Pub Date : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315826
Umra Khan, S. Masood
Human Activity Recognition (HAR) is the problem of classifying an individual's activity into well-defined moments, utilizing responsive sensors that are influenced by human movement. Sensor-enabled smartphones make Human Activity Recognition progressively significant and well known. The physical sensors, gyroscope and accelerometer combinedly allow the devices to provide motion measuring capabilities in a more accurate manner. The present research work adopts a machine learning based approach for recognizing activity on the basis of data collected through the smartphone sensors (accelerometer and gyroscope). Various state-of-the-art machine learning based techniques have been employed and compared on the basis of the performance metrics, accuracy, recall, precision, and the F1-score. Of all the selected different machine learning classifiers, the best result is given by the Support Vector Machine (SVM) with ‘RBF’ kernel, which achieved an accuracy of 96.61 % in classifying the activities into the six different classes.
{"title":"A Machine Learning Approach to Human Activity Recognition","authors":"Umra Khan, S. Masood","doi":"10.1109/PDGC50313.2020.9315826","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315826","url":null,"abstract":"Human Activity Recognition (HAR) is the problem of classifying an individual's activity into well-defined moments, utilizing responsive sensors that are influenced by human movement. Sensor-enabled smartphones make Human Activity Recognition progressively significant and well known. The physical sensors, gyroscope and accelerometer combinedly allow the devices to provide motion measuring capabilities in a more accurate manner. The present research work adopts a machine learning based approach for recognizing activity on the basis of data collected through the smartphone sensors (accelerometer and gyroscope). Various state-of-the-art machine learning based techniques have been employed and compared on the basis of the performance metrics, accuracy, recall, precision, and the F1-score. Of all the selected different machine learning classifiers, the best result is given by the Support Vector Machine (SVM) with ‘RBF’ kernel, which achieved an accuracy of 96.61 % in classifying the activities into the six different classes.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121915847","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315822
A. Khanna, Sanmeet Kaur
In context to advancements in technologies, there exist a variety of sensors that are incorporated within the fields for obtaining vital as well as auxiliary information. Among various areas of implementation for Wireless Sensor Networks (WSN), agriculture is one such domain that has experienced revolutionary advancements over the past few years. Favorable outcome for agricultural practices completely depends on correct identification and selection of sensor. In order to administer the agricultural issues in today's date, deployment of sensors has become a necessity within the domain. The basic vision of this research article is to shed light on various agricultural sensors that are available in today's date followed by proposing a framework that suggests the precise amount of fertilizer requirement by the field after accessing various associated parameters. The study proposes Requirement Based Decision Support System (RbDSS) after evaluating various parameters, i.e., Soil moisture (Sm), Soil temperature (St), Soil humidity (Sh), Volumetric Water Content (VWC), and Electrical conductivity (EC). The results of the experimentation depicts decrease in the consumption of fertilizers by 24.68 %.
{"title":"Wireless Sensor and Actuator Network(s) and its significant impact on Agricultural domain","authors":"A. Khanna, Sanmeet Kaur","doi":"10.1109/PDGC50313.2020.9315822","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315822","url":null,"abstract":"In context to advancements in technologies, there exist a variety of sensors that are incorporated within the fields for obtaining vital as well as auxiliary information. Among various areas of implementation for Wireless Sensor Networks (WSN), agriculture is one such domain that has experienced revolutionary advancements over the past few years. Favorable outcome for agricultural practices completely depends on correct identification and selection of sensor. In order to administer the agricultural issues in today's date, deployment of sensors has become a necessity within the domain. The basic vision of this research article is to shed light on various agricultural sensors that are available in today's date followed by proposing a framework that suggests the precise amount of fertilizer requirement by the field after accessing various associated parameters. The study proposes Requirement Based Decision Support System (RbDSS) after evaluating various parameters, i.e., Soil moisture (Sm), Soil temperature (St), Soil humidity (Sh), Volumetric Water Content (VWC), and Electrical conductivity (EC). The results of the experimentation depicts decrease in the consumption of fertilizers by 24.68 %.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"24 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120910756","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315762
Faisal Alam, Khan Saad Bin Hasan, Arpit Varshney
A large number of robots are used in warehouses to automate mundane tasks, reduce operating costs, make warehouses safer and more efficient. However, there is a tradeoff between cost and accuracy of the robot. A costly robot will be more accurate and precise in its working, But it cannot be used at a large scale in MSMEs in developing countries. Using cheap components would result in a lower cost but there will be a dip in accuracy. Having a low cost, fairly accurate robot would help in developing countries in MSMEs. We are building a low cost, autonomous robot that can assist us in transferring goods from one place to another within a storage facility which can also help us account for products. The robot must also be programmable to do multiple tasks if needed. In this work, We give a review of different robots currently being used in warehouses and explain the working of our robot. We also assess the cost and accuracy of our robot and show how it might be suitable for warehouses in developing countries.
