Computer Science & Engineering and Information Technology (CSE&IT)

Prof. Dr. Vivek Kumar Sehgal

Prof. Dr. Vivek Kumar Sehgal
Professor and Head, Fellow IEI, SM-IEEE, SM-ACM
( 91)1792-239251
vivek.sehgal@juit.ac.in, vivekseh@acm.org, vivekseh@ieee.org
For More Information Click here


Biography :

Vivek Kumar Sehgal (SM’18) received the B.Tech. degree in Instrumentation Engineering from SantLongowal Institute of Engineering and Technology (Deemed University), in 2000, M.Tech. degree in Process Control Engineering from NetajiSubhash Institute of Technology (Delhi University), in 2002, and the Ph.D. degree in Computer Science and Engineering from Uttrakhand Technical University, Dehradun, in 2007-2010. He is currently Professor with the Department of Information Technology, Jaypee University of Information Technology, Solan, H.P-India. He is member of various technical Societies including IEEE, IEEE Computer Society, Member of IEEE Exe. Com. Delhi Section, Computer Society of India, ACM, SIAM, and IAENG. His areas of interest include embedded processor architecture, hardware software co-design, NoC, Smart MEMS and soft computing for chip design. Dr.Vivek Kumar Sehgal is a member of the technical program committees for several technical conferences, and editorial member of IEEE Access and other reputed journals

Education:

  • Ph.D. (Computer Science and Engineering), Uttarakhand Technical University, Dehradun, India in (2007 - 2010). Title: Stochastic Communication and Packets Flow Control in Networks-on-Chip.
  • M. Tech. (Process Control), Netaji Subhas Institute of Technology (NSIT), (Formerly Delhi Institute of Technology - a division of Instrumentation & Control Engineering, University of Delhi) in 2002.
  • B. Tech. (Instrumentation Engineering), Sant Longowal Institute of Engineering & Technology Longowal (Deemed University Est. by Govt. of India) in 2000.

Research Interests

  • Embedded Systems
  • Advanced Computer Architecture
  • Networks on Chip (NoC)
  • Industrial Internet of Things
  • Cyber Physical Systems, Industry 4.0
  • Deep Learning

Ph.D. Students Supervised:

Ruchi Verma (2017) : Modeling for Crisis Management Occurred during Computer Mediated Communications

Dinesh Kumar (2019) : On Performance of Modified Torus Interconnection Networks

Astha Modgil (2019) : Finding Energy Sustainable Techniques for Computer Memory

Amit Chaurasia (2020) : Application Traffic Modeling and Optimization for NoC Communication

Abhilasha Rangra (2021): Social Internet of Things their Trustworthiness Node Rank and Embeddings Management

Kapil Sharma (2022): Improved and Efficient Optical Networks On Chip Architectures and Designs

Harsuminder Kaur Gill (2022) : Context Aware Recommender Systems using Deep Neural Network

Ph.D. Students Supervising:

Mr. Surjeet Singh : Image Forgery Detection Model using CNN Architecture with SVM Classifier

Ms. Payal Thakur : Neuromorphic Cyber Physical Systems Design

Mr. Arush Kaushal : Intelligent Disaster Management System

M.Tech Students Supervised:

Anubhav Patric : Power optimization in Manycore Processors

Suchi Johari : Comparative Studies of Topologies in 3D NoC

Arvind Kumar : Mapping Algorithms for Networks on Chip

Ravi Shankar Jha : Data Synchronization in M2M Communication Through Cloud

Mukesh Kumar Tripathi : Establishing trust in cloud computing security with the help of inter-clouds

Keshav Kaundle : Network Architecture and System Designing in IoT

Mukesh Sharma : Security and Privacy Mechanism in IoT

Shrishti Kak : Heartbeat Monitoring Using Zigbee Network

Kapil Sharma : Enery Efficiency in Wireless Sensor Networks

Piyush Chauhan : Enery Conservation Using Dinamic Voltage Frequency Scalling

Arush Kaushal : Face mask detection using Machine Learning

M.Tech. Students Supervising:

 

Open Project Titles:

1. Implementing Model predictive Control reinforcement learning Tasks in Cyber-Physical Systems
The reinforcement learning-based model predictive control can improve the control performance effectively. And the numerical simulations are given to demonstrate the effectiveness of the proposed approach.

2. Smart Grids: A Cyber-Physical Systems Perspective
Smart grids are electric networks that employ advanced monitoring, control, and communication technologies to deliver reliable and secure energy supply, enhance operation efficiency for generators and distributors, and provide flexible choices for prosumers. Smart grids are a combination of complex physical network systems and cyber systems that face many technological challenges.

