AdaSense: Adaptive Low-Power Sensing and Activity Recognition for Wearable Devices

• URL: http://arxiv.org/abs/2006.05884v1
• Date: Wed, 10 Jun 2020 15:17:11 GMT
• Title: AdaSense: Adaptive Low-Power Sensing and Activity Recognition for Wearable Devices
• Abstract summary: AdaSense is a sensing, feature extraction and classification co-optimized framework for Human Activity Recognition. The framework selects configurations that represent the pareto-frontier of the accuracy and energy trade-off. The introduced approach achieves 69% reduction in the power consumption of the sensor with less than 1.5% decrease in the activity recognition accuracy.
• Score: 2.0119495998780925
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Wearable devices have strict power and memory limitations. As a result, there is a need to optimize the power consumption on those devices without sacrificing the accuracy. This paper presents AdaSense: a sensing, feature extraction and classification co-optimized framework for Human Activity Recognition. The proposed techniques reduce the power consumption by dynamically switching among different sensor configurations as a function of the user activity. The framework selects configurations that represent the pareto-frontier of the accuracy and energy trade-off. AdaSense also uses low-overhead processing and classification methodologies. The introduced approach achieves 69% reduction in the power consumption of the sensor with less than 1.5% decrease in the activity recognition accuracy.

Related papers

• Robust Slip Detection and Material Classification via Spatiotemporal Transformers on a Uniformly-Illuminated Visuo-Tactile Sensor [52.33204893988409]
  We propose a visuo-tactile sensor featuring customized uniform illumination, alongside a unified perception framework.<n>The proposed hardware-software framework provides high-fidelity feedback and a powerful multi-modal perception baseline for complex robotic manipulation.
  arXiv  Detail & Related papers  (2026-08-25T07:25:27Z)
• An Algorithm for On-Sensor Agnostic Detection of Changes in Human Activity for Ultra-Low-Power Applications [0.3181700357675698]
  Wearable devices running Human Activity Recognition (HAR) on Inertial Measurement Units(IMUs) waste energy by performing continuous classification for each window, even during long periods of unchanged activity.<n>We address this with a lightweight change-detection gate: a non-parametric algorithm based on dynamic template matching that runs continuously at only approximately 16kFLOPs per step, requires no offline training, and does not need prior definition of target activity classes.<n>The gate invokes the full HAR network only when it detects an activity change, reducing the computational load by over 67% in realistic monitoring settings.
  arXiv  Detail & Related papers  (2026-04-24T11:28:34Z)
• ReSPEC: A Framework for Online Multispectral Sensor Reconfiguration in Dynamic Environments [6.718801307135799]
  We introduce a framework that unifies sensing, learning, and actuation into a closed reconfiguration loop.<n>We implement and evaluate this framework on a mobile rover, showing that adaptive control reduces load by 29.3% with only a 5.3% accuracy drop compared to a baseline.
  arXiv  Detail & Related papers  (2026-02-11T05:39:24Z)
• Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions [20.180037657388763]
  We find that the influence of weight parameters on power consumption varies depending on factors such as invocation frequency and memory allocation. We propose design principles that enhance on-device speech recognition models by reducing power consumption with minimal impact on accuracy.
  arXiv  Detail & Related papers  (2024-02-20T15:22:25Z)
• 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)
• Big-Little Adaptive Neural Networks on Low-Power Near-Subthreshold Processors [0.0]
  Paper investigates the energy savings that near-subthreshold processors can obtain in edge AI applications. It proposes strategies to improve them while maintaining the accuracy of the application.
  arXiv  Detail & Related papers  (2023-04-19T14:36:30Z)
• HEAT: Hardware-Efficient Automatic Tensor Decomposition for Transformer Compression [69.36555801766762]
  We propose a hardware-aware tensor decomposition framework, dubbed HEAT, that enables efficient exploration of the exponential space of possible decompositions. We experimentally show that our hardware-aware factorized BERT variants reduce the energy-delay product by 5.7x with less than 1.1% accuracy loss.
  arXiv  Detail & Related papers  (2022-11-30T05:31:45Z)
• Optimization of Forcemyography Sensor Placement for Arm Movement Recognition [10.889386494753284]
  This paper focuses on optimizing the placement of Forcemyography sensors for armbands in the application of arm movement recognition. Our algorithm can help maintain a comparable recognition accuracy to using all sensors. This work would like to shed light on the automatic fabrication of wearable devices considering downstream tasks, such as human biological signal collection and movement recognition.
  arXiv  Detail & Related papers  (2022-07-22T07:37:48Z)
• Efficient Decoder-free Object Detection with Transformers [75.00499377197475]
  Vision transformers (ViTs) are changing the landscape of object detection approaches. We propose a decoder-free fully transformer-based (DFFT) object detector. DFFT_SMALL achieves high efficiency in both training and inference stages.
  arXiv  Detail & Related papers  (2022-06-14T13:22:19Z)
• SELF-CARE: Selective Fusion with Context-Aware Low-Power Edge Computing for Stress Detection [9.21629452868642]
  We propose a fully wrist-based method for stress detection that employs context-aware selective sensor fusion. Our method uses motion to determine the context of the system and learns to adjust the fused sensors accordingly. Our approach achieves up to 2.2x (3-class) and 2.7x (2-class) energy efficiency compared to traditional sensor fusion.
  arXiv  Detail & Related papers  (2022-05-08T23:52:07Z)
• An adaptable cognitive microcontroller node for fitness activity recognition [0.0]
  Wobble boards are low-cost equipment that can be used for sensorimotor training to avoid ankle injuries or as part of the rehabilitation process after an injury. In this work, we present a portable and battery-powered microcontroller-based device applicable to a wobble board. To reduce power consumption, we add an adaptivity layer that dynamically manages the device's hardware and software configuration to adapt it to the required operating mode at runtime.
  arXiv  Detail & Related papers  (2022-01-13T18:06:38Z)
• Bandit Quickest Changepoint Detection [55.855465482260165]
  Continuous monitoring of every sensor can be expensive due to resource constraints. We derive an information-theoretic lower bound on the detection delay for a general class of finitely parameterized probability distributions. We propose a computationally efficient online sensing scheme, which seamlessly balances the need for exploration of different sensing options with exploitation of querying informative actions.
  arXiv  Detail & Related papers  (2021-07-22T07:25:35Z)
• SensiX: A Platform for Collaborative Machine Learning on the Edge [69.1412199244903]
  We present SensiX, a personal edge platform that stays between sensor data and sensing models. We demonstrate its efficacy in developing motion and audio-based multi-device sensing systems. Our evaluation shows that SensiX offers a 7-13% increase in overall accuracy and up to 30% increase across different environment dynamics at the expense of 3mW power overhead.
  arXiv  Detail & Related papers  (2020-12-04T23:06:56Z)
• Neural Network Virtual Sensors for Fuel Injection Quantities with Provable Performance Specifications [71.1911136637719]
  We show how provable guarantees can be naturally applied to other real world settings. We show how specific intervals of fuel injection quantities can be targeted to maximize robustness for certain ranges.
  arXiv  Detail & Related papers  (2020-06-30T23:33:17Z)

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.