Internet of things (IOT) does affect every aspect of human life severely, as it is envisioned to bridge physical world and virtual world. Automation and convenience are vital value addition to human life, by IOT phenomena. The growth of IoT technologies is primarily contributed by four factors. 1) Declining cost of sensors, 2) Increasing broadband penetration, 3) Cheap data storage and 4) Advanced software analytics, that can transform raw sensor data into vital knowledge. Smart Home personal area networks(PANs), Industrial grids, Health care body area networks(BANs) and even Military vehicular networks will benefit from IOT concepts. However all the above mentioned areas have different IOT stack requirements. As different IOT networks do encounter issues like spectrum crunch, increased interference, Green energy, heterogeneity and coverage issues at varying degree of intensity. In this paper a broad classification of IOT networks is illustrated, form their stack requirements perspective. This paper also covers emerging Industry standardization efforts, to develop frameworks, API and platforms to realize IOT vision.
{"title":"A Generic stack frame work for Internet Of Things","authors":"Rakesh Kumar Ambhati, ChaudhariShilpa Shashikant, Valluri Sarimela","doi":"10.1109/IC3IOT.2018.8668156","DOIUrl":"https://doi.org/10.1109/IC3IOT.2018.8668156","url":null,"abstract":"Internet of things (IOT) does affect every aspect of human life severely, as it is envisioned to bridge physical world and virtual world. Automation and convenience are vital value addition to human life, by IOT phenomena. The growth of IoT technologies is primarily contributed by four factors. 1) Declining cost of sensors, 2) Increasing broadband penetration, 3) Cheap data storage and 4) Advanced software analytics, that can transform raw sensor data into vital knowledge. Smart Home personal area networks(PANs), Industrial grids, Health care body area networks(BANs) and even Military vehicular networks will benefit from IOT concepts. However all the above mentioned areas have different IOT stack requirements. As different IOT networks do encounter issues like spectrum crunch, increased interference, Green energy, heterogeneity and coverage issues at varying degree of intensity. In this paper a broad classification of IOT networks is illustrated, form their stack requirements perspective. This paper also covers emerging Industry standardization efforts, to develop frameworks, API and platforms to realize IOT vision.","PeriodicalId":155587,"journal":{"name":"2018 International Conference on Communication, Computing and Internet of Things (IC3IoT)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129180964","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 : 2018-02-01DOI: 10.1109/IC3IOT.2018.8668175
Suraj Sawai, Manjula Rathore
This paper develops observer based a sliding mode control for system with mismatched uncertainties. Most system are affected because of disturbance, modelling uncertainty and their nature being nonlinear. In respect to disturbance, this disturbance can be categorise as matched and mismatched uncertainty. In recent time a lot of focused is given to system which are affected by mismatched uncertainty i.e. disturbance does not enter system through input channel, such system are difficult to control. To improve the robustness and enhance the disturbance attenuation of system which are affected by disturbance which does not satisfy matching condition. One of way to deal with the disturbance is to estimate it then it became simpler to attenuate it and make system performance as per specification. Design procedure consist of two stage, A nonlinear controller is developed which satisfy the performance specification an after that nonlinear disturbance observer is design to estimate the disturbance. The second stage consist of integrating the observer in the design controller with estimation obtain through disturbance observer. It also provide the basics step in designing traditional SMC and Integral SMC and discuss the effect of the disturbance on two method. The performance of proposed approach is validated through simulation. Comparison with the integral sliding mode controller, Nonlinear observer show better response attenuate the disturbance.
