Extraction and selection of statistical harmonics features for electrical appliances identification using k-NN classifier combined with voting rules method

Abstract

In this paper, we propose a novel framework for electrical appliances identification using statistical harmonicfeatures of current signals and the use of the k-NN classifier combined with a voting rule strategy. Harmonic coefficientsare computed over time using short-time Fourier series of the current signals. From these sequences of coefficients, themean, standard deviation, skewness, and kurtosis are computed, which provide the statistical harmonic features. Thisframework has three novelties: (i) selecting the best combination of statistical measures in the sense of classificationrate (CR); (ii) combining the k-NN classifier with the voting rule method in order to search for the best number ofvoting vectors; and (iii) selecting relevant features for the task of appliances identification by using one of the relevantfeature selection algorithms based on mutual information. Results evaluated on the Plaid dataset clearly show that themean and standard deviation statistics combination gives the best CR of 92% with 500 features and gives the minimalcomputing time compared to the system based on HMM models. Moreover, combining the k-NN classifier with thevoting rule using the above features increases the CR up to 95%. Using this combination, the results also show that anincrease of the training dataset size further improves identification performance results in terms of precision, sensitivity,and F-score. A feature selection procedure based on joint mutual information strategy shows that using a selected subsetof five features is sufficient, giving similar CR results to those obtained using the total number of features, whatever thetraining dataset size.