scholarly journals Sensor Type, Axis, and Position-Based Fusion and Feature Selection for Multimodal Human Daily Activity Recognition in Wearable Body Sensor Networks

2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Abeer A. Badawi ◽  
Ahmad Al-Kabbany ◽  
Heba A. Shaban
Keyword(s):  
Feature Selection ◽  
Inertial Sensors ◽  
Inertial Sensor ◽  
Real Life ◽  
Human Gait ◽  
Body Sensor Networks ◽  
Sequential Feature Selection ◽  
Wearable Inertial Sensors ◽  
Robust Systems ◽  
Remote Health

This research addresses the challenge of recognizing human daily activities using surface electromyography (sEMG) and wearable inertial sensors. Effective and efficient recognition in this context has emerged as a cornerstone in robust remote health monitoring systems, among other applications. We propose a novel pipeline that can attain state-of-the-art recognition accuracies on a recent-and-standard dataset—the Human Gait Database (HuGaDB). Using wearable gyroscopes, accelerometers, and electromyography sensors placed on the thigh, shin, and foot, we developed an approach that jointly performs sensor fusion and feature selection. Being done jointly, the proposed pipeline empowers the learned model to benefit from the interaction of features that might have been dropped otherwise. Using statistical and time-based features from heterogeneous signals of the aforementioned sensor types, our approach attains a mean accuracy of 99.8%, which is the highest accuracy on HuGaDB in the literature. This research underlines the potential of incorporating EMG signals especially when fusion and selection are done simultaneously. Meanwhile, it is valid even with simple off-the-shelf feature selection methods such the Sequential Feature Selection family of algorithms. Moreover, through extensive simulations, we show that the left thigh is a key placement for attaining high accuracies. With one inertial sensor on that single placement alone, we were able to achieve a mean accuracy of 98.4%. The presented in-depth comparative analysis shows the influence that every sensor type, position, and placement can have on the attained recognition accuracies—a tool that can facilitate the development of robust systems, customized to specific scenarios and real-life applications.

scholarly journals An Evaluation of Wearable Inertial Sensor Configuration and Supervised Machine Learning Models for Automatic Punch Classification in Boxing

IoT ◽  
2020 ◽  
Vol 1 (2) ◽  
pp. 360-381
Author(s):  
Matthew T. O. Worsey ◽  
Hugo G. Espinosa ◽  
Jonathan B. Shepherd ◽  
David V. Thiel
Keyword(s):  
Machine Learning ◽  
Prediction Accuracy ◽  
Inertial Sensors ◽  
Inertial Sensor ◽  
Supervised Machine Learning ◽  
Learning Models ◽  
Significant Statistical Difference ◽  
Sensor Configuration ◽  
Wearable Inertial Sensors ◽  
Machine Learning Models

Machine learning is a powerful tool for data classification and has been used to classify movement data recorded by wearable inertial sensors in general living and sports. Inertial sensors can provide valuable biofeedback in combat sports such as boxing; however, the use of such technology has not had a global uptake. If simple inertial sensor configurations can be used to automatically classify strike type, then cumbersome tasks such as video labelling can be bypassed and the foundation for automated workload monitoring of combat sport athletes is set. This investigation evaluates the classification performance of six different supervised machine learning models (tuned and untuned) when using two simple inertial sensor configurations (configuration 1—inertial sensor worn on both wrists; configuration 2—inertial sensor worn on both wrists and third thoracic vertebrae [T3]). When trained on one athlete, strike prediction accuracy was good using both configurations (sensor configuration 1 mean overall accuracy: 0.90 ± 0.12; sensor configuration 2 mean overall accuracy: 0.87 ± 0.09). There was no significant statistical difference in prediction accuracy between both configurations and tuned and untuned models (p > 0.05). Moreover, there was no significant statistical difference in computational training time for tuned and untuned models (p > 0.05). For sensor configuration 1, a support vector machine (SVM) model with a Gaussian rbf kernel performed the best (accuracy = 0.96), for sensor configuration 2, a multi-layered perceptron neural network (MLP-NN) model performed the best (accuracy = 0.98). Wearable inertial sensors can be used to accurately classify strike-type in boxing pad work, this means that cumbersome tasks such as video and notational analysis can be bypassed. Additionally, automated workload and performance monitoring of athletes throughout training camp is possible. Future investigations will evaluate the performance of this algorithm on a greater sample size and test the influence of impact window-size on prediction accuracy. Additionally, supervised machine learning models should be trained on data collected during sparring to see if high accuracy holds in a competition setting. This can help move closer towards automatic scoring in boxing.

