Optical Fiber Distributed Vibration Sensing Using Grayscale Image and Multi-Class Deep Learning Framework for Multi-Event Recognition

Sun, Zhenshi; Liu, Kun; Jiang, Junfeng; Xu, Tianhua; Wang, Shuang; Zhou, Zhiping; Xue, Kang; Huang, Yuelang

doi:10.1109/jsen.2021.3089004

Cited by 23 publications

(8 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study transformed the 1D signal series after feature extraction into the 2D image on the basis of the phase space reconstruction theory (Huang et al, 2022) and the images were used as the inputs of the training models. The pixels of the time-series signals are filled in order according to the prearranged series (Sun et al 2021). The time-series signals are used to arrange the pixel order in the GSI (Sun et al 2021).…”

Section: Data Preprocessingmentioning

confidence: 99%

See 1 more Smart Citation

Signal Process of Ultrasonic Guided Wave for Damage Detection of Localized Defects in Plates: From Shallow Learning to Deep Learning

Shang,

Zhang,

Tang

et al. 2023

JDSIS

View full text Add to dashboard Cite

Ultrasonic-guided waves are one of the non-destructive inspection techniques used in structural health monitoring (SHM) for localized damage detection. Propagation, scattering, and dispersion of the Lamb waves Even though the great progress in the monitoring technology of the Lamb wave, the detection, identification, and quantification of structure damage still face challenges because of the complexity of the process in the propagation, scattering and dispersion of the Lamb wave. Machine learning methods, including shallow learning (support vector machine (SVM)) and deep learning methods (convolutional neural networks (CNN) and long short-term memory (LSTM)), in recent years have brought revolutionary opportunities for decoding the information of the Lamb wave. Therefore, the methodology structure was proposed from dataset collection, data preprocessing (including feature extraction, feature combination, and feature transformation), data training, and classification. Two different cases of damage types and damage sizes were designed in a COMSOL environment. The shallow learning method of the SVM model and the deep learning method of the CNN-LSTM model were compared with the defined time-series features and transformed images. The results showed that both shallow learning methods and deep learning methods can be used in the application of signal classification, while the deep learning method of CNN-LSTM exhibited higher accuracy in image classification, as compared to the SVM. The robustness of the proposed models has also been verified under noise interference. The results demonstrated that the deep learning architecture of CNN-LSTM has the potential to attain greater precision because of better feature extraction and processing ability than the shallow learning model of SVM. In addition, the performance of signal classification and image classification of SVM and CNN-LSTM models dramatically decreased as the noise levels increased.

show abstract

Section: Data Preprocessingmentioning

confidence: 99%

“…The pixels of the time-series signals are filled in order according to the prearranged series (Sun et al 2021). The time-series signals are used to arrange the pixel order in the GSI (Sun et al 2021).…”

Section: Data Preprocessingmentioning

confidence: 99%

Signal Process of Ultrasonic Guided Wave for Damage Detection of Localized Defects in Plates: From Shallow Learning to Deep Learning

Shang,

Zhang,

Tang

et al. 2023

JDSIS

View full text Add to dashboard Cite

show abstract

“…Wireless Communications and Mobile Computing symbols, not a real-time sequence. With obvious timing features, this paper builds a CLDNN network model that is more suitable for signal modulation recognition based on [21] for feature extraction. Its structure is shown in Figure 3.…”

Section: Feature Extraction and Analysismentioning

confidence: 99%

“…Dulek [18] proposed a classifier based on online and distributed expectation maximization, which can achieve a classification and recognition effect similar to the best channel state performance. Distributed recognition technology is widely used in optical fiber vibration sensing recognition [19,20]; Sun et.al [21] developed an improved deep learning method based on a serial fusion feature extraction model for an optical fiber distributed vibration sensing system which can automatically extract and identify effective features. Distributed fusion schemes based on the feature layer mostly use artificial features to achieve [22][23][24], but in noncoopera-tive communication scenarios, the received signal is usually a weak signal, which makes it difficult to obtain accurate feature expression.…”

Section: Introductionmentioning

confidence: 99%

Research on Distributed Multisensor Spectrum Semantic Sensing and Recognition in Internet of Things Environment

Liu

Zhang

Liu³

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The development of 5G technology has brought about a new era of Internet of Thing (IoT), and at the same time, electromagnetic spectrum monitoring and sensing have also ushered in huge challenges. Digital modulation recognition technology is an important content of electromagnetic spectrum sensing. In the increasingly complex wireless communication transmission environment, especially in noncooperative communication, it becomes more and more difficult to receive target signals and accurately extract effective semantic information from diverse modulation signals of the electromagnetic spectrum. At this stage, with the rapid development of network information and wireless communication technology, within a prescribed distance, the IoT built by many sensors has attracted wide attention from people in related fields. This paper proposes a distributed collaborative sensing spectrum semantic recognition architecture for communication signals based on feature fusion. Perform wireless communication and transmission between multiple sensors to form a self-organizing network to cooperatively sense signal semantic information, and extract the signal features of each sensor in the distributed network structure. Finally, the extracted sensor features are semantically analyzed and modeled, and the effective features are fused to complete the entire perception and recognition process. Even if the channel environment of a small number of receiving nodes deteriorates in a complex transmission environment, the signal quality features can still be accurately extracted, the classification and recognition effect like or higher than the best channel state performance can be achieved, and the fault tolerance of the system can be effectively improved. It can also enhance the performance of spectral semantic information sensing and recognition in the IoT environment.

show abstract

“…2D CNN is primarily used for image recognition and achieves high classification accuracy (95% or above) for images supporting various types of images. Sun et al used the GSI algorithm to convert detected signals into grayscale images and combined it with 2D CNN-LSTM for grayscale image recognition and classification [13]. This approach demonstrated a significant improvement in recognition rate compared to processing one-dimensional signal data.…”

Section: Introductionmentioning

confidence: 99%

Research on substation intrusion event identification method based on MTF and CNN

Shao,

Jiang,

Jiang

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

This research provides a detection approach based on Markov transition field (MTF) and convolutional neural network (CNN) for substation perimeter intrusion event recognition. Because of the complexity and variety of external signals, which makes sensor detection more challenging, determining and analyzing the intrusion behavior of vibration signals induced by intrusion has become critical to improving the identification rate of intrusion-like occurrences. The obtained one-dimensional signals are mapped into two-dimensional pictures using MTF to reflect better the properties of intrusion-like signals, which can yield deeper signal details than the usual feature extraction approach. The CNN-vgg19 model’s excellent image feature identification capabilities are utilized to detect and categorize the acquired 2D feature pictures. The experimental results show that the average recognition rate of the six intrusion events is 96.7%, and the average recognition rate of the noise events is 99%, which can effectively identify the noise events and reduce the false-positive rate. The study’s findings are valuable for substation and peripheral security intrusion products.

show abstract

Optical Fiber Distributed Vibration Sensing Using Grayscale Image and Multi-Class Deep Learning Framework for Multi-Event Recognition

Cited by 23 publications

References 37 publications

Signal Process of Ultrasonic Guided Wave for Damage Detection of Localized Defects in Plates: From Shallow Learning to Deep Learning

Signal Process of Ultrasonic Guided Wave for Damage Detection of Localized Defects in Plates: From Shallow Learning to Deep Learning

Research on Distributed Multisensor Spectrum Semantic Sensing and Recognition in Internet of Things Environment

Research on substation intrusion event identification method based on MTF and CNN

Contact Info

Product

Resources

About