Mental health issues are a growing concern worldwide, and seeking support for these issues can be difficult due to various reasons. Chatbots have emerged as a promising solution to provide accessible and confidential support to individuals facing mental health issues. With recent advances in technology, digital interventions designed to supplement or replace in-person mental health services have proliferated, including the emergence of mental health chatbots that claim to provide assistance through automated natural language processing (NLP) therapeutic approaches. A chatbot can be described as a computer program capable of providing intelligent answers to user input by understanding natural language using one or more NLP techniques. In this study, we discuss the use of NLP in psychotherapy and compare the responses provided by chatbots to a set of predefined user inputs related to well-being and mental health queries and compare existing systems. A general analysis was performed. The general approach to building such chatbots includes basic NLP techniques such as word embedding, sentiment analysis, sequence-by-sequence models, and attention mechanisms. We also looked at Mental Ease, a mobile app that uses NLP technology not only to provide conversational assistance but also to tool up useful features for maintaining mental health. Incorporating mental health assessment tools into the chatbot interface, it can help patients cope with mild anxiety and depression alongside conventional therapy. It can also overcome some barriers to mental health, such as waiting lists and geographical barriers to face-to-face consultations.
{"title":"Chatbot for Mental health support using NLP","authors":"Vanshika Gupta, Varun Joshi, Akshat Jain, Inakshi Garg","doi":"10.1109/INCET57972.2023.10170573","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170573","url":null,"abstract":"Mental health issues are a growing concern worldwide, and seeking support for these issues can be difficult due to various reasons. Chatbots have emerged as a promising solution to provide accessible and confidential support to individuals facing mental health issues. With recent advances in technology, digital interventions designed to supplement or replace in-person mental health services have proliferated, including the emergence of mental health chatbots that claim to provide assistance through automated natural language processing (NLP) therapeutic approaches. A chatbot can be described as a computer program capable of providing intelligent answers to user input by understanding natural language using one or more NLP techniques. In this study, we discuss the use of NLP in psychotherapy and compare the responses provided by chatbots to a set of predefined user inputs related to well-being and mental health queries and compare existing systems. A general analysis was performed. The general approach to building such chatbots includes basic NLP techniques such as word embedding, sentiment analysis, sequence-by-sequence models, and attention mechanisms. We also looked at Mental Ease, a mobile app that uses NLP technology not only to provide conversational assistance but also to tool up useful features for maintaining mental health. Incorporating mental health assessment tools into the chatbot interface, it can help patients cope with mild anxiety and depression alongside conventional therapy. It can also overcome some barriers to mental health, such as waiting lists and geographical barriers to face-to-face consultations.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131108307","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170043
Diya Theresa Sunil, Seema Safar, Abhijit Das, Amijith M M, Devika M Joshy
Image captioning is the task of generating a textual description that accurately represents the content of an image. This task involves combining computer vision techniques, such as object recognition and scene understanding, with natural language processing to produce a human-like description of an image. Over time, various models have been introduced to perform image captioning, all aiming to accurately describe the content of an image. These models have practical applications such as improving the accessibility of multimedia content, assisting individuals with visual impairments, medical image captioning, and enhancing image search and retrieval. This paper explores some of the models and studies their efficiency using different evaluation metrics.
