Pub Date : 2017-12-01DOI: 10.1109/ICCS1.2017.8326010
Vimala Mathew, Tom Toby, Vikram Singh, B. Rao, M. G. Kumar
Maintenance of equipment is a critical activity for any business involving machines. Predictive maintenance is the method of scheduling maintenance based on the prediction about the failure time of any equipment. The prediction can be done by analyzing the data measurements from the equipment. Machine learning is a technology by which the outcomes can be predicted based on a model prepared by training it on past input data and its output behavior. The model developed can be used to predict machine failure before it actually happens. There are different approaches available for developing a machine learning model. In this paper, a comparative study of existing set of machine learning algorithms to predict the Remaining Useful Lifetime of aircraft's turbo fan engine is done. The machine learning models were constructed based on the datasets from turbo fan engine data from the Prognostics Data Repository of NASA. Using a training set, a model was constructed and was verified with a test data set. The results obtained were compared with the actual results to calculate the accuracy and the algorithm that results in maximum accuracy is identified. We have selected ten machine learning algorithms for comparing the prediction accuracy. The different algorithms were compared to obtain the prediction model having the closest prediction of remaining useful lifecycle in terms of number of life cycles.
{"title":"Prediction of Remaining Useful Lifetime (RUL) of turbofan engine using machine learning","authors":"Vimala Mathew, Tom Toby, Vikram Singh, B. Rao, M. G. Kumar","doi":"10.1109/ICCS1.2017.8326010","DOIUrl":"https://doi.org/10.1109/ICCS1.2017.8326010","url":null,"abstract":"Maintenance of equipment is a critical activity for any business involving machines. Predictive maintenance is the method of scheduling maintenance based on the prediction about the failure time of any equipment. The prediction can be done by analyzing the data measurements from the equipment. Machine learning is a technology by which the outcomes can be predicted based on a model prepared by training it on past input data and its output behavior. The model developed can be used to predict machine failure before it actually happens. There are different approaches available for developing a machine learning model. In this paper, a comparative study of existing set of machine learning algorithms to predict the Remaining Useful Lifetime of aircraft's turbo fan engine is done. The machine learning models were constructed based on the datasets from turbo fan engine data from the Prognostics Data Repository of NASA. Using a training set, a model was constructed and was verified with a test data set. The results obtained were compared with the actual results to calculate the accuracy and the algorithm that results in maximum accuracy is identified. We have selected ten machine learning algorithms for comparing the prediction accuracy. The different algorithms were compared to obtain the prediction model having the closest prediction of remaining useful lifecycle in terms of number of life cycles.","PeriodicalId":367360,"journal":{"name":"2017 IEEE International Conference on Circuits and Systems (ICCS)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127987191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-12-01DOI: 10.1109/ICCS1.2017.8326039
R. Raj, K. Purushothaman, N. A. Singh
The application of DC-DC Boost converter is growing day-by-day (eg: Telecommunication application) and it is always fall to attain a regulated output voltage against load and line variations. In order to regulate the output voltage, conventional PID controllers are normally used, which experiences the effect of sensitivity to disturbances and system non-linearity. In this paper, an intelligent Adaptive TSK-type Neural fuzzy Controller (ATNC) is designed for the control of DC-DC Boost converter. First, the description of the circuit frame work of a DC-DC Boost converter and system modeling is introduced. Then an Adaptive TSK-type Neural Fuzzy Controller (ATNC) system is proposed. This ATNC system is the integrated form of both Fuzzy logic and TSK-type Neural network, thereby incorporating the abilities for learning, optimization and adaptation of neural networks with Fuzzy system. In this method, the error between output of converter and its reference value are used to tune and optimize the ATNC's input membership function parameters; then propagating the same back into the controller. Finally, the simulation results show that the proposed ATNC scheme provides better output voltage tracking with minimal overshoot and settling time over conventional PD controllers and fuzzy controllers.
