Pub Date : 2023-09-19DOI: 10.46610/jodmm.2023.v08i03.001
N. Vamsi Krishna, Kowdodi Siva Prasad
IoT is crucial to the implementation of Industry 4.0. Security is an important factor to consider while managing data. At the same time, the Internet of Things (IoT) is a rapidly evolving technological paradigm that promises to revolutionize the way people interact with the world around us. It involves the integration of various devices and sensors into everyday objects, enabling them to collect, exchange, and analyze data to enhance convenience and efficiency. The applications of IoT are vast and diverse, encompassing smartwatches, smartphones, industrial processes, and even educational settings. Central to the functioning of IoT is the seamless exchange of information among interconnected devices. However, this exchange often includes personal and sensitive data, making security a paramount concern. Protecting this data is essential to prevent potential security threats and breaches. This paper delves into the multifaceted world of IoT, exploring its applications across various domains while shedding light on the security challenges it presents. It delves into different types of security threats that can compromise the integrity and confidentiality of IoT data, such as unauthorized access, data breaches, and device manipulation. Moreover, the paper also provides insights into strategies and technologies to mitigate these risks. It discusses the importance of robust authentication protocols, encryption mechanisms, and intrusion detection systems to safeguard IoT ecosystems. As the IoT continues to grow and intertwine with our daily lives, addressing security concerns is crucial to fully harness its potential while ensuring the safety and privacy of individuals and organizations alike.
{"title":"Security Challenges in Data Collection and Processing in Industry 4.0 Implementation","authors":"N. Vamsi Krishna, Kowdodi Siva Prasad","doi":"10.46610/jodmm.2023.v08i03.001","DOIUrl":"https://doi.org/10.46610/jodmm.2023.v08i03.001","url":null,"abstract":"IoT is crucial to the implementation of Industry 4.0. Security is an important factor to consider while managing data. At the same time, the Internet of Things (IoT) is a rapidly evolving technological paradigm that promises to revolutionize the way people interact with the world around us. It involves the integration of various devices and sensors into everyday objects, enabling them to collect, exchange, and analyze data to enhance convenience and efficiency. The applications of IoT are vast and diverse, encompassing smartwatches, smartphones, industrial processes, and even educational settings. Central to the functioning of IoT is the seamless exchange of information among interconnected devices. However, this exchange often includes personal and sensitive data, making security a paramount concern. Protecting this data is essential to prevent potential security threats and breaches. This paper delves into the multifaceted world of IoT, exploring its applications across various domains while shedding light on the security challenges it presents. It delves into different types of security threats that can compromise the integrity and confidentiality of IoT data, such as unauthorized access, data breaches, and device manipulation. Moreover, the paper also provides insights into strategies and technologies to mitigate these risks. It discusses the importance of robust authentication protocols, encryption mechanisms, and intrusion detection systems to safeguard IoT ecosystems. As the IoT continues to grow and intertwine with our daily lives, addressing security concerns is crucial to fully harness its potential while ensuring the safety and privacy of individuals and organizations alike.","PeriodicalId":43061,"journal":{"name":"International Journal of Data Mining Modelling and Management","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135063220","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 : 2023-08-08DOI: 10.46610/jodmm.2023.v08i02.003
Janani B, R. A. Kumar, V. K, Monisha H M M
The increasing interest in Electro-encephalogram (EEG)-based stress prediction is driven by the global prevalence of stress. However, current studies predominantly rely on machine learning and deep learning techniques, utilizing extensive EEG data from 8 to 32 channels for stress prediction. In contrast, our research proposes an innovative approach that predicts stress using only 2 EEG channels and focuses on a specific frequency band (beta). The dataset used in this work is collected and pre-processed in a novel approach which is discussed in depth. Moreover, we have transformed the entire system into a TFLite model to enhance portability. Our experimental results, conducted on 10 subjects, demonstrate that our proposed technique achieves a remarkable prediction accuracy of 74%. Notably, this performance is comparable to other models that employ up to 128-channel data and consider multiple frequency bands. Our work lays the foundation for future advancements, with the ultimate goal of developing a portable EEG-based headband featuring only 2 channels. This would enable stress prediction, and the results could be easily accessed through either a mobile or web interface. By streamlining the EEG data acquisition and focusing on a specific frequency band, our approach not only achieves impressive prediction accuracy but also paves the way for the development of more user-friendly and accessible stress prediction technologies. This has the potential to significantly impact stress management and well-being on a global scale.
