Sahil Garg’s research while affiliated with Chitkara University and other places

This research introduces the Density-Clustering based Aggregation for Personalized Federated Learning (DCPFL) algorithm, which utilizes DBSCAN clustering to enhance model accuracy in AI-enabled aerial and edge computing contexts, particularly for UAVs. The DCPFL framework promotes model sharing among clients, fostering the development of personalized and optimized models. DBSCAN is beneficial in automatically determining cluster numbers using EPS neighborhoods and MinPts, with parameter optimization achieved through cross-experimental analysis. We further refined the model exchange mechanism by integrating a moving average prediction model to optimize the timing of these exchanges. Tests conducted on three public datasets covering two different machine learning tasks show that DCPFL surpasses existing methods, offering greater accuracy and enhanced adaptability in varied data environments. Implementing this algorithm in UAV networks leverages AI capabilities in aerial and edge computing to efficiently balance personalized modeling requirements with high performance, showcasing its potential to push federated learning forward in complex and dynamic settings.

Robust and accurate approaches are in high demand in the field of facial image retrieval systems. The current methods are not as resilient overall since they mostly rely on sign information within small 3 × 3 or 5 × 5 pixel windows. We provide a novel local binary descriptor specifically designed for facial image retrieval, called Multi-scale Block and Mean-based Local Binary Pattern (MBM-LBP), to address this issue head-on. By utilizing a larger 6 × 6 pixel window and taking into account the sign and magnitude of nearby pixels holistically, MBM-LBP represents a paradigm leap in system robustness and improves the richness of feature representation. The suggested MBM-LBP is carefully examined by means of thorough evaluations using two face image datasets. The results clearly demonstrate MBM-LBP's superiority over current state-of-the-art methods in the field of face image retrieval. In addition to improving retrieval accuracy, MBM-LBP has the potential to provide more accurate and consistent results for a broad range of real-world uses. This groundbreaking invention paves the way for improved face image retrieval systems, catering to the diverse requirements of multiple industries where reliable and effective retrieval is vital. Facial image retrieval is about to enter a new era marked by significant improvements in both performance and utility, thanks to the leadership of MBM-LBP.

The digitalization of traffic networks has spurred the development of intelligent transportation systems. By utilizing reinforcement learning for dynamic traffic optimization, it efficiently handles real-world traffic complexities. However, as the demand for real-time, high-efficiency tasks increases, relying solely on reinforcement learning struggles to meet both goals. Integrating reinforcement learning with mobile communication technology offers a promising solution for efficient, low-overhead traffic networks. As an important physical layer technology for Integrated Sensing and Communications Systems, Spectrally Efficient Frequency Division Multiplexing (SEFDM) addresses the communication overhead challenge in reinforcement learning-enabled optimization. However, the main challenge of SEFDM is eliminating the inter-carrier interference (ICI) caused by non-orthogonal modulation. Considering that existing post-interference cancellation methods fail due to the ill-conditioning of the generalized channel matrix, which cannot be directly inverted, we propose a nonlinear precoding algorithm at the transmitter, instead of post-cancellation, that effectively eliminates interference and improves transmission reliability. We firstly use a nonlinear feedback structure to avoid power boost and error propagation. Besides that, Geometric Mean Decomposition (GMD) based interference matrix decomposition algorithm is used in the proposed precoding scheme to avoid matrix singularity and obtain diversity gain. Finally, the numerical results show that the proposed precoding method can achieve higher order QAM SEFDM signaling with higher spectral efficiency and get comparative BER performance.

The Internet of Vehicles (IoV) enables technology that allows IoV and vehicles to connect everything. IoV has become an essential component of modern life. This exponential growth of IoV technology has introduced significant security and privacy issues, which pose potential threats to different types of attacks and cause different threats to the normal operation of vehicles. To prevent intelligent vehicle accidents and identify malicious attacks within IoV networks, various researchers have focused on machine learning (ML)-based methods to detect attacks. Intrusion detection systems (IDS) are a prominent solution for cyber attacks in IoV using ensemble learning. To achieve higher accuracy and detection rate, designing an improved detection framework using ensemble learning is a challenging task. The design of an ensemble-based IDS depends on two main challenges: selecting base classifiers and their combination methods. Therefore, in this study, we propose a hybrid ML model to detect various attacks in IoV. We have used different ML algorithms to develop an enhanced algorithm that can efficiently detect attacks in IoV networks. To evaluate the performance of the proposed system, we have used two well-known datasets, (CIC-IDS2017) and (UNSW-NB15). The proposed algorithm shows outstanding performance from the performance results, with an average attack detection accuracy of 99.75% and 100% and an F1 score of 99.74% and 100%, respectively, for both datasets. Further performance scores, that is, recall, precision, and F1 score metrics, validate the exceptional effectiveness of the proposed framework.