Self-Calibration Algorithm for a Pressure Sensor with a Real-Time Approach Based on an Artificial Neural Network

Deciphering Optimal Radar Ensemble for Advancing Sleep Posture Prediction through Multiview Convolutional Neural Network (MVCNN) Approach Using Spatial Radio Echo Map (SREM)

Assessing sleep posture, a critical component in sleep tests, is crucial for understanding an individual's sleep quality and identifying potential sleep disorders. However, monitoring sleep posture has traditionally posed significant challenges due to factors such as low light conditions and obstructions like blankets. The use of radar technolsogy could be a potential solution. The objective of this study is to identify the optimal quantity and placement of radar sensors to achieve accurate sleep posture estimation. We invited 70 participants to assume nine different sleep postures under blankets of varying thicknesses. This was conducted in a setting equipped with a baseline of eight radars-three positioned at the headboard and five along the side. We proposed a novel technique for generating radar maps, Spatial Radio Echo Map (SREM), designed specifically for data fusion across multiple radars. Sleep posture estimation was conducted using a Multiview Convolutional Neural Network (MVCNN), which serves as the overarching framework for the comparative evaluation of various deep feature extractors, including ResNet-50, EfficientNet-50, DenseNet-121, PHResNet-50, Attention-50, and Swin Transformer. Among these, DenseNet-121 achieved the highest accuracy, scoring 0.534 and 0.804 for nine-class coarse- and four-class fine-grained classification, respectively. This led to further analysis on the optimal ensemble of radars. For the radars positioned at the head, a single left-located radar proved both essential and sufficient, achieving an accuracy of 0.809. When only one central head radar was used, omitting the central side radar and retaining only the three upper-body radars resulted in accuracies of 0.779 and 0.753, respectively. This study established the foundation for determining the optimal sensor configuration in this application, while also exploring the trade-offs between accuracy and the use of fewer sensors.

Modeling and Calibration of Pressure-Sensing Insoles via a New Plenum-Based Chamber

This paper proposes a novel method to reliably calibrate a pair of sensorized insoles utilizing an array of capacitive tactile pixels (taxels). A new calibration setup is introduced that is scalable and suitable for multiple kinds of wearable sensors and a procedure for the simultaneous calibration of each of the sensors in the insoles is presented. The calibration relies on a two-step optimization algorithm that, firstly, enables determination of a relevant set of mathematical models based on the instantaneous measurement of the taxels alone, and, then, expands these models to include the relevant portion of the time history of the system. By comparing the resulting models with our previous work on the same hardware, we demonstrate the effectiveness of the novel method both in terms of increased ability to cope with the non-linear characteristics of the sensors and increased pressure ranges achieved during the experiments performed.

Artificial Neural Network Approach to Guarantee the Positioning Accuracy of Moving Robots by Using the Integration of IMU/UWB with Motion Capture System Data Fusion

This study presents an effective artificial neural network (ANN) approach to combine measurements from inertial measurement units (IMUs) and time-of-flight (TOF) measurements from an ultra-wideband (UWB) system with OptiTrack Motion Capture System (OptiT-MCS) data to guarantee the positioning accuracy of motion tracking in indoor environments. The proposed fusion approach unifies the following advantages of both technologies: high data rates from the MCS, and global translational precision from the inertial measurement unit (IMU)/UWB localization system. Consequently, it leads to accurate position estimates when compared with data from the IMU/UWB system relative to the OptiT-MCS reference system. The calibrations of the positioning IMU/UWB and MCS systems are utilized in real-time movement with a diverse set of motion recordings using a mobile robot. The proposed neural network (NN) approach experimentally revealed accurate position estimates, giving an enhancement average mean absolute percentage error (MAPE) of 17.56% and 7.48% in the X and Y coordinates, respectively, and the coefficient of correlation R greater than 99%. Moreover, the experimental results prove that the proposed NN fusion is capable of maintaining high accuracy in position estimates while preventing drift errors from increasing in an unbounded manner, implying that the proposed approach is more effective than the compared approaches.

Large-Area and Low-Cost Force/Tactile Capacitive Sensor for Soft Robotic Applications

This paper presents a novel design and development of a low-cost and multi-touch sensor based on capacitive variations. This new sensor is very flexible and easy to fabricate, making it an appropriate choice for soft robot applications. Materials (conductive ink, silicone, and control boards) used in this sensor are inexpensive and easily found in the market. The proposed sensor is made of a wafer of different layers, silicone layers with electrically conductive ink, and a pressure-sensitive conductive paper sheet. Previous approaches like e-skin can measure the contact point or pressure of conductive objects like the human body or finger, while the proposed design enables the sensor to detect the object's contact point and the applied force without considering the material conductivity of the object. The sensor can detect five multi-touch points at the same time. A neural network architecture is used to calibrate the applied force with acceptable accuracy in the presence of noise, variation in gains, and non-linearity. The force measured in real time by a commercial precise force sensor (ATI) is mapped with the produced voltage obtained by changing the layers' capacitance between two electrode layers. Finally, the soft robot gripper embedding the suggested tactile sensor is utilized to grasp an object with position and force feedback signals.

