A5025732398- Physical Unclonable Functions (PUFs) and Hardware Security
- Advanced Memory and Neural Computing
- CRISPR and Genetic Engineering
- Anomaly Detection Techniques and Applications
- Maritime Navigation and Safety
- Digital Imaging for Blood Diseases
- Neuroscience and Neural Engineering
- Neural Networks and Reservoir Computing
- Underwater Acoustics Research
- Evolutionary Algorithms and Applications
- COVID-19 diagnosis using AI
- Ferroelectric and Negative Capacitance Devices
- Marine animal studies overview
- DNA and Biological Computing
- Advanced Malware Detection Techniques
Riverside Research Institute
2023
University of Cincinnati
2019-2022
Machine learning approaches are gaining popularity in the medical field for diagnostics, predictive analytics and general research. With data often being unlabeled or sparse to collect, there is a need unsupervised networks field. Self-Organizing Feature Maps (SOFM) common application of allow use their training. We applied chest x-ray images COVID-19 patients an SOFM network found distinct classification between sick healthy with average euclidean distance 1.1 1st 2nd winning neurons our...
Many currently available hardware implementations of the unsupervised self-organizing feature map (SOFM) algorithm utilize complementary metal–oxide–semiconductor (CMOS)-only circuits that often compromise key behaviors SOFM due to complexity. We propose a neuromorphic architecture harnessing unique properties ferroelectric field-effect transistors (FeFETs) and gated-resistive random access memory (RRAM) for in-memory computing implement algorithm. The FeFET-based synapse, organized in novel...
Evolvable hardware is attractive as a design strategy to engineers, but suffers due its lack of scalability larger systems. This work examines how designers can make use evolvable improve the security their systems, and create systems that are better resistant reverse engineering.
As commercial geospatial intelligence data becomes more widely available, algorithms using artificial need to be created analyze it. Maritime traffic is annually increasing in volume, and with it the number of anomalous events that might interest law enforcement agencies, governments, militaries. This work proposes a fusion pipeline uses mixture traditional identify ships at sea classify their behavior. A process visual spectrum satellite imagery automatic identification system (AIS) was...
Hardware Trojans (HT), or malicious attacks on electronic circuits, are difficult to detect within a design without novel analysis methods. Biological paradigms of self-defense exist, providing DNA as possible basis for Trojan detection. Genetic circuits utilize structures allow programmable functions in living cells. The programs used generate genetic their infancy, taking considerable time with limited success rate. In this study, we propose VeriGene new tool and method analyzing adapting...