Pub Date : 2024-03-01DOI: 10.36548/jtcsst.2024.1.003
Oladri Renuka, Niranchana Radhakrishnan
The Bidirectional Encoder Representations from Transformers (BERT) model is used in this work to analyse sentiment on Twitter data. A Kaggle dataset of manually annotated and anonymized COVID-19-related tweets was used to refine the model. Location, tweet date, original tweet content, and sentiment labels are all included in the dataset. When compared to the Multinomial Naive Bayes (MNB) baseline, BERT's performance was assessed, and it achieved an overall accuracy of 87% on the test set. The results indicated that for negative feelings, the accuracy was 0.93, the recall was 0.84, and the F1-score was 0.88; for neutral sentiments, the precision was 0.86, the recall was 0.78, and the F1-score was 0.82; and for positive sentiments, the precision was 0.82, the recall was 0.94, and the F1-score was 0.88. The model's proficiency with the linguistic nuances of Twitter, including slang and sarcasm, was demonstrated. This study also identifies the flaws of BERT and makes recommendations for future research paths, such as the integration of external knowledge and alternative designs.
{"title":"BERT for Twitter Sentiment Analysis: Achieving High Accuracy and Balanced Performance","authors":"Oladri Renuka, Niranchana Radhakrishnan","doi":"10.36548/jtcsst.2024.1.003","DOIUrl":"https://doi.org/10.36548/jtcsst.2024.1.003","url":null,"abstract":"The Bidirectional Encoder Representations from Transformers (BERT) model is used in this work to analyse sentiment on Twitter data. A Kaggle dataset of manually annotated and anonymized COVID-19-related tweets was used to refine the model. Location, tweet date, original tweet content, and sentiment labels are all included in the dataset. When compared to the Multinomial Naive Bayes (MNB) baseline, BERT's performance was assessed, and it achieved an overall accuracy of 87% on the test set. The results indicated that for negative feelings, the accuracy was 0.93, the recall was 0.84, and the F1-score was 0.88; for neutral sentiments, the precision was 0.86, the recall was 0.78, and the F1-score was 0.82; and for positive sentiments, the precision was 0.82, the recall was 0.94, and the F1-score was 0.88. The model's proficiency with the linguistic nuances of Twitter, including slang and sarcasm, was demonstrated. This study also identifies the flaws of BERT and makes recommendations for future research paths, such as the integration of external knowledge and alternative designs.","PeriodicalId":107574,"journal":{"name":"Journal of Trends in Computer Science and Smart Technology","volume":"162 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140283545","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 : 2023-09-01DOI: 10.36548/jtcsst.2023.3.003
Babina Banjara, Jinish Shrestha, Jinu Nyachhyon, Rijan Timilsina, S. Shakya
This proposed system provides a website called 'Safari Nepal', where users can search for destinations and check their location on a map. Users when registering on the website, can fill up the details about themselves and choose to either be a tour guide or a tourist. Based on the search and preferences of the user, similar destinations are recommended to the user via a recommendation system that uses a content-based recommendation feature. This feature works on the data obtained from the user, either explicitly or implicitly. The concept of K-Nearest Neighbours (KNN) and Cosine similarity makes the recommendation more accurate. KNN uses a distance algorithm that sorts from most liked destinations to least liked, based on the preferences of the user. This sorted list of destinations is further filtered by Cosine similarity, which is a measure of how similar two vectors in an inner product space are. It is calculated by taking the cosine of the angle between two vectors and determining whether two vectors are pointing towards the same general direction. Thus, combined KNN and Cosine similarity gives a better recommendation to the user. The map is integrated into the system using Mapbox API. Also, the system connects users with tour guides and gives them space to chat via a chatbox called ‘Travel Buddy’ where they can discuss further the destination, the amount charged by the guide, etc. The chatting feature on the system allows multiple users to connect and make conversations about the destination creating various chatrooms. In the system, the user can also publish their blogs describing their experiences and share their thoughts on particular destinations.
