Anitha Dhakshina Moorthy
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Anitha Dhakshina Moorthy has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Dhakshina Moorthy Kavitha
Department of EEE, Thiagarajar College of Engineering, Madurai, India
3 shared publications - Srimathi Suresh Babu
Department of Applied Mathematics and Computational Science, Thiagarajar College of Enigneering
2 shared publications - Betsybha Evangeline
Thiagarajar College of Engineering, India
1 shared publication - Deisy Chelliah
Thiagarajar College of Engineering
1 shared publication - Jeyamala Chandrasekaran
Thiagarajar College of Engineering
1 shared publication Kavitha Dhakshinamoorthy
Department of Electrical and Electronics Engineering Thiagarajar College of Engineering Madurai Tamil Nadu India
1 shared publication
Latest Publications
- 2 December 2024
- Published by Taylor & Francis
- p. 74-99
Instructional Design with Artificial Intelligence Tools to Support Student-Centered Learning
“We are teaching… Are they learning?” This is the million-dollar question asked by all pedagogy experts. Students who desire to learn, passionate in gaining knowledge, listen keenly to the teacher and try their best in learning. But, unfortunately, now they have many distractions and now it has become the teacher’s role to frame strategies to make them listen and learn. The ARCS model of motivation provides all overall required components to implement student-centered learning. Implementing the ARCS model in regular class demands much time, and pedagogical and content knowledge from the teacher. Hence, technology-aided planning is required. In the current scenario of artificial intelligence, ChatGPT stands as a remarkable indicator of cutting-edge technology that bridges the gap between human communication and machine understanding. This proposal explains an experiment conducted in a class using the ARCS model developed using AI tools particularly, ChatGPT. This chapter discusses the use of ChatGPT for teachers to plan their content delivery for the ARCS model of motivation. ChatGPT is used by teachers to plan activities. it is used also by students to study certain topics and complete some tasks in and out of class.
- 2 December 2024
- Published by Taylor & Francis
- p. 74-99
Instructional Design with Artificial Intelligence Tools to Support Student-Centered Learning
“We are teaching… Are they learning?” This is the million-dollar question asked by all pedagogy experts. Students who desire to learn, passionate in gaining knowledge, listen keenly to the teacher and try their best in learning. But, unfortunately, now they have many distractions and now it has become the teacher’s role to frame strategies to make them listen and learn. The ARCS model of motivation provides all overall required components to implement student-centered learning. Implementing the ARCS model in regular class demands much time, and pedagogical and content knowledge from the teacher. Hence, technology-aided planning is required. In the current scenario of artificial intelligence, ChatGPT stands as a remarkable indicator of cutting-edge technology that bridges the gap between human communication and machine understanding. This proposal explains an experiment conducted in a class using the ARCS model developed using AI tools particularly, ChatGPT. This chapter discusses the use of ChatGPT for teachers to plan their content delivery for the ARCS model of motivation. ChatGPT is used by teachers to plan activities. it is used also by students to study certain topics and complete some tasks in and out of class.
- 2 December 2024
- Published by Taylor & Francis
- p. 291-316
Dynamic Horizon
The educational system has evolved to incorporate innovative methods like e-learning, which allows for learning anytime and anywhere but often struggles with student engagement. Gamification has emerged as an effective teaching strategy that uses game-like elements in nongaming contexts to captivate students. Enabled by artificial intelligence (AI), dynamic gamified learning environments aim to improve learning outcomes, enhance engagement, and offer adaptive experiences tailored to individual needs. Despite its potential, the integration of AI and gamification faces resistance from educators and administrators skeptical of its effectiveness. Overcoming these challenges requires comprehensive training, pilot projects, clear standards, and robust data protection to address ethical concerns. Incremental investments in modular solutions and partnerships with EdTech companies can help manage financial and technical constraints. Gamification enhances engagement through interactive elements like badges and competitions, while AI provides personalized learning by analyzing student data, identifying at-risk pupils, and preparing them for future workforce demands. This chapter presents a consolidated report on the integration of AI and gamification with real-time case studies and promising solutions to the challenges addressed.