{"title":"A Comparative Analysis of Image Captioning Techniques","authors":"Diya Theresa Sunil, Seema Safar, Abhijit Das, Amijith M M, Devika M Joshy","doi":"10.1109/INCET57972.2023.10170043","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170043","url":null,"abstract":"Image captioning is the task of generating a textual description that accurately represents the content of an image. This task involves combining computer vision techniques, such as object recognition and scene understanding, with natural language processing to produce a human-like description of an image. Over time, various models have been introduced to perform image captioning, all aiming to accurately describe the content of an image. These models have practical applications such as improving the accessibility of multimedia content, assisting individuals with visual impairments, medical image captioning, and enhancing image search and retrieval. This paper explores some of the models and studies their efficiency using different evaluation metrics.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131127083","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10169940
Jaiwin Shah, Rishabh Jain, Vedant Jolly, D. Kalbande
According to recent studies, a large number of data scientists spend most of their time on tasks like data cleaning and organizing data. They need to memorize big complex syntaxes for all the major tasks in the data science life cycle. Often these tasks are redundant. Therefore, we propose to build an intelligent system that enables data scientists to perform all the tedious and time-consuming tasks such as EDA, data cleansing, data preprocessing, data visualization, modeling, and data science lifecycle evaluation. Just state the logic of your query in natural language the system will automatically output all relevant Python code snippets. Existing applications involving the text-to-code generation and code search are limited and a lot of them do not work in non-ideal conditions. The reason behind it is the data set on which the existing models have been built. These datasets do not consider real-world factors such as slang, acronyms, and paraphrases. Therefore, a new dataset was created consisting of real-world user queries, representing the scenarios a user is most likely to face daily. We plan to build a logic-oriented system that only needs to convey the logic correctly in text in natural language. It saves a lot of time, allowing data scientists to spend most of their time building logic instead of focusing on code.
{"title":"Smart Intelligent System that can Code Like a Human Being","authors":"Jaiwin Shah, Rishabh Jain, Vedant Jolly, D. Kalbande","doi":"10.1109/INCET57972.2023.10169940","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10169940","url":null,"abstract":"According to recent studies, a large number of data scientists spend most of their time on tasks like data cleaning and organizing data. They need to memorize big complex syntaxes for all the major tasks in the data science life cycle. Often these tasks are redundant. Therefore, we propose to build an intelligent system that enables data scientists to perform all the tedious and time-consuming tasks such as EDA, data cleansing, data preprocessing, data visualization, modeling, and data science lifecycle evaluation. Just state the logic of your query in natural language the system will automatically output all relevant Python code snippets. Existing applications involving the text-to-code generation and code search are limited and a lot of them do not work in non-ideal conditions. The reason behind it is the data set on which the existing models have been built. These datasets do not consider real-world factors such as slang, acronyms, and paraphrases. Therefore, a new dataset was created consisting of real-world user queries, representing the scenarios a user is most likely to face daily. We plan to build a logic-oriented system that only needs to convey the logic correctly in text in natural language. It saves a lot of time, allowing data scientists to spend most of their time building logic instead of focusing on code.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128064628","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170698
M. Reddy, Swaroop Bhat, Nandana Chandrashekar, Sethupathy Venkatraman, P. Kanwal
Conformance analysis is a crucial part of software development that is used for the verification of software systems. Most of the prominent techniques for testing are based on dynamic analysis. Although dynamic analysis handles run-time integration, it does not address the quality of the code and hence the maintainability of the software. Static analysis, which is the analysis of code without execution, can be used to mitigate these issues. Using this technique, the adherence of code to a coding standard can be ascertained. The use of a specific standard improves readability and code maintainability. Traditional methods used for this purpose have been language-specific, and support for user-specified guidelines has been poor.This paper presents a tool that checks the conformance of the source code with user-curated guidelines. A simple, intuitive, and concise manner to specify guidelines is introduced. These guidelines are language-agnostic, thus allowing a uniform style to express them for multiple languages. A library of predefined guidelines has been provided to facilitate rapid development, and methods to add new guidelines are also expounded. Additionally, these guidelines can be used to verify if certain programming constructs have been used. Thus, it brings the codebase closer to the requirement specification document, allowing the programmer to effortlessly implement the code without worrying about its conformance. Lastly, an universal coding metric and benchmarking tool named LAPCA Score is provided which quantifies the extent of guideline violations that can be used to measure the degree of code compliance.
