scispace - formally typeset
Proceedings ArticleDOI: 10.1109/INDICON45594.2018.8987114

Actiotracker: A Smart Pedometer For Monitoring And Analyzing Physical Activities of School Children

01 Dec 2018-
Abstract: With an alarming increase in obesity levels, even among children and adolescents, there is a need to take steps for increasing their motivation and overall physical activity levels. This paper proposes a way for concerned authorities in a school, to easily keep track of each student’s physical activity during school hours and give feedback accordingly. The system uses a portable pedometer that includes a MPU6050 sensor module that uses an accelerometer and gyroscope to collect movement data from each student and stores it, via Wi-Fi communication on to the Thingspeak server. The system implements a k-NN algorithm that classifies the data for each student into activities of sitting, walking, running and cycling. The results of the analysis and feedback for each student are accessible through a web portal, hosted locally on a server located in the school premises.

...read more

Topics: Pedometer (50%)
References
  More

Journal ArticleDOI: 10.1109/TITB.2005.856863
01 Jan 2006-
Abstract: Automatic classification of everyday activities can be used for promotion of health-enhancing physical activities and a healthier lifestyle. In this paper, methods used for classification of everyday activities like walking, running, and cycling are described. The aim of the study was to find out how to recognize activities, which sensors are useful and what kind of signal processing and classification is required. A large and realistic data library of sensor data was collected. Sixteen test persons took part in the data collection, resulting in approximately 31 h of annotated, 35-channel data recorded in an everyday environment. The test persons carried a set of wearable sensors while performing several activities during the 2-h measurement session. Classification results of three classifiers are shown: custom decision tree, automatically generated decision tree, and artificial neural network. The classification accuracies using leave-one-subject-out cross validation range from 58 to 97% for custom decision tree classifier, from 56 to 97% for automatically generated decision tree, and from 22 to 96% for artificial neural network. Total classification accuracy is 82% for custom decision tree classifier, 86% for automatically generated decision tree, and 82% for artificial neural network

...read more

Topics: Decision tree learning (61%), Decision tree (59%)

797 Citations


Journal ArticleDOI: 10.1109/TITB.2007.899496
01 Jan 2008-
Abstract: Physical activity has a positive impact on people's well-being, and it may also decrease the occurrence of chronic diseases. Activity recognition with wearable sensors can provide feedback to the user about his/her lifestyle regarding physical activity and sports, and thus, promote a more active lifestyle. So far, activity recognition has mostly been studied in supervised laboratory settings. The aim of this study was to examine how well the daily activities and sports performed by the subjects in unsupervised settings can be recognized compared to supervised settings. The activities were recognized by using a hybrid classifier combining a tree structure containing a priori knowledge and artificial neural networks, and also by using three reference classifiers. Activity data were collected for 68 h from 12 subjects, out of which the activity was supervised for 21 h and unsupervised for 47 h. Activities were recognized based on signal features from 3-D accelerometers on hip and wrist and GPS information. The activities included lying down, sitting and standing, walking, running, cycling with an exercise bike, rowing with a rowing machine, playing football, Nordic walking, and cycling with a regular bike. The total accuracy of the activity recognition using both supervised and unsupervised data was 89% that was only 1% unit lower than the accuracy of activity recognition using only supervised data. However, the accuracy decreased by 17% unit when only supervised data were used for training and only unsupervised data for validation, which emphasizes the need for out-of-laboratory data in the development of activity-recognition systems. The results support a vision of recognizing a wider spectrum, and more complex activities in real life settings.

...read more

Topics: Activity recognition (51%)

691 Citations


Open accessJournal ArticleDOI: 10.3390/S100201154
01 Feb 2010-Sensors
Abstract: The use of on-body wearable sensors is widespread in several academic and industrial domains. Of great interest are their applications in ambulatory monitoring and pervasive computing systems; here, some quantitative analysis of human motion and its automatic classification are the main computational tasks to be pursued. In this paper, we discuss how human physical activity can be classified using on-body accelerometers, with a major emphasis devoted to the computational algorithms employed for this purpose. In particular, we motivate our current interest for classifiers based on Hidden Markov Models (HMMs). An example is illustrated and discussed by analysing a dataset of accelerometer time series.

...read more

Topics: Wearable computer (51%)

666 Citations


Open accessJournal ArticleDOI: 10.1088/0967-3334/30/4/R01
Abstract: With the advent of miniaturized sensing technology, which can be body-worn, it is now possible to collect and store data on different aspects of human movement under the conditions of free living. This technology has the potential to be used in automated activity profiling systems which produce a continuous record of activity patterns over extended periods of time. Such activity profiling systems are dependent on classification algorithms which can effectively interpret body-worn sensor data and identify different activities. This article reviews the different techniques which have been used to classify normal activities and/or identify falls from body-worn sensor data. The review is structured according to the different analytical techniques and illustrates the variety of approaches which have previously been applied in this field. Although significant progress has been made in this important area, there is still significant scope for further work, particularly in the application of advanced classification techniques to problems involving many different activities.

