Pub Date : 2020-03-01DOI: 10.1109/ICCMC48092.2020.ICCMC-00043
R. Ramachandran, Gopika Ravichandran, Aswathi Raveendran
In this digital era, big data has very high dimension and requires large amount of space for its data storage. Hence a lossless data interpretation will be difficult when big data contains large dimension. But, all these dimensions in big data may not be relevant or they may be interrelated and hence redundancy may exist in attribute set. Dimensionality reduction is a technique which focusses on downsizing the attributes and complication of a high dimensional data. In this paper, a detailed study of different dimensionality reduction techniques namely principal component analysis (PCA), linear discriminant analysis (LDA), kernel principal component analysis (KPCA), singular value decomposition (SVD), independent component analysis (ICA) has been proposed. Furthermore, it also provides comparative analysis based on various parameters.
{"title":"Evaluation of Dimensionality Reduction Techniques for Big data","authors":"R. Ramachandran, Gopika Ravichandran, Aswathi Raveendran","doi":"10.1109/ICCMC48092.2020.ICCMC-00043","DOIUrl":"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-00043","url":null,"abstract":"In this digital era, big data has very high dimension and requires large amount of space for its data storage. Hence a lossless data interpretation will be difficult when big data contains large dimension. But, all these dimensions in big data may not be relevant or they may be interrelated and hence redundancy may exist in attribute set. Dimensionality reduction is a technique which focusses on downsizing the attributes and complication of a high dimensional data. In this paper, a detailed study of different dimensionality reduction techniques namely principal component analysis (PCA), linear discriminant analysis (LDA), kernel principal component analysis (KPCA), singular value decomposition (SVD), independent component analysis (ICA) has been proposed. Furthermore, it also provides comparative analysis based on various parameters.","PeriodicalId":130581,"journal":{"name":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124404576","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 : 2020-03-01DOI: 10.1109/ICCMC48092.2020.ICCMC-000125
D. Mahapatra, Chandan Maharana, S. Panda, J. P. Mohanty, Abu Talib, Amit Mangaraj
Due to the increasing number of digital document repositories there is a heavy demand for information retrieval systems and therefore, information retrieval is still appearing as an emerging area of research. The information retrieval technology these days focuses on achieving better performance under different context by extracting documents most appropriate to the user’s query. Majority of the classical keyword based retrieval techniques does not focus on semantic meanings and therefore, are found to be less effective in reconstructing the actual information conveyed in the context. Also, retrieval of the relevant documents depends on appropriate analysis of the query terms. As words are polysemic, their actual meanings are influenced by their relationships with other words and their syntactic roles in the sentence. This work presents a fuzzy-cluster based semantic information retrieval model that considers these relationships to determine the exact meaning of the user query and extracts relevant documents as per their relevance scores.
{"title":"A Fuzzy-Cluster based Semantic Information Retrieval System","authors":"D. Mahapatra, Chandan Maharana, S. Panda, J. P. Mohanty, Abu Talib, Amit Mangaraj","doi":"10.1109/ICCMC48092.2020.ICCMC-000125","DOIUrl":"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-000125","url":null,"abstract":"Due to the increasing number of digital document repositories there is a heavy demand for information retrieval systems and therefore, information retrieval is still appearing as an emerging area of research. The information retrieval technology these days focuses on achieving better performance under different context by extracting documents most appropriate to the user’s query. Majority of the classical keyword based retrieval techniques does not focus on semantic meanings and therefore, are found to be less effective in reconstructing the actual information conveyed in the context. Also, retrieval of the relevant documents depends on appropriate analysis of the query terms. As words are polysemic, their actual meanings are influenced by their relationships with other words and their syntactic roles in the sentence. This work presents a fuzzy-cluster based semantic information retrieval model that considers these relationships to determine the exact meaning of the user query and extracts relevant documents as per their relevance scores.","PeriodicalId":130581,"journal":{"name":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134095056","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 : 2020-03-01DOI: 10.1109/ICCMC48092.2020.ICCMC-000133
Tarish Ahmed B, M. S. Krishnan, Athul Anil
The recent research advancement of wireless protocols, cloud development services, and reduced hardware costs have launched a new dawn for cloud computing. Fog computing widens the cloud computing paradigm to the network’s edge and assists in the production and creation of multiple new Internet services and applications. Normally, IoT gateways are used under the IoT fog computing model to communicate data with IoT devices and the cloud. A plethora of wireless technologies exist, of that WiFi remains the ideal communication technology and WIFI6 the preferred protocol for fog in particular as it has various advantages over its predecessors like extended battery life, support for more than one device at a time with the help of OFDMA, simultaneous connection with multiple devices, increased data rates with the help of MU-MIMO, and the use of MPTL topology which makes connections easier and faster.
