Pub Date : 2022-01-01DOI: 10.14311/nnw.2022.32.017
Lilian Huang, XueQiang Shi, Jianhong Xiang
In order to better balance the detection accuracy and tracking speed, we propose an online balanced multi-object tracking method (BalMOT), which integrates object detection and appearance extraction into a single network, and can simultaneously output detection and appearance embedding. We also model the training of classification, regression, and embedding features as a multi-task training problem and each part is weighted based on the task-independent uncertainty method. In addition, we introduce the transition layer to optimize the repeated gradient information in the network and reduce the training cost. Through the training, our BalMOT system reaches 71.9% multiple object tracking accuracy (MOTA) on the MOT17 challenge dataset, and the speed fluctuates between 17.4 ~ 22.3 frames per second (FPS) according to the size of the input image.
{"title":"A method for joint detection and re-identification in multi-object tracking","authors":"Lilian Huang, XueQiang Shi, Jianhong Xiang","doi":"10.14311/nnw.2022.32.017","DOIUrl":"https://doi.org/10.14311/nnw.2022.32.017","url":null,"abstract":"In order to better balance the detection accuracy and tracking speed, we propose an online balanced multi-object tracking method (BalMOT), which integrates object detection and appearance extraction into a single network, and can simultaneously output detection and appearance embedding. We also model the training of classification, regression, and embedding features as a multi-task training problem and each part is weighted based on the task-independent uncertainty method. In addition, we introduce the transition layer to optimize the repeated gradient information in the network and reduce the training cost. Through the training, our BalMOT system reaches 71.9% multiple object tracking accuracy (MOTA) on the MOT17 challenge dataset, and the speed fluctuates between 17.4 ~ 22.3 frames per second (FPS) according to the size of the input image.","PeriodicalId":49765,"journal":{"name":"Neural Network World","volume":"1 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67125899","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.2021.31.004
J. Kovanda, V. Rulc
: The aim of the article is the optimisation process of the ADAS (Ad-vanced Driver Assistance Systems) control. The methodology is based on the classification of ADAS systems according to the situations of unavoidable accidents. The evaluation of expected consequences uses injury biomechanics, which represents the extended definition of HMI (Human-Machine Interaction). The evaluation of injury mechanism and the machine intervention enables to control this process with the target to minimise the consequent injuries. Then the decision making takes new inputs to the control process and it enriches the multiparametric control of the system with the target to minimise the consequences.
{"title":"Pre-crash control strategy of driver assistance system","authors":"J. Kovanda, V. Rulc","doi":"10.14311/NNW.2021.31.004","DOIUrl":"https://doi.org/10.14311/NNW.2021.31.004","url":null,"abstract":": The aim of the article is the optimisation process of the ADAS (Ad-vanced Driver Assistance Systems) control. The methodology is based on the classification of ADAS systems according to the situations of unavoidable accidents. The evaluation of expected consequences uses injury biomechanics, which represents the extended definition of HMI (Human-Machine Interaction). The evaluation of injury mechanism and the machine intervention enables to control this process with the target to minimise the consequent injuries. Then the decision making takes new inputs to the control process and it enriches the multiparametric control of the system with the target to minimise the consequences.","PeriodicalId":49765,"journal":{"name":"Neural Network World","volume":"31 1","pages":"77-88"},"PeriodicalIF":0.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67124173","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.2021.31.022
J. Jeyashanthi, J. Barsanabanu
Induction motor (IM) drives with direct torque control (DTC) enable fast torque response without the need for complex orientation conversions or inner loop current loop. In the speed estimation responses, however, there is a significant level of torque ripple. The voltage source inverter adds acoustic noise and needs a high sampling frequency since it operates at a high and variable switching frequency. This work describes an ANN-based DTC technique for controlling the speed of an IM drive over a large speed range. To achieve good dynamic performance of induction motor drive, the ANN-based speed controller will replace the speed controller, switching tables, and hysteresis comparators. The neural network was trained using the back-propagation algorithm. The goal of a neural speed controller is to improve the system ability to respond quickly to changes in process variables while also mitigating the impacts of external perturbations. The projected ANN based DTC considerably and simply tracks the reference speed thus improves the efficiency of speed-torque of induction motors with quicker responses for rapid varying of speed reference and torque as that of Electric Vehicles in any uneven roads circumstances. MATLAB/Simulink software is used to evaluate the drive performance for both transient and dynamic operations. The proposed control performance is simulated and compared to a DTC-based traditional PI speed controller. In comparison to PI, the results show that ANN has better and faster effects. The torque ripple gets reduced by 1.5% in ANN (artificial neural network) controller compared to PI controller. The THD (total harmonic distortion) is reduced by 6.38% from PI controller to ANN controller.
