Hip Kuusk

The goal is to study new solutions & principles for electrical impedance spectroscopy (EIS) with significantly improved metrological and functional characteristics, like higher measurement accuracy, resolution and speed, lower power consumption and wider frequency and dynamic ranges. New solutions enhance the existing and enable new applications of EIS in healthcare, biology and industries. The principles & solutions to measure biological & physiological properties of organs, tissues and microorganisms/pathogens, as well as of composites, alloys etc. are the subjects of the research. Unique low-cost low-power miniaturized high-resolution and flexible measurement components with various connectivity (IoT, BAN etc) will be created by new EIS groundings. An important R&D aspect is synchronous signal processing and communication in EIS sensor-arrays. Research aspects: sampling theory AI/ML) and metrology (eg novel calibration techniques, methods of implementation in biology and medicine.

"EXCITE brings together the topranked ICT research groups Estonia to work jointly on a focussed, yet broad and extendable, research programme. It will capitalize on the existing expertise to create synergies on the rich but fragmented landscape of the Estonian ICT research. The consortium will advance foundational theories of model verification and data analysis. On this groundwork, it will develop methods and tools for sound practices of designing and analyzing reliable and secure ICT systems processing large data volumes, as demanded by applications to domains of high socioeconomic relevance (cyberphysical and robotic systems, ehealth and biomedical systems). We will start with 10 cooperation themes with clearly defined objectives, methodology and expected results. These themes will be refined and redefined after 3 years. EXCITE will support research sustainability and provide a development opportunity for young researchers by financing 20-30 PhD students and postdocs.

Wireless biomedical sensors should dramatically reduce the costs and risks associated with personal health care while being more and more exploited by telemedicine and efficient e-health systems. However, because of the large power consumption of continuous wireless transmission, the battery life of the sensors is reduced for long-term use. Sub-Nyquist continuous-time discrete-amplitude (CTDA) sampling approaches using level-crossing analogto- digital converters (ADCs) have been developed to reduce the sampling rate and energy consumption of the sensors. However, traditional machine learning techniques and architectures are not compatible with the non-uniform sampled data obtained from levelcrossing ADCs. This project aims to develop analog algorithms, circuits, and systems for the implementation of machine learning techniques in CTDA sampled data in wireless biomedical sensors. This “near-sensor computing” approach, will help reduce the wireless transmission rate and therefore the power consumption of the sensor. The output rate of the CTDA is directly proportional to the activity of the analog signal at the input of the sensor. Therefore, artificial intelligence hardware that processes CTDA data should consume significantly less energy. For demonstration purposes, a prototype biomedical sensor for the detection and classification of sleep apnea will be developed using integrated circuit prototypes and a commercially available analog front-end interface. The sensor will acquire electrocardiogram and bioimpedance signals from the subject and will use data fusion techniques and machine learning techniques to achieve high accuracy.