Search

This study addresses the problem of estimating the velocity and displacement of building structures. Initially, the dynamics of a building subject to seismic disturbance are represented using the Euler-Bernoulli beam model. Subsequently, the model is discretized into a finite number of floors through a modal coordinate transformation that produces a set of decoupled dynamics for each story of the building. The Algebraic Observer (AO) takes advantage of this property to ensure the Algebraic Observability Conditions (AOC). This approach allows the representation of velocity and displacement terms as functions of the available acceleration measurements. One notable advantage of the proposed observer is that, due to its design, it does not require tuning of gains to achieve the convergence property. This observer’s simplicity of implementation for practical purposes is another noteworthy characteristic. Note that, to minimize the effect of the measurement noise, iterated integrals of the measured acceleration are introduced to mitigate high-frequency noise. In contrast, second-order filters are employed for low-frequency noise. Finally, the experimental demonstration of the effectiveness and accuracy of this estimation method is conducted using a reduced-scale five-story building prototype.

In-depth research has been done in the literature on applying sophisticated modulation and control systems for power converters, such as Feedback Quantizer and Predictive Control. This research aims to enhance the Feedback Quantizer, a closed-loop modulation technique used in three-phase voltage source inverters. This method naturally reduces harmonics at low frequencies, which harms electrical machinery like transformers and AC motors. This modulation technique achieves an excellent follow-up of the fundamental voltage reference. One of the disadvantages of Feedback Quantizer are the low sampling time to achieve a good waveform quality; in addition, as it is not a carrier-based method, the switching frequency is variable, resulting in a dispersed harmonic spectrum. The three-phase voltage source inverter has eight valid states to monitor the voltage reference; the proposal consists of modifying the feedback quantizer modulation using virtual vectors by discrete space vectors, which achieves a better follow-up. The proposal considers a simplified implementation of discrete space vectors in such a way as to reduce the computational cost to obtain voltage and current waveforms with low WTHD, THD distortion, and a defined harmonic spectrum but with a high sampling time. The proposed modulation scheme obtains a THD of less than 2% in the load current, reducing the noise produced by the traditional scheme of Feedback Quantizer and using a fixed switching frequency for a sampling time of ( $200~\mu $ s). The above is an improvement compared to the conventional Feedback Quantizer. Additionally, it was possible to reduce the mathematical operations of the algorithm by a factor of 5.38 by using strategies to simplify the algorithm of the suggested scheme. The proposed technique operates correctly, according to experimental tests.INDEX TERMS Feedback quantizer, discrete space vector modulation, total harmonic distortion, weighted total harmonic distortion, voltage source converter, modulation scheme.

Achieving uniform Pareto front (PF) approximations across various PF geometries and dimensions is a significant challenge. Most multi-objective evolutionary algorithms (MOEAs) that adapt a reference set to guide the evolutionary process, do not prioritize uniformity but the degree of resemblance to the PF shape. Consequently, these MOEAs often require extensive function evaluations to balance uniformity and diversity while representing the PF effectively. To address this issue, we introduce MOEA-UD, a MOEA designed to construct uniformly distributed PF approximations independent of the PF’s geometrical properties. MOEA-UD features a two-stage niching selection process. Initially, it classifies the population into niches using a reference set for uniformity, where the best solution per niche is selected. If additional solutions are needed to reach the population size, it then employs a reference set for diversity to populate any sparse regions. This approach ensures that uniformity is prioritized, while the diversity is used strategically to fill gaps and avoid empty regions. Also, an external archive using an improved selection mechanism based on niching and pair-potential energy function is employed to adapt both reference sets iteratively. We compared MOEA-UD with twelve state-of-the-art MOEAs on a wide range of artificial and real-world multi-objective optimization problems with different PF geometries. Our experimental results show that MOEA-UD consistently exhibits a PF shape invariant performance according to quality indicators, making it a promising option for generating uniform PF approximations.

This study investigates the optimal spatial window size for estimating chlorophyll-a (Chl-a) concentrations using Sentinel-2 imagery in small reservoirs of Extremadura, Spain. While remote-sensing techniques have proven valuable for water quality monitoring, the influence of pixel window size on estimation accuracy remains understudied, particularly for smaller water bodies. We analyzed 94 atmospherically corrected Sentinel-2 images using the C2RCC processor, corresponding to 32 reservoirs, and compared the results with in situ measurements collected between 2017 and 2022. Our methodology explored window sizes ranging from 1×1 pixels to 20×20 pixels, employing various statistical estimators. Performance was assessed using root-mean-square relative error, mean absolute percentage error, and Spearman's correlation coefficient (ρ). Results show that window sizes between 5×5 and 9×9 pixels yielded optimal Chl-a estimation accuracy. The Cmax estimator consistently outperformed other methods across different window sizes, particularly for mesotrophic and eutrophic waters. Notably, larger window sizes improved correlation with in situ data but showed diminishing returns beyond 9×9 pixels. This study contributes to refining remote-sensing methodologies for inland water quality monitoring, particularly for small- to medium-sized reservoirs. Our findings suggest that careful consideration of spatial window size and statistical estimators can enhance the accuracy of Chl-a concentration predictions, potentially improving water resource management in regions with diverse aquatic ecosystems.

Telehealth and telemedicine are considered as a set of effective solutions, through which an emerging country could ensure its citizens their right for healthcare. This study is focused on designing a telehealth platform for human movement assessment, through a service-oriented approach. Service-oriented architecture presents a methodology for designing the logic of a solution, which considers the organization and usage for distributed applications. Model-based design allows specifying and analyzing interactive software applications from a semantic oriented perspective, rather than immediately approaching the implementation phase. The created model was analyzed by simulation to observe the behavior under different conditions and to verify the functional correctness of the web service. A virtual server was configured, as well as an application programming interface. This approach allowed detailed static and dynamic analysis, as well as behavioral and structural testing of the model, prior to the implementation of a web service, providing important benefits for a multidisciplinary development team.

This paper proposes a dual-coverage Electromagnetic Skin (EM skin) based on a single-layer reflecting panel to provide coverage of blind zones and enhance 6G communications at sub-THz frequencies. The proposed EM skin is able to generate two independent reflected beams in orthogonal linear polarizations, which are pointed in different fixed directions to cover two different regions of users. The unit-cell of the EM skin is based on orthogonal groups of dipole-type elements, which provide independent phasing capability in each linear polarization. A beamforming technique has been applied to broaden the beams in the elevation and azimuth planes with respect to the reference pencil-beam design, so as to cover a wider angular region of $10^{\circ } \times 10^{\circ } $ . A 68 mm $\times 68$ mm EM-skin prototype, comprising $40\times 40$ reflecting cells, has been fabricated and tested, showing good agreement with the simulations at the design frequency of 100 GHz, low cross-polar levels, and stable gain and beamwidth performance in the 95-104 GHz band. The proposed EM skin is a low-cost and energy-efficient solution for improving wireless coverage of blind zones in sub-THz 6G systems, in those scenarios where there is no direct line of sight with the base station or hotspot.