{"title":"Interactive Guide Assignment System with Destination Recommendation and Built-in Chatbox","authors":"Babina Banjara, Jinish Shrestha, Jinu Nyachhyon, Rijan Timilsina, S. Shakya","doi":"10.36548/jtcsst.2023.3.003","DOIUrl":"https://doi.org/10.36548/jtcsst.2023.3.003","url":null,"abstract":"This proposed system provides a website called 'Safari Nepal', where users can search for destinations and check their location on a map. Users when registering on the website, can fill up the details about themselves and choose to either be a tour guide or a tourist. Based on the search and preferences of the user, similar destinations are recommended to the user via a recommendation system that uses a content-based recommendation feature. This feature works on the data obtained from the user, either explicitly or implicitly. The concept of K-Nearest Neighbours (KNN) and Cosine similarity makes the recommendation more accurate. KNN uses a distance algorithm that sorts from most liked destinations to least liked, based on the preferences of the user. This sorted list of destinations is further filtered by Cosine similarity, which is a measure of how similar two vectors in an inner product space are. It is calculated by taking the cosine of the angle between two vectors and determining whether two vectors are pointing towards the same general direction. Thus, combined KNN and Cosine similarity gives a better recommendation to the user. The map is integrated into the system using Mapbox API. Also, the system connects users with tour guides and gives them space to chat via a chatbox called ‘Travel Buddy’ where they can discuss further the destination, the amount charged by the guide, etc. The chatting feature on the system allows multiple users to connect and make conversations about the destination creating various chatrooms. In the system, the user can also publish their blogs describing their experiences and share their thoughts on particular destinations.","PeriodicalId":107574,"journal":{"name":"Journal of Trends in Computer Science and Smart Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129349508","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 : 2023-09-01DOI: 10.36548/jtcsst.2023.3.002
Dr. Vaibhav Eknath Narawade, Chaitali Shetty, Purva Kharsambale, Samruddhi Bhosale, S. Rout
Brain tumors are one of the more severe medical conditions that can affect both children and adults. Brain tumors make up between 85 and 90 percent of all primary Central Nervous System (CNS) malignancies. Each year, brain tumors are found in about 11,700 persons. The 5-year survival rate is around 34% for males and 36% for female patients with malignant brain or CNS tumors. Brain tumors can be classified as benign, malignant, pituitary, and other forms. Appropriate treatment, meticulous planning, and exact diagnostics must be used to prolong patient lives. The most reliable way for detecting brain cancer is Magnetic Resonance Imaging (MRI). The images are examined by the radiologist. As brain tumors are complex the MRI serve as guide to diagnose the seriousness of the disease. Since the placement and size of the brain tumor seems incredibly abnormal for persons affected by the disease it becomes difficult to properly comprehend the nature of the tumor. For MRI analysis, a qualified neurosurgeon is also necessary. Compiling the results of an MRI can be extremely difficult and time-consuming because there are typically not enough qualified medical professionals and individuals who are knowledgeable about malignancy in poor countries. Thus, this issue can be resolved by an automated cloud-based solution. In the proposed model, The Convolutional Neural Networks (CNN) is used for the classification of the brain tumor dataset with an accuracy of 99%.