{"title":"Adaptive TSK-type neural fuzzy controller for boost DC-DC converter","authors":"R. Raj, K. Purushothaman, N. A. Singh","doi":"10.1109/ICCS1.2017.8326039","DOIUrl":"https://doi.org/10.1109/ICCS1.2017.8326039","url":null,"abstract":"The application of DC-DC Boost converter is growing day-by-day (eg: Telecommunication application) and it is always fall to attain a regulated output voltage against load and line variations. In order to regulate the output voltage, conventional PID controllers are normally used, which experiences the effect of sensitivity to disturbances and system non-linearity. In this paper, an intelligent Adaptive TSK-type Neural fuzzy Controller (ATNC) is designed for the control of DC-DC Boost converter. First, the description of the circuit frame work of a DC-DC Boost converter and system modeling is introduced. Then an Adaptive TSK-type Neural Fuzzy Controller (ATNC) system is proposed. This ATNC system is the integrated form of both Fuzzy logic and TSK-type Neural network, thereby incorporating the abilities for learning, optimization and adaptation of neural networks with Fuzzy system. In this method, the error between output of converter and its reference value are used to tune and optimize the ATNC's input membership function parameters; then propagating the same back into the controller. Finally, the simulation results show that the proposed ATNC scheme provides better output voltage tracking with minimal overshoot and settling time over conventional PD controllers and fuzzy controllers.","PeriodicalId":367360,"journal":{"name":"2017 IEEE International Conference on Circuits and Systems (ICCS)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128015805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-12-01DOI: 10.1109/ICCS1.2017.8326040
A. F. Jalin, J. Jayakumari
TTS (Text-To-Speech) systems generate speech equivalent for the text given as input. Though generation of speech is with moderate complexity the aspect of introducing naturality with the expression of the speaker is a big challenge faced in TTS. When in Tamil, because of its phonetics, the algorithms used for other languages like English will not work because of adaptive pronunciations which are completely dependent on the language constructs. Our proposed work will be in the TTS area of signal processing. Current researches have used HMM (A Hidden Markov model) as the machine learning algorithm for classification and is one of the first of the Indic word recognition system. In this paper, an HMM speech synthesis is done using the HMM for the Tamil language.
TTS (text - to - speech)系统为输入的文本生成等效的语音。虽然语音生成具有中等的复杂性，但如何将说话人的表达引入自然是语音生成中面临的一大挑战。在泰米尔语中，由于其语音，用于其他语言(如英语)的算法将不起作用，因为自适应发音完全依赖于语言结构。我们提议的工作将在信号处理的TTS领域。目前的研究使用隐马尔可夫模型(HMM)作为机器学习算法进行分类，是最早的印度语单词识别系统之一。本文利用HMM对泰米尔语进行了HMM语音合成。
{"title":"Text to speech synthesis system for tamil using HMM","authors":"A. F. Jalin, J. Jayakumari","doi":"10.1109/ICCS1.2017.8326040","DOIUrl":"https://doi.org/10.1109/ICCS1.2017.8326040","url":null,"abstract":"TTS (Text-To-Speech) systems generate speech equivalent for the text given as input. Though generation of speech is with moderate complexity the aspect of introducing naturality with the expression of the speaker is a big challenge faced in TTS. When in Tamil, because of its phonetics, the algorithms used for other languages like English will not work because of adaptive pronunciations which are completely dependent on the language constructs. Our proposed work will be in the TTS area of signal processing. Current researches have used HMM (A Hidden Markov model) as the machine learning algorithm for classification and is one of the first of the Indic word recognition system. In this paper, an HMM speech synthesis is done using the HMM for the Tamil language.","PeriodicalId":367360,"journal":{"name":"2017 IEEE International Conference on Circuits and Systems (ICCS)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132508352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-12-01DOI: 10.1109/ICCS1.2017.8326015
Shubankar Kumar, T. Shanmuganantham
This Paper describes a micro PIN photodiode model using Micro-electromechanical Systems (MEMS) technology. The model is developed using Comsol Multiphysics Software. This interface combines the semiconductor interface with the electromagnetic waves, frequency domain interface and is suitable for modeling direct band-gap optoelectronic semiconductor devices. This device is operated at a wavelength of 725 nm for the peak value of the current. The width and the height of the device is 0.5[μm] and 1[μm] respectively. This PIN photodiode can be uses as a light sensor for the solar applications like sun sensor, solar light, solar battery and solar instruments. It is also suitable for the industrial and inter terrestrial applications.
