Towards User-Friendly Wearable Platforms for Monitoring Unconstrained Indoor and Outdoor Activities.

Developing wearable platforms for unconstrained monitoring of limb movements has been an active recent topic of research due to potential applications such as clinical and athletic performance evaluation. However, practicality of these platforms might be affected by the dynamic and complexity of movements as well as characteristics of the surrounding environment. This paper addresses such issues by proposing a novel method for obtaining kinematic information of joints using a custom-designed wearable platform. The proposed method uses data from two gyroscopes and an array of textile stretch sensors to accurately track three-dimensional movements, including extension, flexion, and rotation, of a joint. More specifically, gyroscopes provide angular velocity data of two sides of a joint, while their relative orientation is estimated by a machine learning algorithm. An Unscented Kalman Filter (UKF) algorithm is applied to directly fuse angular velocity/relative orientation data and estimate the kinematic orientation of the joint. Experimental evaluations were carried out using data from 10 volunteers performing a series of predefined as well as unconstrained random three-dimensional trunk movements. Results show that the proposed sensor setup and the UKF-based data fusion algorithm can accurately estimate the orientation of the trunk relative to pelvis with an average error of less than 1.72 degrees in predefined movements and a comparable accuracy of 3.00 degrees in random movements. Moreover, the proposed platform is easy to setup, does not restrict body motion, and is not affected by environmental disturbances. This study is a further step towards developing user-friendly wearable sensor systems than can be readily used in indoor and outdoor settings without requiring bulky equipment or a tedious calibration phase.

Robotics-assisted visual-motor training influences arm position sense in three-dimensional space.

BACKGROUND: Performing activities of daily living depends, among other factors, on awareness of the position and movements of limbs. Neural injuries, such as stroke, might negatively affect such an awareness and, consequently, lead to degrading the quality of life and lengthening the motor recovery process. With the goal of improving the sense of hand position in three-dimensional (3D) space, we investigate the effects of integrating a pertinent training component within a robotic reaching task. METHODS: In the proof-of-concept study presented in this paper, 12 healthy participants, during a single session, used their dominant hand to attempt reaching without vision to two targets in 3D space, which were placed at locations that resembled the functional task of self-feeding. After each attempt, participants received visual and haptic feedback about their hand's position to accurately locate the target. Performance was evaluated at the beginning and end of each session during an assessment in which participants reached without visual nor haptic feedback to three targets: the same two targets employed during the training phase and an additional one to evaluate the generalization of training. RESULTS: Collected data showed a statistically significant [39.81% (p=0.001)] reduction of end-position reaching error when results of reaching to all targets were combined. End-position error to the generalization target, although not statistically significant, was reduced by 15.47%. CONCLUSIONS: These results provide support for the effectiveness of combining an arm position sense training component with functional motor tasks, which could be implemented in the design of future robot-assisted rehabilitation paradigms to potentially expedite the recovery process of individuals with neurological injuries.

Wrist-worn wearables based on force myography: on the significance of user anthropometry.

BACKGROUND: Force myography (FMG) is a non-invasive technology used to track functional movements and hand gestures by sensing volumetric changes in the limbs caused by muscle contraction. Force transmission through tissue implies that differences in tissue mechanics and/or architecture might impact FMG signal acquisition and the accuracy of gesture classifier models. The aim of this study is to identify if and how user anthropometry affects the quality of FMG signal acquisition and the performance of machine learning models trained to classify different hand and wrist gestures based on that data. METHODS: Wrist and forearm anthropometric measures were collected from a total of 21 volunteers aged between 22 and 82 years old. Participants performed a set of tasks while wearing a custom-designed FMG band. Primary outcome measure was the Spearman's correlation coefficient (R) between the anthropometric measures and FMG signal quality/ML model performance. RESULTS: Results demonstrated moderate (0.3 ≤|R| < 0.67) and strong (0.67 ≤ |R|) relationships for ratio of skinfold thickness to forearm circumference, grip strength and ratio of wrist to forearm circumference. These anthropometric features contributed to 23-30% of the variability in FMG signal acquisition and as much as 50% of the variability in classification accuracy for single gestures. CONCLUSIONS: Increased grip strength, larger forearm girth, and smaller skinfold-to-forearm circumference ratio improve signal quality and gesture classification accuracy.

Wearable Device to Monitor Back Movements Using an Inductive Textile Sensor.

