Physical Activity Monitoring System Research Articles

S08-2 Reproducibility and validity of four physical activity questionnaires in 18 European union member states: the European Union Physical Activity and Sport Monitoring System (EUPASMOS) project

BackgroundThe successful promotion of health-enhancing physical activity (HEPA) requires reliable and valid prevalence data of physical activity (PA) to enable the design, implementation and evaluation of effective and cost-effective policies. As part of the development of a new integrated monitoring framework in Europe, the reliability and validity of the Eurobarometer, European Health Interview Survey (EHIS), International Physical Activity Questionnaire (IPAQ) and Global Physical Activity Questionnaire (GPAQ) were studied in the ongoing European Union Physical Activity and Sport Monitoring System project (EUPASMOS) among 18 European Union member states.MethodsPhysical activity (PA) and sedentary behavior (SB) were assessed among 80-100 adults per member state using the four questionnaires and the UKK RM42 accelerometer. Participants completed the questionnaires in random order and wore the accelerometer seven consecutive days on their right hip (during the day) and on their non-dominant wrist (overnight). Time spent in moderate-to-vigorous intensity physical activity (MVPA), sedentary behavior and adherence to the WHO PA guidelines were calculated based on the 5 methods. The reproducibility and validity of the four questionnaires were tested by using the Spearman's correlation coefficient (ρ) or Cohen's kappa coefficient (κ), dependent of the outcome measure.ResultsPreliminary results from the Netherlands (N = 91) showed that the correlations for reproducibility of all four questionnaires varied between 0.51 and 0.63 for MVPA, between 0.30 and 0.60 for the WHO PA guidelines and between 0.65 and 0.82 for SB. All correlations were statically significant (p > 0.05). Significant correlations for validity of the questionnaires were found for MVPA (ρ = 0.22-0.43) and the WHO PA guidelines (ρ = 0.19-0.25). The only exception was the association between the EHIS questionnaire and the WHO PA guidelines. For SB, only GPAQ and the EHIS questionnaire showed significant associations (ρ = 0.31-0.32).ConclusionsFirst analyses of the Dutch data within the EUPASMOS project showed that the four commonly used questionnaires in Europe are fairly to strongly reliable methods depending on the outcome measure. The four questionnaires are fairly valid methods, except the Eurobarometer and IPAQ when examining SB. It is of interest to examine the quality of these questionnaires in all 18 member states for national and European policy makers.

S08-1 Comparing physical activity measurement instruments across member states by means of a conversion factor: European Union Physical Activity and Sport Monitoring System (EUPASMOS) project

BackgroundThe successful promotion of health-enhancing physical activity (HEPA) requires authoritative information to enable the design, implementation and evaluation of effective and cost-effective policies. This includes reliable and valid prevalence data of physical activity (PA) that can be compared across European Union Member States populations regardless of the type of measurement instrument used. In order to enable comparison of PA prevalence data between different measurement instruments, an attempt was made to develop a conversion factor between commonly used questionnaires in Europe and accelerometry in the ongoing European Union Physical Activity and Sport Monitoring System project (EUPASMOS) among 18 member states.MethodsData of physical activity (PA) and sedentary behavior (SB) were collected in 18 member states using four questionnaires (Eurobarometer, European Health Interview Survey, International Physical Activity Questionnaire and Global Physical Activity Questionnaire) and the UKK RM42 accelerometer. The number of measured participants varied between 100 and 1000 among the 18 member states. Participants completed the questionnaires in random order and wore the accelerometer seven consecutive days on their right hip (during the day) and on their non-dominant wrist (overnight). Time spent in moderate-to-vigorous intensity physical activity and sedentary behavior were calculated based on these 5 measurement instruments. The comparison between methods will be examined by using sophisticated regression analyses.ResultsThe EUPASMOS project is in progress and the final data is collected in the last two member states. In the meantime, a model is being developed to examine whether a conversion factor can be calculated to compare prevalence data based on questionnaires and accelerometry. By developing a conversion factor, prevalence data can be compared between member states although the measurement instruments used differ between member states. In June 2020 the results from these analyses are expected.ConclusionsThese results will provide insight into the possibility to compare prevalence data of physical activity among member states, when using different measurement instruments within their monitoring systems.

