Skip Navigation

The College of Engineering - Electrical & Computer Engineering

Research at Rowan ECE

Rowan's Department of Electrical and Computer Engineering has undertaken many advanced research projects for a variety of private, government, and military interests. The contributers for our researches in various fields:

Signal & Image Processing
Computational Intelligence & Pattern Recognition
Power Systems and Renewable Energy
Discrete Event Systems (DES)
Evolutionary Virtual Realty (VR) Platforms for Intelligent Systems Health Management
Digital, Analog and Mixed Signal VLSI Circuit Design
Digital Speech Processing


Signal & Image Processing
It is one of the core fields of electrical engineering deals with developing algorithmic and mathematical techniques for intelligent processing of signal and images so that more relevant and reliable information can be extracted from them. Several application areas are researched at Rowan ECE:
Dr. Ravi Ramachandran is developing robust feature extraction techniques for speech and speaker recognition. Dr. Shreekanth Mandayam collaborating with his colleagues at Fox Chase Cancer Center is working on developing new image analysis techniques for radiodense tissue estimation from digital mammograms. Also, with a grant from National Science Foundation, he and his Civil Engineering colleague Dr. Sukumaran, along with a team of ECE students are developing 3-D image recognition and analysis techniques for identifying different types of sand particles. Dr. Robi Polikar and his students, along with his colleagues at University of Pennsylvania and Drexel are studying various signal processing and automated classification techniques for early diagnosis of Alzheimer's disease from electroencephalogram recordings. Their work is funded by the National Institutes of Health and is being conducted at Rowan’s Signal Processing and Pattern Recognition Lab
 
Back to the top  


Computational Intelligence & Pattern Recognition
Will computers ever be able to make intelligent decisions based on the currently available information and previously acquired experience and knowledge? We are far from it, but progress is being made: Dr. Polikar leads the Signal Processing and Pattern Recognition Laboratory’s (SPPRL) research efforts on various computational intelligence and pattern recognition problems. With a generous funding from the National Science Foundation, Dr. Polikar and his students are developing new algorithms that allow computers to progressively learn from new data without forgetting the previously acquired knowledge, a concept known as incremental learning. He is also working on addressing the problem of missing features, a highly annoying yet real world problem of making intelligent decisions even when unreliable or partially missing data. Yet, another problem intimately involved with computational intelligence tackled at SPPRL is data fusion: the ability to intelligently combine and take advantage of information coming from multiple information sources.
Back to the top


Power Systems and Renewable Energy
Industry applied research involves in solving the electric power systems technology and efficiency, sustainable design, innovation and new product development. Dr. Jansson focuses on increasing electric power system reliability and efficiency in the transmission, distribution, and generation areas via the use of emerging distributed electricity technologies (fuel cells, microturbines dispersed renewable electric systems, etc) and computer analysis of electric transmission and distribution lines and complex systems. His work in sustainability in electricity generation and end use technologies concentrates on high efficiency end use devices, energy auditing, energy analysis techniques, solar, wind, geothermal, and other novel and renewable energy technologies.

His achievements include being named a Summer Advancement Fellow (2005) for the New Jersey Higher Education Partnership for Sustainability of which he is an elected Vice-President, receiving the 2003 Engineering Education Excellence Award from the New Jersey Society of Professional Engineers, and being awarded the New Century Scholars Fellowship in 2002 (supported by the National Science Foundation) at Stanford University. His research also includes: sustainable electric product and equipment design, the life-cycle assessment (LCA) techniques, equipment life extension (ELE) projects and new product design for the environment. Completed and active projects include: the development of a life cycle management system for high pressure sodium streetlamps funded by PHI lighting, Dark-to-Light (a Division of Lithonia), PSEG and Conectiv, Power Delivery; the New Jersey Anemometer Loan Program, Clean Energy Symposia, to name a few. His research sponsors include: NASA, National Science Foundation, DG XII of the European Union, EPSRC of the UK, NJDOT, PSEG, Conectiv, and other industries.
Back to the top


Discrete Event Systems (DES)
DES is a rapidly growing engineering field as a result of computer revolution. DES are typically processes associated with the systems which are discrete (in time and space), asynchronous (event-driven rather than clock driven), and nondeterministic. Such examples include manufacturing systems, computer networks, and air traffic control systems, etc. The application area being researched at Rowan ECE is modeling, design and optimization of reconfigurable manufacturing and de-manufacturing systems. Dr. Ying Tang and her students are developing models and algorithms to effective manage the decision making underlying the disassembly process with a high level of uncertainty. Another problem intimately involved with disassembly tackled at Rowan ECE is disassembly line design: the issues to move disassembly from manual to more efficient automated regime.

Software Security is of paramount importance, as more and more applications are being distributed in platform-independent forms over the Internet. One area being studied at Rowan ECE is to evaluate and develop methods of obfuscation. With a funding from Lockheed Martin Corporation, Dr. Ying Tang and her students are developing analytical metrics for qualitative measure of obfuscator performance. The development of an integrated method with encryption and obfuscation for software protection is also being undertaken.
Back to the top


Evolutionary Virtual Realty (VR) Platforms for Intelligent Systems Health Management
Acquisition of a Desktop, High-Resolution, Three Dimensional X-Ray computed Tomography (CT) System
This project is funded by Principal Investigator, National Science Foundation. Dr. Mandayam and his students are currently working on the development of inage processing algorithms for 3-D shape characterization from non-invasive measurements and validates the method using X-Ray CT. In collaboration with Dr. John Schmalzel and Dr. Robi Polikar, ECE department and Dr.Beena Sukumaran, CEE department at Rowan University.