{"title":"A Predictive Analysis on the Influence of WiFi 6 in Fog Computing with OFDMA and MU-MIMO","authors":"Tarish Ahmed B, M. S. Krishnan, Athul Anil","doi":"10.1109/ICCMC48092.2020.ICCMC-000133","DOIUrl":"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-000133","url":null,"abstract":"The recent research advancement of wireless protocols, cloud development services, and reduced hardware costs have launched a new dawn for cloud computing. Fog computing widens the cloud computing paradigm to the network’s edge and assists in the production and creation of multiple new Internet services and applications. Normally, IoT gateways are used under the IoT fog computing model to communicate data with IoT devices and the cloud. A plethora of wireless technologies exist, of that WiFi remains the ideal communication technology and WIFI6 the preferred protocol for fog in particular as it has various advantages over its predecessors like extended battery life, support for more than one device at a time with the help of OFDMA, simultaneous connection with multiple devices, increased data rates with the help of MU-MIMO, and the use of MPTL topology which makes connections easier and faster.","PeriodicalId":130581,"journal":{"name":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134255549","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 : 2020-03-01DOI: 10.1109/ICCMC48092.2020.ICCMC-000137
S. Kargutkar, V. Chitre
Cyberbullying disturbs harassment online, with alarming implications. It exists in different ways, and is in textual format in most social networks. There is no question that over 1.96 billion of them would have an inescapable social operation. However, the developing decade presents genuine difficulties and the online-conduct of clients have been put to address. Expanding instances of provocation and harassing alongside instances of casualty has been a difficult issue. Programmed discovery of such episodes requires smart frameworks. A large portion of the current studies have been moving towards this issue with standard machine learning models and most of the models produced in these studies are scalable at one time into a solitary social network. Deep learning based models have discovered ways in the identification of digital harassing occurrences, asserting that they can beat the restrictions of the ordinary models, and improve the discovery execution. However, numerous old-school models are accessible to control the incident, the need to successfully order the tormenting is as yet weak. To successfully screen the harassing in the virtual space and to stop the savage outcome with the execution of Machine learning and Language preparing. A system is proposed to give a double characterization of cyberbullying. Our technique utilizes an inventive idea of CNN for content examination anyway the current strategies utilize a guileless way to deal with furnish the arrangement with less precision. A current dataset is utilized for experimentation and our system is proposed with other existing methods and is found to give better precision and grouping.
{"title":"A Study of Cyberbullying Detection Using Machine Learning Techniques","authors":"S. Kargutkar, V. Chitre","doi":"10.1109/ICCMC48092.2020.ICCMC-000137","DOIUrl":"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-000137","url":null,"abstract":"Cyberbullying disturbs harassment online, with alarming implications. It exists in different ways, and is in textual format in most social networks. There is no question that over 1.96 billion of them would have an inescapable social operation. However, the developing decade presents genuine difficulties and the online-conduct of clients have been put to address. Expanding instances of provocation and harassing alongside instances of casualty has been a difficult issue. Programmed discovery of such episodes requires smart frameworks. A large portion of the current studies have been moving towards this issue with standard machine learning models and most of the models produced in these studies are scalable at one time into a solitary social network. Deep learning based models have discovered ways in the identification of digital harassing occurrences, asserting that they can beat the restrictions of the ordinary models, and improve the discovery execution. However, numerous old-school models are accessible to control the incident, the need to successfully order the tormenting is as yet weak. To successfully screen the harassing in the virtual space and to stop the savage outcome with the execution of Machine learning and Language preparing. A system is proposed to give a double characterization of cyberbullying. Our technique utilizes an inventive idea of CNN for content examination anyway the current strategies utilize a guileless way to deal with furnish the arrangement with less precision. A current dataset is utilized for experimentation and our system is proposed with other existing methods and is found to give better precision and grouping.","PeriodicalId":130581,"journal":{"name":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","volume":"28 15","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132938291","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 : 2020-03-01DOI: 10.1109/ICCMC48092.2020.ICCMC-000159
T. Sathis Kumar, P. Mohamed Nabeem, C. K. Manoj, K. Jeyachandran
Web discussions are as often as possible utilized as stages for the trading of data and assessments just as publicity dispersal. The client produced content on the web develops quickly right now age. The transformative changes in innovation utilize such data to catch just the client’s substance lastly the valuable data are presented to data searchers. The majority of the current research on content data preparing, centers in the genuine area as opposed to the assessment space. Content mining assumes a fundamental job in online gathering feeling mining. Be that as it may, feeling mining from online discussion is significantly more troublesome than unadulterated content procedure because of their semi organized qualities. Order dependent on opinions has become another outskirts to content mining network. The assignment of assumption arrangement is to decide the semantic directions of words, sentences or records. Notion investigation is about conclusion mining. Break down feelings, attributes and assessments of clients about any items, subjects, or issue. For the popular feeling, web is turning into a spreading and exceptionally wide stage where online gatherings, social locales, websites and different destinations contains sentiment and audit of individuals in type of remarks and posted messages. Presently a days the information acquired from these destinations, online journals and remarks and publication is helpful for advertising research. Right now propose an extraction method to score the audits and condense the suppositions to end client. In light of conclusions mined it is chosen as whether to break down the slant of client feed backs and furthermore channel the sentiments dependent on client areas. This venture for the most part centers on giving a system to mining the feelings utilizing nonexclusive client centered surveys utilizing common language preparing steps. We can actualize this system progressively situations and furthermore improve the precision in feeling mining in python structure.
