Classification of basic daily movements using a triaxial accelerometer

By M. Mathie, Branko G. Celler, Nigel H. Lovell, A. Coster. Medical and Biological Engineering and Computing, 2004

591 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Physical Therapy, Sports Therapy and Rehabilitation

View Paper: https://www.semanticscholar.org/paper/339fd9a7e839130b1108c1f984e41c279b41ef8f

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

In Physical Therapy, Sports Therapy and Rehabilitation

Citations in the corpus

Optimal Placement of Accelerometers for the Detection of Everyday Activities (2013, background): “Mathie [15] Fall, walking, transitional, sit, stand and lie (6) 26 Waist Signal magnitude area, mean acceleration Decision tree (87%)”
Activity identification using body-mounted sensors—a review of classification techniques (2009, methodology): “For a detailed description of accelerometry the reader is directed to a comprehensive review by Mathie et al (2004b).”
Comparison of low-complexity fall detection algorithms for body attached accelerometers. (2008, background): “Body attached accelerometers [9–12] and gyroscopes [13,14] have been used to detect human movement, including falls.”
Preprocessing techniques for context recognition from accelerometer data (2010, background): “It is also possible to use SMA as the basis for identifying periods of user activity [21].”
Activity Recognition Using Inertial Sensing for Healthcare, Wellbeing and Sports Applications: A Survey (2010, background): “Signal Magnitude Area (SMA) SMA features are shown to be used effectively for identifying periods of daily activities[71].”
Mercury: a wearable sensor network platform for high-fidelity motion analysis (2009, background): “The traditional approach has been to sample data on the sensors and deliver it to a back-end for offline processing [2, 4, 31].”
Using Internet and Mobile Phone Technology to Deliver an Automated Physical Activity Program: Randomized Controlled Trial (2007, methodology): “Accelerometers have been widely used to monitor physical activity [28-30], both for school-age children [31] and adults [32].”
Comparative study on classifying human activities with miniature inertial and magnetic sensors (2010, methodology): “This in turn has a broad range of potential applications in biomechanics [15,16], ergonomics [17], remote monitoring of the physically or mentally disabled, the elderly, and children [18], detecting and classifying falls [19–21], medical diagnosis and treatment [22], home-based rehabilitation and ph”
Machine Learning Methods for Classifying Human Physical Activity from On-Body Accelerometers (2010, methodology): “Interestingly, using accelerometers is also commonplace in many other biomedical applications, such as tremor analysis [27], assessment of physical activity [28] and quantification of metabolic energy expenditure [29], where the computational techniques of interest do not require error-prone procedu”
Recognizing Daily and Sports Activities in Two Open Source Machine Learning Environments Using Body-Worn Sensor Units (2014, background): “Remote monitoring of the physically or mentally disabled, the elderly and children can be achieved indoors and outdoors [43] and cognitive assistance provided when needed.”
Physical Human Activity Recognition Using Wearable Sensors (2015, methodology): “As observed in Table 1, accuracy levels of 83% to 100% for human activity recognition rates have been obtained [14,17–19].”
Using acceleration measurements for activity recognition: An effective learning algorithm for constructing neural classifiers (2008, methodology): “Decision tree classification methods have been successfully used for recognition problems as well as the activity recognition from acceleration data (Bao and Intille, 2004; Mathie et al., 2004; Karantonis et al., 2006; Solà i Carós et al., 2005).”
Real-Time Pervasive Monitoring for Postoperative Care (2007, background): “for classifying daily activities requires extensive computation resources [31].”
Activity recognition using cell phone accelerometers (2011, background): “Additional studies have similarly focused on how one can use a variety of accelerometerbased devices to identify a range of user activities [4-7, 9-16, 21].”
Human Activity Recognition Using Inertial/Magnetic Sensor Units (2010, methodology): “The number of sensors used vary between one [8,23] to twelve [4].”
Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring (2006, unknown): “In this case, Mathie et al. [17] suggest the use of an overlay for validation of classification sequences, which could be implemented using rule-based heuristics, fuzzy logic, or statistical behavioral modeling, such as Markov chaining.”