Desarrollo de un sistema embebido con tecnología DSP para un sistema multisensorial

This article consists in the development of an embedded system with DSP technology to be applied to a multi-sensory system (i.e. Electronic Nose). The idea of the present study was to improve the efficiency of the- se multisensory systems in portable applications, using different algorithms to classify three-class of volatile compounds, detected by a chemical gas sensor array. The Code Composer Studio (CCS) software was coupled with Matlab for programming the DSP TMS320F28335 card of Texas Instruments. The results were obtained from samples of wine of three different denominations (i.e., apple, red and Locker), which were then classified by processing algorithms (i.e. artificial neural networks). The system was validated by the technique of principal component analysis (PCA), to verify repeatability and selectivity of the measurement system. In the results, 83.4% of success rate in classification of the measures was obtained using DSP Hardware, through the imple- mentation of an Artificial Neuronal Network (ANN).