Abstract

During the last decade, Convolutional Neural Networks (CNNs) have become the de facto standard for various Computer Vision and Machine Learning operations. CNNs are feed-forward Artificial Neural Networks (ANNs) with alternating convolutional and subsampling layers. Deep 2D CNNs with many hidden layers and millions of parameters have the ability to learn complex objects and patterns providing that they can be trained on a massive size visual database with ground-truth labels. With a proper training, this unique ability makes them the primary tool for various engineering applications for 2D signals such as images and video frames. Yet, this may not be a viable option in numerous applications over 1D signals especially when the training data is scarce or application specific. To address this issue, 1D CNNs have recently been proposed and immediately achieved the state-of-the-art performance levels in several applications such as personalized biomedical data classification and early diagnosis, structural health monitoring, anomaly detection and identification in power electronics and electrical motor fault detection. Another major advantage is that a real-time and low-cost hardware implementation is feasible due to the simple and compact configuration of 1D CNNs that perform only 1D convolutions (scalar multiplications and additions). This paper presents a comprehensive review of the general architecture and principals of 1D CNNs along with their major engineering applications, especially focused on the recent progress in this field. Their state-of-the-art performance is highlighted concluding with their unique properties. The benchmark datasets and the principal 1D CNN software used in those applications are also publicly shared in a dedicated website. While there has not been a paper on the review of 1D CNNs and its applications in the literature, this paper fulfills this gap.

Highlights

  • Artificial neurons used in conventional Artificial Neural Networks (ANNs) are the first-order models of biological neurons

  • A group of identically trained 1D Convolutional Neural Networks (CNNs) can monitor the entire MCM circuitry ‘‘in parallel” and if anyone detects a fault, the corresponding action can immediately be taken. This is a straightforward expectation because the proposed 1D Convolutional Neural Networks (1D CNNs) detector has already shown the ability to distinguish the pattern of the real fault occurring on a particular switch from the other ‘‘distorted” patterns belonging to other switches functioning normally

  • The main limitation or the drawback of 1D CNNs is common for conventional CNNs and ANNs in general: They are homogenous and based solely on linear-neuron model from 1950s

Read more

Summary

Introduction

Artificial neurons used in conventional ANNs are the first-order (linear) models of biological neurons. BP incrementally optimizes the network parameters, i.e., weights and biases, in an iterative manner using the gradient descent optimization technique These two accomplishments have started a new wave of approaches that eventually created the first naïve CNN models but it was the seminal work of Yann LeCun in 1990 who formulated the BP to train the first CNN [23], the so-called ‘‘LeNet”. Proper training of deep CNNs requires a massive size dataset for training to achieve a reasonable generalization capability This may not be a viable option for many practical 1D signal applications where labeled data can be scarce.

Overview of convolutional neural networks
Forward- and back-propagation in CNN-layers
NL ÀyLi
DlkðnÞ n
Applications of 1D CNNs
Automatic speech recognition
Vibration-based structural damage detection in civil infrastructure
Other applications
Computational complexity analysis of 1D-CNNs
BP ðmulÞ
Findings
Conclusions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call