Pub Date : 2014-12-01DOI: 10.1109/SKIMA.2014.7083516
M. Ruhul Amin, Rajib Baran Roy
Carbon emission minimization is one of big challenge in this century. For this purpose, in public transport point of view, the integration of electric vehicle is growing fast. Now the intention of this work is to design wireless charger with the aim of charging vehicle battery. The charger contains with a transmitter antenna which is assembled in parking garage surface in a particular area and a receiver antenna which is attached with vehicle bottom side with battery is to be charged. Here inductive power transfer technique is applied to transfer energy from transmitter to receiver through the air-gap in an optimum distance for achieving high efficiency of transfer link. MATLAB/SIMULINK is used to simulate the power pad of transmitter and receiver with proper calculation of inductance in each pad and mutual inductance between pads. The high frequency signal is thrown for traveling through the air-gap due to contain high signal strength. The received signal is further rectified to DC for restoring it into battery. This paper focuses the design of transmitter and receiver with proper investigation of circuit parameter of transmitter antenna and receiver antenna for electric vehicle. Finally the charger efficiency is determined with MATLAB/SIMULINK.
{"title":"Design and simulation of wireless stationary charging system for hybrid electric vehicle using inductive power pad in parking garage","authors":"M. Ruhul Amin, Rajib Baran Roy","doi":"10.1109/SKIMA.2014.7083516","DOIUrl":"https://doi.org/10.1109/SKIMA.2014.7083516","url":null,"abstract":"Carbon emission minimization is one of big challenge in this century. For this purpose, in public transport point of view, the integration of electric vehicle is growing fast. Now the intention of this work is to design wireless charger with the aim of charging vehicle battery. The charger contains with a transmitter antenna which is assembled in parking garage surface in a particular area and a receiver antenna which is attached with vehicle bottom side with battery is to be charged. Here inductive power transfer technique is applied to transfer energy from transmitter to receiver through the air-gap in an optimum distance for achieving high efficiency of transfer link. MATLAB/SIMULINK is used to simulate the power pad of transmitter and receiver with proper calculation of inductance in each pad and mutual inductance between pads. The high frequency signal is thrown for traveling through the air-gap due to contain high signal strength. The received signal is further rectified to DC for restoring it into battery. This paper focuses the design of transmitter and receiver with proper investigation of circuit parameter of transmitter antenna and receiver antenna for electric vehicle. Finally the charger efficiency is determined with MATLAB/SIMULINK.","PeriodicalId":22294,"journal":{"name":"The 8th International Conference on Software, Knowledge, Information Management and Applications (SKIMA 2014)","volume":"108 3-4 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77186119","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 : 2014-12-01DOI: 10.1109/SKIMA.2014.7083547
M. Hossain, Tajkia Tasnim, Swakkhar Shatabda, D. Farid
Local search methods can quickly find good quality solutions in cases where systematic search methods might take a large amount of time. Moreover, in the context of pattern set mining, exhaustive search methods are not applicable due to the large search space they have to explore. In this paper, we propose the application of stochastic local search to solve the pattern set mining. Specifically, to the task of concept learning. We applied a number of local search algorithms on a standard benchmark instances for pattern set mining and the results show the potentials for further exploration.
{"title":"Stochastic local search for pattern set mining","authors":"M. Hossain, Tajkia Tasnim, Swakkhar Shatabda, D. Farid","doi":"10.1109/SKIMA.2014.7083547","DOIUrl":"https://doi.org/10.1109/SKIMA.2014.7083547","url":null,"abstract":"Local search methods can quickly find good quality solutions in cases where systematic search methods might take a large amount of time. Moreover, in the context of pattern set mining, exhaustive search methods are not applicable due to the large search space they have to explore. In this paper, we propose the application of stochastic local search to solve the pattern set mining. Specifically, to the task of concept learning. We applied a number of local search algorithms on a standard benchmark instances for pattern set mining and the results show the potentials for further exploration.","PeriodicalId":22294,"journal":{"name":"The 8th International Conference on Software, Knowledge, Information Management and Applications (SKIMA 2014)","volume":"164 2","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72553478","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 : 2014-12-01DOI: 10.1109/SKIMA.2014.7083527
Rahat Yasir, R. Khan
Sign language detection and recognition (SLDR) using computer vision is a very challenging task. In respect to Bangladesh, sign language users are around 2.4 million [16]. In this paper, we try to focus for communicating with those users by computer vision. In this respect, an efficient method is proposed consists of some significant steps and they are, skin detection, preprocessing, different machine learning techniques like PCA and LDA, neural network for training and testing purpose of the system. Various hand sign images are used to test the proposed method and results are presented to provide its effectiveness.
