The IES laboratory research topics are both fundamental (basic) and applied researches. The main topics for the theoretical research are learning systems, machine learning and for the applied research are wearable computing, mobile robotics, neural networks hardware implementation and ambient intelligent systems development.
Main research topics
Hardware implementation of artificial neural networks in FPGA circuits
The aim is to test and compare the method developed using System Generator with the HDL description of the ANN and the new high level synthesis tools like Vivado Design Suite HLx. For implementation we use Xilinx All Programmable FPGAs or the Xilinx’s All Programmable SoC (Zynq-7000 SoC, Zynq UltraScale+ MPSoC) to integrate the software programmability of a processor with the hardware programmability of an FPGA. The ANN implemented in this way is used for real-time recognition of the human activity patterns.
Intelligent embedded systems
with learning capacity and adaptive behaviour
We design a hardware-software co-design platform based on FPGA, developed for fast prototyping of embedded systems using hardware modules that can be easily connected and "driver" modules that can manage I/O devices and sensors basic behavior. Using ANN to add learning capabilities and adaptive behavior is essential for an intelligent system and the use of FPGA is an important feature in terms of their hardware implementation. Among possible applications are intelligent computer peripherals enabling people with any kind of handicap to use computer and communicate, as any kind of industrial or domestic device with embedded and hidden intelligence at user for prosthetic, automotive, "domotic" and automation fields where the trend is to produce easy-to-use devices.
Assistive robots and automated guided vehicles (AGV)
The main goal is to develop a telepresence or assistive robots able to be remotely controlled or autonomous movement, obstacle detection and avoidance, video streaming of the on board camera images, etc. Such a robot could be used for daily life assistance of older adults or persons with different type of disabilities.
Activity and health status monitoring platform developement
Development of an intelligent platform (with learning capabilities and adaptive behaviour) for health condition monitoring of elderly or persons with disabilities. For health status monitoring we developed a platform based on a Raspberry Pi minicomputer to acquire regarding body temperature, heart rate, oxygen saturation, ECG, EMG, galvanic skin response, blood pressure, etc. These data are uploaded in a database and could be monitored by entities providing health services.The data are analyzed for extracting patterns using neural networks and alerting in the event of deviation from normal values.
e-Health and Ambient assisted living systems
For human activity monitoring we use multiple commercial and self-developed power-optimized wearable sensor tags that combines the performance of a Bluetooth low energy (BLE) transceiver with 6-9 axis motion sensors (accelerometer + gyroscope 9 magnetometer). We acquire data using these tags and upload data in a database for remote monitoring and further processing. Data is analyzed for behavior patterns extraction using neural networks and alert in case of deviation from normal values. Also we aim to integrate the intelligent home sensors (presence sensor, temperature, humidity, luminosity, gas sensors.) for ambient monitoring.
Human computer interfaces
Artificial Intelligence breakthroughs are providing innovative solutions to a variety of problems. Therefore, we are developing adaptive systems that are capable of recognizing physiological events by training machine learning models to interpret EEG signals. Implementing such technologies can have a significant impact, from providing much desired control to paralyzed patients to improving a plethora of everyday activities.
