Pub Date : 2013-11-01DOI: 10.1109/ICCSCE.2013.6719982
A. Alkahtani, F. H. Nordin, Z. Sharrif
Electric field emission of electrical appliances has become an important problem, especially when testing for safety and compliance with regulations of electromagnetic compatibility (EMC). To confirm the safety and compliance of an electrical appliance, it is important to measure the levels of the emitted electric and magnetic fields from this appliance and compare them to the exposure limit values set by the international standards. Moreover, modeling these emitted fields can aid understanding their characteristics and ease investigating how different systems react to such emission. However, a good model depends mainly on the accuracy and robustness of the measurement methodology. Hence, the aim of this paper is to present a measurement methodology and a frequency domain model for the emitted electric field of vacuum cleaners using system identification tools. The proposed model is a data-driven model where the recorded signal is used to construct the model using polynomial model estimation methods. Measurement setup, related work and the model equation are presented accordingly.
{"title":"Measurement and estimation of electric field emission of a vacuum cleaner","authors":"A. Alkahtani, F. H. Nordin, Z. Sharrif","doi":"10.1109/ICCSCE.2013.6719982","DOIUrl":"https://doi.org/10.1109/ICCSCE.2013.6719982","url":null,"abstract":"Electric field emission of electrical appliances has become an important problem, especially when testing for safety and compliance with regulations of electromagnetic compatibility (EMC). To confirm the safety and compliance of an electrical appliance, it is important to measure the levels of the emitted electric and magnetic fields from this appliance and compare them to the exposure limit values set by the international standards. Moreover, modeling these emitted fields can aid understanding their characteristics and ease investigating how different systems react to such emission. However, a good model depends mainly on the accuracy and robustness of the measurement methodology. Hence, the aim of this paper is to present a measurement methodology and a frequency domain model for the emitted electric field of vacuum cleaners using system identification tools. The proposed model is a data-driven model where the recorded signal is used to construct the model using polynomial model estimation methods. Measurement setup, related work and the model equation are presented accordingly.","PeriodicalId":319285,"journal":{"name":"2013 IEEE International Conference on Control System, Computing and Engineering","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131850248","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 : 2013-11-01DOI: 10.1109/ICCSCE.2013.6720028
Rofilde Hasudungan, R. A. Bakar
Determination of distribution center location is one of importance issue in supply chain management since this problem affect to production cost and product flow. Nerveless, to choose appropriate the distribution center is not easy task, need to consider the best layout where we have to choose the appropriate number of distribution center and its position among all candidates, this make the determination distribution more complicated cause involving combination configuration. In this study, we proposed DNA computing to solve this problem since the advantages this technique is fall into huge massive parallelism.
{"title":"DNA computing for solving distribution center location problem","authors":"Rofilde Hasudungan, R. A. Bakar","doi":"10.1109/ICCSCE.2013.6720028","DOIUrl":"https://doi.org/10.1109/ICCSCE.2013.6720028","url":null,"abstract":"Determination of distribution center location is one of importance issue in supply chain management since this problem affect to production cost and product flow. Nerveless, to choose appropriate the distribution center is not easy task, need to consider the best layout where we have to choose the appropriate number of distribution center and its position among all candidates, this make the determination distribution more complicated cause involving combination configuration. In this study, we proposed DNA computing to solve this problem since the advantages this technique is fall into huge massive parallelism.","PeriodicalId":319285,"journal":{"name":"2013 IEEE International Conference on Control System, Computing and Engineering","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129853344","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 : 2013-11-01DOI: 10.1109/ICCSCE.2013.6719975
Rana Fayyaz Ahmad, A. Malik, N. Kamel, F. Reza
Epilepsy is the brain disorder disease having more than 50 million people worldwide. The treatment for epilepsy is medication and surgery. Some patients are not cured with medicine and surgery. One third of the patients still remain with uncontrolled epilepsy. They need constant monitoring for epileptic seizures. Better treatment can be provided by the doctors or precautionary measures can be taken by the patients themselves if any abnormal brain activity or seizure is predicted before its occurrence. The pre-ictal period has some information about the occurrence of epileptic seizure in EEG signals. The brain behaves normal in inter-ictal and postictal periods. For epilepsy, long duration EEG recording are required from days to week. This keeps the patients to stay in the hospital for many days. Our proposed methodology is to predict the epileptic seizure and monitor the brain abnormality in real time. Still there is no epileptic seizure prediction algorithm using EEG available for clinical applications. Our aim is to study and develop a good epileptic seizure prediction algorithm/method with high value of sensitivity and specificity using scalp EEG i-e noninvasive approach. Also a comprehensive survey is done to find the limitations and research issues related to this. The proposed pattern recognition approach has great potential to be used in real time monitoring for epileptic patients and it can be helpful in improving the quality of life of the patients.
