Pub Date : 2017-11-01DOI: 10.1109/ICSAI.2017.8248489
Jianyu Lin
A new 3D transform video coding algorithm is introduced, which does not use motion compensation. More independent and highly efficient algorithms are employed for each key step of the transform coding. For the transform step, the SCWP (Spectral Condensed Wavelet Packet) is adopted. For the quantization step, a trimming process is implemented, which keeps the bit allocation function of the significant propagation technique but is independent from the entropy coding step. For the entropy coding step, a novel entropy coding technique based upon binary run-length coding is proposed. This binary entropy coding can be applied to multiple symbol source coding, and it approaches an optimal efficiency bound which is within 1.5% of the source entropy when the source approaches iid. Principally, the complexity of the proposed transform video coding algorithm is comparable to that of a 2D still image transform coding algorithm. However, its compression performance is competitive to HEVC at high compression bitrates.
{"title":"Improving the compression efficiency for transform video coding","authors":"Jianyu Lin","doi":"10.1109/ICSAI.2017.8248489","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248489","url":null,"abstract":"A new 3D transform video coding algorithm is introduced, which does not use motion compensation. More independent and highly efficient algorithms are employed for each key step of the transform coding. For the transform step, the SCWP (Spectral Condensed Wavelet Packet) is adopted. For the quantization step, a trimming process is implemented, which keeps the bit allocation function of the significant propagation technique but is independent from the entropy coding step. For the entropy coding step, a novel entropy coding technique based upon binary run-length coding is proposed. This binary entropy coding can be applied to multiple symbol source coding, and it approaches an optimal efficiency bound which is within 1.5% of the source entropy when the source approaches iid. Principally, the complexity of the proposed transform video coding algorithm is comparable to that of a 2D still image transform coding algorithm. However, its compression performance is competitive to HEVC at high compression bitrates.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131244811","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 : 2017-11-01DOI: 10.1109/ICSAI.2017.8248455
Jiaqi Wang, Qinghua Huang, Xin Zhang
Ultrasound elastography is a common medical imaging applied in medical applications since it can provide the tissue hardness information. Most ultrasound elastography techniques are window based methods. The key of the quasi-static ultrasound elastography is to do the similarity measure between two windows from pre- and post-compression to compute the displacement. In view of this situation, the window size has an important influence on the strain images quality. In this paper, a reasonable method utilizing PSO algorithm to search for the optimal window length for different data is brought out to solve this problem. The displacement map can be estimated with the optimal window length using the normalized cross correlation method. And a spatial derivative operator is applied to estimate the strain map. The strain images with the fixed window length 12 and 50 and the optimal window length using PSO algorithm are compared in this paper. Results show that using PSO algorithm to search for the optimal window length can improve the SNR and CNR of strain images.
{"title":"Ultrasound elastography based on the normalized cross-correlation and the PSO algorithm","authors":"Jiaqi Wang, Qinghua Huang, Xin Zhang","doi":"10.1109/ICSAI.2017.8248455","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248455","url":null,"abstract":"Ultrasound elastography is a common medical imaging applied in medical applications since it can provide the tissue hardness information. Most ultrasound elastography techniques are window based methods. The key of the quasi-static ultrasound elastography is to do the similarity measure between two windows from pre- and post-compression to compute the displacement. In view of this situation, the window size has an important influence on the strain images quality. In this paper, a reasonable method utilizing PSO algorithm to search for the optimal window length for different data is brought out to solve this problem. The displacement map can be estimated with the optimal window length using the normalized cross correlation method. And a spatial derivative operator is applied to estimate the strain map. The strain images with the fixed window length 12 and 50 and the optimal window length using PSO algorithm are compared in this paper. Results show that using PSO algorithm to search for the optimal window length can improve the SNR and CNR of strain images.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122010625","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 : 2017-11-01DOI: 10.1109/ICSAI.2017.8248355
Alessandro Palla, D. Moloney, L. Fanucci
In this work, we propose a 3D scene reconstruction algorithm based on a fully convolutional 3D denoising autoencoder neural network. The network is capable of reconstructing a full scene from a single depth image by creating a 3D representation of it and automatically filling holes and inserting hidden elements. We exploit the fact that our neural network is capable of generalizing object shapes by inferring similarities in geometry. Our fully convolutional architecture enables the network to be unconstrained by a fixed 3D shape, and so it is capable of successfully reconstructing arbitrary scene sizes. Our algorithm was evaluated on a real word dataset of tabletop scenes acquired using a Kinect and processed using KinectFusion software in order to obtain ground truth for network training and evaluation. Extensive measurements show that our deep neural network architecture outperforms the previous state of the art both in terms of precision and recall for the scene reconstruction task. The network has been broadly profiled in terms of memory footprint, number of floating point operations, inference time and power consumption in CPU, GPU and embedded devices. Its small memory footprint and its low computation requirements enable low power, memory constrained, real time always-on embedded applications such as autonomous vehicles, warehouse robots, interactive gaming controllers and drones.
