Pub Date : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134038
J. Briskilal, Ch V M Sai Praneeth, Ch Chaitanya, M. J. Karthik, P. P. Reddy
Text classification is a requirement for every text processing application because the web contains a vast amount of text data. Intent detection, information extraction, sentiment analysis, and spam detection involves text categorization. Since text classification uses idioms, metaphors, and polysemic words, intent detection can be difficult. It is challenging to automatically identify idioms in Natural Language Processing applications such as Information Retrieval, Machine Translation, and chatbots. In all these applications, automatic idiom recognition is crucial. In this work, idiomatic and literals sentences are being classified. Idioms are typical expressions with new meanings. This research proposes an ensemble model using pretrained deep learning models to make model with more predictive nature. The models are trained and tested using in-house dataset. Moreover, an in-house dataset that contains 1040 idiomatic and literal sentences is suggested. The experimental results demonstrate the effectiveness of the proposed approach, achieving an accuracy of 86% on the test dataset.
{"title":"An Ensemble Method to Classify Telugu Idiomatic Sentences using Deep Learning Models","authors":"J. Briskilal, Ch V M Sai Praneeth, Ch Chaitanya, M. J. Karthik, P. P. Reddy","doi":"10.1109/ICICT57646.2023.10134038","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134038","url":null,"abstract":"Text classification is a requirement for every text processing application because the web contains a vast amount of text data. Intent detection, information extraction, sentiment analysis, and spam detection involves text categorization. Since text classification uses idioms, metaphors, and polysemic words, intent detection can be difficult. It is challenging to automatically identify idioms in Natural Language Processing applications such as Information Retrieval, Machine Translation, and chatbots. In all these applications, automatic idiom recognition is crucial. In this work, idiomatic and literals sentences are being classified. Idioms are typical expressions with new meanings. This research proposes an ensemble model using pretrained deep learning models to make model with more predictive nature. The models are trained and tested using in-house dataset. Moreover, an in-house dataset that contains 1040 idiomatic and literal sentences is suggested. The experimental results demonstrate the effectiveness of the proposed approach, achieving an accuracy of 86% on the test dataset.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125878935","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 : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134192
Sairam Vasa, Premkumar Borugadda, Archana Koyyada
A stroke is caused by a disturbance in blood flow to a specific location of the brain. This might occur due to an issue with the arteries. The objective of this research to develop the optimal model to predict brain stroke using Machine Learning Algorithms (MLA's), namely Logistic Regression (LR), Decision Tree Classifier (DTC), Random Forest Classifier (RFC), Support Vector Machine (SVC), Naive Bayes Classifier (NBC), KNN Classifier (KNN), and XGBoost Classifier (XGB).Apply the above algorithms with hyperparameter along with GridSearchCV (CV= 5) on the given dataset. The given dataset is imbalanced, while training the models, a few difficulties were met, including underfitting, a dataset with null values, and a model without balancing the data to boost performance of the models, need to balance the data by using a data sampling method such as SMOTE. Among the Seven models, XGB is the optimal model based on the accuracy of 96.34%.
{"title":"A Machine Learning Model to Predict a Diagnosis of Brain Stroke","authors":"Sairam Vasa, Premkumar Borugadda, Archana Koyyada","doi":"10.1109/ICICT57646.2023.10134192","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134192","url":null,"abstract":"A stroke is caused by a disturbance in blood flow to a specific location of the brain. This might occur due to an issue with the arteries. The objective of this research to develop the optimal model to predict brain stroke using Machine Learning Algorithms (MLA's), namely Logistic Regression (LR), Decision Tree Classifier (DTC), Random Forest Classifier (RFC), Support Vector Machine (SVC), Naive Bayes Classifier (NBC), KNN Classifier (KNN), and XGBoost Classifier (XGB).Apply the above algorithms with hyperparameter along with GridSearchCV (CV= 5) on the given dataset. The given dataset is imbalanced, while training the models, a few difficulties were met, including underfitting, a dataset with null values, and a model without balancing the data to boost performance of the models, need to balance the data by using a data sampling method such as SMOTE. Among the Seven models, XGB is the optimal model based on the accuracy of 96.34%.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126045709","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 : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134418
Shaista Fatima, G. Sangeetha, P. Ponmurugan, A. Arularasan, A. Prabhu Chakkaravarthy, R. Denis, A. Chinnasamy
As a result of ML, the healthcare industry undergoes substantial innovation and improvement. As a result, data management, clinical operations, drug research, and surgery are all progressing more quickly. The healthcare sector is now required to use this cutting-edge technology because of the Covid-19 pandemic. More importantly, people stand to benefit the most from technology because it may improve their health outcomes by identifying the best treatment alternatives for them. Thanks to ML's enhanced early disease detection capabilities, the frequency of re-admissions to hospitals and clinics can be reduced. In this article, we'll look at the main applications of machine learning in healthcare as well as its exceptional benefits in changing the industry.
