Finger Joint Angles Research Articles

Highly sensitive measurement of finger joint angle based on a double-U tapered POF embedded in PDMS film

Finger joint angle measurements are important for the fields such as treatment of joint diseases, health monitoring, wearable devices, etc. As an effective detecting device, the joint angle monitoring sensor should have wide measurement angle range, and high sensitivity. In addition, the sensor should have good skin affinity, so as to enhance the degree of comfort for the user. In this paper, high-sensitivity bending angle sensing based on tapered plastic optical fiber (POF) configuration is proposed. The sensing performance is enhanced by tapering the POF and bending the POF taper to form a double U-shaped configuration then encapsulated with Polydimethylsiloxane (PDMS) film, therefore, the POF taper will be bent at three positions simultaneously, so that the bend induced loss will increase. The experimental preparation process of tapered POF and PDMS film package are presented in detail. The influence of taper waist diameter, and bending diameter on the bending loss has been investigated and optimized to enhance the angle sensitivity of the double U-shaped configuration. The results show that the sensitivity can reach 0.070 dB/° with a linearity of 0.995 in a wide bending angle range of 0-105°. The POF sensor is then applied for the joint bending detection. The experimental results show that the sensor can quickly respond to small pressures, and the variation of bending angles can be distinguished in the detection of joint bending. The proposed POF bending sensor shows the advantages of wide measurement angle range, high sensitivity, low cost and good portability, and shows important potential applications in the fields such as human joint movement detection.

Optimized Model Selection for Concurrent Decoding of Finger Kinetics and Kinematics

Myoelectric-based motor intent detection is typically used to interface with assistive devices. However, the intent detection performance is sensitive to interference of electromyogram (EMG) signals. Recently, EMG signals are decomposed into motor units (MU) firing activities, and neuron binary firing activities can be used to predict motor output in a continuous manner. Different functions that map MU firings to motor output have been implemented, and both composite MU firing frequency and individual MU firing frequency have been used. It is unclear whether one mapping function outperform others. Accordingly, we evaluated three MU-based finger kinetic and kinematic prediction models, by varying the number of MUs and the method of including MU firings into the regression model. We also compared the performance of three EMG amplitude-based models with varying number of channels. We performed MU decomposition in advance for real-time implementations. Our results showed that individual firing frequency of five MUs provided the lowest estimation error (force: 4.66±0.36 %MVC; joint angle: 4.81±0.49°) and highest correlation (force: 0.86±0.01; joint angle: 0.93±0.01) with the measured motor outputs, when compared with mapping method using the populational firing frequency of all MUs or the populational firing frequency of a group of MUs with similar firing activities. The results indicated that firing information at the population level may mask critical information of individual MU firings. These findings allowed us to identify the optimal models for concurrent and continuous finger force and joint angle estimation. A combination of the minimal level of complexity and high accuracy make these models suitable for real-time control of assistive robotic devices.

Measurement of Hand Joint Angle Using Inertial-Based Motion Capture System

The inertial sensor motion capture system has significant advantages over the classical optical motion capture system, including its high versatility, portability, and affordability. However, its accuracy is over one order of magnitude lower than the optical system. The measurement error of the finger joint angle is mainly due to sensor drift and misalignment of sensor to finger segment. In this article, we propose a method that includes both orientation estimation and calibration for accurate joint angle estimation. Specifically, at first, the accuracy of the sensor orientation is greatly improved using the square root cubature Kalman filter (SRCKF) to fuse the magnetic and inertial measurement units (MIMUs) data. Second, the kinematic restrictions of the finger joints are used for initial and in-process calibration to achieve sensor-to-segment (StoS) calibration throughout the process. Finally, the difference between the orientation of the two adjacent segments is the joint angle. Experiments show that our proposed system improves joint measurement accuracy compared with the existing inertial sensor-based systems. Evaluation of ten participants showed that the average root mean square error (RMSE) of finger joint measurements is <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$5.5^{\circ }(\pm 4.0^{\circ })$ </tex-math></inline-formula> . Our proposed system provides accurate information in measuring hand joint angles and quantifying hand movement function in clinical practice.

Inter-rater and intra-rater reliability of finger goniometry measured from screenshots taken via video consultation.

The purpose of this study was to assess the intra- and inter-rater reliability of using screenshots and handheld manual goniometers to assess range of finger movements during video consultations. Twenty-seven hand therapists measured finger joint angles from four different screenshots using two different goniometers. Results were compared within and between participants using the intraclass correlation coefficient (ICC). The ICC grading for both intra- and inter-rater reliability was moderate to excellent for all joints and both goniometers. Clinicians can measure finger joint angles from a screenshot with good reliability. The protocol used in this study can be used in remote video consultations as a no-cost substitute for in-person goniometry.Level of evidence: II.