- 2 December 2024
- Published by Taylor & Francis
- p. 291-316
Dynamic Horizon
The educational system has evolved to incorporate innovative methods like e-learning, which allows for learning anytime and anywhere but often struggles with student engagement. Gamification has emerged as an effective teaching strategy that uses game-like elements in nongaming contexts to captivate students. Enabled by artificial intelligence (AI), dynamic gamified learning environments aim to improve learning outcomes, enhance engagement, and offer adaptive experiences tailored to individual needs. Despite its potential, the integration of AI and gamification faces resistance from educators and administrators skeptical of its effectiveness. Overcoming these challenges requires comprehensive training, pilot projects, clear standards, and robust data protection to address ethical concerns. Incremental investments in modular solutions and partnerships with EdTech companies can help manage financial and technical constraints. Gamification enhances engagement through interactive elements like badges and competitions, while AI provides personalized learning by analyzing student data, identifying at-risk pupils, and preparing them for future workforce demands. This chapter presents a consolidated report on the integration of AI and gamification with real-time case studies and promising solutions to the challenges addressed.
- 25 November 2024
- Published by Emerald Publishing in Journal of Applied Research in Higher Education
- Vol. 17 (6) , 2307-2329
PSFAS: Progressive Student Feedback Analysis System for improved teaching learning with intelligent processing of open-responses
Purpose: Student open feedback is an essential element to improve the teaching service. Comprehending the feedback collected daily may not be possible especially in a large classroom. There is needed an automated system that processes feedback and helps to recommend focused, precise points to the teacher stating the positives and negatives of a class. Also, the feedback texts are neither going to be grammatically correct nor going to consist only of English. Hence, an automated feedback processing system is essential that processes the mixed-language language text that provides crisp clear insights to the teachers, thus making effective student–teacher interaction. Design/methodology/approach: This research is designed to analyse daily feedback from the students in grammarless English-Tamil mixed feedback and creates a dashboard that displays concise keywords regarding positive and negative aspects of the class. An ML-based system architecture is proposed for processing English-Tamil mixed grammarless feedback texts and validates the same with an experimental prototype and compares the results with other state-of-the-art models. This prototype classifies the text into different categories and provides the concise view with topic modelling techniques. This system is useful in progressive improvement of teaching learning process, subsequently leading to better teaching learning environment. Findings: The proposed web-based architecture is validated with a prototype by comparing the results with other state-of-the-art models. The accuracy of the results is higher (>90%) in the proposed architecture than other models (<60%). The created teacher dashboard is highly recommendable and provides day-to-day recommendation for finetuning teaching and learning process. The web-based dashboard created for teachers enables them to interpret the student feedback with much ease due to the Machine learning algorithms used in implementing the web-based solution. Research limitations/implications: This system is designed to help the teachers to improve themselves in the teaching learning process with the feedback. The proposed system is a prototype that is initially tested with sample feedback texts obtained in sessions in postgraduate classrooms. The implementation of the prototype and analysis of teacher and student experience are presented as the immediate scope of this research work. This helps the teachers to get an overall view on the best teaching practices and what to improve. This work currently uses Bidirectional Encoder Representations from Transformers (BERT) uncased and in the increase of native language text the system may work with BERT multilingual. Practical implications: This prototype will be implemented as a web-mobile based application. Students can submit their daily feedback through a mobile app, while teachers will access a dashboard that presents a concise overview generated by the proposed system architecture. The dashboard will also provide trend analysis, highlighting positive and negative aspects of the sessions. The system's effectiveness will be evaluated through a qualitative study, incorporating feedback from teachers and insights from students. This evaluation will help teachers gain a comprehensive understanding of the most effective teaching practices and areas needing improvement, thereby enhancing the teaching-learning process. The web-mobile application aims to Streamline the feedback process, making it easy for students to share their thoughts and for teachers to receive actionable insights. This study offers a clear and concise summary of student feedback and trend analysis from which the teachers can quickly identify patterns and make necessary adjustments to their teaching methods. Ultimately, this approach will foster a more responsive and effective educational environment, supporting continuous improvement and better student–teacher interactions. Further, the proposed system requires lesser technical knowledge and can be used by anyone. Social implications: A literature review has identified a critical need for a feedback processing system that functions at short intervals. Such a system is essential for providing teachers with concise, periodic summaries of students' open-ended feedback, which is vital for fostering continuous improvement in the teaching-learning process. The immediate processing of feedback, particularly when it contains English-mixed texts, is crucial for making timely adjustments that enhance both student performance and experience. By swiftly addressing concerns and reinforcing positive feedback, the system will improve student–teacher interactions, provide meaningful insights that contribute to progressive educational growth. This will help implement a feedback system that operates in these short intervals and allows for real-time monitoring and response to students' needs and experiences. Additionally, by highlighting areas of success, teachers can build on effective strategies and practices. Originality/value: This research paper proposes a system architecture PSFAS: Progressive Student Feedback Analysis System with Multi Level Classification and Clustering that enables effective interaction between the student and the teacher with the findings from feedback and presenting an experimental prototype that can be incorporated into the regular teaching learning process, whether online or offline. It has been found from the literature review, that feedback processing is mostly done in the English language. This work proposes a system architecture that gives higher accuracy than other state-of-the art models for feedback texts having English-mix grammarless sentences.