{"title":"Design and modeling of PIN photodiode using MEMS technology","authors":"Shubankar Kumar, T. Shanmuganantham","doi":"10.1109/ICCS1.2017.8326015","DOIUrl":"https://doi.org/10.1109/ICCS1.2017.8326015","url":null,"abstract":"This Paper describes a micro PIN photodiode model using Micro-electromechanical Systems (MEMS) technology. The model is developed using Comsol Multiphysics Software. This interface combines the semiconductor interface with the electromagnetic waves, frequency domain interface and is suitable for modeling direct band-gap optoelectronic semiconductor devices. This device is operated at a wavelength of 725 nm for the peak value of the current. The width and the height of the device is 0.5[μm] and 1[μm] respectively. This PIN photodiode can be uses as a light sensor for the solar applications like sun sensor, solar light, solar battery and solar instruments. It is also suitable for the industrial and inter terrestrial applications.","PeriodicalId":367360,"journal":{"name":"2017 IEEE International Conference on Circuits and Systems (ICCS)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130580932","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-12-01DOI: 10.1109/ICCS1.2017.8325961
K. Sajith, J. Gandhimohan, T. Shanmuganantham
A novel SRR loaded rectangular, octagonal slot and octagonal slot with octagonal patch shape coplanar wave guide fed with truncated ground structure configured wearable antenna is exceptionally essential part for wearable device module for electroencephalogram (EEG) and healthcare monitoring. This antenna designed to fine-tune at resonating frequency 2.45GHz is one of the on-body narrow band unlicensed communication band. This is SRR loaded antenna; hence it has high gain, bandwidth, flexible frequency tune, low-power consumption, less size and weight, low profile and conformal to on body-for high data rate wireless surface body communication. The proposed model using a buffer layer and SRR loaded structure, which is located in between radiation element and skin layer, therefore the designed antenna has enabled to have high gain and more isolation from skin layer. The simulated results for the magnitude of reflection coefficients are −25.4dB at 2.40GHz [a] and −36.5dB at 2.45GHz [b], −22.49dB at 2.43GHz [c], for SRR loaded proposed antennas. These values are more suitable for standard ISM communication.
{"title":"Design of SRR loaded octagonal slot CPW fed wearable antenna for EEG monitoring applications","authors":"K. Sajith, J. Gandhimohan, T. Shanmuganantham","doi":"10.1109/ICCS1.2017.8325961","DOIUrl":"https://doi.org/10.1109/ICCS1.2017.8325961","url":null,"abstract":"A novel SRR loaded rectangular, octagonal slot and octagonal slot with octagonal patch shape coplanar wave guide fed with truncated ground structure configured wearable antenna is exceptionally essential part for wearable device module for electroencephalogram (EEG) and healthcare monitoring. This antenna designed to fine-tune at resonating frequency 2.45GHz is one of the on-body narrow band unlicensed communication band. This is SRR loaded antenna; hence it has high gain, bandwidth, flexible frequency tune, low-power consumption, less size and weight, low profile and conformal to on body-for high data rate wireless surface body communication. The proposed model using a buffer layer and SRR loaded structure, which is located in between radiation element and skin layer, therefore the designed antenna has enabled to have high gain and more isolation from skin layer. The simulated results for the magnitude of reflection coefficients are −25.4dB at 2.40GHz [a] and −36.5dB at 2.45GHz [b], −22.49dB at 2.43GHz [c], for SRR loaded proposed antennas. These values are more suitable for standard ISM communication.","PeriodicalId":367360,"journal":{"name":"2017 IEEE International Conference on Circuits and Systems (ICCS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131974680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-12-01DOI: 10.1109/ICCS1.2017.8325970
R. P. Aneesh, Dinakar Prasad Vajja, P. Pramod, Priyesh Kumar, Arun Peethambaran
Chandra's Surface Thermo-Physical Experiment (ChaSTE) is one of the science experiment proposed to conduct in lunar surface in Chandrayaan-2 mission. This experiment is going to be carried out for twenty eight days in lunar surface by establishing a live control from earth station. Check out systems are being designed and implemented as part of testing payload. The functions of this check out system are the replica of the spacecraft command and data communication system. This system simulates the communication and control operations in the experiment. In this paper, a check out system is proposed as the spacecraft command and data system for the payload ChaSTE using microcontroller. ChaSTE spacecraft command and data system simulator (CCDS) acts as the space craft communication system which simulates the telemetry and telecommand operations. The main functions of the ChaSTE spacecraft command and data system simulator are i) control the set of instruments associated with the payload ii) Collect, process, format, store data from the payload and deliver data to the space craft communication system iii) Receive, decode, store, distribute commands from earth station and initiate all commands. CCDS also measures health parameters of the entire system. In addition, It controls the deployment and heating mechanism with data validation. Simulation model and engineering model of CCDS are designed and implemented with Industrial and space qualified components. Graphical User Interface (GUI) software is designed and developed for the earth control station. The ChaSTE Spacecraft command and data system was successfully tested at different temperature and pressure conditions.
