Cross-Domain Classification of Physical Activity Intensity: An EDA-Based Approach Validated by Wrist-Measured Acceleration and Physiological Data

Performing regular physical activity positively affects individuals’ quality of life in both the short- and long-term and also contributes to the prevention of chronic diseases. However, exerted effort is subjectively perceived from different individuals. Therefore, this work explores an out-of-laboratory approach using a wrist-worn device to classify the perceived intensity of physical effort based on quantitative measured data. First, the exerted intensity is classified by two machine learning algorithms, namely the Support Vector Machine and the Bagged Tree, fed with features computed on heart-related parameters, skin temperature, and wrist acceleration. Then, the outcomes of the classification are exploited to validate the use of the Electrodermal Activity signal alone to rate the perceived effort. The results show that the Support Vector Machine algorithm applied on physiological and acceleration data effectively predicted the relative physical activity intensities, while the Bagged Tree performed best when the Electrodermal Activity data were the only data used.

Download Full-text

Understanding Youths’ Ability to Interpret 3D-Printed Physical Activity Data and Identify Associated Intensity Levels: Mixed-Methods Study (Preprint)

10.2196/preprints.11253 ◽

2018 ◽

Author(s):

Sam Graeme Morgan Crossley ◽

Melitta Anne McNarry ◽

Michael Rosenberg ◽

Zoe R Knowles ◽

Parisa Eslambolchilar ◽

...

Keyword(s):

Physical Activity ◽

Children And Adolescents ◽

Vigorous Physical Activity ◽

Significant Proportion ◽

3D Models ◽

Primary School Children ◽

Moderate Intensity ◽

Physical Activity Intensity ◽

Activity Data ◽

Activity Intensity

BACKGROUND A significant proportion of youth in the United Kingdom fail to meet the recommended 60 minutes of moderate-to-vigorous physical activity every day. One of the major barriers encountered in achieving these physical activity recommendations is the perceived difficulty for youths to interpret physical activity intensity levels and apply them to everyday activities. Personalized physical activity feedback is an important method to educate youths about behaviors and associated outcomes. Recent advances in 3D printing have enabled novel ways of representing physical activity levels through personalized tangible feedback to enhance youths’ understanding of concepts and make data more available in the everyday physical environment rather than on screen. OBJECTIVE The purpose of this research was to elicit youths’ (children and adolescents) interpretations of two age-specific 3D models displaying physical activity and to assess their ability to appropriately align activities to the respective intensity. METHODS Twelve primary school children (9 boys; mean age 7.8 years; SD 0.4 years) and 12 secondary school adolescents (6 boys; mean age 14.1 years; SD 0.3 years) participated in individual semistructured interviews. Interview questions, in combination with two interactive tasks, focused on youths’ ability to correctly identify physical activity intensities and interpret an age-specific 3D model. Interviews were transcribed verbatim, content was analyzed, and outcomes were represented via tables and diagrammatic pen profiles. RESULTS Youths, irrespective of age, demonstrated a poor ability to define moderate-intensity activities. Moreover, children and adolescents demonstrated difficulty in correctly identifying light- and vigorous-intensity activities, respectively. Although youths were able to correctly interpret different components of the age-specific 3D models, children struggled to differentiate physical activity intensities represented in the models. CONCLUSIONS These findings support the potential use of age-specific 3D models of physical activity to enhance youths’ understanding of the recommended guidelines and associated intensities.

Download Full-text

Machine Learning Methods for Fear Classification Based on Physiological Features

Sensors ◽

10.3390/s21134519 ◽

2021 ◽

Vol 21 (13) ◽

pp. 4519

Author(s):

Livia Petrescu ◽

Cătălin Petrescu ◽

Ana Oprea ◽

Oana Mitruț ◽

Gabriela Moise ◽

...