{"title":"Brain Tumor Classification using Transfer Learning","authors":"Dr. Vaibhav Eknath Narawade, Chaitali Shetty, Purva Kharsambale, Samruddhi Bhosale, S. Rout","doi":"10.36548/jtcsst.2023.3.002","DOIUrl":"https://doi.org/10.36548/jtcsst.2023.3.002","url":null,"abstract":"Brain tumors are one of the more severe medical conditions that can affect both children and adults. Brain tumors make up between 85 and 90 percent of all primary Central Nervous System (CNS) malignancies. Each year, brain tumors are found in about 11,700 persons. The 5-year survival rate is around 34% for males and 36% for female patients with malignant brain or CNS tumors. Brain tumors can be classified as benign, malignant, pituitary, and other forms. Appropriate treatment, meticulous planning, and exact diagnostics must be used to prolong patient lives. The most reliable way for detecting brain cancer is Magnetic Resonance Imaging (MRI). The images are examined by the radiologist. As brain tumors are complex the MRI serve as guide to diagnose the seriousness of the disease. Since the placement and size of the brain tumor seems incredibly abnormal for persons affected by the disease it becomes difficult to properly comprehend the nature of the tumor. For MRI analysis, a qualified neurosurgeon is also necessary. Compiling the results of an MRI can be extremely difficult and time-consuming because there are typically not enough qualified medical professionals and individuals who are knowledgeable about malignancy in poor countries. Thus, this issue can be resolved by an automated cloud-based solution. In the proposed model, The Convolutional Neural Networks (CNN) is used for the classification of the brain tumor dataset with an accuracy of 99%.","PeriodicalId":107574,"journal":{"name":"Journal of Trends in Computer Science and Smart Technology","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116427765","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 : 2023-09-01DOI: 10.36548/jtcsst.2023.3.001
Shiva Shrestha, Sushan Shakya, Sandeep Gautam
Plagiarism is the main problem in the digital world, as people use others’ content without giving prior credit to the creator. Therefore, there should be proper and efficient algorithms to find plagiarized content on the Internet. This research proposes two algorithms: the winnowing algorithm and the extended winnowing algorithm. The winnowing algorithm can only calculate the similarity rate between documents, whereas the extended algorithm can mark the plagiarized text segment in the compared records along with their similarity rates. The similarity rate in both algorithms has been calculated using the Jaccard Coefficient. Although the extended algorithm is beneficial as it provides a text marking feature, it consumes more computation power, which is discussed in this study. There are research works done previously using this approach, but none has compared the algorithms’ performance on small texts. Thus, this research utilizes the Twitter form of data to test these algorithms’ performance, as it contains a maximum of 280 characters. The application proposed to detect plagiarism in tweets has been developed using Python as the backend and React as the front-end technology.
{"title":"Winnowing vs Extended-Winnowing: A Comparative Analysis of Plagiarism Detection Algorithms","authors":"Shiva Shrestha, Sushan Shakya, Sandeep Gautam","doi":"10.36548/jtcsst.2023.3.001","DOIUrl":"https://doi.org/10.36548/jtcsst.2023.3.001","url":null,"abstract":"Plagiarism is the main problem in the digital world, as people use others’ content without giving prior credit to the creator. Therefore, there should be proper and efficient algorithms to find plagiarized content on the Internet. This research proposes two algorithms: the winnowing algorithm and the extended winnowing algorithm. The winnowing algorithm can only calculate the similarity rate between documents, whereas the extended algorithm can mark the plagiarized text segment in the compared records along with their similarity rates. The similarity rate in both algorithms has been calculated using the Jaccard Coefficient. Although the extended algorithm is beneficial as it provides a text marking feature, it consumes more computation power, which is discussed in this study. There are research works done previously using this approach, but none has compared the algorithms’ performance on small texts. Thus, this research utilizes the Twitter form of data to test these algorithms’ performance, as it contains a maximum of 280 characters. The application proposed to detect plagiarism in tweets has been developed using Python as the backend and React as the front-end technology.","PeriodicalId":107574,"journal":{"name":"Journal of Trends in Computer Science and Smart Technology","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122814253","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 : 2023-09-01DOI: 10.36548/jtcsst.2023.3.004
Manas Kumar Yogi
The role of chaos theory in the development of cyber threat detection systems is primarily exploratory and theoretical, with limited practical adoption in recent years. Chaos theory offers interesting concepts that have the potential to enhance cyber threat detection capabilities, but its application in the cybersecurity industry faces challenges and limitations. While chaos theory's practical role in cyber threat detection systems remains limited, its principles have the potential to complement existing methodologies and inspire new approaches to address the complex and dynamic nature of cybersecurity threats. As the field progresses, staying informed about the latest research and developments can help gauge the future scope and impact of chaos theory in cyber threat detection. In this paper, the roles and the principles of chaos theory are investigated and this investigation has indicators representing ample scope of chaos theory in design and development of robust frameworks related to cyber threat detection.