{"title":"Spacecraft command and data system simulator for the payload chaste in Chandrayaan-2 mission","authors":"R. P. Aneesh, Dinakar Prasad Vajja, P. Pramod, Priyesh Kumar, Arun Peethambaran","doi":"10.1109/ICCS1.2017.8325970","DOIUrl":"https://doi.org/10.1109/ICCS1.2017.8325970","url":null,"abstract":"Chandra's Surface Thermo-Physical Experiment (ChaSTE) is one of the science experiment proposed to conduct in lunar surface in Chandrayaan-2 mission. This experiment is going to be carried out for twenty eight days in lunar surface by establishing a live control from earth station. Check out systems are being designed and implemented as part of testing payload. The functions of this check out system are the replica of the spacecraft command and data communication system. This system simulates the communication and control operations in the experiment. In this paper, a check out system is proposed as the spacecraft command and data system for the payload ChaSTE using microcontroller. ChaSTE spacecraft command and data system simulator (CCDS) acts as the space craft communication system which simulates the telemetry and telecommand operations. The main functions of the ChaSTE spacecraft command and data system simulator are i) control the set of instruments associated with the payload ii) Collect, process, format, store data from the payload and deliver data to the space craft communication system iii) Receive, decode, store, distribute commands from earth station and initiate all commands. CCDS also measures health parameters of the entire system. In addition, It controls the deployment and heating mechanism with data validation. Simulation model and engineering model of CCDS are designed and implemented with Industrial and space qualified components. Graphical User Interface (GUI) software is designed and developed for the earth control station. The ChaSTE Spacecraft command and data system was successfully tested at different temperature and pressure conditions.","PeriodicalId":367360,"journal":{"name":"2017 IEEE International Conference on Circuits and Systems (ICCS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125112093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-12-01DOI: 10.1109/ICCS1.2017.8325953
T. H. Sardar, A. Khatun, Sahanowaj Khan
In today's world, WSN (Wireless Sensor network) have gained a lot of attention due to its applications. Wireless Sensor Networks (WSNs) consist of small nodes with sensing, computation, and wireless communications capabilities. Designing a routing protocol in WSN is a very challenging task many routing, power management, and data dissemination protocols have been specifically designed for WSNs where energy awareness is an essential design issue. The focus, however, has been given to the routing protocols which might differ depending on the application and network architecture. In this paper we have discussed a routing protocol CTP (Collection Tree Protocol) which is responsible for constructing and maintaining the routing tree to send data to the root node. We have proposed an algorithm which saves energy in CTP in routing by recovering a damaged route. We have run the CTP protocol on TOSSIM Simulator in Tinyos2.1.2.
在当今世界，无线传感器网络(WSN)因其广泛的应用而受到了广泛的关注。无线传感器网络(wsn)由具有传感、计算和无线通信能力的小节点组成。在无线传感器网络中设计路由协议是一项非常具有挑战性的任务，许多路由、电源管理和数据传播协议都是专门为无线传感器网络设计的，其中能量感知是一个基本的设计问题。然而，重点是路由协议，它可能因应用程序和网络体系结构而有所不同。本文讨论了一种路由协议CTP (Collection Tree protocol)，它负责构造和维护路由树，将数据发送到根节点。提出了一种通过恢复损坏路由来节省CTP路由能量的算法。我们已经在Tinyos2.1.2的TOSSIM模拟器上运行了CTP协议。
{"title":"Design of energy aware collection tree protocol in Wireless Sensor Network","authors":"T. H. Sardar, A. Khatun, Sahanowaj Khan","doi":"10.1109/ICCS1.2017.8325953","DOIUrl":"https://doi.org/10.1109/ICCS1.2017.8325953","url":null,"abstract":"In today's world, WSN (Wireless Sensor network) have gained a lot of attention due to its applications. Wireless Sensor Networks (WSNs) consist of small nodes with sensing, computation, and wireless communications capabilities. Designing a routing protocol in WSN is a very challenging task many routing, power management, and data dissemination protocols have been specifically designed for WSNs where energy awareness is an essential design issue. The focus, however, has been given to the routing protocols which might differ depending on the application and network architecture. In this paper we have discussed a routing protocol CTP (Collection Tree Protocol) which is responsible for constructing and maintaining the routing tree to send data to the root node. We have proposed an algorithm which saves energy in CTP in routing by recovering a damaged route. We have run the CTP protocol on TOSSIM Simulator in Tinyos2.1.2.","PeriodicalId":367360,"journal":{"name":"2017 IEEE International Conference on Circuits and Systems (ICCS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122277432","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-12-01DOI: 10.1109/ICCS1.2017.8326014
K. Sajith, J. Gandhimohan, T. Shanmuganantham
The SRR loaded circular ring encircled by an octagonal patch shaped conductor backed coplanar wave guide fed with miniaturizarised antenna is outstandingly necessary part for wearable device module for electroencephalogram (EEG) and healthcare monitoring. This antenna designed to fine-tune at resonating frequency of 2.41GHz and 3.6GHz. The simulated results for the magnitude of reflection coefficients are −13.3dB at 2.47GHz and −31dB at 3.6GHz for SRR loaded proposed antenna, −30.6dB at 2.41GHz and for non-SRR loaded proposed antenna respectively. These values are more suitable for standard ISM and WLAN communication.
