Rashi Rastogi
Research Subjects
Rashi Rastogi has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Mamta Bansal
Department of CSE, Shobhit Institute of Engineering and Technology, Meerut, India
2 shared publications - Nitin Goyal
Department of Computer Science and Engineering, School of Engineering and Technology, Central University of Haryana, Mahendergarh 123031, Haryana, India
2 shared publications - Aarti Sangwan
K. R. Mangalam University, Gurugram, Haryana
1 shared publication - Bhawna Sharma
JMIT Radaur, Symbiosis International (Deemed University), Pune, India
1 shared publication - Chetna Gupta
Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura 140417, Punjab, India
1 shared publication - Gaurav Sharma
Department of Computer Science & Engineering, JMIT, Radaur, India
1 shared publication
Latest Publications
- 17 July 2025
- Published by Springer Nature in International Journal of Information Technology
- Vol. 18 (1) , 133-139
Fuzzy-ant colony clustering energy efficient routing protocol (FACERP) for underwater wireless sensor networks
- 17 July 2025
- Published by Springer Nature in International Journal of Information Technology
- Vol. 18 (1) , 133-139
Fuzzy-ant colony clustering energy efficient routing protocol (FACERP) for underwater wireless sensor networks
- 8 April 2025
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 84 (33) , 41801-41828
Innovative anti-phishing framework using machine learning approach with evolutionary optimization to secure multimedia applications
- 8 April 2025
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 84 (33) , 41801-41828
Innovative anti-phishing framework using machine learning approach with evolutionary optimization to secure multimedia applications
- Open Access
- 2 February 2025
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 15 (1) , 20064-20070
Effective Diabetes Prediction using an IoT-based Integrated Ensemble Machine Learning Framework
Diabetes, a prevalent chronic disease, affects a significant global population. Identifying and being aware of key variables promptly may substantially enhance results for both patients and public health efforts. Systematic methods such as monitoring diabetic patients allow the collection of extensive data from diabetic patients. When it comes to keeping track of a patient's health, IoT sensors, such as those used in diabetic patient monitoring systems, are invaluable. Blood glucose levels, body temperature, and location of a diabetic patient can be tracked and recorded through a monitoring device. In addition to monitoring patients, these data can be classified using Machine Learning (ML) methods. This study applies three ML models to three different diabetes datasets and analyzes their performance. According to the results, the fine-tuned random forest model achieved higher accuracy, i.e., 89%, 90%, and 99%.
- 2 February 2025
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 15 (1) , 20064-20070
Open AccessEffective Diabetes Prediction using an IoT-based Integrated Ensemble Machine Learning Framework
Diabetes, a prevalent chronic disease, affects a significant global population. Identifying and being aware of key variables promptly may substantially enhance results for both patients and public health efforts. Systematic methods such as monitoring diabetic patients allow the collection of extensive data from diabetic patients. When it comes to keeping track of a patient's health, IoT sensors, such as those used in diabetic patient monitoring systems, are invaluable. Blood glucose levels, body temperature, and location of a diabetic patient can be tracked and recorded through a monitoring device. In addition to monitoring patients, these data can be classified using Machine Learning (ML) methods. This study applies three ML models to three different diabetes datasets and analyzes their performance. According to the results, the fine-tuned random forest model achieved higher accuracy, i.e., 89%, 90%, and 99%.
- Open Access
- 25 December 2023
- Published by MDPI AG in Diagnostics
- Vol. 14 (1) , 43
Cross-Silo, Privacy-Preserving, and Lightweight Federated Multimodal System for the Identification of Major Depressive Disorder Using Audio and Electroencephalogram
In this day and age, depression is still one of the biggest problems in the world. If left untreated, it can lead to suicidal thoughts and attempts. There is a need for proper diagnoses of Major Depressive Disorder (MDD) and evaluation of the early stages to stop the side effects. Early detection is critical to identify a variety of serious conditions. In order to provide safe and effective protection to MDD patients, it is crucial to automate diagnoses and make decision-making tools widely available. Although there are various classification systems for the diagnosis of MDD, no reliable, secure method that meets these requirements has been established to date. In this paper, a federated deep learning-based multimodal system for MDD classification using electroencephalography (EEG) and audio datasets is presented while meeting data privacy requirements. The performance of the federated learning (FL) model was tested on independent and identically distributed (IID) and non-IID data. The study began by extracting features from several pre-trained models and ultimately decided to use bidirectional short-term memory (Bi-LSTM) as the base model, as it had the highest validation accuracy of 91% compared to a convolutional neural network and LSTM with 85% and 89% validation accuracy on audio data, respectively. The Bi-LSTM model also achieved a validation accuracy of 98.9% for EEG data. The FL method was then used to perform experiments on IID and non-IID datasets. The FL-based multimodal model achieved an exceptional training and validation accuracy of 99.9% when trained and evaluated on both IID and non-IIID datasets. These results show that the FL multimodal system performs almost as well as the Bi-LSTM multimodal system and emphasize its suitability for processing IID and non-IIID data. Several clients were found to perform better than conventional pre-trained models in a multimodal framework for federated learning using EEG and audio datasets. The proposed framework stands out from other classification techniques for MDD due to its special features, such as multimodality and data privacy for edge machines with limited resources. Due to these additional features, the framework concept is the most suitable alternative approach for the early classification of MDD patients.
- 25 December 2023
- Published by MDPI AG in Diagnostics
- Vol. 14 (1) , 43
Open AccessCross-Silo, Privacy-Preserving, and Lightweight Federated Multimodal System for the Identification of Major Depressive Disorder Using Audio and Electroencephalogram
In this day and age, depression is still one of the biggest problems in the world. If left untreated, it can lead to suicidal thoughts and attempts. There is a need for proper diagnoses of Major Depressive Disorder (MDD) and evaluation of the early stages to stop the side effects. Early detection is critical to identify a variety of serious conditions. In order to provide safe and effective protection to MDD patients, it is crucial to automate diagnoses and make decision-making tools widely available. Although there are various classification systems for the diagnosis of MDD, no reliable, secure method that meets these requirements has been established to date. In this paper, a federated deep learning-based multimodal system for MDD classification using electroencephalography (EEG) and audio datasets is presented while meeting data privacy requirements. The performance of the federated learning (FL) model was tested on independent and identically distributed (IID) and non-IID data. The study began by extracting features from several pre-trained models and ultimately decided to use bidirectional short-term memory (Bi-LSTM) as the base model, as it had the highest validation accuracy of 91% compared to a convolutional neural network and LSTM with 85% and 89% validation accuracy on audio data, respectively. The Bi-LSTM model also achieved a validation accuracy of 98.9% for EEG data. The FL method was then used to perform experiments on IID and non-IID datasets. The FL-based multimodal model achieved an exceptional training and validation accuracy of 99.9% when trained and evaluated on both IID and non-IIID datasets. These results show that the FL multimodal system performs almost as well as the Bi-LSTM multimodal system and emphasize its suitability for processing IID and non-IIID data. Several clients were found to perform better than conventional pre-trained models in a multimodal framework for federated learning using EEG and audio datasets. The proposed framework stands out from other classification techniques for MDD due to its special features, such as multimodality and data privacy for edge machines with limited resources. Due to these additional features, the framework concept is the most suitable alternative approach for the early classification of MDD patients.
- 18 August 2023
- Published by Springer Nature
- p. 445-461
Assessment on Different IoT-Based Healthcare Services and Applications
- 18 August 2023
- Published by Springer Nature
- p. 445-461
Assessment on Different IoT-Based Healthcare Services and Applications