Pub Date : 2011-10-10DOI: 10.1109/ICIINFS.2011.6038065
D. Dissanayaka, C. Fernando, S. Abeyratne
The paper proposes an inverter controlling network which integrates demand response and energy management through a smart meter. The network consists of slave controllers each of which has the capability of controlling an inverter. The system incorporates one master controller which handles the communication with slave controllers, a smart meter with a ZigBee module for monitoring the overall power consumption, and a software application (centralized controlling system) to implement control actions-based on the data captured in the smart meter. The application-software applies on the system, the pre-defined constraints and priorities defined in the smart meter. Also the application-software communicates with the smart gird for demand responses, and derives appropriate load controlling (shedding/shifting) commands. These commands are then sent to inverter controlling network so that the energy consumption of the system is managed. The implementation of energy management and saving with integrated commercially available smart-meter is illustrated in this paper through the proposed inverter network. The features of the developed application software are also presented.
{"title":"Smart meter based inverter controlling network for demand response applications in smart grids","authors":"D. Dissanayaka, C. Fernando, S. Abeyratne","doi":"10.1109/ICIINFS.2011.6038065","DOIUrl":"https://doi.org/10.1109/ICIINFS.2011.6038065","url":null,"abstract":"The paper proposes an inverter controlling network which integrates demand response and energy management through a smart meter. The network consists of slave controllers each of which has the capability of controlling an inverter. The system incorporates one master controller which handles the communication with slave controllers, a smart meter with a ZigBee module for monitoring the overall power consumption, and a software application (centralized controlling system) to implement control actions-based on the data captured in the smart meter. The application-software applies on the system, the pre-defined constraints and priorities defined in the smart meter. Also the application-software communicates with the smart gird for demand responses, and derives appropriate load controlling (shedding/shifting) commands. These commands are then sent to inverter controlling network so that the energy consumption of the system is managed. The implementation of energy management and saving with integrated commercially available smart-meter is illustrated in this paper through the proposed inverter network. The features of the developed application software are also presented.","PeriodicalId":353966,"journal":{"name":"2011 6th International Conference on Industrial and Information Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129554240","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 : 2011-10-10DOI: 10.1109/ICIINFS.2011.6038098
Pradeep Kumar, Ashutosh Kumar Singh, Nitin Singh
This paper presents a comparative study of two sensitivity based methods, namely loss sensitivity method and bus sensitivity method, for the optimal capacitor placement problem. The sizing of capacitors is done using the particle swarm optimization (PSO). The performance of these two methods is compared on the basis of the active losses and voltage profile of the bus systems after optimal capacitor placement. The methods have been implemented on IEEE 9-bus and IEEE 69-bus radial distribution systems. The results obtained clearly indicate that bus sensitivity method based capacitor placement gives better results in comparison to the loss sensitivity method.
{"title":"Sensitivity based capacitor placement: A comparative study","authors":"Pradeep Kumar, Ashutosh Kumar Singh, Nitin Singh","doi":"10.1109/ICIINFS.2011.6038098","DOIUrl":"https://doi.org/10.1109/ICIINFS.2011.6038098","url":null,"abstract":"This paper presents a comparative study of two sensitivity based methods, namely loss sensitivity method and bus sensitivity method, for the optimal capacitor placement problem. The sizing of capacitors is done using the particle swarm optimization (PSO). The performance of these two methods is compared on the basis of the active losses and voltage profile of the bus systems after optimal capacitor placement. The methods have been implemented on IEEE 9-bus and IEEE 69-bus radial distribution systems. The results obtained clearly indicate that bus sensitivity method based capacitor placement gives better results in comparison to the loss sensitivity method.","PeriodicalId":353966,"journal":{"name":"2011 6th International Conference on Industrial and Information Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121227641","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 : 2011-10-10DOI: 10.1109/ICIINFS.2011.6038083
W.M. D. R. Gunathilaka, H. G. C. P. Dinesh, K. Narampanawe
Link Budget is a main estimate in telecommunication microwave link planning for accurate and reliable link. This software program is a comprehensive path design tool and it can be used for radio links operating in the microwave frequency range. When a link budget is prepared, many parameters are considered for calculations. Therefore this software program is very essential tool in the telecommunication industry. This paper presents a software tool that can be used to prepare link budgets by providing essential parameters. Moreover this software can be used for applications such as frequency selection according to ITU (International Telecommunication Union) standards, graphical representation of the radio path profile between any two geographical locations on the loaded terrain and generates the Fresnel zone according to the frequency. Furthermore this software tool can be interfaced with a GPS (Global Positioning System) receiver to gather geographical locations and based on this information, microwave frequency band is suggested according to regulatory body guidelines.