A Data Fusion System for the Non-Destructive Evaluation of Non-Piggable Pipes
This was funded by Principal Investigator, US Department of Energy This project develops multi-sensor data fusion algorithms for predicting the integrity of gas transmission pipelines. In collaboration with Dr.Robi Polikar, ECE department, Dr.John Chen, ME department at Rowan University, Ronnie Miller, Physical Acoustics Corporation, Princeton, NJ and David Wang, Shell Oil Co., Houston, TX.

Acquisition of a Portable Large Scale Visualization System for Nondestructive Evaluation
This project develops immersive, navigable, interactive and evolutionary VR algorithms for visualizing in-line gas transmission pipeline inspections and their is funded by Principal Investigator ,National Science foundation. In collaboration with Dr.John Schmalzel, ECE department, Dr.Robi Polikar, ECE department at Rowan University and Richard Finlayson, Physical Acoustics Corporation, Princeton, NJ.

Three Dimensional Characterization and Modeling of Angular Materials, Co-Principal Investigator, National Science Foundation
This project develops image-processing algorithms for describing the 3-D shapes of particles in an aggregate mix. In collaboration with Dr.Beena Sukumaran, CEE department at Rowan University and Alaa Ashmaway, University of South Florida, Tampa, FL.This project is funded by Co-Principal Investigator, National Science Foundation.

Back to the top


Digital, Analog and Mixed Signal VLSI Circuit Design
Many of the products that we use everyday, from alarm clocks to vending machines, our cell phones and climate control for buildings and cars, all depend on the proper function of Integrated Circuits (IC’s). Students in Dr. Head's classes, clinics, and projects work on design and implementation of VLSI or Very Large Scale Integrated Circuits with applications in RF communications, speech processing and neural networks. Most speech processing is performed by digital computations that can be accomplished by general purpose microprocessors or by Application Specific IC’s (ASIC’s). Just such an ASIC was designed at Rowan University in the VLSI Design Lab to implement an algorithm developed by Dr. Ravi Ramachandran. These ASIC’s are used to enhance the speed and reliability of products such as cell phones, hearing enhancement devices, and security installations for industry and government. At the other end of the digital/analog divide many circuits that interface with the human body such as drug delivery devices and function monitors rely on the interpretation and processing of slow and widely varying current and voltage values comparable to the output of human "systems". At the Rowan VLSI Design Lab students are working on circuits that reproduce the functionality of biological neurons in order to better understand, and possibly enhance, the electro-chemical processes of the human body. VLSI circuit design is a crucial skill for modern technology and Rowan’s students are contributing to the knowledge base in this important field.
Back to the top


Digital Speech Processing
The ECE Department has undertaken several research projects in the field of Digital Speech proceesing. The list of research projects are:

(1).Neural networks for biodegradation kinetics (with Dr.Raul Ordonez and Dr.Kauser Jahan).
(2). Estimation of the SNR of a speech signal (funded by Rome Airforce Labs, with Dr.Linda Head)
(3). ASIC Implementation of speech processing algorithms (with Dr.Linda Head)
(4). Robust speaker recognition
(5). Robust vowel recognition
(6). Low bit rate speech coding
(7). Robust pitch detection for speech enhancement (with Dr.Shubha Kadambe)
(8). IIR Adaptive Filters (with Dr.Raul Ordonez and Dr.Linda Head)
(9). One and two dimensional signal processing theory
(10). Pattern recognition for vehicle reidentification – includes fusion strategies (funded by California Department of Transport, with Carlos Sun)

Robust speaker recognition refers to the task of identifying a speaker based on his/her voice regardless of how the signal is corrupted. Examples of signal corruption include noise, communication channel effects, cellular phone effects and nonlinear distortions. Speaker recognition is accomplished using a pattern recognition paradigm that encompasses (1) speech signal analysis, (2) signal enhancement, (3) feature extraction and (4) classification. Dr. Ravi and his students concentrates on achieving robustness at the signal, feature and classifier level which is extremely significant when the training and testing conditions are mismatched. At the signal level, a wavelet based pitch detection scheme is used to derive an adaptive speech enhancement filter to mitigate noise. Robust features that show little cariation due to noise and channel effects are being configured. Various classifiers and fusion strategies are used to render a reliable decision. Blind SNR estimation of the speech signal to be analyzed is used in deriving a confidence metric for the speaker recognition task.

Even with the tremendous increases in computation power since the advent of digital computers and the incredible advances in surveillance technology, the world of traffic surveillance and control has yet to feel their full effect. The field of Intelligent Transportation Systems (ITS) seeks to improve the current state of our transportation system by harnessing our increased communications, processing, and detection capabilities. There is great need for advanced surveillance capabilities to complement the rapid deployment of ITS strategies. This investigation deals with the potential of pattern recognition and multi-detector fusion for intelligent surveillance. Specifically, the focus is to study vehicle reidentification which is the task of matching a vehicle signal detected at one location (upstream) with the signal generated by the same vehicle detected at a downstream location at some later time. To perform the task at hand, different features that can distinguish one vehicle from another are derived from the detected signals. Identification is performed using a nearest neighbor classifier and a linear fusion strategy. Fusion of multiple detector signals is shown to improve vehicle reidentification accuracy. Feature based on color information from video cameras and the inductive signature feature obtained from inductive loop detectors are fused. Inductive signatures are unique deviations in the inductance of a loop detector caused by the passage of a vehicle. Inductive loop detectors are prevalent in many cities all over the world.

Back to the top