Pub Date : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126494
Digant Rastogi, Manika Jain, M. M. Rayguru, S. K. Valluru
This paper presents a framework to apply Reinforcement Learning control algorithm on benchmark nonlinear dynamical systems. This work focuses on a novel Artificial Neural Network (ANN) based dynamic programming approach using Value Iteration to obtain optimal control for continuous-time nonlinear system. In particular, Coupled Tank System has been chosen to represent benchmark nonlinear dynamical system. The proposed Artificial Neural Network-Reinforcement Learning (ANN-RL) algorithm, Naive Reinforcement Learning (Naive-RL) algorithm and traditional PID control schemes are investigated on coupled tank system. The ANN-RL algorithm performs better than the Naive-RL and PID controllers in terms of steady state error, stability, oscillations and overshoot.
{"title":"Design & Validation of ANN based Reinforcement Learning Control Algorithm for Coupled Tank System","authors":"Digant Rastogi, Manika Jain, M. M. Rayguru, S. K. Valluru","doi":"10.1109/I2CT57861.2023.10126494","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126494","url":null,"abstract":"This paper presents a framework to apply Reinforcement Learning control algorithm on benchmark nonlinear dynamical systems. This work focuses on a novel Artificial Neural Network (ANN) based dynamic programming approach using Value Iteration to obtain optimal control for continuous-time nonlinear system. In particular, Coupled Tank System has been chosen to represent benchmark nonlinear dynamical system. The proposed Artificial Neural Network-Reinforcement Learning (ANN-RL) algorithm, Naive Reinforcement Learning (Naive-RL) algorithm and traditional PID control schemes are investigated on coupled tank system. The ANN-RL algorithm performs better than the Naive-RL and PID controllers in terms of steady state error, stability, oscillations and overshoot.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129388493","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126248
J. Baikerikar, Nilesh Ghavate, Vaishali Kavathekar, Allen Kodiyan
The Intelligent Medicine box is an effective health-care product that is implemented using a physically inexpensive medicine box powered by IoT devices and an application powered by Android operating system. The Android application is used to start a new medication and store the treatment details along with the medicine history. This application also provides an effective platform for the user to schedule an appointment with the doctor seamlessly. In addition to this the android application has an inbuilt prescription which will be beneficial in times of pandemic. The user can also add custom treatment plan if necessary. The medicine box alerts the user at the correct time to take the medicine. The box produces audio and illuminates the correct container number, thus making it fool proof and prevents the user from taking the wrong medicine. The Intelligent medicine box proposed by us is a very effective solution in the Health care sector and will reduce the care giver’s burden.
{"title":"Intelligent Medicine Box for COVID like Pandemic","authors":"J. Baikerikar, Nilesh Ghavate, Vaishali Kavathekar, Allen Kodiyan","doi":"10.1109/I2CT57861.2023.10126248","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126248","url":null,"abstract":"The Intelligent Medicine box is an effective health-care product that is implemented using a physically inexpensive medicine box powered by IoT devices and an application powered by Android operating system. The Android application is used to start a new medication and store the treatment details along with the medicine history. This application also provides an effective platform for the user to schedule an appointment with the doctor seamlessly. In addition to this the android application has an inbuilt prescription which will be beneficial in times of pandemic. The user can also add custom treatment plan if necessary. The medicine box alerts the user at the correct time to take the medicine. The box produces audio and illuminates the correct container number, thus making it fool proof and prevents the user from taking the wrong medicine. The Intelligent medicine box proposed by us is a very effective solution in the Health care sector and will reduce the care giver’s burden.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129599338","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126277
Amruta E Kabade, P. Desai, S. C, Shankar G
Sign Language Recognition(SLR) is a complex gesture recognition problem because of the quick and highly coarticulated motion involved in gestures. This research work focuses on Fingerspelling recognition task, which constitutes 35% of the American Sign Language (ASL). Fingerspelling identifies the word letter by letter. Fingerspelling is used for signing the words which do not have designated ASL signs such as technical terms, content words and proper nouns. In our proposed work for ASL Fingerspelling recognition, we consider ChicagoFSWild dataset which consists of occlusions and images captured in varying illuminations, lighting conditions (in the wild environments). The optical flow is obtained from Lucas-Kanade algorithm, prior is generated, images are resized and cropped with face-roi technique to get the region of interest (ROI). The visual attention mechanism attends to the ROI iteratively. ResNet, pretrained on Imagenet is used for the extraction of spatial features. The Bi-LSTM network with Connectionist Temporal Classification (CTC) is used to predict the sign. It provides the accuracy of 57% on ChicagoFSWild dataset for Fingerspelling recognition task.