{"title":"Two-handed hand gesture recognition for Bangla sign language using LDA and ANN","authors":"Rahat Yasir, R. Khan","doi":"10.1109/SKIMA.2014.7083527","DOIUrl":"https://doi.org/10.1109/SKIMA.2014.7083527","url":null,"abstract":"Sign language detection and recognition (SLDR) using computer vision is a very challenging task. In respect to Bangladesh, sign language users are around 2.4 million [16]. In this paper, we try to focus for communicating with those users by computer vision. In this respect, an efficient method is proposed consists of some significant steps and they are, skin detection, preprocessing, different machine learning techniques like PCA and LDA, neural network for training and testing purpose of the system. Various hand sign images are used to test the proposed method and results are presented to provide its effectiveness.","PeriodicalId":22294,"journal":{"name":"The 8th International Conference on Software, Knowledge, Information Management and Applications (SKIMA 2014)","volume":"19 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73016767","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 : 2014-12-01DOI: 10.1109/SKIMA.2014.7083532
Pathathai Na-Lumpoon
Service composition brings many benefits of reusing existing services (so called components) to synthesize a new resulting service (so called composite). Composing a service composition usually happens at design time, but this limit the choices of component services. This paper presents a framework for web service composition and execution based on the integration of different domains. Given a user's query, and a list of service descriptions (in SAWSDL), the framework first provides an automated composition of services based on Fluent Calculus. This step, employing chaining inference from AI-planning with FLUX constraint programming method, generates a plan which is either a sequence or a parallel composition of operations offered by the selected services. As a second step, the plan is transformed into a BPMN (Business Process Modeling Notation) model in order to be executed by any BPMN engine. The proposed work relies on a broad project that aims at design and develop a non intrusive framework dediated to context aware mobile services [1]-[3].
{"title":"Toward a framework for automated service composition and execution","authors":"Pathathai Na-Lumpoon","doi":"10.1109/SKIMA.2014.7083532","DOIUrl":"https://doi.org/10.1109/SKIMA.2014.7083532","url":null,"abstract":"Service composition brings many benefits of reusing existing services (so called components) to synthesize a new resulting service (so called composite). Composing a service composition usually happens at design time, but this limit the choices of component services. This paper presents a framework for web service composition and execution based on the integration of different domains. Given a user's query, and a list of service descriptions (in SAWSDL), the framework first provides an automated composition of services based on Fluent Calculus. This step, employing chaining inference from AI-planning with FLUX constraint programming method, generates a plan which is either a sequence or a parallel composition of operations offered by the selected services. As a second step, the plan is transformed into a BPMN (Business Process Modeling Notation) model in order to be executed by any BPMN engine. The proposed work relies on a broad project that aims at design and develop a non intrusive framework dediated to context aware mobile services [1]-[3].","PeriodicalId":22294,"journal":{"name":"The 8th International Conference on Software, Knowledge, Information Management and Applications (SKIMA 2014)","volume":"56 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79432140","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 : 2014-12-01DOI: 10.1109/SKIMA.2014.7083389
R. Rajasinghe, W. Weerapperuma, W. Wijesinghe, K. Rathnayake, L. Seneviratne
Stock Market is the platform that enables investors to channel their savings to generate a profit. Companies pay dividends for the shareholders at the end of a profitable period. The Random Walk Hypothesis governs the Stock Prices as the prices are stated as total random fluctuations that cannot be predicted. Hybrid System for Forecasting Stock Prices Variations in the Stock Market (Hybrid Forecaster) is a research carried out to implement a decision support system that provides insight for selecting profitable stocks using forecasting methodologies. Multitude of researches carried out in this field are limited to forecasting stock market using a single standpoint that affects the stock prices. The research explores critical elements that affects the prices from multiple dimensions.
