In recent times, there is great interest shown in the stock market activities, for reasons like unpredictability of circumstances due to the pandemic situation. Since stock market procedures are extremely dynamic in nature and it is very challenging to do any kind of prediction, employing Machine Learning algorithms to do so is but natural. We are interested particularly in exploring the situation in Indian Stock Market. In this paper, we describe the implementation of the Long Short-Term Memory (LSTM) network, Gated Recurrent Unit (GRU) networks for stock prediction. The prediction is performed for the closing prices of stocks of twenty-five Indian companies. The results indicate that a two-layer GRU outperforms all other networks as far as these twenty-five companies are concerned. We have predicted the stock market opening of next day using the closing of global market indices, concluding that there is a high correlation between the global and Indian market movement. Work on how the twitter financial sentiment effects the stock market has been performed by predicting the change in price over the week using twitter sentiment. The tweets were divided into three categories, positive, negative, and neutral. We have used support vector machine (SVM), Gradient boost and XGBoost, of which Gradient Boost provided the best results. The accuracies of the methods we have implemented for all the three tasks-predicting stock opening price, using historic data and global indices; range between a good 93% to 99%. In case of prediction using twitter sentiment, it ranges from 85% to 91 % when relevant financial tweets are available. The work has a natural extension to study robustness of our model for the pandemic year 2020-2021; which is currently under progress.
{"title":"Indian Stock Movement Prediction with Global Indices and Twitter Sentiment using Machine Learning","authors":"Shwetha Salimath, Triparna Chatterjee, Titty Mathai, Pooja Kamble, Megha M. Kolhekar","doi":"10.1109/CSI54720.2022.9924056","DOIUrl":"https://doi.org/10.1109/CSI54720.2022.9924056","url":null,"abstract":"In recent times, there is great interest shown in the stock market activities, for reasons like unpredictability of circumstances due to the pandemic situation. Since stock market procedures are extremely dynamic in nature and it is very challenging to do any kind of prediction, employing Machine Learning algorithms to do so is but natural. We are interested particularly in exploring the situation in Indian Stock Market. In this paper, we describe the implementation of the Long Short-Term Memory (LSTM) network, Gated Recurrent Unit (GRU) networks for stock prediction. The prediction is performed for the closing prices of stocks of twenty-five Indian companies. The results indicate that a two-layer GRU outperforms all other networks as far as these twenty-five companies are concerned. We have predicted the stock market opening of next day using the closing of global market indices, concluding that there is a high correlation between the global and Indian market movement. Work on how the twitter financial sentiment effects the stock market has been performed by predicting the change in price over the week using twitter sentiment. The tweets were divided into three categories, positive, negative, and neutral. We have used support vector machine (SVM), Gradient boost and XGBoost, of which Gradient Boost provided the best results. The accuracies of the methods we have implemented for all the three tasks-predicting stock opening price, using historic data and global indices; range between a good 93% to 99%. In case of prediction using twitter sentiment, it ranges from 85% to 91 % when relevant financial tweets are available. The work has a natural extension to study robustness of our model for the pandemic year 2020-2021; which is currently under progress.","PeriodicalId":221137,"journal":{"name":"2022 International Conference on Connected Systems & Intelligence (CSI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124538365","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 : 2022-08-31DOI: 10.1109/CSI54720.2022.9924058
M. Bhargavi, Bharani Prabhakar
Alzheimer's disease is a neurodegenerative disorder and one of the most prevalent forms of progressive Dementia. Alzheimer's disease does not have any cure as it leads to brain shrinkage and damage of the brain cells. Early detection can aid in assessing and administering suitable treatment that can slow down disease progression. Progressive monitoring of individuals diagnosed with Mild Cognitive Impairment (MCI) through neuroimaging has gained considerable interest recently for early detection. The most popular neuroimaging used being the Magnetic Resonance Imaging (MRI). The intention of monitoring individuals diagnosed with MCI is that, MCI diagnosed are more likely to get converted to Alzheimer's. Deep learning models have proven to be very effective and shown powerful performance in neuroimaging analytics. Deep learning techniques have been employed over brain MRI for assessing Alzheimer's disease progression and gained immense popularity in recent times due to its commendable performance. In this paper, we present a study on the applications of Deep learning techniques in early detection and progression of Alzheimer's disease. The study focuses on recent advances in the early detection of Alzheimer's using Deep learning models and MRI neuroimaging.