{"title":"American Sign Language Fingerspelling Recognition using Attention Model","authors":"Amruta E Kabade, P. Desai, S. C, Shankar G","doi":"10.1109/I2CT57861.2023.10126277","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126277","url":null,"abstract":"Sign Language Recognition(SLR) is a complex gesture recognition problem because of the quick and highly coarticulated motion involved in gestures. This research work focuses on Fingerspelling recognition task, which constitutes 35% of the American Sign Language (ASL). Fingerspelling identifies the word letter by letter. Fingerspelling is used for signing the words which do not have designated ASL signs such as technical terms, content words and proper nouns. In our proposed work for ASL Fingerspelling recognition, we consider ChicagoFSWild dataset which consists of occlusions and images captured in varying illuminations, lighting conditions (in the wild environments). The optical flow is obtained from Lucas-Kanade algorithm, prior is generated, images are resized and cropped with face-roi technique to get the region of interest (ROI). The visual attention mechanism attends to the ROI iteratively. ResNet, pretrained on Imagenet is used for the extraction of spatial features. The Bi-LSTM network with Connectionist Temporal Classification (CTC) is used to predict the sign. It provides the accuracy of 57% on ChicagoFSWild dataset for Fingerspelling recognition task.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125002887","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126479
Nivedita Kasturi, S. G. Totad, Goldina Ghosh
Contribution of social network is not only limited to inter-personal relationship, but there are increasing number of research works carried out towards other arena of commercial applications harnessing the potential of social network. Irrespective of decades of work being carried out in social networking, the idea of using social networking towards crowdsourcing has not received much attention owing to different levels of research challenges. Existing studies have no reported discussion about this and therefore, this paper contributes towards exploring the strength and weakness of existing approaches of building analytics on social networking in order to understand the possible challenges that crowdsourcing encounters while dealing massive and unstructured data. The paper also contributes towards illustrating research trends highlighting the possible limitations.
{"title":"Research Approaches for Building Analytics in Social Network towards Crowdsourcing","authors":"Nivedita Kasturi, S. G. Totad, Goldina Ghosh","doi":"10.1109/I2CT57861.2023.10126479","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126479","url":null,"abstract":"Contribution of social network is not only limited to inter-personal relationship, but there are increasing number of research works carried out towards other arena of commercial applications harnessing the potential of social network. Irrespective of decades of work being carried out in social networking, the idea of using social networking towards crowdsourcing has not received much attention owing to different levels of research challenges. Existing studies have no reported discussion about this and therefore, this paper contributes towards exploring the strength and weakness of existing approaches of building analytics on social networking in order to understand the possible challenges that crowdsourcing encounters while dealing massive and unstructured data. The paper also contributes towards illustrating research trends highlighting the possible limitations.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130536760","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126493
Richa Tengshe, Eisha Akanksha
The IoT has brought a digital revolution in connecting vast number of heterogeneous devices together through wireless communication. Definitely it brings a comfort and convenience to the people’s life but on the counterpart the security, privacy and information leakage has become a prime concern specially in the area of finance, trading and healthcare. By the rapid growth of the market low power wide area network technologies have become the area of interest. Narrow band IoT (NB-IoT) and Long range (LoRa) are quite efficient in providing indoor and outdoor coverage with low data rate. Unlicensed LoRa supports a long-range coverage with longer battery life, cost, capacity. While, licensed NB-IoT benefits in terms of latency, reliability, QoS and range. Both the protocols are encapsulated with cryptographic algorithms to provide the secure communication. But still are vulnerable to a wide range of attacks. In this paper network architecture, vulnerabilities, possible security breaches and counter solutions of NB-IoT and LoRa are discussed.
{"title":"Security in LP-WAN Technologies: Challenges and Solutions","authors":"Richa Tengshe, Eisha Akanksha","doi":"10.1109/I2CT57861.2023.10126493","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126493","url":null,"abstract":"The IoT has brought a digital revolution in connecting vast number of heterogeneous devices together through wireless communication. Definitely it brings a comfort and convenience to the people’s life but on the counterpart the security, privacy and information leakage has become a prime concern specially in the area of finance, trading and healthcare. By the rapid growth of the market low power wide area network technologies have become the area of interest. Narrow band IoT (NB-IoT) and Long range (LoRa) are quite efficient in providing indoor and outdoor coverage with low data rate. Unlicensed LoRa supports a long-range coverage with longer battery life, cost, capacity. While, licensed NB-IoT benefits in terms of latency, reliability, QoS and range. Both the protocols are encapsulated with cryptographic algorithms to provide the secure communication. But still are vulnerable to a wide range of attacks. In this paper network architecture, vulnerabilities, possible security breaches and counter solutions of NB-IoT and LoRa are discussed.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130583458","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126215
Tony Alwin
High sensitivity strain sensor using Polymer Fiber Bragg Grating(P-FBG) is presented. An enhancement in strain sensitivity with an increase in the length of polymer FBG is simulated and demonstrated. The strain sensitivity increased from 1.39 to 5.15 pm/μɛ with the change in grating length from 26mm to100mm.Further, the strain sensitivity is increased by placing a polarization rotator in one arm of strain sensor.
