Wrist-worn Inertial Measurement Unit Research Articles

Quantifying lumbar sagittal plane kinematics using a wrist-worn inertial measurement unit.

Wearable sensors like inertial measurement units (IMUs), and those available as smartphone or smartwatch applications, are increasingly used to quantify lumbar mobility. Currently, wearable sensors have to be placed on the back to measure lumbar mobility, meaning it cannot be used in unsupervised environments. This study aims to compare lumbar sagittal plane angles quantified from a wrist-worn against that of a lumbar-worn sensor. Twenty healthy participants were recruited. An IMU was placed on the right wrist and the L3 spinal level. Participants had to position their right forearm on their abdomen, parallel to the floor. Three sets of three consecutive repetitions of flexion, and extension were formed. Linear mixed models were performed to quantify the effect of region (lumbar vs. wrist) on six outcomes [minimum, maximum, range of motion (ROM) of flexion and extension]. Only flexion ROM was significantly different between the wrist and lumbar sensors, with a mean of 4.54° (95% CI = 1.82°-7.27°). Across all outcomes, the maximal difference between a wrist-worn and lumbar-worn sensor was <8°. A wrist-worn IMU sensor could be used to measure gross lumbar sagittal plane mobility in place of a lumbar-worn IMU. This may be useful for remote monitoring during rehabilitation.

The effects of selected object features on a pick-and-place task: A human multimodal dataset

We propose a dataset to study the influence of object-specific characteristics on human pick-and-place movements and compare the quality of the motion kinematics extracted by various sensors. This dataset is also suitable for promoting a broader discussion on general learning problems in the hand-object interaction domain, such as intention recognition or motion generation with applications in the Robotics field. The dataset consists of the recordings of 15 subjects performing 80 repetitions of a pick-and-place action under various experimental conditions, for a total of 1200 pick-and-places. The data has been collected thanks to a multimodal setup composed of multiple cameras, observing the actions from different perspectives, a motion capture system, and a wrist-worn inertial measurement unit. All the objects manipulated in the experiments are identical in shape, size, and appearance but differ in weight and liquid filling, which influences the carefulness required for their handling.

Counting Finger and Wrist Movements Using Only a Wrist-Worn, Inertial Measurement Unit: Toward Practical Wearable Sensing for Hand-Related Healthcare Applications

The ability to count finger and wrist movements throughout the day with a nonobtrusive, wearable sensor could be useful for hand-related healthcare applications, including rehabilitation after a stroke, carpal tunnel syndrome, or hand surgery. Previous approaches have required the user to wear a ring with an embedded magnet or inertial measurement unit (IMU). Here, we demonstrate that it is possible to identify the occurrence of finger and wrist flexion/extension movements based on vibrations detected by a wrist-worn IMU. We developed an approach we call “Hand Activity Recognition through using a Convolutional neural network with Spectrograms” (HARCS) that trains a CNN based on the velocity/acceleration spectrograms that finger/wrist movements create. We validated HARCS with the wrist-worn IMU recordings obtained from twenty stroke survivors during their daily life, where the occurrence of finger/wrist movements was labeled using a previously validated algorithm called HAND using magnetic sensing. The daily number of finger/wrist movements identified by HARCS had a strong positive correlation to the daily number identified by HAND (R2 = 0.76, p &lt; 0.001). HARCS was also 75% accurate when we labeled the finger/wrist movements performed by unimpaired participants using optical motion capture. Overall, the ringless sensing of finger/wrist movement occurrence is feasible, although real-world applications may require further accuracy improvements.

Comparing algorithms for assessing upper limb use with inertial measurement units.

