Classification and characterization of postural transitions using instrumented shoes

A Hybrid Deep Residual Network for Efficient Transitional Activity Recognition Based on Wearable Sensors

Numerous learning-based techniques for effective human behavior identification have emerged in recent years. These techniques focus only on fundamental human activities, excluding transitional activities due to their infrequent occurrence and short period. Nevertheless, postural transitions play a critical role in implementing a system for recognizing human activity and cannot be ignored. This study aims to present a hybrid deep residual model for transitional activity recognition utilizing signal data from wearable sensors. The developed model enhances the ResNet model with hybrid Squeeze-and-Excitation (SE) residual blocks combining a Bidirectional Gated Recurrent Unit (BiGRU) to extract deep spatio-temporal features hierarchically, and to distinguish transitional activities efficiently. To evaluate recognition performance, the experiments are conducted on two public benchmark datasets (HAPT and MobiAct v2.0). The proposed hybrid approach achieved classification accuracies of 98.03% and 98.92% for the HAPT and MobiAct v2.0 datasets, respectively. Moreover, the outcomes show that the proposed method is superior to the state-of-the-art methods in terms of overall accuracy. To analyze the improvement, we have investigated the effects of combining SE modules and BiGRUs into the deep residual network. The findings indicates that the SE module is efficient in improving transitional activity recognition.

Assessment of Balance Instability by Wearable Sensor Systems During Postural Transitions

Several studies have demonstrated beneficial effects of real-time biofeedback for improving postural control. However, the application for daily activities, which also include postural transitions, is still limited. One crucial aspect is the time point of providing feedback, and thus its reliability. This might depend on the sensor system used, but also on how the threshold is defined. This study investigates which wearable sensor system and what kind of threshold is more reliable in a situation of a postural transition.To this end, we compared three sensor systems regarding their accuracy in timing in a stable and unstable postural transition in 16 healthy young adults: a multiple Inertial Measurement Unit system (IMU), a pressure Insoles System (IS), and a combination of both systems (COMB). Further, we contrasted two threshold parameters for each system: a Quiet Standing-based threshold (QSth) and a Limits of Stability-based threshold (LoSth).Two-way repeated measures ANOVAs and Wilcoxon tests (α = 0.05) indicated highest accuracy in the COMB LoSth, though with small differences to the IS LoSth. The LoSth showed more accurate timing than the QSth, especially in medio-lateral direction for IS and COMB.Consequently, for providing a reliable timing for a potential biofeedback applied by a wearable device in everyday life situations applications should focus on pressure insoles and a functional stability threshold, such as the LoS-based threshold.

Fall risk assessment in the wild: A critical examination of wearable sensor use in free-living conditions

BACKGROUND

Despite advances in laboratory-based supervised fall risk assessment methods (FRAs), falls still remain a major public health problem. This can be due to the alteration of behavior in laboratory due to the awareness of being observed (i.e., Hawthorne effect), the multifactorial complex etiology of falls, and our limited understanding of human behaviour in natural environments, or in the' wild'. To address these imitations, a growing body of literature has focused on free-living wearable-sensor-based FRAs. The objective of this narrative literature review is to discuss papers investigating natural data collected by wearable sensors for a duration of at least 24 h to identify fall-prone older adults.

METHODS

Databases (Scopus, PubMed and Google Scholar) were searched for studies based on a rigorous search strategy.

RESULTS

Twenty-four journal papers were selected, in which inertial sensors were the only wearable system employed for FRA in the wild. Gait was the most-investigated activity; but sitting, standing, lying, transitions and gait events, such as turns and missteps, were also explored. A multitude of free-living fall predictors (FLFPs), e.g., the quantity of daily steps, were extracted from activity bouts and events. FLFPs were further categorized into discrete domains (e.g., pace, complexity) defined by conceptual or data-driven models. Heterogeneity was found within the reviewed studies, which includes variance in: terminology (e.g., quantity vs macro), hyperparameters to define/estimate FLFPs, models and domains, and data processing approaches (e.g., the cut-off thresholds to define an ambulatory bout). These inconsistencies led to different results for similar FLFPs, limiting the ability to interpret and compare the evidence.