{"title":"Deep Learning Approaches for Early Detection of Alzheimer's Disease using MRI Neuroimaging","authors":"M. Bhargavi, Bharani Prabhakar","doi":"10.1109/CSI54720.2022.9924058","DOIUrl":"https://doi.org/10.1109/CSI54720.2022.9924058","url":null,"abstract":"Alzheimer's disease is a neurodegenerative disorder and one of the most prevalent forms of progressive Dementia. Alzheimer's disease does not have any cure as it leads to brain shrinkage and damage of the brain cells. Early detection can aid in assessing and administering suitable treatment that can slow down disease progression. Progressive monitoring of individuals diagnosed with Mild Cognitive Impairment (MCI) through neuroimaging has gained considerable interest recently for early detection. The most popular neuroimaging used being the Magnetic Resonance Imaging (MRI). The intention of monitoring individuals diagnosed with MCI is that, MCI diagnosed are more likely to get converted to Alzheimer's. Deep learning models have proven to be very effective and shown powerful performance in neuroimaging analytics. Deep learning techniques have been employed over brain MRI for assessing Alzheimer's disease progression and gained immense popularity in recent times due to its commendable performance. In this paper, we present a study on the applications of Deep learning techniques in early detection and progression of Alzheimer's disease. The study focuses on recent advances in the early detection of Alzheimer's using Deep learning models and MRI neuroimaging.","PeriodicalId":221137,"journal":{"name":"2022 International Conference on Connected Systems & Intelligence (CSI)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126223649","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 : 2022-08-31DOI: 10.1109/CSI54720.2022.9923991
Rajat Saxena, Ajay Patel
Generalized Multi Protocol Label Switching (GMPLS) or Multi-Protocol Lambda Switching is a new technology which produce amplification in Multi Protocol Label Switching (MPLS) to provide support network switching, space switching, and packet switching for time and wavelength. Thus, we can say that GMPLS is extension of MPLS which provides resilience and restoration by automatic switching. In this paper, we provide a Docker based simu-1ation environment which emulates a complex network and create insight functioning of GMPLS. The Docker based simulation environment is light-weight and scalable. It emulates large and complex network with minimal specifications. We have tested this Docker based GMPLS simulation testbed that depends on scaled network resources. Our method has shown tremendous improvement over the other virtualization methods. In this paper, we do a comparative study based on UML, Virtual Box, and Docker and found that Docker consumes very less resources when compared to UML and Virtual Box. In a system with 1 TB Hard disk space and 16 GB RAM, we can design and study a topology with 30–40 nodes using Virtual Box and a topology with 10–15 nodes using UML. Whereas, with Docker a topology with 300-nodes can be designed and tested. Thus scalability is limited by system specifications.
{"title":"Generalized Multi-protocol Label Switching based Virtualization for Cloud Computing","authors":"Rajat Saxena, Ajay Patel","doi":"10.1109/CSI54720.2022.9923991","DOIUrl":"https://doi.org/10.1109/CSI54720.2022.9923991","url":null,"abstract":"Generalized Multi Protocol Label Switching (GMPLS) or Multi-Protocol Lambda Switching is a new technology which produce amplification in Multi Protocol Label Switching (MPLS) to provide support network switching, space switching, and packet switching for time and wavelength. Thus, we can say that GMPLS is extension of MPLS which provides resilience and restoration by automatic switching. In this paper, we provide a Docker based simu-1ation environment which emulates a complex network and create insight functioning of GMPLS. The Docker based simulation environment is light-weight and scalable. It emulates large and complex network with minimal specifications. We have tested this Docker based GMPLS simulation testbed that depends on scaled network resources. Our method has shown tremendous improvement over the other virtualization methods. In this paper, we do a comparative study based on UML, Virtual Box, and Docker and found that Docker consumes very less resources when compared to UML and Virtual Box. In a system with 1 TB Hard disk space and 16 GB RAM, we can design and study a topology with 30–40 nodes using Virtual Box and a topology with 10–15 nodes using UML. Whereas, with Docker a topology with 300-nodes can be designed and tested. Thus scalability is limited by system specifications.","PeriodicalId":221137,"journal":{"name":"2022 International Conference on Connected Systems & Intelligence (CSI)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127082246","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 : 2022-08-31DOI: 10.1109/CSI54720.2022.9923968
G. Rajendran, Vinayak Ks, P. Au, P. Poornachandran
The COVID-19 pandemic brought down the entire world to a standstill. There was a sudden surge in the infection occurrences referred to as waves during which hospitals and treatment facilities experienced multiple challenges because of sudden and unexpected demands. Timely diagnosis, treatment, and medication are very important for the survival of the patients. India, being the second most populous nation in the world, required technology based innovations to overcome the Covid challenges. As an answer to this challenge, we identified multiple sources on the internet providing reliable information for relief measures and collected data and presented them in one platform. This helps in connecting the affected users from the Internet, social media platforms etc to the right facility in the fastest and most efficient way possible by aggregating and disseminating the relevant data. This one-stop website with all the imperative features directly benefits citizens/general public and help desk / emergency responders.
