scholarly journals Design and Implementation of Opportunity Signal Perception Unit Based on Time-Frequency Representation and Convolutional Neural Network

Sensors ◽  
2021 ◽  
Vol 21 (23) ◽  
pp. 7871
Author(s):  
Zhongliang Deng ◽  
Hang Qi ◽  
Yanxu Liu ◽  
Enwen Hu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Frequency Domain ◽  
Utilization Efficiency ◽  
Prototype System ◽  
Positioning System ◽  
Signal Recognition ◽  
Positioning Systems ◽  
Time Frequency ◽  
Signal Perception

The traditional signal of opportunity (SOP) positioning system is equipped with dedicated receivers for each type of signal to ensure continuous signal perception. However, it causes a low equipment resources utilization and energy waste. With increasing SOP types, problems become more serious. This paper proposes a new signal perception unit for SOP positioning systems. By extracting the perception function from the positioning system and operating independently, the system can flexibly schedule resources and reduce waste based on the perception results. Through time-frequency joint representation, time-frequency image can be obtained which provides more information for signal recognition, and is difficult for traditional single time/frequency-domain analysis. We also designed a convolutional neural network (CNN) for signal recognition and a negative learning method to correct the overfitting to noisy data. Finally, a prototype system was built using USRP and LabVIEW for a 2.4 GHz frequency band test. The results show that the system can effectively identify Wi-Fi, Bluetooth, and ZigBee signals at the same time, and verified the effectiveness of the proposed signal perception architecture. It can be further promoted to realize SOP perception in almost full frequency domain, and improve the integration and resource utilization efficiency of the SOP positioning system.

Ultrasonic feature imaging of a multi-layered structure beyond a thin, highly reflective layer using a convolutional neural network

2021 ◽  
Vol 63 (4) ◽  
pp. 219-228
Author(s):  
Chuanyu Lu ◽  
Minghui Lu ◽  
Yiting Chen ◽  
Yongdong Pan
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Frequency Domain ◽  
Layered Structure ◽  
Composite Structures ◽  
Service Failure ◽  
Joint Analysis ◽  
Echo Signal ◽  
Training Time ◽  
Time Frequency

A helicopter propeller is a kind of multi-layered composite material bonding structure. Ensuring that composite structures are free from defects can reduce the risk of in-service failure and hence improve safety. As a common non-destructive testing (NDT) technology, ultrasonic testing is often used in the inspection of composite structures. However, a composite structure made of multiple thin-layer materials bonded together can cause a serious aliasing problem for echo signals when inspecting with ultrasound. In this study, the frequency-domain characteristics of an aliasing echo signal were analysed using the spectrum of the acoustic pressure reflection coefficient. Furthermore, the time-frequency joint analysis results of the echo signal were obtained using a continuous wavelet transform. Finally, the obtained time-frequency features of the echo signal were used to classify and image with a convolutional neural network (CNN). The results revealed that, as opposed to the direct imaging of the time- and frequency-domain features, the time-frequency wavelet map of a thin-walled multi-layered structure that was classified and imaged with a CNN exhibited greater clarity and better defect recognition ability. In addition, the training time of the CNN was 17 s and the classification accuracy of the verification set was high, reaching 97.8%.

scholarly journals Tool Wear Prediction Based on Multidomain Feature Fusion by Attention-Based Depth-Wise Separable Convolutional Neural Network in Manufacturing

2021 ◽  
Author(s):  
Guofa Li ◽  
Yanbo Wang ◽  
Jialong He ◽  
Yongchao Huo
Keyword(s):  
Neural Network ◽  
Tool Wear ◽  
Convolutional Neural Network ◽  
Frequency Domain ◽  
Prediction Accuracy ◽  
Feature Fusion ◽  
Prediction Method ◽  
Wear Prediction ◽  
Time Frequency ◽  
Tool Wear Prediction