Liquid Metal-Based Flexible and Wearable Sensor for Functional Human-Machine Interface.

Rigid sensors are a mature type of sensor, but their poor deformation and flexibility limit their application range. The appearance and development of flexible sensors provide an opportunity to solve this problem. In this paper, a resistive flexible sensor utilizes gallium−based liquid metal (eutectic gallium indium alloy, EGaIn) and poly(dimethylsiloxane) (PDMS) and is fabricated using an injecting thin−line patterning technique based on soft lithography. Combining the scalable fabrication process and unique wire−shaped liquid metal design enables sensitive multifunctional measurement under stretching and bending loads. Furthermore, the flexible sensor is combined with the glove to demonstrate the application of the wearable sensor glove in the detection of finger joint angle and gesture control, which offers the ability of integration and multifunctional sensing of all−soft wearable physical microsystems for human–machine interfaces. It shows its application potential in medical rehabilitation, intelligent control, and so on.

Accurate Continuous Prediction of 14 Degrees of Freedom of the Hand from Myoelectrical Signals through Convolutive Deep Learning.

Natural control of assistive devices requires continuous positional encoding and decoding of the user's volition. Human movement is encoded by recruitment and rate coding of spinal motor units. Surface electromyography provides some information on the neural code of movement and is usually decoded into finger joint angles. However, the current approaches to mapping the electrical signal into joint angles are unsatisfactory. There are no methods that allow precise estimation of joint angles during natural hand movements within the large numbers of degrees of freedom of the hand. We propose a framework to train a neural network from digital cameras and high-density surface electromyography from the extrinsic (forearm and wrist) hand muscles. Furthermore, we show that our 3D convolutional neural network optimally predicted 14 functional flexion/extension joints of the hand. We found in our experiments (4 subjects; mean age of 26±2.12 years) that our model can predict individual sinusoidal finger movement at different speeds (0.5 and 1.5 Hz), as well as two and three finger pinching, and hand opening and closing, covering 14 degrees of freedom of the hand. Our deep learning method shows a mean absolute error of 2.78±0.28 degrees with a mean correlation coefficient between predicted and expected joint angles of 0.94, 95% confidence interval (CI) [0.81, 0.98] with simulated real-time inference times lower than 30 milliseconds. These results demonstrate that our approach is capable of predicting the user's volition similar to digital cameras through a non-invasive wearable neural interface. Clinical relevance- This method establishes a viable interface that can be used for both immersive virtual reality medical simulations environments and assistive devices such as exoskeleton and prosthetics.

초음파용 프로브 설계의 인간공학적 분석

Objective: The present study is intended to analyze the design characteristics of ultrasonic probes in different sizes and shapes and identify the preferred design characteristics by ergonomic evaluation.<BR><BR>Background: The use of an ultrasound probe among sonographers in improper postures with high repetitions for long periods of time has resulted in a high incidence of musculoskeletal symptoms and/or disorders.<BR><BR>Method: While sonographers (n = 12) simulated ultrasound scanning tasks with two linear array probes (small-flat, SF; large-curved, LC) in different sizes and shapes by applying forces of 20±4N, EMG activities, body motions, and grip postures were measured. After completing the ultrasound simulation tasks, a comparative evaluation of subjective satisfaction with the two probe designs was conducted.<BR><BR>Results: The SF probe required a larger range of motion at the elbow (up to 9.9° on average), higher RMS EMG levels (-1.8~48.4%) during the probe rotation task at the shoulder (pectoralis and infraspinatus), neck (right/left sterno-cleido-mastoid and trapezius), and upper-arm (biceps), and larger finger joint angles (-6.3~15.8°) than the LC probe.<BR><BR>Conclusion: The SF probe was preferred to the LC probe in terms of grip fit, the opposite was found in terms of the efficiency of force transfer.<BR><BR>Application: The analysis and evaluation methods of ultrasound probe design and the identification of the preferred design characteristics of linear array probe will be of use to develop ergonomic probe designs that can reduce musculoskeletal symptoms and disorders among sonographers.

Finger Movement Recognition via High-Density Electromyography of Intrinsic and Extrinsic Hand Muscles

Surface electromyography (sEMG) is commonly used to observe the motor neuronal activity within muscle fibers. However, decoding dexterous body movements from sEMG signals is still quite challenging. In this paper, we present a high-density sEMG (HD-sEMG) signal database that comprises simultaneously recorded sEMG signals of intrinsic and extrinsic hand muscles. Specifically, twenty able-bodied participants performed 12 finger movements under two paces and three arm postures. HD-sEMG signals were recorded with a 64-channel high-density grid placed on the back of hand and an 8-channel armband around the forearm. Also, a data-glove was used to record the finger joint angles. Synchronisation and reproducibility of the data collection from the HD-sEMG and glove sensors were ensured. The collected data samples were further employed for automated recognition of dexterous finger movements. The introduced dataset offers a new perspective to study the synergy between the intrinsic and extrinsic hand muscles during dynamic finger movements. As this dataset was collected from multiple participants, it also provides a resource for exploring generalized models for finger movement decoding.

Backhand-Approach-Based American Sign Language Words Recognition Using Spatial-Temporal Body Parts and Hand Relationship Patterns.

Most of the existing methods focus mainly on the extraction of shape-based, rotation-based, and motion-based features, usually neglecting the relationship between hands and body parts, which can provide significant information to address the problem of similar sign words based on the backhand approach. Therefore, this paper proposes four feature-based models. The spatial–temporal body parts and hand relationship patterns are the main feature. The second model consists of the spatial–temporal finger joint angle patterns. The third model consists of the spatial–temporal 3D hand motion trajectory patterns. The fourth model consists of the spatial–temporal double-hand relationship patterns. Then, a two-layer bidirectional long short-term memory method is used to deal with time-independent data as a classifier. The performance of the method was evaluated and compared with the existing works using 26 ASL letters, with an accuracy and F1-score of 97.34% and 97.36%, respectively. The method was further evaluated using 40 double-hand ASL words and achieved an accuracy and F1-score of 98.52% and 98.54%, respectively. The results demonstrated that the proposed method outperformed the existing works under consideration. However, in the analysis of 72 new ASL words, including single- and double-hand words from 10 participants, the accuracy and F1-score were approximately 96.99% and 97.00%, respectively.

Smart- textile strain sensor for human joint monitoring

With the revolutionary advancement of wearable electronics for human motion monitoring, it has become a keen interest for researchers to turn traditional textiles into precise strain sensors with high accuracy levels and broad-spectrum sensitivity. Therefore, it is considered an active measurement that avoids the misuse of a sensing system. Since these platforms become more ubiquitous, they began to enter the industrial scales such as the fitness and health sector. To do so, stability, user-friendly, cost-effective, and minimum step fabrication processes are imperative in practice. Targeting those goals, a highly efficient textile strain sensor from a crochet knitted elastic (CKE) band was prepared and integrated into a wearable human motion monitoring device systematically. A low-cost customized conductive graphite-polyurethane nanocomposite (G-PU) paste has been developed and applied to the modify CKE band through a dip-coating technique. Finally, an appropriate shape was designed for the estimation of movement and angle measurement of finger, wrist, and elbow belonging a gentle gauge factor (GF=26.8) with high mechanical stability (1000 cycles). The strain sensor was capable to distinguish finger, wrist, and elbow joint angle following the change of resistance dynamically, enabling such potential to be integrated further into a human-machine interface for real-time monitoring.

Continuous Estimation of Finger and Wrist Joint Angles Using a Muscle Synergy Based Musculoskeletal Model

Recently, many muscle synergy-based human motion prediction models and algorithms have been proposed. In this study, the muscle synergies extracted from electromyography (EMG) data were used to construct a musculoskeletal model (MSM) to predict the joint angles of the wrist, thumb, index finger, and middle finger. EMG signals were analyzed using independent component analysis to reduce signal noise and task-irrelevant artifacts. The weights of each independent component (IC) were converted into a heat map related to the motion pattern and compared with human anatomy to find a different number of ICs matching the motion pattern. Based on the properties of the MSM, non-negative matrix factorization was used to extract muscle synergies from selected ICs that represent the extensor and flexor muscle groups. The effects of these choices on the prediction accuracy was also evaluated. The performance of the model was evaluated using the correlation coefficient (CC) and normalized root-mean-square error (NRMSE). The proposed method has a higher prediction accuracy than those of traditional methods, with an average CC of 92.0% and an average NRMSE of 10.7%.

Explainable Deep Learning Model for EMG-Based Finger Angle Estimation Using Attention.

