A piecewise linear recursive approximation scheme is applied to the computation of the sigmoid function and its derivative in artificial neurons with learning capability. The scheme provides high approximation accuracy with very low memory requirements. The recursive nature of this method allows for the control of the rate accuracy/computation-delay just by modifying one parameter with no impact on the occupied area. The error analysis shows an accuracy comparable to or better than other reported piecewise linear approximation schemes. No multiplier is needed for a digital implementation of the sigmoid generator and only one memory word is required to store the parameter that optimises the approximation.

This paper describes the development of efficient hardware/software (HW/SW) neuro-fuzzy systems. The model used in this work consists of an adaptive neuro-fuzzy inference system modified for efficient HW/SW implementation. The design of two different on-chip approaches are presented: a high-performance parallel architecture for offline training and a pipelined architecture suitable for online parameter adaptation. Details of important aspects concerning the design of HW/SW solutions are given. The proposed architectures have been implemented using a system-on-a-programmable-chip. The device contains an embedded-processor core and a large field programmable gate array (FPGA). The processor provides flexibility and high precision to implement the learning algorithms, while the FPGA allows the development of high-speed inference architectures for real-time embedded applications.

The progressive integration of driver assistance systems (DAS) into vehicles in recent decades has contributed to improving the quality of the driving experience. Currently, there is a need for individualization of advanced DAS with the aim of improving safety, security and comfort of the driver. In particular, the need to adapt the vehicle to individual preferences and requirements of the driver is an important research focus. In this work, an individualized and non-intrusive monitoring system for real-time driver support is proposed. The kernel of the system is a driver identification module based on driving behavior signals and a high-performance machine learning technique. The scheme is suitable for the development of single-chip embedded systems. Moreover, most of the measurement units used in this research are nowadays available in commercial vehicles, so the deployment of the system can be performed with minimal additional cost. Experimental results using a reduced set of features are very encouraging. Identification rates greater than 75% are obtained for a working set of 11 drivers, 86% for five-driver groups, 88% for four-driver groups, and 90% for three-driver groups.

A controlled accuracy approximation scheme of the sigmoid function for artificial neuron implementation based on Taylor's theorem and the Lagrange form of the error is proposed. The main advantages of the proposed solution are two: it provides a systematic way to guarantee the required accuracy and it reuses the circuitry of the linear part of the neuron to compute the sigmoid function. The sigmoid derivative is also available for artificial neural networks with online learning capabilities.