S08 Do results from physical activity questionnaires (IPAQ, GPAQ, EHIS and Eurobarometer) and accelerometer tell same story - results from 18 countries in the EUPASMOS project

Physical activity (PA) is associated with reduced risk of many noncommunicable diseases while a high volume of sedentary behavior (SB) is also considered to increase the risk of these diseases. Accurate measurement of both PA and SB is crucial for estimating these risk factors, and accelerometers together with standardized questionnaires are suggested a feasible way to measure these behaviors. However, collecting raw acceleration data of PA, SB and sleep in a standardized and similar way on a large scale has not been done before. In the European Union Physical Activity and Sport Monitoring System project (EUPASMOS), this has been done for the first time in 18 EU Member States.

S08-3 Physical activity, sedentary behavior and sleep-time of Eupasmos-project participants in 16 European countries: European Union Physical Activity and Sport Monitoring System (EUPASMOS) project

Abstract Background Increasing number of studies use device-based measurements to report levels of physical activity (PA) and sedentary behavior (SB) of populations. The studies have used different devices, device placements and analysis methods, and thus the comparison of the results between studies and populations is very challenging. The purpose of the present study was to present preliminary results of PA, SB and sleep-time measured with a similar method among adults of 16 European countries. Methods The study is based on the Eupasmos-project where PA, SB and sleep-time of the participants (n = 6674) were measured by a tri-axial accelerometer 24/7 (UKK RM42, UKK Terveyspalvelut Oy, Tampere, Finland). Accelerometer was worn on an elastic hip-band during waking-hours and on a wrist-band attached to a non-dominant wrist during bed-time (sleeping). PA-parameters were based on mean amplitude deviation (MAD) of acceleration analyzed in 1min exponential moving average (epoch length 6s). Assessment of SB (e.g. sitting and laying down) and standing were based on the angle for posture estimation (APE). Sleep measurement was based on the movement of a non-dominant wrist during bed-time. Parameters analyzed were total daily times and different bout lengths of SB, standing, light PA, moderate-to-vigorous PA, sleep and mean number of daily steps. Results The preliminary analysis included 47-1952 participants/country. In all countries participants spent most of their waking-hours sedentary. On weekdays the country-mean of SB varied from 8h18min to 10h7min. Participants took on average 6907-9716 steps/day. Light PA varied from 3h46min to 5h10min and moderate-to-vigorous PA from 45 to 78min. Participants wore the device on their wrist (sleeping-time) 6h42min-8h37min on weekdays. Although the total times of these behaviors were quite similar between the countries, the variation increased when different bout lengths were analyzed: the longer the bout length, the larger the variation. The hour-by-hour pattern of these behaviors varied a lot between the countries as well. Conclusions General pattern of SB, PA and sleep-time was quite similar in all countries, but the deeper analysis revealed clear differences. To be able to compare levels and patterns of these behaviors it is essential to use the exactly same method in all participating countries.

Transfer Learning Improves Accelerometer-Based Child Activity Recognition via Subject-Independent Adult-Domain Adaption.

Wearable activity recognition can collate the type, intensity, and duration of each child's physical activity profile, which is important for exploring underlying adolescent health mechanisms. Traditional machine-learning-based approaches require large labeled data sets; however, child activity data sets are typically small and insufficient. Thus, we proposed a transfer learning approach that adapts adult-domain data to train a high-fidelity, subject-independent model for child activity recognition. Twenty children and twenty adults wore an accelerometer wristband while performing walking, running, sitting, and rope skipping activities. Activity classification accuracy was determined via the traditional machine learning approach without transfer learning and with the proposed subject-independent transfer learning approach. Results showed that transfer learning increased classification accuracy to 91.4% as compared to 80.6% without transfer learning. These results suggest that subject-independent transfer learning can improve accuracy and potentially reduce the size of the required child data sets to enable physical activity monitoring systems to be adopted more widely, quickly, and economically for children and provide deeper insights into injury prevention and health promotion strategies.