{"title":"ANN-based direct torque control scheme of an IM drive for a wide range of speed operation","authors":"J. Jeyashanthi, J. Barsanabanu","doi":"10.14311/nnw.2021.31.022","DOIUrl":"https://doi.org/10.14311/nnw.2021.31.022","url":null,"abstract":"Induction motor (IM) drives with direct torque control (DTC) enable fast torque response without the need for complex orientation conversions or inner loop current loop. In the speed estimation responses, however, there is a significant level of torque ripple. The voltage source inverter adds acoustic noise and needs a high sampling frequency since it operates at a high and variable switching frequency. This work describes an ANN-based DTC technique for controlling the speed of an IM drive over a large speed range. To achieve good dynamic performance of induction motor drive, the ANN-based speed controller will replace the speed controller, switching tables, and hysteresis comparators. The neural network was trained using the back-propagation algorithm. The goal of a neural speed controller is to improve the system ability to respond quickly to changes in process variables while also mitigating the impacts of external perturbations. The projected ANN based DTC considerably and simply tracks the reference speed thus improves the efficiency of speed-torque of induction motors with quicker responses for rapid varying of speed reference and torque as that of Electric Vehicles in any uneven roads circumstances. MATLAB/Simulink software is used to evaluate the drive performance for both transient and dynamic operations. The proposed control performance is simulated and compared to a DTC-based traditional PI speed controller. In comparison to PI, the results show that ANN has better and faster effects. The torque ripple gets reduced by 1.5% in ANN (artificial neural network) controller compared to PI controller. The THD (total harmonic distortion) is reduced by 6.38% from PI controller to ANN controller.","PeriodicalId":49765,"journal":{"name":"Neural Network World","volume":"40 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67125235","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.2021.31.013
V. Malinovsky
This paper deals with problems of processing freight statistic data into the form of time series and analysing consequent results by means of two completely different methods. The first method for calculating chosen transport trends uses the transport model Trans-Tools based on conventional mathematical and statistical functions while the second one uses the scikit learn software providing users with development environment including algorithms of neural networks. The obtained results are similar to a certain extent which shows new possibilities of progressive use of neural networks in future and enables modern approach to analysing time series not only in transportation sector. Comparative analysis of results obtained from the same transport data processed by “standard” mathematical (Trans-Tool) method and neuron-network (scikit learn) method as well as a research focused on some trends development within the scope of freight transport in EU represent goals of this work.
{"title":"Comparative analysis of freight transport prognoses results provided by transport system model and neural network","authors":"V. Malinovsky","doi":"10.14311/nnw.2021.31.013","DOIUrl":"https://doi.org/10.14311/nnw.2021.31.013","url":null,"abstract":"This paper deals with problems of processing freight statistic data into the form of time series and analysing consequent results by means of two completely different methods. The first method for calculating chosen transport trends uses the transport model Trans-Tools based on conventional mathematical and statistical functions while the second one uses the scikit learn software providing users with development environment including algorithms of neural networks. The obtained results are similar to a certain extent which shows new possibilities of progressive use of neural networks in future and enables modern approach to analysing time series not only in transportation sector. Comparative analysis of results obtained from the same transport data processed by “standard” mathematical (Trans-Tool) method and neuron-network (scikit learn) method as well as a research focused on some trends development within the scope of freight transport in EU represent goals of this work.","PeriodicalId":49765,"journal":{"name":"Neural Network World","volume":"50 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67124274","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.2021.31.010
S. Sultana, Syed Sajjad Hussain, M. Hashmani, Jawwad Ahmad, Muhammad Zubair
Biomedical imaging, archiving, and classification is the recent challenge of computer-aided medical imaging. The popular and influential Deep Learning methods predict and congregate distinct markable features of ambiguity in radiographs precisely and accurately. This study submits a new topology of a deep learning network for chest radiograph classification. In this approach, a hybrid ensemble fusion of neural network topology can better diagnose ambiguities with high precision. The proposed topology also compares statistical findings with three optimizers and the most possible varying essential attributes of dropout probabilities and learning rates. The performance as a function of the AUCROC of this model is measured on the Chest Xpert dataset.