{"title":"Investigating the Scope of Chaos Theory for Cyber Threat Detection","authors":"Manas Kumar Yogi","doi":"10.36548/jtcsst.2023.3.004","DOIUrl":"https://doi.org/10.36548/jtcsst.2023.3.004","url":null,"abstract":"The role of chaos theory in the development of cyber threat detection systems is primarily exploratory and theoretical, with limited practical adoption in recent years. Chaos theory offers interesting concepts that have the potential to enhance cyber threat detection capabilities, but its application in the cybersecurity industry faces challenges and limitations. While chaos theory's practical role in cyber threat detection systems remains limited, its principles have the potential to complement existing methodologies and inspire new approaches to address the complex and dynamic nature of cybersecurity threats. As the field progresses, staying informed about the latest research and developments can help gauge the future scope and impact of chaos theory in cyber threat detection. In this paper, the roles and the principles of chaos theory are investigated and this investigation has indicators representing ample scope of chaos theory in design and development of robust frameworks related to cyber threat detection.","PeriodicalId":107574,"journal":{"name":"Journal of Trends in Computer Science and Smart Technology","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133908998","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 : 2023-09-01DOI: 10.36548/jtcsst.2023.3.005
Rahul Kumar Jha
Smart grid technology has transformed electricity distribution and management, but it also exposes critical infrastructures to cybersecurity threats. To mitigate these risks, the integration of machine learning (ML) and natural language processing (NLP) techniques has emerged as a promising approach. This survey paper analyses current research and applications related to ML and NLP integration, exploring methods for risk assessment, log analysis, threat analysis, intrusion detection, and anomaly detection. It also explores challenges, potential opportunities, and future research directions for enhancing smart grid cybersecurity through the synergy of ML and NLP. The study's key contributions include providing a thorough understanding of state-of-the-art techniques and paving the way for more robust and resilient smart grid defences against cyber threats.
{"title":"Strengthening Smart Grid Cybersecurity: An In-Depth Investigation into the Fusion of Machine Learning and Natural Language Processing","authors":"Rahul Kumar Jha","doi":"10.36548/jtcsst.2023.3.005","DOIUrl":"https://doi.org/10.36548/jtcsst.2023.3.005","url":null,"abstract":"Smart grid technology has transformed electricity distribution and management, but it also exposes critical infrastructures to cybersecurity threats. To mitigate these risks, the integration of machine learning (ML) and natural language processing (NLP) techniques has emerged as a promising approach. This survey paper analyses current research and applications related to ML and NLP integration, exploring methods for risk assessment, log analysis, threat analysis, intrusion detection, and anomaly detection. It also explores challenges, potential opportunities, and future research directions for enhancing smart grid cybersecurity through the synergy of ML and NLP. The study's key contributions include providing a thorough understanding of state-of-the-art techniques and paving the way for more robust and resilient smart grid defences against cyber threats.","PeriodicalId":107574,"journal":{"name":"Journal of Trends in Computer Science and Smart Technology","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125282879","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 : 2023-06-01DOI: 10.36548/jtcsst.2023.2.003
Ismankhan Y M
There are so many social networking sites available. Tweets have evolved into a crucial tool for gathering people's thoughts, ideas, behaviours and sentiments surrounding particular entities. One of the most intriguing subjects in this context is analyzing the sentiment of tweets using natural language processing (NLP). Although several methods have been created, the accuracy and effectiveness of those methods for sentiment analysis are yet to be improved. This paper proposes an innovative strategy that takes advantage of machine learning and lexical dictionaries. Tweets are classified using a stacked ensemble model that has Naive Bayes as a base classifier and the Logistic Regression as a meta classifier model. The performance of the proposed method is compared with common machine learning models such as Naïve Bayes and Logistic Regression using the sentiment140 dataset, experiments were carried out and their accuracy was determined. The results of the experiment endorse the proposed methodology. exhibits better outcomes of attaining accuracy score of 86%.