Physical Exercise Monitoring System Based on Computer Somatosensory Technology

Aiming at the problems of poor convergence, slow acceleration, and low throughput in traditional physical exercise monitoring systems, a physical exercise monitoring system based on computer somatosensory technology is proposed and designed. The whole structure of the physical activity monitoring system was created from the hardware and software, according to the research. Human body posture monitoring sensor module, communication connection module, power supply module, main control unit module, sensor module, and other pieces make up the hardware section. To improve detection performance, computer somatosensory technology is used in the software design to gather physical activity posture data. Also, for experimental comparison and verification, we employ system convergence, acceleration, and throughput as indicators. Experimental results show that the improved method can effectively improve system convergence, increase system acceleration, and increase system throughput, which has certain advantages in use.

IoT-Based Unobtrusive Physical Activity Monitoring System for Predicting Dementia

Mental health-related disorders are common in elderly populations. Among the various mental health disorders, one most significant threat is dementia, and prediction of dementia has become an important issue related to well-being in old age, because the disease progression of dementia can be slowed by early diagnosis and disease control. In this paper, we propose an unobtrusive dementia-prediction system for monitoring physical activities of elderly persons either living alone or as a couple in different house structures, achieved through passive infrared (PIR) motion sensors combined with data processing. The proposed feature extraction algorithm extracts feature values related to physical activities from simple passive infrared sensors located in each room space. We then apply a variety of common popular classification models, including Deep Neural Networks (DNNs), to predict the risk of dementia in a sensor-enabled home. We implemented and validated algorithms on data collected for over a month from 18 participants who were engaged with a variety of living conditions. The proposed system was effective in predicting dementia risk, with up to an 0.99 area under the curve (AUC) using DNN with principal component analysis (PCA) and a quantile transformer scaler. In terms of the result based on leave-one-subject-out (LOSO) analysis, an accuracy of 63.38% was achieved using DNN with PCA and a standard scaler. The proposed methodology is non-invasive and cost-effective, and can be used for a variety of long-term monitoring and early symptom detection systems, helping caregivers provide optimal interventions to elderly individuals at risk for dementia.

An inventory of national surveillance systems assessing physical activity, sedentary behaviour and sport participation of adults in the European Union

BackgroundPhysical inactivity has been recognised as a global public health problem that requires concerted action. This calls for systematic physical activity (PA) surveillance as a mechanism for assessing the problem and evaluating the effectiveness of related policies. Because countries tend to design their policy measures based on national surveillance data, here we present an inventory of existing national surveillance systems on PA, sedentary behaviour (SB) and sport participation (SP) among adult population in all European Union (EU) Member States.MethodsAs a part of the European Physical Activity and Sports Monitoring System (EUPASMOS) project, a questionnaire was constructed in the form of an on-line survey to collect detailed information on existing national surveillance systems on either PA, SB, or SP. National HEPA focal points from all 27 EU Member States were invited to answer the on-line questionnaire and data collection took part in the period May 2018–September 2019.ResultsNational monitoring of PA or SB or SP for adults has been established in 16/27 EU Member States, that host 33 different PA/SB/SP monitoring systems. Apart from 3 countries that are using accelerometers (Finland, Ireland and Portugal), surveillance is typically based on questionnaires. In most Member States these questionnaires have not been validated in the particular language and cultural setting. Next, specific domains and dimensions of PA, SB and SP assessed vary a lot across countries. Only 3 countries (the Netherlands, Portugal and Slovenia) are monitoring all three behaviours while covering most of the domains and dimensions of PA/SB/SP. Lastly, as half of the existing surveillance systems set an upper age limit, in 9/16 countries that are monitoring PA/SB/SP, no data for people older than 80 years are available.ConclusionsSystematic surveillance of PA is lacking among 11/27 EU countries, with even few monitoring SB and SP. Besides, existing surveillance systems typically fail to assess all dimensions and domains of PA/SB/SP with only three countries maintaining monitoring systems that encompass all three behaviours while covering most of the domains and dimensions of PA/SB/SP. Hence, additional efforts in advocacy of systematic PA surveillance in the EU are called for.