{"title":"A deep learning hybrid ensemble fusion for chest radiograph classification","authors":"S. Sultana, Syed Sajjad Hussain, M. Hashmani, Jawwad Ahmad, Muhammad Zubair","doi":"10.14311/nnw.2021.31.010","DOIUrl":"https://doi.org/10.14311/nnw.2021.31.010","url":null,"abstract":"Biomedical imaging, archiving, and classification is the recent challenge of computer-aided medical imaging. The popular and influential Deep Learning methods predict and congregate distinct markable features of ambiguity in radiographs precisely and accurately. This study submits a new topology of a deep learning network for chest radiograph classification. In this approach, a hybrid ensemble fusion of neural network topology can better diagnose ambiguities with high precision. The proposed topology also compares statistical findings with three optimizers and the most possible varying essential attributes of dropout probabilities and learning rates. The performance as a function of the AUCROC of this model is measured on the Chest Xpert dataset.","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":"67124394","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.2021.31.003
Bohumír Garlík
: The article deals with the current state of energy consumption, the development of distribution networks in the context of its decentralization and integrated community energy systems. The article focuses on the issue and optimization of the operation of EnergyHubs (EH) – energy centres in terms of solving environmental aspects using a mathematical model in the GAMS environment. The acquired knowledge and results of simulations were then applied to a specific urban area to find the optimal variant of EH. The aim of the research is to present its results at the level of cleaner production, improvement of the environment, significant reduction of CO 2 and sustainability of society. My experience proves that the achievement of sustainable development goals represents fundamental gaps in research and practical applications, especially at the level of specific projects. It is mainly the application of insufficient indicators and work methodologies in the design of building projects with almost zero energy consumption. Another short-coming is the coordination of design procedures and applications of optimization and simulation methods necessary to address the energy performance of buildings or clusters of buildings. In addition, the results show growing expectations about the added value of applying artificial intelligence in meeting sustainable development goals, through new data sources that inevitably enter the energy sustainability design process. energy losses, the basic process of designing a Smart Area environmental system. The state of the system in terms of all control and state variables, including energy flows, is defined by other variables. I present the EH concept and its modelling, including the optimization of the hybrid electricity system and gas network. The general framework for modelling power systems based on the hub concept is little known at this time. It is a medium-term management of EH based on the price of electricity
{"title":"Modelling and optimization of an intelligent environmental energy system in an intelligent area","authors":"Bohumír Garlík","doi":"10.14311/NNW.2021.31.003","DOIUrl":"https://doi.org/10.14311/NNW.2021.31.003","url":null,"abstract":": The article deals with the current state of energy consumption, the development of distribution networks in the context of its decentralization and integrated community energy systems. The article focuses on the issue and optimization of the operation of EnergyHubs (EH) – energy centres in terms of solving environmental aspects using a mathematical model in the GAMS environment. The acquired knowledge and results of simulations were then applied to a specific urban area to find the optimal variant of EH. The aim of the research is to present its results at the level of cleaner production, improvement of the environment, significant reduction of CO 2 and sustainability of society. My experience proves that the achievement of sustainable development goals represents fundamental gaps in research and practical applications, especially at the level of specific projects. It is mainly the application of insufficient indicators and work methodologies in the design of building projects with almost zero energy consumption. Another short-coming is the coordination of design procedures and applications of optimization and simulation methods necessary to address the energy performance of buildings or clusters of buildings. In addition, the results show growing expectations about the added value of applying artificial intelligence in meeting sustainable development goals, through new data sources that inevitably enter the energy sustainability design process. energy losses, the basic process of designing a Smart Area environmental system. The state of the system in terms of all control and state variables, including energy flows, is defined by other variables. I present the EH concept and its modelling, including the optimization of the hybrid electricity system and gas network. The general framework for modelling power systems based on the hub concept is little known at this time. It is a medium-term management of EH based on the price of electricity","PeriodicalId":49765,"journal":{"name":"Neural Network World","volume":"31 1","pages":"47-76"},"PeriodicalIF":0.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67124063","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.2021.31.001
Jin Dai, Yuhong He, Jiayao Li
Dynamic time warping (DTW) is a classical similarity measure for arbitrary length time series. As an effective improvement of DTW, dynamic time warping under limited warping path length (LDTW) oppresses the long-term pathological alignment problem and allows better flexibility. However, since LDTW increases path lengths, it directly leads to higher time-consuming. In this paper, a new method of similarity sequence measurement (ACO LDTW) is proposed by the parallel computing characteristics of ant colony optimization (ACO) algorithm with bio-inspired strategy and the idea of LDTW path restriction. This algorithm searches the optimal path on the restricted distance matrix by simulating the behavior of ant colony parallel foraging. Firstly, the distance matrix is mapped to the 0− 1 matrix of grid method, and the search range of ants is limited by the warping path in LDTW. Secondly, the state transition probability function, pheromone initialization and update mechanism of ACO algorithm are adapted. On the basis of ensuring the accurate results, the convergence rate can be effectively improved. The validity of ACO LDTW is verified by cases. In the 22 data sets of 1NN classification experiment, ACO LDTW has the lowest classification error rate in 16 data sets, and it is shorter than the calculation time of LDTW. At the same time, it is applied to the field of mechanical fault diagnosis and has the ability to solve practical engineering applications. Experiments show that ACO LDTW is more effective in terms of accuracy and computation time.
