scholarly journals Pruning Growing Self-Organizing Map Network for Human Physical Activity Identification

2022 ◽  
Vol 2022 ◽  
pp. 1-15
Author(s):  
Lingfei Mo ◽  
Hongjie Yu ◽  
Wenqi Hua
Keyword(s):  
Physical Activity ◽  
Wearable Sensors ◽  
Data Distribution ◽  
Identification Accuracy ◽  
Small Scale ◽  
Self Organizing Map ◽  
Training Stage ◽  
Unbalanced Dataset ◽  
Speed Up ◽  
Som Model

Human physical activity identification based on wearable sensors is of great significance to human health analysis. A large number of machine learning models have been applied to human physical activity identification and achieved remarkable results. However, most human physical activity identification models can only be trained based on labeled data, and it is difficult to obtain enough labeled data, which leads to weak generalization ability of the model. A Pruning Growing SOM model is proposed in this paper to address the limitations of small-scale labeled dataset, which is unsupervised in the training stage, and then only a small amount of labeled data is used for labeling neurons to reduce dependency on labeled data. In training stage, the inactive neurons in network can be deleted by pruning mechanism, which makes the model more consistent with the data distribution and improves the identification accuracy even on unbalanced dataset, especially for the action categories with poor identification effect. In addition, the pruning mechanism can also speed up the inference of the model by controlling its scale.

scholarly journals An empirical example of analysis using a two-stage modeling approach: within-subject association of outdoor context and physical activity predicts future daily physical activity levels

2020 ◽  
Author(s):  
Chih-Hsiang Yang ◽  
Jaclyn P Maher ◽  
Aditya Ponnada ◽  
Eldin Dzubur ◽  
Rachel Nordgren ◽  
...  
Keyword(s):  
Physical Activity ◽  
Vigorous Physical Activity ◽  
Wearable Sensors ◽  
Activity Levels ◽  
Two Stage ◽  
Modeling Approach ◽  
Source Program ◽  
Modeling Strategy ◽  
Stage Modeling

Abstract People differ from each other to the extent to which momentary factors, such as context, mood, and cognitions, influence momentary health behaviors. However, statistical models to date are limited in their ability to test whether the association between two momentary variables (i.e., subject-level slopes) predicts a subject-level outcome. This study demonstrates a novel two-stage statistical modeling strategy that is capable of testing whether subject-level slopes between two momentary variables predict subject-level outcomes. An empirical case study application is presented to examine whether there are differences in momentary moderate-to-vigorous physical activity (MVPA) levels between the outdoor and indoor context in adults and whether these momentary differences predict mean daily MVPA levels 6 months later. One hundred and eight adults from a multiwave longitudinal study provided 4 days of ecological momentary assessment (during baseline) and accelerometry data (both at baseline and 6 month follow-up). Multilevel data were analyzed using an open-source program (MixWILD) to test whether momentary strength between outdoor context and MVPA during baseline was associated with average daily MVPA levels measured 6 months later. During baseline, momentary MVPA levels were higher in outdoor contexts as compared to indoor contexts (b = 0.07, p < .001). Participants who had more momentary MVPA when outdoors (vs. indoors) during baseline (i.e., a greater subject-level slope) had higher daily MVPA at the 6 month follow-up (b = 0.09, p < .05). This empirical example shows that the subject-level momentary association between specific context (i.e., outdoors) and health behavior (i.e., physical activity) may contribute to overall engagement in that behavior in the future. The demonstrated two-stage modeling approach has extensive applications in behavioral medicine to analyze intensive longitudinal data collected from wearable sensors and mobile devices.

scholarly journals Reliability of activity monitors for physical activity assessment in patients with musculoskeletal disorders: A systematic review

2021 ◽  
pp. 1-9
Author(s):  
Francesco Negrini ◽  
Alessandro de Sire ◽  
Stefano Giuseppe Lazzarini ◽  
Federico Pennestrì ◽  
Salvatore Sorce ◽  
...  
Keyword(s):  
Physical Activity ◽  
Systematic Review ◽  
Musculoskeletal Disorders ◽  
Wearable Sensors ◽  
Activity Monitors ◽  
Activity Assessment ◽  
Measurement Tools ◽  
Different Types ◽  
Measurement Units ◽  
Full Text Screening

BACKGROUND: Activity monitors have been introduced in the last years to objectively measure physical activity to help physicians in the management of musculoskeletal patients. OBJECTIVE: This systematic review aimed at describing the assessment of physical activity by commercially available portable activity monitors in patients with musculoskeletal disorders. METHODS: PubMed, Embase, PEDro, Web of Science, Scopus and CENTRAL databases were systematically searched from inception to June 11th, 2020. We considered as eligible observational studies with: musculoskeletal patients; physical activity measured by wearable sensors based on inertial measurement units; comparisons performed with other tools; outcomes consisting of number of steps/day, activity/inactivity time, or activity counts/day. RESULTS: Out of 595 records, after removing duplicates, title/abstract and full text screening, 10 articles were included. We noticed a wide heterogeneity in the wearable devices, that resulted to be 10 different types. Patients included suffered from rheumatoid arthritis, osteoarthritis, juvenile idiopathic arthritis, polymyalgia rheumatica, and fibromyalgia. Only 3 studies compared portable activity trackers with objective measurement tools. CONCLUSIONS: Taken together, this systematic review showed that activity monitors might be considered as useful to assess physical activity in patients with musculoskeletal disorders, albeit, to date, the high device heterogeneity and the different algorithms still prevent their standardization.