Low back pain (LBP) is the most common work-related musculoskeletal disorder among healthcare workers and is directly related to long hours of working in twisted/bent postures or with awkward trunk movements. It has already been established that providing relevant feedback helps individuals to maintain better body posture during the activities of daily living. With the goal of preventing LBP through objective monitoring of back posture, this paper proposes a wireless, comfortable, and compact textile-based wearable platform to track trunk movements when the user bends forward. The smart garment developed for this purpose was prototyped with an inductive sensor formed by sewing a copper wire into an elastic fabric in a zigzag pattern. The results of an extensive simulation study showed that this unique design increases the inductance value of the sensor, and, consequently, improves its resolution. Furthermore, experimental evaluation on a healthy participant confirmed that the proposed wearable system with the suggested sensor design can easily detect forward bending movements. The evaluation scenario was then extended to also include twisting and lateral bending of the trunk, and it was observed that the proposed design can successfully discriminate such movements from forward bending of the trunk. Results of the magnetic interference test showed that, most notably, moving a cellphone towards the unworn prototype affects sensor readings, however, manipulating a cellphone, when wearing the prototype, did not affect the capability of the sensor in detecting forward bends. The proposed platform is a promising step toward developing wearable systems to monitor back posture in order to prevent or treat LBP.

FMG- and RNN-Based Estimation of Motor Intention of Upper-Limb Motion in Human-Robot Collaboration.

Research on human-robot interactions has been driven by the increasing employment of robotic manipulators in manufacturing and production. Toward developing more effective human-robot collaboration during shared tasks, this paper proposes an interaction scheme by employing machine learning algorithms to interpret biosignals acquired from the human user and accordingly planning the robot reaction. More specifically, a force myography (FMG) band was wrapped around the user's forearm and was used to collect information about muscle contractions during a set of collaborative tasks between the user and an industrial robot. A recurrent neural network model was trained to estimate the user's hand movement pattern based on the collected FMG data to determine whether the performed motion was random or intended as part of the predefined collaborative tasks. Experimental evaluation during two practical collaboration scenarios demonstrated that the trained model could successfully estimate the category of hand motion, i.e., intended or random, such that the robot either assisted with performing the task or changed its course of action to avoid collision. Furthermore, proximity sensors were mounted on the robotic arm to investigate if monitoring the distance between the user and the robot had an effect on the outcome of the collaborative effort. While further investigation is required to rigorously establish the safety of the human worker, this study demonstrates the potential of FMG-based wearable technologies to enhance human-robot collaboration in industrial settings.

Robot-Aided Upper-limb Proprioceptive Training in Three-Dimensional Space.

Proprioception, the ability to sense body position and limb movements in space without visual feedback, is one of the key factors in controlling body movements and performing activities of daily living. However, this capability might be affected after neural injuries such as stroke. Robotic platforms can be used to monitor and promote arm movements and, therefore, can assist in developing rehabilitation protocols that aim to improve proprioception through repetitive reaching motions without vision. The objective of this paper is to investigate if a robotic training protocol improves the end-position reaching proprioceptive sense in three-dimensional (3D) space. As an initial step towards clinical application, a robotic platform was employed to train the end-position proprioceptive sense in six healthy participants. During the training phase, volunteers used their dominant hand to reach without vision to two different targets in 3D space. Positions of these targets were carefully chosen to create a hand movement pattern similar to that used when self-feeding, which is an important activity of daily living. At the end of each training trial, participants were provided with visual feedback to help them move their hands to the exact locations confirmed through haptic feedback. Their performance was evaluated before and after the training in an assessment phase during which participants were asked to move from the start position to the same two targets as well as an additional third one without any visual or haptic feedback. The results from this study show significant improvements in overall reaching accuracy and trajectory smoothness, demonstrated by 41% decrease in the average end-position error and 13% reduction in the average index of curvature after the training. This research suggests the potential of designing robotic rehabilitation protocols for improving 3D proprioception.

Estimation of Ankle Joint Power during Walking Using Two Inertial Sensors.

(1) Background: Ankle joint power, as an indicator of the ability to control lower limbs, is of great relevance for clinical diagnosis of gait impairment and control of lower limb prosthesis. However, the majority of available techniques for estimating joint power are based on inverse dynamics methods, which require performing a biomechanical analysis of the foot and using a highly instrumented environment to tune the parameters of the resulting biomechanical model. Such techniques are not generally applicable to real-world scenarios in which gait monitoring outside of the clinical setting is desired. This paper proposes a viable alternative to such techniques by using machine learning algorithms to estimate ankle joint power from data collected by two miniature inertial measurement units (IMUs) on the foot and shank, (2) Methods: Nine participants walked on a force-plate-instrumented treadmill wearing two IMUs. The data from the IMUs were processed to train and test a random forest model to estimate ankle joint power. The performance of the model was then evaluated by comparing the estimated power values to the reference values provided by the motion tracking system and the force-plate-instrumented treadmill. (3) Results: The proposed method achieved a high accuracy with the correlation coefficient, root mean square error, and normalized root mean square error of 0.98, 0.06 w/kg, and 1.05% in the intra-subject test, and 0.92, 0.13 w/kg, and 2.37% in inter-subject test, respectively. The difference between the predicted and true peak power values was 0.01 w/kg and 0.14 w/kg with a delay of 0.4% and 0.4% of gait cycle duration for the intra- and inter-subject testing, respectively. (4) Conclusions: The results of this study demonstrate the feasibility of using only two IMUs to estimate ankle joint power. The proposed technique provides a basis for developing a portable and compact gait monitoring system that can potentially offer monitoring and reporting on ankle joint power in real-time during activities of daily living.

