Pub Date : 2023-10-05DOI: 10.53759/7669/jmc202303036
Rajendra Pujari, Mageswari M, Herald Anantha Rufus N, Prabagaran S, Mahendran G, Saravanan R
The current study investigates the wear behavior of three distinct composite compositions designated as C1, C2, and C3, with direct implications for aerospace applications. Critical factors such as the Coefficient of Friction (Cf), Specific Rate of Wear (Sw), and Frictional Force (FF) were meticulously analyzed using a systematic experimental approach and the Taguchi L27 array design. Significant relationships between input factors and responses emerged after subjecting these responses to Taguchi signal-to-noise ratio analysis. The optimal parameter combination of a 5% composition, 14.5 N Applied Load (Ap), 150 rpm Rotational Speed (Rs), and 40.5 m Distance of Sliding (Ds) highlights the interplay of factors in improving wear resistance. An Artificial Neural Network (ANN) was used as a predictive tool to boost research efficiency, achieving an impressive 99.663% accuracy in response predictions. The result shows comparison of the ANN's efficacy with actual experimental results. These findings hold great promise for aerospace applications where wear-resistant materials are critical for long-term performance under harsh operating conditions. The incorporation of ANN predictions allows for rapid material optimization while adhering to the stringent requirements of aerospace environments. This research contributes to the evolution of tailored composite materials, poised to improve aerospace applications with increased reliability, efficiency, and durability by advancing wear analysis methodologies and predictive technologies.
{"title":"Artificial Neural Network Based Wear and Tribological Analysis of Al 7010 Alloy Reinforced with Nanoparticles of SIC for Aerospace Application","authors":"Rajendra Pujari, Mageswari M, Herald Anantha Rufus N, Prabagaran S, Mahendran G, Saravanan R","doi":"10.53759/7669/jmc202303036","DOIUrl":"https://doi.org/10.53759/7669/jmc202303036","url":null,"abstract":"The current study investigates the wear behavior of three distinct composite compositions designated as C1, C2, and C3, with direct implications for aerospace applications. Critical factors such as the Coefficient of Friction (Cf), Specific Rate of Wear (Sw), and Frictional Force (FF) were meticulously analyzed using a systematic experimental approach and the Taguchi L27 array design. Significant relationships between input factors and responses emerged after subjecting these responses to Taguchi signal-to-noise ratio analysis. The optimal parameter combination of a 5% composition, 14.5 N Applied Load (Ap), 150 rpm Rotational Speed (Rs), and 40.5 m Distance of Sliding (Ds) highlights the interplay of factors in improving wear resistance. An Artificial Neural Network (ANN) was used as a predictive tool to boost research efficiency, achieving an impressive 99.663% accuracy in response predictions. The result shows comparison of the ANN's efficacy with actual experimental results. These findings hold great promise for aerospace applications where wear-resistant materials are critical for long-term performance under harsh operating conditions. The incorporation of ANN predictions allows for rapid material optimization while adhering to the stringent requirements of aerospace environments. This research contributes to the evolution of tailored composite materials, poised to improve aerospace applications with increased reliability, efficiency, and durability by advancing wear analysis methodologies and predictive technologies.","PeriodicalId":91709,"journal":{"name":"International journal of machine learning and computing","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134975370","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 : 2023-10-05DOI: 10.53759/7669/jmc202303039
Sujatha A, Suguna R, Jothilakshmi R, Kavitha Rani R, Riyajuddin Yakub Mujawar, Prabagaran S
The Automated Dynamic Traffic Assignment (ADTA) system introduces a novel approach to urban traffic management, merging the power of IoT with machine learning. This research assessed the system's performance in comparison to traditional traffic management strategies across various real-world scenarios. Findings consistently showcased the ADTA's superior efficiency: during peak traffic, it reduced vehicle wait times by half, and in scenarios with unexpected road closures, congestion detection was almost five times quicker, rerouting traffic with a remarkable 95% efficiency. The system's adaptability was further highlighted during weather challenges, ensuring safer vehicle speeds and substantially reducing weather-induced incidents. Large-scale public events, known disruptors of traffic flow, witnessed significantly reduced backlogs under the ADTA. Moreover, emergency situations benefitted from the system's rapid response, ensuring minimal delays for critical vehicles. This research underscores the potential of the ADTA system as a transformative solution for urban traffic woes, emphasizing its scalability and real-world applicability. With its integration of innovative technology and adaptive mechanisms, the ADTA offers a blueprint for the future of intelligent urban transport management.
