Instance based human physical activity(hpa) recognition using shimmer2 wearable sensor data sets

There is interest in using wearable sensors to measure infant movement patterns and physical activity, however, this approach is confounded by caregiver motion. The purpose of this study is to estimate the extent that caregiver motion confounds wearable sensor data in full-day studies of infant leg movements. We used wearable sensors to measure leg movements of a four-month-old infant across 8.5 hours, during which the infant was handled by the caregiver in a typical manner. A researcher mimicked the actions of the caregiver with a doll. We calculated 7744 left and 7107 right leg movements for the infant and 1013 left and 1115 right “leg movements” for the doll. In this case, approximately 15% of infant leg movements can be attributed to background motion of the caregiver. This case report is the first step toward removing caregiver-produced background motion from the infant wearable sensor signal. We have estimated the size of the effect and described the activities that were related to noise in the signal. Future research can characterize the noise in detail and systematically explore different methods to remove it.

Download Full-text

Wavelet-Based Analysis of Physical Activity and Sleep Movement Data from Wearable Sensors among Obese Adults

Sensors ◽

10.3390/s19173710 ◽

2019 ◽

Vol 19 (17) ◽

pp. 3710 ◽

Cited By ~ 2

Author(s):

Rahul Soangra ◽

Vennila Krishnan

Keyword(s):

Physical Activity ◽

Health Care ◽

Inertial Sensor ◽

Wearable Sensors ◽

Physical Activities ◽

Sensor Data ◽

Time Interval ◽

Wearable Sensor ◽

Obesity Management ◽

Sleep Behavior

Decreased physical activity in obese individuals is associated with a prevalence of cardiovascular and metabolic disorders. Physicians usually recommend that obese individuals change their lifestyle, specifically changes in diet, exercise, and other physical activities for obesity management. Therefore, understanding physical activity and sleep behavior is an essential aspect of obesity management. With innovations in mobile and electronic health care technologies, wearable inertial sensors have been used extensively over the past decade for monitoring human activities. Despite significant progress with the wearable inertial sensing technology, there is a knowledge gap among researchers regarding how to analyze longitudinal multi-day inertial sensor data to explore activities of daily living (ADL) and sleep behavior. The purpose of this study was to explore new clinically relevant metrics using movement amplitude and frequency from longitudinal wearable sensor data in obese and non-obese young adults. We utilized wavelet analysis to determine movement frequencies on longitudinal multi-day wearable sensor data. In this study, we recruited 10 obese and 10 non-obese young subjects. We found that obese participants performed more low-frequency (0.1 Hz) movements and fewer movements of high frequency (1.1–1.4 Hz) compared to non-obese counterparts. Both obese and non-obese subjects were active during the 00:00–06:00 time interval. In addition, obesity affected sleep with significantly fewer transitions, and obese individuals showed low values of root mean square transition accelerations throughout the night. This study is critical for obesity management to prevent unhealthy weight gain by the recommendations of physical activity based on our results. Longitudinal multi-day monitoring using wearable sensors has great potential to be integrated into routine health care checkups to prevent obesity and promote physical activities.

Download Full-text

Human Activity Recognition using Fourier Transform Inspired Deep Learning Combination Model

International Journal of Sensors Wireless Communications and Control ◽

10.2174/2210327908666180727123657 ◽

2019 ◽

Vol 9 (1) ◽

pp. 16-31

Author(s):

Kyungkoo Jun

Keyword(s):

Fourier Transform ◽

Deep Learning ◽

Short Term Memory ◽

Window Size ◽

Sensor Data ◽

Data Sets ◽

Data Set ◽

Proposed Model ◽

Testing Data ◽

Labeling Scheme

Background & Objective: This paper proposes a Fourier transform inspired method to classify human activities from time series sensor data. Methods: Our method begins by decomposing 1D input signal into 2D patterns, which is motivated by the Fourier conversion. The decomposition is helped by Long Short-Term Memory (LSTM) which captures the temporal dependency from the signal and then produces encoded sequences. The sequences, once arranged into the 2D array, can represent the fingerprints of the signals. The benefit of such transformation is that we can exploit the recent advances of the deep learning models for the image classification such as Convolutional Neural Network (CNN). Results: The proposed model, as a result, is the combination of LSTM and CNN. We evaluate the model over two data sets. For the first data set, which is more standardized than the other, our model outperforms previous works or at least equal. In the case of the second data set, we devise the schemes to generate training and testing data by changing the parameters of the window size, the sliding size, and the labeling scheme. Conclusion: The evaluation results show that the accuracy is over 95% for some cases. We also analyze the effect of the parameters on the performance.

