Search

The paper presents a novel neural design methodology based on the End User Programming concept. The proposed solution empowers end users, by means of abstracting the low-level hardware functionalities, to hardware implement Artificial Neural Networks (ANN) using field-programmable gate arrays (FPGA). The main outcomes include rapid ANN design and hardware implementation. A case study of an ANN as a pattern recognition module of an artificial olfaction system trained to identify four coffee brands is presented. An extended analysis has been carried out regarding the recognition rates versus data representation.

The PI algorithm has proven to be a popular and widely used control method, due to its relative simplicity and robustness. Despite this, the linear nature of the algorithm means it doesn't provide optimal control to non-linear systems. This paper presents a novel method of improving the performance of the PI controller using an ANFIS network to provide gain scheduling. This control scheme is applied to a Boost Converter circuit and simulated within the PSIM modelling environment. The simulation results indicate that using the ANFIS controller provides a fast system response with minimal errors even under dynamic operating conditions. The ANFIS controller is also shown to simplify the design flow in comparison to the popular Fuzzy-PI gain scheduling method.

Urinary system disorders may be prevented by achieving a good body hydration level (BHL). This paper investigated a measurement platform set-up for detecting the shade of the (yellow) colour of urine and its integration with the IoT principles for providing ubiquitous services to the users (citizens). We propose a smart IoT-based holistic system that consists of a urine colour measurement component to be fitted in urinals. Based on RGB colour theory, the system was implemented using a myRio board, which interacts with a mobile application. Bio-samples (urine) gathered from volunteers were tested using this board and with a hand-held refractometer. The results showed that it is possible to infer the BHL by analysing the blue values of RGB colour and by comparison with the recommended urine colour chart. We believe that the proposed system promotes sustainable healthy lifestyle through its ubiquitous “on-the-go” self-test solution and raises BHL awareness in a “greener” and more “personal” way.