{"title":"An approach for heuristic parallel LDTW distance optimization method with bio-inspired strategy","authors":"Jin Dai, Yuhong He, Jiayao Li","doi":"10.14311/NNW.2021.31.001","DOIUrl":"https://doi.org/10.14311/NNW.2021.31.001","url":null,"abstract":"Dynamic time warping (DTW) is a classical similarity measure for arbitrary length time series. As an effective improvement of DTW, dynamic time warping under limited warping path length (LDTW) oppresses the long-term pathological alignment problem and allows better flexibility. However, since LDTW increases path lengths, it directly leads to higher time-consuming. In this paper, a new method of similarity sequence measurement (ACO LDTW) is proposed by the parallel computing characteristics of ant colony optimization (ACO) algorithm with bio-inspired strategy and the idea of LDTW path restriction. This algorithm searches the optimal path on the restricted distance matrix by simulating the behavior of ant colony parallel foraging. Firstly, the distance matrix is mapped to the 0− 1 matrix of grid method, and the search range of ants is limited by the warping path in LDTW. Secondly, the state transition probability function, pheromone initialization and update mechanism of ACO algorithm are adapted. On the basis of ensuring the accurate results, the convergence rate can be effectively improved. The validity of ACO LDTW is verified by cases. In the 22 data sets of 1NN classification experiment, ACO LDTW has the lowest classification error rate in 16 data sets, and it is shorter than the calculation time of LDTW. At the same time, it is applied to the field of mechanical fault diagnosis and has the ability to solve practical engineering applications. Experiments show that ACO LDTW is more effective in terms of accuracy and computation time.","PeriodicalId":49765,"journal":{"name":"Neural Network World","volume":"31 1","pages":"1-28"},"PeriodicalIF":0.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67123949","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.2021.31.002
Anosh Babu P. Samson, Sekhara Rao Annavarapu Chandra, Manikant Manikant
: The subcellular localization of proteins is an essential characteristic of human cells, which plays a vital part in understanding distinct functions and cells’ biological processes. The abnormal protein subcellular localization affects protein functionality and may cause many human diseases ranging from metabolic disorders to cancer. Therefore, the prediction of subcellular locations of the proteins is an important task. Artificial neural network has become a popular research topic in machine learning that can achieve remarkable results in learning high-level latent traits. This paper proposes a deep neural network (DNN) model to predict the human protein subcellular locations. The DNN automatically learns high-level representations of abstract features and proteins by examining nonlinear relationships between different subcellular locations. The experimental results have shown that the proposed method gave better results compared with the classical machine learning techniques such as support vector machine and random forest. This model also outperformed the similar model, which uses stacked auto-encoder (SAE) with a softmax classifier.