Communication Network for Sports Activity Monitoring Systems

In this paper, through research and analysis of the communication network of the physical activity monitoring system, we combine wearable technology and identification technology and design a physical health monitoring bracelet that integrates multifaceted physical data collection and effective identity matching function. We match the identity through the chip and collect the physical fitness data generated in the process of exercise and centralized test by the sensor in real-time. Finally, the data transmission is realized through the WIFI communication function to achieve the purpose of monitoring physical exercise and improving physical quality. To ensure the continuity and stability of information transmission, the joint transmission method of direct transmission and indirect transmission is essential. Besides, considering the energy causality limitation of sensor nodes and relay nodes, a collaborative transmission model of wireless body area network based on wireless cognitive network is constructed. And, a power allocation algorithm based on maximum ratio merging and wireless cognitive network is proposed, which puts forward a new idea for the future research of wireless body area network resource allocation.

Criterion validity and reliability of the International Physical Activity Questionnaire \u2013 Hungarian short form against the RM42 accelerometer

BackgroundPhysical inactivity is a global phenomenon in European welfare countries. Proper monitoring is essential to measure the physical activity level of the population.MethodsIn the Hungarian cohort of the European Physical Activity and Sport Monitoring System (EUPASMOS) project, our participants (N = 598) completed sociodemographic questions and the International Physical Activity Questionnaire – short form (IPAQ-SF) survey. The validity and reliability of the subjective measurement tool were examined, IPAQ-SF outcomes were contrasted against triaxial RM42 accelerometer wore for 7 consecutive days.ResultsThe IPAQ-SF showed moderate internal consistency (Cronbach Alpha = 0.647). The concurrent validity of the IPAQ-SF to triaxial accelerometer indicated a significant weak-to-moderate correlation (R = 0.111–0.338, p = 0.042; p < 0.001). The test-retest reliability showed a significant correlation between two measurements (R = 0.788–0.981, p < 0.001).ConclusionThe Hungarian version of the IPAQ-SF had excellent test-retest reliability, but low-to-fair concurrent validity for moderate and vigorous physical activity, walking and sitting time, as compared to the objective criterion measure among Hungarian adults.

PMS76 Correlation between Accelerometer and Ipaq-SF-Derived Sedentary Time in Hungarian Adults, Preliminary Study of the Eupasmos Project

The reliable examination of the health enhancing physical activity is one of the main goal of the European Physical Activity and Sport Monitoring System (EUPASMOS) project. The self-report measured physical activity (PA), especially IPAQ-SF are popular but the reliability is not examined among Hungarian adults population. Furthermore several studies proved that sedentary behaviour negatively impacts health status. Our study aim was to compare an important score, the sedentary time measured by accelerometer and IPAQ-SF. The study comprised 593 participating adults (248 males and 345 females, age: 44.41±18.64). The data was collected during February-May 2019 in Budapest and Pécs and their agglomeration, using quota sampling by age and gender representing the Hungarian adult (18+) population. The self-reported physical activity by IPAQ-SF was compared to RM 42 hip-worn triaxial accelerometer for 7 consecutive days. Data were presented as median and interquartile range (IQR), Spearman’s rank correlation was used to compare the objective and subjective PA measurement tools using SPSS 24. program, where level of significance was set at p<0.05. The IPAQ-SF sedentary time (ST) per day (min/day) for the full sample was 360.00 (240.00-480.00) and the median accelerometer-derived ST was 505.00 (434.50-578.50) min/day. The self-reported and accelerometer-based data were significantly correlated (R=0.236, p<0.001). However the questionnaire results were overestimated the accelerometer-based result. The median difference between the two measurement was 150.00 min/day (-29.00-293.50) Notable result was that the ST was significantly negatively correlated with age (Accelerometer: R=-0.114, p=0.007; IPAQ-SF: R=-0.145; p=0.001). Overall, we conclude that the IPAQ-SF was not showed strong reliability in ST examination. The questionnaire was weakly correlated with accelerometer data but further analysis needed to test the validity and reliability of the questionnaire compare to the accelerometer and other measurement tools to suggest the best self-reported questionnaire to measure PA level of the population.