A comprehensive analysis of the COVID-19 pandemic is necessary to prepare for future healthcare challenges. In this regard, the large number of datasets collected during the pandemic has allowed various studies on disease behavior and characteristics. For example, collected datasets can be used to extract knowledge about the symptomatic behavior of the disease. In this work, we are interested in analyzing the relationships between the different symptoms of the disease, considering various dimensions, such as countries, variants of COVID-19, and age groups. To this end, we consider the co-occurrence of symptoms as a fundamental element. More precisely, we implemented clustering techniques to discover symptomatic patterns across the various dimensions. For instance, in analyzing the dominant patterns, we observe that symptom congestion or runny nose almost always appears with the symptom muscle pain across many dimensions. Hence, the information on symptom patterns can be helpful in decision-making processes to detect and combat COVID-19 and similar diseases.

Finite-control-set model predictive control (FCS-MPC) has achieved superiority in managing multiphase induction machines due to its quick dynamic response, control flexibility, and overall good performance. Its advantages, including simplicity, computational efficiency, compensation for system perturbations, and effective handling of multivariable problems, have made it a competitive alternative in various industrial applications. Nevertheless, FCS-MPC has some limitations. It is highly dependent on the accuracy of the predictive model’s parameters. Unfortunately, the estimation of magnetizing inductance, the most critical factor, especially in the weakening field region, has not been studied yet. Focusing on this gap, this article proposes a technique to estimate the magnetizing inductance in the field weakening zone for a six-phase asymmetrical induction machine driven by the FCS-MPC. Experimental tests have verified the effectiveness of the proposed method, considering stator currents and rotor speed tracking, as well as a reduction in the ( $x-y$ ) currents.

Human-Machine Interfaces (HMIs) play an important role in ensuring performance reliability to create safety and comfort during the operation of autonomous vehicles, by efficiently communicating their current state and driving intentions to drivers, passengers, and pedestrians. The motivation for this study emerges from the increasing development of autonomous vehicles and the critical need for effective HMIs to bridge the communication gap between these vehicles and their users. Examples of HMI technologies include visual displays for status updates, auditory alerts for immediate hazards, and haptic feedback for enhanced control. During automated driving tasks that may require users to take control of the vehicle under certain conditions, the interfaces must support the situational awareness of the drivers by providing effective communication of the situation. Design challenges include ensuring intuitive interaction, minimizing driver distraction, and achieving seamless integration with advanced vehicle control systems. The objective of this literature review is to present a comprehensive overview of the development of human-machine interface technologies in autonomous vehicles in different domain areas and to identify design challenges and opportunities to improve their interaction with their users.

The increase in maritime traffic due to the globalization of trade has led to an exponential growth in logistics operations and port traffic management is becoming increasingly complicated. The need to improve the efficiency, safety, and sustainability of operations is leading to a strong demand for automation in port processes. A significant challenge is the optimization and automation of loading and unloading systems, given their complexity and repetitive nature. Advances in automated systems, through ongoing research and application in various transportation scenarios, are addressing these challenges. However, automating vehicles alone is insufficient; it is also important to have a connected, infrastructure-based collaborative framework to manage the complex logistics of port operations effectively and in a synchronized manner. In this sense, ESTIBA+2022, a Spanish-funded project, is addressing this challenge, aiming to develop strategic technologies for Smart-Ports. Its goal is to design and validate a scalable collaborative framework that meets the specifications and functions of port services using Industry 4.0 technologies and advanced wireless communications through Connected Intelligent Transportation Systems (C-ITS). This article presents the proposed architecture and its validation in the comprehensive use case of the project, focusing on communication from the supervision platform to Automated Guided Vehicles (AGVs) to ensure optimal traffic flow and management in ports. Specifically, the scenario involves three different forklifts equipped with an On-Board Unit (OBU) that interact with each other and the infrastructure via Roadside Units (RSU). The outcome of the project shows that the framework can meet the requirements for Smart-Port logistics, showing the feasibility of the implementation with a collaborative maneuver between three forklifts, a supervision station, and connected traffic lights.

We consider in this paper the practical implementation of a siftingless quantum key distribution protocol. The protocol is considered siftingless since it combines sifting and error correction in a single step for basis and information reconciliation, respectively. The protocol can be efficiently implemented even assuming the existence of errors in the communication. In this case, the correlations between the legitimate parties can be modeled by a binary symmetric channel with erasures. Specific codes for this channel are included and simulated for intermediate block lengths. Simulation results show that a key reconciliation step carrying simultaneously both basis and information reconciliation can be efficiently implemented.

Even though reinforcement-learning-based algorithms achieved superhuman performance in many domains, the field of robotics poses significant challenges as the state and action spaces are continuous, and the reward function is predominantly sparse. Furthermore, on many occasions, the agent is devoid of access to any form of demonstration. Inspired by human learning, in this work, we propose a method named highlight experience replay (HiER) that creates a secondary highlight replay buffer for the most relevant experiences. For the weights update, the transitions are sampled from both the standard and the highlight experience replay buffer. It can be applied with or without the techniques of hindsight experience replay (HER) and prioritized experience replay (PER). Our method significantly improves the performance of the state-of-the-art, validated on 8 tasks of three robotic benchmarks. Furthermore, to exploit the full potential of HiER, we propose HiER+ in which HiER is enhanced with an arbitrary data collection curriculum learning method. Our implementation, the qualitative results, and a video presentation are available on the project site: http://www.danielhorvath.eu/hier/.

Text processing is a fundamental aspect of Natural Language Processing (NLP) and is crucial for various applications in fields such as artificial intelligence, data science, and information retrieval. It plays a core role in language models. Most text-processing approaches focus on describing and synthesizing, to a greater or lesser degree, lexical, syntactic, and semantic properties of text in the form of numerical vectors that induce a metric space, in which, it is possible to find underlying patterns and structures related to the original text. Since each approach has strengths and weaknesses, finding a single approach that perfectly extracts representative text properties for every task and application domain is hard. This paper proposes a novel approach capable of synthesizing information from heterogeneous state-of-the-art text processing approaches into a unified representation. Encouraging results demonstrate that using this representation in popular machine-learning tasks not only leads to superior performance but also offers notable advantages in memory efficiency and preservation of underlying information of the distinct sources involved in such a representation.