{"title":"Low-Cost Autonomous Vehicle for Inventory Movement in Warehouses","authors":"Faisal Alam, Khan Saad Bin Hasan, Arpit Varshney","doi":"10.1109/PDGC50313.2020.9315762","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315762","url":null,"abstract":"A large number of robots are used in warehouses to automate mundane tasks, reduce operating costs, make warehouses safer and more efficient. However, there is a tradeoff between cost and accuracy of the robot. A costly robot will be more accurate and precise in its working, But it cannot be used at a large scale in MSMEs in developing countries. Using cheap components would result in a lower cost but there will be a dip in accuracy. Having a low cost, fairly accurate robot would help in developing countries in MSMEs. We are building a low cost, autonomous robot that can assist us in transferring goods from one place to another within a storage facility which can also help us account for products. The robot must also be programmable to do multiple tasks if needed. In this work, We give a review of different robots currently being used in warehouses and explain the working of our robot. We also assess the cost and accuracy of our robot and show how it might be suitable for warehouses in developing countries.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129270965","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315831
Sarita Jiyal, R. Saini
In all developing countries such as India the main problem of premature death is air pollution which also effect the economy of country. When urbanization started then various problem occurs such as environmental pollution, traffic system etc. there is so much loss of resources in crowded cities due to urbanization. The concept of smart sustainable city can be used to balance the resources. If we do loss of resources excessively than we will definitely create problems to our future generation and excessive use of resources causes air pollution. Than it is necessary to predict air pollution timely by which it can be monitored. Using Internet of Things monitoring of air pollution is necessary to save our environment from all harmful pollutants. Vehicles are the main cause of air pollution. Electric Vehicles and cycles can be used in place of other vehicles for controlling the air pollution. This research teaches that prediction of air pollution level is very important by which peoples can divert there route of travelling.
{"title":"Prediction and Monitoring of Air Pollution Using Internet of Things (IoT)","authors":"Sarita Jiyal, R. Saini","doi":"10.1109/PDGC50313.2020.9315831","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315831","url":null,"abstract":"In all developing countries such as India the main problem of premature death is air pollution which also effect the economy of country. When urbanization started then various problem occurs such as environmental pollution, traffic system etc. there is so much loss of resources in crowded cities due to urbanization. The concept of smart sustainable city can be used to balance the resources. If we do loss of resources excessively than we will definitely create problems to our future generation and excessive use of resources causes air pollution. Than it is necessary to predict air pollution timely by which it can be monitored. Using Internet of Things monitoring of air pollution is necessary to save our environment from all harmful pollutants. Vehicles are the main cause of air pollution. Electric Vehicles and cycles can be used in place of other vehicles for controlling the air pollution. This research teaches that prediction of air pollution level is very important by which peoples can divert there route of travelling.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129125183","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315823
Rani Astya, N. Rakesh
Underwater Wireless Sensor network (UWSN) is a newly emerging area of wireless sensor network application which is used for naval, aquatic network, oiling network, surveillance, researchand distinct applicationinunderwater environment. Routing is one of the major concern of UWSN apart from mobility, bandwidth, robustness, high latency, node failure and various other. There are different research aspects which are categorized in variety of communication approaches in underwater environment which is quite different from the traditional approaches of network communication. In this paper we have broadly classifiedmost of the existing routing protocols in accordance to the usability. The classification is defined based on data forwarding and operations of routing protocols. This paper has distinguished the routing mechanisms to be adopted in accordance to the application requirement of Underwater Wireless Sensors for dynamic and static applicability.
