Multimodal Wearable Sensing for Fine-Grained Activity Recognition in Healthcare

@article{De2015MultimodalWS,
  title={Multimodal Wearable Sensing for Fine-Grained Activity Recognition in Healthcare},
  author={Debraj De and Pratool Bharti and Sajal K. Das and Sriram Chellappan},
  journal={IEEE Internet Computing},
  year={2015},
  volume={19},
  pages={26-35}
}
State-of-the-art in-home activity recognition schemes with wearable devices are mostly capable of detecting coarse-grained activities (sitting, standing, walking, or lying down), but can't distinguish complex activities (sitting on the floor versus the sofa or bed). Such schemes often aren't effective for emerging critical healthcare applications -- for example, in remote monitoring of patients with Alzheimer's disease, bulimia, or anorexia -- because they require a more comprehensive… Expand
Context-based Human Activity Recognition Using Multimodal Wearable Sensors
TLDR
This dissertation designed a novel approach for in-home, fine-grained activity recognition using multimodal wearable sensors on multiple body positions, along with very small Bluetooth beacons deployed in the environment and introduced Watch-Dog – a self-harm activity recognition engine, which attempts to infer selfharming activities from sensing accelerometer data using wearable sensors worn on a subject's wrist. Expand
HuMAn: Complex Activity Recognition with Multi-Modal Multi-Positional Body Sensing
TLDR
Experimental results demonstrate that the HuMAn system can detect 21 complex at-home activities with high degree of accuracy, and a novel two-level structured classification algorithm that improves accuracy by leveraging sensors in multiple body positions. Expand
Detailed Human Activity Recognition using Wearable Sensor and Smartphones
TLDR
The contribution of this work is to present a framework for detailing in identification for both static and dynamic activities, as well as their intense counterparts by designing an ensemble of classifiers. Expand
Data-driven Context Detection Leveraging Passively Sensed Nearables for Recognizing Complex Activities of Daily Living
TLDR
A methodology to automatically detect the context using passively observable information broadcasted by devices in users’ locale is developed and a pattern extraction algorithm and probabilistic mapping between the context and activities to reduce the set of probable outcomes. Expand
Fine grained activity recognition using smart handheld
TLDR
This paper proposes a fine grained ubiquitous activity recognition system that uses only smartphone accelerometer that is available in any smartphone configuration and selects minimal set of features that can precisely recognize twelve activities. Expand
A Survey on Activity Detection and Classification Using Wearable Sensors
Activity detection and classification are very important for autonomous monitoring of humans for applications, including assistive living, rehabilitation, and surveillance. Wearable sensors haveExpand
Detailed Activity Recognition with Smartphones
TLDR
A detailed activity recognition system that uses smartphone accelerometer (available in almost every smartphone) thus does not need any special device to be carried by the user and introduces a new feature based on jerk to detect both detailed static activities (sit on chair) and detailed dynamic activities (brisk walk). Expand
Human Physical Activity Recognition Using Smartphone Sensors
TLDR
A human physical activity recognition system based on data collected from smartphone sensors that shows good accuracy for recognizing all six activities, with especially good results obtained for walking, running, sitting, and standing. Expand
An Ensemble of Condition Based Classifiers for Device Independent Detailed Human Activity Recognition Using Smartphones †
TLDR
A ubiquitous solution to detailed activity recognition through the use of smartphone sensors by forming an ensemble of the condition based classifiers to address the variance due to different hardware configuration and usage behavior in terms of where the smartphone is kept. Expand
Design of a Wearable Wireless Multi-Sensor Monitoring System and Application for Activity Recognition Using Deep Learning
TLDR
ConvLSTM outperforms CNN and LSTM as far as activity recognition is concerned and is focused on new dataset generation for activity recognition. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 10 REFERENCES
Multi-scale Conditional Random Fields for first-person activity recognition
  • Kai Zhan, S. Faux, F. Ramos
  • Computer Science
  • 2014 IEEE International Conference on Pervasive Computing and Communications (PerCom)
  • 2014
TLDR
A feature extraction method from accelerometer and video; a classification algorithm integrating both locomotive (body motions) and stationary activities (without or with small motions); a novel multi-scale dynamic graphical model structure for structured classification over time. Expand
Infrastructure-assisted smartphone-based ADL recognition in multi-inhabitant smart environments
  • N. Roy, A. Misra, D. Cook
  • Computer Science
  • 2013 IEEE International Conference on Pervasive Computing and Communications (PerCom)
  • 2013
TLDR
This work proposes a hybrid approach for recognizing complex Activities of Daily Living that lie between the two extremes of intensive use of body-worn sensors and the use of infrastructural sensors and shows how spatiotemporal constraints can be used to significantly improve the accuracy and computational overhead of traditional coupled-HMM based approaches. Expand
Feature Selection and Activity Recognition System Using a Single Triaxial Accelerometer
  • P. Gupta, T. Dallas
  • Engineering, Computer Science
  • IEEE Transactions on Biomedical Engineering
  • 2014
TLDR
An accurate activity recognition system utilizing a body worn wireless accelerometer, to be used in the real-life application of patient monitoring, utilizes data from a single, waist-mounted triaxial accelerometer to classify gait events into six daily living activities and transitional events. Expand
Complex activity recognition using context-driven activity theory and activity signatures
TLDR
This article proposes, develops and validate a novel Context-Driven Activity Theory (CDAT) for recognizing complex activities, and develops a mechanism using probabilistic and Markov chain analysis to discover complex activity signatures and generate complex activity definitions. Expand
The hierarchical relationship between activities of daily living and instrumental activities of daily living.
TLDR
A six-level scale similar in structure and detail to the Katz Index of ADL was examined and can be used to described a broader range of needs of elders in the community and will be particularly useful to health services planners, practitioners, and researchers. Expand
The Complete Guide to Alzheimer's Proofing your Home
Written by a practising architect and gerontologist, this text explains how to create a home environment that will help coping with the many difficulties associated with Alzheimer's. The text isExpand
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
TLDR
This work presents iterative parameter estimation algorithms for conditional random fields and compares the performance of the resulting models to HMMs and MEMMs on synthetic and natural-language data. Expand
Review of the prevalence and incidence of eating disorders.
TLDR
Only a minority of people who meet stringent diagnostic criteria for eating disorders are seen in mental health care, and the incidence of anorexia nervosa increased over the past century, until the 1970s. Expand
Mark L. Warner. The Complete Guide to Alzheimer's Proofing Your Home. West Lafayette IN: Purdue University, 1998.
  • N. Gnaedinger
  • Medicine
  • Canadian Journal on Aging / La Revue canadienne du vieillissement
  • 2000
TLDR
Le guide s'insère bien dans la collection des ouvrages de référence destinés aux soignants oeuvrant auprès of patients atteints de démence ainsi que dans les bibliothèques des universités and les collèges. Expand
We welcome articles accompanied by Web-based demos. For more information, see our author guidelines at www
  • We welcome articles accompanied by Web-based demos. For more information, see our author guidelines at www