Machine Learning Methods of Regression for Plasmonic Nanoantenna Glucose Sensing

The measurement and quantification of glucose concentrations is a field of major interest, whether motivated by potential clinical applications or as a prime example of biosensing in basic research. In recent years, optical sensing methods have emerged as promising glucose measurement techniques in the literature, with surface-enhanced infrared absorption (SEIRA) spectroscopy combining the sensitivity of plasmonic systems and the specificity of standard infrared spectroscopy. The challenge addressed in this paper is to determine the best method to estimate the glucose concentration in aqueous solutions in the presence of fructose from the measured reflectance spectra. This is referred to as the inverse problem of sensing and usually solved via linear regression. Here, instead, several advanced machine learning regression algorithms are proposed and compared, while the sensor data are subject to a pre-processing routine aiming to isolate key patterns from which to extract the relevant information. The most accurate and reliable predictions were finally made by a Gaussian process regression model which improves by more than 60% on previous approaches. Our findings give insight into the applicability of machine learning methods of regression for sensor calibration and explore the limitations of SEIRA glucose sensing.

Victory Prediction of Ladies Professional Golf Association Players: Influential Factors and Comparison of Prediction Models

This study aims to identify the most accurate prediction model for the possibility of victory from the annual average data of 25 seasons (1993–2017) of the Ladies Professional Golf Association (LPGA), and to determine the importance of the predicting factors. The four prediction models considered in this study were a decision tree, discriminant analysis, logistic regression, and artificial neural network analysis. The mean difference in the classification accuracy of these models was analyzed using SPSS 22.0 software (IBM Corp., Armonk, NY, USA) and the one-way analysis of variance (ANOVA). When the prediction was based on technical variables, the most important predicting variables for determining victory were greens in regulation (GIR) and putting average (PA) in all four prediction models. When the prediction was based on the output of the technical variables, the most important predicting variable for determining victory was birdies in all four prediction models. When the prediction was based on the season outcome, the most important predicting variables for determining victory were the top 10 finish% (T10) and official money. A significant mean difference in classification accuracy was observed while performing the one-way ANOVA, and the least significant difference post-hoc test showed that artificial neural network analysis exhibited higher accuracy than the other models, especially, for larger data sizes. From the results of this study, it can be inferred that the player who wants to win the LPGA should aim to increase GIR, reduce PA, and improve driving distance and accuracy through training to increase the birdies chance at each hole, which can lead to lower average strokes and increased possibility of being within T10.

A Review on Upper Limb Rehabilitation Robots

Rehabilitation is the process of treating post-stroke consequences. Impaired limbs are considered the common outcomes of stroke, which require a professional therapist to rehabilitate the impaired limbs and restore fully or partially its function. Due to the shortage in the number of therapists and other considerations, researchers have been working on developing robots that have the ability to perform the rehabilitation process. During the last two decades, different robots were invented to help in rehabilitation procedures. This paper explains the types of rehabilitation treatments and robot classifications. In addition, a few examples of well-known rehabilitation robots will be explained in terms of their efficiency and controlling mechanisms.

Inconsistency Calibrating Algorithms for Large Scale Piezoresistive Electronic Skin

In the field of safety and communication of human-robot interaction (HRI), using large-scale electronic skin will be the tendency in the future. The force-sensitive piezoresistive material is the key for piezoresistive electronic skin. In this paper, a non-array large scale piezoresistive tactile sensor and its corresponding calibration methods were presented. Because of the creep inconsistency of large scale piezoresistive material, a creep tracking compensation method based on K-means clustering and fuzzy pattern recognition was proposed to improve the detection accuracy. With the compensated data, the inconsistency and nonlinearity of the sensor was calibrated. The calibration process was divided into two parts. The hierarchical clustering algorithm was utilized firstly to classify and fuse piezoresistive property of different regions over the whole sensor. Then, combining the position information, the force detection model was constructed by Back-Propagation (BP) neural network. At last, a novel flexible tactile sensor for detecting contact position and force was designed as an example and tested after being calibrated. The experimental results showed that the calibration methods proposed were effective in detecting force, and the detection accuracy was improved.