{"title":"A deep neural network approach for the prediction of protein subcellular localization","authors":"Anosh Babu P. Samson, Sekhara Rao Annavarapu Chandra, Manikant Manikant","doi":"10.14311/NNW.2021.31.002","DOIUrl":"https://doi.org/10.14311/NNW.2021.31.002","url":null,"abstract":": The subcellular localization of proteins is an essential characteristic of human cells, which plays a vital part in understanding distinct functions and cells’ biological processes. The abnormal protein subcellular localization affects protein functionality and may cause many human diseases ranging from metabolic disorders to cancer. Therefore, the prediction of subcellular locations of the proteins is an important task. Artificial neural network has become a popular research topic in machine learning that can achieve remarkable results in learning high-level latent traits. This paper proposes a deep neural network (DNN) model to predict the human protein subcellular locations. The DNN automatically learns high-level representations of abstract features and proteins by examining nonlinear relationships between different subcellular locations. The experimental results have shown that the proposed method gave better results compared with the classical machine learning techniques such as support vector machine and random forest. This model also outperformed the similar model, which uses stacked auto-encoder (SAE) with a softmax classifier.","PeriodicalId":49765,"journal":{"name":"Neural Network World","volume":"31 1","pages":"29-45"},"PeriodicalIF":0.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67124014","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.2021.31.012
S. Jozová, Jaromír Tobiška, I. Nagy
According to the statistics about vehicle accidents, there are many causes such as traffic violations, reduced concentration, micro sleep, hasty aggression, but the most frequent cause of accidents at highways is a carelessness of the driver and violation of keeping a safe distance. Producers of vehicles try to take into account this situation by development of assistance systems which are able to avoid accidents or at least to mitigate its consequences. This urgent situation leaded to the described project of investigation of behavior of drivers in dangerous situations occurring in vehicle driving. The research is to help in solution of the present unsatisfactory situation in driving accidents. The developed decisionmaking algorithm of detection serious driving situations that can lead to accidents was tested in the laboratory of driving simulators in FTS CTU, Prague. The data for its testing resembled highway traffic.
{"title":"On-line recognition of critical driving situations","authors":"S. Jozová, Jaromír Tobiška, I. Nagy","doi":"10.14311/nnw.2021.31.012","DOIUrl":"https://doi.org/10.14311/nnw.2021.31.012","url":null,"abstract":"According to the statistics about vehicle accidents, there are many causes such as traffic violations, reduced concentration, micro sleep, hasty aggression, but the most frequent cause of accidents at highways is a carelessness of the driver and violation of keeping a safe distance. Producers of vehicles try to take into account this situation by development of assistance systems which are able to avoid accidents or at least to mitigate its consequences. This urgent situation leaded to the described project of investigation of behavior of drivers in dangerous situations occurring in vehicle driving. The research is to help in solution of the present unsatisfactory situation in driving accidents. The developed decisionmaking algorithm of detection serious driving situations that can lead to accidents was tested in the laboratory of driving simulators in FTS CTU, Prague. The data for its testing resembled highway traffic.","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":"67124155","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.2021.31.009
T. D. Sajanraj, J. Mulerikkal, S. Raghavendra, R. Vinith, V. Fábera
Metro rail systems are increasingly becoming relevant and inevitable in the context of rising demand for sustainable transportation methods. Metros are therefore going to have a consistently expanding user-base and hence user satisfaction will require meticulous planning. Usage forecast is clearly an integral component of metro planning as it enables forward looking and efficient allocation of resources leading to greater commuter satisfaction. An observation from studying the usage of Kochi Metro Rail Ltd. is that there is a consistently occurring temporal pattern in usage for every station. But the patterns differ from station to station. This hinders the search for a global model representing all stations. We propose a way to overcome this by using station memorizing Long Short-Term Memory (LSTM) which takes in stations in encoded form as input along with usage sequence of stations. This is observed to significantly improve the performance of the model. The proposed architecture with station parameter is compared with algorithms like SVR (support vector regression) and neural network implementation with the best architecture to testify the claim. The proposed model can predict the future flow with an error rate of 0.00127 MSE (mean squared error), which is better than the other models tested.
{"title":"Passenger flow prediction from AFC data using station memorizing LSTM for metro rail systems","authors":"T. D. Sajanraj, J. Mulerikkal, S. Raghavendra, R. Vinith, V. Fábera","doi":"10.14311/nnw.2021.31.009","DOIUrl":"https://doi.org/10.14311/nnw.2021.31.009","url":null,"abstract":"Metro rail systems are increasingly becoming relevant and inevitable in the context of rising demand for sustainable transportation methods. Metros are therefore going to have a consistently expanding user-base and hence user satisfaction will require meticulous planning. Usage forecast is clearly an integral component of metro planning as it enables forward looking and efficient allocation of resources leading to greater commuter satisfaction. An observation from studying the usage of Kochi Metro Rail Ltd. is that there is a consistently occurring temporal pattern in usage for every station. But the patterns differ from station to station. This hinders the search for a global model representing all stations. We propose a way to overcome this by using station memorizing Long Short-Term Memory (LSTM) which takes in stations in encoded form as input along with usage sequence of stations. This is observed to significantly improve the performance of the model. The proposed architecture with station parameter is compared with algorithms like SVR (support vector regression) and neural network implementation with the best architecture to testify the claim. The proposed model can predict the future flow with an error rate of 0.00127 MSE (mean squared error), which is better than the other models tested.","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":"67124347","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：