{"title":"A proposed frame work for real time epileptic seizure prediction using scalp EEG","authors":"Rana Fayyaz Ahmad, A. Malik, N. Kamel, F. Reza","doi":"10.1109/ICCSCE.2013.6719975","DOIUrl":"https://doi.org/10.1109/ICCSCE.2013.6719975","url":null,"abstract":"Epilepsy is the brain disorder disease having more than 50 million people worldwide. The treatment for epilepsy is medication and surgery. Some patients are not cured with medicine and surgery. One third of the patients still remain with uncontrolled epilepsy. They need constant monitoring for epileptic seizures. Better treatment can be provided by the doctors or precautionary measures can be taken by the patients themselves if any abnormal brain activity or seizure is predicted before its occurrence. The pre-ictal period has some information about the occurrence of epileptic seizure in EEG signals. The brain behaves normal in inter-ictal and postictal periods. For epilepsy, long duration EEG recording are required from days to week. This keeps the patients to stay in the hospital for many days. Our proposed methodology is to predict the epileptic seizure and monitor the brain abnormality in real time. Still there is no epileptic seizure prediction algorithm using EEG available for clinical applications. Our aim is to study and develop a good epileptic seizure prediction algorithm/method with high value of sensitivity and specificity using scalp EEG i-e noninvasive approach. Also a comprehensive survey is done to find the limitations and research issues related to this. The proposed pattern recognition approach has great potential to be used in real time monitoring for epileptic patients and it can be helpful in improving the quality of life of the patients.","PeriodicalId":319285,"journal":{"name":"2013 IEEE International Conference on Control System, Computing and Engineering","volume":"35 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130765709","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 : 2013-11-01DOI: 10.1109/ICCSCE.2013.6719958
A. Hani, T. Soomro, I. Faye
Diabetic Retinopathy (DR) is vision loss impairment due to complication arising from diabetic condition affecting the retina. It is known that the foveal avascular zone (FAZ) enlarges with progression of DR due to the loss of capillaries in perifoveal capillary network. However, normal retinal fundus images suffer from low and varied contrast problems. A non-invasive digital image enhancement technique called RETICA has been developed that overcomes the problem of varied and low contrast in fundus images. RETICA first normalises the varied contrast using a Retinex-based method that separates the illumination from the reflectance part of the image followed by ICA that forms the original retinal pigment makeup namely the macular, haemoglobin and melanin retinal pigment. The technique has been applied on our FINDeRS dataset contained 175 fundus images and another 35 fundus image pairs obtained from an earlier study containing colour fundus images and their corresponding fluorescein fundus angiogram (FFA) images. For the 35 image pairs, RETICA achieved an average contrast improvement factor (CIF) of up to 5.46 compared to the invasive FFA at 5.12. For the FINDeRS images, RETICA achieved an average CIF of 5.63 with denoising. The RETICA image enhancement technique potentially reduces the need for the invasive fluorescein angiogram in DR assessment.
{"title":"Non-invasive contrast enhancement for retinal fundus imaging","authors":"A. Hani, T. Soomro, I. Faye","doi":"10.1109/ICCSCE.2013.6719958","DOIUrl":"https://doi.org/10.1109/ICCSCE.2013.6719958","url":null,"abstract":"Diabetic Retinopathy (DR) is vision loss impairment due to complication arising from diabetic condition affecting the retina. It is known that the foveal avascular zone (FAZ) enlarges with progression of DR due to the loss of capillaries in perifoveal capillary network. However, normal retinal fundus images suffer from low and varied contrast problems. A non-invasive digital image enhancement technique called RETICA has been developed that overcomes the problem of varied and low contrast in fundus images. RETICA first normalises the varied contrast using a Retinex-based method that separates the illumination from the reflectance part of the image followed by ICA that forms the original retinal pigment makeup namely the macular, haemoglobin and melanin retinal pigment. The technique has been applied on our FINDeRS dataset contained 175 fundus images and another 35 fundus image pairs obtained from an earlier study containing colour fundus images and their corresponding fluorescein fundus angiogram (FFA) images. For the 35 image pairs, RETICA achieved an average contrast improvement factor (CIF) of up to 5.46 compared to the invasive FFA at 5.12. For the FINDeRS images, RETICA achieved an average CIF of 5.63 with denoising. The RETICA image enhancement technique potentially reduces the need for the invasive fluorescein angiogram in DR assessment.","PeriodicalId":319285,"journal":{"name":"2013 IEEE International Conference on Control System, Computing and Engineering","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125943097","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 : 2013-11-01DOI: 10.1109/ICCSCE.2013.6719936
Andri Mirzal
Latent semantic indexing (LSI) is an indexing method to improve performance of an information retrieval system by indexing terms that appear in related documents and weakening influences of terms that appear in unrelated documents. LSI usually is conducted by using the truncated singular value decomposition (SVD). The main difficulty in using this technique is its retrieval performance depends strongly on the choosing of an appropriate decomposition rank. In this paper, by observing the fact that the truncated SVD makes the related documents more connected, we devise a matrix completion algorithm that can mimick this capability. The proposed algorithm is nonparametric, has convergence guarantee, and produces a unique solution for each input. Thus it is more practical and easier to use than the truncated SVD. Experimental results using four standard datasets in LSI research show that the retrieval performances of the proposed algorithm are comparable to the best results offered by the truncated SVD over some decomposition ranks.
