The Simulation and Estimation of Epidemics with Algorithms (SEEPIA) research group was formed at the very first weeks of the COVID-19 pandemic, in Grenoble Alpes University, France. The group was formed from independent researchers with various backgrounds (including mathematicians, control theory experts, signal processing experts, epidemiologists, and research engineers) who volunteered to synergize their expertise in modeling and forecasting the spread of the pandemic, under social and economic constraints.
This project has been one of my major fields of research since my PhD. Over the past years, our research team has contributed to many aspects of the problem, including theoretical modeling and signal processing, low-level signal processing engine design and implementation, and frontend software development. Some of our developments have been patented and licensed, leading to an FDA approved noninvasive fetal cardiac monitor system. Our research in this field has been continuously published in top-tier journals and presented in conferences. Our most recent scientific advances in this area include: a) online fetal ECG (fECG) extraction using online source separation algorithms; b) using the fECG for estimating and tracking fetal motions/rotations with respect to the maternal body coordinates; c) noninvasive fECG extraction from low-rank (as few as a single-channel) and time-varying mixtures; d) a novel semi-blind source separation algorithm for fECG extraction in presence of nonstationary noise and irregular maternal beats.
OSET is a collection of electrophysiological data and open source codes for biological signal generation, modeling, processing, and filtering, originally released in June 2006 and continuously updated. The latest version (the Pi version) can be cloned from my gitlab or github mirror repositories.
We have contributed to various aspects of adult and fetal electroencephalography, including:
Hardware accelerators are currently at the heart of many machine learning and (biomedical) signal processing systems. In a continuous research, which I have directed over the past years, my graduate students and I have contributed to developing efficient computational firmware based on field-programmable gate array (FPGA) technologies. Our objective has been to develop firmware modules that are common in many machine learning and biomedical signal processing systems. To date, our contributions include the development of FPGA-based linear and nonlinear filter units, automated deep and shallow neural network architectures, low-level toolboxes for matrix and vector manipulation on hardware, automated mechanisms for porting state-space systems onto FPGA, and an automated mechanism for transforming recursive signal processing pseudo-codes into FPGA-based modules. The ultimate objective is to develop an ecosystem of open-source firmware modules, which can be integrated and used to develop machine learning and signal processing hardware accelerators. Considering that the FPGA technology is also used for prototyping application specific integrated circuits (ASIC), the developed units can be eventually used for developing customized machine learning chips. The FPGA hardware systems required for our firmware design and evaluation have also been designed and manufactured by our own team and used as trainer boards for an FPGA lab. Besides the engineering work, some of our scientific contributions in this area include:
Interpretive Signal Processing (ISP) is an ad hoc technique for customizing signal processing algorithms for non-numeric data. Genomic data such as DNA or protein sequences are examples of such data. Contrary to the conventional approach of coding and decoding non-numeric data to numeric values, the main idea in ISP is to interpret signal processing algorithm as they are and to taylor similar operators for the direct manipulation of non-numeric data. We have studied two cases of ISP in our previous research: