Design of sensing system for experimental modeling of soft actuator applied for finger rehabilitation

Robotica ◽  
2021 ◽  
pp. 1-21
Author(s):  
Shokoufeh Davarzani ◽  
Mohammad Ali Ahmadi-Pajouh ◽  
Hamed Ghafarirad
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Index Finger ◽  
Experimental Models ◽  
Measurement Unit ◽  
Fusion Algorithm ◽  
Soft Actuator ◽  
Sensing System ◽  
Bending Actuator ◽  
Artificial Neural

Abstract Safe interaction and inherent compliance with soft robots have motivated the evolution of soft rehabilitation robots. Among these, soft robotic gloves are known as an effective tool for stroke rehabilitation. This research proposed a pneumatically actuated soft robotic for index finger rehabilitation. The proposed system consists of a soft bending actuator and a sensing system equipped with four inertial measurement unit sensors to generate kinematic data of the index finger. The designed sensing system can estimate the range of motion (ROM) of the finger’s joints by combining angular velocity and acceleration values with the standard Kalman filter. The sensing system is evaluated regarding repeatability and reliability through static and dynamic experiments in the first step. The root mean square error attained in static and dynamic states are 2 $^\circ$ and 3 $^\circ$ , sequentially, representing an efficient function of the fusion algorithm. In the next step, experimental models have been developed to analyze and predict a soft actuator’s behavior in free and constrained states using the sensing system’s data. Thus, parametric system identification methods, artificial neural network—multilayer perceptron (ANN-MLP), and artificial neural network—radial basis function algorithms (ANN-RBF) have been compared to achieve an optimal model. The results reveal that ANN models, particularly RBF ones, can predict the actuator behavior with reasonable accuracy in the free and constrained state (<1 $^\circ$ ). Hence, the need for intricate analytical modeling and material characterization will be eliminated, and controlling the soft actuator will be more practical. Besides, it assesses the ROM and finger functionality.

scholarly journals Artificial Neural Network Analyzing Wearable Device Gait Data for Identifying Patients With Stroke Unable to Return to Work

2021 ◽  
Vol 12 ◽  
Author(s):  
Marco Iosa ◽  
Edda Capodaglio ◽  
Silvia Pelà ◽  
Benedetta Persechino ◽  
Giovanni Morone ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Return To Work ◽  
Measurement Unit ◽  
Walking Ability ◽  
Double Support ◽  
Important Input ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

A potential dramatic effect of long-term disability due to stroke is the inability to return to work. An accurate prognosis and the identification of the parameters inflating the possibility of return to work after neurorehabilitation are crucial. Many factors may influence it, such as mobility and, in particular, walking ability. In this pilot study, two emerging technologies have been combined with the aim of developing a prognostic tool for identifying patients able to return to work: a wearable inertial measurement unit for gait analysis and an artificial neural network (ANN). Compared with more conventional statistics, the ANN showed a higher accuracy in identifying patients with respect to healthy subjects (90.9 vs. 75.8%) and also in identifying the subjects unable to return to work (93.9 vs. 81.8%). In this last analysis, the duration of double support phase resulted the most important input of the ANN. The potentiality of the ANN, developed also in other fields such as marketing on social networks, could allow a powerful support for clinicians that today should manage a large amount of instrumentally recorded parameters in patients with stroke.

scholarly journals Artificial Neural Network Solution for Anomalous Operation Detection in Power Systems

2021 ◽  
Author(s):  
Nathan Elias Maruch Barreto ◽  
Ciro Monteiro Baer ◽  
Mateus Jaensen Daros ◽  
Marlon Alexsandro Fritzen ◽  
Guilherme Schneider de Oliveira ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Power Systems ◽  
Power System ◽  
Test System ◽  
Measurement Unit ◽  
Two Phase ◽  
Advantages And Disadvantages ◽  
Phasor Measurement ◽  
Artificial Neural

This paper presents an anomalous operation detection system for power systems using the artificial neural network approach while discussing its advantages and disadvantages. The initial data for the proposed technique is a set of simulated post-fault bus voltages and currents obtained in a sampling rate so as to emulate a phasor measurement unit network. Several types of faults are dealt with, such as three-phase to ground, two-phase, two-phase to ground and single-phase to the ground as well as line and load contingencies. All fault and steady-state simulations were performed on MATLAB using Graham Rogers’ Power System Toolbox. The artificial neural network was designed on MATLAB, using an architecture proper for pattern recognition with supervised learning and obtaining high accuracy predictions within a short amount of time. The test system used in all simulations is the IEEE 39-Bus New England Power System, which presents 10 generation units, 21 loads and three distinct areas alongside transient and sub transient models, with phasor measurement units in 14 buses. Future works are discussed, showing the possibilities for feature engineering in this type of problem, fault type detection and fault location in operation using analogous dataset and neural network structures.

scholarly journals Optimized Dose of Dendritic Cell-based Vaccination in Experimental Model of Tumor Using Artificial Neural Network