Strategies to enhance compliance to physical activity for patients with insulin resistance

2007 ◽  
Vol 32 (3) ◽  
pp. 549-556 ◽  
Author(s):  
Alison Kirk ◽  
Pierpaolo De Feo
Keyword(s):  
Physical Activity ◽  
Insulin Resistance ◽  
Type 2 Diabetes ◽  
Wearable Sensors ◽  
Physical Activity Promotion ◽  
Physical Activity Behaviour ◽  
Future Research ◽  
Evidence Based ◽  
Activity Promotion

The evidence that physical activity is an effective therapeutic tool in the management of insulin resistance and type 2 diabetes is well documented. Limited research has addressed how best to promote and maintain physical activity in these individuals. This paper explores strategies to enhance compliance to physical activity for patients with insulin resistance. Several evidence-based guidelines and reviews recommend that physical activity interventions are based on a valid theoretical framework. However, there is no evidence-based consensus on the best theory or the combination of theories to use. Motivational tools such as pedometers, wearable sensors measuring energy expenditure, and point of choice prompts appear to be effective at stimulating short-term substantial increases in physical activity, but further strategies to maintain physical activity behaviour change are required. Physical activity consultation has demonstrated effective physical activity promotion over periods of up to 2 years in people with type 2 diabetes. Future research should identify the longer term effects of this intervention and the effectiveness of different methods of delivery. Overall, there needs to be a lot more focus on this area of research. Without this, the abundance of research investigating the effects of physical activity on people with insulin resistance and type 2 diabetes is essentially redundant.

GaitSense: Towards Ubiquitous Gait-Based Human Identification with Wi-Fi

2022 ◽  
Vol 18 (1) ◽  
pp. 1-24
Author(s):  
Yi Zhang ◽  
Yue Zheng ◽  
Guidong Zhang ◽  
Kun Qian ◽  
Chen Qian ◽  
...  
Keyword(s):  
Data Augmentation ◽  
Gait Recognition ◽  
Wearable Sensors ◽  
Human Identification ◽  
Training Data ◽  
Identification Accuracy ◽  
Identification System ◽  
Gait Patterns ◽  
Training Samples ◽  
Augmentation Techniques

Gait, the walking manner of a person, has been perceived as a physical and behavioral trait for human identification. Compared with cameras and wearable sensors, Wi-Fi-based gait recognition is more attractive because Wi-Fi infrastructure is almost available everywhere and is able to sense passively without the requirement of on-body devices. However, existing Wi-Fi sensing approaches impose strong assumptions of fixed user walking trajectories, sufficient training data, and identification of already known users. In this article, we present GaitSense , a Wi-Fi-based human identification system, to overcome the above unrealistic assumptions. To deal with various walking trajectories and speeds, GaitSense first extracts target specific features that best characterize gait patterns and applies novel normalization algorithms to eliminate gait irrelevant perturbation in signals. On this basis, GaitSense reduces the training efforts in new deployment scenarios by transfer learning and data augmentation techniques. GaitSense also enables a distinct feature of illegal user identification by anomaly detection, making the system readily available for real-world deployment. Our implementation and evaluation with commodity Wi-Fi devices demonstrate a consistent identification accuracy across various deployment scenarios with little training samples, pushing the limit of gait recognition with Wi-Fi signals.

scholarly journals Active Play in After-school Programmes: development of an intervention and description of a matched-pair cluster-randomised trial assessing physical activity play in after-school programmes

BMJ Open ◽  
2017 ◽  
Vol 7 (8) ◽  
pp. e016585 ◽  
Author(s):  
Kirsti Riiser ◽  
Sølvi Helseth ◽  
Hanna Ellingsen ◽  
Bjørg Fallang ◽  
Knut Løndal
Keyword(s):  
Physical Activity ◽  
First Graders ◽  
Randomised Trial ◽  
Matched Pair ◽  
After School ◽  
Cluster Randomised Trial ◽  
Small Scale ◽  
Control Group ◽  
Active Play ◽  
Cluster Randomised