In this manuscript a novel computationally efficient method for implementing the Deter- ministic Maximum Likelihood estimator of multiple superimposed real sinusoids is derived. This method is an adaptation of a recently proposed algorithm for the estimation of undamped exponentials and offers two significant advantages in terms of complexity with respect to various alternatives available in the technical literature. First, the dependence of the computational complexity on the snapshot length is the same as that of the Fast Fourier Transform. Consequently, increasing the snapshot length does not have a substantial impact on the overall computational burden. Second, the proposed method exploits the ability of the periodogram estimator to coarsely locate the global maximum of the Deterministic Maximum Likelihood cost function, thereby eliminating the need for a global search on this last function. Our numerical results show that it achieves a better accuracy-complexity trade-off than various estimators available in the literature.

In order to improve cybersecurity in newly developed network infrastructures, this research investigates the integration of blockchain technology with zero-trust security concepts. The zero-trust paradigm ensures continuous authentication across entities, in contrast to standard security models that often presuppose trust based on a network environment. Blockchain is used to decentralize and impose authentication intensity of communication clarity and honesty. The study compares the performance of the zero trust model enhanced by blockchain to traditional security systems in a number of parameters, such as intrusion detection rates and security breach reaction times, using extensive simulations. The findings demonstrate that the blockchain-enhanced zero-trust architecture performs better than conventional systems in both identifying and countering threats and methodically handling a large volume of transactions when under pressure. These conclusions, which emphasize significant advancements in security applications and system resilience, are predicated on the use of blockchain in zero-trust systems. Subsequent investigations will endeavor to enhance these technologies and investigate their utilization in networks across diverse intricate scenarios.

This research presents a multi-objective dispatch (MOD) for energy storage systems (ESS) utilizing batteries and renewable energy resources (RES) in distribution network applications. This proposal employs a convex weighting-based approach. The exact MOD nonlinear programming model, which is non-convex due to the power balance constraint, is approximated using a second-order cone equivalent in order to ensure a global optimum, leveraging the convex properties of the objective functions and the conic equivalent in the complex-variable domain. The MOD, based on the linear combination of the objective functions via the weighting-based method, enables the construction of the optimal Pareto front, as each combination of the weighting factors generates a convex optimization sub-problem. The MOD analysis simultaneously considers the minimization of the expected grid operating costs with regard to energy purchasing at the substation terminals, the reduction of the operating costs associated with the RES and the ESS, and the minimization of the expected daily energy losses. This research makes two contributions: 1) the incorporation of the active and reactive power capabilities of the power electronic converters that interface with the ESS and the RES and 2) a robust analysis via convex optimization to address the uncertainties related to the expected daily generation and demand profiles. Numerical results obtained in the IEEE 33- and 85-bus test system confirm the effectiveness and robustness of the proposed MOD in comparison with the continuous genetic algorithm, the particle swarm optimizer, and the vortex search algorithm. In addition, the best metah-euristic technique was employed for constructing the Pareto front and comparing its performance against the proposed convex approach for the 33-bus grid. In the case of the 85-bus grid, battery power losses were included to demonstrate the effectiveness of this solution methodology in medium-scale distribution grids.INDEX TERMS Energy losses minimization, grid operating cost minimization, multi-objective dispatch, second-order conic equivalent, robust convex optimization, variable power factor operation, weighting-based multi-objective methodology.

In the context of neurorehabilitation, there have been rapid and continuous improvements in sensors-based clinical tools to quantify limb performance. As a result of the increasing integration of technologies in the assessment procedure, the need to integrate evidence-based medicine with benchmarking has emerged in the scientific community. In this work, we present the experimental validation of our previously proposed benchmarking scheme for upper limb capabilities in terms of repeatability, reproducibility, and clinical meaningfulness. We performed a prospective multicenter study on neurologically intact young and elderly subjects and post-stroke patients while recording kinematics and electromyography. 60 subjects (30 young healthy, 15 elderly healthy, and 15 post-stroke) completed the benchmarking protocol. The framework was repeatable among different assessors and instrumentation. Age did not significantly impact the performance indicators of the scheme for healthy subjects. In post-stroke subjects, the movements presented decreased smoothness and speed, the movement amplitude was reduced, and the muscular activation showed lower power and lower intra-limb coordination. We revised the original framework reducing it to three motor skills, and we extracted 14 significant performance indicators with a good correlation with the ARAT clinical scale. The applicability of the scheme is wide, and it may be considered a valuable tool for upper limb functional evaluation in the clinical routine.

Mexico exhibits one of the highest rates of identity theft in relation to bank accounts, with 56% of cardholders encountering fraudulent processes. Consequently, financial institutions have elevated security measures in their authentication protocols and implemented more robust procedures. To address this issue, this study advocates a multifactor authentication approach wherein an algorithm incorporates the user’s location as a transparent authentication factor. Traditional multifactor authentication techniques typically necessitate intricate combinations of factors, including passwords, biometrics, external hardware, or time-based one-time passwords, to enhance security levels, albeit inadvertently introducing cumbersome steps. This research proposes a simple authentication implementation that retains the benefits of complex multifactor procedures -such as precision, accuracy, and security-, with the additional feature of utilizing an imperceptible location factor. The experimental phase encompasses the development of two functional prototypes: a software implementation on the Android environment -tested in 79 distinct locations-, and an implementation on Arduino hardware -tested in four locations-. These experiments were conducted in real-world scenarios, spanning a 21-day period, and involving data collection from different participants. The most significant result of this research is intricately linked to the runtime of each authentication process, where the average time elapsed from the user input stage to the completion of the validation section is 1.76 seconds. This time optimization is primarily attributed to the integration of native Android libraries. The findings demonstrate that it is possible to attain 100% accuracy for all secure locations with a 12-meter radius in 1.76 seconds in the case of the Android app. As for the Arduino-based security box, a 100% accuracy rate in all opening attempts is possible by employing a radius of 30 meters. The research endeavors to emphasize the versatility and applicability of the proposed solution for integration into diverse real-world scenarios where the preservation of data integrity holds utmost importance.