scholarly journals Wearable Inertial Sensors to Assess Gait during the 6-Minute Walk Test: A Systematic Review

Sensors ◽  
2020 ◽  
Vol 20 (9) ◽  
pp. 2660 ◽  
Author(s):  
Fabio Alexander Storm ◽  
Ambra Cesareo ◽  
Gianluigi Reni ◽  
Emilia Biffi
Keyword(s):  
Inertial Sensors ◽  
Inertial Sensor ◽  
Pathological Condition ◽  
Low Cost ◽  
Walk Test ◽  
Female Ratio ◽  
Number Of Patients ◽  
Wearable Inertial Sensors ◽  
6 Minute Walk Test ◽  
Minute Walk

Wearable sensors are becoming increasingly popular for complementing classical clinical assessments of gait deficits. The aim of this review is to examine the existing knowledge by systematically reviewing a large number of papers focusing on the use of wearable inertial sensors for the assessment of gait during the 6-minute walk test (6MWT), a widely recognized, simple, non-invasive, low-cost and reproducible exercise test. After a systematic search on PubMed and Scopus databases, two raters evaluated the quality of 28 full-text articles. Then, the available knowledge was summarized regarding study design, subjects enrolled (number of patients and pathological condition, if any, age, male/female ratio), sensor characteristics (type, number, sampling frequency, range) and body placement, 6MWT protocol and extracted parameters. Results were critically discussed to suggest future directions for the use of inertial sensor devices in the clinics.

scholarly journals Feature Selection for Work Recognition and Working Motion Measurement

2018 ◽  
Vol 30 (5) ◽  
pp. 706-716 ◽  
Author(s):  
Saori Miyajima ◽  
Takayuki Tanaka ◽  
Natsuki Miyata ◽  
Mitsunori Tada ◽  
Masaaki Mochimaru ◽  
...  
Keyword(s):  
Feature Selection ◽  
Inertial Sensors ◽  
Inertial Sensor ◽  
Feature Selection Method ◽  
The Body ◽  
Support Vector ◽  
Body Parts ◽  
Care Services ◽  
Physical Burden ◽  
New Feature

As the demand for nursing care services is growing, the physical burden involved in caregiving has drawn widespread attention. To mitigate the physical burden in caregiving, we have to recognize what kind of work and problems are involved in each caregiving task. To identify the problems involved in caregiving, we need to recognize the work and analyze its workload. Aiming to reduce the burden on the waist during caregiving tasks, we are developing inertial sensor suits for measuring the working motions. With the developed method, the burden on the waist is estimated from the waist posture. Considering its use in practical caregiving sites, the number of inertial sensors should be the minimum necessary, which depends on the number of body parts where to measure the posture. In this study, we select the body parts to achieve the two above-mentioned goals: to recognize the work involved in caregiving and capture the waist posture. A support vector machine (SVM) is used to recognize the work. Its conventional method of selecting the features on which to recognize the work only considers the recognition accuracy and does not sufficiently meet the needs for measuring the postures. Therefore, we propose a new feature-selection method, which can evaluate the waist-posture measuring accuracy and can make forward feature selections in the same manner as the conventional wrapper method. We have verified the effectiveness of the proposed method by measuring simple simulated work motions.

