Ambulatory system for human motion analysis using a kinematic sensor: monitoring of daily physical activity in the elderly

By Bijan Najafi, Kamiar Aminian, Anisoara Paraschiv-Ionescu, François Loew, Christophe J. Büla, Philippe A. Robert. IEEE Transactions on Biomedical Engineering, 2003

828 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/aac1b161dd4cff4e63488b2f31218f59f197245e

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

Eye Movement Analysis for Activity Recognition Using Electrooculography (2009, background): “A rich source of information about a person’s context yet under-investigated are the movements The aim of this work is to assess the feasibility of recognising human physical activity using eye movement analysis.”
A Comparison of Feature Extraction Methods for the Classification of Dynamic Activities From Accelerometer Data (2009, background): “In this scenario, more complex signal processing along with an appropriate biomechanical model is required to differentiate between different postures, postural transitions, and continuous dynamic activity [32].”
A Review of Accelerometry-Based Wearable Motion Detectors for Physical Activity Monitoring (2010, background): “Wearable sensors can be directly attached to the skin [15,24], or with some form of indirect attachment by using straps, pant belts and wristbands, or other accessories [20,22,25,26].”
Human Activity Recognition Using Inertial/Magnetic Sensor Units (2010, background): “Some studies also recognize transitions between postures [8,19,23,24].”
Physical Human Activity Recognition Using Wearable Sensors (2015, methodology): “Sensor attachment to the human body involves fixing sensors directly to skin [13] as well as using an assortment of straps, belts and wristbands [34,35].”
Elderly activities recognition and classification for applications in assisted living (2013, methodology): “Examples of activity recognition systems which recognize ambulatory activities were reported in the literatures such as Najafi et al. (2003), Zhu and Sheng (2011) and Fuentes, Gonzalez-Abril, Angulo, and Ortega (2012).”
Activity identification using body-mounted sensors—a review of classification techniques (2009, methodology): “These algorithms are typically sensitive to the exact choice of threshold angle (Najafi et al 2003).”
Recognizing Daily and Sports Activities in Two Open Source Machine Learning Environments Using Body-Worn Sensor Units (2014, background): “In a number of studies, video cameras are used only as a reference for comparison with inertial sensor data [20] [21] [22] [23], whereas in others, data from these two sensing modalities are integrated or fused [24] [25].”
Stretchable, Transparent, Ultrasensitive, and Patchable Strain Sensor for Human-Machine Interfaces Comprising a Nanohybrid of Carbon Nanotubes and Conductive Elastomers. (2015, background): “Detection of strains induced on human skin using patchable conformal strain sensors is one approach to monitor human emotions,(8) intentions, and activities.(2,9,10)”
Activity Recognition Using Inertial Sensing for Healthcare, Wellbeing and Sports Applications: A Survey (2010, background): “[52, 64] Spectral Centroid [9] Spectral Energy [55, 56, 57, 42, 52, 9] Spectral Entropy [34, 55, 19] Freq.”
Window Size Impact in Human Activity Recognition (2014, background): “These disturbances are sometimes removed through a ﬁltering process [18,66]; however, this is not always applied, since it may imply a certain information loss.”
Sensor Positioning for Activity Recognition Using Wearable Accelerometers (2011, background): “Another limitation is that accelerometers alone may not be enough to provide sufficient contextual information and they need to be combined with other sensors, such as microphones [15], gyroscopes [16]‐[ 18 ], and electrocardiogram (ECG) sensors [19] to provide more accurate activity classification.”
Comparative study on classifying human activities with miniature inertial and magnetic sensors (2010, methodology): “The five MTx units are connected with 1 m cables to a device called the Xbus Master, which is attached to the subject’s belt.”
The relevance of clinical balance assessment tools to differentiate balance deficits (2010, neutral): “, 2001) or to determine time spent in various activities such as lying down, walking, sitting, and standing (Tanaka, et al, 1994; Najafi et al., 2002; Najafi et al., 2003).”
Machine Learning Methods for Classifying Human Physical Activity from On-Body Accelerometers (2010, neutral): “[44] 1 2D acc 1 gyro Wavelet coefficients Threshold-based 5 44 > 90”