This paper presents the dynamic phasor-based modeling of three-phase voltage-source converters (VSC) operating as static var compensators (STATCOM). The generalized averaging theory is used to represent the DC, 1st, and 2nd harmonics of the converter fundamental response. The VSC model is characterized by the use of basic power system elements. On the AC side, it consists of three wye-connected, single-phase complex transformers whose taps replicate the AC-to-DC energy conversion of the converter commanded by the modulating variables. On the DC side, a capacitor is connected in parallel with a current source to reproduce the $2{\omega }$ effects of the network unbalances. Dynamic controllers based on symmetrical components were developed for the VSC to operate as STATCOM. All these aspects distinguish the proposed VSC model from the switching-based model (SBM) and averaged-value model (AVM). The model’s dynamic behavior was validated by comparing it to the SBM and AVM, using a five-bus, three-phase network taken from Simulink/Simscape Electrical. Root mean square errors were smaller than 5.56% and 5.53%, with the new model being 43 and 17 times more computationally efficient than the SBM and AVM, respectively. The IEEE 34-bus test system with two STATCOM was also studied to verify the model practicality. Short-circuit faults were assessed to prove that both STATCOM suitably perform under unbalanced operating conditions.

Concerns about climate change have boosted the massive introduction of renewable energy into electric power systems. Renewable generators can mitigate pollution by replacing fuel-based energy with clean energy. However, these generators displace conventional synchronous ones. This changes power system dynamics and can lead to a less stable operation. To face this emerging problem, many approaches have been proposed in order to enable renewable generators and consumers to provide ancillary services. Nevertheless, if renewable generators adjust their production to support grid ancillary services, all the primary energy resources cannot be optimally used. This work proposes a way for railway systems to contribute to primary and supplementary frequency control and to relieve renewable generation from frequency control tasks. Furthermore, a tuning control method is introduced. Due to the high stochasticity of railway system operation, a method for selecting local optimum parameters is proposed. The frequency control scheme is set and tested in simulation, and experimentally validated by means of Hardware In the Loop tests with a real micro controller. The results demonstrate, first, the capacity of railway systems to manage a certain quantity of frequency deviations and, second, the feasibility of implementing the proposed control strategy in real time. This work broadens the framework of railway-based demand response approaches.

This paper presents a finite-control-set model predictive control (FCS-MPC) with fractional-order proportional-integral (FO-PI) controller to regulate the dc-link voltage of a single–phase cascaded H–bridge (CHB) 5-level inverter working as a shunt active power filter (APF). By using the FCS-MPC scheme in a single–phase CHB multilevel inverter as an APF, it is possible to generate a compensation current that tracks its reference with maximum precision, in addition, it presents a quick dynamic reaction to disturbances. When the compensation current is injected into the electrical system, current harmonic distortions are effectively reduced. To simplify the number of evaluations in the algorithm, the voltages on the dc-link of each H-bridge are equalized by a redundant selection of switching states of the multilevel inverter. The discrete-time model of the single-phase shunt APF, the technique to generate the compensation current reference signal, and the developed FCS-MPC algorithm are explained in detail. Furthermore, to keep the dc-link voltage steady, with minimal disturbance, it is proposed to use a discrete-time FO-PI controller. The effectiveness of the proposed control scheme is investigated in steady-state, as well as dynamic transients caused by sudden load changes. The developed control algorithm is verified through experimental tests conducted on a 5 kVA single-phase CHB 5-level inverter-based shunt APF.

This paper presents a promising winding technique which enables higher power-densities in partially superconducting electrical machines with a slotless stator, e.g., self-supporting windings. Firstly, the formulation for defining the skewing factor of the helical winding is given. Afterwards, the skew angle and how diverse winding configurations can be characterised as a function of this angle is explained, along with different parameters such as the skewing factor, the harmonic content of the magnetomotive force wave in the airgap or the resistance per phase of the winding. The sine-shaped winding, a particular case of helical winding, is shown, with which, thanks to the benefits of the additive manufacturing, a better electromagnetic performance is achieved. Finally, the implementation of the helical winding configuration in a slotless partially superconducting 2 MW high-power and high-voltage electric machine for electric aircraft propulsion is assessed, comparing the machine active part weight and their power density.

This research proposes an effective energy management dispatch (EMD) using a convex approximation for battery-based energy storage systems (ESS) and renewable sources in medium-voltage distribution networks. By means of the branch flow formulation, the exact nonlinear programming model representing the EMD is transformed into a convex model through a second-order cone programming relaxation. Two contributions are presented in this work. The first involves analyzing battery-based EES and renewable sources, specifically focusing on their operation with a variable power factor. This analysis considers the reactive power control capabilities of the power electronic converters that connect distributed energy resources to the grid. The second contribution involves evaluating a robust operation scenario by incorporating uncertainties in the availability of renewable generation and the expected daily demand profile. Numerical validations are conducted on two radial distribution networks composed of 27 and 33 nodes. These networks were chosen to represent the characteristics of rural and urban networks in the Colombian distribution system. The results are then compared against those obtained with a classical unitary power factor. The main goal of the proposed EMD is to minimize the expected annual grid energy losses and operating costs through a single-objective analysis. A comparison with metaheuristic optimization algorithms, such as the parallel version of the particle swarm optimizer, the vortex search algorithm, and a genetic algorithm, demonstrates the effectiveness of our convex EMD model for both objective functions under study. All numerical simulations, including the robust model, were run using MATLAB’s Yalmip tool.

In an increasingly aging world, the effort to automate tasks associated with the care of elderly dependent individuals becomes more and more relevant if quality care provision at sustainable costs is desired. One of the tasks susceptible to automation in this field is the automatic detection of falls. The research effort undertaken to develop automatic fall detection systems has been quite substantial and has resulted in reliable fall detection systems. However, individuals who could benefit from these systems only consider their use in certain scenarios. Among them, a relevant scenario is the one associated to semi-supervised patients during the night who wake up and get out of bed, usually disoriented, feeling an urgent need to go to the toilet. Under these circumstances, usually, the person is not supervised, and a fall could go unnoticed until the next morning, delaying the arrival of urgently needed assistance. In this scenario, associated with nighttime rest, the patient prioritizes comfort, and in this situation, body-worn sensors typical of wearable systems are not a good option. Environmental systems, particularly visual-based ones with cameras deployed in the patient’s environment, could be the ideal option for this scenario. However, it is necessary to work with far-infrared (FIR) images in the low-light conditions of this environment. This work develops and implements, for the first time, a fall detection system that works with FIR imagery. The system integrates the output of a human pose estimation neural network with a detection methodology which uses the relative movement of the body’s most important joints in order to determine whether a fall has taken place. The pose estimation neural networks used represent the most relevant architectures in this field and have been trained using the first large public labeled FIR dataset. Thus, we have developed the first vision-based fall detection system working on FIR imagery able to operate in conditions of absolute darkness whose performance indexes are equivalent to the ones of equivalent systems working on conventional RGB images.