{"title":"Semi-automated microwave radio link planning tool","authors":"W.M. D. R. Gunathilaka, H. G. C. P. Dinesh, K. Narampanawe","doi":"10.1109/ICIINFS.2011.6038083","DOIUrl":"https://doi.org/10.1109/ICIINFS.2011.6038083","url":null,"abstract":"Link Budget is a main estimate in telecommunication microwave link planning for accurate and reliable link. This software program is a comprehensive path design tool and it can be used for radio links operating in the microwave frequency range. When a link budget is prepared, many parameters are considered for calculations. Therefore this software program is very essential tool in the telecommunication industry. This paper presents a software tool that can be used to prepare link budgets by providing essential parameters. Moreover this software can be used for applications such as frequency selection according to ITU (International Telecommunication Union) standards, graphical representation of the radio path profile between any two geographical locations on the loaded terrain and generates the Fresnel zone according to the frequency. Furthermore this software tool can be interfaced with a GPS (Global Positioning System) receiver to gather geographical locations and based on this information, microwave frequency band is suggested according to regulatory body guidelines.","PeriodicalId":353966,"journal":{"name":"2011 6th International Conference on Industrial and Information Systems","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123242817","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 : 2011-10-10DOI: 10.1109/ICIINFS.2011.6038055
Melwyn D'Souza, V. S. Ananthanarayana
The explosive growth of mobile devices and wireless networks has raised the interest for information and online service access anywhere and anytime. Due to user mobility, users will have a much closer relationship with their surrounding physical environment and will thus have a much stronger need for search and consume services that are relevant to that environment. This need has driven the development of architectures for supporting the provision of location-based services in which services are associated with particular locations or geographical positions. Location sensitive applications can use such services to provide users with the information that is relevant to their current location. This paper explains the decentralized registry based architecture which provides local services to mobile users depending on their current geographic location using the Web services technology.
{"title":"Decentralized registry based architecture for location-based services","authors":"Melwyn D'Souza, V. S. Ananthanarayana","doi":"10.1109/ICIINFS.2011.6038055","DOIUrl":"https://doi.org/10.1109/ICIINFS.2011.6038055","url":null,"abstract":"The explosive growth of mobile devices and wireless networks has raised the interest for information and online service access anywhere and anytime. Due to user mobility, users will have a much closer relationship with their surrounding physical environment and will thus have a much stronger need for search and consume services that are relevant to that environment. This need has driven the development of architectures for supporting the provision of location-based services in which services are associated with particular locations or geographical positions. Location sensitive applications can use such services to provide users with the information that is relevant to their current location. This paper explains the decentralized registry based architecture which provides local services to mobile users depending on their current geographic location using the Web services technology.","PeriodicalId":353966,"journal":{"name":"2011 6th International Conference on Industrial and Information Systems","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115390068","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 : 2011-10-10DOI: 10.1109/ICIINFS.2011.6038106
S. Al-Mamun, M. S. Islam
Crosstalk due to four-wave mixing (FWM) is the dominant nonlinear effect in long-haul multi-channel optical communication systems which can severely limit system performance. In this paper, we have simulated the effect of chromatic dispersion on FWM using equal and unequal channel spacing in terms of input/output spectrum, eye diagram and bit error rate. Results show that the effect of FWM reduces with the increasing dispersion coefficient, but the reduction is more effective for unequal channel spacing than equal channel spacing.