Using Inertial Sensor System to Measure the Workspace of the Surgeon's Upper Limbs during Operations

2015 ◽  
Vol 772 ◽  
pp. 329-333
Author(s):  
Ali Soroush ◽  
Farzam Farahmand
Keyword(s):  
Upper Limb ◽  
Inertial Sensors ◽  
Inertial Sensor ◽  
Kinematic Model ◽  
Experimental Results ◽  
Upper Body ◽  
Upper Limbs ◽  
Surgical Robots ◽  
Raw Data ◽  
Wearable Inertial Sensors

The aim of this study was to determine the workspace of surgeon's body for designing more efficient surgical robots in the operation rooms. Five wearable inertial sensors were placed near the wrist and elbow joints and also on the thorax of surgeons to track the orientation of upper limb. Assuming that the lengths of five segments of an upper limb were known, measurements of the inertial sensors were used to determine the position of the wrist and elbow joints via an established kinematic model. subsequently, to assess the workspace of surgeon upper body, raw data were collected in the arthroscopy and laparoscopy operations. Experimental results demonstrated that the workspaces of surgeon's joints are limited and predefined. The results can be used for designing surgical robots and surgeon body supports.

scholarly journals Wearable Inertial Sensors for Gait Analysis in Adults with Osteoarthritis—A Scoping Review

Sensors ◽  
2020 ◽  
Vol 20 (24) ◽  
pp. 7143 ◽  
Author(s):  
Dylan Kobsar ◽  
Zaryan Masood ◽  
Heba Khan ◽  
Noha Khalil ◽  
Marium Yossri Kiwan ◽  
...  
Keyword(s):  
Gait Analysis ◽  
Scoping Review ◽  
Inertial Sensors ◽  
Inertial Sensor ◽  
Linear Acceleration ◽  
Patient Specific ◽  
Common Location ◽  
Spatiotemporal Parameters ◽  
Wearable Inertial Sensors ◽  
Study Designs

Our objective was to conduct a scoping review which summarizes the growing body of literature using wearable inertial sensors for gait analysis in lower limb osteoarthritis. We searched six databases using predetermined search terms which highlighted the broad areas of inertial sensors, gait, and osteoarthritis. Two authors independently conducted title and abstract reviews, followed by two authors independently completing full-text screenings. Study quality was also assessed by two independent raters and data were extracted by one reviewer in areas such as study design, osteoarthritis sample, protocols, and inertial sensor outcomes. A total of 72 articles were included, which studied the gait of 2159 adults with osteoarthritis (OA) using inertial sensors. The most common location of OA studied was the knee (n = 46), followed by the hip (n = 22), and the ankle (n = 7). The back (n = 41) and the shank (n = 40) were the most common placements for inertial sensors. The three most prevalent biomechanical outcomes studied were: mean spatiotemporal parameters (n = 45), segment or joint angles (n = 33), and linear acceleration magnitudes (n = 22). Our findings demonstrate exceptional growth in this field in the last 5 years. Nevertheless, there remains a need for more longitudinal study designs, patient-specific models, free-living assessments, and a push for “Code Reuse” to maximize the unique capabilities of these devices and ultimately improve how we diagnose and treat this debilitating disease.

scholarly journals Exploring Risk of Falls and Dynamic Unbalance in Cerebellar Ataxia by Inertial Sensor Assessment

Sensors ◽  
2019 ◽  
Vol 19 (24) ◽  
pp. 5571 ◽  
Author(s):  
Pietro Caliandro ◽  
Carmela Conte ◽  
Chiara Iacovelli ◽  
Antonella Tatarelli ◽  
Stefano Filippo Castiglia ◽  
...  
Keyword(s):  
Cerebellar Ataxia ◽  
Gait Cycle ◽  
Inertial Sensors ◽  
Inertial Sensor ◽  
Step Length ◽  
Clinical Severity ◽  
Variable Step ◽  
Risk Of Falls ◽  
Wearable Inertial Sensors ◽  
Dynamic Unbalance

