Convolutional Recurrent Neural Network-Based Event Detection in Tunnels Using Multiple Microphones

Abstract

This paper proposes a sound event detection (SED) method in tunnels to prevent further uncontrollable accidents. Tunnel accidents are accompanied by crashes and tire skids, which usually produce abnormal sounds. Since the tunnel environment always has a severe level of noise, the detection accuracy can be greatly reduced in the existing methods. To deal with the noise issue in the tunnel environment, the proposed method involves the preprocessing of tunnel acoustic signals and a classifier for detecting acoustic events in tunnels. For preprocessing, a non-negative tensor factorization (NTF) technique is used to separate the acoustic event signal from the noisy signal in the tunnel. In particular, the NTF technique developed in this paper consists of source separation and online noise learning. In other words, the noise basis is adapted by an online noise learning technique for enhancement in adverse noise conditions. Next, a convolutional recurrent neural network (CRNN) is extended to accommodate the contributions of the separated event signal and noise to the event detection; thus, the proposed CRNN is composed of event convolution layers and noise convolution layers in parallel followed by recurrent layers and the output layer. Here, a set of mel-filterbank feature parameters is used as the input features. Evaluations of the proposed method are conducted on two datasets: a publicly available road audio events dataset and a tunnel audio dataset recorded in a real traffic tunnel for six months. In the first evaluation where the background noise is low, the proposed CRNN-based SED method with online noise learning reduces the relative recognition error rate by 56.25% when compared to the conventional CRNN-based method with noise. In the second evaluation, where the tunnel background noise is more severe than in the first evaluation, the proposed CRNN-based SED method yields superior performance when compared to the conventional methods. In particular, it is shown that among all of the compared methods, the proposed method with the online noise learning provides the best recognition rate of 91.07% and reduces the recognition error rates by 47.40% and 28.56% when compared to the Gaussian mixture model (GMM)–hidden Markov model (HMM)-based and conventional CRNN-based SED methods, respectively. The computational complexity measurements also show that the proposed CRNN-based SED method requires a processing time of 599 ms for both the NTF-based source separation with online noise learning and CRNN classification when the tunnel noisy signal is one second long, which implies that the proposed method detects events in real-time.

Real time detection of acoustic anomalies in industrial processes using sequential autoencoders

“…For abnormal event detection using acoustic signals, mostly supervised sequential methods have been utilized like in Kim, Jeon, and Kim (2019) and Hayashi, Komatsu, Kondo, Toda, and Takeda (2018). However, only few approaches for AAD have been proposed for different application domains such as surveillance using a method based on OCSVM with a Radial Basis Function kernel (Aurino et al, 2014).…”

Smart Detection of Fire Source in Tunnel Based on the Numerical Database and Artificial Intelligence

“…Fire detection was handled by solving a nonlinear classification problem with a support vector machine (SVM) classifier, but it has a high false-alarm rate. To solve this problem, deep convolutional neural networks (CNNs) have been developed [19,20]. Without detailed engineering feature extraction, CNNs were claimed to automatically increase the fire-detection accuracy via deep learning.…”

Adaptive and Efficient Mixture-Based Representation for Range Data

“…As a result of the flexibility to model distributions whose parametric forms are unknown, the Gaussian Mixture Model (GMM) is a convenient and essential probability model used in many research domains, from image processing to machine learning [10][11][12][13][14]. Approaches have been proposed to address the various problems associated with GMMs, such as problems involving environment representation [15,16], registration [17][18][19][20][21][22], mapping [23][24][25], localization [26], and planning [25].…”