Transmission Line Fault Classification Based on the Combination of Scaled Wavelet Scalograms and CNNs Using a One-Side Sensor for Data Collection.

This research focuses on leveraging wavelet transform for fault classification within electrical power transmission networks. This study meticulously examines the influence of various parameters, such as fault resistance, fault inception angle, fault location, and other essential components, on the accuracy of fault classification. We endeavor to explore the interplay between classification accuracy and the input data while assessing the efficacy of combining wavelet analysis with deep learning methodologies. The data, sourced from network recorders, including phase currents and voltages, undergo a scaled continuous wavelet transform (S-CWT) to generate scalogram images. These images are subsequently utilized as inputs for pretrained deep learning models. The experiments encompass various fault scenarios, spanning distinct fault types, locations, times, and resistance values. A remarkable feature of the proposed work is the attainment of 100% classification accuracy, obviating the need for additional algorithmic enhancements. The foundation of this achievement is the deliberate selection of the right input. The decision to employ an identical number of samples as the number of scales for the CWT emerges as a pivotal factor. This approach underpins the high accuracy and renders supplementary algorithms superfluous. Furthermore, this research underscores the versatility of this approach, showcasing its effectiveness across diverse networks and scenarios. Wavelet transform, after rigorous experimentation, emerges as a reliable tool for capturing transient fault characteristics with an optimal balance between time and frequency resolutions.

Passive Exercise Adaptation for Ankle Rehabilitation Based on Learning Control Framework.

Ankle injuries are among the most common injuries in sport and daily life. However, for their recovery, it is important for patients to perform rehabilitation exercises. These exercises are usually done with a therapist's guidance to help strengthen the patient's ankle joint and restore its range of motion. However, in order to share the load with therapists so that they can offer assistance to more patients, and to provide an efficient and safe way for patients to perform ankle rehabilitation exercises, we propose a framework that integrates learning techniques with a 3-PRS parallel robot, acting together as an ankle rehabilitation device. In this paper, we propose to use passive rehabilitation exercises for dorsiflexion/plantar flexion and inversion/eversion ankle movements. The therapist is needed in the first stage to design the exercise with the patient by teaching the robot intuitively through learning from demonstration. We then propose a learning control scheme based on dynamic movement primitives and iterative learning control, which takes the designed exercise trajectory as a demonstration (an input) together with the recorded forces in order to reproduce the exercise with the patient for a number of repetitions defined by the therapist. During the execution, our approach monitors the sensed forces and adapts the trajectory by adding the necessary offsets to the original trajectory to reduce its range without modifying the original trajectory and subsequently reducing the measured forces. After a predefined number of repetitions, the algorithm restores the range gradually, until the patient is able to perform the originally designed exercise. We validate the proposed framework with both real experiments and simulation using a Simulink model of the rehabilitation parallel robot that has been developed in our lab.

Non-Contact, Simple Neonatal Monitoring by Photoplethysmography.

This paper presents non-contact vital sign monitoring in neonates, based on image processing, where a standard color camera captures the plethysmographic signal and the heart and breathing rates are processed and estimated online. It is important that the measurements are taken in a non-invasive manner, which is imperceptible to the patient. Currently, many methods have been proposed for non-contact measurement. However, to the best of the authors' knowledge, it has not been possible to identify methods with low computational costs and a high tolerance to artifacts. With the aim of improving contactless measurement results, the proposed method based on the computer vision technique is enhanced to overcome the mentioned drawbacks. The camera is attached to an incubator in the Neonatal Intensive Care Unit and a single area in the neonate's diaphragm is monitored. Several factors are considered in the stages of image acquisition, as well as in the plethysmographic signal formation, pre-filtering and filtering. The pre-filter step uses numerical analysis techniques to reduce the signal offset. The proposed method decouples the breath rate from the frequency of sinus arrhythmia. This separation makes it possible to analyze independently any cardiac and respiratory dysrhythmias. Nine newborns were monitored with our proposed method. A Bland-Altman analysis of the data shows a close correlation of the heart rates measured with the two approaches (correlation coefficient of 0.94 for heart rate (HR) and 0.86 for breath rate (BR)) with an uncertainty of 4.2 bpm for HR and 4.9 for BR (k = 1). The comparison of our method and another non-contact method considered as a standard independent component analysis (ICA) showed lower central processing unit (CPU) usage for our method (75% less CPU usage).

Practical Use of Robot Manipulators as Intelligent Manufacturing Systems.

This paper presents features and advanced settings for a robot manipulator controller in a fully interconnected intelligent manufacturing system. Every system is made up of different agents. As also occurs in the Internet of Things and smart cities, the big issue here is to ensure not only that implementation is key, but also that there is better common understanding among the main players. The commitment of all agents is still required to translate that understanding into practice in Industry 4.0. Mutual interactions such as machine-to-machine and man-to-machine are solved in real time with cyber physical capabilities. This paper explores intelligent manufacturing through the context of industrial robot manipulators within a Smart Factory. An online communication algorithm with proven intelligent manufacturing abilities is proposed to solve real-time interactions. The algorithm is developed to manage and control all robot parameters in real-time. The proposed tool in conjunction with the intelligent manufacturing core incorporates data from the robot manipulators into the industrial big data to manage the factory. The novelty is a communication tool that implements the Industry 4.0 standards to allow communications among the required entities in the complete system. It is achieved by the developed tool and implemented in a real robot and simulation.

A novel pyrogallol red-based assay to assess catalase activity: Optimization by response surface methodology.