- 25 November 2024
- Published by Emerald Publishing in Journal of Applied Research in Higher Education
- Vol. 17 (6) , 2307-2329
PSFAS: Progressive Student Feedback Analysis System for improved teaching learning with intelligent processing of open-responses
Purpose: Student open feedback is an essential element to improve the teaching service. Comprehending the feedback collected daily may not be possible especially in a large classroom. There is needed an automated system that processes feedback and helps to recommend focused, precise points to the teacher stating the positives and negatives of a class. Also, the feedback texts are neither going to be grammatically correct nor going to consist only of English. Hence, an automated feedback processing system is essential that processes the mixed-language language text that provides crisp clear insights to the teachers, thus making effective student–teacher interaction. Design/methodology/approach: This research is designed to analyse daily feedback from the students in grammarless English-Tamil mixed feedback and creates a dashboard that displays concise keywords regarding positive and negative aspects of the class. An ML-based system architecture is proposed for processing English-Tamil mixed grammarless feedback texts and validates the same with an experimental prototype and compares the results with other state-of-the-art models. This prototype classifies the text into different categories and provides the concise view with topic modelling techniques. This system is useful in progressive improvement of teaching learning process, subsequently leading to better teaching learning environment. Findings: The proposed web-based architecture is validated with a prototype by comparing the results with other state-of-the-art models. The accuracy of the results is higher (>90%) in the proposed architecture than other models (<60%). The created teacher dashboard is highly recommendable and provides day-to-day recommendation for finetuning teaching and learning process. The web-based dashboard created for teachers enables them to interpret the student feedback with much ease due to the Machine learning algorithms used in implementing the web-based solution. Research limitations/implications: This system is designed to help the teachers to improve themselves in the teaching learning process with the feedback. The proposed system is a prototype that is initially tested with sample feedback texts obtained in sessions in postgraduate classrooms. The implementation of the prototype and analysis of teacher and student experience are presented as the immediate scope of this research work. This helps the teachers to get an overall view on the best teaching practices and what to improve. This work currently uses Bidirectional Encoder Representations from Transformers (BERT) uncased and in the increase of native language text the system may work with BERT multilingual. Practical implications: This prototype will be implemented as a web-mobile based application. Students can submit their daily feedback through a mobile app, while teachers will access a dashboard that presents a concise overview generated by the proposed system architecture. The dashboard will also provide trend analysis, highlighting positive and negative aspects of the sessions. The system's effectiveness will be evaluated through a qualitative study, incorporating feedback from teachers and insights from students. This evaluation will help teachers gain a comprehensive understanding of the most effective teaching practices and areas needing improvement, thereby enhancing the teaching-learning process. The web-mobile application aims to Streamline the feedback process, making it easy for students to share their thoughts and for teachers to receive actionable insights. This study offers a clear and concise summary of student feedback and trend analysis from which the teachers can quickly identify patterns and make necessary adjustments to their teaching methods. Ultimately, this approach will foster a more responsive and effective educational environment, supporting continuous improvement and better student–teacher interactions. Further, the proposed system requires lesser technical knowledge and can be used by anyone. Social implications: A literature review has identified a critical need for a feedback processing system that functions at short intervals. Such a system is essential for providing teachers with concise, periodic summaries of students' open-ended feedback, which is vital for fostering continuous improvement in the teaching-learning process. The immediate processing of feedback, particularly when it contains English-mixed texts, is crucial for making timely adjustments that enhance both student performance and experience. By swiftly addressing concerns and reinforcing positive feedback, the system will improve student–teacher interactions, provide meaningful insights that contribute to progressive educational growth. This will help implement a feedback system that operates in these short intervals and allows for real-time monitoring and response to students' needs and experiences. Additionally, by highlighting areas of success, teachers can build on effective strategies and practices. Originality/value: This research paper proposes a system architecture PSFAS: Progressive Student Feedback Analysis System with Multi Level Classification and Clustering that enables effective interaction between the student and the teacher with the findings from feedback and presenting an experimental prototype that can be incorporated into the regular teaching learning process, whether online or offline. It has been found from the literature review, that feedback processing is mostly done in the English language. This work proposes a system architecture that gives higher accuracy than other state-of-the art models for feedback texts having English-mix grammarless sentences.