Keyword(s):

Machine Learning ◽

Support Vector Machine ◽

Dimensionality Reduction ◽

Data Augmentation ◽

Binary Classification ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Physiological Data ◽

Gradient Boosting ◽

Support Vector

This paper focuses on the binary classification of the emotion of fear, based on the physiological data and subjective responses stored in the DEAP dataset. We performed a mapping between the discrete and dimensional emotional information considering the participants’ ratings and extracted a substantial set of 40 types of features from the physiological data, which represented the input to various machine learning algorithms—Decision Trees, k-Nearest Neighbors, Support Vector Machine and artificial networks—accompanied by dimensionality reduction, feature selection and the tuning of the most relevant hyperparameters, boosting classification accuracy. The methodology we approached included tackling different situations, such as resolving the problem of having an imbalanced dataset through data augmentation, reducing overfitting, computing various metrics in order to obtain the most reliable classification scores and applying the Local Interpretable Model-Agnostic Explanations method for interpretation and for explaining predictions in a human-understandable manner. The results show that fear can be predicted very well (accuracies ranging from 91.7% using Gradient Boosting Trees to 93.5% using dimensionality reduction and Support Vector Machine) by extracting the most relevant features from the physiological data and by searching for the best parameters which maximize the machine learning algorithms’ classification scores.

Download Full-text

Analysis of Fluctuation Patterns in Emotional States Using Electrodermal Activity Signals and Improved Symbolic Aggregate Approximation

Fluctuation and Noise Letters ◽

10.1142/s0219477522500134 ◽

2021 ◽

Author(s):

Yedukondala Rao Veeranki ◽

Nagarajan Ganapathy ◽

Ramakrishnan Swaminathan

Keyword(s):

Support Vector Machine ◽

Electrodermal Activity ◽

Maximum Amplitude ◽

Machine Learning Algorithms ◽

Support Vector ◽

Clinical Settings ◽

Emotional States ◽

Rotation Forest ◽

Symbolic Aggregate Approximation ◽

Symbolic Sequences

Analysis of fluctuations in electrodermal activity (EDA) signals is widely preferred for emotion recognition. In this work, an attempt has been made to determine the patterns of fluctuations in EDA signals for various emotional states using improved symbolic aggregate approximation. For this, the EDA is obtained from a publicly available online database. The EDA is decomposed into phasic components and divided into equal segments. Each segment is transformed into a piecewise aggregate approximation (PAA). These approximations are discretized using 11 time-domain features to obtain symbolic sequences. Shannon entropy is extracted from each PAA-based symbolic sequence using varied symbol size [Formula: see text] and window length [Formula: see text]. Three machine-learning algorithms, namely Naive Bayes, support vector machine and rotation forest, are used for the classification. The results show that the proposed approach is able to determine the patterns of fluctuations for various emotional states in EDA signals. PAA features, namely maximum amplitude and chaos, significantly identify the subtle fluctuations in EDA and transforms them in symbolic sequences. The optimal values of [Formula: see text] and [Formula: see text] yield the highest performance. The rotation forest is accurate (F-[Formula: see text] and 60.02% for arousal and valence dimensions) in classifying various emotional states. The proposed approach can capture the patterns of fluctuations for varied-length signals. Particularly, the support vector machine yields the highest performance for a lower length of signals. Thus, it appears that the proposed method might be utilized to analyze various emotional states in both normal and clinical settings.

Download Full-text

Prediction of Relative Physical Activity Intensity Using Multimodal Sensing of Physiological Data

Sensors ◽

10.3390/s19204509 ◽

2019 ◽

Vol 19 (20) ◽

pp. 4509 ◽

Cited By ~ 2

Author(s):

Alok Kumar Chowdhury ◽

Dian Tjondronegoro ◽

Vinod Chandran ◽

Jinglan Zhang ◽

Stewart G. Trost

Keyword(s):