{"title":"Machine Learning Development in Solving Critical Medical Problems","authors":"Shaista Fatima, G. Sangeetha, P. Ponmurugan, A. Arularasan, A. Prabhu Chakkaravarthy, R. Denis, A. Chinnasamy","doi":"10.1109/ICICT57646.2023.10134418","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134418","url":null,"abstract":"As a result of ML, the healthcare industry undergoes substantial innovation and improvement. As a result, data management, clinical operations, drug research, and surgery are all progressing more quickly. The healthcare sector is now required to use this cutting-edge technology because of the Covid-19 pandemic. More importantly, people stand to benefit the most from technology because it may improve their health outcomes by identifying the best treatment alternatives for them. Thanks to ML's enhanced early disease detection capabilities, the frequency of re-admissions to hospitals and clinics can be reduced. In this article, we'll look at the main applications of machine learning in healthcare as well as its exceptional benefits in changing the industry.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126740636","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 : 2023-04-26DOI: 10.1109/ICICT57646.2023.10133957
Nikkila Prakash, Mohitth Mahesh, P. Gouthaman
Cardiovascular diseases (CVD) are one of the highest causes of death in the world. The early detection of cardiac risk is a critical factor in proper diagnosis and treatment. This way, patients with critical needs get priority access to doctors and healthcare systerns. In this study, a cardiac risk assessment system was developed using the Logistic Regression algorithm, a machine learning model that has a high accuracy and is easy to interpret. The datasetused in this study included information from various patients. A total of 13 features were used to train the Logistic Regression model, including age, gender, blood pressure, and cholesterol levels. The results demonstrated that the Logistic Regression algorithm achieved high accuracy in predicting CVD risk, with an accuracy of 86.89. The main challenge when it comes to CVD risk assessment is the complexity of algorithms which makes it difficult for healthcare practitioners to interpret the results. Some systems require the personnel to go through additional training to use the risk assessment system, which can be time consuming. Logistic Regression is straightforward and simple. It is easy to interpret, making it suitable for clinical settings. It also has a well-established framework, which makes it very practical and reliable. This study showcases the importance of machine learning in the field of healthcare and highlights the effectiveness of the Logistic Regression algorithm in predicting cardiac risk. The high accuracy achieved by the model enables the early identification of cardiovascular disease risk. This makes it a useful tool for the healthcare industry and public health initiatives.