Micrometer Backstepping Control System for Linear Motion Single Axis Robot Machine Drive

In order to cut down influence on the uncertainty disturbances of a linear motion single axis robot machine, such as the external load force, the cogging force, the column friction force, the Stribeck force, and the parameters variations, the micrometer backstepping control system, using an amended recurrent Gottlieb polynomials neural network and altered ant colony optimization (AACO) with the compensated controller, is put forward for a linear motion single axis robot machine drive system mounted on the linear-optical ruler with 1 um resolution. To achieve high-precision control performance, an adaptive law of the amended recurrent Gottlieb polynomials neural network based on the Lyapunov function is proposed to estimate the lumped uncertainty. Besides this, a novel error-estimated law of the compensated controller is also proposed to compensate for the estimated error between the lumped uncertainty and the amended recurrent Gottlieb polynomials neural network with the adaptive law. Meanwhile, the AACO is used to regulate two variable learning rates in the weights of the amended recurrent Gottlieb polynomials neural network to speed up the convergent speed. The main contributions of this paper are: (1) The digital signal processor (DSP)-based current-regulation pulse width modulation (PWM) control scheme being successfully applied to control the linear motion single axis robot machine drive system; (2) the micrometer backstepping control system using an amended recurrent Gottlieb polynomials neural network with the compensated controller being successfully derived according to the Lyapunov function to diminish the lumped uncertainty effect; (3) achieving high-precision control performance, where an adaptive law of the amended recurrent Gottlieb polynomials neural network based on the Lyapunov function is successfully applied to estimate the lumped uncertainty; (4) a novel error-estimated law of the compensated controller being successfully used to compensate for the estimated error; and (5) the AACO being successfully used to regulate two variable learning rates in the weights of the amended recurrent Gottlieb polynomials neural network to speed up the convergent speed. Finally, the effectiveness of the proposed control scheme is also verified by the experimental results.

Neural Network Direct Control with Online Learning for Shape Memory Alloy Manipulators

New actuators and materials are constantly incorporated into industrial processes, and additional challenges are posed by their complex behavior. Nonlinear hysteresis is commonly found in shape memory alloys, and the inclusion of a suitable hysteresis model in the control system allows the controller to achieve a better performance, although a major drawback is that each system responds in a unique way. In this work, a neural network direct control, with online learning, is developed for position control of shape memory alloy manipulators. Neural network weight coefficients are updated online by using the actuator position data while the controller is applied to the system, without previous training of the neural network weights, nor the inclusion of a hysteresis model. A real-time, low computational cost control system was implemented; experimental evaluation was performed on a 1-DOF manipulator system actuated by a shape memory alloy wire. Test results verified the effectiveness of the proposed control scheme to control the system angular position, compensating for the hysteretic behavior of the shape memory alloy actuator. Using a learning algorithm with a sine wave as reference signal, a maximum static error of 0.83° was achieved when validated against several set-points within the possible range.

A Deep Neural Network Based Model for a Kind of Magnetorheological Dampers

In this paper, a deep neural network based model for a set of small-scale magnetorheological dampers (MRD) is developed where relevant parameters that have a physical meaning are inputs to the model. An experimental platform and a 3D-printing rapid prototyping facility provided a set of different conditions including MRD filled with two different MR fluids, which were used to train a Deep Neural Network (DNN), which is the core of the proposed model. Testing results indicate the model could forecast the hysteretic response of magnetorheological dampers for different load conditions and various physical configurations.

Precision Motion Control of a Linear Permanent Magnet Synchronous Machine Based on Linear Optical-Ruler Sensor and Hall Sensor

The linear optical-ruler sensor with 1 μm precision mounted in the linear permanent magnet synchronous machine (LPMSM) is used for measuring the mover position of LPMSM in order to enhance the precision of a measured mover position. Due to nonlinear friction and uncertainty effects, linear controllers are very hard to achieve good mover positioning of LPMSM. The proposed adaptive amended Elman neural network backstepping (AAENNB) control system is adopted for controlling the LPMSM drive system to bring about the mover positioning precision of LPMSM. Firstly, a backstepping scheme is posed for controlling the tracing motion of the LPMSM drive system. The proposed backstepping control system, which is applied in the mover position of the LPMSM drive system, possesses better dynamic control performance and robustness to uncertainties for the tracing trajectories. Because of the LPMSM with nonlinear and time-varying dynamic characteristics, an adaptive amended Elman neural network uncertainty observer (AAENNUO) is posed to estimate the required lumped uncertainty. According to the Lyapunov stability theorem, on-line parameter training methodology of the amended Elman neural network (AENN) can be derived by use of adaptive law. The error estimated law is proposed to compensate for the observed error induced by the AENN with adaptive law. Furthermore, to help improve convergence and to obtain better learning performance, the mended particle swarm optimization (PSO) algorithm is utilized for adjusting the varied learning rate of the weights in the AENN. At last, these experimental results, which show better performance, are verified by the proposed control system.