{"title":"Language Agnostic Program Conformance Analysis","authors":"M. Reddy, Swaroop Bhat, Nandana Chandrashekar, Sethupathy Venkatraman, P. Kanwal","doi":"10.1109/INCET57972.2023.10170698","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170698","url":null,"abstract":"Conformance analysis is a crucial part of software development that is used for the verification of software systems. Most of the prominent techniques for testing are based on dynamic analysis. Although dynamic analysis handles run-time integration, it does not address the quality of the code and hence the maintainability of the software. Static analysis, which is the analysis of code without execution, can be used to mitigate these issues. Using this technique, the adherence of code to a coding standard can be ascertained. The use of a specific standard improves readability and code maintainability. Traditional methods used for this purpose have been language-specific, and support for user-specified guidelines has been poor.This paper presents a tool that checks the conformance of the source code with user-curated guidelines. A simple, intuitive, and concise manner to specify guidelines is introduced. These guidelines are language-agnostic, thus allowing a uniform style to express them for multiple languages. A library of predefined guidelines has been provided to facilitate rapid development, and methods to add new guidelines are also expounded. Additionally, these guidelines can be used to verify if certain programming constructs have been used. Thus, it brings the codebase closer to the requirement specification document, allowing the programmer to effortlessly implement the code without worrying about its conformance. Lastly, an universal coding metric and benchmarking tool named LAPCA Score is provided which quantifies the extent of guideline violations that can be used to measure the degree of code compliance.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133195438","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170280
S. Marlin, S. D. S. Sundarsingh Jebaseelan
Recent years have seen a rise in the use of solar Photovoltaic (PV) systems in numerous application systems because of their effectiveness and affordability. One of the main challenges is producing the maximum energy from PV panels under various environmental circumstances. In order to achieve the highest energy output, numerous optimization-based MPPT controlling systems have been devised in traditional works. Low convergence, computational complexity, the length of time required to discover the optimum solution, and inefficiency are major drawbacks. In order to put a recently created optimization technique called Mongoose Optimization (MO) for MPPT regulating into practise that is the aim of this study. With superior tracking efficiency and enhanced speed, it facilitates obtaining the maximum power from the PV panels. Moreover, a bi-directional converter is employed to control PV output while decreasing switching stress and loss. Also, the voltage source inverter is employed to lower harmonic distortion levels in order to guarantee improved power quality. Performance study evaluates and compares the simulation outcomes and the efficacy of the suggested regulating architecture using a variety of metrics.
{"title":"A New MPPT Controlling Mechanism based on Adaptive Mongoose Optimization (MO) Algorithm for Grid-PV Systems","authors":"S. Marlin, S. D. S. Sundarsingh Jebaseelan","doi":"10.1109/INCET57972.2023.10170280","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170280","url":null,"abstract":"Recent years have seen a rise in the use of solar Photovoltaic (PV) systems in numerous application systems because of their effectiveness and affordability. One of the main challenges is producing the maximum energy from PV panels under various environmental circumstances. In order to achieve the highest energy output, numerous optimization-based MPPT controlling systems have been devised in traditional works. Low convergence, computational complexity, the length of time required to discover the optimum solution, and inefficiency are major drawbacks. In order to put a recently created optimization technique called Mongoose Optimization (MO) for MPPT regulating into practise that is the aim of this study. With superior tracking efficiency and enhanced speed, it facilitates obtaining the maximum power from the PV panels. Moreover, a bi-directional converter is employed to control PV output while decreasing switching stress and loss. Also, the voltage source inverter is employed to lower harmonic distortion levels in order to guarantee improved power quality. Performance study evaluates and compares the simulation outcomes and the efficacy of the suggested regulating architecture using a variety of metrics.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134237563","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170052
Shaik. Pathima, Gude. SindhuPriya, Gudavalli. Lakshmi Yesaswini, S. Suhasini
It can be challenging to access information about books and users quickly. In any Catalogue systems, there is a sizable collection of books and other materials that are available for users to access. For the academic institutions, it serves as the brain. Mistakes can happen during the processing of documenting, cataloguing, and stacking books, and they may not be able to find the books they are looking for. It is difficult to keep track of all the books and users manually. If the book may be misplaced or stolen, this leads to a loss of revenue for the catalogue management system. Automated catalogue administration systems have several advantages, including expensive upkeep, technical challenges, the necessity for training courses, dependency on technology, and customizability. Yet, they also provide several advantages, such as improved information access, data management, and efficiency. The current application is a free and open-source web application developed using the MERN stack and hosts into the firebase up to a server. The goal of this paper is to develop a system that effectively handles all of the activities that take place in the catalogue system, enabling all users to access it whenever it is most convenient for them. Two factor authentications is carried out in the proposed system for handling users, email verification, notifications, book access, returns etc. admin handles security about users and other information to maintain effectiveness, confidentiality, integrity in the proposed system. Firebase is used to deploy the proposed web application and its operability. Real time updates, analytics are part of the proposed system