{"title":"A Hybrid System for Forecasting Stock Price Variations in the Stock Market","authors":"R. Rajasinghe, W. Weerapperuma, W. Wijesinghe, K. Rathnayake, L. Seneviratne","doi":"10.1109/SKIMA.2014.7083389","DOIUrl":"https://doi.org/10.1109/SKIMA.2014.7083389","url":null,"abstract":"Stock Market is the platform that enables investors to channel their savings to generate a profit. Companies pay dividends for the shareholders at the end of a profitable period. The Random Walk Hypothesis governs the Stock Prices as the prices are stated as total random fluctuations that cannot be predicted. Hybrid System for Forecasting Stock Prices Variations in the Stock Market (Hybrid Forecaster) is a research carried out to implement a decision support system that provides insight for selecting profitable stocks using forecasting methodologies. Multitude of researches carried out in this field are limited to forecasting stock market using a single standpoint that affects the stock prices. The research explores critical elements that affects the prices from multiple dimensions.","PeriodicalId":22294,"journal":{"name":"The 8th International Conference on Software, Knowledge, Information Management and Applications (SKIMA 2014)","volume":"45 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90611512","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 : 2014-12-01DOI: 10.1109/SKIMA.2014.7083560
V. Veneziano, Imran Mahmud, Amena Khatun, W. Peng
Information systems play a massive role in measuring, analyzing, improving and controlling business processes, especially where the working environment is collaborative and distributed. Though management information system (MIS), as a sector and a discipline, is inventor of many guidelines and models, yet it seems a slow runner on practical implications of usability within its industry of reference. In this paper, researchers critically examined usability using system usability scale (SUS) on most popular enterprise resource planning system SAP, an integrated solution that incorporates the key business operation functions and processes of an organization. The purpose of this research was to investigate the influence of ERP users' demographic information like educational background and job experiences (as factors affecting users' cognitive performance) against the task of rating usability of the system. Survey questionnaire were used as a data collection method and regression testing was conducted to obtain the result of impact. Several potential outputs were achieved and further explained.
{"title":"Usability analysis of ERP software: Education and experience of users' as moderators","authors":"V. Veneziano, Imran Mahmud, Amena Khatun, W. Peng","doi":"10.1109/SKIMA.2014.7083560","DOIUrl":"https://doi.org/10.1109/SKIMA.2014.7083560","url":null,"abstract":"Information systems play a massive role in measuring, analyzing, improving and controlling business processes, especially where the working environment is collaborative and distributed. Though management information system (MIS), as a sector and a discipline, is inventor of many guidelines and models, yet it seems a slow runner on practical implications of usability within its industry of reference. In this paper, researchers critically examined usability using system usability scale (SUS) on most popular enterprise resource planning system SAP, an integrated solution that incorporates the key business operation functions and processes of an organization. The purpose of this research was to investigate the influence of ERP users' demographic information like educational background and job experiences (as factors affecting users' cognitive performance) against the task of rating usability of the system. Survey questionnaire were used as a data collection method and regression testing was conducted to obtain the result of impact. Several potential outputs were achieved and further explained.","PeriodicalId":22294,"journal":{"name":"The 8th International Conference on Software, Knowledge, Information Management and Applications (SKIMA 2014)","volume":"43 ","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91455463","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 : 2014-12-01DOI: 10.1109/SKIMA.2014.7083525
Rajib Baran Roy, E. Basher, Rojoba Yasmin, M. Rokonuzzaman
The maximum power point tracking (MPPT) is required for harnessing maximum power from the grid connected photovoltaic (PV) system. This paper describes a real time implementation of a grid connected photovoltaic system based on the fuzzy MPPT algorithm to control the power of the PV panel on the generation side as well as the current of the voltage source inverter (VSI) which is connected to the grid side. The performance of the control algorithm is verified by simulation and experiment. The implementation of the fuzzy algorithm is realized on a dSPACE 1104 single board by controlling a boost chopper and a VSI. The experimental results prove the effectiveness of the control techniques of the proposed fuzzy logic by fixing the MPPT in the I-V curve of the solar panel. The DC bus voltage controller based on Lyapounov theory and the hysteresis based current control of the inverter allow a quasi total transit of the maximum extracted power from the solar panel to the grid under unit power factor operation.