Electromyography (EMG) is one of the most common methods to detect muscle activities and intentions. However, it has been difficult to estimate accurate hand motions represented by the finger joint angles using EMG signals. We propose an encoder-decoder network with an attention mechanism, an explainable deep learning model that estimates 14 finger joint angles from forearm EMG signals. This study demonstrates that the model trained by the single-finger motion data can be generalized to estimate complex motions of random fingers. The color map result of the after-training attention matrix shows that the proposed attention algorithm enables the model to learn the nonlinear relationship between the EMG signals and the finger joint angles, which is explainable. The highly activated entries in the color map of the attention matrix derived from model training are consistent with the experimental observations in which certain EMG sensors are highly activated when a particular finger moves. In summary, this study proposes an explainable deep learning model that estimates finger joint angles based on EMG signals of the forearm using the attention mechanism.

Finger Joint Angle Estimation With Visual Attention for Rehabilitation Support: A Case Study of the Chopsticks Manipulation Test

Most East Asian rehabilitation centers offer chopsticks manipulation tests (CMT). In addition to impaired hand function, approximately two-thirds of stroke survivors have visual impairment related to eye movement. This article investigates the significance of combining finger joint angle estimation and a visual attention measurement in CMT. We present a multiscopic framework that consists of microscopic, mesoscopic, and macroscopic levels. We develop a feature extraction technique to extract the kinematic finger model at the microscopic level. At the mesoscopic level, we propose an active perception ability to detect the position and geometry of the finger on the chopsticks. The proposed framework estimates the proximal interphalangeal (PIP) joint angle on the index finger during CMT using fully connected cascade neural networks (FCC-NN). At the macroscopic level, we implement a cognitive ability by measuring visual attention during CMT. We further evaluate the proposed framework with a conventional test that counts the number of peanuts (NP) which are moved from one bowl to another using chopsticks within a particular time frame. For the evaluation, we introduce three parameters, namely joint angle estimation movement (JAEM), chopstick attention movement (CAM), and chopstick tip movement (CTM), by detecting the local minima and maxima of the signal. According to the experiment results, the velocity of these three parameters could indicate improvement in hand and eye function during CMT. We expect this study to benefit therapists and researchers by providing valuable information that is not accessible in the clinic. Code and datasets are available online at https://github.com/anom-tmu/cmt-attention.

Research on Double-U Tapered Pof Bending Sensor for the Measurement of Finger Joint Angle

Research on Double-U Tapered Pof Bending Sensor for the Measurement of Finger Joint Angle

Finger joint angle estimation based on sEMG signals by Attention-MLP

sEMG(Surface electromyography) signal was widely applied in human-machine interactive field, especially in robotic arm control. In this paper, we built the Attention-MLP (Multilayer Perceptron) model to implement a type of continuous joint angle estimation method based on sEMG for six grasp movements, we tested this model on Ninapro dataset and the average Pearson correlation coefficient (CC) and the average root mean square error (RMSE) of the proposed Attention-MLP method achieved 0.812±0.02 and 10.51±1.98; the average CC and RMSE of this method are better than Sparse Pseudo-input Gaussian processes (SPGP), its average CC and RMSE are 12.14±2.30 and 0.727±0.07. Compared with the traditional method SPGP, our model performed better on continuously estimation of ten main hand joint angles under 6 grip movements.

Estimating finger joint angles on surface EMG using Manifold Learning and Long Short-Term Memory with Attention mechanism

The success criteria of electromyography (EMG) rely on recognizing the pattern and correlating it to its target, especially in the regression task, which has become a popular topic in this decade because of its flexibility in accessing targets compared to classification tasks. Therefore, it will be beneficial when the methods used in stroke therapy devices require wide access to estimate flexion/extensions in the degree of freedom of fingers. Previous researchers have made many efforts to achieve accuracy and performance results in this regression task. Therefore, many variations of the regression method were found. However, the existed method combination brings drawbacks because the signals containing sparse samples and noise could make the regressor overfitting. For encountering this problem, this work deploys a Manifold Learning to handle sparse data and Long Short-Term Memory (LSTM) based attention mechanism as a regressor, distinguishing between time series data with different importance by allocating weights of Manifold Learning results. Besides applying those methods, this work compares with various combination techniques such as different preprocessing signals, feature extraction, dimensional reduction, and regressor that are widely used to determine the proposed investigated contribution various parameters applied according to a different combination of methods. The results show that the proposed methods outperform performance by getting 0.957 in the R-Square score. In addition, Manifold Learning as dimensional reduction contributes to the improvement of the performance in various parameters such as different feature domains and regressors.