{"title":"SRR loaded and CB-CPW fed octagonal shape antenna for wearable applications","authors":"K. Sajith, J. Gandhimohan, T. Shanmuganantham","doi":"10.1109/ICCS1.2017.8326014","DOIUrl":"https://doi.org/10.1109/ICCS1.2017.8326014","url":null,"abstract":"The SRR loaded circular ring encircled by an octagonal patch shaped conductor backed coplanar wave guide fed with miniaturizarised antenna is outstandingly necessary part for wearable device module for electroencephalogram (EEG) and healthcare monitoring. This antenna designed to fine-tune at resonating frequency of 2.41GHz and 3.6GHz. The simulated results for the magnitude of reflection coefficients are −13.3dB at 2.47GHz and −31dB at 3.6GHz for SRR loaded proposed antenna, −30.6dB at 2.41GHz and for non-SRR loaded proposed antenna respectively. These values are more suitable for standard ISM and WLAN communication.","PeriodicalId":367360,"journal":{"name":"2017 IEEE International Conference on Circuits and Systems (ICCS)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116768810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-12-01DOI: 10.1109/ICCS1.2017.8325954
T. H. Sardar, Z. Ansari, A. Khatun
One of the significant data mining techniques is clustering. Due to digitalization and globalization of each work space, large datasets are being generated rapidly. Such large dataset clustering is a challenge for traditional sequential clustering algorithms as it requires large execution time to cluster such datasets. Distributed parallel architectures and algorithms are thus helpful to achieve performance and scalability requirement of clustering large datasets. In this study, we design and experiment a parallel k-means algorithm using MapReduce programming model and compared the result with sequential k-means for clustering varying size of document dataset. The result demonstrates that proposed k-means obtains higher performance and outperformed sequential k-means while clustering documents.
{"title":"An evaluation of Hadoop cluster efficiency in document clustering using parallel K-means","authors":"T. H. Sardar, Z. Ansari, A. Khatun","doi":"10.1109/ICCS1.2017.8325954","DOIUrl":"https://doi.org/10.1109/ICCS1.2017.8325954","url":null,"abstract":"One of the significant data mining techniques is clustering. Due to digitalization and globalization of each work space, large datasets are being generated rapidly. Such large dataset clustering is a challenge for traditional sequential clustering algorithms as it requires large execution time to cluster such datasets. Distributed parallel architectures and algorithms are thus helpful to achieve performance and scalability requirement of clustering large datasets. In this study, we design and experiment a parallel k-means algorithm using MapReduce programming model and compared the result with sequential k-means for clustering varying size of document dataset. The result demonstrates that proposed k-means obtains higher performance and outperformed sequential k-means while clustering documents.","PeriodicalId":367360,"journal":{"name":"2017 IEEE International Conference on Circuits and Systems (ICCS)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128583820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-12-01DOI: 10.1109/ICCS1.2017.8325988
B. K. Jose, G. Vincent
In this paper, an improves islanding detection technique for grid connected photovoltaic systems is proposed based on the harmonic current produced by the inverter. The inverter is controlled using constant current control scheme by injecting harmonic current signal generated from the system itself. So this detection technique has the benefits of both passive and active detection methods such as power quality enhancement and reduction of non-detection zone (NDZ) respectively. The proposal is validated through simulation studies in a single phase grid connected Photovoltaic system and the islanding operation is detected in a very short time, with reduction in the NDZ compared to the conventional current control method.
{"title":"Harmonic current based islanding detection for grid connected PV systems","authors":"B. K. Jose, G. Vincent","doi":"10.1109/ICCS1.2017.8325988","DOIUrl":"https://doi.org/10.1109/ICCS1.2017.8325988","url":null,"abstract":"In this paper, an improves islanding detection technique for grid connected photovoltaic systems is proposed based on the harmonic current produced by the inverter. The inverter is controlled using constant current control scheme by injecting harmonic current signal generated from the system itself. So this detection technique has the benefits of both passive and active detection methods such as power quality enhancement and reduction of non-detection zone (NDZ) respectively. The proposal is validated through simulation studies in a single phase grid connected Photovoltaic system and the islanding operation is detected in a very short time, with reduction in the NDZ compared to the conventional current control method.","PeriodicalId":367360,"journal":{"name":"2017 IEEE International Conference on Circuits and Systems (ICCS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122082501","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：