Learning-to-Learn Personalised Human Activity Recognition Models

• URL: http://arxiv.org/abs/2006.07472v1
• Date: Fri, 12 Jun 2020 21:11:59 GMT
• Title: Learning-to-Learn Personalised Human Activity Recognition Models
• Authors: Anjana Wijekoon, Nirmalie Wiratunga
• Abstract summary: We present a meta-learning methodology for learning to learn personalised HAR models for HAR. We introduce two algorithms, Personalised MAML and Personalised Relation Networks inspired by existing Meta-Learning algorithms. A comparative study shows significant performance improvements against the state-of-the-art Deep Learning algorithms and the Few-shot Meta-Learning algorithms in multiple HAR domains.
• Score: 1.5087842661221904
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Human Activity Recognition~(HAR) is the classification of human movement, captured using one or more sensors either as wearables or embedded in the environment~(e.g. depth cameras, pressure mats). State-of-the-art methods of HAR rely on having access to a considerable amount of labelled data to train deep architectures with many train-able parameters. This becomes prohibitive when tasked with creating models that are sensitive to personal nuances in human movement, explicitly present when performing exercises. In addition, it is not possible to collect training data to cover all possible subjects in the target population. Accordingly, learning personalised models with few data remains an interesting challenge for HAR research. We present a meta-learning methodology for learning to learn personalised HAR models for HAR; with the expectation that the end-user need only provides a few labelled data but can benefit from the rapid adaptation of a generic meta-model. We introduce two algorithms, Personalised MAML and Personalised Relation Networks inspired by existing Meta-Learning algorithms but optimised for learning HAR models that are adaptable to any person in health and well-being applications. A comparative study shows significant performance improvements against the state-of-the-art Deep Learning algorithms and the Few-shot Meta-Learning algorithms in multiple HAR domains.

Related papers

• A Comprehensive Methodological Survey of Human Activity Recognition Across Divers Data Modalities [2.916558661202724]
  Human Activity Recognition (HAR) systems aim to understand human behaviour and assign a label to each action. HAR can leverage various data modalities, such as RGB images and video, skeleton, depth, infrared, point cloud, event stream, audio, acceleration, and radar signals. This paper presents a comprehensive survey of the latest advancements in HAR from 2014 to 2024.
  arXiv  Detail & Related papers  (2024-09-15T10:04:44Z)
• PILOT: A Pre-Trained Model-Based Continual Learning Toolbox [71.63186089279218]
  This paper introduces a pre-trained model-based continual learning toolbox known as PILOT. On the one hand, PILOT implements some state-of-the-art class-incremental learning algorithms based on pre-trained models, such as L2P, DualPrompt, and CODA-Prompt. On the other hand, PILOT fits typical class-incremental learning algorithms within the context of pre-trained models to evaluate their effectiveness.
  arXiv  Detail & Related papers  (2023-09-13T17:55:11Z)
• Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memory [64.11870454160614]
  We propose an efficient Adaptive HOI Detector with Concept-guided Memory (ADA-CM) ADA-CM has two operating modes. The first mode makes it tunable without learning new parameters in a training-free paradigm. Our proposed method achieves competitive results with state-of-the-art on the HICO-DET and V-COCO datasets with much less training time.
  arXiv  Detail & Related papers  (2023-09-07T13:10:06Z)
• randomHAR: Improving Ensemble Deep Learners for Human Activity Recognition with Sensor Selection and Reinforcement Learning [4.5830802802139585]
  The general idea behind randomHAR is training a series of deep learning models with the same architecture on randomly selected sensor data. In contrast to existing work, this approach optimize the ensemble process rather than the architecture of the constituent models. The experiment demonstrates that the proposed approach outperforms the state-of-the-art method, ensembleLSTM.
  arXiv  Detail & Related papers  (2023-07-15T10:51:03Z)
• ALP: Action-Aware Embodied Learning for Perception [60.64801970249279]
  We introduce Action-Aware Embodied Learning for Perception (ALP) ALP incorporates action information into representation learning through a combination of optimizing a reinforcement learning policy and an inverse dynamics prediction objective. We show that ALP outperforms existing baselines in several downstream perception tasks.
  arXiv  Detail & Related papers  (2023-06-16T21:51:04Z)
• 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)
• Easy Ensemble: Simple Deep Ensemble Learning for Sensor-Based Human Activity Recognition [0.0]
  We propose Easy Ensemble (EE) for sensor-based human activity recognition (HAR) EE enables the easy implementation of deep ensemble learning in a single model. In addition, we propose input masking as a method for diversifying the input for EE.
  arXiv  Detail & Related papers  (2022-03-08T15:30:32Z)
• What Matters in Learning from Offline Human Demonstrations for Robot Manipulation [64.43440450794495]
  We conduct an extensive study of six offline learning algorithms for robot manipulation. Our study analyzes the most critical challenges when learning from offline human data. We highlight opportunities for learning from human datasets.
  arXiv  Detail & Related papers  (2021-08-06T20:48:30Z)
• Efficient Realistic Data Generation Framework leveraging Deep Learning-based Human Digitization [0.0]
  The proposed method takes as input real background images and populates them with human figures in various poses. A benchmarking and evaluation in the corresponding tasks shows that synthetic data can be effectively used as a supplement to real data.
  arXiv  Detail & Related papers  (2021-06-28T08:07:31Z)
• Personalized Semi-Supervised Federated Learning for Human Activity Recognition [1.9014535120129343]
  We propose FedHAR: a novel hybrid method for human activities recognition. FedHAR combines semi-supervised and federated learning. We show that FedHAR reaches recognition rates and personalization capabilities similar to state-of-the-art FL supervised approaches.
  arXiv  Detail & Related papers  (2021-04-15T10:24:18Z)
• Few-Cost Salient Object Detection with Adversarial-Paced Learning [95.0220555274653]
  This paper proposes to learn the effective salient object detection model based on the manual annotation on a few training images only. We name this task as the few-cost salient object detection and propose an adversarial-paced learning (APL)-based framework to facilitate the few-cost learning scenario.
  arXiv  Detail & Related papers  (2021-04-05T14:15:49Z)

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.