Search

Assessing the financial risks is an essential component of portfolio management. This assessment involves the employment of one or more risk measures, i.e., quantitative coefficients employed to capture how risky a portfolio is. As the risk measures are important both to create and evaluate portfolios, it is imperative to understand their characteristics and possible shortcomings. This study analyzes six risk measures: variance, value at risk (VaR), conditional value at risk (CVaR), expectile-based value at risk (EVaR), omega ratio, and Sortino ratios. As a first step, closed form solutions were calculated for all measures, as function of the variance and mean of a simple distribution. In a second moment, the risk measures behavior was studied when the mean and variance are kept constant and only the worst scenarios are displaced. Their behavior was then studied numerically for two more examples: the Johnson’ $S_{U}$ distribution and the Brazilian energy market. Among the risk measures analyzed, CVaR and EVaR are the only ones that are invariant to mean and with proper sensitivity to variance and displacement of worst scenarios.

This paper evaluates the submodule capacitor current and voltage ripple of a direct three-phase to single-phase ac/ac MMC under unbalanced grid conditions. The submodule capacitor RMS current and the necessary capacitance to maintain a desired voltage ripple are determined, which can be used to dimension the ac/ac MMC's submodule capacitors. The derived analytical expressions are evaluated under unbalanced grid conditions using three well-established current control techniques. The analysis is validated through simulations and measurements for a phase-to-ground fault.

Unmanned Aerial Vehicles (UAVs) play a crucial role in delivering life-saving supplies, such as medication and food, to remote or hazardous locations, including areas affected by conflicts and natural disasters. This research focuses on the complex challenges of planning UAV routes in high-risk environments, where real-time adjustments to flight strategies are often necessary to ensure mission success and the safety of the UAVs. As a case study, we consider scenarios involving UAVs delivering essential aid to vulnerable groups in unsafe areas, which presents unique logistical challenges. To address these issues, we propose a novel model based on Safe Path Prioritization, which emphasizes the selection of previously flown and confirmed safe paths over sending UAVs into unknown, potentially dangerous areas. Our innovative approach combines two advanced tools for efficient route planning: Rapidly-Exploring Random Trees (RRT) for effective pathfinding and a genetic algorithm-based mechanism for optimizing routes. Additionally, the model utilizes a dynamic risk map to enhance decision-making, ensuring that UAVs aim to visit the closest beneficiary groups while accounting for critical constraints such as battery consumption. The proposed method was rigorously validated through extensive computer simulations, which varied configurations, including the number of beneficiary groups, UAVs, and unsafe zones. The results demonstrated a significant improvement in operational effectiveness: specifically, there was a 28% increase in the number of beneficiary groups visited and a remarkable 71% increase in successful deliveries, even under less favorable conditions that necessitated longer flight paths. Conversely, in scenarios deemed less challenging, UAVs tended to reduce visits to beneficiary groups, prioritizing safer but lengthier routes. Overall, our findings illustrate that Safe Path Prioritization is a reliable and effective method for completing missions where both UAV preservation and timely aid delivery to beneficiary groups are of paramount importance.

This paper aims to study the effects of impedance mismatch in low-power Radio Frequency Energy Harvesting (RFEH) systems caused by the dependence of Schottky diode input impedance on temperature and propose solutions to mitigate them. Thus, the effects of temperature variation on impedance matching and Radio Frequency (RF) to Direct Current (DC) Power Conversion Efficiency (PCE) will be analyzed through the design, simulation and measurement of an RF rectifier to operate at low input power levels in the 2.4 GHz Industrial, Scientific and Medical (ISM) band in two specific temperature ranges, one around the 300 K (reference ambient temperature) and other around the 325 K (higher temperatures). In order to solve the problem of impedance mismatch due to the temperature dependence of the Schottky diode, the RF rectifier is designed with an Input Matching Network (IMN) with trimming of the stubs in parallel that can be enabled or disabled to set up the desired network and operate according to the temperature of the location. Considering an input power ( $P_{in}$ ) of −20 dBm, the PCE obtained with the prototype configured for room temperature ( $P_{300}$ ) and for high temperature ( $P_{325}$ ) are of 14.73% and 10.53% at 283 K, 16.72% and 16.15% at 303 K, 12.74% and 15.39% at 323 K and 5.82% and 11.67% at 343 K, respectively. As possibly expected by this proposal, the results indicate a higher and more stabler PCE at high temperatures in the prototype configured for 325 K while at room temperature the PCE is higher and more stabler in the prototype configured for 300 K.