IntroductionInterventions delivered in after-school programmes (ASPs) have the potential to become a means of ensuring adequate physical activity among schoolchildren. This requires a motivational climate, allowing for self-determined play. If trained, ASP staff may represent a valuable resource for supporting such play. Increasing knowledge and supportive skills among ASP staff may also potentially increase their motivation for work. The purpose of this article is to describe the development of the ‘Active Play in ASP’ intervention, which aims to promote physical activity among first graders attending ASP, and to present a protocol for a matched-pair cluster-randomised trial to evaluate the intervention.Methods and analysisInformed by experiences from practice, evidence-based knowledge and theory, the intervention was developed in a stepwise process including focus group meetings and a small-scale pilot test. The intervention contains a course programme for ASP staff to increase their skills in how to support physical activity through play. In a cluster randomised controlled trial, the ASPs will be matched and randomly allocated to receive the 7-month intervention or to a control group. Outcomes will be assessed at baseline, after 7 and 19 months. First graders attending the ASPs included are eligible. The primary outcome will be accelerometer-determined minutes in moderate to vigorous physical activity in the ASP. The study uses a mixed methods approach including observations and interviews to provide rich descriptions of the concept of children's physical activity in ASP. Moreover, the trial will assess whether the ASP staff benefits from participation in the intervention in terms of increased work motivation. Lastly, process evaluations of programme fidelity, satisfaction and suggestions on improvement will be performed.Ethics and disseminationThe study is approved by the Data Protection Official for Research (reference no 46008). Results will be presented in conferences and peer-reviewed journals.Trial registration numberClinical Trials (NCT02954614), pre-results.

scholarly journals Stochastic Recognition of Physical Activity and Healthcare Using Tri-Axial Inertial Wearable Sensors

2020 ◽  
Vol 10 (20) ◽  
pp. 7122
Author(s):  
Ahmad Jalal ◽  
Mouazma Batool ◽  
Kibum Kim
Keyword(s):  
Physical Activity ◽  
Human Health ◽  
Activity Recognition ◽  
Human Activity ◽  
Health Monitoring ◽  
Wearable Sensors ◽  
Gaussian Mixture ◽  
Sensor Data ◽  
Tree Classifier ◽  
Combined Features

The classification of human activity is becoming one of the most important areas of human health monitoring and physical fitness. With the use of physical activity recognition applications, people suffering from various diseases can be efficiently monitored and medical treatment can be administered in a timely fashion. These applications could improve remote services for health care monitoring and delivery. However, the fixed health monitoring devices provided in hospitals limits the subjects’ movement. In particular, our work reports on wearable sensors that provide remote monitoring that periodically checks human health through different postures and activities to give people timely and effective treatment. In this paper, we propose a novel human activity recognition (HAR) system with multiple combined features to monitor human physical movements from continuous sequences via tri-axial inertial sensors. The proposed HAR system filters 1D signals using a notch filter that examines the lower/upper cutoff frequencies to calculate the optimal wearable sensor data. Then, it calculates multiple combined features, i.e., statistical features, Mel Frequency Cepstral Coefficients, and Gaussian Mixture Model features. For the classification and recognition engine, a Decision Tree classifier optimized by the Binary Grey Wolf Optimization algorithm is proposed. The proposed system is applied and tested on three challenging benchmark datasets to assess the feasibility of the model. The experimental results show that our proposed system attained an exceptional level of performance compared to conventional solutions. We achieved accuracy rates of 88.25%, 93.95%, and 96.83% over MOTIONSENSE, MHEALTH, and the proposed self-annotated IM-AccGyro human-machine dataset, respectively.

scholarly journals Changes in Objectively Measured Lifestyle Factors During the COVID-19 Pandemic in Community-Dwelling Older Adults

2021 ◽  
Author(s):  
Takuya Ataka ◽  
Noriyuki Kimura ◽  
Atsuko Eguchi ◽  
Etsuro Matsubara
Keyword(s):  
Physical Activity ◽  
Older Adults ◽  
Sedentary Time ◽  
Vigorous Physical Activity ◽  
Wearable Sensors ◽  
Lifestyle Factors ◽  
Community Dwelling ◽  
Activity Level ◽  
Objectively Measured ◽  
Community Dwelling Older Adults

Abstract Background: In this manuscript, we aimed at investigating whether objectively measured lifestyle factors, including walking steps, sedentary time, amount of unforced physical activity, level of slight and energetic physical activity, conversation time, and sleep parameters altered before and during the COVID-19 pandemic among community-dwelling older adults.Methods: Data were obtained from a prospective cohort study conducted from 2015 to 2019 and a subsequent dementia prevention study undertaken in September 2020. Community-dwelling adults aged ≥65 years wore wearable sensors before and during the pandemic.Results: A total of 56 adults were enrolled in this study. The mean age was 74.2±3.9 years, and 58.9% (n=33) of the participants were female. The moderate and vigorous physical activity time significantly decreased and sedentary time significantly increased during the pandemic. Conclusions: This is the first study to demonstrate differences in objectively assessed lifestyle factors before and during the COVID-19 pandemic among community-dwelling older adults. The findings show that the pandemic has adversely affected physical activity among older adults living on their own in Japan.

Sign in / Sign up

Export Citation Format

Share Document