Vehicle Classification Based on FBG Sensor Arrays Using Neural Networks

Abstract

This article is focused on the automatic classification of passing vehicles through an experimental platform using optical sensor arrays. The amount of data generated from various sensor systems is growing proportionally every year. Therefore, it is necessary to look for more progressive solutions to these problems. Methods of implementing artificial intelligence are becoming a new trend in this area. At first, an experimental platform with two separate groups of fiber Bragg grating sensor arrays (horizontally and vertically oriented) installed into the top pavement layers was created. Interrogators were connected to sensor arrays to measure pavement deformation caused by vehicles passing over the pavement. Next, neural networks for visual classification with a closed-circuit television camera to separate vehicles into different classes were used. This classification was used for the verification of measured and analyzed data from sensor arrays. The newly proposed neural network for vehicle classification from the sensor array dataset was created. From the obtained experimental results, it is evident that our proposed neural network was capable of separating trucks from other vehicles, with an accuracy of 94.9%, and classifying vehicles into three different classes, with an accuracy of 70.8%. Based on the experimental results, extending sensor arrays as described in the last part of the paper is recommended.

Neural-Network-Optimized Vehicle Classification Using Clustered Image and Fiber-Sensor Datasets

“…8b From the obtained results, we can conclude that conventional CNNs (AlexNet, GoogleNet, ResNet-50 and ResNet-101) are better suited for pure image data recognition. For this reason, the afore-mentioned standard CNNs, in all cases fed by sensor data only, obtained results that are less precise compared to the CNN architectures based on CCTV-based image inputs [27]. To monitor the generalization performance and select the optimal study model, the dataset was divided into a training set with a data amount of 70% and a validation set, having a 30% of data amount.…”

“…Ground-based solutions can provide neat monitoring, management, and car classification. They are typically based on inductive and magnetic loops or may benefit from many sensing methods [20][21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36]. The sensing maps a measurable physical quantity into virtual data, creating a basis for computation, analytics, and adoption of artificial intelligence (AI) and machine learning (ML) algorithms.…”

“…For a sensing part, anisotropic magneto-resistance [20], piezoelectricity [21,22], or hydro-electricity [23] are typically exploited. Alternative classes for on-road traffic control rely on embedded strain gauge [24], vibration [25], or fiber-optics [26][27][28][29][30][31][32][33][34][35][36] sensors.…”

“…Coexistence between high-speed network and optical sensing platform is highly desired to keep both cost and complexity at low levels [36]. Fiber Bragg gratings (FBGs) emerge as an attractive optical platform to form single-and multi-point sensor arrays [26,27,[29][30][31][32][33][34][35]. In FBGs, the reflected light adds constructively in the backward direction and creates a distinct narrowband drop in the transmission, while the rest of the light passes through the grating.…”

Smart Sensors and Devices in Artificial Intelligence

“…The results show that the proposed "time-aware density-based incremental local outlier detection" performs better than that of the existing candidates in the sense of the AUC in most of the cases on different kinds of datasets. In [3], the study was focused on the vehicle classification with (fiber Bragg grating) FBG sensor arrays by employing AI from partial records. The developed neural network was trained by resorting to a dataset which lacked vehicle velocity data, which is generated by the visual identification of a vehicle going over the testing platform.…”