Research
Research Interests
Hyperspectral imaging (HSI) and remote sensing
Near-infrared (NIR) and Fourier-transform infrared (FTIR) spectroscopy
Deep hyperspectral image reconstruction and explainable artificial intelligence (XAI)
Organic compound-based nanozymes and portable biosensors for toxic molecule detection
Real-time process monitoring in food and agricultural systems
Research
Our lab focuses on developing innovative sensing technologies and intelligent systems to address critical challenges in food, and agricultural system monitoring. We integrate spectroscopy, advanced imaging, machine learning, and organic nanozyme to create next-generation solutions that are rapid, non-destructive, portable, and cost-effective.
Key research areas include:
Hyperspectral Imaging and Remote Sensing
We utilize HSI for detailed spatial and spectral analysis to assess quality, detect contamination, and monitor stress in crops and food products. Applications range from controlled lab setups to field-based systems including UAV and satellite platforms.
NIR and FTIR Spectroscopy
We apply NIR and FTIR spectroscopy for real-time, non-invasive characterization of agricultural and biological materials, enabling quality evaluation, process optimization, and authenticity detection.
Deep Hyperspectral Image Reconstruction and Explainable AI
We develop deep learning models that reconstruct hyperspectral data from RGB images, aiming to reduce hardware complexity while retaining accuracy. We emphasize the use of XAI to ensure model interpretability, reliability, and adoption in real-world applications.
Nanozyme-Enabled Biosensing
We design organic compound-based nanozymes and incorporate them into portable biosensing platforms for the detection of toxic compounds such as pesticides, allergens, and heavy metals.
Electronic Nose (E-nose) Systems
We employ e-nose systems for volatile compound analysis to detect spoilage, contamination, and product freshness. These sensor arrays mimic the human olfactory system and are integrated with machine learning for classification and prediction.
Real-Time Process Monitoring
We develop sensor-integrated platforms for real-time monitoring and control of food and agricultural processes, with a particular focus on drying operations. Using spectroscopy, imaging, and smart sensing technologies, we monitor critical parameters such as moisture and fat content during drying to ensure product quality, energy efficiency, and process optimization.
Overall, our goal is to drive innovation at the intersection of optical sensing, AI, and organic nanozyme to support sustainable and data-driven solutions across the food and agricultural sectors.
Supervised PhD Candidate to Completion and Graduation
Dong Hoon Lee (PhD dissertation defended on December 3, 2024)
Md. Toukir Ahmed (PhD dissertation defended on March 27, 2025)
Md Wadud Ahmed (PhD dissertation defended on April 10, 2025)
Supervised MS Candidate to Completion and Graduation
Runyu Zheng (MS dissertation defended on April 4, 2024)
Nathan Schumer (MS dissertation defended on August 1, 2024)