Background. Patients suffering from cerebellar ataxia have extremely variable gait kinematic features. We investigated whether and how wearable inertial sensors can describe the gait kinematic features among ataxic patients. Methods. We enrolled 17 patients and 16 matched control subjects. We acquired data by means of an inertial sensor attached to an ergonomic belt around pelvis, which was connected to a portable computer via Bluetooth. Recordings of all the patients were obtained during overground walking. From the accelerometric data, we obtained the harmonic ratio (HR), i.e., a measure of the acceleration patterns, smoothness and rhythm, and the step length coefficient of variation (CV), which evaluates the variability of the gait cycle. Results. Compared to controls, patients had a lower HR, meaning a less harmonic and rhythmic acceleration pattern of the trunk, and a higher step length CV, indicating a more variable step length. Both HR and step length CV showed a high effect size in distinguishing patients and controls (p < 0.001 and p = 0.011, respectively). A positive correlation was found between the step length CV and both the number of falls (R = 0.672; p = 0.003) and the clinical severity (ICARS: R = 0.494; p = 0.044; SARA: R = 0.680; p = 0.003). Conclusion. These findings demonstrate that the use of inertial sensors is effective in evaluating gait and balance impairment among ataxic patients.

scholarly journals Evidence for the Effectiveness of Feedback from Wearable Inertial Sensors during Work-Related Activities: A Scoping Review

Sensors ◽  
2021 ◽  
Vol 21 (19) ◽  
pp. 6377
Author(s):  
Roger Lee ◽  
Carole James ◽  
Suzi Edwards ◽  
Geoff Skinner ◽  
Jodi L. Young ◽  
...  
Keyword(s):  
Inertial Sensors ◽  
Inertial Sensor ◽  
Upper Body ◽  
Sensor Technology ◽  
Vibrotactile Feedback ◽  
Level Of Evidence ◽  
Work Related ◽  
Wearable Inertial Sensors ◽  
Effects Of Feedback

Background: Wearable inertial sensor technology (WIST) systems provide feedback, aiming to modify aberrant postures and movements. The literature on the effects of feedback from WIST during work or work-related activities has not been previously summarised. This review examines the effectiveness of feedback on upper body kinematics during work or work-related activities, along with the wearability and a quantification of the kinematics of the related device. Methods: The Cinahl, Cochrane, Embase, Medline, Scopus, Sportdiscus and Google Scholar databases were searched, including reports from January 2005 to July 2021. The included studies were summarised descriptively and the evidence was assessed. Results: Fourteen included studies demonstrated a ‘limited’ level of evidence supporting posture and/or movement behaviour improvements using WIST feedback, with no improvements in pain. One study assessed wearability and another two investigated comfort. Studies used tri-axial accelerometers or IMU integration (n = 5 studies). Visual and/or vibrotactile feedback was mostly used. Most studies had a risk of bias, lacked detail for methodological reproducibility and displayed inconsistent reporting of sensor technology, with validation provided only in one study. Thus, we have proposed a minimum ‘Technology and Design Checklist’ for reporting. Conclusions: Our findings suggest that WIST may improve posture, though not pain; however, the quality of the studies limits the strength of this conclusion. Wearability evaluations are needed for the translation of WIST outcomes. Minimum reporting standards for WIST should be followed to ensure methodological reproducibility.

scholarly journals Automatic methods of hoof-on and -off detection in horses using wearable inertial sensors during walk and trot on asphalt, sand and grass

PLoS ONE ◽  
2021 ◽  
Vol 16 (7) ◽  
pp. e0254813
Author(s):  
Eloise V. Briggs ◽  
Claudia Mazzà
Keyword(s):  
Event Detection ◽  
Inertial Sensors ◽  
Inertial Sensor ◽  
Wearable Sensors ◽  
Force Plate ◽  
Field Conditions ◽  
Future Studies ◽  
Gait Classification ◽  
Automatic Methods ◽  
Wearable Inertial Sensors

