A5101662802- Advanced MIMO Systems Optimization
- Advanced Wireless Network Optimization
- Fractional Differential Equations Solutions
- Cooperative Communication and Network Coding
- Fluid Dynamics and Turbulent Flows
- Wireless Networks and Protocols
- Autonomous Vehicle Technology and Safety
- Numerical methods for differential equations
- Power Quality and Harmonics
- Vehicle emissions and performance
- Digital Filter Design and Implementation
- Vibration and Dynamic Analysis
- Traffic control and management
- Advanced Control Systems Design
- Energy Harvesting in Wireless Networks
- Nonlinear Waves and Solitons
- Heat Transfer and Optimization
- Advanced MEMS and NEMS Technologies
- Mathematical functions and polynomials
- Privacy-Preserving Technologies in Data
- IoT Networks and Protocols
- Particle Dynamics in Fluid Flows
- Model Reduction and Neural Networks
- Optimization and Variational Analysis
- Connexins and lens biology
University of Illinois Urbana-Champaign
2018-2025
Toyota Motor North America (United States)
2022-2024
Tata Consultancy Services (India)
2024
Medi-Caps University
2024
Toyota Motor Corporation (Switzerland)
2024
University of Central Florida
2023
Dr. B. R. Ambedkar National Institute of Technology Jalandhar
2022
All India Institute of Medical Sciences Bhopal
2021
All India Institute of Medical Sciences Raipur
2021
All India Institute of Medical Sciences Rishikesh
2021
Driving automation is gradually replacing human driving maneuvers in different applications such as adaptive cruise control and lane keeping. However, contemporary based on expert systems or prede-fined strategies are not line with individual driver's preference. To overcome this problem, we propose a Personalized Adaptive Cruise Control (P-ACC) system that can learn the car-following preferences from historical data using model-based maximum entropy Inverse Reinforcement Learning (IRL)....
While the IoT has made significant progress along lines of supporting its individual applications, there are many MMTC scenarios in which performance offered by any single RAT available today might be insufficient. To address these use cases, we introduce concept MR-MMTC, implies availability and utilization several RATs within a device. We begin offering insights into cases could beneficial what key challenges for MR-MMTC implementation are. continue discussing potential technical solutions...
The problem of server sprawl is common in data centers most business organizations. It often the case that an application run on dedicated servers. This leads to situations where organizations end up having numerous servers remain under-utilized times. servers, such scenarios, are allocated more resources (disk, cpu and memory) than justified by their present workloads. Consolidating multiple into a fewer number non-dedicated can host applications effective tool for businesses enhance...
Device-to-Device communications represent a paradigm shift in cellular networks. Analytical results on D2D performance are very promising, but there is no experimental evidence that validates these to date. This paper the first provide an analysis of outband schemes. Moreover, we design DORE, complete framework for handling channel opportunities offered by relay nodes. DORE consists resource allocation optimization tools and protocols suitable integrate QoS-aware opportunistic within...
Concept bottleneck models have been successfully used for explainable machine learning by encoding information within the model with a set of human-defined concepts. In context human-assisted or autonomous driving, explainability can help user acceptance and understanding decisions made vehicle, which be to rationalize explain driver vehicle behavior. We propose new approach using concept bottlenecks as visual features control command predictions explanations learn human-understandable layer...
The exponential increase in high rate traffic driven by the new generation of wireless services is expected to overload cellular network capacity near future. Femtocell networks have recently been proposed as an efficient and cost-effective solution enhance coverage. However, dense unplanned deployment Base Stations (BSs) their uncoordinated operation may system power consumption rise co-channel interference. Thus, schemes are essential for managing femtocell activity improving performance....
A digital twin is a replica of physical entity in the real world. As an emerging technology, it has been widely used various industries. Vehicle-to-everything (V2X) communications enable connected and automated vehicles (CAVs) to communicate with other entities (other vehicles, infrastructures, pedestrians, etc.) transportation environment achieve cooperative driving maneuvers. In this paper, twin-based system developed for CAVs enhance performance terms sustainability, efficiency, safety at...
This paper deals with Multiple Input and Output (MIMO) based Discontinuous Transmission (DTX) algorithms for cloud Radio Access Network (RAN) systems. While DTX MIMO have been individually investigated to improve the Energy Efficiency of base-stations, joint optimization is still an open issue. In this paper, we first investigate practical limits performance use using models remote radio head (RRH). Then, illustrate identify scenarios in which are jointly beneficial improving energy access network.
In this demo, we describe the realization of cloud radio access network (C-RAN) prototype using OpenAirInterface (OAI) software and commodity hardware. The deployment centralized baseband processing on remote center (RCC), units (RRU), connected over Ethernet fronthaul is demonstrated. Further, demo illustrates flexibility in deploying several cellular protocol split architectures OAI.
Character-based translation has several appealing advantages, but its performance is in general worse than a carefully tuned BPE baseline. In this paper we study the impact of character-based input and output with Transformer architecture. particular, our experiments on EN-DE show that models are more robust their counterpart, both when translating noisy text, text from different domain. To obtain comparable BLEU scores clean, in-domain data close gap BPE-based use known techniques to train...