{"title":"EEG-Based Human Stress Level Predictor Using Customized EEGNet Model","authors":"Janani B, R. A. Kumar, V. K, Monisha H M M","doi":"10.46610/jodmm.2023.v08i02.003","DOIUrl":"https://doi.org/10.46610/jodmm.2023.v08i02.003","url":null,"abstract":"The increasing interest in Electro-encephalogram (EEG)-based stress prediction is driven by the global prevalence of stress. However, current studies predominantly rely on machine learning and deep learning techniques, utilizing extensive EEG data from 8 to 32 channels for stress prediction. In contrast, our research proposes an innovative approach that predicts stress using only 2 EEG channels and focuses on a specific frequency band (beta). The dataset used in this work is collected and pre-processed in a novel approach which is discussed in depth. Moreover, we have transformed the entire system into a TFLite model to enhance portability. Our experimental results, conducted on 10 subjects, demonstrate that our proposed technique achieves a remarkable prediction accuracy of 74%. Notably, this performance is comparable to other models that employ up to 128-channel data and consider multiple frequency bands. Our work lays the foundation for future advancements, with the ultimate goal of developing a portable EEG-based headband featuring only 2 channels. This would enable stress prediction, and the results could be easily accessed through either a mobile or web interface. By streamlining the EEG data acquisition and focusing on a specific frequency band, our approach not only achieves impressive prediction accuracy but also paves the way for the development of more user-friendly and accessible stress prediction technologies. This has the potential to significantly impact stress management and well-being on a global scale.","PeriodicalId":43061,"journal":{"name":"International Journal of Data Mining Modelling and Management","volume":"226 1","pages":""},"PeriodicalIF":0.5,"publicationDate":"2023-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88824316","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 : 2023-03-31DOI: 10.46610/jodmm.2023.v08i01.005
S. Rajesh, G. Yogarajan, M. Sivakumar
In this paper, we offer research that focuses on the value of Assistive Technologies (ATs) and Information and Communication Technologies (ICTs) for students with intellectual disabilities. Integrating Information and Communication Technology (ICT) and Assistive Technology (AT) in education has become an emerging strategy for supporting the learning and development of students with impairments, including intellectually handicapped children, such as those with mental retardation. The adoption of these technologies in education has the potential to provide such students with personalised and engaging learning experiences by giving them access to a variety of multimedia resources, interactive activities, and educational software that can be customized according to their needs and preferences. Furthermore, these tools can help students overcome physical, cognitive, and sensory limitations that may be impeding their academic success. ICT and AT can help intellectually impaired youngsters enhance their academic achievement and social skills by promoting individualised and interactive learning. Furthermore, by allowing individuals to learn at their speed and take responsibility for their learning, utilizing ICT and AT in education may encourage their freedom and self-determination. This can help them gain confidence and a sense of independence, which can lead to high success rates in academic and social areas. Special educators teaching at institutions for children with intellectual disabilities in southern Tamil Nadu districts were considered and 100 samples have been taken for the study. Statistical analysis was performed by calculating Pearson's Product Moment Coefficient of Correlation. The research found a substantial link between learners with intellectual impairments' cognitive, psychomotor, and social abilities and ICTs and ATs.