Download Full-text

An edge-cloud collaboration architecture for pattern anomaly detection of time series in wireless sensor networks

Complex & Intelligent Systems ◽

10.1007/s40747-021-00442-6 ◽

2021 ◽

Author(s):

Cong Gao ◽

Ping Yang ◽

Yanping Chen ◽

Zhongmin Wang ◽

Yue Wang

Keyword(s):

Time Series ◽

Wireless Sensor Networks ◽

Sensor Networks ◽

Anomaly Detection ◽

Estimation Method ◽

Feature Representation ◽

Sensor Data ◽

Wireless Sensor ◽

Data Sets ◽

Edge Node

AbstractWith large deployment of wireless sensor networks, anomaly detection for sensor data is becoming increasingly important in various fields. As a vital data form of sensor data, time series has three main types of anomaly: point anomaly, pattern anomaly, and sequence anomaly. In production environments, the analysis of pattern anomaly is the most rewarding one. However, the traditional processing model cloud computing is crippled in front of large amount of widely distributed data. This paper presents an edge-cloud collaboration architecture for pattern anomaly detection of time series. A task migration algorithm is developed to alleviate the problem of backlogged detection tasks at edge node. Besides, the detection tasks related to long-term correlation and short-term correlation in time series are allocated to cloud and edge node, respectively. A multi-dimensional feature representation scheme is devised to conduct efficient dimension reduction. Two key components of the feature representation trend identification and feature point extraction are elaborated. Based on the result of feature representation, pattern anomaly detection is performed with an improved kernel density estimation method. Finally, extensive experiments are conducted with synthetic data sets and real-world data sets.

Download Full-text

Biosignal Compression Toolbox for Digital Biomarker Discovery

Sensors ◽

10.3390/s21020516 ◽

2021 ◽

Vol 21 (2) ◽

pp. 516

Author(s):

Brinnae Bent ◽

Baiying Lu ◽

Juseong Kim ◽

Jessilyn P. Dunn

Keyword(s):

Wavelet Transform ◽

Singular Value Decomposition ◽

Data Compression ◽

Biomarker Discovery ◽

Singular Value ◽

Sensor Data ◽

Discrete Wavelet ◽

Wearable Sensor ◽

Huffman Encoding ◽

Value Decomposition

A critical challenge to using longitudinal wearable sensor biosignal data for healthcare applications and digital biomarker development is the exacerbation of the healthcare “data deluge,” leading to new data storage and organization challenges and costs. Data aggregation, sampling rate minimization, and effective data compression are all methods for consolidating wearable sensor data to reduce data volumes. There has been limited research on appropriate, effective, and efficient data compression methods for biosignal data. Here, we examine the application of different data compression pipelines built using combinations of algorithmic- and encoding-based methods to biosignal data from wearable sensors and explore how these implementations affect data recoverability and storage footprint. Algorithmic methods tested include singular value decomposition, the discrete cosine transform, and the biorthogonal discrete wavelet transform. Encoding methods tested include run-length encoding and Huffman encoding. We apply these methods to common wearable sensor data, including electrocardiogram (ECG), photoplethysmography (PPG), accelerometry, electrodermal activity (EDA), and skin temperature measurements. Of the methods examined in this study and in line with the characteristics of the different data types, we recommend direct data compression with Huffman encoding for ECG, and PPG, singular value decomposition with Huffman encoding for EDA and accelerometry, and the biorthogonal discrete wavelet transform with Huffman encoding for skin temperature to maximize data recoverability after compression. We also report the best methods for maximizing the compression ratio. Finally, we develop and document open-source code and data for each compression method tested here, which can be accessed through the Digital Biomarker Discovery Pipeline as the “Biosignal Data Compression Toolbox,” an open-source, accessible software platform for compressing biosignal data.

