High-Accuracy Airborne Rangefinder via Deep Learning Based on Piezoelectric Micromachined Ultrasonic Cantilevers

Abstract

This article presents a high-accuracy air-coupled acoustic rangefinder based on piezoelectric microcantilever beam array using continuous waves. Cantilevers are used to create a functional ultrasonic rangefinder with a range of 0–1 m. This is achieved through a design of custom arrays. This research investigates various classification techniques to identify airborne ranges using ultrasonic signals. The initial approach involves implementing individual models such as support vector machine (SVM), Gaussian Naive Bayes (GNB), logistic regression (LR), k-nearest neighbors (KNNs), and decision tree (DT). To potentially achieve better performance, the study introduces a deep learning (DL) architecture based on convolutional neural networks (CNNs) to categorize different ranges. The CNN model combines the strengths of multiple classification models, aiming for more accurate range detection. To ensure the model generalizes well to unseen data, a technique called k-fold cross-validation (CV), which provides the reliability assessment, is used. The proposed framework demonstrates a significant improvement in accuracy (100%), and area under the curve (AUC) (1.0) over other approaches.