{"title":"Observer Based Sliding Mode Control for System with Mismatched Uncertinity","authors":"Suraj Sawai, Manjula Rathore","doi":"10.1109/IC3IOT.2018.8668175","DOIUrl":"https://doi.org/10.1109/IC3IOT.2018.8668175","url":null,"abstract":"This paper develops observer based a sliding mode control for system with mismatched uncertainties. Most system are affected because of disturbance, modelling uncertainty and their nature being nonlinear. In respect to disturbance, this disturbance can be categorise as matched and mismatched uncertainty. In recent time a lot of focused is given to system which are affected by mismatched uncertainty i.e. disturbance does not enter system through input channel, such system are difficult to control. To improve the robustness and enhance the disturbance attenuation of system which are affected by disturbance which does not satisfy matching condition. One of way to deal with the disturbance is to estimate it then it became simpler to attenuate it and make system performance as per specification. Design procedure consist of two stage, A nonlinear controller is developed which satisfy the performance specification an after that nonlinear disturbance observer is design to estimate the disturbance. The second stage consist of integrating the observer in the design controller with estimation obtain through disturbance observer. It also provide the basics step in designing traditional SMC and Integral SMC and discuss the effect of the disturbance on two method. The performance of proposed approach is validated through simulation. Comparison with the integral sliding mode controller, Nonlinear observer show better response attenuate the disturbance.","PeriodicalId":155587,"journal":{"name":"2018 International Conference on Communication, Computing and Internet of Things (IC3IoT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131017293","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}
In this work, we are focusing on design and construction of Service-Oriented Architecture (SOA) enabled Internet of Things (IoT) based smart assistive system prototype, which can be dynamically configured and interfaced with array of sensors to prevent injuries of Autism Spectrum Disorder (ASD) individuals. This increase the quality of life of people with ASD. The proposed model suggested implementing a wearable array of sensor components to gather information about the physiological status of a person and environmental condition of his surroundings. Afterward the data forwarded to a cloud service for analysis purpose. The system compromises of various tier of interaction and storage, to form a ubiquitous platform. One of the layer in the tier are linked to wearable computing platform. Another layer of the tier is dedicated to data storage captured from raw sensor data. The interaction between the tiers nodes is performed over the Internet through HyperText Transfer Protocol (HTTP) REST API and Message Queuing Telemetry Transport (MQTT) protocol. The system work in three domain: services at home, services at community i.e. neighborhood and services away from home. We can access in real time and monitor of ASD person though mobile app and web. So our approach will be helpful to manage ASD affected individuals.
{"title":"A Service-Oriented IoT System to Support Individuals with ASD","authors":"Yigremachew Eshetu, Prachet Bhuyan, Ashutosh Behura","doi":"10.1109/IC3IOT.2018.8668138","DOIUrl":"https://doi.org/10.1109/IC3IOT.2018.8668138","url":null,"abstract":"In this work, we are focusing on design and construction of Service-Oriented Architecture (SOA) enabled Internet of Things (IoT) based smart assistive system prototype, which can be dynamically configured and interfaced with array of sensors to prevent injuries of Autism Spectrum Disorder (ASD) individuals. This increase the quality of life of people with ASD. The proposed model suggested implementing a wearable array of sensor components to gather information about the physiological status of a person and environmental condition of his surroundings. Afterward the data forwarded to a cloud service for analysis purpose. The system compromises of various tier of interaction and storage, to form a ubiquitous platform. One of the layer in the tier are linked to wearable computing platform. Another layer of the tier is dedicated to data storage captured from raw sensor data. The interaction between the tiers nodes is performed over the Internet through HyperText Transfer Protocol (HTTP) REST API and Message Queuing Telemetry Transport (MQTT) protocol. The system work in three domain: services at home, services at community i.e. neighborhood and services away from home. We can access in real time and monitor of ASD person though mobile app and web. So our approach will be helpful to manage ASD affected individuals.","PeriodicalId":155587,"journal":{"name":"2018 International Conference on Communication, Computing and Internet of Things (IC3IoT)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134230251","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 : 2018-02-01DOI: 10.1109/IC3IOT.2018.8668198
Sheikh Amanur Rahman, M. M. Sufyan Beg
Today, a greater amount of products/services reviews available on the Internet, e.g., blogs, review forum, discussion groups, etc. However, it is almost impossible for a user to read all of the different and possibly even contradictory opinions and make an informed decision. Generally, reviewers write the reviews related to the aspects of the product in the form of text and give the rating to the product. But some of the reviewers are biased while giving the rating to the product and while writing the review, they used to write genuine re-views, at least up to some extent, related to the aspects of the products. Moreover, there are also spammers who are paid to give the fake rating to the product. So, to overcome the challenges of direct rating of the product, instead, the rating of the product can be projected with the help of the aspects reviews of the product. Till now, there is no significant work on product rating based on the aspects reviews.Our proposed system works for the above-mentioned problem. The proposed system works in three phase, firstly; it identifies aspects and predicts the aspects rating, secondly; aspects along with their rating are classified/clustered and finally; based on aspect rating, product rating is calculated. Our work diminishes the effect of spam review or biased review. To the best of author’s knowledge, it is virtually first of its kind, related to product/aspect rating based on their aspect reviews.