Pyrogallol red (PGR) was identified as a novel optical probe for the detection of hydrogen peroxide (H2O2) based on horseradish peroxidase (HRP)-catalyzed oxidation. Response surface methodology (RSM) was applied as a tool to optimize the concentrations of PGR (100µmolL-1), HRP (1UmL-1) and H2O2 (250µmolL-1) and used to develop a sensitive PGR-based catalase (CAT) activity assay (PGR-CAT assay). N-ethylmaleimide -NEM- (102mmolL-1) was used to avoid interference produced by thiol groups while protecting CAT activity. Incubation time (30min) for samples or CAT used as standard and H2O2 as well as signal stability (stable between 5 and 60min) were also evaluated. PGR-CAT assay was linear within the range of 0-4UmL-1 (R2=0.993) and very sensitive with limits of detection (LOD) of 0.005UmL-1 and quantitation (LOQ) of 0.01UmL-1. PGR-CAT assay showed an adequate intra-day RSD=0.6-9.5% and inter-day RSD=2.4-8.9%. Bland-Altman analysis and Passing-Bablok and Pearson correlation analysis showed good agreement between CAT activity as measured by the PRG-CAT assay and the Amplex Red assay. The PGR-CAT assay is more sensitive than all the other colorimetric assays reported, particularly the Amplex Red assay, and the cost of PGR is a small fraction (about 1/1000) of that of an Amplex Red probe, so it can be expected to find wide use among scientists studying CAT activity in biological samples.

A novel high-throughput image based rapid Folin-Ciocalteau assay for assessment of reducing capacity in foods.

The aim of the presented work was to develop and validate a novel high-throughput rapid Folin-Ciocalteau assay for the quantification of reducing capacity of foods based on image scanner (Image-F-C assay). The original rapid F-C assay using a 96-well plate was improved by adding a neutralization step that stabilizes the formed color, enabling image acquisition using a flatbed scanner. Although the scanner has been already used in other analytical applications, no analysis has been reported regarding the effect of the scanner model, the plate orientation or the reaction volume. In the present study, we establish that the mentioned parameters do affect the linearity and precision of image based Folin-Ciocalteau assay, and provide the optimal scanning conditions for the analyzed scanner models. Euclidean distance calculated from R (Red), G (Green) and B (Blue) values was chosen, based on linearity and sensitivity, in order to quantify the reducing capacity. An in-house program using free ImageJ macro language was written to calculate automatically the RGB values of each well. The Image-F-C assay is linear within the range of 0-20 mg L(-1) of gallic acid (R(2)≥0.9939). We compared reducing capacity values from real samples quantified by the image F-C assay and by a microplate reader and an inter-day relative standard error<8% was observed. Bland-Altman and correlation analyzes showed that there were no significant differences between the two methods.

Prediction of fermentation index of cocoa beans (Theobroma cacao L.) based on color measurement and artificial neural networks.

Several procedures are currently used to assess fermentation index (FI) of cocoa beans (Theobroma cacao L.) for quality control. However, all of them present several drawbacks. The aim of the present work was to develop and validate a simple image based quantitative procedure, using color measurement and artificial neural network (ANNs). ANN models based on color measurements were tested to predict fermentation index (FI) of fermented cocoa beans. The RGB values were measured from surface and center region of fermented beans in images obtained by camera and desktop scanner. The FI was defined as the ratio of total free amino acids in fermented versus non-fermented samples. The ANN model that included RGB color measurement of fermented cocoa surface and R/G ratio in cocoa bean of alkaline extracts was able to predict FI with no statistical difference compared with the experimental values. Performance of the ANN model was evaluated by the coefficient of determination, Bland-Altman plot and Passing-Bablok regression analyses. Moreover, in fermented beans, total sugar content and titratable acidity showed a similar pattern to the total free amino acid predicted through the color based ANN model. The results of the present work demonstrate that the proposed ANN model can be adopted as a low-cost and in situ procedure to predict FI in fermented cocoa beans through apps developed for mobile device.

Tracking moving optima using Kalman-based predictions.

The dynamic optimization problem concerns finding an optimum in a changing environment. In the field of evolutionary algorithms, this implies dealing with a time-changing fitness landscape. In this paper we compare different techniques for integrating motion information into an evolutionary algorithm, in the case it has to follow a time-changing optimum, under the assumption that the changes follow a nonrandom law. Such a law can be estimated in order to improve the optimum tracking capabilities of the algorithm. In particular, we will focus on first order dynamical laws to track moving objects. A vision-based tracking robotic application is used as testbed for experimental comparison.

Dynamic biomechanical model for assessing and monitoring robot-assisted upper-limb therapy.

This article describes the design, validation, and application of a dynamic biomechanical model that assesses and monitors trajectory, position, orientation, force, and torque generated by upper-limb (UL) movement during robot-assisted therapy. The model consists of two links that represent the upper arm and forearm, with 5 degrees of freedom (DOF) for the shoulder and elbow joints. The model is a useful tool for enhancing the functionality of poststroke robot-assisted UL therapy. The individualized inertial segment parameters were based on anthropometric measurements. The model performed inverse dynamic analysis of UL movements to calculate reaction forces and moments acting about the 3-DOF shoulder and 2-DOF elbow joints. Real-time fused biofeedback of a 6-DOF force sensor and three-dimensional (3-D) pose sensors supported the model validation and application. The force sensor was mounted between the robot manipulator and the subject's wrist, while the 3-D pose sensors were fixed at specific positions on the subject's UL segments. The model input and output parameters were stored in the subject's database, which is part of the rehabilitation information system. We assigned 20 nondisabled subjects three different therapy exercises to test and validate the biomechanical model. We found that when the biomechanical model is taught an exercise, it can accurately predict a subject's actual UL joint angles and torques and confirm that the exercise is isolating the desired movement.