Physical Activity ◽

Machine Learning ◽

Perceived Exertion ◽

Feature Fusion ◽

Electrodermal Activity ◽

Decision Fusion ◽

Sensor Data ◽

Physiological Data ◽

Support Vector ◽

Improve Performance

This study examined the feasibility of a non-laboratory approach that uses machine learning on multimodal sensor data to predict relative physical activity (PA) intensity. A total of 22 participants completed up to 7 PA sessions, where each session comprised 5 trials (sitting and standing, comfortable walk, brisk walk, jogging, running). Participants wore a wrist-strapped sensor that recorded heart-rate (HR), electrodermal activity (Eda) and skin temperature (Temp). After each trial, participants provided ratings of perceived exertion (RPE). Three classifiers, including random forest (RF), neural network (NN) and support vector machine (SVM), were applied independently on each feature set to predict relative PA intensity as low (RPE ≤ 11), moderate (RPE 12–14), or high (RPE ≥ 15). Then, both feature fusion and decision fusion of all combinations of sensor modalities were carried out to investigate the best combination. Among the single modality feature sets, HR provided the best performance. The combination of modalities using feature fusion provided a small improvement in performance. Decision fusion did not improve performance over HR features alone. A machine learning approach using features from HR provided acceptable predictions of relative PA intensity. Adding features from other sensing modalities did not significantly improve performance.

Download Full-text

Estimation of physical activity using accelerometry in adult populations: Using the Sensewear Armband and the ACT24 as comparison tools for the estimation of energy expenditure and physical activity intensity by the Sojourn method

10.31274/etd-180810-6101 ◽

2018 ◽

Author(s):

Matthew Stewart

Keyword(s):

Physical Activity ◽

Energy Expenditure ◽

Physical Activity Intensity ◽

Sensewear Armband ◽

Activity Intensity

Download Full-text

Predicting Future Occurrence of Acute Hypotensive Episodes Using Noninvasive and Invasive Features

Military Medicine ◽

10.1093/milmed/usaa418 ◽

2021 ◽

Vol 186 (Supplement_1) ◽

pp. 445-451

Author(s):

Yifei Sun ◽

Navid Rashedi ◽

Vikrant Vaze ◽

Parikshit Shah ◽

Ryan Halter ◽

...

Keyword(s):

Machine Learning ◽

Support Vector Machine ◽

Real World ◽

Short Term Memory ◽

Model Performance ◽

Learning Technologies ◽

Machine Learning Algorithms ◽

Support Vector ◽

K Nearest Neighbor ◽

Continuous Map

ABSTRACT Introduction Early prediction of the acute hypotensive episode (AHE) in critically ill patients has the potential to improve outcomes. In this study, we apply different machine learning algorithms to the MIMIC III Physionet dataset, containing more than 60,000 real-world intensive care unit records, to test commonly used machine learning technologies and compare their performances. Materials and Methods Five classification methods including K-nearest neighbor, logistic regression, support vector machine, random forest, and a deep learning method called long short-term memory are applied to predict an AHE 30 minutes in advance. An analysis comparing model performance when including versus excluding invasive features was conducted. To further study the pattern of the underlying mean arterial pressure (MAP), we apply a regression method to predict the continuous MAP values using linear regression over the next 60 minutes. Results Support vector machine yields the best performance in terms of recall (84%). Including the invasive features in the classification improves the performance significantly with both recall and precision increasing by more than 20 percentage points. We were able to predict the MAP with a root mean square error (a frequently used measure of the differences between the predicted values and the observed values) of 10 mmHg 60 minutes in the future. After converting continuous MAP predictions into AHE binary predictions, we achieve a 91% recall and 68% precision. In addition to predicting AHE, the MAP predictions provide clinically useful information regarding the timing and severity of the AHE occurrence. Conclusion We were able to predict AHE with precision and recall above 80% 30 minutes in advance with the large real-world dataset. The prediction of regression model can provide a more fine-grained, interpretable signal to practitioners. Model performance is improved by the inclusion of invasive features in predicting AHE, when compared to predicting the AHE based on only the available, restricted set of noninvasive technologies. This demonstrates the importance of exploring more noninvasive technologies for AHE prediction.

Download Full-text