Abstract Tool wear during machining has a great influence on the quality of machined surface and dimensional accuracy. Tool wear monitoring is extremely important to improve machining efficiency and workpiece quality. Multidomain features (time domain, frequency domain and time-frequency domain) can accurately characterise the degree of tool wear. However, manual feature fusion is time consuming and prevents the improvement of monitoring accuracy. A new tool wear prediction method based on multidomain feature fusion by attention-based depth-wise separable convolutional neural network is proposed to solve these problems. In this method, multidomain features of cutting force and vibration signals are extracted and recombined into feature tensors. The proposed hypercomplex position encoding and high dimensional self-attention mechanism are used to calculate the new representation of input feature tensor, which emphasizes the tool wear sensitive information and suppresses large area background noise. The designed depth-wise separable convolutional neural network is used to adaptively extract high-level features that can characterize tool wear from the new representation, and the tool wear is predicted automatically. The proposed method is verified on three sets of tool run-to-failure data sets of three-flute ball nose cemented carbide tool in machining centre. Experimental results show that the prediction accuracy of the proposed method is remarkably higher than other state-of-art methods. Therefore, the proposed tool wear prediction method is beneficial to improve the prediction accuracy and provide effective guidance for decision making in processing.

scholarly journals Using Convolutional Neural Network and a Single Heartbeat for ECG Biometric Recognition

Entropy ◽  
2021 ◽  
Vol 23 (6) ◽  
pp. 733
Author(s):  
Dalal A. AlDuwaile ◽  
Md Saiful Islam
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Frequency Domain ◽  
Recognition System ◽  
Ecg Signal ◽  
Biometric Recognition ◽  
Short Segment ◽  
Time Frequency ◽  
Learning Techniques ◽  
Proposed Model

The electrocardiogram (ECG) signal has become a popular biometric modality due to characteristics that make it suitable for developing reliable authentication systems. However, the long segment of signal required for recognition is still one of the limitations of existing ECG biometric recognition methods and affects its acceptability as a biometric modality. This paper investigates how a short segment of an ECG signal can be effectively used for biometric recognition, using deep-learning techniques. A small convolutional neural network (CNN) is designed to achieve better generalization capability by entropy enhancement of a short segment of a heartbeat signal. Additionally, it investigates how various blind and feature-dependent segments with different lengths affect the performance of the recognition system. Experiments were carried out on two databases for performance evaluation that included single and multisession records. In addition, a comparison was made between the performance of the proposed classifier and four well-known CNN models: GoogLeNet, ResNet, MobileNet and EfficientNet. Using a time–frequency domain representation of a short segment of an ECG signal around the R-peak, the proposed model achieved an accuracy of 99.90% for PTB, 98.20% for the ECG-ID mixed-session, and 94.18% for ECG-ID multisession datasets. Using the preprinted ResNet, we obtained 97.28% accuracy for 0.5-second segments around the R-peaks for ECG-ID multisession datasets, outperforming existing methods. It was found that the time–frequency domain representation of a short segment of an ECG signal can be feasible for biometric recognition by achieving better accuracy and acceptability of this modality.

scholarly journals Bearing Life Prediction Method Based on Parallel Multichannel Recurrent Convolutional Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Jianmin Zhou ◽  
Sen Gao ◽  
Jiahui Li ◽  
Wenhao Xiong
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Convolutional Neural Network ◽  
Frequency Domain ◽  
Time Series Data ◽  
Prediction Method ◽  
Remaining Useful Life ◽  
Series Data ◽  
Time Frequency ◽  
The Time Domain

To extract the time-series characteristics of the original bearing signals and predict the remaining useful life (RUL) more effectively, a parallel multichannel recurrent convolutional neural network (PMCRCNN) is proposed for the prediction of RUL. Firstly, the time domain, frequency domain, and time-frequency domain features are extracted from the original signal. Then, the PMCRCNN model is constructed. The front of the model is the parallel multichannel convolution unit to learn and integrate the global and local features from the time-series data. The back of the model is the recurrent convolution layer to model the temporal dependence relationship under different degradation features. Normalized life values are used as labels to train the prediction model. Finally, the RUL was predicted by the trained neural network. The proposed method is verified by full life tests of bearing. The comparison with the existing prognostics approaches of convolutional neural network (CNN) and the recurrent convolutional neural network (RCNN) models proves that the proposed method (PMCRCNN) is effective and superior in improving the accuracy of RUL prediction.