The various existing measures to quantify upper limb use from wrist-worn inertial measurement units can be grouped into three categories: 1) Thresholded activity counting, 2) Gross movement score and 3) machine learning. However, there is currently no direct comparison of all these measures on a single dataset. While machine learning is a promising approach to detecting upper limb use, there is currently no knowledge of the information used by machine learning measures and the data-related factors that influence their performance. The current study conducted a direct comparison of the 1) thresholded activity counting measures, 2) gross movement score,3) a hybrid activity counting and gross movement score measure (introduced in this study), and 4) machine learning measures for detecting upper-limb use, using previously collected data. Two additional analyses were also performed to understand the nature of the information used by machine learning measures and the influence of data on the performance of machine learning measures. The intra-subject random forest machine learning measure detected upper limb use more accurately than all other measures, confirming previous observations in the literature. Among the non-machine learning (or traditional) algorithms, the hybrid activity counting and gross movement score measure performed better than the other measures. Further analysis of the random forest measure revealed that this measure used information about the forearm's orientation and amount of movement to detect upper limb use. The performance of machine learning measures was influenced by the types of movements and the proportion of functional data in the training/testing datasets. The study outcomes show that machine learning measures perform better than traditional measures and shed some light on how these methods detect upper-limb use. However, in the absence of annotated data for training machine learning measures, the hybrid activity counting and gross movement score measure presents a reasonable alternative. We believe this paper presents a step towards understanding and optimizing measures for upper limb use assessment using wearable sensors.

Activity-Free User Identification Using Wearables Based on Vision Techniques.

In order to achieve the promise of smart spaces where the environment acts to fulfill the needs of users in an unobtrusive and personalized manner, it is necessary to provide means for a seamless and continuous identification of users to know who indeed is interacting with the system and to whom the smart services are to be provided. In this paper, we propose a new approach capable of performing activity-free identification of users based on hand and arm motion patterns obtained from an wrist-worn inertial measurement unit (IMU). Our approach is not constrained to particular types of movements, gestures, or activities, thus, allowing users to perform freely and unconstrained their daily routine while the user identification takes place. We evaluate our approach based on IMU data collected from 23 people performing their daily routines unconstrained. Our results indicate that our approach is able to perform activity-free user identification with an accuracy of 0.9485 for 23 users without requiring any direct input or specific action from users. Furthermore, our evaluation provides evidence regarding the robustness of our approach in various different configurations.

Estimation of Temporal Parameters During Running with a Wrist-worn Inertial Sensor: an In-field Validation.

The aim of this study was to estimate the temporal gait parameters using a wrist-worn Inertial Measurement Unit (IMU) during an outdoor run. While it is easier to compute running gait parameters using foot IMUs, a wrist IMU is more convenient and less obtrusive when it comes to data acquisition. During a track run of 12 minutes, we equipped 14 highly-trained male runners with one IMU on the wrist and one on each foot. We trained machine learning models based on CNN, GPR, and Lasso regression using wrist IMU signals and validated them with a foot-worn IMU reference system. Lasso model performed the best, with the accuracy for cycle time, swing time, flight time, and contact time being 0.27 % ±0.1 %, 2.6 %±1.7 %, 7.3 % ±4.9 %, and 10.6 % ±5.5 %, respectively.

Drinking Gesture Detection Using Wrist-Worn IMU Sensors with Multi-Stage Temporal Convolutional Network in Free-Living Environments.

Maintaining adequate hydration is important for health. Inadequate liquid intake can cause dehydration problems. Despite the increasing development of liquid intake monitoring, there are still open challenges in drinking detection under free-living conditions. This paper proposes an automatic liquid intake monitoring system comprised of wrist-worn Inertial Measurement Units (IMU s) to recognize drinking gesture in free-living environments. We build an end-to-end approach for drinking gesture detection by employing a novel multi-stage temporal convolutional network (MS-TCN). Two datasets are collected in this research, one contains 8.9 hours data from 13 participants in semi-controlled environments, the other one contains 45.2 hours data from 7 participants in free-living environments. The Leave-One-Subject-Out (LOSO) evaluation shows that this method achieves a segmental F1-score of 0.943 and 0.900 in the semi-controlled and free-living datasets, respectively. The results also indicate that our approach outperforms the convolutional neural network and long-short-term-memory network combined model (CNN-LSTM) on our datasets. The dataset used in this paper is available at https://github.com/Pituohai/drinking-gesture-dataset/. Clinical Relevance- This automatic liquid intake monitoring system can detect drinking gesture in daily life. It has the potential to be used to record the frequency of drinking water for at-risk elderly or patients in the hospital.