{"title":"COVID-19 Relief Measures assimilating Open Source Intelligence","authors":"G. Rajendran, Vinayak Ks, P. Au, P. Poornachandran","doi":"10.1109/CSI54720.2022.9923968","DOIUrl":"https://doi.org/10.1109/CSI54720.2022.9923968","url":null,"abstract":"The COVID-19 pandemic brought down the entire world to a standstill. There was a sudden surge in the infection occurrences referred to as waves during which hospitals and treatment facilities experienced multiple challenges because of sudden and unexpected demands. Timely diagnosis, treatment, and medication are very important for the survival of the patients. India, being the second most populous nation in the world, required technology based innovations to overcome the Covid challenges. As an answer to this challenge, we identified multiple sources on the internet providing reliable information for relief measures and collected data and presented them in one platform. This helps in connecting the affected users from the Internet, social media platforms etc to the right facility in the fastest and most efficient way possible by aggregating and disseminating the relevant data. This one-stop website with all the imperative features directly benefits citizens/general public and help desk / emergency responders.","PeriodicalId":221137,"journal":{"name":"2022 International Conference on Connected Systems & Intelligence (CSI)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114982060","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 : 2022-08-31DOI: 10.1109/CSI54720.2022.9924109
Sougata Das, M. Chatterjee
As Orthogonal Frequency Division Multiplexing (OFDM) allows flexible spectrum allocation, OFDM based optical grids have replaced traditional Wavelength Division Multiplexed (WDM) optical grids. Since a fiber-cut is the most common failure in optical networks and grids process resource intensive tasks, survivability is a key issue in designing optical grids. In a dynamic scenario, spectral fragmentation arises due to random arrival and departure of requests, leading to blocking of new requests. In this paper, we address the problem of survivability and minimizing request blocking in a dynamic scenario in OFDM based transparent optical grids. We propose a dynamic survivable route and spectrum allocation strategy. Time complexity analysis of the proposed algorithm Blocking Minimized Survivable Routing and Spectrum Allocation (BMSRSA), shows that it runs in polynomial time. Furthermore, intensive simulation experiments and performance comparisons with a well-known strategy show that the proposed strategy can lead to appreciable reduction in request blocking probability.
{"title":"Minimizing Request Blocking in Survivable Transparent OFDM Based Optical Grids","authors":"Sougata Das, M. Chatterjee","doi":"10.1109/CSI54720.2022.9924109","DOIUrl":"https://doi.org/10.1109/CSI54720.2022.9924109","url":null,"abstract":"As Orthogonal Frequency Division Multiplexing (OFDM) allows flexible spectrum allocation, OFDM based optical grids have replaced traditional Wavelength Division Multiplexed (WDM) optical grids. Since a fiber-cut is the most common failure in optical networks and grids process resource intensive tasks, survivability is a key issue in designing optical grids. In a dynamic scenario, spectral fragmentation arises due to random arrival and departure of requests, leading to blocking of new requests. In this paper, we address the problem of survivability and minimizing request blocking in a dynamic scenario in OFDM based transparent optical grids. We propose a dynamic survivable route and spectrum allocation strategy. Time complexity analysis of the proposed algorithm Blocking Minimized Survivable Routing and Spectrum Allocation (BMSRSA), shows that it runs in polynomial time. Furthermore, intensive simulation experiments and performance comparisons with a well-known strategy show that the proposed strategy can lead to appreciable reduction in request blocking probability.","PeriodicalId":221137,"journal":{"name":"2022 International Conference on Connected Systems & Intelligence (CSI)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121487588","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 : 2022-08-31DOI: 10.1109/CSI54720.2022.9924038
A. V. Shubhasree, P. Sankaran, C. V. Raghu
India has seen numerous flood events with severe infra structural damages and fatalities in recent years. UAV assisted technologies can contribute towards preparedness and response during these disasters. UAV images that capture a bird's eye view of the flooded area can be utilized for situation assessment and feedback. A major bottleneck identified here is the lack of a suitable data set. This work utilizes existing publicly available video data to create annotated data set of flooded areas in Kerala with 3 classes. This data set is then used to train YOLOv3 and YOLOv4 and the resulting models are analyzed. Within this framework we study the network behaviour by varying the loss function utilized and by feeding patches of images as input. It is seen that our method resulted in models that have high average precision values. This work provides a framework which can be utilized to generate focused data set to expand the number of classes involved and the situations analyzed.
