System Applications and Methods Based on Sound Processing: AI Based and Conventional Approaches

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Circuit and Signal Processing".

Deadline for manuscript submissions: closed (31 October 2023) | Viewed by 7314

Special Issue Editors


E-Mail Website
Guest Editor

E-Mail Website
Guest Editor
Institute of Circuits and Systems, Technische Universität Dresden, 01062 Dresden, Germany
Interests: circuit theory; memristors; chaotic circuits; cellular neural networks (CNNs); deep learning; biomedical signal processing
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Sound is an essential component of nature. Any activity that involves the mediation of mechanical energy produces sounds. The sound characteristics determine the operating state of the system in question. When an abnormality occurs, the produced sound is modulated accordingly. This differentiation can be used to diagnose possible damages. This approach for diagnosis is well known and quite reliable and corresponding electronic systems have been developed for a multitude of applications. The exploitation of sounds is achieved either by using signal processing algorithms or by using artificial intelligence. Fields of application include the detection of damages in moving parts of machines, material defects, and leaks in pipelines, but also classification of vehicles, detection of the health status of living organisms, identification of pieces of music and many others.

The topics of the Special Issue include but are not limited to:

Methods and systems using sound signals for:
  • Leak detection and localization in pipelines
  • Defect detection in materials and machines
  • Classification of ground vehicles
  • Applications of bioacoustics in animal ecology
  • Identification in music
  • Machine learning and deep learning approaches based on acoustic signals
  • Acoustic signal applications on embedded systems
  • Hardware for processing acoustic signals

Prof. Dr. Spyridon Nikolaidis
Prof. Dr. Ronald Tetzlaff
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • sound signal processing
  • conventional techniques
  • machine learning techniques
  • implementation on embedded systems
  • hardware solutions

Published Papers (5 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

15 pages, 6029 KiB  
Article
Self-Supervised Health Index Curve Generation for Condition-Based Predictive Maintenance
by Steffen Seitz, Marvin Arnold, Ronald Tetzlaff and Peter Holstein
Electronics 2023, 12(24), 4941; https://doi.org/10.3390/electronics12244941 - 8 Dec 2023
Cited by 1 | Viewed by 786
Abstract
Modern machine degradation trend evaluation relies on the unsupervised model-based estimation of a health index (HI) from asset measurement data. This minimizes the need for timely human evaluation and avoids assumptions on the degradation shape. However, the comparability of multiple HI curves over [...] Read more.
Modern machine degradation trend evaluation relies on the unsupervised model-based estimation of a health index (HI) from asset measurement data. This minimizes the need for timely human evaluation and avoids assumptions on the degradation shape. However, the comparability of multiple HI curves over time generated by unsupervised methods suffers from a scaling mismatch (non-coherent HIs) caused by the slightly different asset initial conditions and distinct HI model training. In this paper, we propose a novel self-supervised approach to obtain HI curves without suffering from the scale mismatch. Our approach uses an unsupervised autoencoder based on a convolutional neural network (CNN) to detect initial faults and autonomously label measurement samples. The resulting self-labeled data is used to train a 1D-CNN health predictor, effectively eliminating the scaling mismatch problem. On the basis of a bearing test-to-failure experiment, we show that our self-supervised scheme offers a promising solution for the non-coherent HI problem. In addition, we observed that our method indicates the gradual wear affecting the bearing prior to the independent analysis of a human expert. Full article
Show Figures

Figure 1

17 pages, 1609 KiB  
Article
A 34.7 µW Speech Keyword Spotting IC Based on Subband Energy Feature Extraction
by Gexuan Wu, Jianlong Wei, Shuai Wang, Guangshun Wei and Bing Li
Electronics 2023, 12(15), 3287; https://doi.org/10.3390/electronics12153287 - 31 Jul 2023
Viewed by 847
Abstract
In the era of the Internet of Things (IoT), voice control has enhanced human–machine interaction and the accuracy of keyword spotting (KWS) algorithms has reached 97%; however, the high power consumption of KWS algorithms caused by their huge computing and storage requirements has [...] Read more.
In the era of the Internet of Things (IoT), voice control has enhanced human–machine interaction and the accuracy of keyword spotting (KWS) algorithms has reached 97%; however, the high power consumption of KWS algorithms caused by their huge computing and storage requirements has limited their application in Artificial Intelligence of Things (AIoT) devices. In this study, voice features are extracted by utilizing the fast discrete cosine transform (FDCT) for frequency-domain transformation and to shorten the process of calculating the logarithmic spectrum and cepstrum. The designed KWS system is a two-stage wake-up system, with a sound detection (SD) awakening KWS. The inference process of the KWS network is achieved using time-division computation, reducing the KWS clock to an ultra-low frequency of 24 kHz.At the same time, the implementation of a depthwise separable convolution neural network (DSCNN) greatly reduces the parameter quantity and computation. Under the GSMC 0.11 µm technology, post-layout simulation results show that the total synthesized area of the entire system circuit is 0.58 mm2, the power consumption is 34.7 µW, and the F1-score of the KWS is 0.89 with 10 dB noise, which makes it suitable as a KWS system in AIoT devices. Full article
Show Figures