{"title":"ProRat: Product Rating Prediction Model based on Online Product Reviews","authors":"Sheikh Amanur Rahman, M. M. Sufyan Beg","doi":"10.1109/IC3IOT.2018.8668198","DOIUrl":"https://doi.org/10.1109/IC3IOT.2018.8668198","url":null,"abstract":"Today, a greater amount of products/services reviews available on the Internet, e.g., blogs, review forum, discussion groups, etc. However, it is almost impossible for a user to read all of the different and possibly even contradictory opinions and make an informed decision. Generally, reviewers write the reviews related to the aspects of the product in the form of text and give the rating to the product. But some of the reviewers are biased while giving the rating to the product and while writing the review, they used to write genuine re-views, at least up to some extent, related to the aspects of the products. Moreover, there are also spammers who are paid to give the fake rating to the product. So, to overcome the challenges of direct rating of the product, instead, the rating of the product can be projected with the help of the aspects reviews of the product. Till now, there is no significant work on product rating based on the aspects reviews.Our proposed system works for the above-mentioned problem. The proposed system works in three phase, firstly; it identifies aspects and predicts the aspects rating, secondly; aspects along with their rating are classified/clustered and finally; based on aspect rating, product rating is calculated. Our work diminishes the effect of spam review or biased review. To the best of author’s knowledge, it is virtually first of its kind, related to product/aspect rating based on their aspect reviews.","PeriodicalId":155587,"journal":{"name":"2018 International Conference on Communication, Computing and Internet of Things (IC3IoT)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131807420","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 : 2018-02-01DOI: 10.1109/IC3IOT.2018.8668153
J. Dhamija, T. Choudhury, Praveen Kumar, Arushi Tetarbe
Nowadays we see that everyday a lot of cases come up where patients are detected and diagnosed with swine flu fever. And mostly it is too late to do something for them. There are blood tests performed on patients to perform early prognostic testing so that the early signs help us fight the symptomatic fever that is swine flu.Eight genomic biomarkers for early detection of swine flu known to us have been used in this paper. Existing work uses PSO approach for test cases of dengue and malaria which achieved the accuracy of 90.91% but no work has been performed for swine flu. In order to achieve high accuracy, we are using optimization algorithms like SVM Decision Tree and ANN so as to determine which is the best one and which gives the highest accuracy for detection of swine flu by using gene expression database and further validated using k-fold validation techniques
{"title":"Classification of swine flu patients using gene expression : “For a safer future”","authors":"J. Dhamija, T. Choudhury, Praveen Kumar, Arushi Tetarbe","doi":"10.1109/IC3IOT.2018.8668153","DOIUrl":"https://doi.org/10.1109/IC3IOT.2018.8668153","url":null,"abstract":"Nowadays we see that everyday a lot of cases come up where patients are detected and diagnosed with swine flu fever. And mostly it is too late to do something for them. There are blood tests performed on patients to perform early prognostic testing so that the early signs help us fight the symptomatic fever that is swine flu.Eight genomic biomarkers for early detection of swine flu known to us have been used in this paper. Existing work uses PSO approach for test cases of dengue and malaria which achieved the accuracy of 90.91% but no work has been performed for swine flu. In order to achieve high accuracy, we are using optimization algorithms like SVM Decision Tree and ANN so as to determine which is the best one and which gives the highest accuracy for detection of swine flu by using gene expression database and further validated using k-fold validation techniques","PeriodicalId":155587,"journal":{"name":"2018 International Conference on Communication, Computing and Internet of Things (IC3IoT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123909897","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 : 2018-02-01DOI: 10.1109/IC3IOT.2018.8668159
S. Narang, Tarun Nalwa, T. Choudhury, Nirbhay Kashyap
The Internet of Things (IoT) is an interconnection of day to day objects in a network that are provided with colossal intelligence level. It has increased the usage of Internet gigantically by integrating every object for interaction through embedded systems that ends up in an extremely dispersed network of devices communicating with humans as well as electronic devices that support web. IoT is exploding in size and complexity, connecting a huge universe of consumer, industrial, and digital services to the network. IoT is in need of an advanced prototype for security, which considers the security issues from a holistic perspective comprising the advanced users and their intercommunication with this technology. In this paper, the advantages and disadvantages of IoT have been analyzed and also how current approaches are ensuring fundamental and basic security requisites and securing intercommunication of IoT, along with the rolling changes and scope for work in this field in the coming future.
