Accelerometer Signal Processing for User Activity Detection

Baek, Jaemin; Lee, Geehyuk; Park, Won-Bae; Yun, Byoung-Ju

doi:10.1007/978-3-540-30134-9_82

Cited by 71 publications

(29 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This was attached to the waist of the subjects, following the recommendations of previous works [18,[27][28][29]. Data were digitized (100 samples/s) and transmitted to a laptop system through Bluetooth connection.…”

Section: Procedures and Data Collectionmentioning

confidence: 99%

Varying behavior of different window sizes on the classification of static and dynamic physical activities from a single accelerometer

Fida

Bernabucci

Bibbo

et al. 2015

Medical Engineering & Physics

View full text Add to dashboard Cite

Section: Procedures and Data Collectionmentioning

confidence: 99%

Varying behavior of different window sizes on the classification of static and dynamic physical activities from a single accelerometer

Fida

Bernabucci

Bibbo

et al. 2015

Medical Engineering & Physics

View full text Add to dashboard Cite

“…This method is the simplest form of greedy feature selection, which is employed by Marais et al [24] to classify sheep behavior, finding the maximum and minimum values for each axis in a frame as the most important feature out of mean, standard deviation, variance, skewness, kurtosis, energy, frequency-domain entropy, correlation between axes, and average signal magnitude. This combination of features is widely used in activity classification [2,4,25,37]. Previous approaches either select features by using randomly selected training and test data from the full dataset [24], providing similar proportions of each specimen's data in both the training and the test set by visual or statistical analysis [33], or by comparing various feature combinations found in the literature to reach the highest performing combination [16,36].…”

Section: Related Workmentioning

confidence: 99%

Robust Sensor-Orientation-Independent Feature Selection for Animal Activity Recognition on Collar Tags

Kamminga

Meijers

et al. 2018

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.

View full text Add to dashboard Cite

Fundamental challenges faced by real-time animal activity recognition include variation in motion data due to changing sensor orientations, numerous features, and energy and processing constraints of animal tags. This paper aims at finding small optimal feature sets that are lightweight and robust to the sensor's orientation. Our approach comprises four main steps. First, 3D feature vectors are selected since they are theoretically independent of orientation. Second, the least interesting features are suppressed to speed up computation and increase robustness against overfitting. Third, the features are further selected through an embedded method, which selects features through simultaneous feature selection and classification. Finally, feature sets are optimized through 10-fold cross-validation. We collected real-world data through multiple sensors around the neck of five goats. The results show that activities can be accurately recognized using only accelerometer data and a few lightweight features. Additionally, we show that the performance is robust to sensor orientation and position. A simple Naive Bayes classifier using only a single feature achieved an accuracy of 94 % with our empirical dataset. Moreover, our optimal feature set yielded an average of 94 % accuracy when applied with six other classifiers. This work supports embedded, real-time, energy-efficient, and robust activity recognition for animals.

show abstract

“…After testing a wide range of features [3] [15], we selected the following four features based on classification accuracy and computational cost. Details are shown in the table in Figure 5 .…”

Section: Naive Bayes Classificationmentioning

confidence: 99%

Coarse In-Building Localization with Smartphones

Parnandi

Le²,

Vaghela³

et al. 2010

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

Abstract. Geographic location of a person is important contextual information that can be used in a variety of scenarios like disaster relief, directional assistance, context-based advertisements, etc. GPS provides accurate localization outdoors but is not useful inside buildings. We propose an coarse indoor localization approach that exploits the ubiquity of smart phones with embedded sensors. GPS is used to find the building in which the user is present. The Accelerometers are used to recognize the user's dynamic activities (going up or down stairs or an elevator) to determine his/her location within the building. We demonstrate the ability to estimate the floor-level of a user. We compare two techniques for activity classification, one is naive Bayes classifier and the other is based on dynamic time warping. The design and implementation of a localization application on the HTC G1 platform running Google Android is also presented.

show abstract

Accelerometer Signal Processing for User Activity Detection

Cited by 71 publications

References 4 publications

Varying behavior of different window sizes on the classification of static and dynamic physical activities from a single accelerometer

Varying behavior of different window sizes on the classification of static and dynamic physical activities from a single accelerometer

Robust Sensor-Orientation-Independent Feature Selection for Animal Activity Recognition on Collar Tags

Coarse In-Building Localization with Smartphones

Contact Info

Product

Resources

About