{"title":"Significance of Information Communication Technology and Assistive Technology in Relation to the Mentally Retarded Children’s Education","authors":"S. Rajesh, G. Yogarajan, M. Sivakumar","doi":"10.46610/jodmm.2023.v08i01.005","DOIUrl":"https://doi.org/10.46610/jodmm.2023.v08i01.005","url":null,"abstract":"In this paper, we offer research that focuses on the value of Assistive Technologies (ATs) and Information and Communication Technologies (ICTs) for students with intellectual disabilities. Integrating Information and Communication Technology (ICT) and Assistive Technology (AT) in education has become an emerging strategy for supporting the learning and development of students with impairments, including intellectually handicapped children, such as those with mental retardation. The adoption of these technologies in education has the potential to provide such students with personalised and engaging learning experiences by giving them access to a variety of multimedia resources, interactive activities, and educational software that can be customized according to their needs and preferences. Furthermore, these tools can help students overcome physical, cognitive, and sensory limitations that may be impeding their academic success. ICT and AT can help intellectually impaired youngsters enhance their academic achievement and social skills by promoting individualised and interactive learning. Furthermore, by allowing individuals to learn at their speed and take responsibility for their learning, utilizing ICT and AT in education may encourage their freedom and self-determination. This can help them gain confidence and a sense of independence, which can lead to high success rates in academic and social areas. Special educators teaching at institutions for children with intellectual disabilities in southern Tamil Nadu districts were considered and 100 samples have been taken for the study. Statistical analysis was performed by calculating Pearson's Product Moment Coefficient of Correlation. The research found a substantial link between learners with intellectual impairments' cognitive, psychomotor, and social abilities and ICTs and ATs.","PeriodicalId":43061,"journal":{"name":"International Journal of Data Mining Modelling and Management","volume":"1 1","pages":""},"PeriodicalIF":0.5,"publicationDate":"2023-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87192383","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 : 2023-03-29DOI: 10.46610/jodmm.2023.v08i01.004
Nihar M. Ranjan, Gitanjali Mate, Maya Bembde
Parkinson's Disease is a progressive neurodegenerative disorder of movement that affects your ability to control movement. This disease can prove fatal if not detected at an earlier stage. Motor and non-motor symptoms are raised by the loss of dopamine-producing neurons. Currently, there is no test available to detect disease at early stages where the symptoms may be poorly characterised. Handwriting analysis is one of the traditional aspects of studying human personality and also can be used to identify the symptoms of this disease. Identifying such accurate biomarkers provides roots for better clinical diagnosis. In this paper, we proposed a system that makes use of two types of handwriting analysis, spiral and wave drawings of healthy as well as Parkinson's patients as an input to the system. For feature extraction, we are using a histogram of the oriented gradient. The developed system uses a machine learning algorithm and a random forest classifier for the detection of Parkinson's disease among patients. Our model achieved an accuracy of 86.67 % in the case of spiral drawing and 83.30% with wave drawing.
{"title":"Detection of Parkinson's Disease using Machine Learning Algorithms and Handwriting Analysis","authors":"Nihar M. Ranjan, Gitanjali Mate, Maya Bembde","doi":"10.46610/jodmm.2023.v08i01.004","DOIUrl":"https://doi.org/10.46610/jodmm.2023.v08i01.004","url":null,"abstract":"Parkinson's Disease is a progressive neurodegenerative disorder of movement that affects your ability to control movement. This disease can prove fatal if not detected at an earlier stage. Motor and non-motor symptoms are raised by the loss of dopamine-producing neurons. Currently, there is no test available to detect disease at early stages where the symptoms may be poorly characterised. Handwriting analysis is one of the traditional aspects of studying human personality and also can be used to identify the symptoms of this disease. Identifying such accurate biomarkers provides roots for better clinical diagnosis. In this paper, we proposed a system that makes use of two types of handwriting analysis, spiral and wave drawings of healthy as well as Parkinson's patients as an input to the system. For feature extraction, we are using a histogram of the oriented gradient. The developed system uses a machine learning algorithm and a random forest classifier for the detection of Parkinson's disease among patients. Our model achieved an accuracy of 86.67 % in the case of spiral drawing and 83.30% with wave drawing.","PeriodicalId":43061,"journal":{"name":"International Journal of Data Mining Modelling and Management","volume":"351 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135468201","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 : 2023-03-02DOI: 10.46610/jodmm.2023.v08i01.003
Rakshith M D
The smart home environment is embedded with technologies like machine learning, deep learning artificial intelligence and internet of things. The services intended by the resident are provided by the smart home environment through interactions with the home appliances. In recent years, predicting user intention and behaviour in real-time applications like e-commerce, smart home, and entertainment, healthcare has appeared as a popular research domain. Contextual modalities such as speech, activity, emotion, object affordances, and physiological parameters are the features through which the intention of the resident can be predicted concerning the home appliances like door, television, light, etc. Other examples of contextual modalities include gesture and mood. Home appliances can be made smart by embedding intelligent algorithms which in turn helps them to understand the residents' intentions. This creates a dynamic relationship between the resident & home appliances thereby improving the resident’s satisfaction level. For example, the context: Resident issuing the command ‘OPEN’ by standing in front of the door illustrates that the intention is to get the door opened automatically. Contextual modalities are the main source for a system that works based on resident intention prediction. In this paper, an effort has been made to predict the resident intentions by applying machine learning algorithms like Decision Tree-based ID3, Naive Bayes classifier, and Rule-based classifier on context-aware door dataset.
