Dr. Majeed Hayat, chair and professor of electrical and computer engineering in the Opus College of Engineering, is the principal investigator on a National Science Foundation grant worth nearly $600,000 to develop novel improvements to provide efficient sensing and processing for hyperspectral imaging.
Hyperspectral imaging is commonly used in medical, environmental monitoring, military and agricultural fields, and is the process of capturing every wavelength for every pixel of an image. This process produces massive file sizes, which leads to typical lagging and processing delays associated with the management and transmission of files of that size.
Hayat and his colleagues will develop a hardware-software solution that captures only the wavelengths necessary for the task at hand, analyzes the captured image at the image source, and only transmits a verdict related to the task. This process would eliminate the need to both transmit and store large image files.
“Continuous increases in the spectral bands and pixel count of hyperspectral imaging sensors have led to prohibitively large amounts of data produced by these sensors that must be transmitted, stored, and analyzed in the cloud or on powerful local servers,” Hayat said. “Our goal is to meet the need and interest for novel software-hardware co-design approaches which sense only the spectral bands that are relevant to a given application and perform most of the sensor data processing and analysis as close as possible to the sensor array. These requirements will render a device that transmits only outcomes, thereby significantly reducing communication traffic and power consumption while improving speed, privacy and performance.”
The researchers have three aims with this project, which are to develop a Smart Event-Based Spectral Imager with advanced sensing algorithms that will identify and sense only the necessary wavelength related to the task; design intelligent analog readout integrated circuits, or “iROICs,” to enable on-chip implementation of the sensing algorithms; and develop novel machine learning models optimized for deployment on an edge device, tightly coupled with the iROIC circuits and the tunable filter it controls, to enable high performance hyperspectral object classification.
“Dr. Hayat and his team have identified an opportunity to make significant efficiency advancements in a technology that will continue to grow across industries and applications,” said Dr. Kristina Ropella, Opus Dean of the Opus College of Engineering. “Their work could become a gamechanger as we face challenges in computing power and energy demands amid a surge of data volume. I am grateful for their creative expertise to take this technology to the next level so it can better serve human needs.”
Hayat is joined on the project by Dr. Christinel Ababei, associate professor of electrical and computer engineering at Marquette; Dr. Payman Zarkesh-Ha, professor of electrical and computer engineering at the University of New Mexico; and Dr. Bradley Ratliff, associate professor of electrical and computer engineering at the University of Dayton.
Zarkesh-Ha has spoken at Marquette several times in recent years and will join the Department of Electrical and Computer Engineering faculty in fall 2026.
This grant is funded through NSF’s Division of Electrical, Communications and Cyber Systems, which supports research at the quantum, nano, micro and macro scales to fuel progress in the applications of engineering systems. ECCS promotes fundamental research in device and component technologies, power, controls, computation, networking, communications and cyber technologies to support integration and networking of intelligent systems.