- 18 September 2024
- Published by Springer Nature
- p. 321-331
A Comprehensive Review on Augmentative and Alternative Communication Tools for Speech-Impaired Individuals
- 18 September 2024
- Published by Springer Nature
- p. 321-331
A Comprehensive Review on Augmentative and Alternative Communication Tools for Speech-Impaired Individuals
- Top Cited Papers
- 27 September 2023
- Published by Wiley in Computer Applications in Engineering Education
- Vol. 32 (1)
Application of artificial intelligence in adaptation of gamification in education: A literature review
The education system has been changing continuously with several new strategies for effective student learning. E‐learning has provided the opportunity for students to learn from anywhere and from anyone. To motivate the learners and improve their performance in e‐learning courses, different pedagogical activities have been practiced among which gamification has a good edge. Gamification is one of the upcoming fields in education for getting students motivated and engaged through game‐like activities with various gamification elements in nongame settings. Gamification can be further improved by dynamically adapting the mechanics and dynamics of gamification to a variety of factors such as the personality, needs, values, performance, and motivations of learners. The advancement of artificial intelligence (AI) enables the development of dynamically adapting gamification environments with established AI techniques. The application of AI in adaptive gamification needs to be further explored to discover new approaches. This study provides a comprehensive report of adaptive gamification from the perspective of the existing studies, which map different gamification elements, user profile elements, and intelligent techniques through a systematic literature analysis. Research questions have been formulated and the findings have been presented by exploring 29 focused studies from a selected pool of 622 research articles. The findings have identified the commonly used gamification elements and presented the methods of incorporating them with various AI techniques based on different user profile elements.
- 27 September 2023
- Published by Wiley in Computer Applications in Engineering Education
- Vol. 32 (1)
Top Cited PapersApplication of artificial intelligence in adaptation of gamification in education: A literature review
The education system has been changing continuously with several new strategies for effective student learning. E‐learning has provided the opportunity for students to learn from anywhere and from anyone. To motivate the learners and improve their performance in e‐learning courses, different pedagogical activities have been practiced among which gamification has a good edge. Gamification is one of the upcoming fields in education for getting students motivated and engaged through game‐like activities with various gamification elements in nongame settings. Gamification can be further improved by dynamically adapting the mechanics and dynamics of gamification to a variety of factors such as the personality, needs, values, performance, and motivations of learners. The advancement of artificial intelligence (AI) enables the development of dynamically adapting gamification environments with established AI techniques. The application of AI in adaptive gamification needs to be further explored to discover new approaches. This study provides a comprehensive report of adaptive gamification from the perspective of the existing studies, which map different gamification elements, user profile elements, and intelligent techniques through a systematic literature analysis. Research questions have been formulated and the findings have been presented by exploring 29 focused studies from a selected pool of 622 research articles. The findings have identified the commonly used gamification elements and presented the methods of incorporating them with various AI techniques based on different user profile elements.
- 4 September 2020
- Published by Wiley in Computer Applications in Engineering Education
- Vol. 28 (6) , 1580-1590
Online coding event as a formative assessment tool in introductory programming and algorithmic courses—An exploration study
Information technology is an integral part of current education, even in noncomputer disciplines. As the role of Information technology‐based education tools is recognized as significant in the education of millennial learners, there is a development of different types of tools and techniques in education. Usage of such tools in content delivery and assessment has been found to improve student engagement and active learning. When looking for unique tools to practice and assess computer programming and algorithmic courses, online coding events launched by popular forums have been identified as a tool for practice and assessment. These forums have been introducing new computing problems specified in a professional language, so that students get trained in programming these complex problems rather than the conventional problems. This article explores the possibility and success measure of integrating online coding events as a part of formative assessment. A study has been performed with two consecutive offerings of a course. The results obtained from the various forms of assessment are analyzed and presented in terms of correlation with summative and formative assessment scores and improved student performance. The results of the experimental study are found encouraging, thereby appreciating the usage of online coding platforms for introductory programming and algorithmic courses.
- 4 September 2020
- Published by Wiley in Computer Applications in Engineering Education
- Vol. 28 (6) , 1580-1590
Online coding event as a formative assessment tool in introductory programming and algorithmic courses—An exploration study
Information technology is an integral part of current education, even in noncomputer disciplines. As the role of Information technology‐based education tools is recognized as significant in the education of millennial learners, there is a development of different types of tools and techniques in education. Usage of such tools in content delivery and assessment has been found to improve student engagement and active learning. When looking for unique tools to practice and assess computer programming and algorithmic courses, online coding events launched by popular forums have been identified as a tool for practice and assessment. These forums have been introducing new computing problems specified in a professional language, so that students get trained in programming these complex problems rather than the conventional problems. This article explores the possibility and success measure of integrating online coding events as a part of formative assessment. A study has been performed with two consecutive offerings of a course. The results obtained from the various forms of assessment are analyzed and presented in terms of correlation with summative and formative assessment scores and improved student performance. The results of the experimental study are found encouraging, thereby appreciating the usage of online coding platforms for introductory programming and algorithmic courses.
