Jegatha Deborah L - Academia.edu (original) (raw)

Papers by Jegatha Deborah L

2017 Second International Conference on Recent Trends and Challenges in Computational Models (ICRTCCM), 2017

This paper addresses a simple, easy to implement method for calculating the geographical area of ... more This paper addresses a simple, easy to implement method for calculating the geographical area of a place on the map using the Shoelace Algorithm. The procedure basically involves placing the Longitudes and Latitudes of the polygon for which the area needs to be found into the technique and obtain its area.

Journal of Systems Architecture, 2021

Abstract Internet of Things (IoT) is a network convergence of multiple intelligent devices and ad... more Abstract Internet of Things (IoT) is a network convergence of multiple intelligent devices and advanced technologies aiming at connecting and exchanging data over the Internet. IoT is extensively applied in consumer, commercial, industrial, infrastructure and military spaces. With the prevalence of IoT applications, security issues such as identity authenticity and data privacy are increasingly become critical concerns. Authentication and confidential data sharing are the important measures towards secure IoT communication and applications. Blockchain is a burgeoning technology supporting for efficient authentication and secure data sharing. A secure and accountable data transmission scheme based on blockchain has been proposed by Hong et al. recently. But this scheme has security weaknesses of impersonation attack, man-in-the-middle attack, replay attack, denial of service attack (DoS) and key compromise attack. Thus we put forward an improved scheme to overcome the identified security flaws. Our scheme is provably secure and performance analysis shows that our scheme reduces 15.34% computation costs and 40.68% communication costs compared with Hong et al.’s scheme. Meanwhile, we also compare our scheme with other three recent and related researches, which finally indicates that our scheme realizes a well tradeoff between security and efficiency.

Handbook of Computational Intelligence in Biomedical Engineering and Healthcare, 2021

Abstract Protracted driving causes physical mental stress that increases life in higher-risk stat... more Abstract Protracted driving causes physical mental stress that increases life in higher-risk state and it takes health to all negative issues. Spending more time on driving a vehicle governs a long, uninterrupted session that leads to obesity, risk to mental health, lack of sleep, bad habits like addictions have changed the quality of life. In this research work, a reliable emergency service ensures a safe driving experience. Such experience guarantees the continual monitoring of the driver's health condition in smart manner. In order to monitor the driver's heart rate, an intelligent healthcare system is proposed that utilizes an artificial recurrent neural network (RNN) model which continually monitors driver's health condition and persistently update to the cloud server. However, tracking their health status is a complex task because health condition statuses are varied and hence this leads to the essential creation of optimized Electronic Health Record (EHR). To accomplish a reliable emergency service, the proposed proximity-based communication model transmits the critical condition record to the service providers even without Internet capability. The long-short term memory is capable of learning the driver's behavior continually in long-term decencies of his/her activity which converts sensor reading into optimized EHR. These health readings are generated from various external body sensors. The proposed work would be noticed as one step toward guaranteed guarded journey. The experimental results achieved 94.65% accuracy of higher prediction rate.

Traditionally, the web search engines return thousands of pages in response to a broad query,maki... more Traditionally, the web search engines return thousands of pages in response to a broad query,making it difficult for users to browse or to identify relevant information.For the purpose of quick access to the relevant information, clustering method is a better choice and can be used to automatically group the retrieved and relevant documents of the target domain.In this paper, a new method which combines the techniques of constrained and coclustering methods has been proposed. This combined approach achieves two goals: First, it combines information theoretic coclustering and constrained clustering to improve the clustering performance. Second, additionallythe unsupervised constraints are incorporated into the proposed method to demonstrate the effectiveness of the algorithm. To achieve this goal, a two-sided hidden Markov random field (HMRF) model is developed to represent both document and word constraints.The results of our evaluation over benchmark data sets exhibit that the proposed algorithm is superior compared to other existing approaches.