{"title":"Text based Tweet Classification using Ensemble Classifier","authors":"Ismankhan Y M","doi":"10.36548/jtcsst.2023.2.003","DOIUrl":"https://doi.org/10.36548/jtcsst.2023.2.003","url":null,"abstract":"There are so many social networking sites available. Tweets have evolved into a crucial tool for gathering people's thoughts, ideas, behaviours and sentiments surrounding particular entities. One of the most intriguing subjects in this context is analyzing the sentiment of tweets using natural language processing (NLP). Although several methods have been created, the accuracy and effectiveness of those methods for sentiment analysis are yet to be improved. This paper proposes an innovative strategy that takes advantage of machine learning and lexical dictionaries. Tweets are classified using a stacked ensemble model that has Naive Bayes as a base classifier and the Logistic Regression as a meta classifier model. The performance of the proposed method is compared with common machine learning models such as Naïve Bayes and Logistic Regression using the sentiment140 dataset, experiments were carried out and their accuracy was determined. The results of the experiment endorse the proposed methodology. exhibits better outcomes of attaining accuracy score of 86%.","PeriodicalId":107574,"journal":{"name":"Journal of Trends in Computer Science and Smart Technology","volume":"174 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125800155","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 : 2023-06-01DOI: 10.36548/jtcsst.2023.2.004
Satheeshkumar A, A. M, Hari Thirunavukkarsu A, S. S, G. Manavaalan
Every city in the downtown areas around the world faces a major problem due to heavy traffic, especially during the peak hours. Traditional traffic signals used in manging the traffic allots a fixed time for managing the traffic in a junction of a four way or a two-way crossroads and cannot adjust to account for changes in traffic. The proposed system provides a scheduled crossing time that is automatically adjusted based on the traffic. A long green light is assigned using the proposed to the particular side of the crossroad that faces heavy traffic. For this the suggested model uses IR sensors installed in every 5 meters of the road to detect objects.
{"title":"SMART CITY TRAFFIC CONTROL SYSTEM","authors":"Satheeshkumar A, A. M, Hari Thirunavukkarsu A, S. S, G. Manavaalan","doi":"10.36548/jtcsst.2023.2.004","DOIUrl":"https://doi.org/10.36548/jtcsst.2023.2.004","url":null,"abstract":"Every city in the downtown areas around the world faces a major problem due to heavy traffic, especially during the peak hours. Traditional traffic signals used in manging the traffic allots a fixed time for managing the traffic in a junction of a four way or a two-way crossroads and cannot adjust to account for changes in traffic. The proposed system provides a scheduled crossing time that is automatically adjusted based on the traffic. A long green light is assigned using the proposed to the particular side of the crossroad that faces heavy traffic. For this the suggested model uses IR sensors installed in every 5 meters of the road to detect objects.","PeriodicalId":107574,"journal":{"name":"Journal of Trends in Computer Science and Smart Technology","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115259755","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 : 2023-06-01DOI: 10.36548/jtcsst.2023.2.007
S. Suriya, J. Joanish Muthu
Type 2 diabetes is a persistent disorder that affects millions of individuals globally. It is characterised by the excessive levels of glucose within the blood due to insulin resistance or the incapability to supply insulin. Early detection and prediction of type 2 diabetes can improve patient outcomes. K-Nearest Neighbor (KNN) is used in the present model to predict type 2 diabetes. The KNN set of rules is a simple but powerful machine learning set of rules used for categorization and regression. It's far a non-parametric approach that makes predictions based totally on the nearest k-neighbours in a dataset. KNN is widely used in healthcare and scientific studies to expect and classify sicknesses primarily based on the affected person’s data. The intention of this work is to predict the threat of growing type 2 diabetes using the KNN set of rules. Data has been collected from electronic medical records of patients diagnosed with type 2 diabetes and healthy individuals. The dataset consists of various patient attributes, such as age, gender, body mass index, blood pressure, cholesterol levels, and glucose levels. Information has also been collected about lifestyle habits, such as physical activity, smoking status, and alcohol consumption. Data have been pre-processed by removing missing values and outliers, and normalization of the data has been done to ensure that all features have the same scale. Splitting the dataset into training and test sets, with training sets using 80% of the data and test sets using 20% of the data is performed. KNN algorithm have been used to classify the patients into two groups: those at high risk of developing type 2 diabetes and those at low risk. The model's performance has been assessed using a variety of metrics, including accuracy, precision, recall, and F1-score.
