期刊
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING
卷 10, 期 1, 页码 450-462出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TETC.2020.3029044
关键词
Convolutional neural networks; material classification; bio-inspired recognition; echoacoustics; remote sensing
资金
- Institute of Information & Communications Technology Planning & Evaluation (IITP) - Korea government (MSIT) [2019-0-00050]
- National Research Foundation of Korea (NRF) - Korea government (MSIT) [NRF-2020R1C1C1010666]
- Hallym University [HRF-201704-001]
In this study, a novel method for learning and recognizing material properties using self-emitted acoustic signals and mimicking acoustic recognition mechanisms found in animals is presented. The proposed approach, based on convolutional neural networks, achieved high accuracies in recognizing texture and density information compared to conventional machine learning methods. Experimental validation was conducted to demonstrate the effectiveness of the method and its potential for incorporating acoustic recognition functionality into computers.
In this study, we present a novel method for learning and recognizing the properties of materials by using the returning echoes of self-emitted acoustic signals. This is achieved by mimicking the acoustic recognition mechanisms that are present in several animals like bats and dolphins. To implement this mechanism on a computer. we propose an end-to-end machine learning approach that uses convolutional neural networks (CNNs), which can translate spectral cues that are delivered by reflected echoes into meaningful information for the target object. To validate the proposed approach. we conducted two different experiments. In the first experiment, we attempted to learn a set of predefined everyday surfaces using that reflected acoustic signals that are emitted from a distance. As an extension of the first experiment, the second experiment investigated whether echo-acoustic signals can be used for the classification of an acoustically smooth surface (e.g., liquid solutions). The experimental results showed that our system can recognize texture and, density information. In comparison to the conventional machine learning approach that relies on feature-engineering processes, our approach that is based on CNNs demonstrated high accuracies ( > 90%) in the test datasets in a robust manner. We conclude this article by discussing the limitations of the proposed approach and exploring the potential avenues to incorporate acoustic recognition functionality into computers.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据