Ruchi Kaushik
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Ruchi Kaushik has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- A. Tamizhselvi
IT, St. Joseph’s College of Engineering, Chennai, India
2 shared publications - Manjula Shanbhog
Department of Computer Science, Christ University, Bangalore, India
2 shared publications - Rajani Kumari
ICFAI Foundation for Higher Education, Off Campus Center Bangalore (Deemed to Be University)
2 shared publications - Ahilan Appathurai
PSN college of Engineering and Technology
1 shared publication - Blerta Prevalla Etemi
Rochester Institute of Technology
1 shared publication - Debabrata Samanta
Rochester Institute of Technology
1 shared publication
Latest Publications
- 29 April 2025
- Published by Springer Nature in International Journal of Information Technology
- Vol. 18 (1) , 717-724
Intrusion detection system with walrus optimization algorithm (WOA) and BiGRU-CNN for securing IoT systems
- 29 April 2025
- Published by Springer Nature in International Journal of Information Technology
- Vol. 18 (1) , 717-724
Intrusion detection system with walrus optimization algorithm (WOA) and BiGRU-CNN for securing IoT systems
- 13 April 2025
- Published by Springer Nature
- p. 191-202
Intelligent Systems with Design Patterns and Data Integrity on Smart Cities and Industries
- 13 April 2025
- Published by Springer Nature
- p. 191-202
Intelligent Systems with Design Patterns and Data Integrity on Smart Cities and Industries
- Open Access
- 9 October 2024
- Published by Science and Technology Limited in JOURNAL OF INTELLIGENT SYSTEMS AND COMPUTING
- Vol. 5 (2)
Enhancing Anemia Prediction in Adolescents: A Study of Machine-Learning Ensembles Incorporating Gaussian Naive Bayes Algorithm, Random Forest Classifier, and Bayesian Forest Fusion
Anemia is a worldwide health concern especially common in teenagers, affecting 46.3% of teenage girls globally, according to estimates. When the body lacks the number of healthy red blood cells that source oxygen to the tissues of our body, anemia, a common blood condition, develops. Numerous factors, such as iron deficiency, malnourishment, and chronic illnesses, might contribute to it. Teenage girls are more likely to acquire anemia because of several reasons, such as growth and development, poor food, and menstruation. This proposed study explores machine learning for accurate anemia prediction by the use of three models: Naive Bayes, Random Forest, and a novel hybrid model combining both. Analyzing a dataset of teenagers collected from a diagnostic center, this proposed research analyzes each model's performance from parameters including F1 score, precision, accuracy, and recall. This study marks the way for utilizing machine learning models in early anemia detection, that enables timely intervention and improved patient outcomes.
- 9 October 2024
- Published by Science and Technology Limited in JOURNAL OF INTELLIGENT SYSTEMS AND COMPUTING
- Vol. 5 (2)
Open AccessEnhancing Anemia Prediction in Adolescents: A Study of Machine-Learning Ensembles Incorporating Gaussian Naive Bayes Algorithm, Random Forest Classifier, and Bayesian Forest Fusion
Anemia is a worldwide health concern especially common in teenagers, affecting 46.3% of teenage girls globally, according to estimates. When the body lacks the number of healthy red blood cells that source oxygen to the tissues of our body, anemia, a common blood condition, develops. Numerous factors, such as iron deficiency, malnourishment, and chronic illnesses, might contribute to it. Teenage girls are more likely to acquire anemia because of several reasons, such as growth and development, poor food, and menstruation. This proposed study explores machine learning for accurate anemia prediction by the use of three models: Naive Bayes, Random Forest, and a novel hybrid model combining both. Analyzing a dataset of teenagers collected from a diagnostic center, this proposed research analyzes each model's performance from parameters including F1 score, precision, accuracy, and recall. This study marks the way for utilizing machine learning models in early anemia detection, that enables timely intervention and improved patient outcomes.