{"title":"Traffic Congestion Detection and Alternative Route Provision Using Machine Learning and IoT-Based Surveillance","authors":"Sujatha A, Suguna R, Jothilakshmi R, Kavitha Rani R, Riyajuddin Yakub Mujawar, Prabagaran S","doi":"10.53759/7669/jmc202303039","DOIUrl":"https://doi.org/10.53759/7669/jmc202303039","url":null,"abstract":"The Automated Dynamic Traffic Assignment (ADTA) system introduces a novel approach to urban traffic management, merging the power of IoT with machine learning. This research assessed the system's performance in comparison to traditional traffic management strategies across various real-world scenarios. Findings consistently showcased the ADTA's superior efficiency: during peak traffic, it reduced vehicle wait times by half, and in scenarios with unexpected road closures, congestion detection was almost five times quicker, rerouting traffic with a remarkable 95% efficiency. The system's adaptability was further highlighted during weather challenges, ensuring safer vehicle speeds and substantially reducing weather-induced incidents. Large-scale public events, known disruptors of traffic flow, witnessed significantly reduced backlogs under the ADTA. Moreover, emergency situations benefitted from the system's rapid response, ensuring minimal delays for critical vehicles. This research underscores the potential of the ADTA system as a transformative solution for urban traffic woes, emphasizing its scalability and real-world applicability. With its integration of innovative technology and adaptive mechanisms, the ADTA offers a blueprint for the future of intelligent urban transport management.","PeriodicalId":91709,"journal":{"name":"International journal of machine learning and computing","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134975365","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 : 2023-10-05DOI: 10.53759/7669/jmc202303049
Anbumani K, Murali Dhar M S, Jasmine J, Subramanian P, Mahaveerakannan R, John Justin Thangaraj S
Inevitably, researchers in the field of medicine must deal with the issue of missing data. Imputation is frequently employed as a solution to this issue. Unfortunately, the perfect would overfit the experiential data distribution due to the uncertainty introduced by imputation, which would have a negative effect on the replica's generalisation presentation. It is unclear how machine learning (ML) approaches are applied in medical research despite claims that they can work around lacking data. We hope to learn if and how machine learning prediction model research discuss how they deal with missing data. Information contained in EHRs is evaluated to ensure it is accurate and comprehensive. The missing information is imputed from the recognised EHR record. The Predictive Modelling approach is used for this, and the Naive Bayesian (NB) model is then used to assess the results in terms of performance metrics related to imputation. An adaptive optimisation technique, called the Adaptive Dolphin Atom Search Optimisation (Adaptive DASO) procedure, is used to teach the NB. The created Adaptive DASO method syndicates the DASO procedure with the adaptive idea. Dolphin Echolocation (DE) and Atom Search Optimisation (ASO) come together to form DASO. This indicator of performance metrics verifies imputation's fullness.