{"title":"UAV Image Analysis of Flooded Area Using Convolutional Neural Networks","authors":"A. V. Shubhasree, P. Sankaran, C. V. Raghu","doi":"10.1109/CSI54720.2022.9924038","DOIUrl":"https://doi.org/10.1109/CSI54720.2022.9924038","url":null,"abstract":"India has seen numerous flood events with severe infra structural damages and fatalities in recent years. UAV assisted technologies can contribute towards preparedness and response during these disasters. UAV images that capture a bird's eye view of the flooded area can be utilized for situation assessment and feedback. A major bottleneck identified here is the lack of a suitable data set. This work utilizes existing publicly available video data to create annotated data set of flooded areas in Kerala with 3 classes. This data set is then used to train YOLOv3 and YOLOv4 and the resulting models are analyzed. Within this framework we study the network behaviour by varying the loss function utilized and by feeding patches of images as input. It is seen that our method resulted in models that have high average precision values. This work provides a framework which can be utilized to generate focused data set to expand the number of classes involved and the situations analyzed.","PeriodicalId":221137,"journal":{"name":"2022 International Conference on Connected Systems & Intelligence (CSI)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115845439","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 : 2022-08-31DOI: 10.1109/csi54720.2022.9924137
Swati Goel
A novel procedure to compute service criticality level in a safety and business critical systems is presented. The presented “Service Composability Count (SCC)” procedure can be used to schedule the outage of services, according to their criticality level. This SCC plays an important role in modelling planned outage, as continuous availability of some critical services is highly desirable in service-based systems (SBS). This paper focuses on accurately scheduling the outage on the basis of service criticality. Results indicate that highly composable services are critical, whereas atomic services are very less critical. That means, while scheduling the outage of services for maintenance purposes -Atomic services should be scheduled first while composable services should be scheduled at last.
{"title":"Proposed SCC Metric: Criticality Measure in modeling scheduled outage","authors":"Swati Goel","doi":"10.1109/csi54720.2022.9924137","DOIUrl":"https://doi.org/10.1109/csi54720.2022.9924137","url":null,"abstract":"A novel procedure to compute service criticality level in a safety and business critical systems is presented. The presented “Service Composability Count (SCC)” procedure can be used to schedule the outage of services, according to their criticality level. This SCC plays an important role in modelling planned outage, as continuous availability of some critical services is highly desirable in service-based systems (SBS). This paper focuses on accurately scheduling the outage on the basis of service criticality. Results indicate that highly composable services are critical, whereas atomic services are very less critical. That means, while scheduling the outage of services for maintenance purposes -Atomic services should be scheduled first while composable services should be scheduled at last.","PeriodicalId":221137,"journal":{"name":"2022 International Conference on Connected Systems & Intelligence (CSI)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115867294","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 : 2022-08-31DOI: 10.1109/CSI54720.2022.9923980
Harshit Mishra, L. Saini, A. Bhandwale
EtherCAT has distinct advantages in terms of speed, topology flexibility, synchronisation accuracy, and communication efficiency. A single board computer from Advantech and Hilscher CIFX 90E-RE are utilized to create a new slave system to ensure a high speed and reliable communication for HMI displays. The design process including hardware and software are all scrutinized. The communication between the master and slave is fast with better synchronization among the slaves, and the system operates reliably under the EtherCAT protocol, after passing through multiple test cases.