Multimedia Tools and Applications, 2021

Cervical cancer is one of the curable cancers when it is diagnosed in the early stages. Pap smear... more Cervical cancer is one of the curable cancers when it is diagnosed in the early stages. Pap smear test and visual inspection using acetic acid are the most common screening mechanism for the cervical lesion to categorize the cervical cells as normal, precancerous, or cancerous. However, most of the classification methods success depends on the accurate spotting and segmenting of cervical location. These challenges pave the way for sixty years of research in cervical cancer diagnosis, but still, accurate spotting of the cervical cell remains an open challenge. Moreover, state-of-the-art classification methods are developed based upon the extraction of manual annotations of features. In this paper, an effective hybrid deep learning technique using Small-Object Detection-Generative Adversarial Networks (SOD-GAN) with Fine-tuned Stacked Autoencoder (F-SAE) is developed to address the shortcomings mentioned above. The generator and discriminator of the SOD-GAN are developed using Region-based Convolutional Neural Network (RCNN). The model parameters are fine-tuned using F-SAE, and the hyperparameters of the SOD-GAN are normalized and optimized to make the lesion detection faster. The proposed approach automatically detects and classifies the cervical premalignant and malignant conditions based on deep features without any preliminary classification and segmentation assistance. Extensive experimentation has also been done with multivariate heterogeneous data, and the proposed approach has shown promising improvement in efficiency and reduces the time complexity.

International Journal of Internet Technology and Secured Transactions, 2017

Wi-Fi Mesh Community has turn out to be an important area community to offer internet to challeng... more Wi-Fi Mesh Community has turn out to be an important area community to offer internet to challenge the thrown domains and wireless link in metropolitan environments. In this paper, hassle of figuring out the most to be had bandwidth direction is targeted, which is an essential problem in helping pleasant-of-carrier in WMCs. Due to the concept of interference, bandwidth, which is a familiar challenging metric in restive networks, a new direction is validated in which the weight captures the available route bandwidth statistics. It is also proved that the hop using the hop routing procedure based on the new path weight completely satisfies the consistency and loop-freeness necessities. The property of consistency ensures that each node follows a proper packet forwarding choice, in order that a statistics packet traverses over the supposed path. The experimental results additionally show that our proposed work on direction weight outperforms all the other existing direction metrics in figuring out excessive-throughput paths.

2017 Second International Conference on Recent Trends and Challenges in Computational Models (ICRTCCM), 2017

In the recent times, the smart phones have become versatile that they are used for sensitive appl... more In the recent times, the smart phones have become versatile that they are used for sensitive applications such as m-banking, m-commerce, m-governance, m-health, digital marketing, SMS and have become a vital gadget to share posts in social networking applications such as Facebook, Twitter, WhatsApp and others. It is also used for online gaming, surfing, chatting and also used for storing the personal information like photos, videos, documents and other important files. In this scenario, it is no surprise that the basic demand for utilizing a smart phone is secure authentication. Though a number of authentication schemes have been proposed in the literature through PIN numbers, passwords and patterns, they are susceptible for shoulder surfing or smudging attacks. Thus, combing gestures with such authentication schemes prove to be more successful in the present times and hence a new kind of pattern has been proposed with essential gestures such as finger pressure and inclination of th...

2018 International Conference on Circuits and Systems in Digital Enterprise Technology (ICCSDET), 2018

Documents that are classified into different categories gets flooded in the internet every day. T... more Documents that are classified into different categories gets flooded in the internet every day. These documents have many links or associations with the other documents in the web. The terms in the document are open to multiple interpretations which are vague and unclear. Hence there is a need to find the semantic understanding of the terms. One of the major application in identifying and applying such semantic measure lies in clustering the related textual documents. However, the traditional clustering algorithms may exhibit reduced performances due to the existence of irrelevant terms in the raw documents. Hence, the proposed algorithm in this paper exploits the use of a feature selection algorithm in order to increase the performance of the clustering algorithm. In this paper, a feature selection algorithm with booster technique is used. Moreover, clustering algorithm based on a fuzzy linguistic variable measure that uses separation and dominance value is used in this paper for precise clustering. Experimental analysis shows that the three performance measures that evaluates the clustering algorithm increases, in comparison to the other existing algorithms.

An important criterion in teaching is to analyze how well the teaching has been effective for the... more An important criterion in teaching is to analyze how well the teaching has been effective for the student’s. In order to do such analysis student’s feedback is obtained which would depict the quality and quantity of teaching. The existing evaluation technique tells about the opinion levels but does not clearly inform is it necessary to bring immediate changes in teaching or can proceed with the current teaching strategy. To address this drawback an automated ideology is proposed to initially analyze the student feedback comments and further based on the analysis introduce a recommendation system that would give a clear idea whether to bring in changes or proceed with the currently adopted teaching technique. This would provide tutors insight about opinion and allow them to make professionally sound decision so as to upgrade the performance of students.