...read more

  • Figure 3. An example of the accelerometer signal along with the approximation and detail coefficients at the first and second levels of decomposition. It can be seen that the high pass filtering associated with the detail coefficient results in the removal of the non-zero offset present in the original signal.
    Figure 3. An example of the accelerometer signal along with the approximation and detail coefficients at the first and second levels of decomposition. It can be seen that the high pass filtering associated with the detail coefficient results in the removal of the non-zero offset present in the original signal.
  • Figure 2. Wavelet decomposition tree. S refers to the original signal and cA1 and cD1 to the approximation and detail coefficients at the first level of decomposition. These two coefficients are obtained by low pass and high pass filtering of the original signal respectively. Subsequent levels of wavelet decomposition are obtained by filtering the approximation coefficient from the previous level.
    Figure 2. Wavelet decomposition tree. S refers to the original signal and cA1 and cD1 to the approximation and detail coefficients at the first level of decomposition. These two coefficients are obtained by low pass and high pass filtering of the original signal respectively. Subsequent levels of wavelet decomposition are obtained by filtering the approximation coefficient from the previous level.
  • Figure 4. An example hierarchical decision structure. Classification is based on simple threshold rules for each of the four input parameters. These are (1) waist HP mean, (2) wrist HP mean, (3) thigh HP mean AC and (4) thigh median frequency (HP refers to a high pass filtered signal).
    Figure 4. An example hierarchical decision structure. Classification is based on simple threshold rules for each of the four input parameters. These are (1) waist HP mean, (2) wrist HP mean, (3) thigh HP mean AC and (4) thigh median frequency (HP refers to a high pass filtered signal).
  • Figure 6. Three example membership functions used to specify the input to a fuzzy classification scheme. The vertical line represents a particular value of deceleration and corresponds to a separate fuzzy truth value for each of the three functions (0 for high impact, 0.2 for medium impact and 0.8 for low impact).
    Figure 6. Three example membership functions used to specify the input to a fuzzy classification scheme. The vertical line represents a particular value of deceleration and corresponds to a separate fuzzy truth value for each of the three functions (0 for high impact, 0.2 for medium impact and 0.8 for low impact).
  • Figure 1. Defining (a) sliding windows, (b) event-based windows and (c) activity-defined windows along a continuous body-worn sensor signal.
    Figure 1. Defining (a) sliding windows, (b) event-based windows and (c) activity-defined windows along a continuous body-worn sensor signal.
  • + 3

560 Citations


Open accessJournal ArticleDOI: 10.1109/TBME.2008.2006190
Abstract: Driven by the demands on healthcare resulting from the shift toward more sedentary lifestyles, considerable effort has been devoted to the monitoring and classification of human activity. In previous studies, various classification schemes and feature extraction methods have been used to identify different activities from a range of different datasets. In this paper, we present a comparison of 14 methods to extract classification features from accelerometer signals. These are based on the wavelet transform and other well-known time- and frequency-domain signal characteristics. To allow an objective comparison between the different features, we used two datasets of activities collected from 20 subjects. The first set comprised three commonly used activities, namely, level walking, stair ascent, and stair descent, and the second a total of eight activities. Furthermore, we compared the classification accuracy for each feature set across different combinations of three different accelerometer placements. The classification analysis has been performed with robust subject-based cross-validation methods using a nearest-neighbor classifier. The findings show that, although the wavelet transform approach can be used to characterize nonstationary signals, it does not perform as accurately as frequency-based features when classifying dynamic activities performed by healthy subjects. Overall, the best feature sets achieved over 95% intersubject classification accuracy.

...read more

  • Table III: Classification accuracies (%) obtained using leave-one-out cross validation for the three-activity classification problem (level walking, stair ascent and stair descent) with the wavelet features (table I). Accuracies have been reported for each of the different accelerometer combinations.
    Table III: Classification accuracies (%) obtained using leave-one-out cross validation for the three-activity classification problem (level walking, stair ascent and stair descent) with the wavelet features (table I). Accuracies have been reported for each of the different accelerometer combinations.
  • Table II: Summary of the time and frequency-domain features
    Table II: Summary of the time and frequency-domain features
  • Table VII: Sensitivity and specificity for each activity for the best performing time/frequency and wavelet feature sets.
    Table VII: Sensitivity and specificity for each activity for the best performing time/frequency and wavelet feature sets.
  • Table VI: Classification accuracies (%) obtained using leave-one-out cross validation for the eight-activity classification problem with the time and frequency features (table II). Accuracies have been reported for each of the different accelerometer combinations.
    Table VI: Classification accuracies (%) obtained using leave-one-out cross validation for the eight-activity classification problem with the time and frequency features (table II). Accuracies have been reported for each of the different accelerometer combinations.
  • Table VII: Sensitivity and specificity for each activity for the best performing time/frequency and wavelet feature sets.
    Table VII: Sensitivity and specificity for each activity for the best performing time/frequency and wavelet feature sets.
  • + 3

Topics: Feature extraction (55%), Wavelet transform (50%)

480 Citations


Network Information
Related Papers (5)
01 Jan 2012

Michal Tomlein, Pavol Bielik +4 more

View PDF
01 Nov 2018

Rami Yared, Michaeli Ekubay Negassi +1 more

01 Oct 2018

Abdul Kadar Muhammad Masum, Arnab Barua +4 more