Pub Date : 2011-11-03DOI: 10.1109/RAICS.2011.6069323
X. Liu, R. Bansal
The work presented in this paper has been developed aiming at how to integrate an online learning controller with an online simulation module to control a complex combustion process, in which some critical process variables which are not easy to be measured using industry instruments. First, it is intended to design a neural network based adaptive controller which owns the ability of learning a real time process. This work consists of designing an online indirect adaptive controller based on radial basis function (RBF) and combining the controller with a numerical combustion process simulated using computational fluid dynamics (CFD). Secondly, the integrated system is simulated in Simulink. Finally, another proportional-integral-derivation (PID) controller is built which substitutes the proposed online learning controller combined with CFD based simulation module to test the proposed control system. The performance of the two different controllers is compared and the results show that the online learning controller is more efficient than PID controller. Moreover, all the work show encouraging results that integrating online learning controller with CFD based online simulation module can provide a new strategy to control a complex combustion process in which instrument reading data is difficult to obtain.
{"title":"Integrating online learning technology with computational fluid dynamics to control combustion process","authors":"X. Liu, R. Bansal","doi":"10.1109/RAICS.2011.6069323","DOIUrl":"https://doi.org/10.1109/RAICS.2011.6069323","url":null,"abstract":"The work presented in this paper has been developed aiming at how to integrate an online learning controller with an online simulation module to control a complex combustion process, in which some critical process variables which are not easy to be measured using industry instruments. First, it is intended to design a neural network based adaptive controller which owns the ability of learning a real time process. This work consists of designing an online indirect adaptive controller based on radial basis function (RBF) and combining the controller with a numerical combustion process simulated using computational fluid dynamics (CFD). Secondly, the integrated system is simulated in Simulink. Finally, another proportional-integral-derivation (PID) controller is built which substitutes the proposed online learning controller combined with CFD based simulation module to test the proposed control system. The performance of the two different controllers is compared and the results show that the online learning controller is more efficient than PID controller. Moreover, all the work show encouraging results that integrating online learning controller with CFD based online simulation module can provide a new strategy to control a complex combustion process in which instrument reading data is difficult to obtain.","PeriodicalId":394515,"journal":{"name":"2011 IEEE Recent Advances in Intelligent Computational Systems","volume":"166 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126224244","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 : 2011-11-03DOI: 10.1109/RAICS.2011.6069422
V. Khetade, Rashtrasant Tukdoji Maharaj
Asynchronous design offers an attractive solution to overcome the problems faced by Networks-on-Chip (NoC) designers such as timing constraints. GALS Asynchronous NoCs requires efficient calibrated clocking scheme which has minimum drift, independent of Process Voltage Temperature(PVT), use minimum static and dynamic power. Clocking scheme should enable smooth synchronization among different clock domain. This paper first presents novel data dependent Pausible clocking scheme with Phase lock loop calibration. It calibrate for phase alignment. Local Clock is calibrated with reference clock generated from reference clock source with PLL mode for the desired frequency which is set with dealylined. This aligned local clock will use for clocking of synchronous module which is wrapped with asynchronous wrapper. It helps in avoiding metastability during crossing of data from one clock domain to another clock domain. Here we present the Petri net models of the Globally Asynchronous and Locally Synchronous(GALS) architectures for speed independent (SI). The models are feed into Petrify to produce logic equations for gate level implementation of asynchronous circuit. The synchronous and asynchronous circuits are implemented on technology of saed90nm provided with Synopsys university program. Simulation is carried on VCS of Synopsys and synthesis on design compiler.