Learning Style is: “A particular way in which an individual learns”. Different kinds of learners ... more Learning Style is: “A particular way in which an individual learns”. Different kinds of learners are distinguished according to their learning styles based on the explicit characteristics shown by the learners, during the earlier period. The latent nature of the learners in addition to the explicit nature, addressed by most of the traditional learning style models also influences the learning style of an individual and such identification could provide better E-Learning framework in terms of content delivery. This paper categorizes new kind of learners: “Intelligent Learners” who are identified by two varying dimensions: Uncovering the latent attitude (Browsing History in an E-Learning server) in them and testing of linguistic intelligence and are trained using a neural-network algorithm. The paper also provides a brief summary of the different categories of learning styles available in the past. The experimental results shown are compared with other models and are found to be promi...

International Journal of Software Science and Computational Intelligence, 2022

Agriculture is the country's mainstay. Plant diseases reduce production and thus product pric... more Agriculture is the country's mainstay. Plant diseases reduce production and thus product prices. Clearly, prices of edible and non-edible goods rose dramatically after the outbreak. We can save plants and correct pricing inconsistencies using automated disease detection. Using light detection and range (LIDAR) to identify plant diseases lets farmers handle dense volumes with minimal human intervention. To address the limitations of passive systems like climate, light variations, viewing angle, and canopy architecture, LIDAR sensors are used. The DSRC was used to receive an alert signal from the cloud server and convey it to farmers in real-time via cluster heads. For each concept, we evaluate its strengths and weaknesses, as well as the potential for future research. This research work aims to improve the way deep neural networks identify plant diseases. Google Net, Inceptionv3, Res Net 50, and Improved Vgg19 are evaluated before Biased CNN. Finally, our proposed Biased CNN (B-C...

Security and Communication Networks, 2021

Smart driving has become conceivable due to the rapid growth of vehicular ad hoc networks. VANETs... more Smart driving has become conceivable due to the rapid growth of vehicular ad hoc networks. VANETs are considered as the main platform for providing safety road information and instant vehicle communication. Nevertheless, due to the open wireless nature of communication channels, VANET is susceptible to security attacks by malicious users. For this reason, secure anonymous authentication schemes are essential in VANETs. However, when vehicles reach a new roadside unit (RSU) coverage area, the vehicles need to perform reauthentication with the current RSU, which significantly diminishes the efficiency of the entire VANET. Therefore, the introduction of blockchain technology has created opportunities for VANETs to resolve the aforementioned challenges. Due to the decentralized nature of blockchain technology, rapid reauthentication of vehicles is achieved in this paper through secure authentication code transfer between the consecutive RSUs. The security strength of the proposed blockc...

Information Systems Frontiers, 2021

The use of Recommendation Systems in any domain plays a vital role in almost all information tech... more The use of Recommendation Systems in any domain plays a vital role in almost all information technology applications. The major focus of this research paper deals with users more preferably e-learners using the proposed Recommendation system. The major objective in developing any Recommendation system is based on many factors like accuracy, preciseness and fast measures. Recommendations given to each user is based on his/her domain interest was time consuming in the past. This research paper deals with the development of a recommendation system which is based on accuracy and fastness measures. One of the factors for developing a fast recommendation system can be obtained by developing efficient algorithms for grouping the existing and the new users quickly so that further domain recommendations might be easier. The proposed framework is based on deep neural network, which proved to be an efficient algorithm for high dimensional data training and testing. The accuracy of the algorith...

Journal of Ambient Intelligence and Humanized Computing

International Journal of Communication Systems

2017 Second International Conference on Recent Trends and Challenges in Computational Models (ICRTCCM)

International Journal on Semantic Web and Information Systems

Predicting learners' affective states through the internet has great impact on their learning... more Predicting learners' affective states through the internet has great impact on their learning experiences. Hence, it is important for an intelligent tutoring system (ITS) to consider the learners' affective state in their learning models. This research work focuses on finding learners' frustration levels during learning. Motivating the learners appropriately can enhance their learning experiences. Therefore, the authors also bring in a strategy to respond to learners' affective states in order to motivate them. This work uses Behavioral theory for goal generation, and frustration index is calculated. Based on the frustration level of the learner, motivational messages are displayed to the learners using Regulatory fit theory. The authors evaluated the model using t-test by collecting learners' data from MoodleCloud. The results of the evaluation demonstrate that 80% of the learners' performance significantly increases statistically as an impact of motivationa...