{"title":"Fully convolutional denoising autoencoder for 3D scene reconstruction from a single depth image","authors":"Alessandro Palla, D. Moloney, L. Fanucci","doi":"10.1109/ICSAI.2017.8248355","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248355","url":null,"abstract":"In this work, we propose a 3D scene reconstruction algorithm based on a fully convolutional 3D denoising autoencoder neural network. The network is capable of reconstructing a full scene from a single depth image by creating a 3D representation of it and automatically filling holes and inserting hidden elements. We exploit the fact that our neural network is capable of generalizing object shapes by inferring similarities in geometry. Our fully convolutional architecture enables the network to be unconstrained by a fixed 3D shape, and so it is capable of successfully reconstructing arbitrary scene sizes. Our algorithm was evaluated on a real word dataset of tabletop scenes acquired using a Kinect and processed using KinectFusion software in order to obtain ground truth for network training and evaluation. Extensive measurements show that our deep neural network architecture outperforms the previous state of the art both in terms of precision and recall for the scene reconstruction task. The network has been broadly profiled in terms of memory footprint, number of floating point operations, inference time and power consumption in CPU, GPU and embedded devices. Its small memory footprint and its low computation requirements enable low power, memory constrained, real time always-on embedded applications such as autonomous vehicles, warehouse robots, interactive gaming controllers and drones.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116203419","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 : 2017-11-01DOI: 10.1109/ICSAI.2017.8248493
Munyaradzi Munochiveyi, Xiaohui Zhao, Hui Liang
Time-reversal communication is considered as a potential Green wireless communications scheme for cognitive radio networks. The network base station utilizes time-reversal communication to exploit multi-path propagation, in order to provide spatial focusing at an intended cognitive radio. This reduces interference to other radios in the network. However, time-reversal spatial focusing performance is dependent on robust channel estimation. Under time-varying channel conditions or imperfect channel estimation, the performance of time-reversal communication deteriorates immensely. To ameliorate this deterioration, we design a non-stationary time-varying non-causal Wiener filter based on the time-varying spectrum. The time-varying spectrum is obtained by first modeling the time-varying channel as a locally stationary process. Which means that over small time intervals the channel is approximately stationary, and correlated inside these stationary intervals. Consequently, the time-varying spectrum can be easily calculated by estimating the covariance of the Wigner-Ville distribution of each locally stationary process. Based on that premise, the goal of this paper is to investigate through simulation, the performance of the proposed Wiener filter versus the conventional optimal Wiener filter when the time-varying channel is modeled as a locally stationary process. The performance is derived by computing the symbol error rate (SER), minimum mean square error (MMSE) and the output versus input signal-to-noise ratio (SNR).
