SoK: Behind the Accuracy of Complex Human Activity Recognition Using Deep Learning

• URL: http://arxiv.org/abs/2405.00712v2
• Date: Sat, 4 May 2024 03:48:19 GMT
• Title: SoK: Behind the Accuracy of Complex Human Activity Recognition Using Deep Learning
• Authors: Duc-Anh Nguyen, Nhien-An Le-Khac,
• Abstract summary: Human Activity Recognition (HAR) is a well-studied field with research dating back to the 1980s. In this paper, we comprehensively systematise factors leading to inaccuracy in complex HAR, such as data variety and model capacity.
• Score: 4.580983642743026
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Human Activity Recognition (HAR) is a well-studied field with research dating back to the 1980s. Over time, HAR technologies have evolved significantly from manual feature extraction, rule-based algorithms, and simple machine learning models to powerful deep learning models, from one sensor type to a diverse array of sensing modalities. The scope has also expanded from recognising a limited set of activities to encompassing a larger variety of both simple and complex activities. However, there still exist many challenges that hinder advancement in complex activity recognition using modern deep learning methods. In this paper, we comprehensively systematise factors leading to inaccuracy in complex HAR, such as data variety and model capacity. Among many sensor types, we give more attention to wearable and camera due to their prevalence. Through this Systematisation of Knowledge (SoK) paper, readers can gain a solid understanding of the development history and existing challenges of HAR, different categorisations of activities, obstacles in deep learning-based complex HAR that impact accuracy, and potential research directions.

Related papers

• VCHAR:Variance-Driven Complex Human Activity Recognition framework with Generative Representation [6.278293754210117]
  VCHAR (Variance-Driven Complex Human Activity Recognition) is a novel framework that treats the outputs of atomic activities as a distribution over specified intervals. We show that VCHAR enhances the accuracy of complex activity recognition without necessitating precise temporal or sequential labeling of atomic activities.
  arXiv  Detail & Related papers  (2024-07-03T17:24:36Z)
• A Survey on Multimodal Wearable Sensor-based Human Action Recognition [15.054052500762559]
  Wearable Sensor-based Human Activity Recognition (WSHAR) emerges as a promising assistive technology to support the daily lives of older individuals. Recent surveys in WSHAR have been limited, focusing either solely on deep learning approaches or on a single sensor modality. In this study, we present a comprehensive survey on how to leverage multimodal learning to WSHAR domain for newcomers and researchers.
  arXiv  Detail & Related papers  (2024-04-14T18:43:16Z)
• Investigating Deep Neural Network Architecture and Feature Extraction Designs for Sensor-based Human Activity Recognition [0.0]
  In light of deep learning's proven effectiveness across various domains, numerous deep methods have been explored to tackle the challenges in activity recognition. We investigate the performance of common deep learning and machine learning approaches as well as different training mechanisms. Various feature representations extracted from the sensor time-series data and measure their effectiveness for the human activity recognition task.
  arXiv  Detail & Related papers  (2023-09-26T14:55:32Z)
• Recognizing Unseen Objects via Multimodal Intensive Knowledge Graph Propagation [68.13453771001522]
  We propose a multimodal intensive ZSL framework that matches regions of images with corresponding semantic embeddings. We conduct extensive experiments and evaluate our model on large-scale real-world data.
  arXiv  Detail & Related papers  (2023-06-14T13:07:48Z)
• Deep Active Learning for Computer Vision: Past and Future [50.19394935978135]
  Despite its indispensable role for developing AI models, research on active learning is not as intensive as other research directions. By addressing data automation challenges and coping with automated machine learning systems, active learning will facilitate democratization of AI technologies.
  arXiv  Detail & Related papers  (2022-11-27T13:07:14Z)
• Efficient Deep Clustering of Human Activities and How to Improve Evaluation [53.08810276824894]
  We present a new deep clustering model for human activity re-cog-ni-tion (HAR) In this paper, we highlight several distinct problems with how deep HAR clustering models are evaluated. We then discuss solutions to these problems, and suggest standard evaluation settings for future deep HAR clustering models.
  arXiv  Detail & Related papers  (2022-09-17T14:12:42Z)
• Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information [77.19830787312743]
  In real-world reinforcement learning applications the learner's observation space is ubiquitously high-dimensional with both relevant and irrelevant information about the task at hand. We introduce a new problem setting for reinforcement learning, the Exogenous Decision Process (ExoMDP), in which the state space admits an (unknown) factorization into a small controllable component and a large irrelevant component. We provide a new algorithm, ExoRL, which learns a near-optimal policy with sample complexity in the size of the endogenous component.
  arXiv  Detail & Related papers  (2022-06-09T05:19:32Z)
• What Makes Good Contrastive Learning on Small-Scale Wearable-based Tasks? [59.51457877578138]
  We study contrastive learning on the wearable-based activity recognition task. This paper presents an open-source PyTorch library textttCL-HAR, which can serve as a practical tool for researchers.
  arXiv  Detail & Related papers  (2022-02-12T06:10:15Z)
• Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances [8.642789007878479]
  Deep learning has greatly pushed the boundaries of human activity recognition on mobile and wearable devices. This paper systematically categorizes and summarizes existing work that introduces deep learning methods for wearables-based HAR. We also present cutting-edge frontiers and future directions for deep learning--based HAR.
  arXiv  Detail & Related papers  (2021-10-31T07:16:23Z)
• Continual Learning in Sensor-based Human Activity Recognition: an Empirical Benchmark Analysis [4.686889458553123]
  Sensor-based human activity recognition (HAR) is a key enabler for many real-world applications in smart homes, personal healthcare, and urban planning. How can a HAR system autonomously learn new activities over a long period of time without being re-engineered from scratch? This problem is known as continual learning and has been particularly popular in the domain of computer vision.
  arXiv  Detail & Related papers  (2021-04-19T15:38:22Z)
• Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities [52.59080024266596]
  We present a survey of the state-of-the-art deep learning methods for sensor-based human activity recognition. We first introduce the multi-modality of the sensory data and provide information for public datasets. We then propose a new taxonomy to structure the deep methods by challenges.
  arXiv  Detail & Related papers  (2020-01-21T09:55:59Z)

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.