Mel-log energies analysis of authentic audible intrusion activities in a Malaysian forest

Wildlife has been endangered due to illegal activities.  This requires more effective surveillance measures.  Felling timber and poaching are regular illegal activities but challenging to detect.  Hence authorities should resort to modern technologies such as employing autonoumous surveillance to stop them.  The Malaysian forest audio data were recorded to lay a foundation in initiating a cheaper and practical approach.  Hence this paper reports the collection, processing and analysis of audio data in preparation to develop an autonomous sound event detection system.  The recording was an emulation of possible illegal activities in a reserved forest.  Sounds of chainsaw and hand hatchet cutting tree trunks were taken.  It was found that there was a distinct pattern in the Mel-log energies audio feature of the sound, which could be used to identify illegal activities.  Thus, it is believed that a detection through audio is a possible approach to be employed as one of the methods to stop illegal activities in the tropical reserve forests like those in Malaysia.

[1]  Tuomas Virtanen,et al.  Sound Event Detection in Multichannel Audio Using Spatial and Harmonic Features , 2017, DCASE.

[2]  Deepak Kumar Singh,et al.  Automatic detection of tree cutting in forests using acoustic properties , 2019 .

[3]  Mathieu Lagrange,et al.  Detection of overlapping acoustic events using a temporally-constrained probabilistic model , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[4]  P. Ranjit Jeba Thangaiah,et al.  An Improved Hybrid Feature Selection Method for Huge Dimensional Datasets , 2019, IAES International Journal of Artificial Intelligence (IJ-AI).

[5]  David Sánchez-Rodríguez,et al.  Acoustic Classification of Singing Insects Based on MFCC/LFCC Fusion , 2019, Applied Sciences.

[6]  M. Ariffin.  Enforcement against wildlife crimes in West Malaysia: the challenges , 2015 .

[7]  T. Virtanen,et al.  Convolutional Recurrent Neural Networks for Rare Sound Event Detection , 2017, DCASE.

[8]  Ankit Shah,et al.  DCASE2017 Challenge Setup: Tasks, Datasets and Baseline System , 2017, DCASE.

[9]  N. Tsiatis.  Understanding Distance Shooting and the Type of Firearm from the Analysis of Gunshot Sounds , 2016 .

[10]  Marina Yusoff,et al.  Review of anomalous sound event detection approaches , 2019 .

[11]  Kyogu Lee,et al.  Rare Sound Event Detection Using 1D Convolutional Recurrent Neural Networks , 2017, DCASE.

[12]  M. A. Yusnita,et al.  Statistical Descriptors of Mel-Bands Spectral Energy Features with Feature Reduction for Robust Accent Recognition in Malaysian English , 2015 .

[13]  Prajoy Podder,et al.  Comparative Performance Analysis of Hamming, Hanning and Blackman Window , 2014 .

[14]  Weifeng Li,et al.  Robust speech recognition by selecting mel-filter banks , 2017 .

[15]  Michael Khoo,et al.  Heat Map Visualizations of Seating Patterns in an Academic Library , 2014 .

[16]  Bezoui Mouaz,et al.  Speech Recognition of Moroccan Dialect Using Hidden Markov Models , 2019 .

[17]  Will L Kinard,et al.  Noise in a laboratory animal facility from the human and mouse perspectives. , 2010, Journal of the American Association for Laboratory Animal Science : JAALAS.

[18]  Steven W. Smith,et al.  The Scientist and Engineer's Guide to Digital Signal Processing , 1997 .