{"title":"Non-stationary wiener filter design for channel estimation of PS-OFDM cognitive radio using time-reversal communication: A locally stationary approach","authors":"Munyaradzi Munochiveyi, Xiaohui Zhao, Hui Liang","doi":"10.1109/ICSAI.2017.8248493","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248493","url":null,"abstract":"Time-reversal communication is considered as a potential Green wireless communications scheme for cognitive radio networks. The network base station utilizes time-reversal communication to exploit multi-path propagation, in order to provide spatial focusing at an intended cognitive radio. This reduces interference to other radios in the network. However, time-reversal spatial focusing performance is dependent on robust channel estimation. Under time-varying channel conditions or imperfect channel estimation, the performance of time-reversal communication deteriorates immensely. To ameliorate this deterioration, we design a non-stationary time-varying non-causal Wiener filter based on the time-varying spectrum. The time-varying spectrum is obtained by first modeling the time-varying channel as a locally stationary process. Which means that over small time intervals the channel is approximately stationary, and correlated inside these stationary intervals. Consequently, the time-varying spectrum can be easily calculated by estimating the covariance of the Wigner-Ville distribution of each locally stationary process. Based on that premise, the goal of this paper is to investigate through simulation, the performance of the proposed Wiener filter versus the conventional optimal Wiener filter when the time-varying channel is modeled as a locally stationary process. The performance is derived by computing the symbol error rate (SER), minimum mean square error (MMSE) and the output versus input signal-to-noise ratio (SNR).","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122824916","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 : 2017-11-01DOI: 10.1109/ICSAI.2017.8248273
N. Dimitrov, A. Topalov, Sevil A. Ahmed, Pavel Radev
The demand of the industry for high performance electric motors has significantly increased nowadays. This has boosted the usage of permanent magnet brushless synchronous motors (BLSM) in many applications where the accuracy and performance requirements are high. Further improvement of the BLSM drive systems performance can be achieved by providing them with adaptive control capabilities. The relative complexity of adaptive control schemes and algorithms and the computational load that they impose have prevented until recently their practical implementation into the industrial servo systems. In this investigation, a neuro-adaptive control scheme where the rule for parameter adaptation is designed by taking into account the variable structure control (VSC) concepts and Lyapunov stability, is proposed and embedded into an inexpensive, available on the market, position control system for brushless synchronous servomotors. The experimental tests have been carried on using compact and flexible, based on open hardware and software concept, dual-axis motion controllers PMC201/PMC202 manufactured by the PicoMotion Inc. The applied software has been written using the Motion Control Framework software platform, provided together with the above controllers. The results obtained with the proposed neuro-adaptive control scheme have been compared to those obtained using the originally built into the system PI controller. The experiments have shown that the implemented advanced adaptive control approach is practically viable and can be embedded into the industrial motion control systems which will lead to their improved performance.
{"title":"Implementing neuro-adaptive control algorithms with sliding mode learning on industrial servo drives","authors":"N. Dimitrov, A. Topalov, Sevil A. Ahmed, Pavel Radev","doi":"10.1109/ICSAI.2017.8248273","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248273","url":null,"abstract":"The demand of the industry for high performance electric motors has significantly increased nowadays. This has boosted the usage of permanent magnet brushless synchronous motors (BLSM) in many applications where the accuracy and performance requirements are high. Further improvement of the BLSM drive systems performance can be achieved by providing them with adaptive control capabilities. The relative complexity of adaptive control schemes and algorithms and the computational load that they impose have prevented until recently their practical implementation into the industrial servo systems. In this investigation, a neuro-adaptive control scheme where the rule for parameter adaptation is designed by taking into account the variable structure control (VSC) concepts and Lyapunov stability, is proposed and embedded into an inexpensive, available on the market, position control system for brushless synchronous servomotors. The experimental tests have been carried on using compact and flexible, based on open hardware and software concept, dual-axis motion controllers PMC201/PMC202 manufactured by the PicoMotion Inc. The applied software has been written using the Motion Control Framework software platform, provided together with the above controllers. The results obtained with the proposed neuro-adaptive control scheme have been compared to those obtained using the originally built into the system PI controller. The experiments have shown that the implemented advanced adaptive control approach is practically viable and can be embedded into the industrial motion control systems which will lead to their improved performance.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121121716","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 : 2017-11-01DOI: 10.1109/ICSAI.2017.8248289
J. Ferreira, Tao Liu, Portugal Coimbra, Paulo Coimbra
The main objective of this research project is to develop a low cost computerized system to automatically diagnose gait disorders and characterize their severity. The system uses 2 video cameras to provide a 3D position acquisition system connected to a personal computer. The patient gait and posture are analyzed from the data acquired by a vision-based gait acquisition system. The whole system will be an important novel tool in medical rehabilitation and diagnosis, resulting on a more effective functional rehabilitation of a patient's gait, assessing their clinical evolution and solving the limitations of the current subjective gait diagnosis tools. The system allows the calculation of 17 human gait joint trajectories. This system will provide a much more objective understanding of the patient's clinical evolution, and thus enables a more effective functional rehabilitation of a patient's gait. In this paper it is presented the selection of the relevant diagnosis parameters of the gait patterns, which is one of the steps to get to the main objective, the automatic diagnosis of human gaits.
