Clustering Methods for Vibro-Acoustic Sensing Features as a Potential Approach to Tissue Characterisation in Robot-Assisted Interventions

Abstract

This article provides a comprehensive analysis of the feature extraction methods applied to vibro-acoustic signals (VA signals) in the context of robot-assisted interventions. The primary objective is to extract valuable information from these signals to understand tissue behaviour better and build upon prior research. This study is divided into three key stages: feature extraction using the Cepstrum Transform (CT), Mel-Frequency Cepstral Coefficients (MFCCs), and Fast Chirplet Transform (FCT); dimensionality reduction employing techniques such as Principal Component Analysis (PCA), t-Distributed Stochastic Neighbour Embedding (t-SNE), and Uniform Manifold Approximation and Projection (UMAP); and, finally, classification using a nearest neighbours classifier. The results demonstrate that using feature extraction techniques, especially the combination of CT and MFCC with dimensionality reduction algorithms, yields highly efficient outcomes. The classification metrics (Accuracy, Recall, and F1-score) approach 99%, and the clustering metric is 0.61. The performance of the CT–UMAP combination stands out in the evaluation metrics.

Soundscape Characterization Using Autoencoders and Unsupervised Learning

“…Moreover, its mathematical formulation seeks the preservation of both local and global structures inherent in the data [ 42 ]. Over time, UMAP has emerged as a highly popular non-linear projection technique, particularly for visualizing intricate patterns delineated by features in two or three dimensions [ 43 ].…”

Advanced Machine Learning Techniques for Seismic Anomaly Detection in Indonesia: A Comparative Study of Lof, Isolation Forest, and One-Class SVM

“…These technologies have been promising in enhancing prediction accuracy but are often hindered by the need for extensive labeled data, which is challenging due to the erratic and rare nature of seismic anomalies (Chamola et al, 2020;Shyalika, Wickramarachchi, & Sheth, 2023;Wang & Brenning, 2023). Recent research underscores the significance of unsupervised learning algorithms in scenarios where data is plentiful but lacking in labels, especially relevant to Indonesia where seismic occurrences are frequent yet varied, leading to a scarcity of representative labeled data (Umasha, Wijayakulasooriya, & Ranaweera, 2023;Urrutia et al, 2023). Our study seeks to assess the efficacy of various machine learning methods in detecting anomalies in Indonesian earthquake data.…”