WeHAPTIC-light: A cable slack-based compact hand force feedback system for virtual reality

Various force feedback devices for the hand have been developed for the virtual reality field, but many systems are heavy, and various functions have not been fully developed with respect to finger motion measurement and stiffness generation. We propose a light and wearable force feedback device that can measure finger motion without calibration and can implement different stiffnesses using a cable slack-based mechanism. The proposed system has a small weight of 298 g, using a 10 g motor. To measure finger motion without calibration, an equation for each finger joint angle is derived from the three-dimensional position and orientation information of the fingertip. To realize different stiffnesses, the proposed system connects a motor and a finger structure with a cable; zero impedance is realized by maintaining a slack. The adjustable cable slack mechanism ensures to restrict the finger motion when the fingertip touches the surface of a virtual object even in fast motion; different stiffnesses are realized by proportional control input to the motor according to the deformation of the virtual object. We manufactured a prototype for three fingers and experimentally verified the performance of the proposed system.

Development of a Low-Cost Wearable Data Glove for Capturing Finger Joint Angles.

Capturing finger joint angle information has important applications in human–computer interaction and hand function evaluation. In this paper, a novel wearable data glove is proposed for capturing finger joint angles. A sensing unit based on a grating strip and an optical detector is specially designed for finger joint angle measurement. To measure the angles of finger joints, 14 sensing units are arranged on the back of the glove. There is a sensing unit on the back of each of the middle phalange, proximal phalange, and metacarpal of each finger, except for the thumb. For the thumb, two sensing units are distributed on the back of the proximal phalange and metacarpal, respectively. Sensing unit response tests and calibration experiments are conducted to evaluate the feasibility of using the designed sensing unit for finger joint measurement. Experimental results of calibration show that the comprehensive precision of measuring the joint angle of a wooden finger model is 1.67%. Grasping tests and static digital gesture recognition experiments are conducted to evaluate the performance of the designed glove. We achieve a recognition accuracy of 99% by using the designed glove and a generalized regression neural network (GRNN). These preliminary experimental results indicate that the designed data glove is effective in capturing finger joint angles.

Flexible and highly sensitive ionic skins with multiple dielectric layers for finger joint bending angle monitoring

Finger joint motion monitoring is crucial for rehabilitation training and ergonomics. Based on a multilayer dielectric structure, this study proposed flexible and highly sensitive ionic skins (sensors) for the measurement of the bending angles of finger joints. Each ionic skin, consisting silicon rubber films (multiple dielectric layers) and highly stretchable ionic conductors, was attached to the finger joint surface. The capacitance change of the skin was captured and used to measure finger joint bending angles. On this basis, the relationship between angles and capacitance variations was established. The relationship agreed with the experimental results. Furthermore, the effect of number of dielectric layers on sensitivity and linearity was discussed. The experimental results indicated that an increase in the number of dielectric layers improved sensitivity but suppressed linearity. The proposed ionic skins provided higher sensitivity and linearity than other flexible sensors. The five-layer ionic skin was four times more sensitive than existing ionic skins. The results confirmed that the multilayer dielectric structure of our ionic skins substantially enhanced the sensitivity for finger joint bending angle measurements.

Emerging Wearable Interfaces and Algorithms for Hand Gesture Recognition: A Survey.

Hands are vital in a wide range of fundamental daily activities, and neurological diseases that impede hand function can significantly affect quality of life. Wearable hand gesture interfaces hold promise to restore and assist hand function and to enhance human-human and human-computer communication. The purpose of this review is to synthesize current novel sensing interfaces and algorithms for hand gesture recognition, and the scope of applications covers rehabilitation, prosthesis control, exoskeletons for augmentation, sign language recognition, human-computer interaction, and user authentication. Results showed that electrical, mechanical, acoustical/vibratory, and optical sensing were the primary input modalities in gesture recognition interfaces. Two categories of algorithms were identified: 1) classification algorithms for predefined, fixed hand poses and 2) regression algorithms for continuous finger and wrist joint angles. Conventional machine learning algorithms, including linear discriminant analysis, support vector machines, random forests, and non-negative matrix factorization, have been widely used for a variety of gesture recognition applications, and deep learning algorithms have more recently been applied to further facilitate the complex relationship between sensor signals and multi-articulated hand postures. Future research should focus on increasing recognition accuracy with larger hand gesture datasets, improving reliability and robustness for daily use outside of the laboratory, and developing softer, less obtrusive interfaces.