{"title":"Effect of chromatic dispersion on four-wave mixing in optical WDM transmission system","authors":"S. Al-Mamun, M. S. Islam","doi":"10.1109/ICIINFS.2011.6038106","DOIUrl":"https://doi.org/10.1109/ICIINFS.2011.6038106","url":null,"abstract":"Crosstalk due to four-wave mixing (FWM) is the dominant nonlinear effect in long-haul multi-channel optical communication systems which can severely limit system performance. In this paper, we have simulated the effect of chromatic dispersion on FWM using equal and unequal channel spacing in terms of input/output spectrum, eye diagram and bit error rate. Results show that the effect of FWM reduces with the increasing dispersion coefficient, but the reduction is more effective for unequal channel spacing than equal channel spacing.","PeriodicalId":353966,"journal":{"name":"2011 6th International Conference on Industrial and Information Systems","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129141373","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 : 2011-10-10DOI: 10.1109/ICIINFS.2011.6038062
R. M. T. P. Rajakaruna, W. Fernando, J. Calic
Performance of real-time video processing applications such as surveillance systems, content-based search, is limited by the complexity of video content analysis in the pixel domain. A low complex alternative is to analyse the video in the compressed domain, where content features already available in the compressed video are directly used in the analysis. However, this is achieved at the expense of output precision and reliability, due to compression-efficiency driven feature selection at the encoder. Therefore, video applications could benefit from enhanced reliability of data embedded in the compressed video. In this paper, we present a scalable optimization model that addresses the accuracy of content features in parallel with the conventional rate-distortion optimization criterion. We analyse and optimize rate-distortion performance of video encoder under content description accuracy constrain, using a motion calibrated synthetic data set containing a range of scene and motion complexity levels. Finally, using a natural video data set, we demonstrate that the proposed optimization framework can be used to enhance compressed feature accuracy without incurring a rate-distortion overhead.
{"title":"Video encoder optimization for efficient video analysis in resource-limited systems","authors":"R. M. T. P. Rajakaruna, W. Fernando, J. Calic","doi":"10.1109/ICIINFS.2011.6038062","DOIUrl":"https://doi.org/10.1109/ICIINFS.2011.6038062","url":null,"abstract":"Performance of real-time video processing applications such as surveillance systems, content-based search, is limited by the complexity of video content analysis in the pixel domain. A low complex alternative is to analyse the video in the compressed domain, where content features already available in the compressed video are directly used in the analysis. However, this is achieved at the expense of output precision and reliability, due to compression-efficiency driven feature selection at the encoder. Therefore, video applications could benefit from enhanced reliability of data embedded in the compressed video. In this paper, we present a scalable optimization model that addresses the accuracy of content features in parallel with the conventional rate-distortion optimization criterion. We analyse and optimize rate-distortion performance of video encoder under content description accuracy constrain, using a motion calibrated synthetic data set containing a range of scene and motion complexity levels. Finally, using a natural video data set, we demonstrate that the proposed optimization framework can be used to enhance compressed feature accuracy without incurring a rate-distortion overhead.","PeriodicalId":353966,"journal":{"name":"2011 6th International Conference on Industrial and Information Systems","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127583744","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 : 2011-10-10DOI: 10.1109/ICIINFS.2011.6038071
W. Ruwansiri, E. C. Kulasekere, D. M. M. J. Senarathna, I. Dayawansa
Dielectric spectroscopy (DS) has been suggested as a possible approach for non-invasive glycaemia monitoring. In this procedure, a radiating antenna is used as a sensor to measure the change in impedance due to blood glucose level fluctuation. The type and orientation of the sensor considerably influence the reading and hence the indicated blood glucose level and its accuracy. We propose a novel concentric annular ring slot antenna (CARSA) as a sensor and evaluate the influence of penetration depth on non-invasive glycaemia monitoring using DS. Results demonstrated 40 times increment in sensitivity of DS measurements using CARSA compared with earlier studies.