- 12 August 2024
- Published by Springer Nature in International Journal of Information Technology
- Vol. 16 (7) , 4599-4604
NSS-ML: a Novel spectrum sensing framework using machine learning for cognitive radio IoT networks
- 12 August 2024
- Published by Springer Nature in International Journal of Information Technology
- Vol. 16 (7) , 4599-4604
NSS-ML: a Novel spectrum sensing framework using machine learning for cognitive radio IoT networks
- Open Access
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2723 (1)
Artificial intelligence: A new model for online proctoring in education
As a result of technological advancements, society is becoming increasingly computerized. Massive open online courses and other forms of remote instruction continue to grow in popularity and reach. COVID-19’s global impact has boosted the demand for similar courses by a factor of ten. The ability to successfully assign distant online examinations is a crucial limiting factor in this next stage of education’s adaptability. Human proctoring is now the most frequent method of evaluation, which involves either forcing test takers to visit an examination centre or watching them visually and audibly throughout tests via a webcam. However, such approaches are time-consuming and expensive. In this paper, we provide a multimedia solution for semi-automated proctoring that does not require any extra gear other than the student’s computer’s webcam and microphone. The system continuously monitors and analyses the user based on gaze detection, lip movement, the number of individuals in the room, and mobile phone detection, and captures audio in real time through the microphone and transforms it to text for assessment using speech recognition. Access the words gathered by speech recognition and match them for keywords with the questions being asked for higher accuracy using Natural Language Processing. If any inconsistencies are discovered, they are reported to the proctor, who can investigate and take appropriate action. Extensive experimental findings illustrate the correctness, resilience, and efficiency of our online exam proctoring system, as well as how it allows a single proctor to simultaneously monitor several test takers.
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2723 (1)
Open AccessArtificial intelligence: A new model for online proctoring in education
As a result of technological advancements, society is becoming increasingly computerized. Massive open online courses and other forms of remote instruction continue to grow in popularity and reach. COVID-19’s global impact has boosted the demand for similar courses by a factor of ten. The ability to successfully assign distant online examinations is a crucial limiting factor in this next stage of education’s adaptability. Human proctoring is now the most frequent method of evaluation, which involves either forcing test takers to visit an examination centre or watching them visually and audibly throughout tests via a webcam. However, such approaches are time-consuming and expensive. In this paper, we provide a multimedia solution for semi-automated proctoring that does not require any extra gear other than the student’s computer’s webcam and microphone. The system continuously monitors and analyses the user based on gaze detection, lip movement, the number of individuals in the room, and mobile phone detection, and captures audio in real time through the microphone and transforms it to text for assessment using speech recognition. Access the words gathered by speech recognition and match them for keywords with the questions being asked for higher accuracy using Natural Language Processing. If any inconsistencies are discovered, they are reported to the proctor, who can investigate and take appropriate action. Extensive experimental findings illustrate the correctness, resilience, and efficiency of our online exam proctoring system, as well as how it allows a single proctor to simultaneously monitor several test takers.
- 17 November 2021
- Published by Taru Publications in Journal of Discrete Mathematical Sciences and Cryptography
- Vol. 24 (8) , 2137-2153
Multi-class SVM based network intrusion detection with attribute selection using infinite feature selection technique
An intrusion detection mechanism is a software program or a device that monitors the network and provides information about any suspicious activity. This paper proposes a multi-class support vector machine (SVM) based network intrusion detection using an infinite feature selection technique for identifying suspicious activity. Single and multiple classifiers generally have high complexity. To overcome all the limitations of single and multiple classifiers, we used a multi-class classifier using an infinite feature selection technique, which performed well with multiple classes and gave better results than other classifiers in terms of accuracy, precision, recall, and f_score. Infinite feature selection is a graph-based filtering approach that analyses subsets of features as routes in a graph. We used a standard dataset, namely the UNSW_NB15 data set generated by the IXIA perfect-storm tool in the Australian Centre for Cyber Security. This dataset has a total of nine types of attacks and 49 features. The comparative analysis of the manuscript work is done against eight different techniques, namely, hybrid intrusion detection system (HIDS), C5, one-class support vector machine, and others. The proposed work gave better simulation results using the 2015a Matlab simulator.
- 17 November 2021
- Published by Taru Publications in Journal of Discrete Mathematical Sciences and Cryptography
- Vol. 24 (8) , 2137-2153
Multi-class SVM based network intrusion detection with attribute selection using infinite feature selection technique
An intrusion detection mechanism is a software program or a device that monitors the network and provides information about any suspicious activity. This paper proposes a multi-class support vector machine (SVM) based network intrusion detection using an infinite feature selection technique for identifying suspicious activity. Single and multiple classifiers generally have high complexity. To overcome all the limitations of single and multiple classifiers, we used a multi-class classifier using an infinite feature selection technique, which performed well with multiple classes and gave better results than other classifiers in terms of accuracy, precision, recall, and f_score. Infinite feature selection is a graph-based filtering approach that analyses subsets of features as routes in a graph. We used a standard dataset, namely the UNSW_NB15 data set generated by the IXIA perfect-storm tool in the Australian Centre for Cyber Security. This dataset has a total of nine types of attacks and 49 features. The comparative analysis of the manuscript work is done against eight different techniques, namely, hybrid intrusion detection system (HIDS), C5, one-class support vector machine, and others. The proposed work gave better simulation results using the 2015a Matlab simulator.