Autonomous modeling of repetitive movement for rehabilitation exercise monitoring

BackgroundInsightful feedback generation for daily home-based stroke rehabilitation is currently unavailable due to the inefficiency of exercise inspection done by therapists. We aim to produce a compact anomaly representation that allows a therapist to pay attention to only a few specific sections in a long exercise session record and boost their efficiency in feedback generation.MethodsThis study proposes a data-driven technique to model a repetitive exercise using unsupervised phase learning on an artificial neural network and statistical learning on principal component analysis (PCA). After a model is built on a set of normal healthy movements, the model can be used to extract a sequence of anomaly scores from a movement of the same prescription.ResultsThe method not only works on a standard marker-based motion capture system but also performs well on a more compact and affordable motion capture system based-on Kinect V2 and wrist-worn inertial measurement units that can be used at home. An evaluation of four different exercises shows its potential in separating anomalous movements from normal ones with an average area under the curve (AUC) of 0.9872 even on the compact motion capture system.ConclusionsThe proposed processing technique has the potential to help clinicians in providing high-quality feedback for telerehabilitation in a more scalable way.

Measuring Movement Quality of the Stroke-Impaired Upper Extremity with a Wearable Sensor: Toward a Smoothness Metric for Home Rehabilitation Exercise Programs.

Remote patient monitoring systems show promise for assisting stroke patients in home exercise programs. While these systems typically measure exercise repetitions in order to monitor compliance, a key goal of therapists is to also monitor movement quality. Here we develop a measure of movement quality - Peak Intensity - that is a measure of movement smoothness that is implementable with a wrist-worn inertial measurement unit (IMU) in the context of performing repetitions of an upper extremity exercise. To calculate Peak Intensity, we assume we have an accurate count of the number of exercise repetitions in an exercise set, then calculate Peak Intensity as the total number of movement peaks from the continuous stream of IMU data generated across the set, divided by the number of repetitions. Using wrist-worn IMU measurements from 19 participants with chronic stroke performing a sample exercise in which they picked up and moved blocks across a divider (i.e. the Box and Blocks Test) we show that Peak Intensity is moderately correlated with a widely used measure of movement quality, the Quality of Movement score of the Motor Activity Log. Peak Intensity is also strongly correlated with a measure of hand function (the BBT score itself), but is more sensitive at greater levels of impairment. Finally, we show Peak Intensity can be validly derived from either wrist acceleration or angular velocity. These results suggest Peak Intensity could serve as an indicator of movement exercise quality for therapists monitoring home rehabilitation, and, potentially, as a means to provide augmented feedback to patients about their exercise quality.

DeepFoG: An IMU-Based Detection of Freezing of Gait Episodes in Parkinson's Disease Patients via Deep Learning.

Freezing of Gait (FoG) is a movement disorder that mostly appears in the late stages of Parkinson’s Disease (PD). It causes incapability of walking, despite the PD patient’s intention, resulting in loss of coordination that increases the risk of falls and injuries and severely affects the PD patient’s quality of life. Stress, emotional stimulus, and multitasking have been encountered to be associated with the appearance of FoG episodes, while the patient’s functionality and self-confidence are constantly deteriorating. This study suggests a non-invasive method for detecting FoG episodes, by analyzing inertial measurement unit (IMU) data. Specifically, accelerometer and gyroscope data from 11 PD subjects, as captured from a single wrist-worn IMU sensor during continuous walking, are processed via Deep Learning for window-based detection of the FoG events. The proposed approach, namely DeepFoG, was evaluated in a Leave-One-Subject-Out (LOSO) cross-validation (CV) and 10-fold CV fashion schemes against its ability to correctly estimate the existence or not of a FoG episode at each data window. Experimental results have shown that DeepFoG performs satisfactorily, as it achieves 83%/88% and 86%/90% sensitivity/specificity, for LOSO CV and 10-fold CV schemes, respectively. The promising performance of the proposed DeepFoG reveals the potentiality of single-arm IMU-based real-time FoG detection that could guide effective interventions via stimuli, such as rhythmic auditory stimulation (RAS) and hand vibration. In this way, DeepFoG may scaffold the elimination of risk of falls in PD patients, sustaining their quality of life in everyday living activities.