Estrous detection with an activity and rumination monitoring system in an organic grazing and a low-input conventional dairy herd

The objective of this study was to evaluate estrous detection using a physical activity and rumination monitoring system in a seasonal calving organic grazing (GRAZ) and a low-input conventional (ZEROGRAZ) dairy herd. The study was conducted from June 2014 to August 2017. During each breeding season, physical activity and rumination were monitored electronically using an activity and rumination monitoring system (HR-LD tags; SCR Engineers Ltd., Netanya, Israel). Signals resulting from the activity and rumination monitoring system for individual cows were used to determine consistency of the values using this system with the breeding date of cows. Breeding dates were determined using EstrotectTM patches. The study included 1,463 breeding dates from 531 cows. Within the GRAZ herd, during the summer breeding season the monitoring system was less sensitive for estrous detection (33.8 %) than during the winter breeding season (79.8 %).The activity and rumination monitoring system had a sensitivity of 56.7 %, specificity of 99.3 % and positive predictive value of 59.8 % for the GRAZ herd, and sensitivity of 70.1 %, specificity of 99.2 % and positive predictive value of 66.3 % for the ZEROGRAZ herd. For cows that were determined to be pregnant and subsequently calved as a result of the mating, the sensitivity for estrous detection was slightly greater for the GRAZ (60.7 %) and ZEROGRAZ (72.5 %) herds. The activity and rumination monitoring system evaluated in this study has potential for estrous detection in grazing herds during the winter breeding season and in small-input dairy herds during both, winter and summer breeding seasons.

A monitoring system to provide feedback on student physical activity during physical education lessons.

School-based physical education (PE) provides opportunities to accumulate moderate-to-vigorous physical activity (MVPA), but many students are insufficiently active during PE lessons. Providing teachers with feedback regarding their students' physical activity may increase the effectiveness of PE for achieving MVPA goals, but existing physical activity monitoring technologies have limitations in class environments. Therefore, the purpose of this study was to develop and validate a system capable of providing feedback on PE lesson MVPA. Equations for translating step counts to %MVPA were derived from measures in 492 students who concurrently wore an ActiGraph GT3X+ (ActiGraph) and Yamax pedometer (Yamax) during a PE lesson. To enhance feedback availability during PE lessons, we then developed a bespoke monitoring system using wireless tri-axial pedometers (HMM) and a smart device app. After developing and testing the monitoring system, we assessed its validity and reliability in 100 students during a PE lesson. There was a strong correlation of 0.896 between step counts and accelerometer-determined %MVPA and quantile regression equations showed good validity for translating step counts to %MVPA with a mean absolute difference of 5.3 (95% CI, 4.4-6.2). The physical activity monitoring system was effective at providing %MVPA during PE lessons with a mean difference of 1.6±7.1 compared with accelerometer-determined %MVPA (7% difference between the two measurement methods). Teachers and students can use a smart device app and wireless pedometers to conveniently obtain feedback during PE lessons. Future studies should determine whether such technologies help teachers to increase physical activity during PE lessons.

ANALYSIS OF THE SELF-REPORTED PHYSICAL ACTIVITY QUESTIONNAIRES INDICATORS

“Global action plan on physical activity 2018–2030” emphasizes the need for weekly moderate physical activity for ensuring human health. Physical activity can be measured by a variety of objective and subjective methods, but one of the prerequisites for understanding the connection between active lifestyle and health certainty that the measuring instrument measures the feature for which it has been created and that it can be used in many countries. The goal of the research is to determine the correlations between measurement properties of fitness club clients’ self-reported physical activity indicators in the Global Physical Activity Questionnaire (GPAQ), International Physical Activity Questionnaire (IPAQ), European Health Interview Survey-Physical Activity Questionnaire (EHIS-PAQ), and to evaluate their concurrent validity. Methods: participants (volunteers) were 70 fitness club visitors (age 18-79). This research is preparative part for the further research of the project “European Physical Activity and Sports Monitoring System (EUPASMOS)”. The type, involvement and amount of physical activity was determined by the GPAQ, IPAQ and EHIS-PAQ adapted into Latvian. The research results showed that questionnaires allowed to determine the respondents’ physical activity indicators in and out of fitness club activities. Statistically significant correlations were determined between indicators obtained in all physical activity questionnaires applied in the research (p&lt;0.05). This confirms that all three physical activity determination questionnaires can be used for physical activity research in Latvian environment.