{"title":"Analysis of Missing Health Care Data by Effective Adaptive DASO Based Naive Bayesian Model","authors":"Anbumani K, Murali Dhar M S, Jasmine J, Subramanian P, Mahaveerakannan R, John Justin Thangaraj S","doi":"10.53759/7669/jmc202303049","DOIUrl":"https://doi.org/10.53759/7669/jmc202303049","url":null,"abstract":"Inevitably, researchers in the field of medicine must deal with the issue of missing data. Imputation is frequently employed as a solution to this issue. Unfortunately, the perfect would overfit the experiential data distribution due to the uncertainty introduced by imputation, which would have a negative effect on the replica's generalisation presentation. It is unclear how machine learning (ML) approaches are applied in medical research despite claims that they can work around lacking data. We hope to learn if and how machine learning prediction model research discuss how they deal with missing data. Information contained in EHRs is evaluated to ensure it is accurate and comprehensive. The missing information is imputed from the recognised EHR record. The Predictive Modelling approach is used for this, and the Naive Bayesian (NB) model is then used to assess the results in terms of performance metrics related to imputation. An adaptive optimisation technique, called the Adaptive Dolphin Atom Search Optimisation (Adaptive DASO) procedure, is used to teach the NB. The created Adaptive DASO method syndicates the DASO procedure with the adaptive idea. Dolphin Echolocation (DE) and Atom Search Optimisation (ASO) come together to form DASO. This indicator of performance metrics verifies imputation's fullness.","PeriodicalId":91709,"journal":{"name":"International journal of machine learning and computing","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135546676","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 : 2023-10-05DOI: 10.53759/7669/jmc202303043
Qusay Abdullah Abed
Several improvements have been suggested to process Transmission Control Protocol problems across wireless links. We are going to examine the standard TCP performance in two other methods allocated for progress, which are ELN- TCP (Explicit Loss Notification with Transmission Control Protocol) and I-TCP (Indirect Transmission Control Protocol). The TCP offers services over the wireless links, where this study is aimed for the purpose of additional enhancement relevant services. Such improvements are required due to the high transmission mistakes average in wireless links.
{"title":"Study the Performance of Transmission Control Protocol Versions in Several Domains","authors":"Qusay Abdullah Abed","doi":"10.53759/7669/jmc202303043","DOIUrl":"https://doi.org/10.53759/7669/jmc202303043","url":null,"abstract":"Several improvements have been suggested to process Transmission Control Protocol problems across wireless links. We are going to examine the standard TCP performance in two other methods allocated for progress, which are ELN- TCP (Explicit Loss Notification with Transmission Control Protocol) and I-TCP (Indirect Transmission Control Protocol). The TCP offers services over the wireless links, where this study is aimed for the purpose of additional enhancement relevant services. Such improvements are required due to the high transmission mistakes average in wireless links.","PeriodicalId":91709,"journal":{"name":"International journal of machine learning and computing","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134975367","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 : 2023-10-05DOI: 10.53759/7669/jmc202303045
Yangsun Lee
The emergence of blockchain technology represents a significant advancement in the field of computer science. Blockchain, an innovative technology that functions as a decentralized and publicly accessible record of all financial transactions, has significantly transformed the manner in which commercial activities are conducted. Companies and large- scale technology corporations have started substantial investments in the blockchain industry, a sector that experts forecast will exceed a valuation of $3 trillion during the next five-year period. The surge in its popularity may be ascribed to its robust security measures and comprehensive resolution for all issues pertaining to digital identity. The system in question is a decentralized digital ledger. A blockchain refers to an immutable and decentralized ledger composed of blocks, which function as collections of entries. The interconnection among these blocks is secured using encryption. The blockchain technology is captivating due to its inherent qualities, and it has significant potential in several domains owing to its desired attributes such as decentralization, transparency, and irreversibility. While blockchain technology is now most prominently associated with cryptocurrency, it has a diverse array of potential applications. This article aims to explore the many applications of blockchain in the domains of voting mechanisms, Internet of Things (IoT), supply chains, and identity management.
