R. Thandeeswaran’s research while affiliated with Vellore Institute of Technology University and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (27)


An improved adaptive personalization model for instructional video-based e-learning environments
  • Article

January 2024

·

41 Reads

·

2 Citations

Journal of Computers in Education

T S Sanal Kumar

·

R. Thandeeswaran

Due to the unexpected COVID-19 pandemic, video-based e-learning environments for programming education have disrupted traditional classroom teaching methods. The major drawbacks of these environments are that they never consider the individual differences and personal traits of the learner while building a challenging course like programming, having high dropout and failure rates. To address this issue, this paper proposed a learning style-enabled novel rule-based personalized instructional video delivery model for programming education. The model used the following four learning parameters for delivering the instructional videos: (a) most recent instructional video, (b) assessment score, (c) complexity level, and (d) weight (variance of two recent assessments) score. This work was designed using a paired pre-test–post-test experimental approach with first-year undergraduate students. For the experimental evaluation, students were randomly classified into three groups. Learner scores and feedback were taken as evaluation metrics. Results revealed that the proposed model-driven group showed significant improvements in knowledge acquisition, grade, and positive feedback compared to the other groups. Hence, the proposed model is highly recommended for traditional programming e-learning environments to deliver personalized instructional videos based on learners’ receptive pace, cognitive level, and learning preference.


Intervention procedure
Screenshots of the Instructional video design patterns for VPTH
VPTH Learning Style Identification
Python programming Concept map
Architecture of VPTH-based e-learning environment

+13

Adapting video-based programming instruction: An empirical study using a decision tree learning model
  • Article
  • Publisher preview available

January 2024

·

541 Reads

·

2 Citations

Education and Information Technologies

The COVID-19 pandemic has forced a significant increase in the utilization of video-based e-learning platforms for programming education. These platforms never considered the essential attributes of student characteristics and learning preferences while designing such a problematic subject having high dropout and failure rates. The traditional e-learning environments deliver instructional videos to the learners by assuming all learners have a single learning preference. Moreover, existing learning style models need to address the recent requirements of e-learning paradigms. To address this issue, this paper presents a novel learning style model tailored for instructional video-based programming e-learning environments that map individual learning preferences with various video design patterns. An adaptive e-learning environment was employed to assess the effectiveness of the proposed model that leveraged a decision tree classifier to divide learners into four preferences. In a paired experimental design, 195 first-year undergraduate students were randomly assigned to one of three groups where learner scores and feedback were taken as evaluation metrics. The control group partook without instructional videos for the entire semester of six months. During the same period, experimental group-1 learned with a traditional video-based e-learning environment, and experimental group-2, with the proposed learning style model, enabled an adaptive e-learning environment. Based on the proposed decision tree learning model, it is understood that the intervention group showed significant improvements in knowledge acquisition, grade, and positive feedback compared to the other groups. Hence, the proposed model is highly recommended for traditional programming e-learning environments to deliver instructional videos based on learners' learning preferences.

View access options


Predictive Analysis of Network-Based Attacks by Hybrid Machine Learning Algorithms Utilizing Bayesian Optimization, Logistic Regression, and Random Forest Algorithm

January 2024

·

28 Reads

·

2 Citations

IEEE Access

These days, intrusion detection systems are one of the newest trends in society. These technologies serve as a defense against a variety of security breaches, the number of which has been rising recently. The need for adaptive security solutions is pressing since the sorts of attacks that arise are ever-changing. This study aims to enhance the performance of intrusion detection models on the KDD99 and NSL-KDD datasets through advanced optimization techniques. By addressing challenges related to evolving attack strategies and intricate tasks, the research introduces innovative machine learning approaches tailored for intrusion detection, focusing on both binary and multiclass classification scenarios. The study employs a Bayesian Optimization-enhanced Random Forest (BO_RF) algorithm for binary classification and a hybrid Logistic Regression and Random Forest (LR_RF) algorithm for multiclass classification. Our models were implemented and evaluated in a Jupyter Notebook environment using key metrics: Accuracy, Precision, Recall, and F1-Score. For binary classification, eight metrics were assessed, while twenty-six were analyzed for multiclass classification across both datasets. The results demonstrate the effectiveness of the proposed approaches in both classification types, highlighting their potential for robust and adaptable intrusion detection. Theoretical contributions include advancing the understanding of intrusion detection methodologies and the effectiveness of machine learning algorithms in cybersecurity. From a practical perspective, the proposed model can offers a robust and adaptable solution for real-world intrusion detection scenarios, potentially minimizing security breaches and enhancing overall cyber security posture.