{"title":"Predicting Resident Intention Using Machine Learning","authors":"Rakshith M D","doi":"10.46610/jodmm.2023.v08i01.003","DOIUrl":"https://doi.org/10.46610/jodmm.2023.v08i01.003","url":null,"abstract":"The smart home environment is embedded with technologies like machine learning, deep learning artificial intelligence and internet of things. The services intended by the resident are provided by the smart home environment through interactions with the home appliances. In recent years, predicting user intention and behaviour in real-time applications like e-commerce, smart home, and entertainment, healthcare has appeared as a popular research domain. Contextual modalities such as speech, activity, emotion, object affordances, and physiological parameters are the features through which the intention of the resident can be predicted concerning the home appliances like door, television, light, etc. Other examples of contextual modalities include gesture and mood. Home appliances can be made smart by embedding intelligent algorithms which in turn helps them to understand the residents' intentions. This creates a dynamic relationship between the resident & home appliances thereby improving the resident’s satisfaction level. For example, the context: Resident issuing the command ‘OPEN’ by standing in front of the door illustrates that the intention is to get the door opened automatically. Contextual modalities are the main source for a system that works based on resident intention prediction. In this paper, an effort has been made to predict the resident intentions by applying machine learning algorithms like Decision Tree-based ID3, Naive Bayes classifier, and Rule-based classifier on context-aware door dataset.","PeriodicalId":43061,"journal":{"name":"International Journal of Data Mining Modelling and Management","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135479464","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 : 2023-03-02DOI: 10.46610/jodmm.2022.v08i01.003
Rakshith M D
The smart home environment is embedded with technologies like machine learning, deep learning artificial intelligence and internet of things. The services intended by the resident are provided by the smart home environment through interactions with the home appliances. In recent years, predicting user intention and behaviour in real-time applications like e-commerce, smart home, and entertainment, healthcare has appeared as a popular research domain. Contextual modalities such as speech, activity, emotion, object affordances, and physiological parameters are the features through which the intention of the resident can be predicted concerning the home appliances like door, television, light, etc. Other examples of contextual modalities include gesture and mood. Home appliances can be made smart by embedding intelligent algorithms which in turn helps them to understand the residents' intentions. This creates a dynamic relationship between the resident & home appliances thereby improving the resident’s satisfaction level. For example, the context: Resident issuing the command ‘OPEN’ by standing in front of the door illustrates that the intention is to get the door opened automatically. Contextual modalities are the main source for a system that works based on resident intention prediction. In this paper, an effort has been made to predict the resident intentions by applying machine learning algorithms like Decision Tree-based ID3, Naive Bayes classifier, and Rule-based classifier on context-aware door dataset.
{"title":"Predicting Resident Intention Using Machine Learning","authors":"Rakshith M D","doi":"10.46610/jodmm.2022.v08i01.003","DOIUrl":"https://doi.org/10.46610/jodmm.2022.v08i01.003","url":null,"abstract":"The smart home environment is embedded with technologies like machine learning, deep learning artificial intelligence and internet of things. The services intended by the resident are provided by the smart home environment through interactions with the home appliances. In recent years, predicting user intention and behaviour in real-time applications like e-commerce, smart home, and entertainment, healthcare has appeared as a popular research domain. Contextual modalities such as speech, activity, emotion, object affordances, and physiological parameters are the features through which the intention of the resident can be predicted concerning the home appliances like door, television, light, etc. Other examples of contextual modalities include gesture and mood. Home appliances can be made smart by embedding intelligent algorithms which in turn helps them to understand the residents' intentions. This creates a dynamic relationship between the resident & home appliances thereby improving the resident’s satisfaction level. For example, the context: Resident issuing the command ‘OPEN’ by standing in front of the door illustrates that the intention is to get the door opened automatically. Contextual modalities are the main source for a system that works based on resident intention prediction. In this paper, an effort has been made to predict the resident intentions by applying machine learning algorithms like Decision Tree-based ID3, Naive Bayes classifier, and Rule-based classifier on context-aware door dataset.","PeriodicalId":43061,"journal":{"name":"International Journal of Data Mining Modelling and Management","volume":"23 1","pages":""},"PeriodicalIF":0.5,"publicationDate":"2023-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85960604","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 : 2023-01-24DOI: 10.46610/jodmm.2023.v08i01.002
N. Ranjan, R. Prasad
The exponential growth of unstructured data is one of the most critical challenges in data mining, text analytics, or data analytics. Around 80% of the world's data are available in unstructured format and most are left unattended due to the complexity of its analysis. It is a great challenge to guarantee the quality of the text document classifier that classifies documents based on user preferences because of large-scale terms and data patterns. The World Wide Web is growing rapidly and the availability of electronic documents is also increasing. Therefore, the automatic categorization of documents is the key factor for the systematic organization of information and knowledge discovery. Most existing widespread text mining and classification strategies have adopted term-based approaches. However, the problems of polysemy and synonymy in such approaches are of great concern. To classify documents based on their context, the context-based approach is needed to be followed. Semantic analysis of the text overcomes the limitations of the term-based approach and it also enhances the accuracy of the classifiers. This paper aims to highlight the important algorithms, techniques, and methodologies that can be used for text document classification. Furthermore, the paper also provides a review of the different stages of Text Document Classification.