Download Full-text

Direct Lightweight Temporal Compression for Wearable Sensor Data

IEEE Sensors Letters ◽

10.1109/lsens.2021.3051809 ◽

2021 ◽

Vol 5 (2) ◽

pp. 1-4

Author(s):

Lucie Klus ◽

Roman Klus ◽

Elena Simona Lohan ◽

Carlos Granell ◽

Jukka Talvitie ◽

...

Keyword(s):

Sensor Data ◽

Wearable Sensor ◽

Temporal Compression

Download Full-text

Estimating Clinical Scores From Wearable Sensor Data In Stroke Survivors

Archives of Physical Medicine and Rehabilitation ◽

10.1016/j.apmr.2017.08.202 ◽

2017 ◽

Vol 98 (10) ◽

pp. e65

Author(s):

Claire Meagher ◽

Stefano Sapienza ◽

Catherine Adans-Dester ◽

Anne O’Brien ◽

Shyamal Patel ◽

...

Keyword(s):

Sensor Data ◽

Stroke Survivors ◽

Wearable Sensor ◽

Clinical Scores

Download Full-text

Getting Enough Sleep: On the Importance of Collecting Longitudinal Data from Wearables to Assess Sleep Quality and Seasonal Effects on Variability in Daily Activity (Preprint)

10.2196/preprints.31807 ◽

2021 ◽

Author(s):

María Óskarsdóttir ◽

Anna Sigridur Islind ◽

Elias August ◽

Erna Sif Arnardóttir ◽

Francois Patou ◽

...

Keyword(s):

Physical Activity ◽

Heart Rate ◽

Data Collection ◽

Sleep Quality ◽

Daily Activity ◽

Hospital Environment ◽

Sensor Data ◽

Seasonal Patterns ◽

Sleep Patterns ◽

Sleep Habits

BACKGROUND The method considered the gold standard for recording sleep is a polysomnography, where the measurement is performed in a hospital environment for 1-3 nights. This requires subjects to sleep with a device and several sensors attached to their face, scalp, and body, which is both cumbersome and expensive. For longer studies with actigraphy, 3-14 days of data collection is typically used for both clinical and research studies. OBJECTIVE The primary goal of this paper is to investigate if the aforementioned timespan is sufficient for data collection, when performing sleep measurements at home using wearable and non-wearable sensors. Specifically, whether 3-14 days of data collection sufficient to capture an individual’s sleep habits and fluctuations in sleep patterns in a reliable way for research purposes. Our secondary goals are to investigate whether there is a relationship between sleep quality, physical activity, and heart rate, and whether individuals who exhibit similar activity and sleep patterns in general and in relation to seasonality can be clustered together. METHODS Data on sleep, physical activity, and heart rate was collected over a period of 6 months from 54 individuals in Denmark aged 52-86 years. The Withings Aura sleep tracker (non-wearable) and Withings Steel HR smartwatch (wearable) were used. At the individual level, we investigated the consistency of various physical activities and sleep metrics over different time spans to illustrate how sensor data from self-trackers can be used to illuminate trends. RESULTS Significant variability in standard metrics of sleep quality was found between different periods throughout the study. We show specifically that in order to get more robust individual assessment of sleep and physical activity patterns through wearable and non-wearable devices, a longer evaluation period than 3-14 days is necessary. Additionally, we found seasonal patterns in sleep data related to changing of the clock for Daylight Saving Time (DST). CONCLUSIONS We demonstrate that over two months worth of self-tracking data is needed to provide a representative summary of daily activity and sleep patterns. By doing so, we challenge the current standard of 3-14 days for sleep quality assessment and call for rethinking standards when collecting data for research purposes. Seasonal patterns and DST clock change are also important aspects that need to be taken into consideration, and designed for, when choosing a period for collecting data. Furthermore, we suggest using consumer-grade self-trackers (wearable and non-wearable ones) to support longer term evaluations of sleep and physical activity for research purposes and, possibly, clinical ones in the future.

Download Full-text