3. Software-defined digital twins mapping on Networks on Chip
A complex computational task of a physical system is digitally replicated in connected IP cores of Networks on Chip to enhance the performance of system. The complete physical process is divided in small modules and each module is mapped on processing tile of Networks on chip.

4. Probabilistic Graph Models with Kalman Estimator
Bayes filters, such as the Kalman and particle filters, have been used in sensor fusion to integrate two sources of information and obtain the best estimate of unknowns. The efficient integration of multiple sensors requires deep knowledge of their error sources. Some sensors, such as Inertial Measurement Unit (IMU), have complicated error sources.

Minor Project Titles:

Machine Learning (ML) for IoT
Machine learning can help demystify the hidden patterns in IoT data by analyzing massive volumes of data using sophisticated algorithms. Machine learning inference can supplement or replace manual processes with automated systems using statistically derived actions in critical processes. There are a wide variety of data science libraries available (e.g., Tensorflow®, Keras, Scikit-learn) for developing machine learning models. Cumulocity IoT Machine Learning allows models to be developed in data science frameworks of your choice. These models can be transformed into industry-standard formats using open-source tools and made available for scoring within Cumulocity IoT. Cumulocity IoT Machine Learning provides easy access to data residing in operational and historical data stores for model training. It can retrieve this data on a periodic basis and route it through an automated pipeline to transform the data and train a machine-learning model. Data can be hosted on Amazon® S3 or Microsoft® Azure® Data Lake Storage, as well as local data storage, and retrieved using prebuilt Cumulocity IoT DataHub connectors.

Markovian jump systems (MJSs)
These systems can be regarded as a special type of jump system, whose jumping law governing the switches among the subsystems are a Markovian chain or process . Similar to other Cyber-Physical Systems, the subsystems in MJSs are usually described by some type of dynamic equations, while a Markov process that can be either continuous time or discrete time describes the jumping law. On the other hand, MJSs also are hybrid dynamic systems typically consisting of both the dynamic state space and the set of discrete events, where a Markov process describes the discrete events for MJSs

Quantum Machine Learning and Quantum Communication Networks
The two emerging technologies are machine learning and artificial intelligence, and as we all know, quantum computing is one of the most revolutionary developments in technology. Researchers are considering combining machine learning and quantum computing with the advancements in both fields. As a result, quantum machine learning-a fusion of these two fields-has evolved. It has the capacity to effectively address a wide range of real-world issues. Both fields will surely benefit from the combined results of the two fields. When the potential of quantum principles and its peculiarities is employed with machine learning, quantum machine learning reaches a very advanced level.

Undergraduate projects supervised:

2016       Intelligent Stick Navigator for blind persons

2016       Green House Monitoring using IoT

2016       SCADA implementation using IoT

2015       Waste management in smart city using IoT.

2015       Car security using IoT protocol.

2015       IoT based remote sensing.

2015      Electromagnetic lock interface through LTE network.

2014      NoC simulator for diffirent topologies

2014      GALS communication in NoC

2012      Bio Metric Password Protected Mail Server Design.

2012    RF ID Based Toll Tax Charging System.

2012    Mobile Gyroscope Controlled Surveillance Robot.

2012    Modern Control System Mapping on Networks-on-Chip

2012    Job portal with mobile alert.

2011    Piezoelectric generator for street light.

2011    GPS based controlled railway crossing.

2010    An embedded platform for intelligent traffic control.

2010    Electronic Energy Meter with Instant Billing.

2009    DELSIC: A Delay Simulator for Interconnect Circuits.

2009    An Embedded Application for Driverless Metro Train.

2009    D-Torus Topology in Networks-on-Chip: A Perspective Study.

2009    An Intelligent Water Management and Distribution System.

2009    Emergency Shutdown Procedure for Applications in Mass Rapid Transit System

2009    Peltier    Effect Based Solar Powered Air Conditioning System.

2008    Closed-form expressions for extraction of capacitances in multilayer VLSI interconnects

2008    Optimal Dynamic Routing and Flow Control in Interconnection Networks-on-Chip.

2008    Time-Domain Analysis of VLSI Interconnects Considering Oscillatory Inputs.

2008    Smart Wireless Temperature Data Logger.

2008    An Embedded Platform for GSM/CDMA Controlled Surveillance Robot.

2007    RJ-11 Interfaced Embedded Platform for DTMF Based Remote Control System.

2007    Compiler design for 64 bit RISC architecture.

2007    Six Channel Data Acquisition System.        

2007    JUIT-Image Based Authentication System.

2006    Voice  Coded Stepper Motor Control.

2006    D25 LPT Port based Network Controlled System.

2006    Four Channel Embedded SCADA System.