{"title":"Classification of Routing Protocols for Under Water Sensor Network","authors":"Rani Astya, N. Rakesh","doi":"10.1109/PDGC50313.2020.9315823","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315823","url":null,"abstract":"Underwater Wireless Sensor network (UWSN) is a newly emerging area of wireless sensor network application which is used for naval, aquatic network, oiling network, surveillance, researchand distinct applicationinunderwater environment. Routing is one of the major concern of UWSN apart from mobility, bandwidth, robustness, high latency, node failure and various other. There are different research aspects which are categorized in variety of communication approaches in underwater environment which is quite different from the traditional approaches of network communication. In this paper we have broadly classifiedmost of the existing routing protocols in accordance to the usability. The classification is defined based on data forwarding and operations of routing protocols. This paper has distinguished the routing mechanisms to be adopted in accordance to the application requirement of Underwater Wireless Sensors for dynamic and static applicability.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132139456","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315828
V. Shelake, N. Shekokar
Now-a-days, huge amount of personal and sensitive data of individuals resides across different data sources that refer to the same entity. Thus, it is crucial and necessary to detect and link duplicate records from multiple data sets in secure manner referred to as privacy preserving record linkage (PPRL). The PPRL enables data integration, analysis and research activities for business benefits. Since real world data exhibits its dirty and erroneous representations, achieving linkage accuracy is a prominent factor for PPRL techniques. Hence, approximate matching techniques play a crucial role for achieving linkage accuracy in PPRL applications. In this paper, different suitable attribute combinations for PPRL are identified. This paper introduces a similarity matching strategy for privacy preserving record linkage named as SMSPPRL for achieving increased linkage accuracy. Our SMSPPRL technique performs better than existing PPRL techniques Basic Bloom, hardened balanced Bloom filter in terms of linkage accuracy.
{"title":"SMSPPRL: A Similarity Matching Strategy for Privacy Preserving Record Linkage","authors":"V. Shelake, N. Shekokar","doi":"10.1109/PDGC50313.2020.9315828","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315828","url":null,"abstract":"Now-a-days, huge amount of personal and sensitive data of individuals resides across different data sources that refer to the same entity. Thus, it is crucial and necessary to detect and link duplicate records from multiple data sets in secure manner referred to as privacy preserving record linkage (PPRL). The PPRL enables data integration, analysis and research activities for business benefits. Since real world data exhibits its dirty and erroneous representations, achieving linkage accuracy is a prominent factor for PPRL techniques. Hence, approximate matching techniques play a crucial role for achieving linkage accuracy in PPRL applications. In this paper, different suitable attribute combinations for PPRL are identified. This paper introduces a similarity matching strategy for privacy preserving record linkage named as SMSPPRL for achieving increased linkage accuracy. Our SMSPPRL technique performs better than existing PPRL techniques Basic Bloom, hardened balanced Bloom filter in terms of linkage accuracy.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128035380","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315799
Amit Nayyer, A. Sharma, L. Awasthi
Software Defined Network is a significant and emerging paradigm that separates its control plane from the data plane. The separation of planes makes it centralized, different from the traditional network and provide various advantages to the network. The centralized paradigm offers a key benefit of global network view at the controller, which can be efficiently utilized for routing in the network. Along with benefits, there are several issues specific to routing that researchers need to address before developing a new routing protocol. The traditional routing protocols cannot be directly implemented in this modern architecture; if implemented, they cannot take full advantages of the paradigm. This article provided various issues of concern specifically for routing in Software Defined Networks. The target is to introduce newbies the issues and make them aware of multiple research efforts made in this direction. The discussion provided in the article can be considered before developing routing solutions for such networks.
{"title":"Issues with Routing in Software Defined Networks","authors":"Amit Nayyer, A. Sharma, L. Awasthi","doi":"10.1109/PDGC50313.2020.9315799","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315799","url":null,"abstract":"Software Defined Network is a significant and emerging paradigm that separates its control plane from the data plane. The separation of planes makes it centralized, different from the traditional network and provide various advantages to the network. The centralized paradigm offers a key benefit of global network view at the controller, which can be efficiently utilized for routing in the network. Along with benefits, there are several issues specific to routing that researchers need to address before developing a new routing protocol. The traditional routing protocols cannot be directly implemented in this modern architecture; if implemented, they cannot take full advantages of the paradigm. This article provided various issues of concern specifically for routing in Software Defined Networks. The target is to introduce newbies the issues and make them aware of multiple research efforts made in this direction. The discussion provided in the article can be considered before developing routing solutions for such networks.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129751431","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315795
A. Bansal, Aarushi Bhardwaj, Aman Sharma
Corona virus also known as COVID 19 is a critical ongoing pandemic that is on a rise across the globe. Italy and China have been considered as one of the main epicentres from where the pandemic came into full effect. Here, the highest death rates across the world are registered as a consequence of COVID-19. One of the leading countries, the USA has also been in the registered countries with an increasing number of cases of COVID 19. In this paper ARIMA model that is an auto regressive integrated moving average model is used to help forecast the epidemic trend over a period of time (i.e. April 2020). The dataset used is from the Italian epidemiological data at National and Regional level. It refers to the number of daily confirmed cases as well as the fatalities registered by Italian Ministry of Health. The model has various advantages like it is easy to use, to manage and a suitable model for forecasting purposes. Moreover, it gives a thorough clarity of basic trends, by predicting the hypothetical epidemic's inflection point and final size.
