Activity classification using realistic data from wearable sensors

By Juha Pärkkä, Miikka Ermes, Panu Korpipää, Jani Mäntyjärvi, Johannes Peltola, Ilkka Korhonen. IEEE Transactions on Information Technology in Biomedicine, 2006

839 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/e294c01b3f586cda75058ec16fe64b90e2807f54

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 Signal Processing

Citations in the corpus

Activity Recognition on an Accelerometer Embedded Mobile Phone with Varying Positions and Orientations (2010, background): “In [12], dozens of heterogeneous sensors are placed in various parts of the body to measure 18 different quantities, such as the acceleration of the chest and wrist, heart rate from finger, forehead and chest, temperature of the environment and skin.”
Smart Devices are Different: Assessing and MitigatingMobile Sensing Heterogeneities for Activity Recognition (2015, background): “Accelerometer-based HAR has been deployed in a large number of domains including smart homes [5, 32, 38], health care [31, 37], daily activity tracking [29], fitness tracking [16], fall detection of elderly people [18] and transportation mode detection [9, 24, 42].”
A Comparison of Feature Extraction Methods for the Classification of Dynamic Activities From Accelerometer Data (2009, methodology): “features directly from the time-varying acceleration signal [12, 16-18] and others from a frequency analysis [11, 13, 19, 20].”
Direct measurement of human movement by accelerometry. (2008, methodology): “Decision trees—classification and regression tree CART) The most simple and straight forward of these methods is a lassification and regression trees (CART), which have been dopted for pattern recognition involving human movement ased upon activity performed during ADL [53,61].”
A Review of Wearable Technologies for Elderly Care that Can Accurately Track Indoor Position, Recognize Physical Activities and Monitor Vital Signs in Real Time (2017, methodology): “The Minimum Redundancy and Maximum Relevance (MRMR) method is also utilized in feature set construction [82].”
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].”
Recognizing Daily and Sports Activities in Two Open Source Machine Learning Environments Using Body-Worn Sensor Units (2014, background): “The best and most ergonomic way to use a tool or a machine can be taught to workers in complex industrial environments [46].”
Optimal Placement of Accelerometers for the Detection of Everyday Activities (2013, background): “Parkka [16] Lying sitting, walking, rowing, cycling (8) 11 Chest and wrist Mean, variance, median, skewness, kurtosis, peak frequency, signal power Decision tree (86%) Hierarchical (82%) Neural network (82%)”
A Survey on Activity Detection and Classification Using Wearable Sensors (2017, background): “There are yet other sensor combinations explored in [136], [139], [146], [152], [153], and [221].”
Assessment of physical activity in youth. (2008, background): “More recently, activitytype classification schemes for interpretation of accelerometry data have emerged that aim to detect a multidimensional movement signature and assign membership to a (limited) set of activity types (7, 37, 48, 75, 79, 122).”
Understanding mobility based on GPS data (2008, methodology): “RELATED WORKS Solutions based on multiple sensors: In paper [4] and [9], Parkka et al.”
Wearable Sensors for Human Activity Monitoring: A Review (2015, background): “activity classification [20], [21], or even harvesting energy from body heat [22].”
Real-Time Recognition of Physical Activities and Their Intensities Using Wireless Accelerometers and a Heart Rate Monitor (2007, methodology): “Furthermore, most work with accelerometers has either used cumbersome wired sensors [3] or sensors that store data locally for off-line processing [1, 4, 5].”
Elderly activities recognition and classification for applications in assisted living (2013, methodology): “, 2006), Multi Perceptron (MLP) Neural Network (Györbı́ró, Fábián, & Hományi, 2009; Parkka et al., 2006), etc.”