{"title":"An in Depth Analysis of Blockchain Technology, and its Potential Industrial Applications","authors":"Yangsun Lee","doi":"10.53759/7669/jmc202303045","DOIUrl":"https://doi.org/10.53759/7669/jmc202303045","url":null,"abstract":"The emergence of blockchain technology represents a significant advancement in the field of computer science. Blockchain, an innovative technology that functions as a decentralized and publicly accessible record of all financial transactions, has significantly transformed the manner in which commercial activities are conducted. Companies and large- scale technology corporations have started substantial investments in the blockchain industry, a sector that experts forecast will exceed a valuation of $3 trillion during the next five-year period. The surge in its popularity may be ascribed to its robust security measures and comprehensive resolution for all issues pertaining to digital identity. The system in question is a decentralized digital ledger. A blockchain refers to an immutable and decentralized ledger composed of blocks, which function as collections of entries. The interconnection among these blocks is secured using encryption. The blockchain technology is captivating due to its inherent qualities, and it has significant potential in several domains owing to its desired attributes such as decentralization, transparency, and irreversibility. While blockchain technology is now most prominently associated with cryptocurrency, it has a diverse array of potential applications. This article aims to explore the many applications of blockchain in the domains of voting mechanisms, Internet of Things (IoT), supply chains, and identity management.","PeriodicalId":91709,"journal":{"name":"International journal of machine learning and computing","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134975368","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 : 2023-10-05DOI: 10.53759/7669/jmc202303042
Divya G, Manoj Kumar D S, Shri Bharathi SV
Computer vision is a dynamic and rapidly evolving field within the broader domain of artificial intelligence. Within surveillance monitoring systems, one of the central tasks is object detection, which involves identifying and localizing objects of interest in video sequences to provide safety and security of the people. Detection of multiple objects is a challenging task in video sequences which interprets less accuracy and false Bounding box regression. In this paper, enhanced faster R-CNN model is proposed and trained to compute regional proposal through Convolutional layers on the different scene of the sequences in term of lighting, motion capture related to spatial analysis. These enhancements could encompass architectural improvements, novel training strategies, or the incorporation of additional data sources to improve the model's overall performance. Proposed model is experimented on pedestrian video gives an improved accuracy detection rate than single detector techniques.
{"title":"Multiple Object Detection on Surveillance Videos for Improving Accuracy Using Enhanced Faster R-CNN","authors":"Divya G, Manoj Kumar D S, Shri Bharathi SV","doi":"10.53759/7669/jmc202303042","DOIUrl":"https://doi.org/10.53759/7669/jmc202303042","url":null,"abstract":"Computer vision is a dynamic and rapidly evolving field within the broader domain of artificial intelligence. Within surveillance monitoring systems, one of the central tasks is object detection, which involves identifying and localizing objects of interest in video sequences to provide safety and security of the people. Detection of multiple objects is a challenging task in video sequences which interprets less accuracy and false Bounding box regression. In this paper, enhanced faster R-CNN model is proposed and trained to compute regional proposal through Convolutional layers on the different scene of the sequences in term of lighting, motion capture related to spatial analysis. These enhancements could encompass architectural improvements, novel training strategies, or the incorporation of additional data sources to improve the model's overall performance. Proposed model is experimented on pedestrian video gives an improved accuracy detection rate than single detector techniques.","PeriodicalId":91709,"journal":{"name":"International journal of machine learning and computing","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134975374","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 : 2023-10-05DOI: 10.53759/7669/jmc202303040
Hannah Rose Esther T, Duraimutharasan N
This work proposes a method for detecting and tracking moving objects that rely onthe partial differential equation technique and can track both forward and backward. In order to reduce the amount of noise in the output video, it is first divided into many frames and then pre-processed using methods for the Gaussian filters. The transfer function is calculated on the binarized frames following the acquisition of the absolute difference for forward tracking and backward tracking. The forward and backward tracking outputs are combined at the object tracking step to get the desired outcome. Statistics like f-measure, accuracy, retention, and precision are used to evaluate the predicted technique, and classic motion detection methods are also used to examine its effectiveness. According to the evaluation results, the suggested system is superior to the usual high-accuracy rate techniques.
