This page showcases a selection of my research papers.
For more visit my Google Scholar and ResearchGate profiles.
The zero-crossing signature (ZCS) approach is a novel time-domain feature extraction method that analyzes zero-crossing (ZC) points over multiple amplitude-shifted versions of an acoustic signal, enabling richer information extraction while maintaining computational efficiency. This method is especially suitable for real-time classification in the emerging Internet of Things (IoT) landscape, where resource-constrained devices require low-power solutions to support emission reduction efforts. In this study, the ZCS method was employed to showcase its full potential by classifying vehicles as diesel or gasoline based on their acoustic signatures. This classification task, applied to a database of car sounds acquired in the authors’ previous research, serves as a comprehensive demonstration of the method’s capabilities in distinguishing between engine types through characteristic sound wave patterns, highlighting its effectiveness and applicability in real-world scenarios. To further enhance feature extraction while keeping computational costs low, simple transformations using the first and second derivatives of the acoustic signals were applied, offering an efficient means of capturing additional signal characteristics. A dataset of 417 vehicle recordings was analyzed, and the classification performance of ZCS was compared with the conventional ZC method using a self-organizing map (SOM) configured with a 1-D grid of nine neurons. The study evaluated various time constants and crossing threshold densities for ZCS, benchmarking them against the classical ZC approach to assess their effectiveness.
Analysis of unsupervised learning approach for classification of vehicle fuel type using psychoacoustic features
- The acquisition system uses ultrasonic sensors to detect vehicles and then creates a dataset of audio recordings of the engine idling.
- The dataset of audio samples is analyzed by an unsupervised learning algorithm that uses psychoacoustic features to classify vehicles as those with gasoline or diesel engines.
- A self-organizing map used for classification achieves an F1 score of 91.1%, which increases to 96.7% when vehicles with mechanical anomalies are excluded.
Automated identification and assessment of environmental noise sources
- Inclusion of the spatial domain uncovers the acoustic environment in more detail.
- Automatic assessment of noise source contribution to the total 𝐿𝐴,𝑒𝑞 was achieved.
- The results of three measurements were compared with the conventional approach.
- A new way of monitoring of cavitation in a centrifugal pump that can detect the onset of cavitaiton.
- Multiple metrics retain all the advantages of classical detection using acoustic emission.
- Implementation of signal derivative and log dt/dp, a completely different behaviour of metrics has been achieved.
- Modest computational power needed for calculation of psychoacoustic metrics and other presented signal descriptors opens the possibility of developing a smartphone application.
- Such system for detection of cavitation on a centrifugal pump can be translated to different areas.