Detection of hoof-on and -off events are essential to gait classification in horses. Wearable sensors have been endorsed as a convenient alternative to the traditional force plate-based method. The aim of this study was to propose and validate inertial sensor-based methods of gait event detection, reviewing different sensor locations and their performance on different gaits and exercise surfaces. Eleven horses of various breeds and ages were recruited to wear inertial sensors attached to the hooves, pasterns and cannons. Gait events detected by pastern and cannon methods were compared to the reference, hoof-detected events. Walk and trot strides were recorded on asphalt, grass and sand. Pastern-based methods were found to be the most accurate and precise for detecting gait events, incurring mean errors of between 1 and 6ms, depending on the limb and gait, on asphalt. These methods incurred consistent errors when used to measure stance durations on all surfaces, with mean errors of 0.1 to 1.16% of a stride cycle. In conclusion, the methods developed and validated here will enable future studies to reliably detect equine gait events using inertial sensors, under a wide variety of field conditions.

PREDICTION OF THE SPATIO-TEMPORAL GAIT PARAMETERS USING INERTIAL SENSOR

2018 ◽  
Vol 18 (07) ◽  
pp. 1840002 ◽  
Author(s):  
JIAN LIU ◽  
THURMON LOCKHART ◽  
SUKWON KIM
Keyword(s):  
Prediction Models ◽  
Inertial Sensors ◽  
Inertial Sensor ◽  
Cost Effective ◽  
Human Gait ◽  
Measurement Unit ◽  
Promising Alternative ◽  
Gait Parameters ◽  
Optical Motion ◽  
Spatio Temporal

Monitoring human gait is essential to quantify gait issues associated with fall-prone individuals as well as other gait-related movement disorders. Being portable and cost-effective, ambulatory gait analysis using inertial sensors is considered a promising alternative to traditional laboratory-based approach. The current study aimed to provide a method for predicting the spatio-temporal gait parameters using the wrist-worn inertial sensors. Eight young adults were involved in a laboratory study. Optical motion analysis system and force-plates were used for the assessment of baseline gait parameters. Spatio-temporal features of an Inertial Measurement Unit (IMU) on the wrist were analyzed. Multi-variate correlation analyses were performed to develop gait parameter prediction models. The results indicated that gait stride time was strongly correlated with peak-to-peak duration of wrist gyroscope signal in the anterio-posterior direction. Meanwhile, gait stride length was successfully predicted using a combination model of peak resultant wrist acceleration and peak sagittal wrist angle. In conclusion, current study provided the evidence that the wrist-worn inertial sensors are capable of estimating spatio-temporal gait parameters. This finding paves the foundation for developing a wrist-worn gait monitor with high user compliance.

Badminton stroke identification using wireless inertial sensor and neural network

2021 ◽  
pp. 175433712110483
Author(s):  
Jian Hui Ooi ◽  
Darwin Gouwanda
Keyword(s):  
Neural Network ◽  
Inertial Sensors ◽  
Inertial Sensor ◽  
Objective Evaluation ◽  
Training Algorithm ◽  
Segmentation Method ◽  
Competitive Environments ◽  
Risk Of Injury ◽  
Timely Feedback ◽  
Wearable Inertial Sensors

Objective evaluation is essential in sports to monitor athlete performance, provide relevant and timely feedback, and minimize the risk of injury. Activity recognition is the first step in sport skill and technique performance analysis. This study investigated the use of wearable inertial sensors and a neural network (NN) to identify badminton strokes. The study also explored the effect of different NN configurations and a different number of sensors on the classification. Sensors were placed at the dominant wrist, left ankle, and right ankle. Six different strokes, ranging from soft hitting net shots to smashes, were performed with a total of 3300 repetitions from six well-trained badminton players. An automated window segmentation method was developed to identify the stroke instances. A scaled conjugate gradient training algorithm with two hidden layers and 55 neurons in each layer was found to be the best approach to classify badminton strokes with an accuracy of 97.69%. Even just wearing the inertial sensor on the wrist was sufficient, providing an accuracy of 95.09%. These results demonstrate the viability of using inertial sensors and NN to recognize badminton strokes, which can be applied in training and competitive environments.

Sign in / Sign up

Export Citation Format

Share Document