Analysis of Cross-Site Scripting Vulnerabilities in Various Day-To-Day Web Applications

September 2022

·

50 Reads

Networking threats aim to disrupt the normal flow of data and communication. They attack basic security measures—confidentiality, integrity and availability. Cross-site scripting (XSS) aims at rattling either confidentiality or integrity, depending on the focus of the attack. Since the dawn of the Internet, the amount of cyber-attacks and also the need for cybersecurity has grown exponentially. Today, there are numerous predefined ways network resources that can be attacked. It can be via malware or networking threats like XSS. This paper is an attempt to discover the most commonly exploited flaw in today’s web pages—the XSS vulnerability—using various testing tools like Burp Suite and Nessus.KeywordsCross-site scripting (XSS)ConfidentialityReal-time applicationsThreatsAttacksBurp SuiteNessus





Smart Security Algorithm: Ensured Confidentiality and Integrity

November 2019

·

19 Reads

·

1 Citation

International Journal of Innovative Technology and Exploring Engineering

The main aim of this paper is to provide confidentiality, integrity to the message. It Encrypts the message when it is passing from the sender side to the receiver side. If we take the Caesar cipher it is weak against the brute force attack, dictionary attack but this algorithm is stronger against the brute-force attack and dictionary attack. It has both private and public key encryption which is unlikely for other encryption algorithms like hill cipher, play fair cipher etc. Some Encryption algorithms will prone to be attacked with man-in-the-middle attack but this will be overcome with using hash code concept. This proposal encrypts the message with the novel algorithm at the client side and does the counterpart at the server side. Algorithm implemented using python programming and proves our algorithm is stronger against brute force and dictionary attacks.


Citations (18)


... LR is interpretable and effective for binary classification tasks with linear relationships. It has low time complexity, making it efficient for large datasets, but it may underperform with non-linear or complex patterns (26,27). To evaluate the predictive effect of various types of variables on MASLD, we constructed models utilizing 1) all variables; 2) insulin-related indexes (HOMA-IR, TyG indexrelated parameters); 3) demographic characteristics variables; and 4) other indexes, respectively. ...

Reference:

Development and validation of machine learning models for MASLD: based on multiple potential screening indicators
Predictive Analysis of Network-Based Attacks by Hybrid Machine Learning Algorithms Utilizing Bayesian Optimization, Logistic Regression, and Random Forest Algorithm

IEEE Access

... After seven days of project work, students must upload the PjBL practicum products implemented on Google Classroom for product assessment or assessment. The stages of providing project time, opportunities for discussion and consultation, and product assessment are by the project-based learning steps stages: (3) preparing a schedule, (4) monitoring project progress, and (5) assessing results (Sanal Kumar & Thandeeswaran, 2024;. The PjBL practicum module design for the alkaloid analysis gravimetrically presented in this article is the final form after revision based on expert input at the validation stage. ...

An improved adaptive personalization model for instructional video-based e-learning environments
  • Citing Article
  • January 2024

Journal of Computers in Education

... Partiendo de la metodología empleada, se realizó un análisis comparativo de las cinco herramientas antes presentadas en el Objeto de análisis. Las variables por analizar fueron: curva de aprendizaje, biblioteca de recursos, personalización, edición, generación IA e integración con otros sistemas y plataformas, tal y como realizaron anteriormente autores como Kumar & Thandeeswaran (2023) o Koliska et al. (2021). ...

A general model for an instructional video-based personalized programming learning environment and its practical implications
  • Citing Conference Paper
  • August 2023

... WikiLeaks reported that it was targeted by a distributed denial of service (DDoS) attack that lasted for over longer than one week. The website stated it was subjected to a traffic flood of 10 gigabits per second, causing slowness and unresponsiveness [5]. The research gap in this paper is applying machine learning algorithms to automatically the process of predicting Dos and DDoS attacks such as "DDoS", "DoS Hulk", "DoS GoldenEye", "DoS Slowhttptest" and "DoS Slowloris". ...

Bi-level user authentication for enriching legitimates and eradicating duplicates in cloud infrastructure
  • Citing Article
  • January 2020

International Journal of Computer Aided Engineering and Technology

... The problem of authenticating users and authorizing them to access variety of resources and services provided by the Cloud Service Providers (CSP) in multicloud environment are studied extensively. The various methodologies and schemes are proposed to secure the cloud infrastructure in [1][2][3][4]. The users in wireless LAN are authenticated using Service set identifier [5] and based on the behaviour of the existing users credits are assigned to authorize them to access the cloud resources [6]. ...

Bi-level user authentication for enriching legitimates and eradicating duplicates in cloud infrastructure
  • Citing Article
  • January 2020

International Journal of Computer Aided Engineering and Technology