{"title":"Evaluation of compact CARSA sensor and penetration depth of EM signal for non-invasive blood glucose measurement","authors":"W. Ruwansiri, E. C. Kulasekere, D. M. M. J. Senarathna, I. Dayawansa","doi":"10.1109/ICIINFS.2011.6038071","DOIUrl":"https://doi.org/10.1109/ICIINFS.2011.6038071","url":null,"abstract":"Dielectric spectroscopy (DS) has been suggested as a possible approach for non-invasive glycaemia monitoring. In this procedure, a radiating antenna is used as a sensor to measure the change in impedance due to blood glucose level fluctuation. The type and orientation of the sensor considerably influence the reading and hence the indicated blood glucose level and its accuracy. We propose a novel concentric annular ring slot antenna (CARSA) as a sensor and evaluate the influence of penetration depth on non-invasive glycaemia monitoring using DS. Results demonstrated 40 times increment in sensitivity of DS measurements using CARSA compared with earlier studies.","PeriodicalId":353966,"journal":{"name":"2011 6th International Conference on Industrial and Information Systems","volume":"512 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130014665","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 : 2011-10-10DOI: 10.1109/ICIINFS.2011.6038068
Thabotharan Kathiravelu, N. Ranasinghe, A. Pears
The adaptive routing protocol recently proposed by researchers for opportunistic networks often makes an assumption that when each node makes an intelligent decision of choosing a best forwarder node to route its messages, the chosen forwarder will often have a large buffer storage and will always altruistically devote its resources for forwarding those messages towards their destination nodes. However, copies of messages fill up buffers on receiving intermediate nodes very quickly when few nodes become more central than the other nodes and when the connectivity becomes more and more intermittent. This paper investigates about a more realistic behavior of mobile opportunistic nodes where the storage buffer in nodes gets full very quickly, especially at the more centric nodes, when such nodes store, carry and forward messages for other nodes. Because of these practical issues, messages passed to most popular nodes just get dropped when the buffers get filled up which ultimately results in the performance degradation of the network. We investigate the cases of buffer overflow and analyze how the performance of a considered opportunistic networking environment can get degraded when buffers get overflowed. We then propose an algorithmic approach where nodes choose the potential nodes based not only on potential nodes' predicted connectivity to other nodes but also based on the other factors such as available buffer space in the potential intermediate nodes and the intermediate nodes' willingness to store, carry and forward messages for other nodes. Our initial simulation based experiment results are encouraging and indicate that a congestion aware adaptive routing protocol performs well and the overall network performance increases by means of the number of messages delivered when the message forwarding is constrained by the buffer size.
{"title":"An enhanced congestion aware adaptive routing protocol for opportunistic networks","authors":"Thabotharan Kathiravelu, N. Ranasinghe, A. Pears","doi":"10.1109/ICIINFS.2011.6038068","DOIUrl":"https://doi.org/10.1109/ICIINFS.2011.6038068","url":null,"abstract":"The adaptive routing protocol recently proposed by researchers for opportunistic networks often makes an assumption that when each node makes an intelligent decision of choosing a best forwarder node to route its messages, the chosen forwarder will often have a large buffer storage and will always altruistically devote its resources for forwarding those messages towards their destination nodes. However, copies of messages fill up buffers on receiving intermediate nodes very quickly when few nodes become more central than the other nodes and when the connectivity becomes more and more intermittent. This paper investigates about a more realistic behavior of mobile opportunistic nodes where the storage buffer in nodes gets full very quickly, especially at the more centric nodes, when such nodes store, carry and forward messages for other nodes. Because of these practical issues, messages passed to most popular nodes just get dropped when the buffers get filled up which ultimately results in the performance degradation of the network. We investigate the cases of buffer overflow and analyze how the performance of a considered opportunistic networking environment can get degraded when buffers get overflowed. We then propose an algorithmic approach where nodes choose the potential nodes based not only on potential nodes' predicted connectivity to other nodes but also based on the other factors such as available buffer space in the potential intermediate nodes and the intermediate nodes' willingness to store, carry and forward messages for other nodes. Our initial simulation based experiment results are encouraging and indicate that a congestion aware adaptive routing protocol performs well and the overall network performance increases by means of the number of messages delivered when the message forwarding is constrained by the buffer size.","PeriodicalId":353966,"journal":{"name":"2011 6th International Conference on Industrial and Information Systems","volume":"23 Suppl 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122475907","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 : 2011-10-10DOI: 10.1109/ICIINFS.2011.6038056
S. Vidanagamachchi, S. Dewasurendra, R. Ragel, M. Niranjan
Advances in life sciences over the last few decades have lead to the generation of a huge amount of biological data. Computing research has become a vital part in driving biological discovery where analysis and categorization of biological data are involved. String matching algorithms can be applied for protein/gene sequence matching and with the phenomenal increase in the size of string databases to be analyzed, software implementations of these algorithms seems to have hit a hard limit and hardware acceleration is increasingly being sought. Several hardware platforms such as Field Programmable Gate Arrays (FPGA), Graphics Processing Units (GPU) and Chip Multi Processors (CMP) are being explored as hardware platforms. In this paper, we give a comprehensive overview of the literature on hardware acceleration of string matching algorithms, we take an FPGA hardware exploration and expedite the design time by a design automation technique. Further, our design automation is also optimized for better hardware utilization through optimizing the number of peptides that can be represented in an FPGA tile. The results indicate significant improvements in design time and hardware utilization which are reported in this paper.