{"title":"Digitalization of Catalogue Automation System with Firebase","authors":"Shaik. Pathima, Gude. SindhuPriya, Gudavalli. Lakshmi Yesaswini, S. Suhasini","doi":"10.1109/INCET57972.2023.10170052","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170052","url":null,"abstract":"It can be challenging to access information about books and users quickly. In any Catalogue systems, there is a sizable collection of books and other materials that are available for users to access. For the academic institutions, it serves as the brain. Mistakes can happen during the processing of documenting, cataloguing, and stacking books, and they may not be able to find the books they are looking for. It is difficult to keep track of all the books and users manually. If the book may be misplaced or stolen, this leads to a loss of revenue for the catalogue management system. Automated catalogue administration systems have several advantages, including expensive upkeep, technical challenges, the necessity for training courses, dependency on technology, and customizability. Yet, they also provide several advantages, such as improved information access, data management, and efficiency. The current application is a free and open-source web application developed using the MERN stack and hosts into the firebase up to a server. The goal of this paper is to develop a system that effectively handles all of the activities that take place in the catalogue system, enabling all users to access it whenever it is most convenient for them. Two factor authentications is carried out in the proposed system for handling users, email verification, notifications, book access, returns etc. admin handles security about users and other information to maintain effectiveness, confidentiality, integrity in the proposed system. Firebase is used to deploy the proposed web application and its operability. Real time updates, analytics are part of the proposed system","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114539052","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}
Skin disease is a major issue of global health problem affecting a large amount of persons. The advancement of dermatological diseases categorization has grown more accurate in recent years due to the rapid growth of technology and the use of various machine learning techniques. Therefore the creation of machine learning methods that can accurately differentiate between the classifications of skin diseases is one of the great importance. This research work focuses on the classification of different kinds of skin diseases using machine learning techniques. In this research, we introduce a novel approach that makes use of four distinct data mining techniques like support vector machine (SVM), k-nearest neighbor (KNN), random forest (RF) and, naive bayes (NB) algorithm. This research work proposed an ensemble model that is combination of SVM, KNN, RF and NB using voting scheme. The proposed model classified the skin disease into five different classes that are Acne, Skin allergy, Nail fungus, Hair loss, and Normal skin. The proposed ensemble model used on skin disease classification that gives better performance over other classifier algorithms. The proposed ensemble model achieved highest 97.33% of accuracy as compared to others.
{"title":"Skin Disease Classification using Machine Learning based Proposed Ensemble Model","authors":"Bisahu Ram Sahu, Akhilesh Kumar Shrivas, Abhinav Shukla","doi":"10.1109/INCET57972.2023.10170128","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170128","url":null,"abstract":"Skin disease is a major issue of global health problem affecting a large amount of persons. The advancement of dermatological diseases categorization has grown more accurate in recent years due to the rapid growth of technology and the use of various machine learning techniques. Therefore the creation of machine learning methods that can accurately differentiate between the classifications of skin diseases is one of the great importance. This research work focuses on the classification of different kinds of skin diseases using machine learning techniques. In this research, we introduce a novel approach that makes use of four distinct data mining techniques like support vector machine (SVM), k-nearest neighbor (KNN), random forest (RF) and, naive bayes (NB) algorithm. This research work proposed an ensemble model that is combination of SVM, KNN, RF and NB using voting scheme. The proposed model classified the skin disease into five different classes that are Acne, Skin allergy, Nail fungus, Hair loss, and Normal skin. The proposed ensemble model used on skin disease classification that gives better performance over other classifier algorithms. The proposed ensemble model achieved highest 97.33% of accuracy as compared to others.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125476484","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170317
Rajat Dudhapachare, M. Awatade, Pushpak Kakde, Nihal Vaidya, Mayur Kapgate, R. Nakhate
The mouse is a prime example of HCI advancement. Although the modern wireless mouse or Bluetooth mouse still requires peripherals like energy cells and cards to connect to the computer, it is not entirely peripheral- free. The suggested AI virtual mouse system addresses the aforementioned issues by capturing hand motions with an external or digital camera, then improving the system's accuracy using voice assistants and hand point detection through object recognition. The system's foundation consists of machine learning techniques. To operate a computer, navigate, and execute actions like left- and right-clicking, digital hand motion can be used instead of a physical mouse. The program employs machine learning for hand identification and Python modules, for voice assistance. The suggested approach eliminates the need for human involvement and computer- controlled equipment in the battle against the spread of COVID-19 by implementing fundamental mouse operations together with brightness, volume control, and the ability to manage noise variations.