Real-Time Driving Distraction Recognition Through a Wrist-Mounted Accelerometer.

We propose a method for recognizing driver distraction in real time using a wrist-worn inertial measurement unit (IMU). Distracted driving results in thousands of fatal vehicle accidents every year. Recognizing distraction using body-worn sensors may help mitigate driver distraction and consequently improve road safety. Twenty participants performed common behaviors associated with distracted driving while operating a driving simulator. Acceleration data collected from an IMU secured to each driver's right wrist were used to detect potential manual distractions based on 2-s long streaming data. Three deep neural network-based classifiers were compared for their ability to recognize the type of distractive behavior using F1-scores, a measure of accuracy considering both recall and precision. The results indicated that a convolutional long short-term memory (ConvLSTM) deep neural network outperformed a convolutional neural network (CNN) and recursive neural network with long short-term memory (LSTM) for recognizing distracted driving behaviors. The within-participant F1-scores for the ConvLSTM, CNN, and LSTM were 0.87, 0.82, and 0.82, respectively. The between-participant F1-scores for the ConvLSTM, CNN, and LSTM were 0.87, 0.76, and 0.85, respectively. The results of this pilot study indicate that the proposed driving distraction mitigation system that uses a wrist-worn IMU and ConvLSTM deep neural network classifier may have potential for improving transportation safety.

Quantification of the relative arm use in patients with hemiparesis using inertial measurement units

IntroductionAccelerometry-based activity counting for measuring arm use is prone to overestimation due to non-functional movements. In this paper, we used an inertial measurement unit (IMU)-based gross movement (GM) score to quantify arm use.MethodsIn this two-part study, we first characterized the GM by comparing it to annotated video recordings of 5 hemiparetic patients and 10 control subjects performing a set of activities. In the second part, we tracked the arm use of 5 patients and 5 controls using two wrist-worn IMUs for 7 and 3 days, respectively. The IMU data was used to develop quantitative measures (total and relative arm use) and a visualization method for arm use.ResultsFrom the characterization study, we found that GM detects functional activities with 50–60% accuracy and eliminates non-functional activities with >90% accuracy. Continuous monitoring of arm use showed that the arm use was biased towards the dominant limb and less paretic limb for controls and patients, respectively.ConclusionsThe gross movement score has good specificity but low sensitivity in identifying functional activity. The at-home study showed that it is feasible to use two IMU-watches to monitor relative arm use and provided design considerations for improving the assessment method.Clinical trial registry number: CTRI/2018/09/015648

Accuracy and Acceptability of Wearable Motion Tracking for Inpatient Monitoring Using Smartwatches.

Inertial Measurement Units (IMUs) within an everyday consumer smartwatch offer a convenient and low-cost method to monitor the natural behaviour of hospital patients. However, their accuracy at quantifying limb motion, and clinical acceptability, have not yet been demonstrated. To this end we conducted a two-stage study: First, we compared the inertial accuracy of wrist-worn IMUs, both research-grade (Xsens MTw Awinda, and Axivity AX3) and consumer-grade (Apple Watch Series 3 and 5), and optical motion tracking (OptiTrack). Given the moderate to strong performance of the consumer-grade sensors, we then evaluated this sensor and surveyed the experiences and attitudes of hospital patients (N = 44) and staff (N = 15) following a clinical test in which patients wore smartwatches for 1.5–24 h in the second study. Results indicate that for acceleration, Xsens is more accurate than the Apple Series 5 and 3 smartwatches and Axivity AX3 (RMSE 1.66 ± 0.12 m·s−2; R2 0.78 ± 0.02; RMSE 2.29 ± 0.09 m·s−2; R2 0.56 ± 0.01; RMSE 2.14 ± 0.09 m·s−2; R2 0.49 ± 0.02; RMSE 4.12 ± 0.18 m·s−2; R2 0.34 ± 0.01 respectively). For angular velocity, Series 5 and 3 smartwatches achieved similar performances against Xsens with RMSE 0.22 ± 0.02 rad·s−1; R2 0.99 ± 0.00; and RMSE 0.18 ± 0.01 rad·s−1; R2 1.00± SE 0.00, respectively. Surveys indicated that in-patients and healthcare professionals strongly agreed that wearable motion sensors are easy to use, comfortable, unobtrusive, suitable for long-term use, and do not cause anxiety or limit daily activities. Our results suggest that consumer smartwatches achieved moderate to strong levels of accuracy compared to laboratory gold-standard and are acceptable for pervasive monitoring of motion/behaviour within hospital settings.