CONCLUSION

Free-living FRA is a promising avenue for fall prevention. Achieving a harmonized model is necessary to systematically address the inconsistencies in the field and identify FLFPs with the highest predictive values for falls to eventually address intervention programs and fall prevention.

Standard reference values of the upper body posture in healthy middle-aged female adults in Germany

In order to classify and analyze the parameters of upper body posture, a baseline in form of standard values is demanded. To this date, standard values have only been published for healthy young women. Data for female adults between 51 and 60 years are lacking. 101 symptom-free female volunteers aged 51–60 (55.16 ± 2.89) years. The mean height of the volunteers was 1.66 ± 0.62 m, with a mean body weight of 69.3 ± 11.88 kg and an average BMI of 25.02 ± 4.55 kg/m². By means of video raster stereography, a 3D-scan of the upper back surface was measured in a habitual standing position. The confidence interval, tolerance range and ICCs were calculated for all parameters. The habitual standing position is almost symmetrical in the frontal plane the most prominent deviation being a slightly more ventral position of the left shoulder blade in comparison to the right. The upper body (spine position) is inclined ventrally with a minor tilt to the left. In the sagittal plane, the kyphosis angle of the thoracic spine is greater than the lordosis angle of the lumbar spine. The pelvis is virtually evenly balanced with deviations from an ideal position falling under the measurement error margin of 1 mm/1°. There were also BMI influenced postural variations in the sagittal plane and shoulder distance. The ICCs are calculated from three repeated measurements and all parameters can be classified as "almost perfect". Deflections from an ideally symmetric spinal alignment in women aged 51–60 years are small-scaled, with a minimal frontal-left inclination and accentuated sigmoidal shape of the spine. Postural parameters presented in this survey allow for comparisons with other studies as well as the evaluation of clinical diagnostics and applications.

Leveraging Wearable Sensors for Human Daily Activity Recognition with Stacked Denoising Autoencoders

Activity recognition has received considerable attention in many research fields, such as industrial and healthcare fields. However, many researches about activity recognition have focused on static activities and dynamic activities in current literature, while, the transitional activities, such as stand-to-sit and sit-to-stand, are more difficult to recognize than both of them. Consider that it may be important in real applications. Thus, a novel framework is proposed in this paper to recognize static activities, dynamic activities, and transitional activities by utilizing stacked denoising autoencoders (SDAE), which is able to extract features automatically as a deep learning model rather than utilize manual features extracted by conventional machine learning methods. Moreover, the resampling technique (random oversampling) is used to improve problem of unbalanced samples due to relatively short duration characteristic of transitional activity. The experiment protocol is designed to collect twelve daily activities (three types) by using wearable sensors from 10 adults in smart lab of Ulster University, the experiment results show the significant performance on transitional activity recognition and achieve the overall accuracy of 94.88% on three types of activities. The results obtained by comparing with other methods and performances on other three public datasets verify the feasibility and priority of our framework. This paper also explores the effect of multiple sensors (accelerometer and gyroscope) to determine the optimal combination for activity recognition.

Postural transitions detection and characterization in healthy and patient populations using a single waist sensor

Background

Sit-to-stand and stand-to-sit transitions are frequent daily functional tasks indicative of muscle power and balance performance. Monitoring these postural transitions with inertial sensors provides an objective tool to assess mobility in both the laboratory and home environment. While the measurement depends on the sensor location, the clinical and everyday use requires high compliance and subject adherence. The objective of this study was to propose a sit-to-stand and stand-to-sit transition detection algorithm that works independently of the sensor location.