Proceeding of the International Conference on Computer Networks, Big Data and IoT (ICCBI - 2019)

2017 Second International Conference on Recent Trends and Challenges in Computational Models (ICRTCCM), 2017

This paper addresses a simple, easy to implement method for calculating the geographical area of ... more This paper addresses a simple, easy to implement method for calculating the geographical area of a place on the map using the Shoelace Algorithm. The procedure basically involves placing the Longitudes and Latitudes of the polygon for which the area needs to be found into the technique and obtain its area.

Journal of Systems Architecture, 2021

Abstract Internet of Things (IoT) is a network convergence of multiple intelligent devices and ad... more Abstract Internet of Things (IoT) is a network convergence of multiple intelligent devices and advanced technologies aiming at connecting and exchanging data over the Internet. IoT is extensively applied in consumer, commercial, industrial, infrastructure and military spaces. With the prevalence of IoT applications, security issues such as identity authenticity and data privacy are increasingly become critical concerns. Authentication and confidential data sharing are the important measures towards secure IoT communication and applications. Blockchain is a burgeoning technology supporting for efficient authentication and secure data sharing. A secure and accountable data transmission scheme based on blockchain has been proposed by Hong et al. recently. But this scheme has security weaknesses of impersonation attack, man-in-the-middle attack, replay attack, denial of service attack (DoS) and key compromise attack. Thus we put forward an improved scheme to overcome the identified security flaws. Our scheme is provably secure and performance analysis shows that our scheme reduces 15.34% computation costs and 40.68% communication costs compared with Hong et al.’s scheme. Meanwhile, we also compare our scheme with other three recent and related researches, which finally indicates that our scheme realizes a well tradeoff between security and efficiency.

Handbook of Computational Intelligence in Biomedical Engineering and Healthcare, 2021

Abstract Protracted driving causes physical mental stress that increases life in higher-risk stat... more Abstract Protracted driving causes physical mental stress that increases life in higher-risk state and it takes health to all negative issues. Spending more time on driving a vehicle governs a long, uninterrupted session that leads to obesity, risk to mental health, lack of sleep, bad habits like addictions have changed the quality of life. In this research work, a reliable emergency service ensures a safe driving experience. Such experience guarantees the continual monitoring of the driver's health condition in smart manner. In order to monitor the driver's heart rate, an intelligent healthcare system is proposed that utilizes an artificial recurrent neural network (RNN) model which continually monitors driver's health condition and persistently update to the cloud server. However, tracking their health status is a complex task because health condition statuses are varied and hence this leads to the essential creation of optimized Electronic Health Record (EHR). To accomplish a reliable emergency service, the proposed proximity-based communication model transmits the critical condition record to the service providers even without Internet capability. The long-short term memory is capable of learning the driver's behavior continually in long-term decencies of his/her activity which converts sensor reading into optimized EHR. These health readings are generated from various external body sensors. The proposed work would be noticed as one step toward guaranteed guarded journey. The experimental results achieved 94.65% accuracy of higher prediction rate.

Traditionally, the web search engines return thousands of pages in response to a broad query,maki... more Traditionally, the web search engines return thousands of pages in response to a broad query,making it difficult for users to browse or to identify relevant information.For the purpose of quick access to the relevant information, clustering method is a better choice and can be used to automatically group the retrieved and relevant documents of the target domain.In this paper, a new method which combines the techniques of constrained and coclustering methods has been proposed. This combined approach achieves two goals: First, it combines information theoretic coclustering and constrained clustering to improve the clustering performance. Second, additionallythe unsupervised constraints are incorporated into the proposed method to demonstrate the effectiveness of the algorithm. To achieve this goal, a two-sided hidden Markov random field (HMRF) model is developed to represent both document and word constraints.The results of our evaluation over benchmark data sets exhibit that the proposed algorithm is superior compared to other existing approaches.