scholarly journals Bearing Fault Classification Using Ensemble Empirical Mode Decomposition and Convolutional Neural Network

Electronics ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1248
Author(s):  
Rafia Nishat Toma ◽  
Cheol-Hong Kim ◽  
Jong-Myon Kim
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Empirical Mode Decomposition ◽  
Vibration Signal ◽  
Ensemble Empirical Mode Decomposition ◽  
Fault Classification ◽  
Original Signal ◽  
Time Frequency ◽  
Mode Decomposition ◽  
Reconstructed Signal

Condition monitoring is used to track the unavoidable phases of rolling element bearings in an induction motor (IM) to ensure reliable operation in domestic and industrial machinery. The convolutional neural network (CNN) has been used as an effective tool to recognize and classify multiple rolling bearing faults in recent times. Due to the nonlinear and nonstationary nature of vibration signals, it is quite difficult to achieve high classification accuracy when directly using the original signal as the input of a convolution neural network. To evaluate the fault characteristics, ensemble empirical mode decomposition (EEMD) is implemented to decompose the signal into multiple intrinsic mode functions (IMFs) in this work. Then, based on the kurtosis value, insignificant IMFs are filtered out and the original signal is reconstructed with the rest of the IMFs so that the reconstructed signal contains the fault characteristics. After that, the 1-D reconstructed vibration signal is converted into a 2-D image using a continuous wavelet transform with information from the damage frequency band. This also transfers the signal into a time-frequency domain and reduces the nonstationary effects of the vibration signal. Finally, the generated images of various fault conditions, which possess a discriminative pattern relative to the types of faults, are used to train an appropriate CNN model. Additionally, with the reconstructed signal, two different methods are used to create an image to compare with our proposed image creation approach. The vibration signal is collected from a self-designed testbed containing multiple bearings of different fault conditions. Two other conventional CNN architectures are compared with our proposed model. Based on the results obtained, it can be concluded that the image generated with fault signatures not only accurately classifies multiple faults with CNN but can also be considered as a reliable and stable method for the diagnosis of fault bearings.

scholarly journals Automatic ECG Classification Using Continuous Wavelet Transform and Convolutional Neural Network

Entropy ◽  
2021 ◽  
Vol 23 (1) ◽  
pp. 119
Author(s):  
Tao Wang ◽  
Changhua Lu ◽  
Yining Sun ◽  
Mei Yang ◽  
Chun Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Wavelet Transform ◽  
Convolutional Neural Network ◽  
Continuous Wavelet Transform ◽  
Continuous Wavelet ◽  
Time Frequency ◽  
Ecg Signals ◽  
Rr Interval ◽  
Frequency Components ◽  
Fully Connected

Early detection of arrhythmia and effective treatment can prevent deaths caused by cardiovascular disease (CVD). In clinical practice, the diagnosis is made by checking the electrocardiogram (ECG) beat-by-beat, but this is usually time-consuming and laborious. In the paper, we propose an automatic ECG classification method based on Continuous Wavelet Transform (CWT) and Convolutional Neural Network (CNN). CWT is used to decompose ECG signals to obtain different time-frequency components, and CNN is used to extract features from the 2D-scalogram composed of the above time-frequency components. Considering the surrounding R peak interval (also called RR interval) is also useful for the diagnosis of arrhythmia, four RR interval features are extracted and combined with the CNN features to input into a fully connected layer for ECG classification. By testing in the MIT-BIH arrhythmia database, our method achieves an overall performance of 70.75%, 67.47%, 68.76%, and 98.74% for positive predictive value, sensitivity, F1-score, and accuracy, respectively. Compared with existing methods, the overall F1-score of our method is increased by 4.75~16.85%. Because our method is simple and highly accurate, it can potentially be used as a clinical auxiliary diagnostic tool.

Sign in / Sign up

Export Citation Format

Share Document