A System-on-Chip Development of a Neuro–Fuzzy Embedded Agent for Ambient-Intelligence Environments

Abstract

This paper presents the development of a neuro-fuzzy agent for ambient-intelligence environments. The agent has been implemented as a system-on-chip (SoC) on a reconfigurable device, i.e., a field-programmable gate array. It is a hardware/software (HW/SW) architecture developed around a MicroBlaze processor (SW partition) and a set of parallel intellectual property cores for neuro-fuzzy modeling (HW partition). The SoC is an autonomous electronic device able to perform real-time control of the environment in a personalized and adaptive way, anticipating the desires and needs of its inhabitants. The scheme used to model the intelligent agent is a particular class of an adaptive neuro-fuzzy inference system with piecewise multilinear behavior. The main characteristics of our model are computational efficiency, scalability, and universal approximation capability. Several online experiments have been performed with data obtained in a real ubiquitous computing environment test bed. Results obtained show that the SoC is able to provide high-performance control and adaptation in a life-long mode while retaining the modeling capabilities of similar agent-based approaches implemented on larger computing machines.

A new approach for data processing in supply chain network based on FPGA

“…The application of FPGA technology to industrial control systems [63,64] is one of the hot topics. FPGA is usually used to control the PWM wave in electric drive and power electronics systems [65], so as to build a SoC (system on a chip) [66] and designed fuzzy logic controller [67]. From investigation, one can notice some advantages of FPGA as a logic controller.…”

Hardware implemented adaptive neuro fuzzy system

“…SYSTEM GENERATOR BASED HARDWARE IMPLEMENTATION With both methods we designed an IP Core from the adaptive neuro fuzzy system, which we connected to a processor bus system. We implemented it in hardware as a SOC type system containing reconfigurable parts [6]. In this section we present the pipeline structure system.…”

An FPGA-based multiprocessor-architecture for intelligent environments

“…70 The intelligent capabilities of the system are achieved by means 71 of Neuro-Fuzzy Systems (NFS) which have the ability to learn 72 and adapt from incoming samples (the main feature of neural net-73 works) and also the ability to perform imprecise or vague reason-74 ing (the main feature of fuzzy systems) [8]. This twofold feature 75 makes NFS very suitable for AmI environments, as has been shown 76 by the authors in previous works [10][11][12]. 77 Bearing in mind this NFS structure, an efficient architecture has 78 been developed to be implemented in the FPGA.…”