{"title":"Similarity-based matrix completion algorithm for latent semantic indexing","authors":"Andri Mirzal","doi":"10.1109/ICCSCE.2013.6719936","DOIUrl":"https://doi.org/10.1109/ICCSCE.2013.6719936","url":null,"abstract":"Latent semantic indexing (LSI) is an indexing method to improve performance of an information retrieval system by indexing terms that appear in related documents and weakening influences of terms that appear in unrelated documents. LSI usually is conducted by using the truncated singular value decomposition (SVD). The main difficulty in using this technique is its retrieval performance depends strongly on the choosing of an appropriate decomposition rank. In this paper, by observing the fact that the truncated SVD makes the related documents more connected, we devise a matrix completion algorithm that can mimick this capability. The proposed algorithm is nonparametric, has convergence guarantee, and produces a unique solution for each input. Thus it is more practical and easier to use than the truncated SVD. Experimental results using four standard datasets in LSI research show that the retrieval performances of the proposed algorithm are comparable to the best results offered by the truncated SVD over some decomposition ranks.","PeriodicalId":319285,"journal":{"name":"2013 IEEE International Conference on Control System, Computing and Engineering","volume":"353 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125636261","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 : 2013-11-01DOI: 10.1109/ICCSCE.2013.6719991
N. Khalid, J. R. A. Hamid, Z. Latif
Meranti (Shorea Spp) is one of the most widely-used tropical timbers due to its high timber value, vertical stability and moderately durable. Monitoring the distribution and inventory of this species is deemed necessary so as to assist the timber producers and forest personnel in their effective growth analysis and forest management daily activities. Unfortunately, detailed of tree biophysical measurement for inventory purposes are often constrained by inaccessibility to site locations, costly and time-consuming. The advancement in remote sensing technology such as the provision of active airborne LiDAR allows for accurate acquisition of tree biophysical parameters and overcome the constrained assemble of tree inventory attained through traditional practices. This paper focuses on defining the allometric relationship for Meranti tree species and depicts the watershed segmentation algorithm approach to delineate tree canopy in a heterogeneous (Ampang) forest. The results have indicated that there is high correlation between tree height and crown diameter for Meranti whereby R2 for linear model is 0.738. The findings point to the fact that accurate delineation of tree parameters contributes to the accurate allometric relationship analysis which would be able to support sustainable forest development especially for forest management personnel.
{"title":"Tree biophysical relationship in the Ampang forest reserve","authors":"N. Khalid, J. R. A. Hamid, Z. Latif","doi":"10.1109/ICCSCE.2013.6719991","DOIUrl":"https://doi.org/10.1109/ICCSCE.2013.6719991","url":null,"abstract":"Meranti (Shorea Spp) is one of the most widely-used tropical timbers due to its high timber value, vertical stability and moderately durable. Monitoring the distribution and inventory of this species is deemed necessary so as to assist the timber producers and forest personnel in their effective growth analysis and forest management daily activities. Unfortunately, detailed of tree biophysical measurement for inventory purposes are often constrained by inaccessibility to site locations, costly and time-consuming. The advancement in remote sensing technology such as the provision of active airborne LiDAR allows for accurate acquisition of tree biophysical parameters and overcome the constrained assemble of tree inventory attained through traditional practices. This paper focuses on defining the allometric relationship for Meranti tree species and depicts the watershed segmentation algorithm approach to delineate tree canopy in a heterogeneous (Ampang) forest. The results have indicated that there is high correlation between tree height and crown diameter for Meranti whereby R2 for linear model is 0.738. The findings point to the fact that accurate delineation of tree parameters contributes to the accurate allometric relationship analysis which would be able to support sustainable forest development especially for forest management personnel.","PeriodicalId":319285,"journal":{"name":"2013 IEEE International Conference on Control System, Computing and Engineering","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130507759","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 : 2013-11-01DOI: 10.1109/ICCSCE.2013.6720025
Suraya Abdul Rahim, T. Ibrahim, A. Ma'Radzi, M. M. Jamil
Mixing of two fluid is an essential process for most of microfluidic device such as Lab-On-Chip (LOC) device. Mixing performance in this microsystem mainly relies on effective and rapid mixing of sample and reagent. Therefore, the development of oblique groove micromixer for application of blood and reagent mixing has been carried out. In this study, two types of fluids are involve in the mixing, which are the blood and reagent. Two mixer namely Y-Shape mixer and Y-Shape oblique groove mixer are designed and simulated using CoventorWare2010 software at low Reynolds number. The development of oblique groove micromixer are obtained by analyzing the geometries effect of groove pattern on mixing performance. In this study, it has been demonstrated that the Y-Shape mixer with the oblique groove structure located at the floor of the mixing channel can increase the mixing performance. Thus, the simulation result in this study shows that mixing performance can be enhanced when depth and width of oblique groove having 40% of the channel width with the angle of oblique groove is 45°.