{"title":"An Automated Partial Derivative Based Method for Detecting and Monitoring Moving Objects","authors":"Hannah Rose Esther T, Duraimutharasan N","doi":"10.53759/7669/jmc202303040","DOIUrl":"https://doi.org/10.53759/7669/jmc202303040","url":null,"abstract":"This work proposes a method for detecting and tracking moving objects that rely onthe partial differential equation technique and can track both forward and backward. In order to reduce the amount of noise in the output video, it is first divided into many frames and then pre-processed using methods for the Gaussian filters. The transfer function is calculated on the binarized frames following the acquisition of the absolute difference for forward tracking and backward tracking. The forward and backward tracking outputs are combined at the object tracking step to get the desired outcome. Statistics like f-measure, accuracy, retention, and precision are used to evaluate the predicted technique, and classic motion detection methods are also used to examine its effectiveness. According to the evaluation results, the suggested system is superior to the usual high-accuracy rate techniques.","PeriodicalId":91709,"journal":{"name":"International journal of machine learning and computing","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134975376","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 : 2023-10-05DOI: 10.53759/7669/jmc202303046
Deageon Kim, Dongoun Lee
This paper introduces the state-of-the-art biomaterials that may be used to build in a way that is both environmentally friendly and long-term. Concrete, polymers, admixtures, asphalt, and soils are all examples of these materials. It is only because of natural selection that biomaterials may have desirable characteristics that would otherwise be impossible. They are known for characteristics that cannot be replicated in a laboratory setting. These characteristics develop throughout time and by natural means. Biomaterials' naturally occurring characteristics are ideal for meeting the demands of the building industry. Biomaterials having negligible or very negligible linear coefficients of thermal expansion may be utilized in different building applications. They aid in the reduction of internal strains because to their resistance to any change in length brought on by variations in temperature. Biomaterials have various benefits over synthetic materials, including lower production costs and less of an impact on the environment. Use of biodegradable materials may help alleviate the environmental problem caused by the dumping of synthetics. Cracks in the concrete are patched by the live bacteria inside it, making the material stronger.
{"title":"Engineering, Structural Materials and Biomaterials: A Review of Sustainable Engineering Using Advanced Biomaterials","authors":"Deageon Kim, Dongoun Lee","doi":"10.53759/7669/jmc202303046","DOIUrl":"https://doi.org/10.53759/7669/jmc202303046","url":null,"abstract":"This paper introduces the state-of-the-art biomaterials that may be used to build in a way that is both environmentally friendly and long-term. Concrete, polymers, admixtures, asphalt, and soils are all examples of these materials. It is only because of natural selection that biomaterials may have desirable characteristics that would otherwise be impossible. They are known for characteristics that cannot be replicated in a laboratory setting. These characteristics develop throughout time and by natural means. Biomaterials' naturally occurring characteristics are ideal for meeting the demands of the building industry. Biomaterials having negligible or very negligible linear coefficients of thermal expansion may be utilized in different building applications. They aid in the reduction of internal strains because to their resistance to any change in length brought on by variations in temperature. Biomaterials have various benefits over synthetic materials, including lower production costs and less of an impact on the environment. Use of biodegradable materials may help alleviate the environmental problem caused by the dumping of synthetics. Cracks in the concrete are patched by the live bacteria inside it, making the material stronger.","PeriodicalId":91709,"journal":{"name":"International journal of machine learning and computing","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134975242","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 : 2023-10-05DOI: 10.53759/7669/jmc202303048
Keerthika N, Nithyanandam S
Health care Management System (HMS) is a key to successful management of any health care industry. Health care management systems have so many research dimensions such as identifying disease and diagnostic, drug discovery manufacturing, Bioinformatics’ problem, personalized treatments, Patient image analysis and so on. Heart Disease Prediction (HDP) is a process of identifying heart disease in advance and recognizes patient health condition by applying techniques on patient heart related symptoms. Now a day’s the problem of identifying heart diseases is solved by machine learning techniques. In this paper we construct a heart disease prediction method using combined feature selection and classification machine learning techniques. According to the existing study the one of the main difficult in heart disease prediction system is that the available data in open sources are not properly recorded the necessary characteristics and there is some lagging in finding the useful features from the available features. The process of removing inappropriate features from an available feature set while preserving sufficient classification accuracy is known as feature selection. A methodology is proposed in this paper that consists of two phases: Phase one employs two broad categories of feature selection techniques to identify the efficient feature sets and it is given to the input of our second phase such as classification. In this work we will concentrate on filter-based method for feature selection such as Chi-square, Fast Correlation Based Filter (FCBF), Gini Index (GI), RelifeF, and wrapper-based method for feature selection such as Backward Feature Elimination (BFE), Exhaustive Feature Selection (EFS), Forward Feature Selection (FFS), and Recursive Feature Elimination (RFE). The UCI heart disease data set is used to evaluate the output in this study. Finally, the proposed system's performance is validated by various experiments setups.
