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

Sensors ◽  
2019 ◽  
Vol 19 (12) ◽  
pp. 2695 ◽  
Author(s):  
Nam Kyun Kim ◽  
Kwang Myung Jeon ◽  
Hong Kook Kim
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Event Detection ◽  
Background Noise ◽  
Source Separation ◽  
Error Rates ◽  
Superior Performance ◽  
Detection Accuracy ◽  
Noisy Signal ◽  
Recognition Error

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.

scholarly journals Automatic Modulation Classification Based on Deep Feature Fusion for High Noise Level and Large Dynamic Input

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2117
Author(s):  
Hui Han ◽  
Zhiyuan Ren ◽  
Lin Li ◽  
Zhigang Zhu
Keyword(s):  
Neural Network ◽  
Frequency Domain ◽  
Noise Level ◽  
Background Noise ◽  
Dynamic Range ◽  
Feature Fusion ◽  
Superior Performance ◽  
Modulation Classification ◽  
High Background ◽  
Automatic Modulation Classification

Automatic modulation classification (AMC) is playing an increasingly important role in spectrum monitoring and cognitive radio. As communication and electronic technologies develop, the electromagnetic environment becomes increasingly complex. The high background noise level and large dynamic input have become the key problems for AMC. This paper proposes a feature fusion scheme based on deep learning, which attempts to fuse features from different domains of the input signal to obtain a more stable and efficient representation of the signal modulation types. We consider the complementarity among features that can be used to suppress the influence of the background noise interference and large dynamic range of the received (intercepted) signals. Specifically, the time-series signals are transformed into the frequency domain by Fast Fourier transform (FFT) and Welch power spectrum analysis, followed by the convolutional neural network (CNN) and stacked auto-encoder (SAE), respectively, for detailed and stable frequency-domain feature representations. Considering the complementary information in the time domain, the instantaneous amplitude (phase) statistics and higher-order cumulants (HOC) are extracted as the statistical features for fusion. Based on the fused features, a probabilistic neural network (PNN) is designed for automatic modulation classification. The simulation results demonstrate the superior performance of the proposed method. It is worth noting that the classification accuracy can reach 99.8% in the case when signal-to-noise ratio (SNR) is 0 dB.

Automatic Segmentation and Classification of COVID-19 CT Image Using Deep Learning and Multi-Scale Recurrent Neural Network Based Classifier

2021 ◽  
Vol 11 (10) ◽  
pp. 2618-2625
Author(s):  
R. T. Subhalakshmi ◽  
S. Appavu Alias Balamurugan ◽  
S. Sasikala
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Deep Learning ◽  
Recurrent Neural Network ◽  
Automatic Segmentation ◽  
Ct Images ◽  
Superior Performance ◽  
Multi Scale ◽  
Proposed Model ◽  
Class Labels

In recent times, the COVID-19 epidemic turn out to be increased in an extreme manner, by the accessibility of an inadequate amount of rapid testing kits. Consequently, it is essential to develop the automated techniques for Covid-19 detection to recognize the existence of disease from the radiological images. The most ordinary symptoms of COVID-19 are sore throat, fever, and dry cough. Symptoms are able to progress to a rigorous type of pneumonia with serious impediment. As medical imaging is not recommended currently in Canada for crucial COVID-19 diagnosis, systems of computer-aided diagnosis might aid in early COVID-19 abnormalities detection and help out to observe the disease progression, reduce mortality rates potentially. In this approach, a deep learning based design for feature extraction and classification is employed for automatic COVID-19 diagnosis from computed tomography (CT) images. The proposed model operates on three main processes based pre-processing, feature extraction, and classification. The proposed design incorporates the fusion of deep features using GoogLe Net models. Finally, Multi-scale Recurrent Neural network (RNN) based classifier is applied for identifying and classifying the test CT images into distinct class labels. The experimental validation of the proposed model takes place using open-source COVID-CT dataset, which comprises a total of 760 CT images. The experimental outcome defined the superior performance with the maximum sensitivity, specificity, and accuracy.

scholarly journals Real-time event detection using recurrent neural network in social sensors

