Dr. Shweta Agarwal
@cuchd.in
Assistant Professor in CSE
Chandigarh University
EDUCATION
Ph.D in CSE
RESEARCH, TEACHING, or OTHER INTERESTS
Computer Science, Artificial Intelligence
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Shweta Agarwal, Bobbinpreet Kaur, and Bhoopesh Singh Bhati
Springer Science and Business Media LLC
Binayak Kumar Mahato, Shweta Agarwal, Rajnish Kumar, Abhinav Paswan, Amar Kumar Mandal, and Prince Thakur
IEEE
In this paper, we analyze the current state of targeted advertising on various social media platforms using algorithmic analysis and implementing strategies. Social media plays an increasingly important role in modern marketing, especially in the wake of COVID-19, which hastened the transition to online platforms. Drawing on advances in technology, including machine learning and natural language processing (NLP), we demonstrate the value of personalized advertising in increasing user engagement and brand affinity. Drawing on recent research and case studies, we highlight the need to balance targeted advertising with user privacy. In summary, we call for innovation and ethical considerations as we navigate the ever-changing advertising landscape.
Shweta Agarwal, Bobbinpreet Kaur, and Bhoopesh Singh Bhati
IEEE
The most significant improvement in human-computer interfaces revolves around the accurate decoding of hand gestures from electromyography signals. The existing methods of doing this have a number of limitations. These include: feature redundancy and diminishing estimation accuracy for new users when pre-trained models are applied. Therefore, the current study focuses on enhancing the EMGbased recognition of hand gestures by developing a swarm intelligence based model to select features. In this model, a feature extractor, feature selector, and label classifier interface are integrated. The proposed model uses time domain (TD), frequency domain (FD), and time-frequency domain (TFD) analyses to establish the basic information of gesture recognition. Improved Grasshopper Optimization Algorithm (IGOA) chooses the most discriminative features from the EMG data. It is noteworthy that a DNN classifier improves the classification result of the EMG-based gesture classification using the created feature set. It evaluates the proposed model from an 8-channel Myo Armband dataset. The proposed approach, on average improves by $2.4 \\%, \\mathbf{9. 6 \\%, 6. 1 \\%,}$ and 8% in precision, recall, F-measure, and accuracy respectively compared with a common KNN, NB, and RF estimators. Moreover, the average enhancements in recall by 7.3%, in precision by 4.9%, in accuracy by 4.1%, and in F-measure by 6.2% over popular optimization techniques like PSO, GA, and GH demonstrate the strength of the DNN and label the IGOA + DNN combination as a very effective strategy for EMG-based gesture classification.
Shweta Agarwal, Neetu Rani, and Amit Vajpayee
Wiley
Shweta Agarwal, Bobbinpreet Kaur, and Bhoopesh Singh Bhati
IEEE
Feature Selection is a way of improving machine learning models in terms of efficacy and accuracy. The process involves identifying the most relevant features within a dataset to improve the efficiency of the model. Traditionally, the approaches have had issues in selecting the most relevant features to the case in most instances with accuracy. This paper, therefore, looks to develop and evaluate a novel approach for feature selection based on the Grasshopper Algorithm (GH). The idea is to address some specific problems of feature selection tasks and assess its performance against traditional swarm intelligence techniques. In this regard, the modified GH has been comprehensively assessed against the traditional or common techniques like ABC, GA and PSO. The results which are obtained reveal that modified GH algorithm outperformed PSO, GA and ABC in all the feature selection tasks. It improved the accuracy to 92.01%, which is 10.84% higher than PSO, 25.12% higher than GA, and 12.92% higher than ABC. That means the GH algorithm performs very well in feature selection. Consequently, swarms of algorithms are rather competitive for the optimization performance of various machine learning applications. To this end, this paper reveals the pertinent knowledge of swarm intelligence in feature selection to researchers and readers.
Shweta Agarwal, Raman Chadha, and Bhoopesh Singh Bhati
IEEE
Nowadays, many computing systems are a part of daily life; therefore, it is more comfortable to communicate with them naturally. The field of human-computer interaction (HCI) was created in order to break down the obstacles to human-computer communication. One of the types of HCI that is, Hand Gesture Recognition (HGR), which predicts the type of a certain hand action. The electrical activity of skeletal muscles is one potential input for these types of models. The purpose of movement produced by the human brain is communicated through electromyography (EMG) signals. In order to identify EMG data that is precise for any class, the most pertinent collection of EMG attribute values must be used to train a system. With the aid of a combination of machine learning and EMG data, this paper aims to present the most recent real-time feature selection techniques and classification algorithms in a comprehensive review of the literature. Finally, several gaps have been found that may point the way for fresh lines of inquiry in the field of EMG-based gesture detection, and a proposed approach for improving the overall classification accuracy of the EMG signal is presented.
Nidhi, Mukesh Kumar, Disha Handa, and Shweta Agarwal
AIP Publishing
Shweta Agarwal and Chander Prabha
Springer Nature Singapore
Shweta Agarwal and Chander Prabha
CRC Press
Nidhi Nidhi, Mukesh Kumar, and Shweta Agarwal
IEEE
Data stored in digital form is increasing daily, and so its complexity. Processing a massive volume of data needs efficient technology. Data mining and Machine Learning researchers are focused on finding a suitable algorithm that can find important information after processing that data. In educational data mining, most of the students' records are also stored in digital form. So, the researchers are also trying to find some informative knowledge that can be helpful for the students, teachers, and management to improve their working towards the success of the students and institution also. In predictive modelling, the main challenge is finding the most effective predictive techniques that help achieve an acceptable accuracy level. This article, therefore, proposes a hybrid or heterogeneous approach of Correlation Attribute Evaluation, Ensemble Learning like Stacking, Voting and MultiScheme, in conjunction with seven different Machine Learning algorithms to improve the prediction accuracy up to an acceptable level. Here, k-fold cross-validation was used as a test method to evaluate the predictive performance of the classification algorithms.