Classical Machine Learning Versus Deep Learning for the Older Adults Free-Living Activity Classification

Physical activity has a strong influence on mental and physical health and is essential in healthy ageing and wellbeing for the ever-growing elderly population. Wearable sensors can provide a reliable and economical measure of activities of daily living (ADLs) by capturing movements through, e.g., accelerometers and gyroscopes. This study explores the potential of using classical machine learning and deep learning approaches to classify the most common ADLs: walking, sitting, standing, and lying. We validate the results on the ADAPT dataset, the most detailed dataset to date of inertial sensor data, synchronised with high frame-rate video labelled data recorded in a free-living environment from older adults living independently. The findings suggest that both approaches can accurately classify ADLs, showing high potential in profiling ADL patterns of the elderly population in free-living conditions. In particular, both long short-term memory (LSTM) networks and Support Vector Machines combined with ReliefF feature selection performed equally well, achieving around 97% F-score in profiling ADLs.

Determining Physical Activity Characteristics from Wristband Data for Use in Automated Insulin Delivery Systems

Algorithms that can determine the type of physical activity (PA) and quantify the intensity can allow precision medicine approaches, such as automated insulin delivery systems that modulate insulin administration in response to PA. In this work, data from a multi-sensor wristband is used to design classifiers to distinguish among five different physical states (PS) (resting, activities of daily living, running, biking, and resistance training), and to develop models to estimate the energy expenditure (EE) of the PA for diabetes therapy. The data collected are filtered, features are extracted from the reconciled signals, and the extracted features are used by machine learning algorithms, including deep-learning techniques, to obtain accurate PS classification and EE estimation. The various machine learning techniques have different success rates ranging from 75.7% to 94.8% in classifying the five different PS. The deep neural network model with long short-term memory has 94.8% classification accuracy. We achieved 0.5 MET (Metabolic Equivalent of Task) root-mean-square error for EE estimation accuracy, relative to indirect calorimetry with randomly selected testing data (10% of collected data). We also demonstrate a 5% improvement in PS classification accuracy and a 0.34 MET decrease in the mean absolute error when using multi-sensor approach relative to using only accelerometer data.

Performance Analysis of Boosting Classifiers in Recognizing Activities of Daily Living

Physical activity is essential for physical and mental health, and its absence is highly associated with severe health conditions and disorders. Therefore, tracking activities of daily living can help promote quality of life. Wearable sensors in this regard can provide a reliable and economical means of tracking such activities, and such sensors are readily available in smartphones and watches. This study is the first of its kind to develop a wearable sensor-based physical activity classification system using a special class of supervised machine learning approaches called boosting algorithms. The study presents the performance analysis of several boosting algorithms (extreme gradient boosting-XGB, light gradient boosting machine-LGBM, gradient boosting-GB, cat boosting-CB and AdaBoost) in a fair and unbiased performance way using uniform dataset, feature set, feature selection method, performance metric and cross-validation techniques. The study utilizes the Smartphone-based dataset of thirty individuals. The results showed that the proposed method could accurately classify the activities of daily living with very high performance (above 90%). These findings suggest the strength of the proposed system in classifying activity of daily living using only the smartphone sensor's data and can assist in reducing the physical inactivity patterns to promote a healthier lifestyle and wellbeing.

Comparison of a Wearable Tracker with Actigraph for Classifying Physical Activity Intensity and Heart Rate in Children

Introduction: To examine the validity and reliability of the Fitbit Charge HR (FCH), wrist-worn ActiGraph (AG) accelerometers were used for assessing the classification of physical activity (PA) into intensity categories in children. Methods: Forty-three children (n = 43) participated in the study. Each participant completed 3 min bouts of 12 PAs ranging from sedentary to vigorous intensity while simultaneously wearing FCH and AG on both hands, a Polar HR monitor, and a portable indirect calorimeter. Total time spent in different PA intensity levels measured by FCH and AG were compared to the indirect calorimetry. Results: The highest classification accuracy values of sedentary behavior was 81.1% for FCH. The highest classification (72.4%) of light intensity PA was observed with Crouter’s algorithm from the non-dominant wrist. Crouter’s algorithm also show the highest classification (81.8%) for assessing moderate to vigorous intensity PA compared to FCH (70.8%). Across the devices, a high degree of reliability was found in step measurements, ranging from an intra-class correlation (ICC) = 0.92 to an ICC = 0.94. The reliability of the AG and the FCH showed high agreement for each variable. Conclusion: The FCH shows better validity for estimating sedentary behavior and similar validity for assessing moderate to vigorous PA compared to the research-grade monitor. Across the devices, the reliability showed the strongest association.

Identifying Free-Living Physical Activities Using Lab-Based Models with Wearable Accelerometers

The purpose of this study was to classify, and model various physical activities performed by a diverse group of participants in a supervised lab-based protocol and utilize the model to identify physical activity in a free-living setting. Wrist-worn accelerometer data were collected from (N=152) adult participants; age 18–64 years, and processed the data to identify and model unique physical activities performed by the participants in controlled settings. The Gaussian mixture model (GMM) and the hidden Markov model (HMM) algorithms were used to model the physical activities with time and frequency-based accelerometer features. An overall model accuracy of 92.7% and 94.7% were achieved to classify 24 physical activities using GMM and HMM, respectively. The most accurate model was then used to identify physical activities performed by 20 participants, each recorded for two free-living sessions of approximately six hours each. The free-living activity intensities were estimated with 80% accuracy and showed the dominance of stationary and light intensity activities in 36 out of 40 recorded sessions. This work proposes a novel activity recognition process to identify unsupervised free-living activities using lab-based classification models. In summary, this study contributes to the use of wearable sensors to identify physical activities and estimate energy expenditure in free-living settings.

Performance Evaluation of State of the Art Systems for Physical Activity Classification of Older Subjects Using Inertial Sensors in a Real Life Scenario: A Benchmark Study

The popularity of using wearable inertial sensors for physical activity classification has dramatically increased in the last decade due to their versatility, low form factor, and low power requirements. Consequently, various systems have been developed to automatically classify daily life activities. However, the scope and implementation of such systems is limited to laboratory-based investigations. Furthermore, these systems are not directly comparable, due to the large diversity in their design (e.g., number of sensors, placement of sensors, data collection environments, data processing techniques, features set, classifiers, cross-validation methods). Hence, the aim of this study is to propose a fair and unbiased benchmark for the field-based validation of three existing systems, highlighting the gap between laboratory and real-life conditions. For this purpose, three representative state-of-the-art systems are chosen and implemented to classify the physical activities of twenty older subjects (76.4 ± 5.6 years). The performance in classifying four basic activities of daily life (sitting, standing, walking, and lying) is analyzed in controlled and free living conditions. To observe the performance of laboratory-based systems in field-based conditions, we trained the activity classification systems using data recorded in a laboratory environment and tested them in real-life conditions in the field. The findings show that the performance of all systems trained with data in the laboratory setting highly deteriorates when tested in real-life conditions, thus highlighting the need to train and test the classification systems in the real-life setting. Moreover, we tested the sensitivity of chosen systems to window size (from 1 s to 10 s) suggesting that overall accuracy decreases with increasing window size. Finally, to evaluate the impact of the number of sensors on the performance, chosen systems are modified considering only the sensing unit worn at the lower back. The results, similarly to the multi-sensor setup, indicate substantial degradation of the performance when laboratory-trained systems are tested in the real-life setting. This degradation is higher than in the multi-sensor setup. Still, the performance provided by the single-sensor approach, when trained and tested with real data, can be acceptable (with an accuracy above 80%).