{"title":"Voice Guided, Gesture Controlled Virtual Mouse","authors":"Rajat Dudhapachare, M. Awatade, Pushpak Kakde, Nihal Vaidya, Mayur Kapgate, R. Nakhate","doi":"10.1109/INCET57972.2023.10170317","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170317","url":null,"abstract":"The mouse is a prime example of HCI advancement. Although the modern wireless mouse or Bluetooth mouse still requires peripherals like energy cells and cards to connect to the computer, it is not entirely peripheral- free. The suggested AI virtual mouse system addresses the aforementioned issues by capturing hand motions with an external or digital camera, then improving the system's accuracy using voice assistants and hand point detection through object recognition. The system's foundation consists of machine learning techniques. To operate a computer, navigate, and execute actions like left- and right-clicking, digital hand motion can be used instead of a physical mouse. The program employs machine learning for hand identification and Python modules, for voice assistance. The suggested approach eliminates the need for human involvement and computer- controlled equipment in the battle against the spread of COVID-19 by implementing fundamental mouse operations together with brightness, volume control, and the ability to manage noise variations.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134637213","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170497
Prajna K B, Balasubramanian V Iyer, B. C, Kruthi Mohan Thambanda, H. R. Kanasu
Polycystic Ovary Syndrome (PCOS) is a hormonal condition that affects women of reproductive age and can cause acne, facial hair growth, hair loss, infertility, irregular menstrual cycles, and weight gain. Early detection and treatment of PCOS can be challenging. We propose a system that uses machine learning algorithms to predict and diagnose PCOS using minimal parameters. We used a dataset from the open-source database "KAGGLE" and identified the top 10 to 15 features after speaking to gynaecologists. Four machine learning algorithms were used to train, validate and test the model, including the Random Forest classifier, logistic regression, Decision tree classifier and Chi-Square algorithm. Our results show that the Random forest classifier (Chi-Square) has the highest accuracy compared to the other algorithms. Our system can provide early detection, prognosis, and treatment suggestions for PCOS, which can improve the quality of life for women affected by this disorder.