{"title":"High sensitivity strain sensor based on Polymer Fiber Bragg Grating","authors":"Tony Alwin","doi":"10.1109/I2CT57861.2023.10126215","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126215","url":null,"abstract":"High sensitivity strain sensor using Polymer Fiber Bragg Grating(P-FBG) is presented. An enhancement in strain sensitivity with an increase in the length of polymer FBG is simulated and demonstrated. The strain sensitivity increased from 1.39 to 5.15 pm/μɛ with the change in grating length from 26mm to100mm.Further, the strain sensitivity is increased by placing a polarization rotator in one arm of strain sensor.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130867187","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126445
Gauthami Sreenivas, Kishan Minna Murthy, Kshitij Prit Gopali, Navya Eedula, Mamatha H R
Sentiment analysis is an important domain in Natural Language Processing (NLP) since it is an efficient way to extract features and user sentiments from textual data. Performing sentiment analysis of big data in the tourism industry is useful for businesses to understand the needs of their customers and improve hotel facilities to increase customer satisfaction. This paper aims to compare, analyze and employ different types of supervised, unsupervised, and pre-trained models. The supervised models - Decision Trees, XGBoost, Multinomial Naïve Bayes, Multinomial Logistic Regression, SVM, and Stochastic Gradient Descent were tested and the parameters were optimised using GridSearchCV. Two unsupervised models, K-means clustering and Latent Dirichlet Allocation were implemented with TF-IDF and Word2Vec embeddings. The pre-trained models, VADER and TextBlob were also implemented. The labelled dataset used for this study contains user reviews of hotels around the world, where each review is classified as positive, neutral, or negative. The SVM model resulted in the highest weighted F1 score of 0.8516.
{"title":"Sentiment Analysis of Hotel Reviews - a Comparative Study","authors":"Gauthami Sreenivas, Kishan Minna Murthy, Kshitij Prit Gopali, Navya Eedula, Mamatha H R","doi":"10.1109/I2CT57861.2023.10126445","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126445","url":null,"abstract":"Sentiment analysis is an important domain in Natural Language Processing (NLP) since it is an efficient way to extract features and user sentiments from textual data. Performing sentiment analysis of big data in the tourism industry is useful for businesses to understand the needs of their customers and improve hotel facilities to increase customer satisfaction. This paper aims to compare, analyze and employ different types of supervised, unsupervised, and pre-trained models. The supervised models - Decision Trees, XGBoost, Multinomial Naïve Bayes, Multinomial Logistic Regression, SVM, and Stochastic Gradient Descent were tested and the parameters were optimised using GridSearchCV. Two unsupervised models, K-means clustering and Latent Dirichlet Allocation were implemented with TF-IDF and Word2Vec embeddings. The pre-trained models, VADER and TextBlob were also implemented. The labelled dataset used for this study contains user reviews of hotels around the world, where each review is classified as positive, neutral, or negative. The SVM model resulted in the highest weighted F1 score of 0.8516.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130960093","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126204
Shiyona Dash, Deepjyoti Kalita, K. B. Mirza
Recent research works have increasingly focused on gaining a better understanding of visual perception from brain activity. This work was partially motivated by functional Magnetic Resonance Imaging (fMRI) based studies on the neurobiology of "mental images" and Brain-Computer Interface (BCI) devices. The ultimate objective is to recreate thoughts from brain activity using generative AI models. It is crucial to extract and enumerate the differences between visual perception (when a stimulus is present) and visual imagery (the recall of the stimulus after that) by the brain. In this work, we determine that it is possible to detect changes in brain activity due to differences in Visual Perception and Imagery even while using EEG signal features recorded with limited channels. The first step in this process was doing a spatiotemporal-based feature estimation on the EEG data for seven people across all channels and trials. Results indicate that Alpha Band power, an essential characteristic in the posterior electrodes and indicating a parieto-occipital origin, significantly differed across the different channels.