{"title":"An Efficient Filter and Wrapper based Selection Methods along With Random Forest and Support Vector Machines Classification Technique in Health Care System","authors":"Keerthika N, Nithyanandam S","doi":"10.53759/7669/jmc202303048","DOIUrl":"https://doi.org/10.53759/7669/jmc202303048","url":null,"abstract":"Health care Management System (HMS) is a key to successful management of any health care industry. Health care management systems have so many research dimensions such as identifying disease and diagnostic, drug discovery manufacturing, Bioinformatics’ problem, personalized treatments, Patient image analysis and so on. Heart Disease Prediction (HDP) is a process of identifying heart disease in advance and recognizes patient health condition by applying techniques on patient heart related symptoms. Now a day’s the problem of identifying heart diseases is solved by machine learning techniques. In this paper we construct a heart disease prediction method using combined feature selection and classification machine learning techniques. According to the existing study the one of the main difficult in heart disease prediction system is that the available data in open sources are not properly recorded the necessary characteristics and there is some lagging in finding the useful features from the available features. The process of removing inappropriate features from an available feature set while preserving sufficient classification accuracy is known as feature selection. A methodology is proposed in this paper that consists of two phases: Phase one employs two broad categories of feature selection techniques to identify the efficient feature sets and it is given to the input of our second phase such as classification. In this work we will concentrate on filter-based method for feature selection such as Chi-square, Fast Correlation Based Filter (FCBF), Gini Index (GI), RelifeF, and wrapper-based method for feature selection such as Backward Feature Elimination (BFE), Exhaustive Feature Selection (EFS), Forward Feature Selection (FFS), and Recursive Feature Elimination (RFE). The UCI heart disease data set is used to evaluate the output in this study. Finally, the proposed system's performance is validated by various experiments setups.","PeriodicalId":91709,"journal":{"name":"International journal of machine learning and computing","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134975244","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 : 2023-10-05DOI: 10.53759/7669/jmc202303034
Smitha B A, Raja Praveen K N
The high pace rising global competitions across education sector has forced institutions to enhance aforesaid aspects, which require assessing students or related stakeholders’ perception and opinion towards the learning materials, courses, learning methods or pedagogies, etc. To achieve it, the use of reviews by students can of paramount significance; yet, annotating student’s opinion over huge heterogenous and unstructured data remains a tedious task. Though, the artificial intelligence (AI) and natural language processing (NLP) techniques can play decisive role; yet the conventional unsupervised lexicon, corpus-based solutions, and machine learning and/or deep driven approaches are found limited due to the different issues like class-imbalance, lack of contextual details, lack of long-term dependency, convergence, local minima etc. The aforesaid challenges can be severe over large inputs in Big Data ecosystems. In this reference, this paper proposed an outlier resilient semantic featuring deep driven sentiment analysis model (ORDSAENet) for educational domain sentiment annotations. To address data heterogeneity and unstructured-ness over unpredictable digital media, the ORDSAENet applies varied pre-processing methods including missing value removal, Unicode normalization, Emoji and Website link removal, removal of the words with numeric values, punctuations removal, lower case conversion, stop-word removal, lemmatization, and tokenization. Moreover, it applies a text size-constrained criteria to remove outlier texts from the input