Action classification from motion capture data using topological data analysis

Dirafzoon, Alireza; Lokare, Namita; Lobatón, Edgar

doi:10.1109/globalsip.2016.7906043

Cited by 16 publications

(17 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, the hearth's climate has undergone several sudden transitions to and back from a "snowball earth" [13]. Identifying markedly different regimes in a system's evolution can thus be used for warning, modeling and parameter estimation purposes [10] that barcodes on sliding window point clouds from motion capture time series, can be used to classify activities with very high accuracy.…”

Section: Some Applications Of Sliding Window Persistencementioning

confidence: 99%

Topological Time Series Analysis

Perea¹

2019

Notices Amer. Math. Soc.

View full text Add to dashboard Cite

show abstract

Section: Some Applications Of Sliding Window Persistencementioning

confidence: 99%

Topological Time Series Analysis

Perea¹

2019

Notices Amer. Math. Soc.

View full text Add to dashboard Cite

show abstract

“…The TDA techniques had become a useful representation extraction tool for different complex data analysis applications [21][22][23][24]. In the field of signal analysis, the TDA showed potentials for classification and detection [20,25,26], other than the traditional statistical-based methods. TDA provided an alternative viewpoint for signal analysis and enriched the nonlinear dynamical system based signal processing research.…”

Section: Introductionmentioning

confidence: 99%

Persistence Landscape based Topological Data Analysis for Personalized Arrhythmia Classification

Yan¹,

Ivanov²,

Cen³

et al. 2019

Preprint

View full text Add to dashboard Cite

Data can be illustrated in shapes, and the shapes could provide insight for data modeling and information extraction. Topological data analysis provides an alternative insight in biomedical data analysis and knowledge discovery with the algebra topology tools. In present work, we study the application of topological data analysis for personalized electrocardiographic signal classification toward arrhythmia analysis. Using phase space reconstruction technique, the signal samples are converted into point clouds for topological analysis facility. With topological techniques the persistence landscapes from the point clouds are extracted as features to perform the arrhythmia classification task. We find that the proposed method is robust to the training set size, with only a training set size of 20% percents, the normal heartbeat class are 100% recognized, ventricular beats for 97.13%, supra-ventricular beats for 94.27% and fusion beats for 94.27% within the corresponding experiments. The property of keeping high performance when using smaller training sample proves that the proposed method is especially applicable to personalized analysis. With the present study, we show that the topological data analysis technique could be a useful tool in biomedical signal analysis, and provide powerful ability in personalized analysis.

show abstract

“…The authors in [9], use a windowed time-delay embedded [15] signal as an input to the maxmin subsampling strategy. Features from the persistence diagrams (obtained from subsampled point clouds) are used for classifying activities.…”

Section: Application To Activity Recognitionmentioning

confidence: 99%

“…The TRED landmarks and quadtree for the time-delay embedded signal are shown in Figure 4 (middle), and the corresponding persistence diagram on the Figure 4 (right). In [9], features from the persistent diagram are used for activity recognition.…”

Section: Application To Activity Recognitionmentioning

confidence: 99%

“…In order to validate the correctness of our approach, we present a comparison of topological features with point-density based subsampling. As an example application, the topological features of sensor data on a person's joint can be used for activity recognition as shown by the authors of [9]. Yet we note the running time of density based subsampling does not allow for real time activity recognition.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust trajectory-based density estimation for geometric structure recovery

Richmond

Lokare

Lobatón

2017

2017 25th European Signal Processing Conference (EUSIPCO)

Self Cite

View full text Add to dashboard Cite

Abstract-We propose a method to both quickly and robustly extract geometric information from trajectory data. While point density may be of interest in some applications, trajectories provide different guarantees about our data such as path densities as opposed to location densities provided by points. We aim to utilize the concise nature of quadtrees in two dimensions to reduce run time complexity of counting trajectories in a neighborhood. We compare the accuracy of our methodology to a common current practice for subsampling a structure. Our results show that the proposed method is able to capture the geometric structure. We find an improvement in performance over the current practice in that our method is able to extract only the salient data and ignore trajectory outliers.

show abstract

Action classification from motion capture data using topological data analysis

Cited by 16 publications

References 23 publications

Topological Time Series Analysis

Topological Time Series Analysis

Persistence Landscape based Topological Data Analysis for Personalized Arrhythmia Classification

Robust trajectory-based density estimation for geometric structure recovery

Contact Info

Product

Resources

About