{"title":"Parameter analysis and selection for human gait characterization using a low cost vision system","authors":"J. Ferreira, Tao Liu, Portugal Coimbra, Paulo Coimbra","doi":"10.1109/ICSAI.2017.8248289","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248289","url":null,"abstract":"The main objective of this research project is to develop a low cost computerized system to automatically diagnose gait disorders and characterize their severity. The system uses 2 video cameras to provide a 3D position acquisition system connected to a personal computer. The patient gait and posture are analyzed from the data acquired by a vision-based gait acquisition system. The whole system will be an important novel tool in medical rehabilitation and diagnosis, resulting on a more effective functional rehabilitation of a patient's gait, assessing their clinical evolution and solving the limitations of the current subjective gait diagnosis tools. The system allows the calculation of 17 human gait joint trajectories. This system will provide a much more objective understanding of the patient's clinical evolution, and thus enables a more effective functional rehabilitation of a patient's gait. In this paper it is presented the selection of the relevant diagnosis parameters of the gait patterns, which is one of the steps to get to the main objective, the automatic diagnosis of human gaits.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121194899","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}
The traditional threat assessment (TA) methods are confronted with the problems that most of them only focus on the static threat of a single target and the threshold of threat degree fusion is hard to set. For this reason, a novel DBN (dynamic Bayesian network) based TA algorithm is proposed. In the proposed algorithm, firstly, DBN is constructed with various factors, i.e., terrain, weather, time, relative strength, distance and velocity vector, for the TA of group targets. Then, the fast approximate inference is implemented according to Markov property. Finally, the probabilities of threat degrees are integrated into the continuous threat index and the discrete threat degree. Simulation results show that the proposed algorithm can be used to reliably and dynamically evaluate the threat of group targets in complex environment.
{"title":"A novel dynamic Bayesian network based threat assessment algorithm","authors":"Zhen-Hua Fan, Bengbeng Shi, Jin-Yong Chen, Tong-Le Duan","doi":"10.1109/ICSAI.2017.8248362","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248362","url":null,"abstract":"The traditional threat assessment (TA) methods are confronted with the problems that most of them only focus on the static threat of a single target and the threshold of threat degree fusion is hard to set. For this reason, a novel DBN (dynamic Bayesian network) based TA algorithm is proposed. In the proposed algorithm, firstly, DBN is constructed with various factors, i.e., terrain, weather, time, relative strength, distance and velocity vector, for the TA of group targets. Then, the fast approximate inference is implemented according to Markov property. Finally, the probabilities of threat degrees are integrated into the continuous threat index and the discrete threat degree. Simulation results show that the proposed algorithm can be used to reliably and dynamically evaluate the threat of group targets in complex environment.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127042464","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 : 2017-11-01DOI: 10.1109/ICSAI.2017.8248564
Yan-hua Zeng, Y. Fu, Dong-mei Tang, Yiqi Zhu
Standard silicon wafer, which is standard instruments for semiconductors, large scale integrated circuits and photovoltaic industries, is the internationally accepted physical standard. The thickness of silicon wafer is directly related to the performance of integrated devices or performance of photoelectric conversion. In this paper, a standard measuring device for thickness of silicon wafer based on double-layer embedded table is introduced. With sensor compensation technology based on laser compensation principle, the inductance used in measurement is linearly compensated, resulting in improving the accuracy of standard silicon wafer thickness measurement. By measuring the standard silicon wafers with different diameter and thickness, the effectiveness of the method is verified.