Investigation on the effect of noisy galvanic vestibular stimulation on fine motor skills during a visuomotor task in healthy participants.

Noisy galvanic vestibular stimulation (nGVS) has been shown to improve dynamic walking stability, affect postural responses, enhance balance in healthy subjects, and influence motor performance in individuals with Parkinson's disease. Although the studies to fully characterize the effect of nGVS are still ongoing, stochastic resonance theory which states that the addition of noisy signal may enhance a weak sensory input signals transmission in a non-linear system may provide a possible explanation for the observed positive effects of nGVS. This study explores the effect of nGVS on fine tracking behavior in healthy subjects. Ten healthy participants performed a computer-based visuomotor task by controlling an object with a joystick to follow an amplitude-modulated signal path while simultaneously receiving a sham or pink noise nGVS. The stimulation was generated to have a zero-mean, linearly detrended 1/f-type power spectrum, Gaussian distribution within 0.1-10 Hz range, and a standard deviation (SD) set to 90% based on each participant's cutaneous threshold value. Results show that simultaneous nGVS delivery statistically improved the tracking performance with a decreased root-mean-squared error of 5.71±6.20% (mean±SD), a decreased time delay of 11.88±9.66% (mean±SD), and an increased signal-to-noise ratio of 2.93% (median, interquartile range (IQR) 3.31%). This study showed evidence that nGVS may be beneficial in improving sensorimotor performance during a fine motor tracking task requiring fine wrist movement in healthy subjects. Further research with a more comprehensive subset of tasks is required to fully characterize the effects of nGVS on fine motor skills.

Two-channel in-ear EEG system for detection of visuomotor tracking state: A preliminary study.

Evaluating an operator's mental workload during work activities is crucial to maintain safety and performance. By minimizing human error associated with work demands, especially in a hazardous environment, potentially serious errors may be avoided. This study aims to assess the feasibility of using an in-ear EEG system to classify the user's state in a visuomotor tracking task that may influence mental workload and motor action. A two-channel wireless in-ear EEG system was used to record EEG signals while subjects performed the task using a joystick to manipulate an object displayed on a monitor. A highly comparative time series analysis was employed on the processed signals to extract and select the top features for each subject individually. The features sets were trained and tested with support vector machines, random forest, linear discriminant analysis, subspace discriminant, and neural network to compare their performances. Models trained on two trials, each 14 minutes in duration and tested on the other trial were able to yield an accuracy of 79.30 ± 4.85% on average across the ten participants with an individualized moving average threshold filter and classifier. This proof-of-concept study demonstrates the feasibility of using a two-channel wireless in-ear EEG system as a viable solutions to develop wearable devices to detect mental workload associated with the execution of visuomotor tasks.

Effects of Galvanic Vestibular Stimulation on Upper and Lower Extremities Motor Symptoms in Parkinson's Disease.

As a neurodegenerative movement disorder, Parkinson's disease (PD) is commonly characterized by motor symptoms such as resting tremor, rigidity, bradykinesia, and balance and postural impairments. While the main cause of PD is still not clear, it is shown that the basal ganglia loop, which has a role in adjusting a planned movement execution through fine motor control, is altered during this disease and contributes toward the manifested motor symptoms. Galvanic vestibular stimulation (GVS) is a non-invasive technique to influence the vestibular system and stimulate the motor system. This study explores how the motor symptoms of upper and lower extremities in PD are instantly affected by vestibular stimulation. In this regard, direct current GVS was applied to 11 individuals with PD on medication while they were performing two sets of experiments: (1) Instrumented Timed Up and Go (iTUG) test and (2) finger tapping task. The performance of participants was recorded with accelerometers and cameras for offline processing of data. Several outcome measures including coefficient of variation of the step duration, gait phase, phase coordination index, tapping score, and the number and duration of manual motor blocks (MMBs) were considered for objective quantifying of performance. Results showed that almost all of considered outcome measures were improved with the application of GVS and that the improvement in the coefficient of variation of the step duration, the tapping score, and the number of MMBs was statistically significant (p-value < 0.05). The results of this study suggest that GVS can be used to alleviate some of the common motor symptoms of PD. Further research is required to fully characterize the effects of GVS and determine its efficacy in the long term.