{"title":"Fuzzy logic based MPPT approach in a grid connected photovoltaic system","authors":"Rajib Baran Roy, E. Basher, Rojoba Yasmin, M. Rokonuzzaman","doi":"10.1109/SKIMA.2014.7083525","DOIUrl":"https://doi.org/10.1109/SKIMA.2014.7083525","url":null,"abstract":"The maximum power point tracking (MPPT) is required for harnessing maximum power from the grid connected photovoltaic (PV) system. This paper describes a real time implementation of a grid connected photovoltaic system based on the fuzzy MPPT algorithm to control the power of the PV panel on the generation side as well as the current of the voltage source inverter (VSI) which is connected to the grid side. The performance of the control algorithm is verified by simulation and experiment. The implementation of the fuzzy algorithm is realized on a dSPACE 1104 single board by controlling a boost chopper and a VSI. The experimental results prove the effectiveness of the control techniques of the proposed fuzzy logic by fixing the MPPT in the I-V curve of the solar panel. The DC bus voltage controller based on Lyapounov theory and the hysteresis based current control of the inverter allow a quasi total transit of the maximum extracted power from the solar panel to the grid under unit power factor operation.","PeriodicalId":22294,"journal":{"name":"The 8th International Conference on Software, Knowledge, Information Management and Applications (SKIMA 2014)","volume":"39 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90243263","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 : 2014-12-01DOI: 10.1109/SKIMA.2014.7083530
Tasnim Azad Abir, Md. Rashedul Islam, A. Aowlad Hossain
Application of nonlinear ultrasound techniques is recently gaining importance in medical imaging. Ultrasound imaging is a commonly used diagnostic method due to its low cost, safe and portable facilities. However, linear ultrasound imaging provides poor resolutions. The harmonic content can provide better resolution rather than the fundamental frequency. Conversely, increasing complexity is obvious impact of nonlinearity consideration. This simulation study presents a comparative analysis of linear and non-linear ultrasound imaging of different synthetic phantoms in order to find the effectiveness on nonlinear ultrasound techniques. We have used two widely accepted ultrasound simulator Field II and CREANUIS. Synthetic phantom has been developed considering both linear and non-linear propagation media with possible inhomogeneous coefficient of nonlinearity. Simulated images have been examined in terms of SNR, CNR and resolution. The nonlinear imaging has showed its effectiveness over linear technique for the images with closely located multiple cysts where lateral resolution is important.
{"title":"Simulation analysis on effectiveness of nonlinear ultrasound imaging using synthetic cyst phantoms","authors":"Tasnim Azad Abir, Md. Rashedul Islam, A. Aowlad Hossain","doi":"10.1109/SKIMA.2014.7083530","DOIUrl":"https://doi.org/10.1109/SKIMA.2014.7083530","url":null,"abstract":"Application of nonlinear ultrasound techniques is recently gaining importance in medical imaging. Ultrasound imaging is a commonly used diagnostic method due to its low cost, safe and portable facilities. However, linear ultrasound imaging provides poor resolutions. The harmonic content can provide better resolution rather than the fundamental frequency. Conversely, increasing complexity is obvious impact of nonlinearity consideration. This simulation study presents a comparative analysis of linear and non-linear ultrasound imaging of different synthetic phantoms in order to find the effectiveness on nonlinear ultrasound techniques. We have used two widely accepted ultrasound simulator Field II and CREANUIS. Synthetic phantom has been developed considering both linear and non-linear propagation media with possible inhomogeneous coefficient of nonlinearity. Simulated images have been examined in terms of SNR, CNR and resolution. The nonlinear imaging has showed its effectiveness over linear technique for the images with closely located multiple cysts where lateral resolution is important.","PeriodicalId":22294,"journal":{"name":"The 8th International Conference on Software, Knowledge, Information Management and Applications (SKIMA 2014)","volume":"62 1","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84779642","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 : 2014-12-01DOI: 10.1109/SKIMA.2014.7083517
M. Y. Arafat, Sanjana Fahrin, Md Jamirul Islam, Md Ashraf Siddiquee, Afsana Khan, Mohammed Rokibul Alam Kotwal, M. N. Huda
This paper illustrates the design and implementation of Bangla (widely used as Bengali) Text to Speech (TTS) system from the very raw level without using any third party speech synthesis tool. For constructing the system we have considered two directions, where one is based on phoneme and another one is on syllable. In this study, our proposed system comprises some stages. At first stage audio sounds are recorded for each of the Bangla phonemes and three thousand out of 250000 syllables in Bangla, and then noise is reduced to obtained high quality sounds for each phoneme and syllable. Second stage searches for longest possible matching of the syllables if it is available in the input text, and if not, then searches for the phonemes to match with the corresponding graphemes. For further improvement, we also added the complex conjuncts which need to be handled separately. It is observed from the experiments that the syllable based method provides the better quality speech for the input text in comparison with the method based on phoneme.
