Activity identification using body-mounted sensors—a review of classification techniques

By Stephen J. Preece, John Yannis Goulermas, Laurence P. J. Kenney, David Howard, Kenneth Meijer, Robin H. Crompton. Physiological Measurement, 2009

617 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/1f6940eeff61cd3bbda010c0e196586fa7c83d3e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

A Survey of Online Activity Recognition Using Mobile Phones (2015, positive): “[26] provides an outline of relevant research and applicable techniques.”
Physical Human Activity Recognition Using Wearable Sensors (2015, background): “Inclinometers and goniometers are other types of sensors that are used to measure upper/lower limbs kinematics [3].”
Human Activity Recognition Using Inertial/Magnetic Sensor Units (2010, background): “Detailed explanations of these algorithms within the context of human activity recognition can be found in [27,29].”
Recognizing Daily and Sports Activities in Two Open Source Machine Learning Environments Using Body-Worn Sensor Units (2014, methodology): “Furthermore, contradictory studies exist [42].”
How accurately can sitting and the intensity of walking and cycling be classified using an accelerometer on the waist for the purpose of the “Global recommendations on physical activity for health”? (2015, methodology): “Other similar research has used 3 till 20 participants [12, 18, 19]”
Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition (2016, background): “Sliding window approaches are commonly used for static and periodic activities, while sporadic activities lend themselves to template matching approaches or hidden Markov modelling [8,11].”
Mobile Health Technology Evaluation (2013, methodology): “, mean, variance, amplitude); and (6) tests the accuracy of the classifier (% agreement with annotated “truth”) with the training data set initially and then externally with the validation data set.(8,9,32,33) These steps are often conducted in an iterative process where various classifiers, window ”
Comparative study on classifying human activities with miniature inertial and magnetic sensors (2010, background): “More detailed descriptions can be found in [14,57] and in the given references.”
The Opportunity challenge: A benchmark database for on-body sensor-based activity recognition (2013, methodology): “…ETH Zürich, Gloriastrasse 35, 8092 Zürich, Switzerland a r t i c l e i n f o a b s t r a c t Article history: Available online xxxx Keywords: Activity recognition Machine learning Body-sensor networks Performance evaluation Metrics ROC analysis 0167-8655/$ - see front matter 2012 Elsevier B.V.”
Optimal Placement of Accelerometers for the Detection of Everyday Activities (2013, background): “SVMs can be implemented in real time and work reliably on noisy data sets [23].”
Sentiment analysis in organizational work: Towards an ontology of people analytics (2018, background): “…2014); Sentiment identification by body motions (Stock, Righart & Gelder, 2007) and tone of voice; Activity profiling through body motion analysis (Preece & Goulermas, 2009; Diego-Mas & Alcaide-Marzal, 2014); Posture identification (Quwaider & Biswas, 2008; Mattmann et al., 2008); Posture…”
Walk detection and step counting on unconstrained smartphones (2013, background): “, falls) [46] and discrimination of walking patterns [24].”
Gait Analysis Using Wearable Sensors (2012, methodology): “[88] reviewed of the techniques which have been used to classify the normal and identify falls from body-worn sensors including accelerometers, gyroscope and other sensors for gait analysis.”
From Data Acquisition to Data Fusion: A Comprehensive Review and a Roadmap for the Identification of Activities of Daily Living Using Mobile Devices (2016, neutral): “For the detection of physical activities, the authors in [10] propose the use of inertial sensors, i.”
A Comparison of Feature Extraction Methods for the Classification of Dynamic Activities From Accelerometer Data (2009, methodology): “techniques typically operate via a two-stage process [15].”