2019 ◽  
Vol 15 (6) ◽  
pp. 155014771985649 ◽  
Author(s):  
Van Quan Nguyen ◽  
Tien Nguyen Anh ◽  
Hyung-Jeong Yang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Language Processing ◽  
Recurrent Neural Network ◽  
Event Detection ◽  
Word Embedding ◽  
Series Data ◽  
Accuracy Score ◽  
Data Set ◽  
Size Limitation

We proposed an approach for temporal event detection using deep learning and multi-embedding on a set of text data from social media. First, a convolutional neural network augmented with multiple word-embedding architectures is used as a text classifier for the pre-processing of the input textual data. Second, an event detection model using a recurrent neural network is employed to learn time series data features by extracting temporal information. Recently, convolutional neural networks have been used in natural language processing problems and have obtained excellent results as performing on available embedding vector. In this article, word-embedding features at the embedding layer are combined and fed to convolutional neural network. The proposed method shows no size limitation, supplementation of more embeddings than standard multichannel based approaches, and obtained similar performance (accuracy score) on some benchmark data sets, especially in an imbalanced data set. For event detection, a long short-term memory network is used as a predictor that learns higher level temporal features so as to predict future values. An error distribution estimation model is built to calculate the anomaly score of observation. Events are detected using a window-based method on the anomaly scores.

scholarly journals Stem Control of a Sliding-Stem Pneumatic Control Valve Using a Recurrent Neural Network

2013 ◽  
Vol 2013 ◽  
pp. 1-7 ◽  
Author(s):  
Mohammad Heidari ◽  
Hadi Homaei
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Neural Control ◽  
Closed Loop ◽  
Control Valve ◽  
Superior Performance ◽  
Pneumatic Control ◽  
Response Characteristics ◽  
Control Scheme ◽  
Simulation Results

This paper presents a neural scheme for controlling an actuator of pneumatic control valve system. Bondgraph method has been used to model the actuator of control valve, in order to compare the response characteristics of valve. The proposed controller is such that the system is always operating in a closed loop, which should lead to better performance characteristics. For comparison, minimum- and full-order observer controllers are also utilized to control the actuator of pneumatic control valve. Simulation results give superior performance of the proposed neural control scheme.

scholarly journals Forward-Backward Convolutional Recurrent Neural Networks and Tag-Conditioned Convolutional Neural Networks for \\Weakly Labeled Semi-supervised Sound Event Detection

2021 ◽  
Author(s):  
Janek Ebbers ◽  
Reinhold Haeb-Umbach
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Recurrent Neural Network ◽  
Event Detection ◽  
Forward Direction ◽  
Time Step ◽  
Sound Event ◽  
Sound Event Detection ◽  
Validation Set ◽  
Classi Fication

In this paper we present our system for thedetection and classi-fication of acoustic scenes and events (DCASE) 2020 ChallengeTask 4: Sound event detection and separation in domestic envi-ronments. We introduce two new models: the forward-backwardconvolutional recurrent neural network (FBCRNN) and the tag-conditioned convolutional neural network (CNN). The FBCRNNemploys two recurrent neural network (RNN) classifiers sharing thesame CNN for preprocessing. With one RNN processing a record-ing in forward direction and the other in backward direction, thetwo networks are trained to jointly predict audio tags, i.e., weak la-bels, at each time step within a recording, given that at each timestep they have jointly processed the whole recording. The pro-posed training encourages the classifiers to tag events as soon aspossible. Therefore, after training, the networks can be appliedto shorter audio segments of, e.g.,200 ms, allowing sound eventdetection (SED). Further, we propose a tag-conditioned CNN tocomplement SED. It is trained to predict strong labels while using(predicted) tags, i.e., weak labels, as additional input. For train-ing pseudo strong labels from a FBCRNN ensemble are used. Thepresented system scored the fourth and third place in the systemsand teams rankings, respectively. Subsequent improvements allowour system to even outperform the challenge baseline and winnersystems in average by, respectively,18.0 %and2.2 %event-basedF1-score on the validation set. Source code is publicly available athttps://github.com/fgnt/pb_sed

Sign in / Sign up

Export Citation Format

Share Document