{"title":"Novel Data dependent pausible clocking scheme with pll calibration for GALS NOC","authors":"V. Khetade, Rashtrasant Tukdoji Maharaj","doi":"10.1109/RAICS.2011.6069422","DOIUrl":"https://doi.org/10.1109/RAICS.2011.6069422","url":null,"abstract":"Asynchronous design offers an attractive solution to overcome the problems faced by Networks-on-Chip (NoC) designers such as timing constraints. GALS Asynchronous NoCs requires efficient calibrated clocking scheme which has minimum drift, independent of Process Voltage Temperature(PVT), use minimum static and dynamic power. Clocking scheme should enable smooth synchronization among different clock domain. This paper first presents novel data dependent Pausible clocking scheme with Phase lock loop calibration. It calibrate for phase alignment. Local Clock is calibrated with reference clock generated from reference clock source with PLL mode for the desired frequency which is set with dealylined. This aligned local clock will use for clocking of synchronous module which is wrapped with asynchronous wrapper. It helps in avoiding metastability during crossing of data from one clock domain to another clock domain. Here we present the Petri net models of the Globally Asynchronous and Locally Synchronous(GALS) architectures for speed independent (SI). The models are feed into Petrify to produce logic equations for gate level implementation of asynchronous circuit. The synchronous and asynchronous circuits are implemented on technology of saed90nm provided with Synopsys university program. Simulation is carried on VCS of Synopsys and synthesis on design compiler.","PeriodicalId":394515,"journal":{"name":"2011 IEEE Recent Advances in Intelligent Computational Systems","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123205283","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 : 2011-11-03DOI: 10.1109/RAICS.2011.6069350
Imthias Ahmed, F. Pazheri, Jasmin E A
Reinforcement Learning (RL) is a machine learning paradigm in which learning system learns which action to take in different situations by using a scalar evaluation received from the environment on performing an action. One major feature of this learning method is that it can learn in a stochastic environment. RL has been successfully applied to many power system optimization problems. Economic Scheduling is an important optimization problem to decide the amount of generation to be allocated to each generating unit so that the total cost of generation is minimized without violating system constraints. One scheduling issue is to accommodate the stochastic cost behaviour of the different generating units. In this paper we demonstrate the capacity of RL algorithm to account the stochastic nature of fuel cost.
{"title":"Reinforcement Learning solution for economic scheduling with stochastic cost function","authors":"Imthias Ahmed, F. Pazheri, Jasmin E A","doi":"10.1109/RAICS.2011.6069350","DOIUrl":"https://doi.org/10.1109/RAICS.2011.6069350","url":null,"abstract":"Reinforcement Learning (RL) is a machine learning paradigm in which learning system learns which action to take in different situations by using a scalar evaluation received from the environment on performing an action. One major feature of this learning method is that it can learn in a stochastic environment. RL has been successfully applied to many power system optimization problems. Economic Scheduling is an important optimization problem to decide the amount of generation to be allocated to each generating unit so that the total cost of generation is minimized without violating system constraints. One scheduling issue is to accommodate the stochastic cost behaviour of the different generating units. In this paper we demonstrate the capacity of RL algorithm to account the stochastic nature of fuel cost.","PeriodicalId":394515,"journal":{"name":"2011 IEEE Recent Advances in Intelligent Computational Systems","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131613831","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 : 2011-11-03DOI: 10.1109/RAICS.2011.6069291
Amit Dave, Jitendra Sharma, Ashutosh Dutt, Anil Sukheja
Space Applications Center (SAC) of Indian Space Research Organization (ISRO) designs and develops electro optical sensors for earth observations and inter-planetary exploration missions. The sensors are fairly complex systems involving linear/area imaging elements, optics, electronics having large number of spectral bands, making their development a highly challenging task. To ensure in-orbit performance, the sensors are exhaustively tested on ground before being flown. XSCoPE (UNIX based Software System for Payload Evaluation) caters to the evaluation requirement throughout the development cycle of the cameras accomplishing data acquisition, parametric evaluation and optimizations. The paper describes an instrument control protocol (ICP) developed as part of the system and provides an abstraction layer in order to seamlessly interface with the test instrumentation having different underlying hardware interfaces. The protocol specifically developed for tests involving repeated measurements and automation, is scalable, generic in nature and can be adopted for different situations. Details of implementation of the protocol are given citing spectral response measurement test as a specific case to explain the idea.