Multimedia Tools and Applications, 2021

Cervical cancer is one of the curable cancers when it is diagnosed in the early stages. Pap smear... more Cervical cancer is one of the curable cancers when it is diagnosed in the early stages. Pap smear test and visual inspection using acetic acid are the most common screening mechanism for the cervical lesion to categorize the cervical cells as normal, precancerous, or cancerous. However, most of the classification methods success depends on the accurate spotting and segmenting of cervical location. These challenges pave the way for sixty years of research in cervical cancer diagnosis, but still, accurate spotting of the cervical cell remains an open challenge. Moreover, state-of-the-art classification methods are developed based upon the extraction of manual annotations of features. In this paper, an effective hybrid deep learning technique using Small-Object Detection-Generative Adversarial Networks (SOD-GAN) with Fine-tuned Stacked Autoencoder (F-SAE) is developed to address the shortcomings mentioned above. The generator and discriminator of the SOD-GAN are developed using Region-based Convolutional Neural Network (RCNN). The model parameters are fine-tuned using F-SAE, and the hyperparameters of the SOD-GAN are normalized and optimized to make the lesion detection faster. The proposed approach automatically detects and classifies the cervical premalignant and malignant conditions based on deep features without any preliminary classification and segmentation assistance. Extensive experimentation has also been done with multivariate heterogeneous data, and the proposed approach has shown promising improvement in efficiency and reduces the time complexity.

International Journal of Internet Technology and Secured Transactions, 2017

Wi-Fi Mesh Community has turn out to be an important area community to offer internet to challeng... more Wi-Fi Mesh Community has turn out to be an important area community to offer internet to challenge the thrown domains and wireless link in metropolitan environments. In this paper, hassle of figuring out the most to be had bandwidth direction is targeted, which is an essential problem in helping pleasant-of-carrier in WMCs. Due to the concept of interference, bandwidth, which is a familiar challenging metric in restive networks, a new direction is validated in which the weight captures the available route bandwidth statistics. It is also proved that the hop using the hop routing procedure based on the new path weight completely satisfies the consistency and loop-freeness necessities. The property of consistency ensures that each node follows a proper packet forwarding choice, in order that a statistics packet traverses over the supposed path. The experimental results additionally show that our proposed work on direction weight outperforms all the other existing direction metrics in figuring out excessive-throughput paths.

2017 Second International Conference on Recent Trends and Challenges in Computational Models (ICRTCCM), 2017

In the recent times, the smart phones have become versatile that they are used for sensitive appl... more In the recent times, the smart phones have become versatile that they are used for sensitive applications such as m-banking, m-commerce, m-governance, m-health, digital marketing, SMS and have become a vital gadget to share posts in social networking applications such as Facebook, Twitter, WhatsApp and others. It is also used for online gaming, surfing, chatting and also used for storing the personal information like photos, videos, documents and other important files. In this scenario, it is no surprise that the basic demand for utilizing a smart phone is secure authentication. Though a number of authentication schemes have been proposed in the literature through PIN numbers, passwords and patterns, they are susceptible for shoulder surfing or smudging attacks. Thus, combing gestures with such authentication schemes prove to be more successful in the present times and hence a new kind of pattern has been proposed with essential gestures such as finger pressure and inclination of th...

2018 International Conference on Circuits and Systems in Digital Enterprise Technology (ICCSDET), 2018

Documents that are classified into different categories gets flooded in the internet every day. T... more Documents that are classified into different categories gets flooded in the internet every day. These documents have many links or associations with the other documents in the web. The terms in the document are open to multiple interpretations which are vague and unclear. Hence there is a need to find the semantic understanding of the terms. One of the major application in identifying and applying such semantic measure lies in clustering the related textual documents. However, the traditional clustering algorithms may exhibit reduced performances due to the existence of irrelevant terms in the raw documents. Hence, the proposed algorithm in this paper exploits the use of a feature selection algorithm in order to increase the performance of the clustering algorithm. In this paper, a feature selection algorithm with booster technique is used. Moreover, clustering algorithm based on a fuzzy linguistic variable measure that uses separation and dominance value is used in this paper for precise clustering. Experimental analysis shows that the three performance measures that evaluates the clustering algorithm increases, in comparison to the other existing algorithms.

An important criterion in teaching is to analyze how well the teaching has been effective for the... more An important criterion in teaching is to analyze how well the teaching has been effective for the student’s. In order to do such analysis student’s feedback is obtained which would depict the quality and quantity of teaching. The existing evaluation technique tells about the opinion levels but does not clearly inform is it necessary to bring immediate changes in teaching or can proceed with the current teaching strategy. To address this drawback an automated ideology is proposed to initially analyze the student feedback comments and further based on the analysis introduce a recommendation system that would give a clear idea whether to bring in changes or proceed with the currently adopted teaching technique. This would provide tutors insight about opinion and allow them to make professionally sound decision so as to upgrade the performance of students.

