Estimating Physical Characteristics with Body-worn Accelerometers Based on Activity Similarities

Masuda, Akira; Maekawa, Taira

doi:10.2197/ipsjjip.24.237

Cited by 3 publications

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, recordings from a single inertial sensor can be employed to deduce the gender, age and height of a user 13 . In this respect, Masuda and Maekawa have also shown that user characteristics (gender, height, weight, dominant hand) can be estimated with machine learning strategies uniquely from basic activities such as washing dishes or walking 14 .…”

Section: Related Workmentioning

confidence: 99%

A study on the impact of the users’ characteristics on the performance of wearable fall detection systems

Santoyo-Ramón

Casilari

Cano-García

2021

Sci Rep

View full text Add to dashboard Cite

Wearable Fall Detection Systems (FDSs) have gained much research interest during last decade. In this regard, Machine Learning (ML) classifiers have shown great efficiency in discriminating falls and conventional movements or Activities of Daily Living (ADLs) based on the analysis of the signals captured by transportable inertial sensors. Due to the intrinsic difficulties of training and testing this type of detectors in realistic scenarios and with their target audience (older adults), FDSs are normally benchmarked against a predefined set of ADLs and emulated falls executed by volunteers in a controlled environment. In most studies, however, samples from the same experimental subjects are used to both train and evaluate the FDSs. In this work, we investigate the performance of ML-based FDS systems when the test subjects have physical characteristics (weight, height, body mass index, age, gender) different from those of the users considered for the test phase. The results seem to point out that certain divergences (weight, height) of the users of both subsets (training ad test) may hamper the effectiveness of the classifiers (a reduction of up 20% in sensitivity and of up to 5% in specificity is reported). However, it is shown that the typology of the activities included in these subgroups has much greater relevance for the discrimination capability of the classifiers (with specificity losses of up to 95% if the activity types for training and testing strongly diverge).

show abstract

Section: Related Workmentioning

confidence: 99%

A study on the impact of the users’ characteristics on the performance of wearable fall detection systems

Santoyo-Ramón

Casilari

Cano-García

2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Algorithmic inferences on audio data can reveal a wide range of potentially private information, such as one's height and weight [17], emotional state [18], [19], and health conditions [19]. Motion sensor data collected by inertial measurement units can also reveal information about an individual's physical characteristics, such as height and weight [20], level of activity [21], and changes in behavioral patterns [22]. These data may be protected with PETs developed for other types of devices and that use transformations of the data [23].…”

mentioning

confidence: 99%