In the contemporary cybersecurity landscape, robust attack detection mechanisms are important for organizations. However, the current state of research in Software-Defined Networking (SDN) suffers from a notable lack of recent SDN-OpenFlow-based datasets. This study seeks to bridge this gap by introducing a novel dataset for intrusion detection in Software-Defined Networking named SDNFlow. The dataset, derived from OpenFlow statistics gathered from real traffic, integrates a comprehensive range of network activities. An empirical evaluation leveraging diverse Machine and deep Learning algorithms was performed. Namely, Logistic regression, decision tree, random forest, K-nearest neighbors, Support Vector Machines, and Multilayer Perceptron were tested getting pretty good results with a precision average of 98% to 99% in binary classification and from 97% to 99% in multiclass classification depending of the attack, we highlight the efficacy of K-Nearest Neighbors (KNN) for traffic classification, particularly in detecting DDoS attacks and port scanning. The dataset is valuable for evaluating intrusion detection systems within SDN environments and deepening the understanding of traffic patterns in Software Defined Networks.

According to the Air Quality Directive 2008/50/EC, air quality zoning divides a territory into air quality zones where pollution and citizen exposure are similar and can be monitored using similar strategies. However, there is no standardized computational methodology to solve this problem, and only a few experiences in the Comunidad of Madrid based on chemistry transport models. In this study, we propose a methodological improvement based on the application of deep learning. Our method uses the CHIMERE-WRF air quality modelling system and adds a step that uses neural networks architectures to calibrate the simulations. We have validated our method in the Region of Murcia. The results obtained are promising given the values of the Pearson coefficient, obtaining $r = 0.94$ for $NO_{2}$ and $r = 0.95$ for $O_{3}$ , improving 86 % and 29 % the performances reported in the state of the art. In addition, the cluster score improves after applying neural networks, demonstrating that neural networks improve the consistency of clusters compared to the current air quality zoning. This opened new research opportunities based on the use of neural networks for dimension reduction in spatial clustering problems, and we were able to provide recommendations for a new measurement point in the Region of Murcia Air Quality Network.

In recent years, there has been a notable surge in the utilization of remote desktop services, largely driven by the emergence of new remote work models introduced during the pandemic. These services cater to interactive cloud-based applications (CIAs), whose core functionality operates in the cloud, demanding strict end-user interactivity requirements. This boom has led to a significant increase in their deployment, accompanied by a corresponding increase in associated maintenance costs. Service administrators aim to guarantee a satisfactory Quality of Experience (QoE) by monitoring metrics like interactivity time, particularly in cloud environments where variables such as network performance and shared resources come into play. This paper analyses anomaly detection state of the art and proposes a novel system for detecting interactivity time anomalies in cloud-based remote desktop environments. We employ an automatic model based on LSTM neural networks that achieves an accuracy of up to 99.97%.

In recent years, transformer language models have made a significant impact on automatic text generation. This study focuses on the task of distractor generation in Spanish using a fine-tuned multilingual text-to-text model, namely mT5. Our method outperformed established baselines based on LSTM networks, confirming the effectiveness of Transformer architectures in such NLP tasks. While comparisons with other Transformer-based solutions yielded diverse outcomes based on the metric of choice, our method notably achieved superior results on the ROUGE metric compared to the GPT-2 approach. Although traditional evaluation metrics such as BLEU and ROUGE are commonly used, this paper argues for more context-sensitive metrics given the inherent variability in acceptable distractor generation results. Among the contributions of this research is a comprehensive comparison with other methods, an examination of the potential drawbacks of multilingual models, and the introduction of alternative evaluation metrics. Future research directions, derived from our findings and a review of related works are also suggested, with a particular emphasis on leveraging other language models and Transformer architectures.

One of the main challenges of visual prostheses is to augment the perceived information to improve the experience of its wearers. Given the limited access to implanted patients, in order to facilitate the experimentation of new techniques, this is often evaluated via Simulated Prosthetic Vision (SPV) with sighted people. In this work, we introduce a novel SPV framework and implementation that presents major advantages with respect to previous approaches. First, it is integrated into a robotics framework, which allows us to benefit from a wide range of methods and algorithms from the field (e.g. object recognition, obstacle avoidance, autonomous navigation, deep learning). Second, we go beyond traditional image processing with 3D point clouds processing using an RGB-D camera, allowing us to robustly detect the floor, obstacles and the structure of the scene. Third, it works either with a real camera or in a virtual environment, which gives us endless possibilities for immersive experimentation through a head-mounted display. Fourth, we incorporate a validated temporal phosphene model that replicates time effects into the generation of visual stimuli. Finally, we have proposed, developed and tested several applications within this framework, such as avoiding moving obstacles, providing a general understanding of the scene, staircase detection, helping the subject to navigate an unfamiliar space, and object and person detection. We provide experimental results in real and virtual environments. The code is publicly available at https://www.github.com/aperezyus/RASPV

Coastal zones close to big river systems are hydrodynamically characterized by inland and open ocean waters. Satellite altimetry data have recently been scientifically exploited in coastal zones. However, more efforts are still needed in terms of using these data in new applications in the coastal strip. Our study analyzes the capability of the European Space Agency CryoSat-2 satellite to measure the sea level elevation associated with bulge-like lens of less salty waters from river discharges, spreading into the adjacent coastal zones. We analyze four events of high river freshwater discharges in two river estuaries in Spain: Guadalquivir and Ebro. We obtain along-track Absolute Dynamic Topography from CryoSat-2 satellite during these events and compare them with periods of low discharge conditions. In three of the events, the bulges increase the sea level between 5 and 10 cm with respect to the sea level observed in low / normal discharge conditions. The extension of the lens is far from the estuary mouth: more than 25 km from the coast in the case of the Guadalquivir River and about 50 km for the Ebro River. The wind regime and the surface circulation explain the lack of a higher sea level in one of the events analyzed.

This paper presents the modeling, control and evaluation in a real-time simulation (RTS) of a three-phase multilevel inverter based on the modular multilevel converter (MMC) topology. The developed model for MMC includes four decoupled state variables per phase, which are instrumental for the control design, namely injected (output) current, circulating current, total energy, and energy balance between arms. Based on this model, a control scheme is proposed with the aim to regulate and balance the total energy on each converter’s phase, regulate the circulating currents, and inject a three-phase current synchronized with the grid voltage. As part of the control process, the proposed controller generates the reference for a modulation scheme to obtain the switching sequence for each converter’s cell, which, in this case, is the phase-shifted carrier-based pulse-width modulation (PSC-PWM). As it was already reported in the literature, this particular modulation guarantees self (natural) balance of all capacitor voltages, i.e., they converge to the same steady-state average value without the need of any external balancing controller.