Learning Style is: “A particular way in which an individual learns”. Different kinds of learners ... more Learning Style is: “A particular way in which an individual learns”. Different kinds of learners are distinguished according to their learning styles based on the explicit characteristics shown by the learners, during the earlier period. The latent nature of the learners in addition to the explicit nature, addressed by most of the traditional learning style models also influences the learning style of an individual and such identification could provide better E-Learning framework in terms of content delivery. This paper categorizes new kind of learners: “Intelligent Learners” who are identified by two varying dimensions: Uncovering the latent attitude (Browsing History in an E-Learning server) in them and testing of linguistic intelligence and are trained using a neural-network algorithm. The paper also provides a brief summary of the different categories of learning styles available in the past. The experimental results shown are compared with other models and are found to be promi...

International Journal of Software Science and Computational Intelligence, 2022

Agriculture is the country's mainstay. Plant diseases reduce production and thus product pric... more Agriculture is the country's mainstay. Plant diseases reduce production and thus product prices. Clearly, prices of edible and non-edible goods rose dramatically after the outbreak. We can save plants and correct pricing inconsistencies using automated disease detection. Using light detection and range (LIDAR) to identify plant diseases lets farmers handle dense volumes with minimal human intervention. To address the limitations of passive systems like climate, light variations, viewing angle, and canopy architecture, LIDAR sensors are used. The DSRC was used to receive an alert signal from the cloud server and convey it to farmers in real-time via cluster heads. For each concept, we evaluate its strengths and weaknesses, as well as the potential for future research. This research work aims to improve the way deep neural networks identify plant diseases. Google Net, Inceptionv3, Res Net 50, and Improved Vgg19 are evaluated before Biased CNN. Finally, our proposed Biased CNN (B-C...

Security and Communication Networks, 2021

Smart driving has become conceivable due to the rapid growth of vehicular ad hoc networks. VANETs... more Smart driving has become conceivable due to the rapid growth of vehicular ad hoc networks. VANETs are considered as the main platform for providing safety road information and instant vehicle communication. Nevertheless, due to the open wireless nature of communication channels, VANET is susceptible to security attacks by malicious users. For this reason, secure anonymous authentication schemes are essential in VANETs. However, when vehicles reach a new roadside unit (RSU) coverage area, the vehicles need to perform reauthentication with the current RSU, which significantly diminishes the efficiency of the entire VANET. Therefore, the introduction of blockchain technology has created opportunities for VANETs to resolve the aforementioned challenges. Due to the decentralized nature of blockchain technology, rapid reauthentication of vehicles is achieved in this paper through secure authentication code transfer between the consecutive RSUs. The security strength of the proposed blockc...

Information Systems Frontiers, 2021

The use of Recommendation Systems in any domain plays a vital role in almost all information tech... more The use of Recommendation Systems in any domain plays a vital role in almost all information technology applications. The major focus of this research paper deals with users more preferably e-learners using the proposed Recommendation system. The major objective in developing any Recommendation system is based on many factors like accuracy, preciseness and fast measures. Recommendations given to each user is based on his/her domain interest was time consuming in the past. This research paper deals with the development of a recommendation system which is based on accuracy and fastness measures. One of the factors for developing a fast recommendation system can be obtained by developing efficient algorithms for grouping the existing and the new users quickly so that further domain recommendations might be easier. The proposed framework is based on deep neural network, which proved to be an efficient algorithm for high dimensional data training and testing. The accuracy of the algorith...

Journal of Ambient Intelligence and Humanized Computing

International Journal of Communication Systems

2017 Second International Conference on Recent Trends and Challenges in Computational Models (ICRTCCM)

International Journal on Semantic Web and Information Systems

Predicting learners' affective states through the internet has great impact on their learning... more Predicting learners' affective states through the internet has great impact on their learning experiences. Hence, it is important for an intelligent tutoring system (ITS) to consider the learners' affective state in their learning models. This research work focuses on finding learners' frustration levels during learning. Motivating the learners appropriately can enhance their learning experiences. Therefore, the authors also bring in a strategy to respond to learners' affective states in order to motivate them. This work uses Behavioral theory for goal generation, and frustration index is calculated. Based on the frustration level of the learner, motivational messages are displayed to the learners using Regulatory fit theory. The authors evaluated the model using t-test by collecting learners' data from MoodleCloud. The results of the evaluation demonstrate that 80% of the learners' performance significantly increases statistically as an impact of motivationa...

Proceeding of the International Conference on Computer Networks, Big Data and IoT (ICCBI - 2019)