Development of a home-based wrist range-of-motion training system for children with cerebral palsy

Abstract This paper presents the proof-of-concept of a home-based gamified wrist rehabilitation training system for children with cerebral palsy (CCP). We describe the user-centered design process of this system, which is composed of a wrist-worn inertial measurement unit (IMU) and a tangible device with an embedded IMU. The system employs a quaternion-based algorithm for automatic real-time estimation of the range of motion (RoM) covered by adduction/abduction and flexion/extension motions of the wrist. Experimental validation shows that the RoM can be determined with sufficient accuracy to control a game and that the algorithm is applicable in CCP. A serious game, which uses the presented algorithm and enables feedback as well as motivating stimuli, is implemented and evaluated by physiotherapists.

Deep Learning for Intake Gesture Detection From Wrist-Worn Inertial Sensors: The Effects of Data Preprocessing, Sensor Modalities, and Sensor Positions

Wrist-worn inertial measurement units have emerged as a promising technology to passively capture dietary intake data. State-of-the-art approaches use deep neural networks to process the collected inertial data and detect characteristic hand movements associated with intake gestures. In order to clarify the effects of data preprocessing, sensor modalities, and sensor positions, we collected and labeled inertial data from wrist-worn accelerometers and gyroscopes on both hands of 100 participants in a semi-controlled setting. The method included data preprocessing and data segmentation, followed by a two-stage approach. In Stage 1, we estimated the probability of each inertial data frame being intake or non-intake, benchmarking different deep learning models and architectures. Based on the probabilities estimated in Stage 1, we detected the intake gestures in Stage 2 and calculated the F1 score for each model. Results indicate that top model performance was achieved by a CNN-LSTM with earliest sensor data fusion through a dedicated CNN layer and a target matching technique (F 1 = .778). As for data preprocessing, results show that applying a consecutive combination of mirroring, removing gravity effect, and standardization was beneficial for model performance, while smoothing had adverse effects. We further investigate the effectiveness of using different combinations of sensor modalities (i.e., accelerometer and/or gyroscope) and sensor positions (i.e., dominant intake hand and/or non-dominant intake hand).

An Exploratory Study Comparing the Hand Arm Vibration Exposures Measured from Bucking Bars using Traditional Tool-mounted Accelerometers and Wrist Worn IMUs

This controlled, exploratory laboratory study was conducted to measure hand-arm vibration (HAV) exposures when using a bucking bar fitted with three different handles: 1) a typical plastic handle, 2) a similarly designed handle with an aluminum core and a built-in dampening spring, and 3) a steel core handle with the same built-in spring. Using two experienced machinists, tri-axial HAV exposures were measured at the bucking bar handles; small, battery-powered, self-contained Inertial Measurement Units (IMUs) were used to measure the vibration transmitted through the tool operator’s left and right arms; and a wearable device worn on the operator’s right wrist estimated the HAV exposures occurring at the tool handle. The plastic handle produced the highest HAV exposures while the aluminum-spring and steel spring handles reduced exposures by 19% and 39%, respectively. On average, 74%, 65% and 40% of the tool-measured vibration was transmitted to the right hand, forearm and upper arm, respectively. The wrist mounted sensor appeared to accurately estimate HAV exposures measured at the hand-tool interface.