Figure 1

22 pages, 4809 KiB  
Article
Classification of Engine Type of Vehicle Based on Audio Signal as a Source of Identification
by Mateusz Materlak and Ewelina Majda-Zdancewicz
Electronics 2023, 12(9), 2012; https://doi.org/10.3390/electronics12092012 - 26 Apr 2023
Viewed by 2107
Abstract
In this work, a combination of signal processing and machine learning techniques is applied for petrol and diesel engine identification based on engine sound. The research utilized real recordings acquired in car dealerships within Poland. The sound database recorded by the authors contains [...] Read more.
In this work, a combination of signal processing and machine learning techniques is applied for petrol and diesel engine identification based on engine sound. The research utilized real recordings acquired in car dealerships within Poland. The sound database recorded by the authors contains 80 various audio signals, equally divided. The study was conducted using feature engineering techniques based on frequency analysis for the generation of sound signal features. The discriminatory ability of feature vectors was evaluated using different machine learning techniques. In order to test the robustness of the proposed solution, the authors executed a number of system experimental tests, including different work conditions for the proposed system. The results show that the proposed approach produces a good accuracy at a level of 91.7%. The proposed system can support intelligent transportation systems through employing a sound signal as a medium carrying information on the type of car moving along a road. Such solutions can be implemented in the so-called ‘clean transport zones’, where only petrol-powered vehicles can freely move. Another potential application is to prevent misfuelling diesel to a petrol engine or petrol to a diesel engine. This kind of system can be implemented in petrol stations to recognize the vehicle based on the sound of the engine. Full article
Show Figures

Figure 1

12 pages, 1277 KiB  
Article
Study of Parameter Configuration on an Embedded System Used for Acoustic Leak Localization in Metallic Pipelines
by Georgios-Panagiotis Kousiopoulos and Spiros Nikolaidis
Electronics 2023, 12(8), 1793; https://doi.org/10.3390/electronics12081793 - 10 Apr 2023
Viewed by 892
Abstract
The subject of pipeline monitoring for a timely response in the case of leakage has raised intense interest and numerous leak localization methods have been presented in the literature. However, most approaches focus more on the performance of the methods themselves and not [...] Read more.
The subject of pipeline monitoring for a timely response in the case of leakage has raised intense interest and numerous leak localization methods have been presented in the literature. However, most approaches focus more on the performance of the methods themselves and not on their implementation on a typical embedded system and the way that the main system parameters affect its operation. The present paper aims to contribute to this field. Specifically, an acoustic leak localization method, developed in our previous research, is implemented in C++ on the Raspberry Pi 4B platform. The main system parameters are defined and certain trade-offs between them are examined. These trade-offs concern three basic metrics: the leak localization accuracy, the execution time of the algorithm, and the memory consumption, which rely on the values of the system parameters. Based on the targeted application, the importance of each of the aforementioned metrics can vary. For this reason, an evaluation function, equipped with user-defined weighting coefficients corresponding to the three metrics, is constructed in this paper. With the help of this function, a given parameter combination can be evaluated and the decision about its utilization in a certain application can be made. Full article
Show Figures

Figure 1

0 pages, 5132 KiB  
Article
RETRACTED: A Novel Deep Learning CNN for Heart Valve Disease Classification Using Valve Sound Detection
by Randa I. Aljohani, Hanan A. Hosni Mahmoud, Alaaeldin Hafez and Magdy Bayoumi
Electronics 2023, 12(4), 846; https://doi.org/10.3390/electronics12040846 - 8 Feb 2023
Cited by 3 | Viewed by 1965 | Retraction
Abstract
Valve sounds are mostly a result of heart valves opening and closing. Laminar blood flow is interrupted and abruptly transforms into turbulent flow, causing some sounds, and is explained by improper valve operation. It has been feasible to demonstrate that the typical and [...] Read more.
Valve sounds are mostly a result of heart valves opening and closing. Laminar blood flow is interrupted and abruptly transforms into turbulent flow, causing some sounds, and is explained by improper valve operation. It has been feasible to demonstrate that the typical and compulsive instances are different for both chronological and spatial aspects through the examination of phono-cardiographic signals. The current work presents the development and application of deep convolutional neural networks for the binary and multiclass categorization of multiple prevalent valve diseases and typical valve sounds. Three alternative methods were taken into consideration for feature extraction: mel-frequency cepstral coefficients and discrete wavelet transform. The precision of both models accomplished F1 scores of more than 98.2% and specificities of more than 98.5%, which reflects the instances that can be wrongly classified as regular. These experimental results prove the proposed model as a highly accurate assisted diagnosis model. Full article
Show Figures

Figure 1

Back to TopTop