{"title":"Design of EtherCAT Slave Controller using CIFX 90E- RE for HMI Display","authors":"Harshit Mishra, L. Saini, A. Bhandwale","doi":"10.1109/CSI54720.2022.9923980","DOIUrl":"https://doi.org/10.1109/CSI54720.2022.9923980","url":null,"abstract":"EtherCAT has distinct advantages in terms of speed, topology flexibility, synchronisation accuracy, and communication efficiency. A single board computer from Advantech and Hilscher CIFX 90E-RE are utilized to create a new slave system to ensure a high speed and reliable communication for HMI displays. The design process including hardware and software are all scrutinized. The communication between the master and slave is fast with better synchronization among the slaves, and the system operates reliably under the EtherCAT protocol, after passing through multiple test cases.","PeriodicalId":221137,"journal":{"name":"2022 International Conference on Connected Systems & Intelligence (CSI)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116122497","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 : 2022-08-31DOI: 10.1109/CSI54720.2022.9923965
M. Ganesh, A. M, Arunbhaarathi Anbu
A Digital twin for the Automated Guided Vehicles (AGVs), Collaborative Robots (COBOTs), and other material handling systems will improve the logistical efficiency in manufacturing. To design the characteristic features of AGVs and the charging stations required (for a given number of pick-up and delivery nodes), a digital twin will be critical to simulate and obtain the information. A digital twin for a fleet of AGVs can dynamically update the system in the virtual platform along with its Physical counterpart. However, it demands modularity, accuracy, localization, and a layered framework of Internet of Things (IoT) nodes in the Industrial Internet of Things (IIoT) platform. In this article, the aim is to design and develop a digital twin framework for a fleet of AGVs providing modularity and concurrent processing capability. The concurrency and real-time computation are validated using machine vision. The performance and optimal usage of the AGVs are also simulated before deployment.
{"title":"Digital Twin framework for material handling and logistics in Manufacturing: Part 1","authors":"M. Ganesh, A. M, Arunbhaarathi Anbu","doi":"10.1109/CSI54720.2022.9923965","DOIUrl":"https://doi.org/10.1109/CSI54720.2022.9923965","url":null,"abstract":"A Digital twin for the Automated Guided Vehicles (AGVs), Collaborative Robots (COBOTs), and other material handling systems will improve the logistical efficiency in manufacturing. To design the characteristic features of AGVs and the charging stations required (for a given number of pick-up and delivery nodes), a digital twin will be critical to simulate and obtain the information. A digital twin for a fleet of AGVs can dynamically update the system in the virtual platform along with its Physical counterpart. However, it demands modularity, accuracy, localization, and a layered framework of Internet of Things (IoT) nodes in the Industrial Internet of Things (IIoT) platform. In this article, the aim is to design and develop a digital twin framework for a fleet of AGVs providing modularity and concurrent processing capability. The concurrency and real-time computation are validated using machine vision. The performance and optimal usage of the AGVs are also simulated before deployment.","PeriodicalId":221137,"journal":{"name":"2022 International Conference on Connected Systems & Intelligence (CSI)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122531097","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 : 2022-08-31DOI: 10.1109/CSI54720.2022.9924128
Lekshmi S. Nair, Shivani M K
An automated question-answering system aims to deliver answers to the questions based on an input text. Such systems are based on text processing and require extended processing time. Knowledge graphs for question answering have proven to be an efficient approach. The knowledge graphs can be applied in teaching-learning to make more efficient remote education. Developing a knowledge graph from unstructured text, processing and evaluating knowledge points, extracting knowledge entities, and integrating them are all focused. This article proposes a Question answering model incorporating a Knowledge graph and the pre-trained BERT(Bidirectional Encoder Representation from Transformers) for learning purposes. This model helps in assisting learners of all ages by providing immediate feedback. Hence it can be highly beneficial to students to obtain access to and continue remote learning.
{"title":"Knowledge Graph based Question Answering System for Remote School Education","authors":"Lekshmi S. Nair, Shivani M K","doi":"10.1109/CSI54720.2022.9924128","DOIUrl":"https://doi.org/10.1109/CSI54720.2022.9924128","url":null,"abstract":"An automated question-answering system aims to deliver answers to the questions based on an input text. Such systems are based on text processing and require extended processing time. Knowledge graphs for question answering have proven to be an efficient approach. The knowledge graphs can be applied in teaching-learning to make more efficient remote education. Developing a knowledge graph from unstructured text, processing and evaluating knowledge points, extracting knowledge entities, and integrating them are all focused. This article proposes a Question answering model incorporating a Knowledge graph and the pre-trained BERT(Bidirectional Encoder Representation from Transformers) for learning purposes. This model helps in assisting learners of all ages by providing immediate feedback. Hence it can be highly beneficial to students to obtain access to and continue remote learning.","PeriodicalId":221137,"journal":{"name":"2022 International Conference on Connected Systems & Intelligence (CSI)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122992977","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：