Improvement of chainsaw sounds identification in the forest environment using maximum ratio combining and classification algorithme

Abstract

To better combat the devastation of the protected forests in Côte d’Ivoire, a study was conducted to create a technique for detecting the acoustic signals produced by chainsaws deployed to fell trees in these areas. To improve the recognition rate of chainsaw sounds in a forest environment and increase the detection range of the recognition system, we are implementing the maximum ratio combining (MRC) technique on a microphone array. Therefore, the employment of an identification system is compared using one (01) microphone against the outcomes obtained by adopting system with three (03), six (06), and twelve (12) microphones. The use of MRC is then contrasted with an alternative recombining approach, referred to as simple summation (SS). The SS is characterized by the mere addition of signals acquired by the network in the frequency domain. The MRC was employed on various microphone arrangements, accounting for varying degrees of attenuation experienced by chainsaw sounds. The K-Nearest Neighbors, in combination with Mel Frequency Cepstral Coefficients (MFCC), was employed to detect chainsaw sounds within the 16 kHz central frequency octave band. MRC applied to microphone arrays provided superior outcomes than simple summation. The enhancement in terms of classification rate ranged from [18; 51], favouring MRC. Moreover, it extended the chainsaw detection range from 520 m (using one microphone) to 1210 m (using a 12-microphone array). Taking into account the criteria for selecting an optimum microphone array, including classification rate, number of microphone nodes, information processing time and detection range, the six-microphone array was chosen as the best configuration. This configuration boasts a theoretical detection range of 1040 meters