Methods

For a location-independent algorithm, the vertical acceleration of the lower back in the global frame was used to detect the postural transitions in daily activities. The detection performance of the algorithm was validated against video observations. To investigate the effect of the location on the kinematic parameters, these parameters were extracted during a five-time sit-to-stand test and were compared for different locations of the sensor on the trunk and lower back.

Results

The proposed detection method demonstrates high accuracy in different populations with a mean positive predictive value (and mean sensitivity) of 98% (95%) for healthy individuals and 89% (89%) for participants with diseases.

Conclusions

The sensor location around the waist did not affect the performance of the algorithm in detecting the sit-to-stand and stand-to-sit transitions. However, regarding the accuracy of the kinematic parameters, the sensors located on the sternum and L5 vertebrae demonstrated the highest reliability.

Lifting Activity Assessment Using Kinematic Features and Neural Networks

Work-related low-back disorders (WLBDs) can be caused by manual lifting tasks. Wearable devices used to monitor these tasks can be one possible way to assess the main risk factors for WLBDs. This study aims at analyzing the sensitivity of kinematic data to the risk level changes, and to define an instrument-based tool for risk classification by using kinematic data and artificial neural networks (ANNs). Twenty workers performed lifting tasks, designed by following the rules of the revised NIOSH lifting equation, with an increasing lifting index (LI). From the acquired kinematic data, we computed smoothness parameters together with kinetic, potential and mechanical energy. We used ANNs for mapping different set of features on LI levels to obtain an automatic risk estimation during these tasks. The results show that most of the calculated kinematic indexes are significantly affected by changes in LI and that all the lifting condition pairs can be correctly distinguished. Furthermore, using specific set of features, different topologies of ANNs can lead to a reliable classification of the biomechanical risk related to lifting tasks. In particular, the training sets and numbers of neurons in each hidden layer influence the ANNs performance, which is instead independent from the numbers of hidden layers. Reliable biomechanical risk estimation can be obtained by using training sets combining body and load kinematic features.

Long-term unsupervised mobility assessment in movement disorders

Mobile health technologies (wearable, portable, body-fixed sensors, or domestic-integrated devices) that quantify mobility in unsupervised, daily living environments are emerging as complementary clinical assessments. Data collected in these ecologically valid, patient-relevant settings can overcome limitations of conventional clinical assessments, as they capture fluctuating and rare events. These data could support clinical decision making and could also serve as outcomes in clinical trials. However, studies that directly compared assessments made in unsupervised and supervised (eg, in the laboratory or hospital) settings point to large disparities, even in the same parameters of mobility. These differences appear to be affected by psychological, physiological, cognitive, environmental, and technical factors, and by the types of mobilities and diagnoses assessed. To facilitate the successful adaptation of the unsupervised assessment of mobility into clinical practice and clinical trials, clinicians and researchers should consider these disparities and the multiple factors that contribute to them.

Wearable Monitoring Devices for Biomechanical Risk Assessment at Work: Current Status and Future Challenges-A Systematic Review

Background: In order to reduce the risk of work-related musculoskeletal disorders (WMSDs) several methods have been developed, accepted by the international literature and used in the workplace. The purpose of this systematic review was to describe recent implementations of wearable sensors for quantitative instrumental-based biomechanical risk assessments in prevention of WMSDs. Methods: Articles written until 7 May 2018 were selected from PubMed, Scopus, Google Scholar and Web of Science using specific keywords. Results: Instrumental approaches based on inertial measurement units and sEMG sensors have been used for direct evaluations to classify lifting tasks into low and high risk categories. Wearable sensors have also been used for direct instrumental evaluations in handling of low loads at high frequency activities by using the local myoelectric manifestation of muscle fatigue estimation. In the field of the rating of standard methods, on-body wireless sensors network-based approaches for real-time ergonomic assessment in industrial manufacturing have been proposed. Conclusions: Few studies foresee the use of wearable technologies for biomechanical risk assessment although the requirement to obtain increasingly quantitative evaluations, the recent miniaturization process and the need to follow a constantly evolving manual handling scenario is prompting their use.