{"title":"Design and development of oblique groove micromixer for laminar blood reagent mixing","authors":"Suraya Abdul Rahim, T. Ibrahim, A. Ma'Radzi, M. M. Jamil","doi":"10.1109/ICCSCE.2013.6720025","DOIUrl":"https://doi.org/10.1109/ICCSCE.2013.6720025","url":null,"abstract":"Mixing of two fluid is an essential process for most of microfluidic device such as Lab-On-Chip (LOC) device. Mixing performance in this microsystem mainly relies on effective and rapid mixing of sample and reagent. Therefore, the development of oblique groove micromixer for application of blood and reagent mixing has been carried out. In this study, two types of fluids are involve in the mixing, which are the blood and reagent. Two mixer namely Y-Shape mixer and Y-Shape oblique groove mixer are designed and simulated using CoventorWare2010 software at low Reynolds number. The development of oblique groove micromixer are obtained by analyzing the geometries effect of groove pattern on mixing performance. In this study, it has been demonstrated that the Y-Shape mixer with the oblique groove structure located at the floor of the mixing channel can increase the mixing performance. Thus, the simulation result in this study shows that mixing performance can be enhanced when depth and width of oblique groove having 40% of the channel width with the angle of oblique groove is 45°.","PeriodicalId":319285,"journal":{"name":"2013 IEEE International Conference on Control System, Computing and Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129383982","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 : 2013-11-01DOI: 10.1109/ICCSCE.2013.6719992
N. Othman, M. I. A. Manan, Z. Othman, S. Junid
This paper presents the performance analysis of dualaxis solar tracking system using Arduino. The ultimate objective of this project is to investigate whether static solar panel is better than solar tracker, or the opposite. This project is divided into two stages namely, hardware and software development. In hardware development, five light dependent resistors (LDR) were utilized to capture the maximum light source from the sun. Two servo motors also were employed to move the solar panel to maximum light source location sensed by the LDRs. As for the software part, the code was constructed by using C programming language and was targeted to the Arduino UNO controller. The performance of the solar tracker was analyzed and compared with the static solar panel and the result showed that the solar tracker is better than the static solar panel in terms of voltage, current and power. Therefore, the solar tracker is proven more effective for capturing the maximum sunlight source for solar harvesting applications.
{"title":"Performance analysis of dual-axis solar tracking system","authors":"N. Othman, M. I. A. Manan, Z. Othman, S. Junid","doi":"10.1109/ICCSCE.2013.6719992","DOIUrl":"https://doi.org/10.1109/ICCSCE.2013.6719992","url":null,"abstract":"This paper presents the performance analysis of dualaxis solar tracking system using Arduino. The ultimate objective of this project is to investigate whether static solar panel is better than solar tracker, or the opposite. This project is divided into two stages namely, hardware and software development. In hardware development, five light dependent resistors (LDR) were utilized to capture the maximum light source from the sun. Two servo motors also were employed to move the solar panel to maximum light source location sensed by the LDRs. As for the software part, the code was constructed by using C programming language and was targeted to the Arduino UNO controller. The performance of the solar tracker was analyzed and compared with the static solar panel and the result showed that the solar tracker is better than the static solar panel in terms of voltage, current and power. Therefore, the solar tracker is proven more effective for capturing the maximum sunlight source for solar harvesting applications.","PeriodicalId":319285,"journal":{"name":"2013 IEEE International Conference on Control System, Computing and Engineering","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129487563","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 : 2013-11-01DOI: 10.1109/ICCSCE.2013.6719944
M. A. Daneshwar, N. Noh
The study of static friction in control engineering is the subject of many researches due to its impact on degradation of performance of the control loops. Mathematical model of systems with static friction is not straight forward. Precise and proper model of this phenomenon is a key factor in model-based control to mitigate its effect. By increasing number of smart valve in industry, demand for identification of such valves is rising. In these valves, identification of process is limited to control signal (OP) and valve position (MV). By taking advantage of Hammerstein approach, identification is divided in two parts, linear dynamic part and nonlinear static part. In this paper, adaptive neuro-fuzzy inference system (ANFIS) is used for identification of nonlinear static part of the plant. The linear dynamic part can be identified using linear identification methods. Results reveal that ANFIS which integrates both neural networks and fuzzy logic principles and has potential to capture the benefits of both in a single framework can capture well the key model of the systems with smart valves involved in static friction.