{"title":"Implementation of Various Machine Learning Algorithms to Predict Polycystic Ovary Syndrome","authors":"Prajna K B, Balasubramanian V Iyer, B. C, Kruthi Mohan Thambanda, H. R. Kanasu","doi":"10.1109/INCET57972.2023.10170497","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170497","url":null,"abstract":"Polycystic Ovary Syndrome (PCOS) is a hormonal condition that affects women of reproductive age and can cause acne, facial hair growth, hair loss, infertility, irregular menstrual cycles, and weight gain. Early detection and treatment of PCOS can be challenging. We propose a system that uses machine learning algorithms to predict and diagnose PCOS using minimal parameters. We used a dataset from the open-source database \"KAGGLE\" and identified the top 10 to 15 features after speaking to gynaecologists. Four machine learning algorithms were used to train, validate and test the model, including the Random Forest classifier, logistic regression, Decision tree classifier and Chi-Square algorithm. Our results show that the Random forest classifier (Chi-Square) has the highest accuracy compared to the other algorithms. Our system can provide early detection, prognosis, and treatment suggestions for PCOS, which can improve the quality of life for women affected by this disorder.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134329811","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170232
Rezuana Haque, Arifa Sultana, Promila Haque
Monkeypox is a rare viral disease that is caused by the monkeypox virus. Monkeypox has clinical symptoms that are similar to those of other diseases such as measles and chickenpox, which makes early detection challenging. The early detection of monkeypox is essential to prevent its spread and reduce the risk of human-to-human transmission. Our study introduces a new method for detecting monkeypox at an early stage using modified transfer learning (TL) algorithms and an ensemble algorithm. The proposed approach can effectively distinguish it from other diseases that have similar symptoms. We used two different datasets, the “Monkeypox Skin Images Dataset (MSID)” and the "Monkeypox-dataset-2022(MD-2022)", which contain images from four classes, including monkeypox, measles, chickenpox, and normal images. We used stratified cross-validation to ensure that each fold of the cross-validation procedure contains a representative sample of each class, which is important when dealing with imbalanced datasets. To evaluate our proposed approach, we trained five pre-trained models, namely DenseNet121, ResNet152V2, ResNet50, InceptionV3, and EfficientNetV2B3, on each dataset separately. The achieved accuracy scores for the MD-2022 dataset were 89.4%, 84.2%, 89.4%, 84.2%, and 84.2%, respectively, while for the MSID dataset, the accuracy scores were 97.4%, 96.2%, 93.6%, 93.6%, and 95% for DenseNet121, ResNet50, InceptionV3, EfficientNetV2B3, and ResNet152V2, respectively. Subsequently, we constructed an ensemble model using a majority voting approach, which combined the predictions of the five models. Our findings indicate that the ensemble model outperformed certain individual models and demonstrated higher efficacy in monkeypox detection by achieving an accuracy score of 89.4% and 98.7% for the "Monkeypox-dataset-2022" and “Monkeypox Skin Images Dataset (MSID)” respectively.
{"title":"Ensemble of Fine-tuned Deep Learning Models for Monkeypox Detection: A Comparative Study","authors":"Rezuana Haque, Arifa Sultana, Promila Haque","doi":"10.1109/INCET57972.2023.10170232","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170232","url":null,"abstract":"Monkeypox is a rare viral disease that is caused by the monkeypox virus. Monkeypox has clinical symptoms that are similar to those of other diseases such as measles and chickenpox, which makes early detection challenging. The early detection of monkeypox is essential to prevent its spread and reduce the risk of human-to-human transmission. Our study introduces a new method for detecting monkeypox at an early stage using modified transfer learning (TL) algorithms and an ensemble algorithm. The proposed approach can effectively distinguish it from other diseases that have similar symptoms. We used two different datasets, the “Monkeypox Skin Images Dataset (MSID)” and the \"Monkeypox-dataset-2022(MD-2022)\", which contain images from four classes, including monkeypox, measles, chickenpox, and normal images. We used stratified cross-validation to ensure that each fold of the cross-validation procedure contains a representative sample of each class, which is important when dealing with imbalanced datasets. To evaluate our proposed approach, we trained five pre-trained models, namely DenseNet121, ResNet152V2, ResNet50, InceptionV3, and EfficientNetV2B3, on each dataset separately. The achieved accuracy scores for the MD-2022 dataset were 89.4%, 84.2%, 89.4%, 84.2%, and 84.2%, respectively, while for the MSID dataset, the accuracy scores were 97.4%, 96.2%, 93.6%, 93.6%, and 95% for DenseNet121, ResNet50, InceptionV3, EfficientNetV2B3, and ResNet152V2, respectively. Subsequently, we constructed an ensemble model using a majority voting approach, which combined the predictions of the five models. Our findings indicate that the ensemble model outperformed certain individual models and demonstrated higher efficacy in monkeypox detection by achieving an accuracy score of 89.4% and 98.7% for the \"Monkeypox-dataset-2022\" and “Monkeypox Skin Images Dataset (MSID)” respectively.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131638553","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：