Predicting Outcomes from Engagement With Specific Components of an Internet-Based Physical Activity Intervention With Financial Incentives: Process Analysis of a Cluster Randomized Controlled Trial.

BackgroundInvestigating participant engagement and nonusage attrition can help identify the likely active ingredients of electronic health interventions. Research on engagement can identify which intervention components predict health outcomes. Research on nonusage attrition is important to make recommendations for retaining participants in future studies.ObjectiveThis study aimed to investigate engagement and nonusage attrition in the Physical Activity Loyalty (PAL) scheme, a 6-month complex physical activity intervention in workplaces in Northern Ireland. The intervention included financial incentives with reward redemption and self-regulation techniques. Specific objectives were (1) to determine whether engagement in specific intervention components predicted physical activity at 6 months, (2) to determine whether engagement in specific intervention components predicted targeted mediators at 6 months, and (3) to investigate predictors of nonusage attrition for participants recording daily activity via the PAL scheme physical activity monitoring system and logging onto the website.MethodsPhysical activity was assessed at baseline and 6 months using pedometers (Yamax Digiwalker CW-701, Japan). Markers of engagement and website use, monitoring system use, and reward redemption were collected throughout the scheme. Random-effects generalized least-squares regressions determined whether engagement with specific intervention components predicted 6-month physical activity and mediators. Cox proportional hazards regressions were used to investigate predictors of nonusage attrition (days until first 2-week lapse).ResultsA multivariable generalized least-squares regression model (n=230) showed that the frequency of hits on the website’s monitoring and feedback component (regression coefficient [b]=50.2; SE=24.5; P=.04) and the percentage of earned points redeemed for financial incentives (b=9.1; SE=3.3; P=.005) were positively related to 6-month pedometer steps per day. The frequency of hits on the discussion forum (b=−69.3; SE=26.6; P=.009) was negatively related to 6-month pedometer steps per day. Reward redemption was not related to levels of more internal forms of motivation. Multivariable Cox proportional hazards regression models identified several baseline predictors associated with nonusage attrition. These included identified regulation (hazard ratio [HR] 0.88, 95% CI 0.81-0.97), recovery self-efficacy (HR 0.88, 95% CI 0.80-0.98), and perceived workplace environment safety (HR 1.07, 95% CI 1.02-1.11) for using the physical activity monitoring system. The EuroQoL health index (HR 0.33, 95% CI 0.12-0.91), financial motivation (HR 0.93, 95% CI 0.87-0.99), and perceived availability of physical activity opportunities in the workplace environment (HR 0.96, 95% CI 0.93-0.99) were associated with website nonusage attrition.ConclusionsOur results provide evidence opposing one of the main hypotheses of self-determination theory by showing that financial rewards are not necessarily associated with decreases in more internal forms of motivation when offered as part of a complex multicomponent intervention. Identifying baseline predictors of nonusage attrition can help researchers to develop strategies to ensure maximum intervention adherence.Trial RegistrationISRCTN Registry ISRCTN17975376; http://www.isrctn.com/ISRCTN17975376 (Archived by WebCite at http://www.webcitation.org/76VGZsZug)

Feasibility and Effectiveness of a Wearable Technology-Based Physical Activity Intervention in Preschoolers: A Pilot Study

The purpose of this pilot study was to evaluate the feasibility and the effectiveness of an intervention that employed a technology-based physical activity (PA) monitoring system and teacher-regulated strategies to promote PA in preschoolers. A total of 93 preschoolers (53% girls, 4.7 years) from 5 child care centers were recruited for a one-week intervention and randomly assigned into control (2 centers, n = 45) or intervention (3 centers, n = 48) group. Key intervention components included: (1) wearable device-based, real-time monitoring of children’s PA by classroom teachers and (2) teacher-regulated strategies for providing more opportunities for PA. Sedentary behavior (SED) and PA were measured using accelerometers. Overall, children in the intervention group showed significantly lower level of SED (31.6 vs. 33.6 min/h) and higher level of total PA (28.4 vs. 26.4 min/h) than children in the control group, after adjusting for age, sex, race, parent education level, parent perception of their child’s PA, BMI, and childcare centers. Teachers in the intervention group reported that the intervention was highly feasible to be implemented in their current classroom settings. In conclusion, we observed high acceptability and initial effectiveness of the current intervention. Subsequent research at larger-scale is warranted to fully evaluate the effectiveness of the intervention strategies tested in this study.