{"title":"Forecasting the Trend of Covid-19 Epidemic","authors":"A. Bansal, Aarushi Bhardwaj, Aman Sharma","doi":"10.1109/PDGC50313.2020.9315795","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315795","url":null,"abstract":"Corona virus also known as COVID 19 is a critical ongoing pandemic that is on a rise across the globe. Italy and China have been considered as one of the main epicentres from where the pandemic came into full effect. Here, the highest death rates across the world are registered as a consequence of COVID-19. One of the leading countries, the USA has also been in the registered countries with an increasing number of cases of COVID 19. In this paper ARIMA model that is an auto regressive integrated moving average model is used to help forecast the epidemic trend over a period of time (i.e. April 2020). The dataset used is from the Italian epidemiological data at National and Regional level. It refers to the number of daily confirmed cases as well as the fatalities registered by Italian Ministry of Health. The model has various advantages like it is easy to use, to manage and a suitable model for forecasting purposes. Moreover, it gives a thorough clarity of basic trends, by predicting the hypothetical epidemic's inflection point and final size.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"BME-17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132836835","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315771
Anushikha Gupta, Mala Kalra
The Security is a vital aspect of cloud service as it comprises of data that belong to multiple users. Cloud service providers are responsible for maintaining data integrity, confidentiality and availability. They must ensure that their infrastructure and data are protected from intruders. In this research work Intrusion Detection System is designed to detect malicious server by using Cuckoo Search (CS) along with Artificial Intelligence. CS is used for feature optimization with the help of fitness function, the server's nature is categorized into two types: normal and attackers. On the basis of extracted features, ANN classify the attackers which affect the networks in cloud environment. The main aim is to distinguish attacker servers that are affected by DoS/DDoS, Black and Gray hole attacks from the genuine servers. Thus, instead of passing data to attacker server, the server passes the data to the genuine servers and hence, the system is protected. To validate the performance of the system, QoS parameters such as PDR (Packet delivery rate), energy consumption rate and total delay before and after prevention algorithm are measured. When compared with existing work, the PDR and the delay have been enhanced by 3.0 %and 21.5 %.
{"title":"Intrusion Detection and Prevention system using Cuckoo search algorithm with ANN in Cloud Computing","authors":"Anushikha Gupta, Mala Kalra","doi":"10.1109/PDGC50313.2020.9315771","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315771","url":null,"abstract":"The Security is a vital aspect of cloud service as it comprises of data that belong to multiple users. Cloud service providers are responsible for maintaining data integrity, confidentiality and availability. They must ensure that their infrastructure and data are protected from intruders. In this research work Intrusion Detection System is designed to detect malicious server by using Cuckoo Search (CS) along with Artificial Intelligence. CS is used for feature optimization with the help of fitness function, the server's nature is categorized into two types: normal and attackers. On the basis of extracted features, ANN classify the attackers which affect the networks in cloud environment. The main aim is to distinguish attacker servers that are affected by DoS/DDoS, Black and Gray hole attacks from the genuine servers. Thus, instead of passing data to attacker server, the server passes the data to the genuine servers and hence, the system is protected. To validate the performance of the system, QoS parameters such as PDR (Packet delivery rate), energy consumption rate and total delay before and after prevention algorithm are measured. When compared with existing work, the PDR and the delay have been enhanced by 3.0 %and 21.5 %.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121865498","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}
According to a 2016 report by the Indian Ministry of Human Resource Development, there were 39,658 student hostels across India. In recent years, owing to the growing number of students residing in such hostels, there has been an interest in helping students know more about these hostels by providing them with information and reviews from residing students. We aim to categorize these based on various aspects and give greater insights about them using applications of aspect based sentiment analysis. We have used a neural network based approach to pre-process the texts and propose two models, one for aspect extraction and classification and the other for sentiment polarity analysis. Further, we have presented an extensive evaluation of our models and have achieved an accuracy of more than 75% on both the models.
{"title":"Aspect Based Sentiment Analysis of Student Housing Reviews","authors":"Aniket Mukherjee, Shiv Jethi, Akshat Jain, Ankit Mundra","doi":"10.1109/PDGC50313.2020.9315324","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315324","url":null,"abstract":"According to a 2016 report by the Indian Ministry of Human Resource Development, there were 39,658 student hostels across India. In recent years, owing to the growing number of students residing in such hostels, there has been an interest in helping students know more about these hostels by providing them with information and reviews from residing students. We aim to categorize these based on various aspects and give greater insights about them using applications of aspect based sentiment analysis. We have used a neural network based approach to pre-process the texts and propose two models, one for aspect extraction and classification and the other for sentiment polarity analysis. Further, we have presented an extensive evaluation of our models and have achieved an accuracy of more than 75% on both the models.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"242 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115657525","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：