2020 ◽  
Author(s):  
Zahra Mirsanei ◽  
Sima Habibi ◽  
Nasim Kheshtchin ◽  
Reza Mirzaei ◽  
Samane Arab ◽  
...  
Keyword(s):  
Neural Network ◽  
Immune Response ◽  
Artificial Neural Network ◽  
Tumor Microenvironment ◽  
Tumor Growth ◽  
Experimental Models ◽  
Optimal Dosage ◽  
Ann Model ◽  
Dc Vaccine ◽  
Artificial Neural

Previous studies have demonstrated that maturation of dendritic cells (DCs) by pathogenic components through pathogen-associated molecular patterns (PAMPs) such as Listeria monocytogenes lysate (LML) or CpG DNA can improve cancer vaccination in experimental models. In this study, a mathematical model based on an artificial neural network (ANN) was used to predict several patterns and dosage of matured DC administration for improved vaccination. The ANN model predicted that repeated co-injection of tumor antigen (TA)-loaded DCs matured with CpG (CpG-DC) and LML (List-DC) results in improved antitumor immune response as well as a reduction of immunosuppression in the tumor microenvironment. In the present study, we evaluated the ANN prediction accuracy about DC-based cancer vaccines pattern in the treatment of Wehi164 fibrosarcoma cancer-bearing mice. Our results showed that the administration of the DC vaccine according to ANN predicted pattern, leads to a decrease in the rate of tumor growth and size and augments CTL effector function. Furthermore, gene expression analysis confirmed an augmented immune response in the tumor microenvironment. Experimentations justified the validity of the ANN model forecast in the tumor growth and novel optimal dosage that led to more effective treatment.

scholarly journals Detection of Gait Modes Using an Artificial Neural Network during Walking with a Powered Ankle-Foot Orthosis

2016 ◽  
Vol 2016 ◽  
pp. 1-9 ◽  
Author(s):  
Mazharul Islam ◽  
Elizabeth T. Hsiao-Wecksler
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Success Rate ◽  
Measurement Unit ◽  
Data Set ◽  
Ankle Foot Orthosis ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
The Right ◽  
Foot Orthosis

This paper presents an algorithm, for use with a Portable Powered Ankle-Foot Orthosis (i.e., PPAFO) that can automatically detect changes in gait modes (level ground, ascent and descent of stairs or ramps), thus allowing for appropriate ankle actuation control during swing phase. An artificial neural network (ANN) algorithm used input signals from an inertial measurement unit and foot switches, that is, vertical velocity and segment angle of the foot. Output from the ANN was filtered and adjusted to generate a final data set used to classify different gait modes. Five healthy male subjects walked with the PPAFO on the right leg for two test scenarios (walking over level ground and up and down stairs or a ramp; three trials per scenario). Success rate was quantified by the number of correctly classified steps with respect to the total number of steps. The results indicated that the proposed algorithm’s success rate was high (99.3%, 100%, and 98.3% for level, ascent, and descent modes in the stairs scenario, respectively; 98.9%, 97.8%, and 100% in the ramp scenario). The proposed algorithm continuously detected each step’s gait mode with faster timing and higher accuracy compared to a previous algorithm that used a decision tree based on maximizing the reliability of the mode recognition.

scholarly journals An integrated artificial neural network–unscented Kalman filter vehicle sideslip angle estimation based on inertial measurement unit measurements

2018 ◽  
Vol 233 (7) ◽  
pp. 1864-1878 ◽  
Author(s):  
Tommaso Novi ◽  
Renzo Capitani ◽  
Claudio Annicchiarico
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Kalman Filter ◽  
Inertial Measurement Unit ◽  
Unscented Kalman Filter ◽  
Kinematic Model ◽  
Numerical Data ◽  
Measurement Unit ◽  
Sideslip Angle ◽  
Artificial Neural

Vehicle dynamics stability control systems rely on the amount of so-called sideslip angle and yaw rate. As the sideslip angle can be measured directly only with very expensive sensors, its estimation has been widely studied in the literature. Because of the large non-linearities and uncertainties in the dynamics, model-based methods are not a good solution to estimate the sideslip angle. On the contrary, machine learning techniques require large datasets that cover the entire working range for a correct estimation. In this paper, we propose an integrated artificial neural network and unscented Kalman filter observer using only inertial measurement unit measurements, which can work as a standalone sensor. The artificial neural network is trained solely with numerical data obtained with a Vi-Grade model and outputs a pseudo-sideslip angle which is used as input for the unscented Kalman filter. This is based on a kinematic model making the filter completely transparent to model uncertainty. A direct integration with integral damping and integral reset value allows the estimation of the longitudinal velocity of the kinematic model. A modification strategy of the pseudo-sideslip angle is then proposed to improve the convergence of the filter’s output. The algorithm is tested on both numerical data and experimental data. The results show the effectiveness of the solution.

Sign in / Sign up

Export Citation Format

Share Document