{"title":"Sentimental Analysis (Opinion Mining) in Social Network by Using Svm Algorithm","authors":"T. Sathis Kumar, P. Mohamed Nabeem, C. K. Manoj, K. Jeyachandran","doi":"10.1109/ICCMC48092.2020.ICCMC-000159","DOIUrl":"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-000159","url":null,"abstract":"Web discussions are as often as possible utilized as stages for the trading of data and assessments just as publicity dispersal. The client produced content on the web develops quickly right now age. The transformative changes in innovation utilize such data to catch just the client’s substance lastly the valuable data are presented to data searchers. The majority of the current research on content data preparing, centers in the genuine area as opposed to the assessment space. Content mining assumes a fundamental job in online gathering feeling mining. Be that as it may, feeling mining from online discussion is significantly more troublesome than unadulterated content procedure because of their semi organized qualities. Order dependent on opinions has become another outskirts to content mining network. The assignment of assumption arrangement is to decide the semantic directions of words, sentences or records. Notion investigation is about conclusion mining. Break down feelings, attributes and assessments of clients about any items, subjects, or issue. For the popular feeling, web is turning into a spreading and exceptionally wide stage where online gatherings, social locales, websites and different destinations contains sentiment and audit of individuals in type of remarks and posted messages. Presently a days the information acquired from these destinations, online journals and remarks and publication is helpful for advertising research. Right now propose an extraction method to score the audits and condense the suppositions to end client. In light of conclusions mined it is chosen as whether to break down the slant of client feed backs and furthermore channel the sentiments dependent on client areas. This venture for the most part centers on giving a system to mining the feelings utilizing nonexclusive client centered surveys utilizing common language preparing steps. We can actualize this system progressively situations and furthermore improve the precision in feeling mining in python structure.","PeriodicalId":130581,"journal":{"name":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117291786","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 : 2020-03-01DOI: 10.1109/ICCMC48092.2020.ICCMC-000157
Xinming Gao, Gaoteng Yuan, Mengjiao Zhang
With electric cars, large-scale development, in order to make the electric vehicles charging more convenient and efficient, public charging piles began to be used on a large scale. However, traditional fault detection methods are still used in charging piles, which makes the detection efficiency low. This paper proposes an error detection procedure of charging pile founded on ELM method. Different from the traditional charging pile fault detection model, this method constructs data for common features of the charging pile and establishes a classification prediction frame work that relies on the Extreme Learning Machine (ELM) algorithm. Experimental results evinces that the frame works accuracy is 83%, with a high efficiency, strong practicability, and is easy to popularize.