{"title":"Cardiovascular Disease Risk Assessment using Machine Learning","authors":"Nikkila Prakash, Mohitth Mahesh, P. Gouthaman","doi":"10.1109/ICICT57646.2023.10133957","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10133957","url":null,"abstract":"Cardiovascular diseases (CVD) are one of the highest causes of death in the world. The early detection of cardiac risk is a critical factor in proper diagnosis and treatment. This way, patients with critical needs get priority access to doctors and healthcare systerns. In this study, a cardiac risk assessment system was developed using the Logistic Regression algorithm, a machine learning model that has a high accuracy and is easy to interpret. The datasetused in this study included information from various patients. A total of 13 features were used to train the Logistic Regression model, including age, gender, blood pressure, and cholesterol levels. The results demonstrated that the Logistic Regression algorithm achieved high accuracy in predicting CVD risk, with an accuracy of 86.89. The main challenge when it comes to CVD risk assessment is the complexity of algorithms which makes it difficult for healthcare practitioners to interpret the results. Some systems require the personnel to go through additional training to use the risk assessment system, which can be time consuming. Logistic Regression is straightforward and simple. It is easy to interpret, making it suitable for clinical settings. It also has a well-established framework, which makes it very practical and reliable. This study showcases the importance of machine learning in the field of healthcare and highlights the effectiveness of the Logistic Regression algorithm in predicting cardiac risk. The high accuracy achieved by the model enables the early identification of cardiovascular disease risk. This makes it a useful tool for the healthcare industry and public health initiatives.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126346464","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 : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134462
Hairya Lakhani, Devang Undaviya, Harsh S. Dave, S. Degadwala, Dhairya Vyas
Combining positron emission tomography (PET) with magnetic resonance imaging (MRI) yields information that is complimentary from both a functional and anatomical standpoint. However, owing to the disparities in imaging physics and acquisition techniques, the integration of different modalities continues to be a difficult endeavor is challenge. Within the scope of this research, a deep learning-based strategy is presented in this study for PET-MRI sequence fusion that makes use of convolutional neural networks (CNNs). The proposed approach trains a CNN model to discover a mapping between the two modalities by capitalizing on the similarities that exist between the spatial and temporal characteristics of the two sequences. The proposed technique was tested using a dataset consisting of fifty PET-MRI scans. The findings illustrate the ability of our method to properly fuse the two sequences and increase picture quality in comparison to registration-based approaches that have been used traditionally. The CNN-based fusion strategy offers promise for enabling the clinical integration of PET-MRI, which would ultimately result in more accurate diagnosis and treatment planning for a variety of disorders.
{"title":"PET-MRI Sequence Fusion using Convolution Neural Network","authors":"Hairya Lakhani, Devang Undaviya, Harsh S. Dave, S. Degadwala, Dhairya Vyas","doi":"10.1109/ICICT57646.2023.10134462","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134462","url":null,"abstract":"Combining positron emission tomography (PET) with magnetic resonance imaging (MRI) yields information that is complimentary from both a functional and anatomical standpoint. However, owing to the disparities in imaging physics and acquisition techniques, the integration of different modalities continues to be a difficult endeavor is challenge. Within the scope of this research, a deep learning-based strategy is presented in this study for PET-MRI sequence fusion that makes use of convolutional neural networks (CNNs). The proposed approach trains a CNN model to discover a mapping between the two modalities by capitalizing on the similarities that exist between the spatial and temporal characteristics of the two sequences. The proposed technique was tested using a dataset consisting of fifty PET-MRI scans. The findings illustrate the ability of our method to properly fuse the two sequences and increase picture quality in comparison to registration-based approaches that have been used traditionally. The CNN-based fusion strategy offers promise for enabling the clinical integration of PET-MRI, which would ultimately result in more accurate diagnosis and treatment planning for a variety of disorders.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126348185","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 : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134060
X. Li, Z. Lin
With the rapid development of imaging and smart intelligent processing technology, complex 3D image semantic segmentation and binocular recognition, its research results are widely used in automatic driving systems (ADS), building informatization, and information early warning. Therefore, the on-line monitoring of 3D prefabricated building printing based on improved binocular system is studied. This study considers the basic method of binocular vision algorithm, introduces the research status of semantic segmentation, which is the current research hotspot of image segmentation. Then, the novel depth estimation algorithm is proposed to modify the traditional binocular system. The Geodesic Active Contour model is also optimized to undertake the task to detailed information segmentation for the visual information. Through the testing on the location accuracy and the visualized monitoring performance, the proposed system's performance is validated.
