Human Motion Detection Using Sharpened Dimensionality Reduction and Clustering

• URL: http://arxiv.org/abs/2202.11667v1
• Date: Wed, 23 Feb 2022 18:18:25 GMT
• Title: Human Motion Detection Using Sharpened Dimensionality Reduction and Clustering
• Authors: Jeewon Heo, Youngjoo Kim and Jos B.T.M. Roerdink
• Abstract summary: We propose clustering methods to easily label the 2D projections of high-dimensional data. We test our pipeline of SDR and the clustering methods on a range of synthetic and real-world datasets. We conclude that clustering SDR results yields better labeling results than clustering plain DR, and that k-means is the recommended clustering method for SDR.
• Score: 1.1172382217477126
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sharpened dimensionality reduction (SDR), which belongs to the class of multidimensional projection techniques, has recently been introduced to tackle the challenges in the exploratory and visual analysis of high-dimensional data. SDR has been applied to various real-world datasets, such as human activity sensory data and astronomical datasets. However, manually labeling the samples from the generated projection are expensive. To address this problem, we propose here to use clustering methods such as k-means, Hierarchical Clustering, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), and Spectral Clustering to easily label the 2D projections of high-dimensional data. We test our pipeline of SDR and the clustering methods on a range of synthetic and real-world datasets, including two different public human activity datasets extracted from smartphone accelerometer or gyroscope recordings of various movements. We apply clustering to assess the visual cluster separation of SDR, both qualitatively and quantitatively. We conclude that clustering SDR results yields better labeling results than clustering plain DR, and that k-means is the recommended clustering method for SDR in terms of clustering accuracy, ease-of-use, and computational scalability.

Related papers

• Self-Supervised Graph Embedding Clustering [70.36328717683297]
  K-means one-step dimensionality reduction clustering method has made some progress in addressing the curse of dimensionality in clustering tasks. We propose a unified framework that integrates manifold learning with K-means, resulting in the self-supervised graph embedding framework.
  arXiv  Detail & Related papers  (2024-09-24T08:59:51Z)
• Distributional Reduction: Unifying Dimensionality Reduction and Clustering with Gromov-Wasserstein [56.62376364594194]
  Unsupervised learning aims to capture the underlying structure of potentially large and high-dimensional datasets. In this work, we revisit these approaches under the lens of optimal transport and exhibit relationships with the Gromov-Wasserstein problem. This unveils a new general framework, called distributional reduction, that recovers DR and clustering as special cases and allows addressing them jointly within a single optimization problem.
  arXiv  Detail & Related papers  (2024-02-03T19:00:19Z)
• Rethinking k-means from manifold learning perspective [122.38667613245151]
  We present a new clustering algorithm which directly detects clusters of data without mean estimation. Specifically, we construct distance matrix between data points by Butterworth filter. To well exploit the complementary information embedded in different views, we leverage the tensor Schatten p-norm regularization.
  arXiv  Detail & Related papers  (2023-05-12T03:01:41Z)
• Unsupervised Deep Learning-based clustering for Human Activity Recognition [8.716606664673982]
  The paper proposes DISC (Deep Inertial Sensory Clustering), a DL-based clustering architecture that automatically labels multi-dimensional inertial signals. The architecture combines a recurrent AutoEncoder and a clustering criterion to predict unlabelled human activities-related signals. The experiments demonstrate the effectiveness of DISC on both clustering accuracy and normalized mutual information metrics.
  arXiv  Detail & Related papers  (2022-11-10T10:56:47Z)
• DRBM-ClustNet: A Deep Restricted Boltzmann-Kohonen Architecture for Data Clustering [0.0]
  A Bayesian Deep Restricted Boltzmann-Kohonen architecture for data clustering termed as DRBM-ClustNet is proposed. The processing of unlabeled data is done in three stages for efficient clustering of the non-linearly separable datasets. The framework is evaluated based on clustering accuracy and ranked against other state-of-the-art clustering methods.
  arXiv  Detail & Related papers  (2022-05-13T15:12:18Z)
• Visual Cluster Separation Using High-Dimensional Sharpened Dimensionality Reduction [65.80631307271705]
  High-Dimensional Sharpened DR' (HD-SDR) is tested on both synthetic and real-world data sets. Our method achieves good quality (measured by quality metrics) and scales computationally well with large high-dimensional data. To illustrate its concrete applications, we further apply HD-SDR on a recent astronomical catalog.
  arXiv  Detail & Related papers  (2021-10-01T11:13:51Z)
• Spatial-Spectral Clustering with Anchor Graph for Hyperspectral Image [88.60285937702304]
  This paper proposes a novel unsupervised approach called spatial-spectral clustering with anchor graph (SSCAG) for HSI data clustering. The proposed SSCAG is competitive against the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-04-24T08:09:27Z)
• Hyperspectral Classification Based on Lightweight 3-D-CNN With Transfer Learning [67.40866334083941]
  We propose an end-to-end 3-D lightweight convolutional neural network (CNN) for limited samples-based HSI classification. Compared with conventional 3-D-CNN models, the proposed 3-D-LWNet has a deeper network structure, less parameters, and lower computation cost. Our model achieves competitive performance for HSI classification compared to several state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-12-07T03:44:35Z)
• Hyperspectral Image Clustering with Spatially-Regularized Ultrametrics [7.487718119544157]
  We propose a method for the unsupervised clustering of hyperspectral images based on spatially regularized spectral clustering with ultrametric path distances. The proposed method efficiently combines data density and geometry to distinguish between material classes in the data, without the need for training labels.
  arXiv  Detail & Related papers  (2020-04-10T14:27:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.