{"title":"A Brief Survey of Text Document Classification Algorithms and Processes","authors":"N. Ranjan, R. Prasad","doi":"10.46610/jodmm.2023.v08i01.002","DOIUrl":"https://doi.org/10.46610/jodmm.2023.v08i01.002","url":null,"abstract":"The exponential growth of unstructured data is one of the most critical challenges in data mining, text analytics, or data analytics. Around 80% of the world's data are available in unstructured format and most are left unattended due to the complexity of its analysis. It is a great challenge to guarantee the quality of the text document classifier that classifies documents based on user preferences because of large-scale terms and data patterns. The World Wide Web is growing rapidly and the availability of electronic documents is also increasing. Therefore, the automatic categorization of documents is the key factor for the systematic organization of information and knowledge discovery. Most existing widespread text mining and classification strategies have adopted term-based approaches. However, the problems of polysemy and synonymy in such approaches are of great concern. To classify documents based on their context, the context-based approach is needed to be followed. Semantic analysis of the text overcomes the limitations of the term-based approach and it also enhances the accuracy of the classifiers. This paper aims to highlight the important algorithms, techniques, and methodologies that can be used for text document classification. Furthermore, the paper also provides a review of the different stages of Text Document Classification.","PeriodicalId":43061,"journal":{"name":"International Journal of Data Mining Modelling and Management","volume":"61 4 1","pages":""},"PeriodicalIF":0.5,"publicationDate":"2023-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79768552","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 : 2023-01-01DOI: 10.1504/ijdmmm.2023.10055078
R. Agjei, O. S. Dada, T. O. Omotehinwa, O. S. Balogun, Frank Adusei Mensah, D. Atsa’am, S. N. O. Devine
{"title":"A Novel Taxonomy of Natural Disasters based on Casualty and Consequence using Hierarchical Clustering","authors":"R. Agjei, O. S. Dada, T. O. Omotehinwa, O. S. Balogun, Frank Adusei Mensah, D. Atsa’am, S. N. O. Devine","doi":"10.1504/ijdmmm.2023.10055078","DOIUrl":"https://doi.org/10.1504/ijdmmm.2023.10055078","url":null,"abstract":"","PeriodicalId":43061,"journal":{"name":"International Journal of Data Mining Modelling and Management","volume":"4 1","pages":"313-330"},"PeriodicalIF":0.5,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73464773","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 : 2023-01-01DOI: 10.1504/ijdmmm.2023.134590
Alaa Khalaf Hamoud, Ali Salah Alasady, Wid Akeel Awadh, Jasim Mohammed Dahr, Mohammed B.M. Kamel, Aqeel Majeed Humadi, Ihab Ahmed Najm
The field of educational data mining (EDM) is one of the most growing fields that aims to improve the performance of students, academic staff, and overall institutional performance. The implementing process of data mining algorithms almost needs the feature selection process to find the most correlated features and improve the accuracy. In this paper, a comparative study is performed to study implementation of supervised/unsupervised algorithms in predicting the students' performance. The student's grade is classified using different fields of supervised and unsupervised algorithms such as decision trees, clustering, and neural networks. These algorithms were examined over the questionnaire dataset before/after feature selection to measure the effect of feature selection on the result accuracy. The results showed that the random forest decision tree outperformed other supervised/unsupervised algorithms. The results also showed that the performance evaluation of algorithms with the dataset after removing the less correlated attributes is enhanced for most of the algorithms.