{"title":"Analysis of differences in EEG Signal features between Visual Imagery and Perception","authors":"Shiyona Dash, Deepjyoti Kalita, K. B. Mirza","doi":"10.1109/I2CT57861.2023.10126204","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126204","url":null,"abstract":"Recent research works have increasingly focused on gaining a better understanding of visual perception from brain activity. This work was partially motivated by functional Magnetic Resonance Imaging (fMRI) based studies on the neurobiology of \"mental images\" and Brain-Computer Interface (BCI) devices. The ultimate objective is to recreate thoughts from brain activity using generative AI models. It is crucial to extract and enumerate the differences between visual perception (when a stimulus is present) and visual imagery (the recall of the stimulus after that) by the brain. In this work, we determine that it is possible to detect changes in brain activity due to differences in Visual Perception and Imagery even while using EEG signal features recorded with limited channels. The first step in this process was doing a spatiotemporal-based feature estimation on the EEG data for seven people across all channels and trials. Results indicate that Alpha Band power, an essential characteristic in the posterior electrodes and indicating a parieto-occipital origin, significantly differed across the different channels.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131294182","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126194
R. Rohit, SA Gandheesh, KS Suriya, Peeta Basa Pati
Text from image documents must be recognized for its usage. Various tasks such as plagiarism & error check, language analysis, information capture rely on the accuracy of this text conversion. OCR systems convert the document images to their text equivalent. These OCR systems are prone to introducing errors during the recognition process.This work reports a system developed to ingest image documents which is converted to text using available OCR technologies. The recognized text, subsequently, is processed with deep network language models to enhance the accuracy of text. The system consists of a client server architecture with user interface available from web application as well as from mobile app. For the language models, encoder-decoder based BART & MarianMT are used. The results obtained demonstrate a 35% reduction in WER using the BART language model.
{"title":"System for Enhancing Accuracy of Noisy Text using Deep Network Language Models","authors":"R. Rohit, SA Gandheesh, KS Suriya, Peeta Basa Pati","doi":"10.1109/I2CT57861.2023.10126194","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126194","url":null,"abstract":"Text from image documents must be recognized for its usage. Various tasks such as plagiarism & error check, language analysis, information capture rely on the accuracy of this text conversion. OCR systems convert the document images to their text equivalent. These OCR systems are prone to introducing errors during the recognition process.This work reports a system developed to ingest image documents which is converted to text using available OCR technologies. The recognized text, subsequently, is processed with deep network language models to enhance the accuracy of text. The system consists of a client server architecture with user interface available from web application as well as from mobile app. For the language models, encoder-decoder based BART & MarianMT are used. The results obtained demonstrate a 35% reduction in WER using the BART language model.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131425586","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126241
Inam Ul Haq, Inzimam Ul Hassan, Hilal Ahmad Shah
Cricket is the most popular sport and most watched now a day. Test matches, One Day Internationals (ODI), and Twenty20 Internationals are the three forms in which it is played. Until the last ball of the last over, no one can predict who would win the match. Machine learning is a new field that uses existing data to predict future results. The goal of this study is to build a model that will predict the winner of a One-Day International Match before it begins. Machine learning techniques will be used on testing and training datasets to predict the winner of ODI match that will be based on the specified features. The data for the model is collected from Kaggle and some of the data are collected from the different cricket websites because the data obtained from Kaggle has only matches up until July 2021. Two algorithms were used for the prediction, K-Nearest and XGBoost, out of these two algorithms prediction accuracy of 91% was obtained by K-Nearest Neighbor Algorithm and prediction accuracy of 89% was obtained by XGBoost Algorithm
{"title":"Machine Learning Techniques for Result Prediction of One Day International (ODI)Cricket Match","authors":"Inam Ul Haq, Inzimam Ul Hassan, Hilal Ahmad Shah","doi":"10.1109/I2CT57861.2023.10126241","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126241","url":null,"abstract":"Cricket is the most popular sport and most watched now a day. Test matches, One Day Internationals (ODI), and Twenty20 Internationals are the three forms in which it is played. Until the last ball of the last over, no one can predict who would win the match. Machine learning is a new field that uses existing data to predict future results. The goal of this study is to build a model that will predict the winner of a One-Day International Match before it begins. Machine learning techniques will be used on testing and training datasets to predict the winner of ODI match that will be based on the specified features. The data for the model is collected from Kaggle and some of the data are collected from the different cricket websites because the data obtained from Kaggle has only matches up until July 2021. Two algorithms were used for the prediction, K-Nearest and XGBoost, out of these two algorithms prediction accuracy of 91% was obtained by K-Nearest Neighbor Algorithm and prediction accuracy of 89% was obtained by XGBoost Algorithm","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127272939","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：