Thermal sensors improve wrist-worn position tracking

Wearable devices provide a means of tracking hand position in relation to the head, but have mostly relied on wrist-worn inertial measurement unit sensors and proximity sensors, which are inadequate for identifying specific locations. This limits their utility for accurate and precise monitoring of behaviors or providing feedback to guide behaviors. A potential clinical application is monitoring body-focused repetitive behaviors (BFRBs), recurrent, injurious behaviors directed toward the body, such as nail biting and hair pulling, which are often misdiagnosed and undertreated. Here, we demonstrate that including thermal sensors achieves higher accuracy in position tracking when compared against inertial measurement unit and proximity sensor data alone. Our Tingle device distinguished between behaviors from six locations on the head across 39 adult participants, with high AUROC values (best was back of the head: median (1.0), median absolute deviation (0.0); worst was on the cheek: median (0.93), median absolute deviation (0.09)). This study presents preliminary evidence of the advantage of including thermal sensors for position tracking and the Tingle wearable device’s potential use in a wide variety of settings, including BFRB diagnosis and management.

Personalized Markerless Upper-Body Tracking with a Depth Camera and Wrist-Worn Inertial Measurement Units.

A markerless motion capture technique is proposed based on a fusion between a depth camera (Kinect V2) and a pair of wrist-worn inertial measurement units (IMU). The method creates a personalized articulated human mesh model from one depth image frame and uses that model to improve the accuracy of the upper-body joint tracking. The IMUs are useful as an additional clue for the arm tracking, especially during an occlusion. An evaluation of the method against a marker-based system as a gold standard using data from 6 subjects is done. The result shows over 20% reduction in upper-limb joint position errors when compared to Kinect's skeleton tracking. All the collected data are calibrated, synchronized, and made publicly available for research purposes.

Regression Model-Based Walking Speed Estimation Using Wrist-Worn Inertial Sensor.

Walking speed is widely used to study human health status. Wearable inertial measurement units (IMU) are promising tools for the ambulatory measurement of walking speed. Among wearable inertial sensors, the ones worn on the wrist, such as a watch or band, have relatively higher potential to be easily incorporated into daily lifestyle. Using the arm swing motion in walking, this paper proposes a regression model-based method for longitudinal walking speed estimation using a wrist-worn IMU. A novel kinematic variable is proposed, which finds the wrist acceleration in the principal axis (i.e. the direction of the arm swing). This variable (called pca-acc) is obtained by applying sensor fusion on IMU data to find the orientation followed by the use of principal component analysis. An experimental evaluation was performed on 15 healthy young subjects during free walking trials. The experimental results show that the use of the proposed pca-acc variable can significantly improve the walking speed estimation accuracy when compared to the use of raw acceleration information (p<0.01). When Gaussian process regression is used, the resulting walking speed estimation accuracy and precision is about 5.9% and 4.7%, respectively.

A method to qualitatively assess arm use in stroke survivors in the home environment

Wearable sensor technology has enabled unobtrusive monitoring of arm movements of stroke survivors in the home environment. However, the most widely established method, based on activity counts, provides quantitative rather than qualitative information on arm without functional insights, and is sensitive to passive arm movements during ambulatory activities. We propose a method to quantify functionally relevant arm use in stroke survivors relying on a single wrist-worn inertial measurement unit. Orientation of the forearm during movements is measured in order identify gross arm movements. The method is validated in 10 subacute/chronic stroke survivors wearing inertial sensors at 5 anatomical locations for 48 h. Measurements are compared to conventional activity counts and to a test for gross manual dexterity. Duration of gross arm movements of the paretic arm correlated significantly better with the Box and Block Test (r=0.95) than conventional activity counts when walking phases were included (r=0.69), and similar results were found when comparing ratios of paretic and non-paretic arms for gross movements and activity counts. The proposed gross arm movement metric is robust against passive arm movements during ambulatory activities and requires only a single-sensor module placed at the paretic wrist for the assessment of functionally relevant arm use.