In this work, the problem of following references and rejecting disturbances that are contaminated with noise and whose dynamics are too complex to have a mathematical model that describes the behavior of such signals is studied. In addition to exploiting the capabilities of the Kalman filter (KF) to clean the signals so that they can serve as external signals for the regulation theory, the construction of the generating system (exosystem) is proposed as a diagonal system by blocks, where each block is a Kalman filter that estimates each one of the corresponding reference/disturbance signals. The viability of the approach is verified by two examples, mimicking the problem of tracking a flying object moving freely in the 3D space by a quadrotor which is under the influence of the proposed controller when the displacements of the arbitrary flying object are measured by low-cost sensors.

The instantaneous centers of rotation (ICRs) for the two treads of skid-steer vehicles moving with low inertia on hard horizontal terrain almost remain with constant local coordinates, which allows to establish an equivalence with differential-drive locomotion. However, this significant kinematic relationship has not been analyzed yet on sloped ground. One relevant difficulty of studying ICR behavior on inclined terrain, even on a flat surface, is the continuous variation of pitch and roll angles while turning. To overcome this problem, this paper analyzes a dynamic simulation of a skid-steer vehicle on horizontal ground where gravity is substituted by an equivalent external force in such a way that pitch and roll are kept constant. Relevant tread ICR variations on inclined ground have been deduced, which have a significant impact on skid-steer kinematics. These new findings have been corroborated experimentally with a four-wheeled mobile robot that turns on an inclined plane.

Overvoltage instability is a growing concern in a standalone low-voltage (LV) microgrid (MG) with non-dispatchable intermittent renewable energies such as residential and commercial photovoltaic generators (PVGs). Several overvoltage controllers used in PV arrays have adopted the concept of standard deviation from the maximum power point (MPP) to curtail the generated power. However, these solutions lack presenting analytical expression for the MPP deviation size, settings tuning independent of the MG’s/PV’s characteristics, scalability, and accurate power-sharing in the same control structure. To overcome these limitations, this paper proposes a new analytical MPP tracking (MPPT)-based overvoltage and power-sharing control method using the series equivalent resistance of the PV module model. By applying this analytical expression, the size of the PV array voltage shift to the right-hand side of the MPP is obtained in terms of overvoltage level, while all PVGs proportionally curtail the active power output. The effectiveness of the proposed methodology is shown in various low-demand and high-PV generation cases through a real time digital simulator (RTDS) platform. In addition to the fast and accurate performance, the presented method benefits from the straightforward and communication-free structure as it solely exploits the point of common coupling (PCC) voltage. Also, the method’s threshold does not require re- tuning after MG restructure, ensuring scalability. Without relying on other microgrid facilities, the proposed methodology is accordingly an effective solution for practical PV-based LV MGs.

Rod pumping systems typically require the analysis of dynamometer cards for fault diagnosis. While external instrumentation assists in obtaining these cards, it simultaneously raises monitoring costs and complexity. To address this issue, this paper introduces a parameter estimator that integrates the equivalent circuit model of an induction motor with the beam pumping unit model. We have compared the performance of two practical estimators, utilizing the terminal quantities of the driving motor as inputs. The results demonstrate surface dynamometer cards under varying operational conditions of the oil well. By augmenting the estimator’s input variables, the estimated cards align more closely with the actual ones. This practical application proposes an alternative method for acquiring the surface dynamometer card, which can function as a supplementary approach in fault diagnostics and contribute to informed maintenance decisions for the pumping unit.

Prostate cancer (PCa) is one of the leading causes of cancer-related mortality among men worldwide. Accurate and efficient segmentation of clinically significant prostate cancer (csPCa) regions from magnetic resonance imaging (MRI) plays a crucial role in diagnosis, treatment planning, and monitoring of the disease, however, this is a challenging task even for the specialized clinicians. This study presents SAM-UNETR, a novel model for segmenting csPCa regions from MRI images. SAM-UNETR combines a transformer-encoder from the Segment Anything Model (SAM), a versatile segmentation model trained on 11 million images, with a residual-convolution decoder inspired by UNETR. The model uses multiple image modalities and applies prostate zone segmentation, normalization, and data augmentation as preprocessing steps. The performance of SAM-UNETR is compared with three other models using the same strategy and preprocessing. The results show that SAM-UNETR achieves superior reliability and accuracy in csPCa segmentation, especially when using transfer learning for the image encoder. This demonstrates the adaptability of large-scale models for different tasks. SAM-UNETR attains a Dice Score of 0.467 and an AUROC of 0.77 for csPCa prediction.

In this study, two models of multilayer quaternionic feedforward neural networks are presented. Whereas the first model is based on quaternion algebra, the second model uses split quaternion algebra. For both quaternionic neural networks, a learning algorithm was derived using an adaptation of the extended Kalman filter. In addition, to analyze the performance of these two neural network models, they were applied to address the problem of enhancing low-light color images, which for this work consists particularly in the recovery of illuminated color images by quaternionic neural network processing from underexposed images. The quaternion neural network enhances images in the RGB color space (Euclidean metric), whereas the split quaternion neural network enhances images in the HSV color space (Minkowski metric). From the results, we can observe that the split quaternion neural network using the HSV color model shows advantages that were not previously published and were not shown by the quaternion neural network using the RGB color model. Therefore, this article introduces a novel quaternionic neural network that uses the Minkowski metric for color image processing, which can be advantageously used by practitioners interested in working with the HSV color model.

A cataract is a medical condition causing an opacity in the ocular nucleus due to various factors such as age and diseases. Starting from traditional image processing techniques for processing and extracting relevant features, using computational intelligence methods is essential to help experts in the medical pre-diagnosis for automatic classification and grading of the disease. However, the learning capabilities of such automated processes rely considerably upon the availability of adequately-labeled databases approved by medical experts. Considering the shortage of available public databases for implementing potential algorithms such as Deep Learning, this work presents a new nuclear cataract database composed of 1437 labeled images for multi-level classification according to the LOCS III system. The images were obtained and correctly classified by experts from an ophthalmologic medical center in Mexico City. Also, our research compares relevant Machine Learning algorithms employed for medical images like Support Vector Machines, Deep Learning structures like GoogLeNet, and our proposed Deep Learning Structure with the highest classification rates for the two and multiple cataract levels according to LOCS III.