{"title":"A comparative study of supervised/unsupervised machine learning algorithms with feature selection approaches to predict student performance","authors":"Alaa Khalaf Hamoud, Ali Salah Alasady, Wid Akeel Awadh, Jasim Mohammed Dahr, Mohammed B.M. Kamel, Aqeel Majeed Humadi, Ihab Ahmed Najm","doi":"10.1504/ijdmmm.2023.134590","DOIUrl":"https://doi.org/10.1504/ijdmmm.2023.134590","url":null,"abstract":"The field of educational data mining (EDM) is one of the most growing fields that aims to improve the performance of students, academic staff, and overall institutional performance. The implementing process of data mining algorithms almost needs the feature selection process to find the most correlated features and improve the accuracy. In this paper, a comparative study is performed to study implementation of supervised/unsupervised algorithms in predicting the students' performance. The student's grade is classified using different fields of supervised and unsupervised algorithms such as decision trees, clustering, and neural networks. These algorithms were examined over the questionnaire dataset before/after feature selection to measure the effect of feature selection on the result accuracy. The results showed that the random forest decision tree outperformed other supervised/unsupervised algorithms. The results also showed that the performance evaluation of algorithms with the dataset after removing the less correlated attributes is enhanced for most of the algorithms.","PeriodicalId":43061,"journal":{"name":"International Journal of Data Mining Modelling and Management","volume":"2015 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135263322","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 : 2023-01-01DOI: 10.1504/ijdmmm.2023.134591
Donald Douglas Atsa', N.A. am, Frank Adusei Mensah, Oluwafemi Samson Balogun, Temidayo Oluwatosin Omotehinwa, Oluwaseun Alexander Dada, Richard Osei Agjei, Samuel Nii Odoi Devine
Post-disaster management requires a proportional deployment of human and material resources. The number of resources required to manage a disaster cannot be known without first evaluating the extent of casualty and consequence. This study proposed a taxonomy for classifying natural disasters based on casualty and consequence. Using a secondary data on global disasters from 1900 to 2021, the hierarchical cluster analysis technique was deployed for taxonomy formation. The learning algorithm evaluated the similarities in numbers of deaths, injuries, and the cost of damaged property caused by disasters. Three clusters were extracted which sub-grouped historical disasters based on similarities in casualty and consequence. Further, a taxonomy that defines the ranges of what constitute low, average, and high deaths/injuries/damage was established. Classifying a future disaster with this taxonomy prior to the deployment of resources for rescue, resettlement, compensation, and other disaster management operations will guide efficient resource allocation on a case-by-case basis.
{"title":"A novel taxonomy of natural disasters based on casualty and consequence using hierarchical clustering","authors":"Donald Douglas Atsa', N.A. am, Frank Adusei Mensah, Oluwafemi Samson Balogun, Temidayo Oluwatosin Omotehinwa, Oluwaseun Alexander Dada, Richard Osei Agjei, Samuel Nii Odoi Devine","doi":"10.1504/ijdmmm.2023.134591","DOIUrl":"https://doi.org/10.1504/ijdmmm.2023.134591","url":null,"abstract":"Post-disaster management requires a proportional deployment of human and material resources. The number of resources required to manage a disaster cannot be known without first evaluating the extent of casualty and consequence. This study proposed a taxonomy for classifying natural disasters based on casualty and consequence. Using a secondary data on global disasters from 1900 to 2021, the hierarchical cluster analysis technique was deployed for taxonomy formation. The learning algorithm evaluated the similarities in numbers of deaths, injuries, and the cost of damaged property caused by disasters. Three clusters were extracted which sub-grouped historical disasters based on similarities in casualty and consequence. Further, a taxonomy that defines the ranges of what constitute low, average, and high deaths/injuries/damage was established. Classifying a future disaster with this taxonomy prior to the deployment of resources for rescue, resettlement, compensation, and other disaster management operations will guide efficient resource allocation on a case-by-case basis.","PeriodicalId":43061,"journal":{"name":"International Journal of Data Mining Modelling and Management","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135263346","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：