{"title":"Generic protocol for seamless control of test instrumentation towards realization of electro optical sensors","authors":"Amit Dave, Jitendra Sharma, Ashutosh Dutt, Anil Sukheja","doi":"10.1109/RAICS.2011.6069291","DOIUrl":"https://doi.org/10.1109/RAICS.2011.6069291","url":null,"abstract":"Space Applications Center (SAC) of Indian Space Research Organization (ISRO) designs and develops electro optical sensors for earth observations and inter-planetary exploration missions. The sensors are fairly complex systems involving linear/area imaging elements, optics, electronics having large number of spectral bands, making their development a highly challenging task. To ensure in-orbit performance, the sensors are exhaustively tested on ground before being flown. XSCoPE (UNIX based Software System for Payload Evaluation) caters to the evaluation requirement throughout the development cycle of the cameras accomplishing data acquisition, parametric evaluation and optimizations. The paper describes an instrument control protocol (ICP) developed as part of the system and provides an abstraction layer in order to seamlessly interface with the test instrumentation having different underlying hardware interfaces. The protocol specifically developed for tests involving repeated measurements and automation, is scalable, generic in nature and can be adopted for different situations. Details of implementation of the protocol are given citing spectral response measurement test as a specific case to explain the idea.","PeriodicalId":394515,"journal":{"name":"2011 IEEE Recent Advances in Intelligent Computational Systems","volume":"139 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131625194","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 : 2011-11-03DOI: 10.1109/RAICS.2011.6069273
Chandrasekhar Yammani, Naresh Siripurapu, Sydulu Maheswarapu, S. Matam
Electrical power consumption is increasing day by day, complicating the operation of distribution systems. Distributed Energy Resource (DER) integration in distribution system is one of the options which give benefits like loss minimization, peak shaving, over load relieving and improved reliability. This paper presents an algorithm for optimal placement and size of the DER considering system loss minimization and voltage profile improvement as objective functions. This work is tested on IEEE 15, 33, 69 and 85 bus distribution systems. For all cases studied, a new heuristic optimization technique Shuffled Frog Leaping Algorithm (SFLA) is applied and current injection based distribution load flow method is employed. Further the results are compared with those results obtained by Particle swarm optimization (PSO) method and found to be encouraging.
{"title":"Optimal placement and sizing of the DER in distribution systems using Shuffled Frog Leap Algorithm","authors":"Chandrasekhar Yammani, Naresh Siripurapu, Sydulu Maheswarapu, S. Matam","doi":"10.1109/RAICS.2011.6069273","DOIUrl":"https://doi.org/10.1109/RAICS.2011.6069273","url":null,"abstract":"Electrical power consumption is increasing day by day, complicating the operation of distribution systems. Distributed Energy Resource (DER) integration in distribution system is one of the options which give benefits like loss minimization, peak shaving, over load relieving and improved reliability. This paper presents an algorithm for optimal placement and size of the DER considering system loss minimization and voltage profile improvement as objective functions. This work is tested on IEEE 15, 33, 69 and 85 bus distribution systems. For all cases studied, a new heuristic optimization technique Shuffled Frog Leaping Algorithm (SFLA) is applied and current injection based distribution load flow method is employed. Further the results are compared with those results obtained by Particle swarm optimization (PSO) method and found to be encouraging.","PeriodicalId":394515,"journal":{"name":"2011 IEEE Recent Advances in Intelligent Computational Systems","volume":"283 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121820292","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 : 2011-11-03DOI: 10.1109/RAICS.2011.6069313
P. Kharat, Dr. Sanjay Vasant Dudul
Epilepsy is a common neurological disorder that is characterized by recurrent unprovoked seizures. About 40 to 50 million people worldwide have epilepsy. In this paper the authors present clinical decision support system (DSS) for the diagnosis of epilepsy. The validity of neural network to diagnose the epilepsy is checked and the most suitable neural network is recommended for the diagnosis of epilepsy. Three different diagnosis of Normal, Epileptic (interictal) and Epileptic (ictal), where estimated by a neural network. The results showed that we were able to achieve 100% results for testing data by using Jordan/Elman neural network
{"title":"Clinical decision support system based on Jordan/Elman neural networks","authors":"P. Kharat, Dr. Sanjay Vasant Dudul","doi":"10.1109/RAICS.2011.6069313","DOIUrl":"https://doi.org/10.1109/RAICS.2011.6069313","url":null,"abstract":"Epilepsy is a common neurological disorder that is characterized by recurrent unprovoked seizures. About 40 to 50 million people worldwide have epilepsy. In this paper the authors present clinical decision support system (DSS) for the diagnosis of epilepsy. The validity of neural network to diagnose the epilepsy is checked and the most suitable neural network is recommended for the diagnosis of epilepsy. Three different diagnosis of Normal, Epileptic (interictal) and Epileptic (ictal), where estimated by a neural network. The results showed that we were able to achieve 100% results for testing data by using Jordan/Elman neural network","PeriodicalId":394515,"journal":{"name":"2011 IEEE Recent Advances in Intelligent Computational Systems","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123727047","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 : 2011-11-03DOI: 10.1109/RAICS.2011.6069387
Azeema Sultana, M. Meenakshi
This paper presents design, implementation and real time validation of Image binarization process using weight based clustering algorithm, which uses the clustering property of neural network. The generic technique for image binarization requires choosing a threshold value and comparing the pixel values with the threshold and classifying as black and white. The proposed algorithm calculates a global optimum threshold by learning from the image background and foreground features. A simple two-weight neural network is implemented to cluster the foreground and background pixels. Here an adaptive thresholding technique based on competitive learning is selected for Weight Updating. The developed algorithm is implemented on a FPGA platform hardware system, which consists of two functional blocks. The first block is used to obtain the threshold value for the image frame; another block to apply the threshold value to the frame. This parallelism and the simple hardware component of both blocks make this approach suitable for real-time applications, while the performance remains comparable with the Otsu technique frequently used in off-line threshold determination. Results from the proposed algorithm are presented for numerous examples, both from simulations and experimentally using the FPGA.
