Prateek Garg

Prateek Garg

Auto-generated profile, based on publicly available information

Prateek Garg

Chitkara University Institute of Engineering and Technology, Chitkara University,Centre for Interdisciplinary Research in Business and Technology,Punjab,India

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 August 2021 in ACM Transactions on Internet Technology
Verified
Journal Article
Open access
PGPrateek Garg
Prateek Garg
ACAnirudh Srinivasan Chakravarthy
Anirudh Srinivasan Chakravarthy
MMMurari Mandal
Murari Mandal
PNPratik Narang
Pratik Narang
Vinay ChamolaVinay Chamola
Vinay Chamola
MGMohsen Guizani
Mohsen Guizani
Aerial scenes captured by UAVs have immense potential in IoT applications related to urban surveillance, road and building segmentation, land cover classification, and so on, which are necessary for the evolution of smart cities. The advancements in deep learning have greatly enhanced visual understanding, but the domain of aerial vision remains largely unexplored. Aerial images pose many unique challenges for performing proper scene parsing such as high-resolution data, small-scaled objects, a large number of objects in the camera view, dense clustering of objects, background clutter, and so on, which greatly hinder the performance of the existing deep learning methods. In this work, we propose ISDNet (Instance Segmentation and Detection Network), a novel network to perform instance segmentation and object detection on visual data captured by UAVs. This work enables aerial image analytics for various needs in a smart city. In particular, we use dilated convolutions to generate improved spatial context, leading to better discrimination between foreground and background features. The proposed network efficiently reuses the segment-mask features by propagating them from early stages using residual connections. Furthermore, ISDNet makes use of effective anchors to accommodate varying object scales and sizes. The proposed method obtains state-of-the-art results in the aerial context.

8 December 2023
Verified
Conference Paper
Closed access
PGPrateek Garg
Prateek Garg
This research introduces an advanced methodology for enhancing edge computing security in IoT networks by employing machine learning techniques. The approach begins with a meticulous data preprocessing and feature engineering phase, preparing raw IoT data for further analysis. Subsequently, the Isolation Forest algorithm is applied for anomaly detection, effectively isolating anomalies by leveraging random feature selection and isolation trees. To enhance intrusion detection, a Convolutional Neural Network (CNN), known for its proficiency in pattern recognition, is utilized. The CNN model learns intricate patterns from preprocessed IoT data and distinguishes normal behavior from potential intrusions. Furthermore, an ensemble fusion technique is proposed, combining the strengths of Isolation Forest and CNN-based intrusion detection to achieve a more accurate and reliable intrusion detection system. Performance evaluation demonstrates that the proposed method consistently outperforms traditional approaches, showcasing superior detection accuracy, lower false positive rates, enhanced privacy preservation, reduced latency, improved scalability, and increased energy efficiency.

8 December 2023
Verified
Conference Paper
Closed access
PGPrateek Garg
Prateek Garg
The increasing incidence of falls among the elderly in hospital settings necessitates the development of advanced predictive models. This paper introduces a comprehensive cognitive assessment model designed to predict fall risks among elderly patients in hospital environments. By integrating cognitive assessment scores, patient demographics, and environmental factors, the model offers a holistic approach to fall risk prediction. Three distinct machine learning algorithms, namely Neural Network-based Fall Risk Prediction (NN-FRP), Support Vector Machine-based Fall Risk Prediction (SVM-FRP), and K-Nearest Neighbors-based Fall Risk Prediction (KNNFRP), are explored. The culmination of this research is the Ensemble-based Fall Risk Prediction (E-FRP), which synergistically combines the strengths of the three individual models. Preliminary results indicate that the ensemble model outperforms its constituent models in terms of accuracy and convergence time.