Transverse flux machines have the potential to offer high torque density in direct-drive vehicle traction applications. Besides, sizing equations are a wide-spread technique for transverse flux machines design, as their computational cost is much lower than the finite element method. In this paper a novel analytical sizing methodology for transverse and radial flux machines is presented, focusing on the current load and the pole length factor as the main design parameters. The motor specifications are intended for a light-duty electric vehicle application. As transverse flux machines have a single, hoop-shaped coil per phase that embraces the flux of all the pole pairs, their principle of operation and therefore their sizing equations differ from radial flux machines. The proposed analytical method allows to compare transverse and radial flux machines easily through a similarity analysis and a parametric study. Furthermore, the discrepancies between the analytical model and the finite element method are quantified and then included in previous equations. Then the analytical model is optimized with a multiobjective genetic algorithm in the final stage. According to the sizing methodology presented here, transverse flux machines have a superior performance than radial flux machines in terms of torque density and efficiency.

Accurate net load forecasting is a cost-effective technique, crucial for the planning, stability, reliability, and integration of variable solar photovoltaic (PV) systems in modern power systems. This work presents a direct short-term net load forecasting (STNLF) methodology for solar-integrated microgrids by leveraging machine learning (ML) principles. The proposed data-driven method comprises of an initial input feature engineering and filtering step, construction of forecasting model using Bayesian neural networks, and an optimization stage. The performance of the proposed model was validated on historical net load data obtained from a university campus solar-powered microgrid. The results demonstrated the effectiveness of the model for providing accurate and robust STNLF. Specifically, the optimally constructed model yielded a normalized root mean square error of 3.98% when benchmarked using a 1-year historical microgrid data. The $k$ -fold cross-validation method was then used and proved the stability of the forecasting model. Finally, the obtained ML-based forecasts demonstrated improvements of 17.77% when compared against forecasts of a baseline naïve persistence model. To this end, this work provides insights on how to construct high-performance STNLF models for solar-integrated microgrids. Such insights on the development of accurate STNLF architectures can have positive implications in actual microgrid decision-making by utilities/operators.

System dynamic models for hundreds of inverter-based generators are necessary to represent the whole behavior and to perform stability analysis at the transmission and distribution level in the electric power system. Aggregated models such as DER_A and PVD1 have been proposed, however, they have many parameters and there is currently no methodology to parameterize them. Many of the parameterization methods for this type of model require only smooth functions. Because these models have non-linear blocks, such as saturation and dead-band functions, this paper proposes a smooth mathematical representation of the DER_A aggregated model. The proposed smooth mathematical representation uses a novel smooth function proposed to represent the saturation function and further uses a proposed method to obtain a smooth dead-band function from the proposed smooth saturation function. Finally, the impact of the use of smooth functions on the dynamics of the DER_A model states is experimentally presented and it is also demonstrated by means of electrical signals that the proposed smooth mathematical representation can represent the dynamics of the aggregated DER_A model, paving a way for future research on parameter identification and stability assessment of the aggregated inverter-based generation models.

The Smart Factory has been a concept studied during the last decade that has not been standardized yet; for this reason, the academy and industry have developed a wide variety of new architectures that describe the integration of elements for digitization and interconnection. The present research aims to introduce a new architecture proposal for migrating traditional (automation) to smart (digitization) factories, implemented through open-source software. The proposed architecture is integrated, for the first time, by the interconnection of six main elements: cyber-physical systems, edge computing, artificial intelligence, cloud computing, data analytics, and cybersecurity; the research describes in detail their definitions, sub-elements, the interconnection between elements, and the minimum requirements for implementation. The test of the proposed smart factory was done through a scale smart factory pilot testing for a pick and place process, where the assembly of wood pieces from the geometric Tangram’s puzzle was required; for this reason, the pilot testing includes a six-degree-of-freedom robot arm, a conveyor, a vision system, and a storage area. The case study conducted in this research allowed the assembly of four puzzles (fish, house, rocket, and swan) that were assembled with four different batches of pieces. The implementation allowed testing flexibility and adaptability. The final assembly reports included the status of assembly, the number of pieces assembled, the number of pieces stored, the assembly sequence, and the assembly time. Similarly, the development of the SCADA system allowed asset control as well as asset monitoring. The KPIs of the assembly process measured productivity (OTD) and time tracking (ATCT and TA) of the 16 tests, founding that the interconnection and digitization of the scale manufacturing cell were fully integrated and allowed repeatability; the proposed SF architecture represents an alternative for the small and medium automated factories to achieve interconnection and digitization, and it is ready to be tested in a more complex scenario.

This paper deals with the design of a robust controller to attenuate matched and unmatched uncertain dynamics as well as external disturbances effects by considering the actuator bandwidth to stabilize the mechanical dynamics of an Unmanned Aerial Vehicle. To this end, the performance of a sliding mode controller is improved with the combination of the attractive ellipsoid method. Likewise, it is guaranteed that the system trajectory arrives into a minimal size invariant set in finite time by using a workable control input. Finally, in order to evaluate the effectiveness of the proposed control approach, a comparative study with a robust Proportional Derivative controller, an integral sliding mode controller and a dynamic sliding mode controller with Proportional Integral Derivative sliding surface was conducted. In order to validate the effectiveness of the proposed controllers, the dynamics of a multirotor aircraft was used to conduct numerical simulations.

This study presents a method based on elementary logic and arithmetic operations to enhance the cryptographic properties of Substitution Boxes (S-Boxes). S-Boxes are a crucial component of cryptosystems, as they apply the confusion principle to information before it is encrypted, making them vital for ensuring the security of sensitive information transmitted through insecure channels. The proposed method employs bitwise XOR, Modular Addition, and Circular Shift operations, which are applied to selected S-Boxes, resulting in numerous S-Box variants that have no fixed points or reverse fixed points. We found that some of these variants can increase nonlinearity when using modular addition or circular shift operations and are therefore more suitable for use in cryptosystems. Our study contributes to the understanding of how S-Boxes can be enhanced by elementary logic and arithmetic operations. We recommend using the proposed method with the bitwise XOR operation when the S-Box has high nonlinearity (112) but requires removing fixed points and reverse fixed points. Otherwise, first use modular addition or circular shift operations to increase nonlinearity.