and hence improve ROI-specific learning for accurate annotation. The tokenized data was processed for Word2Vec assisted continuous bag-of-words (CBOW) semantic embedding followed by synthetic minority over-sampling with edited nearest neighbor (SMOTE-ENN) resampling. The resampled embedding matrix was then processed for Bi-LSTM feature extraction and learning that retains both local as well as contextual features to achieve efficient learning and classification. Executing ORDSAENet model over educational review dataset encompassing both qualitative reviews as well as quantitative ratings for the online courses, revealed that the proposed approach achieves average sentiment annotation accuracy, precision, recall, and F-Measure of 95.87%, 95.26%, 95.06% and 95.15%, respectively, which is higher than the LSTM driven standalone feature learning solutions and other state-of-arts. The overall simulation results and allied inferences confirm robustness of the ORDSAENet model towards real-time educational sentiment annotation solution.
{"title":"ORDSAENet: Outlier Resilient Semantic Featured Deep Driven Sentiment Analysis Model for Education Domain","authors":"Smitha B A, Raja Praveen K N","doi":"10.53759/7669/jmc202303034","DOIUrl":"https://doi.org/10.53759/7669/jmc202303034","url":null,"abstract":"The high pace rising global competitions across education sector has forced institutions to enhance aforesaid aspects, which require assessing students or related stakeholders’ perception and opinion towards the learning materials, courses, learning methods or pedagogies, etc. To achieve it, the use of reviews by students can of paramount significance; yet, annotating student’s opinion over huge heterogenous and unstructured data remains a tedious task. Though, the artificial intelligence (AI) and natural language processing (NLP) techniques can play decisive role; yet the conventional unsupervised lexicon, corpus-based solutions, and machine learning and/or deep driven approaches are found limited due to the different issues like class-imbalance, lack of contextual details, lack of long-term dependency, convergence, local minima etc. The aforesaid challenges can be severe over large inputs in Big Data ecosystems. In this reference, this paper proposed an outlier resilient semantic featuring deep driven sentiment analysis model (ORDSAENet) for educational domain sentiment annotations. To address data heterogeneity and unstructured-ness over unpredictable digital media, the ORDSAENet applies varied pre-processing methods including missing value removal, Unicode normalization, Emoji and Website link removal, removal of the words with numeric values, punctuations removal, lower case conversion, stop-word removal, lemmatization, and tokenization. Moreover, it applies a text size-constrained criteria to remove outlier texts from the input and hence improve ROI-specific learning for accurate annotation. The tokenized data was processed for Word2Vec assisted continuous bag-of-words (CBOW) semantic embedding followed by synthetic minority over-sampling with edited nearest neighbor (SMOTE-ENN) resampling. The resampled embedding matrix was then processed for Bi-LSTM feature extraction and learning that retains both local as well as contextual features to achieve efficient learning and classification. Executing ORDSAENet model over educational review dataset encompassing both qualitative reviews as well as quantitative ratings for the online courses, revealed that the proposed approach achieves average sentiment annotation accuracy, precision, recall, and F-Measure of 95.87%, 95.26%, 95.06% and 95.15%, respectively, which is higher than the LSTM driven standalone feature learning solutions and other state-of-arts. The overall simulation results and allied inferences confirm robustness of the ORDSAENet model towards real-time educational sentiment annotation solution.","PeriodicalId":91709,"journal":{"name":"International journal of machine learning and computing","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134975248","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：