{"title":"Fault Detection of Electric Vehicle Charging Piles Based on Extreme Learning Machine Algorithm","authors":"Xinming Gao, Gaoteng Yuan, Mengjiao Zhang","doi":"10.1109/ICCMC48092.2020.ICCMC-000157","DOIUrl":"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-000157","url":null,"abstract":"With electric cars, large-scale development, in order to make the electric vehicles charging more convenient and efficient, public charging piles began to be used on a large scale. However, traditional fault detection methods are still used in charging piles, which makes the detection efficiency low. This paper proposes an error detection procedure of charging pile founded on ELM method. Different from the traditional charging pile fault detection model, this method constructs data for common features of the charging pile and establishes a classification prediction frame work that relies on the Extreme Learning Machine (ELM) algorithm. Experimental results evinces that the frame works accuracy is 83%, with a high efficiency, strong practicability, and is easy to popularize.","PeriodicalId":130581,"journal":{"name":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121605689","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 : 2020-03-01DOI: 10.1109/ICCMC48092.2020.ICCMC-000185
Sathuluri Mallikharjuna Rao, T. Saikumar, J. Reddy, V.Ravi Chowdary, Ammam.Jaya Apurva Rani
Modern era require modern solutions and modern technologies. Thereby modernizing such in the domain of antennas, a new type of patch antenna intended for C-band applications is designed printing over a FR4_epoxy substrate. whose dimensions, is W$_{1} times L_{1} times h$ as 35mm $times30$ mm $times1.6$ mm the simulations results showed that the antenna works at a single resonant frequency 5.9Ghz, hence covering the applications like military, weather forecasting, defense tracking and air traffic control. The antenna feed with co-planar wave guide (CPW) is a simulation-based design and the parameters of antenna designed are optimized by making use of ANSYS HFSS software.
{"title":"A CPW Fed Patch Antenna Design for Weather Monitoring, Air Traffic Control and Defense Tracking Applications","authors":"Sathuluri Mallikharjuna Rao, T. Saikumar, J. Reddy, V.Ravi Chowdary, Ammam.Jaya Apurva Rani","doi":"10.1109/ICCMC48092.2020.ICCMC-000185","DOIUrl":"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-000185","url":null,"abstract":"Modern era require modern solutions and modern technologies. Thereby modernizing such in the domain of antennas, a new type of patch antenna intended for C-band applications is designed printing over a FR4_epoxy substrate. whose dimensions, is W$_{1} times L_{1} times h$ as 35mm $times30$ mm $times1.6$ mm the simulations results showed that the antenna works at a single resonant frequency 5.9Ghz, hence covering the applications like military, weather forecasting, defense tracking and air traffic control. The antenna feed with co-planar wave guide (CPW) is a simulation-based design and the parameters of antenna designed are optimized by making use of ANSYS HFSS software.","PeriodicalId":130581,"journal":{"name":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115878939","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 : 2020-03-01DOI: 10.1109/ICCMC48092.2020.ICCMC-000146
R. Salagar, Pushpa B. Patil
The presence of the skew in a captured document image through a photographic camera, mobile camera or scanner is inevitable. In a document image detection and correction of skew are challenging phases before further processing like segmentation and analysis. In this paper, Run Length Smoothing Algorithm (RLSA) is proposed for the detection and correction of skew for handwritten Kannada document images. The proposed work has mainly two parts, the first part is preprocessing of a document using methods like thresholding, the maximum gradient for extraction of text and text line area with no loss of any data. The second part is skew detection and correction. The algorithm RLSA is used row and column-wise of a document image. The RLSA is applied for skew detection to determine skew (slant) angle further the document is turned in the anti-clockwise direction with the preferred angle, which will remove the skew of a document that has occurred while taking the photocopy of the document. The performance proposed method is evaluated for handwritten Kannada documents; the experiment outcomes are significantly better.
{"title":"Application of RLSA for Skew Detection and Correction in Kannada Text Images","authors":"R. Salagar, Pushpa B. Patil","doi":"10.1109/ICCMC48092.2020.ICCMC-000146","DOIUrl":"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-000146","url":null,"abstract":"The presence of the skew in a captured document image through a photographic camera, mobile camera or scanner is inevitable. In a document image detection and correction of skew are challenging phases before further processing like segmentation and analysis. In this paper, Run Length Smoothing Algorithm (RLSA) is proposed for the detection and correction of skew for handwritten Kannada document images. The proposed work has mainly two parts, the first part is preprocessing of a document using methods like thresholding, the maximum gradient for extraction of text and text line area with no loss of any data. The second part is skew detection and correction. The algorithm RLSA is used row and column-wise of a document image. The RLSA is applied for skew detection to determine skew (slant) angle further the document is turned in the anti-clockwise direction with the preferred angle, which will remove the skew of a document that has occurred while taking the photocopy of the document. The performance proposed method is evaluated for handwritten Kannada documents; the experiment outcomes are significantly better.","PeriodicalId":130581,"journal":{"name":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116940410","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 : 2020-03-01DOI: 10.1109/ICCMC48092.2020.ICCMC-00013
Edu Gopan, Sanjay Rajesh, Vishnu Gr, Akhil Raj R, M. Thushara
Since there is an increasing number of research documents published every year, the documents available on the Internet will also be increasing rapidly. This poses the need to categorize the available research articles into their respective domain to ease the search process and find their research documents under the specific domain. This classification is a tiresome and prolonged process, which can be avoided by using keywords and keyphrases. Keywords or keyphrases provides a summary or information described in a research document. The domain of a research paper can be determined based on extracted keywords and keyphrases. It is monotonous to manually extract keywords and key phrases [4]. Automatic extraction of keyword techniques helps to overcome this challenging task. The classification of these research papers can be achieved more efficiently by using the keywords applicable to a particular domain. This paper aims to compare key extraction algorithms such as TextRank, PositionRank, keyphrase extraction algorithm (KEA) and Multi-purpose automatic topic indexing (MAUI).