Studies on robotic interventions for gait rehabilitation after stroke require: (i) rigorous performance evidence; (ii) systematic procedures to tune the control parameters; and (iii) combination of control modes. In this study, we investigated how stroke individuals responded to training for two weeks with a knee exoskeleton (ABLE-KS) using both Assistance and Resistance training modes together with auditory feedback to train peak knee flexion angle. During the training, the torque provided by the ABLE-KS and the biofeedback were systematically adapted based on the subject’s performance and perceived exertion level. We carried out a comprehensive experimental analysis that evaluated a wide range of biomechanical metrics, together with usability and users’ perception metrics. We found significant improvements in peak knee flexion ( ${p} = {0}.{0016}$ ), minimum knee angle during stance ( ${p} = {0}.{0053}$ ), paretic single support time ( ${p} = {0}.{0087}$ ) and gait endurance ( ${p} = {0}.{022}$ ) when walking without the exoskeleton after the two weeks of training. Participants significantly ( ${p} < {0}.{00025}$ ) improved the knee angle during the stance and swing phases when walking with the exoskeleton powered in the high Assistance mode in comparison to the No Exo and the Unpowered conditions. No clinically relevant differences were found between Assistance and Resistance training sessions. Participants improved their performance with the exoskeleton (24-55 %) for the peak knee flexion angle throughout the training sessions. Moreover, participants showed a high level of acceptability of the ABLE-KS (QUEST 2.0 score: 4.5 ± 0.3 out of 5). Our preliminary findings suggest that the proposed training approach can produce similar or larger improvements in post-stroke individuals than other studies with knee exoskeletons that used higher training intensities.

Lossy compression solutions have grown up during the past decades because of the increment of the data rate in the new-generation hyperspectral sensors; however, linear compression techniques include useless information on regions of little interest for the final application and, at the same time, scarce information on areas of interest. In this article, a transform-based lossy compressor, HyperLCA, has been extended to include a runtime adaptive distortion feature that brings multiple compression ratios in the same scenario. The solution has been designed to keep the same hardware-friendly feature, just as its previous version, specifically conceived to ease the deployment of the solution on reconfigurable hardware devices (FPGAs). The experiments demonstrate that the new version of the compressor is able to process 1024 × 1024 hyperspectral images and 180 spectral bands (377.5 MB) in 0.935 s with a power consumption of 1.145 W. In addition, experimental results also reveal that our architecture features high throughput (MSamples/s) and remarkable energy-efficiency (MB/s/W) tradeoffs, $10\times$ and $6\times$ greater than the best state-of-the-art solution, respectively.

Following a car accident, an insurance company must assess the level of damage to each vehicle to decide on the compensation paid to the insurance customer. This assessment is usually performed by manual inspection, which is costly and time-consuming. Automatic car damage assessment using image data is an under-addressed problem highly relevant to the insurance industry. Although there have been many attempts at solving particular aspects of this problem, we are unaware of any complete solutions available. In this work, we propose a pipeline that uses photographs of a damaged car, collected by the users from multiple angles, together with structured data about the vehicle, to estimate damage severity following an accident. Our proposed pipeline consists of several computer-vision models for the detection of damage and the determination of its extent. Unlike existing approaches in car damage assessment, we use semantic segmentation to understand which parts of the car are damaged, and to what extent. We then extract computer-vision features, indicating the location and severity of damage to each exterior panel, together with structured data, to arrive at an accurate damage cost estimation. We train and evaluate this model on a large dataset of historical insurance claims with known outcomes, all captured in the wild with mobile-phone hardware.

The performance of induction cooktops (inductor and electronic power converter) is closely related to the inductive properties of the cookware used. Traditionally, they are designed to work optimally with fully ferromagnetic cookware. However, multimaterial cookware with a bottom surface composed of a ferromagnetic material and small pieces of aluminum are nowadays more commonly used. Designing cooktops to also work optimally with this cookwares requires identifying the equivalent parameters, $R_{\text {eq}}$ and $L_{\text {eq}}$ , obtained from the electromagnetic models of the inductor-load system. Modeling multimaterial cookware, with a large number of inserts, complicates the model design and increases its computational cost. This work presents an equivalent model for multimaterial loads that allows the evaluation of the inductor performance and obtaining the equivalent parameters quickly and accurately. The multimaterial cookware is modeled as a disk of uniform material with equivalent electromagnetic properties, $\mu _{\text {r,eq}}$ and $\sigma _{\text {eq}}$ , which depend on the properties of each material and the proportion of area they occupy. The equivalent model has been validated by electromagnetic simulation using a FEA tool and by experimental results. Finally, based on the results obtained, an analysis has been carried out to evaluate the importance of design factors such as the choice of the cookware base material and the size, arrangement, and number of inserts.

Non-Orthogonal Multiple Access (NOMA) has emerged as a promising strategy for increasing spectral efficiency in wireless multiuser communications. The performance of NOMA highly depends on the users’ channel conditions, being enhanced when these are significantly different, i.e., one strong user and one weak user. On the contrary, rate fairness is compromised when users present similar channel conditions since the maximization of the sum capacity may result in the allocation of most resources to one user. In general, this problem can be avoided with correct user grouping. However, there are scenarios, e.g., picocells or femtocells, where finding users with distinctive channel conditions is not always possible. In this paper, we study the application of beamforming in a two-user Multiple-Input-Single-Output (MISO) downlink NOMA system to achieve rate fairness through channel shaping even when the conditions of both users are similar. The proposed formulation includes the effect of Near-Field (NF) radiation, which yields an accurate modeling of the problem at hand in a small-cell scenario. We use an optimization algorithm to jointly calculate both the power allocation and the complex weights to be applied to the elements of a given array. Numerical simulations across scenarios with distinctive or similar channel conditions show that the proposed approach outperforms alternative NOMA methods in ensuring rate fairness. Additionally, it yields improved overall rates compared to Far-Field (FF) formulation-based modelling and beamforming Time Division Multiple Access (TDMA) solutions.

This article presents a software platform (SP) that helps generate convolutional and feed-forward neural networks and a parametric identification algorithm is proposed for a Cartesian robot using convolutional neural networks (CNN) generated and trained with the proposed SP. The user interface is friendly and aids in developing convolutional and feed-forward neural networks. The SP is made in LAB VIEW®. The user does not need the complete knowledge of mathematics used to perform the training or execution of the network or the programming skills to perform the code that performs such tasks. The SP is designed to reduce the deployment time of neural networks, providing the user with a graphical interface that guides the user through the formation and development of the neural network, this is one of the main contributions. The SP interface is described in this article, showing all the options offered. Five neural networks are presented to prove and demonstrate the software platform’s use. The dynamic models of the Cartesian robot are used; one has six parameters and the other ten parameters. The maximum similarity achieved by the identification algorithm with the six-parameter dynamic model was 99.15% and 99.92% for the ten-parameter model; both are numerical torque analyses. A real Cartesian robot was identified, and five experimental torques were reconstructed for each axis; the maximum similarity was 97.87%. The proposed algorithm is compared with least squares, which obtain 95.81%. Therefore, the results show that the proposed method generates better parametric identification.