{"title":"Standard measuring device for thickness of silicon wafer based on laser compensation system","authors":"Yan-hua Zeng, Y. Fu, Dong-mei Tang, Yiqi Zhu","doi":"10.1109/ICSAI.2017.8248564","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248564","url":null,"abstract":"Standard silicon wafer, which is standard instruments for semiconductors, large scale integrated circuits and photovoltaic industries, is the internationally accepted physical standard. The thickness of silicon wafer is directly related to the performance of integrated devices or performance of photoelectric conversion. In this paper, a standard measuring device for thickness of silicon wafer based on double-layer embedded table is introduced. With sensor compensation technology based on laser compensation principle, the inductance used in measurement is linearly compensated, resulting in improving the accuracy of standard silicon wafer thickness measurement. By measuring the standard silicon wafers with different diameter and thickness, the effectiveness of the method is verified.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127228402","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 : 2017-11-01DOI: 10.1109/ICSAI.2017.8248475
Shengyong Li, X. Ai, Ronghua Wu, Nianlong Zeng
Edge detection and extraction is very important in image processing and recognition whose algorithm directly affect the performance of the entire detection system. The ability of image denoising and the accuracy of edge detection are both required high, especially in the complex natural environment at sea. Most of image edge examination algorithms before have limitations and disadvantages of their own, so there is still room for improvement in this area. I'd like to put forward a sea-skyline detection algorithm and give simulation examples based on image filtering processing and gray image corrosion in the complex background of natural environment at sea, aiming at acquiring preferable ability of denoising and target extraction on the premise of ensuring the detection accuracy.
{"title":"Infrared target edge detectionin in sea sky backgrand","authors":"Shengyong Li, X. Ai, Ronghua Wu, Nianlong Zeng","doi":"10.1109/ICSAI.2017.8248475","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248475","url":null,"abstract":"Edge detection and extraction is very important in image processing and recognition whose algorithm directly affect the performance of the entire detection system. The ability of image denoising and the accuracy of edge detection are both required high, especially in the complex natural environment at sea. Most of image edge examination algorithms before have limitations and disadvantages of their own, so there is still room for improvement in this area. I'd like to put forward a sea-skyline detection algorithm and give simulation examples based on image filtering processing and gray image corrosion in the complex background of natural environment at sea, aiming at acquiring preferable ability of denoising and target extraction on the premise of ensuring the detection accuracy.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125453789","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 : 2017-11-01DOI: 10.1109/ICSAI.2017.8248356
Y. Li, Yi An, N. Yu, Rui-bo Zhu
A new model of multiresolution process neural network (MRPNN) which incorporates the characteristics of hierarchical, multiresolution and local learning capability is proposed based on the multiresolution analysis theory and process neural network model. This type of neural network facilitates in tackling with continuous input signals, which makes it possible to forecast time series problem. In addition, in order to approximate the nonlinear system, the hidden layer is used to deal with the nonlinear and complexity problems. A novel learning algorithm is given to expand the input functions and network weight functions based on the expansion of the orthogonal basis functions, subsequently The learning algorithm then builds the network by locating high error regions and adding nodes that get its activation function from the higher resolution space of the current local node, and its support falls within the high error region. Finally, the network is used to forecast the medium-term load of power system. Simulation results show that the network has good convergence and high accuracy. This method provides an effective solution to medium-term load forecasting in power system.
{"title":"Multiresolution process neural network and its learning algorithm","authors":"Y. Li, Yi An, N. Yu, Rui-bo Zhu","doi":"10.1109/ICSAI.2017.8248356","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248356","url":null,"abstract":"A new model of multiresolution process neural network (MRPNN) which incorporates the characteristics of hierarchical, multiresolution and local learning capability is proposed based on the multiresolution analysis theory and process neural network model. This type of neural network facilitates in tackling with continuous input signals, which makes it possible to forecast time series problem. In addition, in order to approximate the nonlinear system, the hidden layer is used to deal with the nonlinear and complexity problems. A novel learning algorithm is given to expand the input functions and network weight functions based on the expansion of the orthogonal basis functions, subsequently The learning algorithm then builds the network by locating high error regions and adding nodes that get its activation function from the higher resolution space of the current local node, and its support falls within the high error region. Finally, the network is used to forecast the medium-term load of power system. Simulation results show that the network has good convergence and high accuracy. This method provides an effective solution to medium-term load forecasting in power system.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124151068","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：