{"title":"On-line Monitoring of 3D Prefabricated Building Printing based on Improved Binocular System","authors":"X. Li, Z. Lin","doi":"10.1109/ICICT57646.2023.10134060","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134060","url":null,"abstract":"With the rapid development of imaging and smart intelligent processing technology, complex 3D image semantic segmentation and binocular recognition, its research results are widely used in automatic driving systems (ADS), building informatization, and information early warning. Therefore, the on-line monitoring of 3D prefabricated building printing based on improved binocular system is studied. This study considers the basic method of binocular vision algorithm, introduces the research status of semantic segmentation, which is the current research hotspot of image segmentation. Then, the novel depth estimation algorithm is proposed to modify the traditional binocular system. The Geodesic Active Contour model is also optimized to undertake the task to detailed information segmentation for the visual information. Through the testing on the location accuracy and the visualized monitoring performance, the proposed system's performance is validated.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125129948","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 : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134168
Debarghya Dutta, P. Biswas, S. Debnath
This paper discusses the operation of a single-phase standalone inverter in renewable energy applications, specifically for active magnetic bearings (AMB), electromagnetic suspension (EMS), and high-speed transportation utilizing magnetic levitation. Previous methods have encountered difficulties with Total Harmonic Distortion (THD) limits, sudden fluctuations, and system complexity. The proposed approach employs a closed-loop PI controller with unipolar pulse width modulation (PWM) and an LC output filter to simplify the system, reduce THD in the output voltage and current, ensure stability, and decrease mechanical vibrations. The proposed system's effectiveness in reducing THD and simplifying the overall design was tested using PSIM software simulations. The objective is to provide a superior alternative to existing switching power amplifier topologies with feedback controllers for different types of inductive loads.
{"title":"Single-Phase Standalone Inverter Using Closed-Loop PI Control for Electromagnetic Suspension","authors":"Debarghya Dutta, P. Biswas, S. Debnath","doi":"10.1109/ICICT57646.2023.10134168","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134168","url":null,"abstract":"This paper discusses the operation of a single-phase standalone inverter in renewable energy applications, specifically for active magnetic bearings (AMB), electromagnetic suspension (EMS), and high-speed transportation utilizing magnetic levitation. Previous methods have encountered difficulties with Total Harmonic Distortion (THD) limits, sudden fluctuations, and system complexity. The proposed approach employs a closed-loop PI controller with unipolar pulse width modulation (PWM) and an LC output filter to simplify the system, reduce THD in the output voltage and current, ensure stability, and decrease mechanical vibrations. The proposed system's effectiveness in reducing THD and simplifying the overall design was tested using PSIM software simulations. The objective is to provide a superior alternative to existing switching power amplifier topologies with feedback controllers for different types of inductive loads.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125230737","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 : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134406
Abaranjitha, Ajaykarthick, Swetha, S. Kamalraj
The number of Anterior Cruciate Ligament (ACL) injuries among young people and athletic professionals is growing rapidly. ACL reconstruction is being performed at an increasing extent nowadays. Although surgically treated, about 79% of these people develop osteoarthritis of the knee and 20% develop injuries again within two years. The risk of recurrent injuries and arthritis has become a financial burden and a public health concern. One in four young adults with an injury to the ACL has a second ACL injury from them in their career. Knee injuries (especially of the ACL) have a major impact on the future athletic performance. To reduce this damage, a suitable performance evaluation and intervention tool is needed to identify factors that make athletes prone to injury. Therefore, this research designs a novel IoT model using small devices with the possibility of measurement, processing, and communication, employing sensors and internal tools for ACL damage analysis. This paper presents a framework based on the IoT model to keep track of human biological signals during activities that may possibly cause ACL damage. The most important benefit of the suggested system is the flexibility in calculating the clinical data with the resources of the user's body network gadgets.
{"title":"ACL Injury Prevention in Athletes with IoT system and Active Sensors","authors":"Abaranjitha, Ajaykarthick, Swetha, S. Kamalraj","doi":"10.1109/ICICT57646.2023.10134406","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134406","url":null,"abstract":"The number of Anterior Cruciate Ligament (ACL) injuries among young people and athletic professionals is growing rapidly. ACL reconstruction is being performed at an increasing extent nowadays. Although surgically treated, about 79% of these people develop osteoarthritis of the knee and 20% develop injuries again within two years. The risk of recurrent injuries and arthritis has become a financial burden and a public health concern. One in four young adults with an injury to the ACL has a second ACL injury from them in their career. Knee injuries (especially of the ACL) have a major impact on the future athletic performance. To reduce this damage, a suitable performance evaluation and intervention tool is needed to identify factors that make athletes prone to injury. Therefore, this research designs a novel IoT model using small devices with the possibility of measurement, processing, and communication, employing sensors and internal tools for ACL damage analysis. This paper presents a framework based on the IoT model to keep track of human biological signals during activities that may possibly cause ACL damage. The most important benefit of the suggested system is the flexibility in calculating the clinical data with the resources of the user's body network gadgets.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123426567","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 : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134001
D. S, Banupriya S
The global prevalence of skin cancer is significant and growing. This is mainly due to the increased exposure to ultraviolet rays. This shifts the normal lifestyle of people to an indoor lifestyle with sun-seeking holidays. In particular, malignant melanoma is considered as the deadliest skin disease due to its fast growth, invasion, and metastasis cycle. Early detection is critical since the prognosis improves significantly when the tumour is removed as soon as possible. Many benign pigmented skin lesions can also look like early melanomas. The major goal of this research work is to classify malignancy from melanoma images by using a deep learning network.