{"title":"Tile optimization for area in FPGA based hardware acceleration of peptide identification","authors":"S. Vidanagamachchi, S. Dewasurendra, R. Ragel, M. Niranjan","doi":"10.1109/ICIINFS.2011.6038056","DOIUrl":"https://doi.org/10.1109/ICIINFS.2011.6038056","url":null,"abstract":"Advances in life sciences over the last few decades have lead to the generation of a huge amount of biological data. Computing research has become a vital part in driving biological discovery where analysis and categorization of biological data are involved. String matching algorithms can be applied for protein/gene sequence matching and with the phenomenal increase in the size of string databases to be analyzed, software implementations of these algorithms seems to have hit a hard limit and hardware acceleration is increasingly being sought. Several hardware platforms such as Field Programmable Gate Arrays (FPGA), Graphics Processing Units (GPU) and Chip Multi Processors (CMP) are being explored as hardware platforms. In this paper, we give a comprehensive overview of the literature on hardware acceleration of string matching algorithms, we take an FPGA hardware exploration and expedite the design time by a design automation technique. Further, our design automation is also optimized for better hardware utilization through optimizing the number of peptides that can be represented in an FPGA tile. The results indicate significant improvements in design time and hardware utilization which are reported in this paper.","PeriodicalId":353966,"journal":{"name":"2011 6th International Conference on Industrial and Information Systems","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126303724","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 : 2011-10-10DOI: 10.1109/ICIINFS.2011.6038043
B. M. T. Lekamge, D. Ratnaweera
This paper presents a novel hybrid method for tea color separation using image processing and artificial intelligence techniques. The objective of this research is to identify the stalk particles which reduce the quality of tea, without removing good particles with the intention of increasing the income of the tea manufacturing process. In order to achieve this goal it is important to identify the positions of the stalk particles. Several methods were tested with the aim of solving this problem including thresholding the image according to pixel values and a fuzzy system. The most accurate outcome was obtained by using the fuzzy system which was developed by using three input variables obtained from the RGB components of each pixel. The stalk particles were identified using threshold values which divided the output in to two sections. Although the fuzzy system gave the most accurate output, the thresholding method was found to be the fastest. However, this thresholding method has a drawback of identifying corners of good tea particles as stalks. The thresholding method provided an accuracy rate of 93% where as the fuzzy system provided an accuracy rate of 99%.
{"title":"A hybrid approach for online tea color separation","authors":"B. M. T. Lekamge, D. Ratnaweera","doi":"10.1109/ICIINFS.2011.6038043","DOIUrl":"https://doi.org/10.1109/ICIINFS.2011.6038043","url":null,"abstract":"This paper presents a novel hybrid method for tea color separation using image processing and artificial intelligence techniques. The objective of this research is to identify the stalk particles which reduce the quality of tea, without removing good particles with the intention of increasing the income of the tea manufacturing process. In order to achieve this goal it is important to identify the positions of the stalk particles. Several methods were tested with the aim of solving this problem including thresholding the image according to pixel values and a fuzzy system. The most accurate outcome was obtained by using the fuzzy system which was developed by using three input variables obtained from the RGB components of each pixel. The stalk particles were identified using threshold values which divided the output in to two sections. Although the fuzzy system gave the most accurate output, the thresholding method was found to be the fastest. However, this thresholding method has a drawback of identifying corners of good tea particles as stalks. The thresholding method provided an accuracy rate of 93% where as the fuzzy system provided an accuracy rate of 99%.","PeriodicalId":353966,"journal":{"name":"2011 6th International Conference on Industrial and Information Systems","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132681361","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：