{"title":"Type 2 Diabetes Prediction using K-Nearest Neighbor Algorithm","authors":"S. Suriya, J. Joanish Muthu","doi":"10.36548/jtcsst.2023.2.007","DOIUrl":"https://doi.org/10.36548/jtcsst.2023.2.007","url":null,"abstract":"Type 2 diabetes is a persistent disorder that affects millions of individuals globally. It is characterised by the excessive levels of glucose within the blood due to insulin resistance or the incapability to supply insulin. Early detection and prediction of type 2 diabetes can improve patient outcomes. K-Nearest Neighbor (KNN) is used in the present model to predict type 2 diabetes. The KNN set of rules is a simple but powerful machine learning set of rules used for categorization and regression. It's far a non-parametric approach that makes predictions based totally on the nearest k-neighbours in a dataset. KNN is widely used in healthcare and scientific studies to expect and classify sicknesses primarily based on the affected person’s data. The intention of this work is to predict the threat of growing type 2 diabetes using the KNN set of rules. Data has been collected from electronic medical records of patients diagnosed with type 2 diabetes and healthy individuals. The dataset consists of various patient attributes, such as age, gender, body mass index, blood pressure, cholesterol levels, and glucose levels. Information has also been collected about lifestyle habits, such as physical activity, smoking status, and alcohol consumption. Data have been pre-processed by removing missing values and outliers, and normalization of the data has been done to ensure that all features have the same scale. Splitting the dataset into training and test sets, with training sets using 80% of the data and test sets using 20% of the data is performed. KNN algorithm have been used to classify the patients into two groups: those at high risk of developing type 2 diabetes and those at low risk. The model's performance has been assessed using a variety of metrics, including accuracy, precision, recall, and F1-score.","PeriodicalId":107574,"journal":{"name":"Journal of Trends in Computer Science and Smart Technology","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123879649","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 : 2023-06-01DOI: 10.36548/jtcsst.2023.2.001
S. Rajkumaran, S. V, Sridevi Sridhar
While many technological solutions have been implemented for accident detection, not many have focused on accident prevention. Accidents have been an everlasting concern as they have caused heavy injuries and death tolls on a large scale. There has been an everlasting increase in the rate of accidents and violation of traffic laws and wrongdoers managing to escape from the legal ramifications of predominantly Hit-and-Run cases. This entails a system to alleviate the occurrence of accidents and deaths caused. Focusing on this, a viable solution that focuses on preventing such circumstances by detecting accident-causing behaviour has been proposed. If accidents take place, it ensures the victim gets their rightful compensation. The research encompasses two modules, Prevention and Recovery. The prevention module uses Deep Learning and Computer Vision to detect whether the driver is drowsy and issues an alert employing CNN. The recovery module focuses on detecting occurrences of accidents and acquiring information about the parties involved in the same. Moreover, the prototype detects drowsiness, and detects and saves the accident footage in real-time enabling information acquisition.
{"title":"Vehicular Safety System using Deep Learning and Computer Vision","authors":"S. Rajkumaran, S. V, Sridevi Sridhar","doi":"10.36548/jtcsst.2023.2.001","DOIUrl":"https://doi.org/10.36548/jtcsst.2023.2.001","url":null,"abstract":"While many technological solutions have been implemented for accident detection, not many have focused on accident prevention. Accidents have been an everlasting concern as they have caused heavy injuries and death tolls on a large scale. There has been an everlasting increase in the rate of accidents and violation of traffic laws and wrongdoers managing to escape from the legal ramifications of predominantly Hit-and-Run cases. This entails a system to alleviate the occurrence of accidents and deaths caused. Focusing on this, a viable solution that focuses on preventing such circumstances by detecting accident-causing behaviour has been proposed. If accidents take place, it ensures the victim gets their rightful compensation. The research encompasses two modules, Prevention and Recovery. The prevention module uses Deep Learning and Computer Vision to detect whether the driver is drowsy and issues an alert employing CNN. The recovery module focuses on detecting occurrences of accidents and acquiring information about the parties involved in the same. Moreover, the prototype detects drowsiness, and detects and saves the accident footage in real-time enabling information acquisition.","PeriodicalId":107574,"journal":{"name":"Journal of Trends in Computer Science and Smart Technology","volume":"134 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131693655","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：