Combine harvesters are the source a large amount of noise in agriculture. Depending on different working conditions, the noise of such machines can have a significant effect on the hearing condition of drivers. Therefore, it is highly important to study the noise signals caused by these machines and find solutions for reducing the produced noise. The present study was carried out is order to obtain the fractal dimension (FD) of the noise signals in Sampo and John Deere combine harvesters in different operational conditions. The noise signals of the combines were recorded with different engine speeds, operational conditions, gear states, and locations. Four methods of direct estimations of the FD of the waveform in the time domain with three sliding windows with lengths of 50, 100, and 200 ms were employed. The results showed that the Fractal Dimension/Sound Pressure Level [dB] in John Deere and Sampo combines varied in the ranges of 1.44/96.8 to 1.57/103.2 and 1.23/92.3 to 1.51/104.1, respectively. The cabins of Sampo and John Deere combines reduced and enhanced these amounts, respectively. With an increase in the length of the sliding windows and the engine speed of the combines, the amount of FD increased. In other words, the size of the suitable window depends on the extraction method of calculating the FD. The results also showed that the type of the gearbox used in the combines could have a tangible effect on the trend of changes in the FD.

The most challenging in speech enhancement technique is tracking non-stationary noises for long speech segments and low Signal-to-Noise Ratio (SNR). Different speech enhancement techniques have been proposed but, those techniques were inaccurate in tracking highly non-stationary noises. As a result, Empirical Mode Decomposition and Hurst-based (EMDH) approach is proposed to enhance the signals corrupted by non-stationary acoustic noises. Hurst exponent statistics was adopted for identifying and selecting the set of Intrinsic Mode Functions (IMF) that are most affected by the noise components. Moreover, the speech signal was reconstructed by considering the least corrupted IMF. Though it increases SNR, the time and resource consumption were high. Also, it requires a significant improvement under nonstationary noise scenario. Hence, in this article, EMDH approach is enhanced by using Sliding Window (SW) technique. In this SWEMDH approach, the computation of EMD is performed based on the small and sliding window along with the time axis. The sliding window depends on the signal frequency band. The possible discontinuities in IMF between windows are prevented by the total number of modes and the number of sifting iterations that should be set a priori. For each module, the number of sifting iterations is determined by decomposition of many signal windows by standard algorithm and calculating the average number of sifting steps for each module. Based on this approach, the time complexity is reduced significantly with suitable quality of decomposition. Finally, the experimental results show the considerable improvements in speech enhancement under non-stationary noise environments.