{"title":"Comparative Study on Different Approaches in Keyword Extraction","authors":"Edu Gopan, Sanjay Rajesh, Vishnu Gr, Akhil Raj R, M. Thushara","doi":"10.1109/ICCMC48092.2020.ICCMC-00013","DOIUrl":"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-00013","url":null,"abstract":"Since there is an increasing number of research documents published every year, the documents available on the Internet will also be increasing rapidly. This poses the need to categorize the available research articles into their respective domain to ease the search process and find their research documents under the specific domain. This classification is a tiresome and prolonged process, which can be avoided by using keywords and keyphrases. Keywords or keyphrases provides a summary or information described in a research document. The domain of a research paper can be determined based on extracted keywords and keyphrases. It is monotonous to manually extract keywords and key phrases [4]. Automatic extraction of keyword techniques helps to overcome this challenging task. The classification of these research papers can be achieved more efficiently by using the keywords applicable to a particular domain. This paper aims to compare key extraction algorithms such as TextRank, PositionRank, keyphrase extraction algorithm (KEA) and Multi-purpose automatic topic indexing (MAUI).","PeriodicalId":130581,"journal":{"name":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","volume":"191 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114591566","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 : 2020-03-01DOI: 10.1109/ICCMC48092.2020.ICCMC-000109
P. Seethalakshmi, K. Venkatalakshmi
The smart grid is a combination of smart network devices and systems that support the efficient generation, distribution and transmission of energy from source to destination. Energy is becoming one of the most important resources of daily life. In general, technology advancements are rapidly increasing and energy demand is also increasing due to the discovery of new electrical/electronic devices. Most of the conditions, there is a mismatch between energy generation and energy consumption. The big challenge is to maintain a balance between generating energy and using it. The service providers need to forecast the energy demand well in advance with minimal error to maintain the equilibrium state, even a small error in the predictive mechanism leads to a loss for both service providers and consumers. To address these problems we proposed an energy prediction model based on Long Short Term Memory (LSTM). It has emerged as a promising Artificial Neural Network (ANN) technique for predicting time series issues due to the properties of selective retrieval patterns for a long time. Further, the LSTM model is optimized by using Optimizer Ensembles to improve the efficiency of the proposed model. The simulation results show that the proposed LSTM achieves better predictive results (less error, high efficiency) compared to existing methods such as Moving Average (MA), Linear Regression (LR) and k-Nearest Neighbors (k-NN) techniques.
{"title":"Prediction of Energy Demand in Smart Grid Using Deep Neural Networks with Optimizer Ensembles","authors":"P. Seethalakshmi, K. Venkatalakshmi","doi":"10.1109/ICCMC48092.2020.ICCMC-000109","DOIUrl":"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-000109","url":null,"abstract":"The smart grid is a combination of smart network devices and systems that support the efficient generation, distribution and transmission of energy from source to destination. Energy is becoming one of the most important resources of daily life. In general, technology advancements are rapidly increasing and energy demand is also increasing due to the discovery of new electrical/electronic devices. Most of the conditions, there is a mismatch between energy generation and energy consumption. The big challenge is to maintain a balance between generating energy and using it. The service providers need to forecast the energy demand well in advance with minimal error to maintain the equilibrium state, even a small error in the predictive mechanism leads to a loss for both service providers and consumers. To address these problems we proposed an energy prediction model based on Long Short Term Memory (LSTM). It has emerged as a promising Artificial Neural Network (ANN) technique for predicting time series issues due to the properties of selective retrieval patterns for a long time. Further, the LSTM model is optimized by using Optimizer Ensembles to improve the efficiency of the proposed model. The simulation results show that the proposed LSTM achieves better predictive results (less error, high efficiency) compared to existing methods such as Moving Average (MA), Linear Regression (LR) and k-Nearest Neighbors (k-NN) techniques.","PeriodicalId":130581,"journal":{"name":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123226121","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：