title":"Tunnel displacement prediction under spatial effect based on Gaussian process regression optimized by differential evolution","authors":"S. Zheng, A. Jiang, X. Yang","doi":"10.14311/nnw.2021.31.011","DOIUrl":"https://doi.org/10.14311/nnw.2021.31.011","url":null,"abstract":"The prediction and analysis of surrounding rock deformation is a primary risk assessment method in tunnel engineering. However, the accurate prediction result is not easy to achieve due to the influence of multiple factors such as rock mass properties, support structure, and the spatial effect of tunnel construction. In this paper, a multivariate time-series model (MTSM) for tunnel displacement prediction is studied based on Gaussian process regression (GPR) optimized by differential evolutionary (DE) strategy, where the spatial effect is intuitively expressed through an extended time-series model. First, building learning samples for GPR, in which the inputs is the displacement data of the previous n days and the output is the data of the day (n + 1). Then, for each sample, an input item is added successively to form an expanded learning sample, which is the “distance between the construction face and monitoring section” on the day (n+ 1). Taking the root mean square error between the regression and measured data as the control index, the GPR model is trained to express the nonlinear mapping relationship between input and output, and the optimal parameters of this model are searched by DE. The displacement multivariate time-series model represented by DE-GPR is known as MTSM. On this basis, the applicability of GPR for tunnel displacement prediction and the necessity of DE optimization are illustrated by comparing the prediction results of several commonly used machine learning models. At the same time, the influence of GPR and DE parameters on the regression result and the computational efficiency of the MTSM model is analyzed, the recommendation for parameter values are given considering both calculation efficiency and accuracy. This method is successfully applied to the Leshanting tunnel of Puyan expressway in Fujian province, China, and the results show that the MTSM based on DE-GPR has a good ability in the deformation prediction of the surrounding rock, which provides a new method for tunnel engineering safety control.","PeriodicalId":49765,"journal":{"name":"Neural Network World","volume":"1 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67123986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-01DOI: 10.14311/nnw.2021.31.005
Lenka Jonáková, I. Nagy
This study reflects a unique task with significant business potential, on the edge of the wholesale and retail power market, i.e., optimization of power derivatives purchase strategy of retail customers. Even though the definition of the task as well as initial assumptions may be highly complex, essentially, the purpose of this study can be narrowed down to the estimation of buying signals. The price signals are estimated with the use of machine learning techniques, i.e., one-, twoand three-layer perceptron with supervised learning as well as long short-term memory network, which allow modelling of highly complex functional relationships, and with the use of relative strength index, i.e., momentum technical indicator, which on the contrary allows higher flexibility in terms of parameters adjustment as well as easier results interpretation. Thereafter, performance of these methods is compared and evaluated against the established benchmark.
{"title":"Power purchase strategy of retail customers utilizing advanced classification methods","authors":"Lenka Jonáková, I. Nagy","doi":"10.14311/nnw.2021.31.005","DOIUrl":"https://doi.org/10.14311/nnw.2021.31.005","url":null,"abstract":"This study reflects a unique task with significant business potential, on the edge of the wholesale and retail power market, i.e., optimization of power derivatives purchase strategy of retail customers. Even though the definition of the task as well as initial assumptions may be highly complex, essentially, the purpose of this study can be narrowed down to the estimation of buying signals. The price signals are estimated with the use of machine learning techniques, i.e., one-, twoand three-layer perceptron with supervised learning as well as long short-term memory network, which allow modelling of highly complex functional relationships, and with the use of relative strength index, i.e., momentum technical indicator, which on the contrary allows higher flexibility in terms of parameters adjustment as well as easier results interpretation. Thereafter, performance of these methods is compared and evaluated against the established benchmark.","PeriodicalId":49765,"journal":{"name":"Neural Network World","volume":"1 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67124196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-01DOI: 10.14311/nnw.2021.31.016
Jiang Liu, Feng Ni, Mingjun Du, Xuyang Zhang, Zhongli Que, Shihang Song
It is one of the fundamental and challenging problems to determine the node numbers of hidden layers in neural networks. Various efforts have been made to study the relations between the approximation ability and the number of hidden nodes of some specific neural networks, such as single-hidden-layer and two-hiddenlayer feedforward neural networks with specific or conditional activation functions. However, for arbitrary feedforward neural networks, there are few theoretical results on such issues. This paper gives an upper bound on the node number of each hidden layer for the most general feedforward neural networks called multilayer perceptrons (MLP), from an algebraic point of view. First, we put forward the method of expansion linear spaces to investigate the algebraic structure and properties of the outputs of MLPs. Then it is proved that given k distinct training samples, for any MLP with k nodes in each hidden layer, if a certain optimization problem has solutions, the approximation error keeps invariant with adding nodes to hidden layers. Furthermore, it is shown that for any MLP whose activation function for the output layer is bounded on R, at most k hidden nodes in each hidden layer are needed to learn k training samples.