Two-stage feature selection using ranking self-adaptive differential evolution algorithm for recognition of acceleration activity

Widespread research on activity recognition is becoming an imperative topic for improving the quality of human health. The fast development of sensing technology has become a fundamental platform for researchers to implement a system that could fulfill human needs. Due to privacy interests and low cost, wearable sensing technology is used in numerous physical activity monitoring and recognition systems. While these systems have proved to be successful, it is crucial to pay attention to the less relevant features to be classified. In such circumstances, it might happen that some features are less meaningful for describing the activity. Less complex and easy to understand, feature ranking is gaining a lot of attention in most feature dimension problems such as in bioinformatics and hyperspectral images. However, the improvement of ranking features in activity recognition has not yet been achieved. On the other hand, an evolutionary algorithm has proven its effectiveness in searching the best feature subsets. An exhaustive searching process of finding an optimal parameter value is another challenge. Consequently, this paper proposes a ranking self-adaptive differential evolution (rsaDE) feature selection algorithm. The proposed algorithm is capable of selecting the optimal feature subsets while improving the recognition of acceleration activity using a minimum number of features. The experiments employed real-world physical acceleration data sets: WISDM and PAMAP2. As a result, rsaDE performed better than the current methods in terms of model performance and its efficiency in the context of random forest ensemble classifiers.

Exploratory study of a virtual community for physical activity

Physical inactivity is increasingly becoming part of today’s lifestyle, leading to a rapid increase in the incidence of diseases including cardiovascular disease, diabetes, and obesity. These chronic diseases are, for the most part, preventable by adopting a healthy lifestyle including regular physical activity. To help people maintain appropriate physical activity levels, researchers are developing interventions based on concepts from social science and ICT solutions. In this line, we investigate virtual communities (or social networks) as a candidate solution to support people in achieving their daily physical activity goals. This study observes and explores the differences between using the virtual community and a physical activity monitoring system on the physical activity level. We designed an exploratory study with a duration of 9 weeks in which an intervention group used a virtual community with a physical activity monitoring system and a control group used only a physical activity monitoring system. The results of this exploratory study demonstrate that using virtual communities may motivate and support people in their daily physical activity; in particular, we observed a decrease in the use of the system later than was observed in previous studies. Future investigations are needed to confirm the effect of the virtual community on physical activity.

Anomaly event detection for sit-to-stand transition recognition to improve mariner physical activity classification during a sea voyage

During a sea voyage, seafarers live on an unstable surface that demands unusual physical activity patterns. Previous studies recognized physical inactivity patterns in their special living environment. This study aims to develop a new sit-to-stand transition detection method based on physical activity classification models using wearable sensors to objectively assess the unstable physical activity patterns of seafarers. The sit-to-stand event detection was selected to improve the classification accuracy of the static activities including sitting and standing during the physical inactivity patterns. Anomaly detection was applied to handle imbalanced training data of sit-to-stand events. A single wearable sensor was attached in a chest pocket of the uniform to extract the upper trunk motion features such as body angle and dynamics. Two classification models with and without sit-to-stand event detection were developed and compared with each other to evaluate the efficacy of the sit-to-stand event detection in classifying the mariners’ physical activity. Our experimental results showed that the sit-to-stand event detectionbased model significantly improved the classification accuracy of static activities. We expect that the proposed model can be integrated into a continuous physical activity monitoring system for the objective assessment of mariner’s physical health in an unstable living environment.

Development of Wearable Physical Activity Monitoring System

Development of Wearable Physical Activity Monitoring System