{"title":"Skin Cancer Detection using Convolutional Neural Network","authors":"D. S, Banupriya S","doi":"10.1109/ICICT57646.2023.10134001","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134001","url":null,"abstract":"The global prevalence of skin cancer is significant and growing. This is mainly due to the increased exposure to ultraviolet rays. This shifts the normal lifestyle of people to an indoor lifestyle with sun-seeking holidays. In particular, malignant melanoma is considered as the deadliest skin disease due to its fast growth, invasion, and metastasis cycle. Early detection is critical since the prognosis improves significantly when the tumour is removed as soon as possible. Many benign pigmented skin lesions can also look like early melanomas. The major goal of this research work is to classify malignancy from melanoma images by using a deep learning network.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116603335","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}
A question answering system aims to answer the asked question with relevant responses thus sufficing the re-quested query asked in natural language by responding in the same language. Knowledge Graph Question Answering (KGQA) aims to answer questions asked by the user on a paragraph from a knowledge graph (KG). A strongly connected KG is essential in picking out answers for the requested question. This is because the KG is traversed to select the answer. A well connected KG thus provides a relevant answer. The knowledge graph is built by identifying the subject, the object and the relation for every sentence in the input text or knowledge base. Questions are processed to identify the source-relation-target triples which are then matched with that of the triples forming the KG. The challenge is in extracting the entities and relations between them to create the KG. The model's performance is directly proportional to the strength of the KG. Hence, the presence of a well connected KG provides great accuracy while a poorly connected one would break the system. The proposed model is tested on a Multi RC dataset. Multi RC is a dataset for multi hop question answering that includes short paragraphs and multi-sentence questions. This allows catering to both single hop and multi hop questions. The primary objective was to build a question answering system with the ability to answer multi hop questions together with an efficient response time through the usage of knowledge graphs. A novel approach has been employed where natural language questions are processed into key-value pairs, by leveraging python modules whose dependencies aid in parts of speech tagging in the English language thereby mapping back to the data entities present in the KG to retrieve the correct answer.
{"title":"Question Answering System using Knowledge Graphs","authors":"Spurthy Skandan, Susheen Kanungo, Shreyas Devaraj, Sahil Gupta, Surabhi Narayan","doi":"10.1109/ICICT57646.2023.10134047","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134047","url":null,"abstract":"A question answering system aims to answer the asked question with relevant responses thus sufficing the re-quested query asked in natural language by responding in the same language. Knowledge Graph Question Answering (KGQA) aims to answer questions asked by the user on a paragraph from a knowledge graph (KG). A strongly connected KG is essential in picking out answers for the requested question. This is because the KG is traversed to select the answer. A well connected KG thus provides a relevant answer. The knowledge graph is built by identifying the subject, the object and the relation for every sentence in the input text or knowledge base. Questions are processed to identify the source-relation-target triples which are then matched with that of the triples forming the KG. The challenge is in extracting the entities and relations between them to create the KG. The model's performance is directly proportional to the strength of the KG. Hence, the presence of a well connected KG provides great accuracy while a poorly connected one would break the system. The proposed model is tested on a Multi RC dataset. Multi RC is a dataset for multi hop question answering that includes short paragraphs and multi-sentence questions. This allows catering to both single hop and multi hop questions. The primary objective was to build a question answering system with the ability to answer multi hop questions together with an efficient response time through the usage of knowledge graphs. A novel approach has been employed where natural language questions are processed into key-value pairs, by leveraging python modules whose dependencies aid in parts of speech tagging in the English language thereby mapping back to the data entities present in the KG to retrieve the correct answer.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"31 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122246546","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：