{"title":"Design and development of FPGA based adaptive thresholder for image processing applications","authors":"Azeema Sultana, M. Meenakshi","doi":"10.1109/RAICS.2011.6069387","DOIUrl":"https://doi.org/10.1109/RAICS.2011.6069387","url":null,"abstract":"This paper presents design, implementation and real time validation of Image binarization process using weight based clustering algorithm, which uses the clustering property of neural network. The generic technique for image binarization requires choosing a threshold value and comparing the pixel values with the threshold and classifying as black and white. The proposed algorithm calculates a global optimum threshold by learning from the image background and foreground features. A simple two-weight neural network is implemented to cluster the foreground and background pixels. Here an adaptive thresholding technique based on competitive learning is selected for Weight Updating. The developed algorithm is implemented on a FPGA platform hardware system, which consists of two functional blocks. The first block is used to obtain the threshold value for the image frame; another block to apply the threshold value to the frame. This parallelism and the simple hardware component of both blocks make this approach suitable for real-time applications, while the performance remains comparable with the Otsu technique frequently used in off-line threshold determination. Results from the proposed algorithm are presented for numerous examples, both from simulations and experimentally using the FPGA.","PeriodicalId":394515,"journal":{"name":"2011 IEEE Recent Advances in Intelligent Computational Systems","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115341691","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 : 2011-11-03DOI: 10.1109/RAICS.2011.6069373
M. Meenakshi, M. Bhat
This paper presents a generic design methodology of robust fixed order H2 controller and onboard computer for Micro air Vehicles. The efficacy of the proposed method is demonstrated by designing a fixed order robust H2 stability augmentation system for lateral dynamics of a Micro air Vehicle, named Sarika-1. Strengthened Discrete Optimal Projection Equations, which approximate the first order necessary optimality condition, are used for the controller design. Effect of low frequency gust disturbance and high frequency sensor noise is alleviated through the output sensitivity and control sensitivity minimization. Digital Signal Processor (DSP) based onboard computer named Flight Instrumentation Controller (FIC) is designed to operate under automatic or manual mode. The controller is ported on to the flight computer, and subsequently, it is validated through the real-time hardware-in-loop-simulation. The responses obtained from the hardware-in-loop-simulation compares well with those obtained from the off-line simulation.
{"title":"Lateral stability augmentation system for Micro air Vehicle - Towards autonomous flight","authors":"M. Meenakshi, M. Bhat","doi":"10.1109/RAICS.2011.6069373","DOIUrl":"https://doi.org/10.1109/RAICS.2011.6069373","url":null,"abstract":"This paper presents a generic design methodology of robust fixed order H2 controller and onboard computer for Micro air Vehicles. The efficacy of the proposed method is demonstrated by designing a fixed order robust H2 stability augmentation system for lateral dynamics of a Micro air Vehicle, named Sarika-1. Strengthened Discrete Optimal Projection Equations, which approximate the first order necessary optimality condition, are used for the controller design. Effect of low frequency gust disturbance and high frequency sensor noise is alleviated through the output sensitivity and control sensitivity minimization. Digital Signal Processor (DSP) based onboard computer named Flight Instrumentation Controller (FIC) is designed to operate under automatic or manual mode. The controller is ported on to the flight computer, and subsequently, it is validated through the real-time hardware-in-loop-simulation. The responses obtained from the hardware-in-loop-simulation compares well with those obtained from the off-line simulation.","PeriodicalId":394515,"journal":{"name":"2011 IEEE Recent Advances in Intelligent Computational Systems","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115480847","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 : 2011-11-03DOI: 10.1109/RAICS.2011.6069383
P. Deepa, K. Suresh
Multimedia datas are growing at a fast rate. Music, which is one of the most popular types of online information, is a part of multimedia data and there are now hundreds of music streaming and downloading services operating on the World-Wide Web. Some of the music collections available are approaching the scale of ten million tracks and this has posed a major challenge for searching, retrieving, and organizing music content. So there is a need for automatic music classification methods for organizing these collections into different classes according to the certain information. In this work, a new effective feature extraction method is proposed for the classification of music according to the genre. Based on the calculated features, a new feature set is proposed to characterize the music content. The multi-class SVM is used for the classification purposes, which is one of the best classifying engines among the existing ones. Experiment result shows that the proposed method outperforms the existing methods implemented on the same database. A retrieval method is also proposed and its accuracy is verified using the proposed classification algorithm. The obtained accuracy indicates that the classifier and the retriever are very efficient compared to the existing ones.
