Sensor-Activity Relevance in Human Activity Recognition with Wearable Motion Sensors and Mutual Information Criterion

Dobrucali, Oguzcan; Barshan, Billur

doi:10.1007/978-3-319-01604-7_28

Cited by 12 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Our daily and sports activities dataset is already available at the same website [36]. In our current work, we are investigating which of the six motion sensor units and which axes of these sensors are most useful in activity and fall detection [37]. Incorporating information from biomedical sensors for vital signs and audio sensors may further improve the robustness of our fall detection system.…”

Section: Discussionmentioning

confidence: 99%

Detecting Falls with Wearable Sensors Using Machine Learning Techniques

Özdemir

Barshan

2014

Sensors

Self Cite

313

235

View full text Add to dashboard Cite

Falls are a serious public health problem and possibly life threatening for people in fall risk groups. We develop an automated fall detection system with wearable motion sensor units fitted to the subjects' body at six different positions. Each unit comprises three tri-axial devices (accelerometer, gyroscope, and magnetometer/compass). Fourteen volunteers perform a standardized set of movements including 20 voluntary falls and 16 activities of daily living (ADLs), resulting in a large dataset with 2520 trials. To reduce the computational complexity of training and testing the classifiers, we focus on the raw data for each sensor in a 4 s time window around the point of peak total acceleration of the waist sensor, and then perform feature extraction and reduction. Most earlier studies on fall detection employ rule-based approaches that rely on simple thresholding of the sensor outputs. We successfully distinguish falls from ADLs using six machine learning techniques (classifiers): the k-nearest neighbor (k-NN) classifier, least squares method (LSM), support vector machines (SVM), Bayesian decision making (BDM), dynamic time warping (DTW), and artificial neural networks (ANNs). We compare the performance and the computational complexity of the classifiers and achieve the best results with the k-NN classifier and LSM, with sensitivity, specificity, and accuracy all above 99%. These classifiers also have acceptable computational requirements for training and testing. Our approach would be applicable in real-world scenarios where data records of indeterminate length, containing multiple activities in sequence, are recorded.

show abstract

Section: Discussionmentioning

confidence: 99%

Detecting Falls with Wearable Sensors Using Machine Learning Techniques

Özdemir

Barshan

2014

Sensors

Self Cite

313

235

View full text Add to dashboard Cite

show abstract

“…Reference [36] provides a framework for multi-dimensional time series classification by weighting each classifier's track record with a self-reported confidence score that is adjusted online. Our ongoing work in this area investigates sensor-activity relevance in human activity recognition with wearable motion sensors using the mutual information criterion [37].…”

mentioning

confidence: 99%

Investigating Inter-Subject and Inter-Activity Variations in Activity Recognition Using Wearable Motion Sensors

Barshan¹,

Yurtman²

2015

The Computer Journal

Self Cite

View full text Add to dashboard Cite

This work investigates inter-subject and inter-activity variability of a given activity dataset and provides some new definitions to quantify such variability. The definitions are sufficiently general and can be applied to a broad class of datasets that involve time sequences or features acquired using wearable sensors. The study is motivated by contradictory statements in the literature on the need for user-specific training in activity recognition. We employ our publicly available dataset that contains 19 daily and sports activities acquired from eight participants who wear five motion sensor units each. We pre-process recorded activity time sequences in three different ways and employ absolute, Euclidean and dynamic time warping distance measures to quantify the similarity of the recorded signal patterns. We define and calculate the average inter-subject and inter-activity distances with various methods based on the raw and pre-processed time-domain data as well as on the raw and preprocessed feature vectors. These definitions allow us to identify the subject who performs the activities in the most representative way and pinpoint the activities that show more variation among the subjects. We observe that the type of pre-processing used affects the results of the comparisons but that the different distance measures do not alter the comparison results as much. We check the consistency of our analysis and results by highlighting some of our activity recognition rates based on an exhaustive set of sensor unit, sensor type and subject combinations. We expect the results to be useful for dynamic sensor unit/type selection, for deciding whether to perform user-specific training and for designing more effective classifiers in activity recognition.

show abstract

“…Aynı duyucu birimi üzerinde, aynı ölçüm türüne ait eksenler bir arada gruplandırılarak, vücudun farklı yerlerindeki ölçüm türleri degerlendirilebildigi gibi; aynı duyucu birimi üzerinde yer alan tüm eksenler de bir arada gruplandırılarak, vücut üzerindeki duyucu birimleri de degerlendirilebilir. Söz konusu degerlendirmelerle ilgili sonuçlar, önceki çalışmamızda yer almaktadır [18].…”

Section: Iiii̇nsan Akti̇vi̇teleri̇ Veri̇ Kümesi̇unclassified

The analysis of wearable motion sensors in human activity recognition based on mutual information criterion

Dobrucali

Barshan

2014

2014 22nd Signal Processing and Communications Applications Conference (SIU)

Self Cite

View full text Add to dashboard Cite

Özetçe-Giyilebilir hareket duyucuları ile insan aktivitelerinin saptanmasında, uygun duyucu yapılanışının seçimi önem taşıyan bir konudur. Bu konu, kullanılacak duyucuların sayısının, türünün, sabitlenecekleri konum ve yönelimin belirlenmesi problemlerini içermektedir. Literatürde konuyla ilgili önceki çalışmalarda araştırmacılar, kendi seçtikleri duyucu yapılanışları ile diger olası duyucu yapılanışlarını, söz konusu yapılanışlar ile insan aktivitelerini ayırt etme başarımlarına göre karşılaştırmışlardır. Ancak, söz konusu ayırt etme başarımlarının, kullanılan öznitelikler ve sınıflandırıcılara baglı oldugu yadsınamaz. Bu çalışmada karşılıklı bilgi ölçütü kullanılarak duyucu yapılanışları, duyuculardan kaydedilen ham ölçümlerin zaman uzayındaki dagılımlarına göre belirlenmektedir. Bedenin farklı noktalarında bulunan ivmeölçer, dönüölçer ve manyetometrelerin ölçüm eksenleri arasından, gerçekleştirilen insan aktiviteleri hakkında en çok bilgi saglayanları saptanmıştır. Anahtar Kelimeler-giyilebilir hareket duyucuları, insan aktivitelerinin tanınması, duyucu yapılanışı, karşılıklı bilgi miktarı Abstract-Selecting a suitable sensor configuration is an important aspect of recognizing human activities with wearable motion sensors. This problem encompasses selecting the number and type of the sensors, their position on the human body. In earlier works, researchers have used customized sensor configurations, and compared them with others in terms of the activity recognition rate. However, it is clear that these comparisons are dependent on the feature sets and classifiers employed. In this study, employing mutual information measure, sensor configurations are determined with respect to the time-domain distributions of the raw sensor measurements. The most informative axes of the accelerometers, gyroscopes, and magnetometers fixed at several locations on the human body are detected.

show abstract

Sensor-Activity Relevance in Human Activity Recognition with Wearable Motion Sensors and Mutual Information Criterion

Cited by 12 publications

References 15 publications

Detecting Falls with Wearable Sensors Using Machine Learning Techniques

Detecting Falls with Wearable Sensors Using Machine Learning Techniques

Investigating Inter-Subject and Inter-Activity Variations in Activity Recognition Using Wearable Motion Sensors

The analysis of wearable motion sensors in human activity recognition based on mutual information criterion

Contact Info

Product

Resources

About