{"title":"An efficient method for security measurement in internet of things","authors":"S. Narang, Tarun Nalwa, T. Choudhury, Nirbhay Kashyap","doi":"10.1109/IC3IOT.2018.8668159","DOIUrl":"https://doi.org/10.1109/IC3IOT.2018.8668159","url":null,"abstract":"The Internet of Things (IoT) is an interconnection of day to day objects in a network that are provided with colossal intelligence level. It has increased the usage of Internet gigantically by integrating every object for interaction through embedded systems that ends up in an extremely dispersed network of devices communicating with humans as well as electronic devices that support web. IoT is exploding in size and complexity, connecting a huge universe of consumer, industrial, and digital services to the network. IoT is in need of an advanced prototype for security, which considers the security issues from a holistic perspective comprising the advanced users and their intercommunication with this technology. In this paper, the advantages and disadvantages of IoT have been analyzed and also how current approaches are ensuring fundamental and basic security requisites and securing intercommunication of IoT, along with the rolling changes and scope for work in this field in the coming future.","PeriodicalId":155587,"journal":{"name":"2018 International Conference on Communication, Computing and Internet of Things (IC3IoT)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124030925","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 : 2018-02-01DOI: 10.1109/IC3IOT.2018.8668204
P. Raju, D. S. Rani, G. Challaram
This paper describes the image fusion methods used in medical field. In this project fusion of CT and MRI images are used for clinical applications. CT image of person gives information about hard tissues where as MRI gives soft tissues details. The fusion of both images gives detail information about the patient. This paper provides a new hybrid fusion method that improves the quality of image. The fusion techniques used in this project are averaging, maximum, minimum, DWT, PCA, DSWT and hybrid fusion method which is the combination of any two methods. The multi-modal fused image performance can be compared by using image Quality metrics like PSNR, MSE, RMSE, Entropy and other parameters. By observing the results, it can be proved that proposed method is more efficient for fusion purpose.
{"title":"Comparison of Medical Image Fusion Methods using Image Quality Metrics","authors":"P. Raju, D. S. Rani, G. Challaram","doi":"10.1109/IC3IOT.2018.8668204","DOIUrl":"https://doi.org/10.1109/IC3IOT.2018.8668204","url":null,"abstract":"This paper describes the image fusion methods used in medical field. In this project fusion of CT and MRI images are used for clinical applications. CT image of person gives information about hard tissues where as MRI gives soft tissues details. The fusion of both images gives detail information about the patient. This paper provides a new hybrid fusion method that improves the quality of image. The fusion techniques used in this project are averaging, maximum, minimum, DWT, PCA, DSWT and hybrid fusion method which is the combination of any two methods. The multi-modal fused image performance can be compared by using image Quality metrics like PSNR, MSE, RMSE, Entropy and other parameters. By observing the results, it can be proved that proposed method is more efficient for fusion purpose.","PeriodicalId":155587,"journal":{"name":"2018 International Conference on Communication, Computing and Internet of Things (IC3IoT)","volume":"168 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114260058","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 : 2018-02-01DOI: 10.1109/IC3IOT.2018.8668205
B. Sreedevi, Priya. M Pachaiammal
Stem cells are biological cells found in all multicellular organisms, that can divide (through mitosis) and differentiate into diverse specialized cell types and can self-renew to produce more stem cells. Optimization algorithms have been proved to be good solutions for many practical applications. They were mainly inspired by natural evolutions. However, they are still faced to some problems such as trapping in local minimums, having low speed of convergence, and also having high order of complexity for implementation. Mesenchymal Stems or stromal Cells (MSCs) are part of maintaining as well as repairing tissues. The functions are mainly examined in bone marrow-derived MSC. In the current study, segmentations are performed through usage of Graph-based image segmentations. Feature extraction is performed through Wavelet while Feature Selection is performed through Stem Cell Optimization techniques. Naïve Bayes as well as Support Vector Machines are utilized for classifiers. Results show that the Stem Cell Optimization has better classification accuracy than Information Gain (IG) and Genetic Algorithm (GA).
{"title":"Analysis of Performance Metrics with Mesenchymal Stem Cell Classification and Optimization Algorithms","authors":"B. Sreedevi, Priya. M Pachaiammal","doi":"10.1109/IC3IOT.2018.8668205","DOIUrl":"https://doi.org/10.1109/IC3IOT.2018.8668205","url":null,"abstract":"Stem cells are biological cells found in all multicellular organisms, that can divide (through mitosis) and differentiate into diverse specialized cell types and can self-renew to produce more stem cells. Optimization algorithms have been proved to be good solutions for many practical applications. They were mainly inspired by natural evolutions. However, they are still faced to some problems such as trapping in local minimums, having low speed of convergence, and also having high order of complexity for implementation. Mesenchymal Stems or stromal Cells (MSCs) are part of maintaining as well as repairing tissues. The functions are mainly examined in bone marrow-derived MSC. In the current study, segmentations are performed through usage of Graph-based image segmentations. Feature extraction is performed through Wavelet while Feature Selection is performed through Stem Cell Optimization techniques. Naïve Bayes as well as Support Vector Machines are utilized for classifiers. Results show that the Stem Cell Optimization has better classification accuracy than Information Gain (IG) and Genetic Algorithm (GA).","PeriodicalId":155587,"journal":{"name":"2018 International Conference on Communication, Computing and Internet of Things (IC3IoT)","volume":"276 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115600488","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 : 2018-02-01DOI: 10.1109/IC3IOT.2018.8668152
S. Aruna, R. Venkataswamy
Renewable energy is one of the growing trend in developing countries. Rapid development of renewable energy leads to the economic benefits and reduce environmental pollution. According to current scenario 20 to 40 percent of the power generated is consumed by streetlights. The problems faced by the current street lighting systems are when there is availability of light there is no proper utilization. Sun intensity shift is not constant all the time, it varies as the climate changes. Real time monitoring and control using intelligent algorithm avoids energy wastage during day time. ZigBee as a communication protocol current and voltage values are sent and received. Base Controller (Single Board Computer) acts as an interphase between the communication protocol and the cloud account. Remote client application is developed to control and monitor streetlight.