- 30 October 2018
- Published by Wiley in Computer Applications in Engineering Education
- Vol. 27 (2) , 319-331
KLSAS—An adaptive dynamic learning environment based on knowledge level and learning style
Adaptive learning environment, the extension of E‐learning, has gained its importance in the present education scenario with the growth in information and communication technology. To develop such an environment, suitable learner characteristics have to be selected and learning materials are to be adapted to the selected characteristics with intelligent mechanisms. The effectiveness of the adaptive systems improves with increased number of learner characteristics considered to build the systems. However, the observations from the existing adaptive systems reveal that the development of systems that adapts to more than one learner characteristic is more challenging than systems that adapt to single learner characteristic. This paper proposes an adaptive learning system, KLSAS: Knowledge and Learning Style based Adaptive System, which is based on two significant learner characteristics, knowledge level and learning style. The adaptation model of KLSAS is proposed as a dynamic system which updates itself with learner performance and preferences. The evaluation of the system is done through the test performance of two different set of learners. The results are encouraging and ensuring that the adaptive strategy based on the selected learner characteristics leads to improvement in learning.
- 30 October 2018
- Published by Wiley in Computer Applications in Engineering Education
- Vol. 27 (2) , 319-331
KLSAS—An adaptive dynamic learning environment based on knowledge level and learning style
Adaptive learning environment, the extension of E‐learning, has gained its importance in the present education scenario with the growth in information and communication technology. To develop such an environment, suitable learner characteristics have to be selected and learning materials are to be adapted to the selected characteristics with intelligent mechanisms. The effectiveness of the adaptive systems improves with increased number of learner characteristics considered to build the systems. However, the observations from the existing adaptive systems reveal that the development of systems that adapts to more than one learner characteristic is more challenging than systems that adapt to single learner characteristic. This paper proposes an adaptive learning system, KLSAS: Knowledge and Learning Style based Adaptive System, which is based on two significant learner characteristics, knowledge level and learning style. The adaptation model of KLSAS is proposed as a dynamic system which updates itself with learner performance and preferences. The evaluation of the system is done through the test performance of two different set of learners. The results are encouraging and ensuring that the adaptive strategy based on the selected learner characteristics leads to improvement in learning.
- 5 October 2015
- Published by SAGE Publications in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
- Vol. 29 (2) , 539-552
Proposing a novel approach for classification and sequencing ofLearning Objects in E-learning systems based on learning style
Learning is a cognitive activity which differs from person to person and hence needs personalization. When learning is performed online, the system needs to understand various traits of learner and deliver Learning Objects (LO) suitable for them to achieve personalization. Many research works have been developing personalization strategies based on various learner traits such as knowledge level, learner characteristics and preferences. However, there are quite few works which consider the relationship between the learner traits and the attributes of LOs that are defined by major standards. This paper focuses on personalization strategy based on Felder and Silverman learning model and proposes a novel approach for classifying and sequencing learning objects according to the learning styles adhering to IEEE LOM metadata standard. The learning styles of the learners are identified and a fuzzy classification scheme maps the IEEE LOM Metadata to the identified learning styles. A pilot study on the research work is performed and the evaluation of the system has given an encouraging result.
- 5 October 2015
- Published by SAGE Publications in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
- Vol. 29 (2) , 539-552
Proposing a novel approach for classification and sequencing ofLearning Objects in E-learning systems based on learning style
Learning is a cognitive activity which differs from person to person and hence needs personalization. When learning is performed online, the system needs to understand various traits of learner and deliver Learning Objects (LO) suitable for them to achieve personalization. Many research works have been developing personalization strategies based on various learner traits such as knowledge level, learner characteristics and preferences. However, there are quite few works which consider the relationship between the learner traits and the attributes of LOs that are defined by major standards. This paper focuses on personalization strategy based on Felder and Silverman learning model and proposes a novel approach for classifying and sequencing learning objects according to the learning styles adhering to IEEE LOM metadata standard. The learning styles of the learners are identified and a fuzzy classification scheme maps the IEEE LOM Metadata to the identified learning styles. A pilot study on the research work is performed and the evaluation of the system has given an encouraging result.