Knowing exactly how much solar radiation reaches a particular area is helpful when planning energy installations. In recent years the use of renewable energies, especially those related to photovoltaic systems, has had an impressive up-tendency. Therefore, mechanisms that allow us predict are essential. This work aims present results for predicting using optimization with Random Forest (RF) algorithm. Moreover, it compares obtained other machine learning models. The conducted analysis...

Received signal strength indicator (RSSI)-based fingerprinting is a widely used technique for indoor localization, but these methods suffer from high error rates due to various reflections, interferences, and noises. The use of disturbances in the magnetic field localization has gained increasing attention recent years, since this technology provides stable measurements with low random fluctuations. In paper, novel fingerprinting-based 2D positioning method, which utilizes fusion RSSI...

This paper proposes a novel fuzzy-adaptive extended Kalman filter (FAEKF) for the real-time attitude estimation of agile mobile platforms equipped with magnetic, angular rate, and gravity (MARG) sensor arrays. The structure employs both quaternion-based EKF an adaptive extension, in which measurement methods are used to calculate magnitudes system vibrations, external accelerations, magnetic distortions. These magnitudes, as disturbances, incorporated into sophisticated fuzzy inference...

Wireless-radio-communication-based devices are used in more and places with the spread of Industry 4.0. Localization plays a crucial part many these applications. In this paper, novel radiocommunication-based indoor positioning method is proposed, which applies fusion fingerprints extracted various technologies to improve overall efficiency. The aim research apply differences, occur due that different behave differently an space. proposed was validated using training test data collected...

Nitrogen (N) availability is critical for cucumber (Cucumis sativus L.) growth and yield in greenhouse production. In this study, we investigated the effects of different N doses on bioimpedance spectroscopy (BIS) parameters plants (ES.22.17 F1 genotype), focusing extracellular fluid resistance (R1), intracellular (R2), vacuole (R4), cell membrane capacitances (Cm, Ct). The results showed that low supply significantly increased R1 reduced Cm leaves, indicative decreased nitrate (NO3−)...

Abstract This paper presents a novel control laboratory project that provides hands‐on experience in feedback concepts (embedded systems) through dedicated assignments, with particular focus on the design and implementation of fuzzy control. The is structured around an inexpensive, portable self‐balancing robot (SBR), whose embedded system realized using commercially available breakout boards as first assignment. For stabilization plant, students are guided to execute essential stages...

This paper presents an open-source environment for development, tuning, and performance evaluation of magnetic, angular rate, gravity-based (MARG-based) filters, such as pose estimators classification algorithms. The is available in both ROS/Gazebo MATLAB/Simulink, it contains a six-degrees freedom (6 DOF) test bench, which simultaneously moves rotates MARG unit the three-dimensional (3D) space. As quality MARG-based estimation becomes crucial dynamic situations, proposed platform intends to...

Accurate and reliable measurement of the electrical impedance spectrum is an essential requirement in order to draw relevant conclusions many fields a variety applications; particular, for biological processes. Even state-of-the-art methods developed this purpose, accuracy efficacy measurements are reduced systems, due regular occurrence parameters causing errors such as residual impedance, parasitic capacitance, generator anomalies, so on. Recent observations have reported necessity...

A simulation model contributes to the development of both algorithms based on navigation sensors and their application in real nonlinear mechatronic systems. The Szabad(ka)-II hexapod walker robot is equipped with an inertial measurement unit (IMU), this paper presents a novel calibration procedure its model. Various sinusoidal movements were performed robot, raw IMU measurements recorded simultaneously motor electrical parameters joint movement variables. includes sensors, where location,...

Vehicle count and classification data are very important inputs for intelligent transportation systems (ITS). Magnetic sensor-based technology provides a promising solution the measurement of different traffic parameters. In this work, novel, real-time vehicle detection system is presented using single magnetometer. The detection, feature extraction, performed online, so there no need external equipment to conduct necessary computation. Data acquisition was in real environment unit installed...

The utilization of stereo cameras in robotic applications is presented this paper. use a depth sensor principal step robotics applications, since it the first sequences actions where intent to detect and extract windows obstacles that are not meant be painted from surrounding wall. A RealSense D435 camera was used for surface recording via real-time, appearance-based (RTAB) mapping procedure, as well navigate painting robot. Later, wall detection obstacle avoidance processes were performed...

With the spread of Internet Things (IoT) different radio communication-based technologies are gaining more attention, and their application in indoor localization problems where GPS signal is not available, becomes relevant. This paper addresses trilateration algorithm-based position estimation approach localization; this uses Received Signal Strength Indication (RSSI) value with Free Space Path Loss (FSPL) model. Comprehensive laboratory measurements were performed namely 433 MHz RSSI, 2.4...

Terrain classification provides valuable information for both control and navigation algorithms of wheeled mobile robots. In this paper, a novel online outdoor terrain algorithm is proposed The based on only time-domain features with low computational memory requirements, which are extracted from the inertial magnetic sensor signals. Multilayer perceptron (MLP) neural networks applied as classifiers. tested measurement database collected using prototype system various types. Different...

In stochastic computing (SC) systems numbers are represented with mean values of random binary sequences. This paper introduces a novel fuzzy inference architecture, in which the computational mechanism is based on logic (SL). First, basic concept SL described, then architecture SL-based controller (SFLC) built up systematically using derived elements. The second part demonstrates application proposed techniques, where SFLC-based control performance evaluated real mechatronic system. results...

Brushed (B) and Brushless (BL) DC motors constitute the cornerstone of mechatronic systems regardless their sizes (including miniaturized), in which both position speed control tasks require application sophisticated algorithms. This manuscript addresses initial step using time series analysis to forecast Back EMF values, thereby enabling elaboration real-time adaptive fine-tuning strategies for PID controllers such a system design problem. An Auto-Regressive Moving Average (ARMA) model is...

S-This paper investigates the optimized control performances of fuzzy and proportional-integral-derivative (PID) schemes developed for stabilization an under-actuated mobile robot. The strategy had been designed in earlier paper, its equivalent PID controller-based scheme is established first. Then a complex cost function defined that evaluates reference tracking performance, efficiency system oscillations suppression average current consumption motor drive system. particle swarm...

This paper presents the use of ZED depth sensor in a robot-based painting application. The stereo is very important factor robotic applications, since it both initial and essential step sequence operations, where goal to detect extract useful surface objects or obstacle on wall that not intended for painting. was used recording navigation our robot. Later, extraction performed using simple image processing morphological operations algorithm. client's instruction well-known, simple, proven...