{"title":"Adaptive neuro-fuzzy inference system identification model for smart control valves with static friction","authors":"M. A. Daneshwar, N. Noh","doi":"10.1109/ICCSCE.2013.6719944","DOIUrl":"https://doi.org/10.1109/ICCSCE.2013.6719944","url":null,"abstract":"The study of static friction in control engineering is the subject of many researches due to its impact on degradation of performance of the control loops. Mathematical model of systems with static friction is not straight forward. Precise and proper model of this phenomenon is a key factor in model-based control to mitigate its effect. By increasing number of smart valve in industry, demand for identification of such valves is rising. In these valves, identification of process is limited to control signal (OP) and valve position (MV). By taking advantage of Hammerstein approach, identification is divided in two parts, linear dynamic part and nonlinear static part. In this paper, adaptive neuro-fuzzy inference system (ANFIS) is used for identification of nonlinear static part of the plant. The linear dynamic part can be identified using linear identification methods. Results reveal that ANFIS which integrates both neural networks and fuzzy logic principles and has potential to capture the benefits of both in a single framework can capture well the key model of the systems with smart valves involved in static friction.","PeriodicalId":319285,"journal":{"name":"2013 IEEE International Conference on Control System, Computing and Engineering","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122239861","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 : 2013-11-01DOI: 10.1109/ICCSCE.2013.6719942
M. Omar, M. Hassan, A. C. Soh, M. Kadir
This paper presents a technique of predicting lightning severity on daily basis by using meteorological data. The data used is supplied by Global Lightning Network (GLN) from WSI Corporation. The input of the system consists of seven meteorology parameters which had been provided by Malaysia Meteorology Service with minimal fees. Input parameters are the Minimum Humidity, Maximum Humidity, Minimum Temperature, Maximum Temperature, Rainfall, Week and Month. The output of the system determines the severity of lightning predictions in three stages; Class1: Hazardous; Class2: Warning; and Class3: Low Risk. Two training algorithms that have been tested in this study namely the Gradient Descent with Momentum Backpropagation (traingdm) and the Scaled Conjugated Gradient Backpropagation (trainscg). The traingdm has indicated better accuracy of 70% compared to the trainscg whilst in contrast; trainscg has demonstrated approximately 4 times faster training compare to traingdm.
{"title":"Lightning severity classification utilizing the meteorological parameters: A neural network approach","authors":"M. Omar, M. Hassan, A. C. Soh, M. Kadir","doi":"10.1109/ICCSCE.2013.6719942","DOIUrl":"https://doi.org/10.1109/ICCSCE.2013.6719942","url":null,"abstract":"This paper presents a technique of predicting lightning severity on daily basis by using meteorological data. The data used is supplied by Global Lightning Network (GLN) from WSI Corporation. The input of the system consists of seven meteorology parameters which had been provided by Malaysia Meteorology Service with minimal fees. Input parameters are the Minimum Humidity, Maximum Humidity, Minimum Temperature, Maximum Temperature, Rainfall, Week and Month. The output of the system determines the severity of lightning predictions in three stages; Class1: Hazardous; Class2: Warning; and Class3: Low Risk. Two training algorithms that have been tested in this study namely the Gradient Descent with Momentum Backpropagation (traingdm) and the Scaled Conjugated Gradient Backpropagation (trainscg). The traingdm has indicated better accuracy of 70% compared to the trainscg whilst in contrast; trainscg has demonstrated approximately 4 times faster training compare to traingdm.","PeriodicalId":319285,"journal":{"name":"2013 IEEE International Conference on Control System, Computing and Engineering","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123819092","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：