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.

PURPOSE Large physical activity surveillance projects such as the UK Biobank and NHANES are using wrist-worn accelerometer-based activity monitors that collect raw data. The goal is to increase wear time by asking subjects to wear the monitors on the wrist instead of the hip, and then to use information in the raw signal to improve activity type and intensity estimation. The purpose of this work is obtaining an algorithm to process wrist and ankle raw data and classify behavior into four broad activity classes: ambulation, cycling, sedentary and other. METHODS Participants (N = 33) wearing accelerometers on the wrist and ankle performed 26 daily activities. The accelerometer data were collected, cleaned, and preprocessed to extract features that characterize 2 s, 4 s, and 12.8 s data windows. Feature vectors encoding information about frequency and intensity of motion extracted from analysis of the raw signal were used with a support vector machine classifier to identify a subject’s activity. Results were compared with categories classified by a human observer. Algorithms were validated using a leave-one-subject-out strategy. The computational complexity of each processing step was also evaluated. RESULTS With 12.8 s windows, the proposed strategy showed high classification accuracies for ankle data (95.0%) that decreased to 84.7% for wrist data. Shorter (4 s) windows only minimally decreased performances of the algorithm on the wrist to 84.2%. CONCLUSIONS A classification algorithm using 13 features shows good classification into the four classes given the complexity of the activities in the original dataset. The algorithm is computationally-efficient and could be implemented in real-time on mobile devices with only 4 s latency.

Machine learning methods have been widely used for gait assessment through the estimation of spatio-temporal parameters. As a further step, the objective of this work is to propose and validate a general probabilistic modeling approach for the classification of different pathological gaits. Specifically, the presented methodology was tested on gait data recorded on two pathological populations (Huntington’s disease and post-stroke subjects) and healthy elderly controls using data from inertial measurement units placed at shank and waist. By extracting features from group-specific Hidden Markov Models (HMMs) and signal information in time and frequency domain, a Support Vector Machines classifier (SVM) was designed and validated. The 90.5% of subjects was assigned to the right group after leave-one-subject–out cross validation and majority voting. The long-term goal we point to is the gait assessment in everyday life to early detect gait alterations.

No abstract

In this paper, we present an approach to the online implementation of a gait event detector based on machine learning algorithms. Gait events were detected using a uniaxial gyro that measured the foot instep angular velocity in the sagittal plane to feed a four-state left-right hidden Markov model (HMM). The short-time Viterbi algorithm was used to overcome the limitation of the standard Viterbi algorithm, which does not allow the online decoding of hidden state sequences. Supervised learning of the HMM structure and validation with the leave-one-subject-out validation method were performed using treadmill gait reference data from an optical motion capture system. The four gait events were foot strike, flat foot (FF), heel off (HO), and toe off. The accuracy ranged, on average, from 45 ms (early detection, FF) to 35 ms (late detection, HO); the latency of detection was less than 100 ms for all gait events but the HO, where the probability that it was greater than 100 ms was 25%. Overground walking tests of the HMM-based gait event detector were also successfully performed.

Study Objectives: To longitudinally examine sleep patterns, habits, and parent-reported sleep problems during the fi rst year of life. Methods: Seven hundred four parent/child pairs participated in a longitudinal cohort study. Structured interview recording general demographic data, feeding habits, intercurrent diseases, family history, sleep habits, and parental evaluation of the infant's sleep carried out at 1, 3, 6, 9, and 12 months Results: Nocturnal, daytime, and total sleep duration showed a high inter-individual variability in the fi rst year of life associated with changes in the fi rst 6 months and stability from 6 to 12 months. Bedtime was at around 22:00 and remained stable at 6, 9, and 12 months of age. Approximately 20% of the infants had more than 2 awakenings and slept more often in the parent bed. Nearly 10% of the infants were considered as having a problematic sleep by parents and this signifi cantly correlated with nocturnal awakenings and diffi culties falling asleep. Conclusions: Sleep patterns change during the fi rst year of life but most sleep variables (i.e., sleep latency and duration) show little variation from 6 to 12 months. Our data provide a context for clinicians to discuss sleep issues with parents and suggest that prevention efforts should focus to the fi rst 3-6 months, since sleep patterns show stability from that time point to 12 months. S C I E N T I F I C I N V E S T I G A T I O N SS leep patterns and sleep structure show signifi cant changes during the fi rst year of life; the circadian rhythm is not established in the fi rst months, and sleep is distributed throughout the day and night with a basic rest/activity cycle, similar to that of fetal life. At 1-2 weeks of age the fetal circadian rhythms starts to fade away and, at 1-2 months, the circadian activity rhythm develops with colic as the fi rst sign of circadian rhythmicity; at 3-4 months of age, infants are entrained to the 24-h cycle and melatonin production is stable. At 6-9 months, wakefulness increases, daytime naps are established, and fi nally, at 12 months 70% to 80% of infants sleep mostly at night. 2 demonstrated that daytime sleep is mostly determined by maturation (age), whereas nocturnal sleep is better predicted by ecological factors. More specifi cally, studies of infant sleep correlates showed that intense parental involvement and reduced self-soothing skills may interfere with nighttime sleep consolidation.2,3 Not only major developmental steps are determined by the interaction between maturational processes and ecological factors; sleep-wake patterns are also heavily infl uenced by biological and cultural factors, and therefore the concept of "normal sleep" varies according to cultural BRIEF SUMMARYCurrent Knowledge/Study Rationale: To our knowledge, most of the data on the sleep pattern development in the previous reports were derived from longitudinal studies designed to collect different information but not exclusively intended to assess sleep structure and ecology. Our study represents the fi r...

Purpose State-of-the-art methods for recognizing human activity using raw data from body worn accelerometers have primarily been validated with data collected from adults. This study applies a previously available method for activity classification using wrist or ankle accelerometer to work on datasets collected from both adults and youth. Methods An algorithm for detecting activity from wrist-worn accelerometers, originally developed using data from 33 adults, is tested on a dataset of 20 youth (age 13±1.3). The algorithm is also extended by adding new features required to improve performance on the youth dataset. Subsequent tests on both the adult and youth data were performed using crossed tests (training on one group and testing on the other) and leave-one-subject-out cross-validation. Results The new feature set improved overall recognition using wrist data by 2.3% for adults and 5.1% for youth. Leave-one-subject-out cross-validation accuracy performance was 87.0% (wrist) and 94.8% (ankle) for adults, and 91.0% (wrist) and 92.4% (ankle) for youth. Merging the two datasets, overall accuracy was 88.5% (wrist) and 91.6% (ankle). Conclusions Previously available methodological approaches for activity classification in adults can be extended to youth data. Including youth data in the training phase and using features designed to capture information on the peculiar activity fragmentation of young participants allows a better fit of the methodological framework to the characteristics of activity in youth, improving its overall performance. The proposed algorithm differentiates ambulation from sedentary activities that involve gesturing in wrist data, such as that being collected in large surveillance studies.

In this paper, we describe an application of hidden Markov models (HMMs) to the problem of time-locating specific events in normal gait movement patterns. The use of HMMs in this paper is mainly related to the opportunity they offer to segment gait data collected at different walking speeds and inclinations of the walking surface. A simple four-state left-right HMM is trained on a dataset of signals collected from a mono-axial gyro during treadmill walking trials performed at different speed and incline values. The gyro is mounted at the foot instep, with its sensitivity axis oriented in the medio-lateral direction. A rule based method applied to gyro signals is used for data annotation. Sensitivity and specificity of phase classification detection higher than 95% are obtained. The estimation accuracy of heel strike, flat foot, heel off and toe off events is about 35 ms on average.