{"title":"Speech synthesis for Bangla Text to Speech conversion","authors":"M. Y. Arafat, Sanjana Fahrin, Md Jamirul Islam, Md Ashraf Siddiquee, Afsana Khan, Mohammed Rokibul Alam Kotwal, M. N. Huda","doi":"10.1109/SKIMA.2014.7083517","DOIUrl":"https://doi.org/10.1109/SKIMA.2014.7083517","url":null,"abstract":"This paper illustrates the design and implementation of Bangla (widely used as Bengali) Text to Speech (TTS) system from the very raw level without using any third party speech synthesis tool. For constructing the system we have considered two directions, where one is based on phoneme and another one is on syllable. In this study, our proposed system comprises some stages. At first stage audio sounds are recorded for each of the Bangla phonemes and three thousand out of 250000 syllables in Bangla, and then noise is reduced to obtained high quality sounds for each phoneme and syllable. Second stage searches for longest possible matching of the syllables if it is available in the input text, and if not, then searches for the phonemes to match with the corresponding graphemes. For further improvement, we also added the complex conjuncts which need to be handled separately. It is observed from the experiments that the syllable based method provides the better quality speech for the input text in comparison with the method based on phoneme.","PeriodicalId":22294,"journal":{"name":"The 8th International Conference on Software, Knowledge, Information Management and Applications (SKIMA 2014)","volume":"112 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89526945","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 : 2014-12-01DOI: 10.1109/SKIMA.2014.7083513
Shumit Saha, Kazi Hasan Uddin, M. Islam, Md Jahiruzzaman, A. B. M. Awolad Hossain
Normalized cut based image segmentation has a variety of applications in the area of image compression, medical imaging, mapping and measurements. But, the computational complexity of conventional normalized cut algorithm based on generalized eigenvalue problem is high. In this study, we proposed a simplified normalized cut algorithm using graph partitioning method for image segmentation. The computational cost of this simplified method are relatively low and hence, it can be implemented on real time embedded system applications. We have implemented an FPGA based image segmentation system using the simplified normalized cut algorithm and tested it for malarial parasites detection. Verilog Hardware Description Language (Verilog HDL) is used to develop the system and implemented on FPGA Spartan-6 targeted device xc6slx16- 2csg324. The Simple-As-Possible (SAP) computer architecture is used to design the system. We think the proposed architecture can be useful for real time image segmentation.
{"title":"Implementation of simplified normalized cut graph partitioning algorithm on FPGA for image segmentation","authors":"Shumit Saha, Kazi Hasan Uddin, M. Islam, Md Jahiruzzaman, A. B. M. Awolad Hossain","doi":"10.1109/SKIMA.2014.7083513","DOIUrl":"https://doi.org/10.1109/SKIMA.2014.7083513","url":null,"abstract":"Normalized cut based image segmentation has a variety of applications in the area of image compression, medical imaging, mapping and measurements. But, the computational complexity of conventional normalized cut algorithm based on generalized eigenvalue problem is high. In this study, we proposed a simplified normalized cut algorithm using graph partitioning method for image segmentation. The computational cost of this simplified method are relatively low and hence, it can be implemented on real time embedded system applications. We have implemented an FPGA based image segmentation system using the simplified normalized cut algorithm and tested it for malarial parasites detection. Verilog Hardware Description Language (Verilog HDL) is used to develop the system and implemented on FPGA Spartan-6 targeted device xc6slx16- 2csg324. The Simple-As-Possible (SAP) computer architecture is used to design the system. We think the proposed architecture can be useful for real time image segmentation.","PeriodicalId":22294,"journal":{"name":"The 8th International Conference on Software, Knowledge, Information Management and Applications (SKIMA 2014)","volume":"28 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83665718","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：