{"title":"An optimized feature set for music genre classification based on Support Vector Machine","authors":"P. Deepa, K. Suresh","doi":"10.1109/RAICS.2011.6069383","DOIUrl":"https://doi.org/10.1109/RAICS.2011.6069383","url":null,"abstract":"Multimedia datas are growing at a fast rate. Music, which is one of the most popular types of online information, is a part of multimedia data and there are now hundreds of music streaming and downloading services operating on the World-Wide Web. Some of the music collections available are approaching the scale of ten million tracks and this has posed a major challenge for searching, retrieving, and organizing music content. So there is a need for automatic music classification methods for organizing these collections into different classes according to the certain information. In this work, a new effective feature extraction method is proposed for the classification of music according to the genre. Based on the calculated features, a new feature set is proposed to characterize the music content. The multi-class SVM is used for the classification purposes, which is one of the best classifying engines among the existing ones. Experiment result shows that the proposed method outperforms the existing methods implemented on the same database. A retrieval method is also proposed and its accuracy is verified using the proposed classification algorithm. The obtained accuracy indicates that the classifier and the retriever are very efficient compared to the existing ones.","PeriodicalId":394515,"journal":{"name":"2011 IEEE Recent Advances in Intelligent Computational Systems","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122640322","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 : 2011-11-03DOI: 10.1109/RAICS.2011.6069300
Soumadip Ghosh, A. Nag, Debasish Biswas, J. Singh, S. Biswas, D. Sarkar, P. Sarkar
Weather Data Mining is a form of Data mining concerned with finding hidden patterns inside largely available meteorological data, so that the information retrieved can be transformed into usable knowledge. A variety of data mining tools and techniques are available in the industry, but they have been used in a very limited way for meteorological data. In this paper, a neural network-based algorithm for predicting the atmosphere for a future time and a given location is presented. We have used Back Propagation Neural (BPN) Network for initial modelling. The results obtained by BPN model are fed to a Hopfield Network. The performance of our proposed ANN-based method (BPN and Hopfield Network based combined approach) tested on 3 years weather data set comprising 15000 records containing attributes like temperature, humidity and wind speed. The prediction error is found to be very less and the learning converges very sharply. The main focus of this paper is based on predictive data mining by which we can extract interesting (non-trivial, implicit, previously unknown and potentially useful) patterns or knowledge from huge amount of meteorological data.
{"title":"Weather Data Mining using Artificial Neural Network","authors":"Soumadip Ghosh, A. Nag, Debasish Biswas, J. Singh, S. Biswas, D. Sarkar, P. Sarkar","doi":"10.1109/RAICS.2011.6069300","DOIUrl":"https://doi.org/10.1109/RAICS.2011.6069300","url":null,"abstract":"Weather Data Mining is a form of Data mining concerned with finding hidden patterns inside largely available meteorological data, so that the information retrieved can be transformed into usable knowledge. A variety of data mining tools and techniques are available in the industry, but they have been used in a very limited way for meteorological data. In this paper, a neural network-based algorithm for predicting the atmosphere for a future time and a given location is presented. We have used Back Propagation Neural (BPN) Network for initial modelling. The results obtained by BPN model are fed to a Hopfield Network. The performance of our proposed ANN-based method (BPN and Hopfield Network based combined approach) tested on 3 years weather data set comprising 15000 records containing attributes like temperature, humidity and wind speed. The prediction error is found to be very less and the learning converges very sharply. The main focus of this paper is based on predictive data mining by which we can extract interesting (non-trivial, implicit, previously unknown and potentially useful) patterns or knowledge from huge amount of meteorological data.","PeriodicalId":394515,"journal":{"name":"2011 IEEE Recent Advances in Intelligent Computational Systems","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125281975","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：