{"title":"Upper bounds on the node numbers of hidden layers in MLPs","authors":"Jiang Liu, Feng Ni, Mingjun Du, Xuyang Zhang, Zhongli Que, Shihang Song","doi":"10.14311/nnw.2021.31.016","DOIUrl":"https://doi.org/10.14311/nnw.2021.31.016","url":null,"abstract":"It is one of the fundamental and challenging problems to determine the node numbers of hidden layers in neural networks. Various efforts have been made to study the relations between the approximation ability and the number of hidden nodes of some specific neural networks, such as single-hidden-layer and two-hiddenlayer feedforward neural networks with specific or conditional activation functions. However, for arbitrary feedforward neural networks, there are few theoretical results on such issues. This paper gives an upper bound on the node number of each hidden layer for the most general feedforward neural networks called multilayer perceptrons (MLP), from an algebraic point of view. First, we put forward the method of expansion linear spaces to investigate the algebraic structure and properties of the outputs of MLPs. Then it is proved that given k distinct training samples, for any MLP with k nodes in each hidden layer, if a certain optimization problem has solutions, the approximation error keeps invariant with adding nodes to hidden layers. Furthermore, it is shown that for any MLP whose activation function for the output layer is bounded on R, at most k hidden nodes in each hidden layer are needed to learn k training samples.","PeriodicalId":49765,"journal":{"name":"Neural Network World","volume":"1 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67124595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-01DOI: 10.14311/nnw.2021.31.018
Matous Cejnek, J. Vrba
This paper introduces an online centered normalized least mean squares (OC-NLMS) algorithm for linear adaptive finite impulse response (FIR) filters and neural networks. As an extension of the normalized least mean squares (NLMS), the OC-NLMS algorithm features an approach of online input centering according to the introduced filter memory. This key feature can compensate the effect of concept drift in data streams, because such a centering makes the filter independent from the nonzero mean value of signal. This approach is beneficial for applications of adaptive filtering of data with offsets. Furthermore, it can be useful for real-time applications like data stream processing where it is impossible to normalize the measured data with respect to its unknown statistical attributes. The OC-NLMS approach holds superior performance in comparison to the NLMS for data with large offsets and dynamical ranges, due to its input centering feature that deals with the nonzero mean value of the input data. In this paper, the derivation of this algorithm is presented. Several simulation results with artificial and real data are also presented and analysed to demonstrate the capability of the proposed algorithm in comparison with NLMS.
{"title":"Online centered NLMS algorithm for concept drift compensation","authors":"Matous Cejnek, J. Vrba","doi":"10.14311/nnw.2021.31.018","DOIUrl":"https://doi.org/10.14311/nnw.2021.31.018","url":null,"abstract":"This paper introduces an online centered normalized least mean squares (OC-NLMS) algorithm for linear adaptive finite impulse response (FIR) filters and neural networks. As an extension of the normalized least mean squares (NLMS), the OC-NLMS algorithm features an approach of online input centering according to the introduced filter memory. This key feature can compensate the effect of concept drift in data streams, because such a centering makes the filter independent from the nonzero mean value of signal. This approach is beneficial for applications of adaptive filtering of data with offsets. Furthermore, it can be useful for real-time applications like data stream processing where it is impossible to normalize the measured data with respect to its unknown statistical attributes. The OC-NLMS approach holds superior performance in comparison to the NLMS for data with large offsets and dynamical ranges, due to its input centering feature that deals with the nonzero mean value of the input data. In this paper, the derivation of this algorithm is presented. Several simulation results with artificial and real data are also presented and analysed to demonstrate the capability of the proposed algorithm in comparison with NLMS.","PeriodicalId":49765,"journal":{"name":"Neural Network World","volume":"1 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67124971","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-01DOI: 10.14311/nnw.2021.31.006
V. Hlavác
A neural network can be used in the identification of a given functional dependency. An undetermined problem (with more degrees of freedom) has to be converted to a determined one by adding other conditions. This is easy for a well-defined problem, described by a theoretical functional dependency; in this case, no identification (using a neural network) is necessary. The article describes how to apply a fitness (or a penalty) function directly to the data, before a neural network is trained. As a result, the trained neural network is near to the best possible solution according to the selected fitness function. In comparison to implementing the fitness function during the training of the neural network, the method described here is simpler and more reliable. The new method is demonstrated on the kinematics control of a redundant 2D manipulator.
