A Graph-based Approach to Human Activity Recognition

• URL: http://arxiv.org/abs/2408.10191v1
• Date: Mon, 19 Aug 2024 17:51:00 GMT
• Title: A Graph-based Approach to Human Activity Recognition
• Authors: Thomas Peroutka, Ilir Murturi, Praveen Kumar Donta, Schahram Dustdar,
• Abstract summary: This paper presents a methodology to efficiently extract substantial insights from expanding real-time datasets. By utilizing data from Inertial Measurement Units (IMU) and Global Navigation Satellite Systems (GNSS) receivers, athletic performance can be analyzed using directed graphs. Our approach is demonstrated on biathlon data and detects specific points of interest and complex movement sequences.
• Score: 5.323279718522213
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Advanced wearable sensor devices have enabled the recording of vast amounts of movement data from individuals regarding their physical activities. This data offers valuable insights that enhance our understanding of how physical activities contribute to improved physical health and overall quality of life. Consequently, there is a growing need for efficient methods to extract significant insights from these rapidly expanding real-time datasets. This paper presents a methodology to efficiently extract substantial insights from these expanding datasets, focusing on professional sports but applicable to various human activities. By utilizing data from Inertial Measurement Units (IMU) and Global Navigation Satellite Systems (GNSS) receivers, athletic performance can be analyzed using directed graphs to encode knowledge of complex movements. Our approach is demonstrated on biathlon data and detects specific points of interest and complex movement sequences, facilitating the comparison and analysis of human physical performance.

Related papers

• Scaling Wearable Foundation Models [54.93979158708164]
  We investigate the scaling properties of sensor foundation models across compute, data, and model size. Using a dataset of up to 40 million hours of in-situ heart rate, heart rate variability, electrodermal activity, accelerometer, skin temperature, and altimeter per-minute data from over 165,000 people, we create LSM. Our results establish the scaling laws of LSM for tasks such as imputation, extrapolation, both across time and sensor modalities.
  arXiv  Detail & Related papers  (2024-10-17T15:08:21Z)
• Automatic Identification and Visualization of Group Training Activities Using Wearable Data [7.130450173185638]
  Human Activity Recognition (HAR) identifies daily activities from time-series data collected by wearable devices like smartwatches. This paper presents a comprehensive framework for imputing, analyzing, and identifying activities from wearable data. Our approach is based on data collected from 135 soldiers wearing Garmin 55 smartwatches over six months.
  arXiv  Detail & Related papers  (2024-10-07T19:35:15Z)
• Deep Reinforcement Learning Empowered Activity-Aware Dynamic Health Monitoring Systems [69.41229290253605]
  Existing monitoring approaches were designed on the premise that medical devices track several health metrics concurrently. This means that they report all relevant health values within that scope, which can result in excess resource use and the gathering of extraneous data. We propose Dynamic Activity-Aware Health Monitoring strategy (DActAHM) for striking a balance between optimal monitoring performance and cost efficiency.
  arXiv  Detail & Related papers  (2024-01-19T16:26:35Z)
• A Real-time Human Pose Estimation Approach for Optimal Sensor Placement in Sensor-based Human Activity Recognition [63.26015736148707]
  This paper introduces a novel methodology to resolve the issue of optimal sensor placement for Human Activity Recognition. The derived skeleton data provides a unique strategy for identifying the optimal sensor location. Our findings indicate that the vision-based method for sensor placement offers comparable results to the conventional deep learning approach.
  arXiv  Detail & Related papers  (2023-07-06T10:38:14Z)
• Multi-Channel Time-Series Person and Soft-Biometric Identification [65.83256210066787]
  This work investigates person and soft-biometrics identification from recordings of humans performing different activities using deep architectures. We evaluate the method on four datasets of multi-channel time-series human activity recognition (HAR) Soft-biometric based attribute representation shows promising results and emphasis the necessity of larger datasets.
  arXiv  Detail & Related papers  (2023-04-04T07:24:51Z)
• Dataset Bias in Human Activity Recognition [57.91018542715725]
  This contribution statistically curates the training data to assess to what degree the physical characteristics of humans influence HAR performance. We evaluate the performance of a state-of-the-art convolutional neural network on two HAR datasets that vary in the sensors, activities, and recording for time-series HAR.
  arXiv  Detail & Related papers  (2023-01-19T12:33:50Z)
• Learn to Predict How Humans Manipulate Large-sized Objects from Interactive Motions [82.90906153293585]
  We propose a graph neural network, HO-GCN, to fuse motion data and dynamic descriptors for the prediction task. We show the proposed network that consumes dynamic descriptors can achieve state-of-the-art prediction results and help the network better generalize to unseen objects.
  arXiv  Detail & Related papers  (2022-06-25T09:55:39Z)
• Human Activity Recognition on wrist-worn accelerometers using self-supervised neural networks [0.0]
  Measures of Activity of Daily Living (ADL) are an important indicator of overall health but difficult to measure in-clinic. We propose a self-supervised learning paradigm to create a robust representation of accelerometer data that can generalize across devices and subjects. We also propose a segmentation algorithm which can identify segments of salient activity and boost HAR accuracy on continuous real-life data.
  arXiv  Detail & Related papers  (2021-12-22T23:35:20Z)
• Self-supervised transfer learning of physiological representations from free-living wearable data [12.863826659440026]
  We present a novel self-supervised representation learning method using activity and heart rate (HR) signals without semantic labels. We evaluate our model in the largest free-living combined-sensing dataset (comprising >280k hours of wrist accelerometer & wearable ECG data)
  arXiv  Detail & Related papers  (2020-11-18T23:21:34Z)
• Learning Generalizable Physiological Representations from Large-scale Wearable Data [12.863826659440026]
  We present a novel self-supervised representation learning method using activity and heart rate (HR) signals without semantic labels. We show that the resulting embeddings can generalize in various downstream tasks through transfer learning with linear classifiers. Overall, we propose the first multimodal self-supervised method for behavioral and physiological data with implications for large-scale health and lifestyle monitoring.
  arXiv  Detail & Related papers  (2020-11-09T17:56:03Z)
• Towards Deep Clustering of Human Activities from Wearables [21.198881633580797]
  We develop an unsupervised end-to-end learning strategy for the fundamental problem of human activity recognition from wearables. We show the effectiveness of our approach to jointly learn unsupervised representations for sensory data and generate cluster assignments with strong semantic correspondence to distinct human activities.
  arXiv  Detail & Related papers  (2020-08-02T13:55:24Z)

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.