A Hardware-Assisted Energy-Efficient Processing Model for Activity Recognition Using Wearables

@article{Ghasemzadeh2016AHE,
  title={A Hardware-Assisted Energy-Efficient Processing Model for Activity Recognition Using Wearables},
  author={Hassan Ghasemzadeh and Ramin Fallahzadeh and Roozbeh Jafari},
  journal={ACM Trans. Design Autom. Electr. Syst.},
  year={2016},
  volume={21},
  pages={58:1-58:27}
}
Wearables are being widely utilized in health and wellness applications, primarily due to the recent advances in sensor and wireless communication, which enhance the promise of wearable systems in providing continuous and real-time monitoring and interventions. Wearables are generally composed of hardware/software components for collection, processing, and communication of physiological data. Practical implementation of wearable monitoring in real-life applications is currently limited due to… 
A Reliable and Reconfigurable Signal Processing Framework for Estimation of Metabolic Equivalent of Task in Wearable Sensors
TLDR
This paper introduces a power-aware sensor localization approach that allows users to wear the sensors on different body locations without need for adhering to a specific installation protocol and proposes a novel transductive transfer learning approach, which gives end-users the ability to add new sensors to the network without need to collecting new training data.
SmartSock: A wearable platform for context-aware assessment of ankle edema
TLDR
A novel wearable sensor, namely SmartSock, equipped with accelerometer and flexible stretch sensor embedded in clothing, powered by advanced machine learning, signal processing, and correlation techniques to provide real-time, reliable, and context-rich information in remote settings is presented.
CyHOP: A generic framework for real-time power-performance optimization in networked wearable motion sensors
TLDR
This work proposes a power-performance optimization framework, namely CyHOP (Cyclic and Holistic Optimization framework), for connected wearable motion sensors that performs a linear search by cycling through the system variables on each iteration until it converges to the global optimum.
S2NI: A mobile platform for nutrition monitoring from spoken data
TLDR
Speech-to-Nutrient-Information (S2NI), a comprehensive nutrition monitoring system that combines speech processing, natural language processing, and text mining in a unified platform to extract nutrient information such as calorie intake from spoken data, is proposed.
Step by Step Towards Effective Human Activity Recognition: A Balance between Energy Consumption and Latency in Health and Wellbeing Applications
TLDR
A balance between energy consumption and latency for HAR in health and wellbeing applications is recommended, which takes into account the context and health of the target population.
Human Activity Recognition Using Accelerometer, Gyroscope and Magnetometer Sensors: Deep Neural Network Approaches
TLDR
The objective of this examination is to break down execution of various classifiers as far as the referenced information preprocessing techniques and furthermore distinguishing the procedure for which the classifiers display prevalent precision.
Context-Aware System Design for Remote Health Monitoring: An Application to Continuous Edema Assessment
TLDR
This article proposes a novel low-power context-aware and real-time wearable platform capable of continuous assessment of ankle edema in remote settings and devise a novel derivative-free power optimization approach to maximize the battery lifetime resulting in improvement in battery lifetime by a factor of 2.13.
Speech2Health: A Mobile Framework for Monitoring Dietary Composition From Spoken Data
TLDR
This research demonstrates that new sensor modalities such as voice can be used either standalone or as a complementary source of information to existing modalities to improve the accuracy and acceptability of mobile health technologies for dietary composition monitoring.
A Statistical and Deep Learning Approach for Human Activity Recognition
TLDR
A comparative study on human activity recognition process in terms of employment of two different data preprocessing methods accompanied by five fashionable classifiers entitled as Random Forest (RF), Support Vector Machine (SVM), Naive Bayes (NB), Multilayer Perceptron (MLP) and Deep Convolutional Neural Network (CNN).
Human-in-the-loop Learning for Personalized Diet Monitoring from Unstructured Mobile Data
TLDR
EZNutriPal is introduced, an interactive diet monitoring system that operates on unstructured mobile data such as speech and free-text to facilitate dietary recording, real-time prompting, and personalized nutrition monitoring and features a natural language processing unit that learns incrementally to add user-specific nutrition data and rules to the system.
...
...

References

SHOWING 1-10 OF 71 REFERENCES
Ultra low-power signal processing in wearable monitoring systems: A tiered screening architecture with optimal bit resolution
TLDR
A granular decision-making architecture for physical movement monitoring applications that allows for significant power saving through an ultra low-power processing architecture and achieves 63.2% energy saving while maintaining a sensitivity in recognizing transitional actions.
Cost-sensitive feature selection for on-body sensor localization
TLDR
A novel signal processing approach that leverages feature selection algorithms to minimize power consumption of node localization and achieves an energy saving that ranges from 88% to 99.59% while obtaining an accuracy performance between 73.15% and 99.85%.
A Survey on Human Activity Recognition using Wearable Sensors
TLDR
The state of the art in HAR based on wearable sensors is surveyed and a two-level taxonomy in accordance to the learning approach and the response time is proposed.
Energy-Efficient Information-Driven Coverage for Physical Movement Monitoring in Body Sensor Networks
TLDR
The notion of compatibility graphs is introduced and how they can be utilized for power optimization in movement-monitoring platforms that operate with inertial sensors and an ILP formulation to attain a lower bound on the solution and a fast greedy technique is proposed.
An Ultra Low Power Granular Decision Making Using Cross Correlation: Minimizing Signal Segments for Template Matching
TLDR
This paper proposes an ultra low power granular decision making architecture, also called screening classifier, that can be viewed as a tiered wake up circuitry that improves the accuracy of classification by dividing a full template into smaller bins, called mini-templates, and activating optimal number of bins during each classification decision.
Structural Action Recognition in Body Sensor Networks: Distributed Classification Based on String Matching
TLDR
A system using inexpensive, off-the-shelf inertial sensor nodes is presented that constructs motion transcripts from biomedical signals and identifies movements by taking collaboration between the nodes into consideration, and obtains a classification accuracy of 84.13% with only one sensor node involved in the classification process.
A Long-Term Evaluation of Sensing Modalities for Activity Recognition
TLDR
A number of issues important for designing activity detection systems that may not have been as evident in prior work when data was collected under more controlled conditions are characterized.
Smart-Cuff: A wearable bio-sensing platform with activity-sensitive information quality assessment for monitoring ankle edema
TLDR
A wearable real-time platform (namely, Smart-Cuff), which integrates advanced technologies in sensing, computation, and signal processing and machine learning for continuous and real- time edema monitoring in remote and in-home settings is proposed.
Physical Movement Monitoring Using Body Sensor Networks: A Phonological Approach to Construct Spatial Decision Trees
TLDR
A novel classification model that identifies physical movements from body-worn inertial sensors while taking collaborative nature and limited resources of the system into consideration is introduced.
Impact of sensor misplacement on estimating metabolic equivalent of task with wearables
TLDR
A framework for sensor location-independent MET estimation is proposed that allows users to wear the sensors on different body locations without having to adhere to a specific installation protocol and how such an algorithm impacts the performance of MET estimation algorithms is studied.
...
...