A Wearable Gait Phase Detection System Based on Force Myography Techniques.

(1) Background: Quantitative evaluation of gait parameters can provide useful information for constructing individuals’ gait profile, diagnosing gait abnormalities, and better planning of rehabilitation schemes to restore normal gait pattern. Objective determination of gait phases in a gait cycle is a key requirement in gait analysis applications; (2) Methods: In this study, the feasibility of using a force myography-based technique for a wearable gait phase detection system is explored. In this regard, a force myography band is developed and tested with nine participants walking on a treadmill. The collected force myography data are first examined sample-by-sample and classified into four phases using Linear Discriminant Analysis. The gait phase events are then detected from these classified samples using a set of supervisory rules; (3) Results: The results show that the force myography band can correctly detect more than 99.9% of gait phases with zero insertions and only four deletions over 12,965 gait phase segments. The average temporal error of gait phase detection is 55.2 ms, which translates into 2.1% error with respect to the corresponding labelled stride duration; (4) Conclusions: This proof-of-concept study demonstrates the feasibility of force myography techniques as viable solutions in developing wearable gait phase detection systems.

Modeling and estimation of tip contact force for steerable ablation catheters.

OBJECTIVE: The efficacy of catheter-based cardiac ablation procedures can be significantly improved if real-time information is available concerning contact forces between the catheter tip and cardiac tissue. However, the widely used ablation catheters are not equipped for force sensing. This paper proposes a technique for estimating the contact forces without direct force measurements by studying the changes in the shape of the deflectable distal section of a conventional 7-Fr catheter (henceforth called the "deflectable distal shaft," the "deflectable shaft," or the "shaft" of the catheter) in different loading situations. METHOD: First, the shaft curvature when the tip is moving in free space is studied and based on that, a kinematic model for the deflectable shaft in free space is proposed. In the next step, the shaft shape is analyzed in the case where the tip is in contact with the environment, and it is shown that the curvature of the deflectable shaft provides useful information about the loading status of the catheter and can be used to define an index for determining the range of contact forces exerted by the ablation tip. RESULTS: Experiments with two different steerable ablation catheters show that the defined index can detect the range of applied contact forces correctly in more than 80% of the cases. Based on the proposed technique, a framework for obtaining contact force information by using the shaft curvature at a limited number of points along the deflectable shaft is constructed. CONCLUSION: The proposed kinematic model and the force estimation technique can be implemented together to describe the catheter's behavior before contact, detect tip/tissue contact, and determine the range of contact forces. SIGNIFICANCE: This study proves that the flexibility of the catheter's distal shaft provides a means of estimating the force exerted on tissue by the ablation tip.

Visual servoing in medical robotics: a survey. Part II: tomographic imaging modalities--techniques and applications.

BACKGROUND: Intraoperative application of tomographic imaging techniques provides a means of visual servoing for objects beneath the surface of organs. METHODS: The focus of this survey is on therapeutic and diagnostic medical applications where tomographic imaging is used in visual servoing. To this end, a comprehensive search of the electronic databases was completed for the period 2000-2013. RESULTS: Existing techniques and products are categorized and studied, based on the imaging modality and their medical applications. This part complements Part I of the survey, which covers visual servoing techniques using endoscopic imaging and direct vision. CONCLUSION: The main challenges in using visual servoing based on tomographic images have been identified. 'Supervised automation of medical robotics' is found to be a major trend in this field and ultrasound is the most commonly used tomographic modality for visual servoing.

Visual servoing in medical robotics: a survey. Part I: endoscopic and direct vision imaging - techniques and applications.

BACKGROUND: Intra-operative imaging is widely used to provide visual feedback to a clinician when he/she performs a procedure. In visual servoing, surgical instruments and parts of tissue/body are tracked by processing the acquired images. This information is then used within a control loop to manoeuvre a robotic manipulator during a procedure. METHODS: A comprehensive search of electronic databases was completed for the period 2000-2013 to provide a survey of the visual servoing applications in medical robotics. The focus is on medical applications where image-based tracking is used for closed-loop control of a robotic system. RESULTS: Detailed classification and comparative study of various contributions in visual servoing using endoscopic or direct visual images are presented and summarized in tables and diagrams. CONCLUSION: The main challenges in using visual servoing for medical robotic applications are identified and potential future directions are suggested. 'Supervised automation of medical robotics' is found to be a major trend in this field.