{"title":"Neural Network for the identification of a functional dependence using data preselection","authors":"V. Hlavác","doi":"10.14311/nnw.2021.31.006","DOIUrl":"https://doi.org/10.14311/nnw.2021.31.006","url":null,"abstract":"A neural network can be used in the identification of a given functional dependency. An undetermined problem (with more degrees of freedom) has to be converted to a determined one by adding other conditions. This is easy for a well-defined problem, described by a theoretical functional dependency; in this case, no identification (using a neural network) is necessary. The article describes how to apply a fitness (or a penalty) function directly to the data, before a neural network is trained. As a result, the trained neural network is near to the best possible solution according to the selected fitness function. In comparison to implementing the fitness function during the training of the neural network, the method described here is simpler and more reliable. The new method is demonstrated on the kinematics control of a redundant 2D manipulator.","PeriodicalId":49765,"journal":{"name":"Neural Network World","volume":"1 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67124312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-01DOI: 10.14311/nnw.2021.31.017
S. Jozová, M. Matowicki, O. Přibyl, M. Zachová, Sathaporn Opasanon, R. Ziółkowski
An analysis of survey data is a fundamental part of research concerning various aspects of human behavior. Such survey data are often discrete, and the size of the collected sample is regularly insufficient for the most potent modelling tools such as logistic regression, clustering, and other data mining techniques. In this paper, we take a closer look at the results of the stated preference survey analyzing how inhabitants of cities in Thailand, Poland, and Czechia understand and perceive “smartness” of a city. An international survey was conducted, where respondents were asked 15 questions. Since the most common data modelling tools failed to provide a useful insight into the relationship between variables, so-called lambda coefficient was used and its usefulness for such challenging data was verified. It uses the principle of conditional probability and proves to be truly useful even in data sets with relatively small sample size.
{"title":"On the analysis of discrete data finding dependencies in small sample sizes","authors":"S. Jozová, M. Matowicki, O. Přibyl, M. Zachová, Sathaporn Opasanon, R. Ziółkowski","doi":"10.14311/nnw.2021.31.017","DOIUrl":"https://doi.org/10.14311/nnw.2021.31.017","url":null,"abstract":"An analysis of survey data is a fundamental part of research concerning various aspects of human behavior. Such survey data are often discrete, and the size of the collected sample is regularly insufficient for the most potent modelling tools such as logistic regression, clustering, and other data mining techniques. In this paper, we take a closer look at the results of the stated preference survey analyzing how inhabitants of cities in Thailand, Poland, and Czechia understand and perceive “smartness” of a city. An international survey was conducted, where respondents were asked 15 questions. Since the most common data modelling tools failed to provide a useful insight into the relationship between variables, so-called lambda coefficient was used and its usefulness for such challenging data was verified. It uses the principle of conditional probability and proves to be truly useful even in data sets with relatively small sample size.","PeriodicalId":49765,"journal":{"name":"Neural Network World","volume":"1 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67124676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-01DOI: 10.14311/nnw.2021.31.019
Zuzana Purkrábková, J. Ruzicka, Z. Belinová, Vojtěch Korec
The article deals with the current issue of traffic accident risk classification in urban area. In connection with the increase in traffic in the Czech Republic, a higher probability of risks of traffic excesses can be expected in the future. If there is a traffic excess in the city, the aim is to propose a meaningful traffic management solution to minimize the social losses. The main needs are the early identification and classification of the cause of the traffic excess, finding a suitable alternative solution, quick application of that solution, and the rapid ability to resume operations in the area of congestion. Traffic prediction is one of the tools for the early identification of traffic excess. The article describes extensive research focused on the classification and prediction of the output variable of accident risk based on own programmed neural networks. The research outputs will be subsequently used for the creation of a traffic application for a selected urban area in the Czech Republic.
{"title":"Traffic accident risk classification using neural networks","authors":"Zuzana Purkrábková, J. Ruzicka, Z. Belinová, Vojtěch Korec","doi":"10.14311/nnw.2021.31.019","DOIUrl":"https://doi.org/10.14311/nnw.2021.31.019","url":null,"abstract":"The article deals with the current issue of traffic accident risk classification in urban area. In connection with the increase in traffic in the Czech Republic, a higher probability of risks of traffic excesses can be expected in the future. If there is a traffic excess in the city, the aim is to propose a meaningful traffic management solution to minimize the social losses. The main needs are the early identification and classification of the cause of the traffic excess, finding a suitable alternative solution, quick application of that solution, and the rapid ability to resume operations in the area of congestion. Traffic prediction is one of the tools for the early identification of traffic excess. The article describes extensive research focused on the classification and prediction of the output variable of accident risk based on own programmed neural networks. The research outputs will be subsequently used for the creation of a traffic application for a selected urban area in the Czech Republic.","PeriodicalId":49765,"journal":{"name":"Neural Network World","volume":"1 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67125098","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-01DOI: 10.14311/nnw.2021.31.023
Jianyu Wang
Based on the theoretical analysis of Elman network, the short-term load forecasting model of regional integrated energy system is established. The structure and parameters of the model are determined through repeated off-line training and experiments. The forecasting accuracy is significantly higher than that of traditional BP network, and the prediction error is less than 3%, which can meet the needs of coordination and scheduling of regional integrated energy system.
{"title":"Short-term load forecasting of regional integrated energy system","authors":"Jianyu Wang","doi":"10.14311/nnw.2021.31.023","DOIUrl":"https://doi.org/10.14311/nnw.2021.31.023","url":null,"abstract":"Based on the theoretical analysis of Elman network, the short-term load forecasting model of regional integrated energy system is established. The structure and parameters of the model are determined through repeated off-line training and experiments. The forecasting accuracy is significantly higher than that of traditional BP network, and the prediction error is less than 3%, which can meet the needs of coordination and scheduling of regional integrated energy system.","PeriodicalId":49765,"journal":{"name":"Neural Network World","volume":"1 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67125257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","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：