{"title":"Academic Workbench for Streetlight Powered by Solar PV System Using Internet of Everything (IoE)","authors":"S. Aruna, R. Venkataswamy","doi":"10.1109/IC3IOT.2018.8668152","DOIUrl":"https://doi.org/10.1109/IC3IOT.2018.8668152","url":null,"abstract":"Renewable energy is one of the growing trend in developing countries. Rapid development of renewable energy leads to the economic benefits and reduce environmental pollution. According to current scenario 20 to 40 percent of the power generated is consumed by streetlights. The problems faced by the current street lighting systems are when there is availability of light there is no proper utilization. Sun intensity shift is not constant all the time, it varies as the climate changes. Real time monitoring and control using intelligent algorithm avoids energy wastage during day time. ZigBee as a communication protocol current and voltage values are sent and received. Base Controller (Single Board Computer) acts as an interphase between the communication protocol and the cloud account. Remote client application is developed to control and monitor streetlight.","PeriodicalId":155587,"journal":{"name":"2018 International Conference on Communication, Computing and Internet of Things (IC3IoT)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126131097","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 : 2018-02-01DOI: 10.1109/IC3IOT.2018.8668134
S. K. Mohapatra, Anamika Upadhyay
Getting semantic similarity in short texts plays an important role for many tasks in the field of information retrieval. This helps in getting search results, fetching answers to queries, building summary of documents etc. We present an approach for manually and automatically getting answers to the different problems and queries of the farmers for their day to day agricultural work. Using this approach, we can provide a query to the model, to find relevant questions asked for that query and their possible answers. We have first preprocessed the data and converted to a similarity matrix which we save in a database using mongoDb. By taking the saved data from database we trained the model to get the information of the query based on similarity between the sentences of the queries, and then the application will find the best possible answer according to the similarity. We will be using Term-frequency-inverse document frequency (TF-IDF) to find the similar queries. With TF-IDF, every word is given weight, the TF-IDF is measured by frequency the relevance is not taken into consideration for this model. This information can be used in trainings to boost call agent effectiveness and improve the customer experience. As an added bonus, more effective communication reduces handle time and operating costs.
{"title":"Using TF-IDF on Kisan Call Centre Dataset for Obtaining Query Answers","authors":"S. K. Mohapatra, Anamika Upadhyay","doi":"10.1109/IC3IOT.2018.8668134","DOIUrl":"https://doi.org/10.1109/IC3IOT.2018.8668134","url":null,"abstract":"Getting semantic similarity in short texts plays an important role for many tasks in the field of information retrieval. This helps in getting search results, fetching answers to queries, building summary of documents etc. We present an approach for manually and automatically getting answers to the different problems and queries of the farmers for their day to day agricultural work. Using this approach, we can provide a query to the model, to find relevant questions asked for that query and their possible answers. We have first preprocessed the data and converted to a similarity matrix which we save in a database using mongoDb. By taking the saved data from database we trained the model to get the information of the query based on similarity between the sentences of the queries, and then the application will find the best possible answer according to the similarity. We will be using Term-frequency-inverse document frequency (TF-IDF) to find the similar queries. With TF-IDF, every word is given weight, the TF-IDF is measured by frequency the relevance is not taken into consideration for this model. This information can be used in trainings to boost call agent effectiveness and improve the customer experience. As an added bonus, more effective communication reduces handle time and operating costs.","PeriodicalId":155587,"journal":{"name":"2018 International Conference on Communication, Computing and Internet of Things (IC3IoT)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127178846","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：