Progressively more advanced and complex models are proposed to address problems related to computer vision, forecasting, Internet of Things, Big Data and so on. However, these disciplines require preprocessing steps to obtain meaningful results. One of the most common problems addressed in this stage is the presence of missing values. Understanding the reason why missingness occurs helps to select data imputation methods that are more adequate to complete these missing values. Missing at Random synthetic generation presents challenges such as achieving extreme missingness rates and preserving the consistency of the mechanism. To address these shortcomings, three new methods that generate synthetic missingness under the Missing at Random mechanism are proposed in this work and compared to a baseline model. This comparison considers a benchmark covering 33 data sets and five missingness rates $(10\%, 20\%, 40\%, 60\%, 80\%)$ . Seven data imputation methods are compared to evaluate the proposals, ranging from traditional methods to deep learning methods. The results demonstrate that the proposals are aligned with the baseline method in terms of the performance and ranking of data imputation methods. Thus, three new feasible and consistent alternatives for synthetic missingness generation under Missing at Random are presented.

In real-world multi-objective optimization, dealing with many objectives and a large number of solutions is a common challenge that complicates data visualization and analysis. This study aims to simplify decision-making by analyzing tools to better explore Pareto optimal solutions in many-objective scenarios, integrating clustering, filtering, and ranking with existing graphics techniques. The dynamic combination of these tools should reduce complexity and highlight significant patterns in the data set, allowing decision-makers to tailor the visualization to their specific needs and preferences. Central to the approach presented in this work is the innovative application of shape-based clustering to organize the solution set and the use of this clustering to define distinct types of filters. Additionally, ranking methods originally proposed to enhance search in many-objective evolutionary algorithms are used here to identify the best solutions based on predefined criteria in combination with other techniques. The efficacy of the proposed integrated approach was evaluated using an application developed with this aim and considering a five-objective problem as a case study. The analysis suggests that using these combined strategies aids interactive visual exploration, effectively reducing solution volume and improving data understanding, potentially facilitating decision-making tasks.

The intrinsic challenges of contemporary marketing encourage discovering new approaches to engage and retain customers effectively. As the main channels of interactions between customers and brands pivot between the physical and the digital world, analyzing the outcome behavioral patterns must be achieved dynamically with the stimulus performed in both poles. This systematic review investigates the collaborative impact of adopting multidisciplinary fields of Affective Computing to evaluate current marketing strategies, upholding the process of using multimodal information from consumers to perform and integrate Sentiment Analysis tasks. The adjusted representation of modalities such as textual, visual, audio, or even psychological indicators enables prospecting a more precise assessment of the advantages and disadvantages of the proposed technique, glimpsing future applications of Multimodal Artificial Intelligence in Marketing. Embracing the Preferred Reporting Items for Systematic Reviews and Meta-Analysis as the research method to be applied, this article warrants a rigorous and sequential identification and interpretation of the synergies between the latest studies about affective computing and marketing. Furthermore, the robustness of the procedure is deepened in knowledge-gathering concerning the current state of Affective Computing in the Marketing area, their technical practices, ethical and legal considerations, and the potential upcoming applications, anticipating insights for the ongoing work of marketers and researchers.

Active fire segmentation through satellite imagery is fundamental to prevention and damage prediction. Algorithms to address this problem usually rely on sensor-specific thresholds, empirically chosen based on a few image samples, and thus, are susceptible to many errors. Deep learning algorithms automatically extract information through various levels of abstraction, avoiding human intervention for feature engineering. However, training a deep network from scratch requires massive labeled data, and efforts in this direction have already been made for the Landsat-8 satellite. For Sentinel-2, another important satellite that has band wavelength similarities with Landsat-8, there is a limited number of such initiatives, with few studies even concerning hand-crafted (traditional) algorithms. In this context, we explored in this article the transfer of knowledge for active fire segmentation from Landsat-8 to Sentinel-2, avoiding the need of a vast amount of labeled data from Sentinel-2, and also reducing the computational resources for training. We also compiled a benchmark containing 12 584 image patches extracted from 26 Sentinel-2 images from around the globe, along with manually annotated fire pixels, to assess the algorithm's response compared to a human specialist. In a series of transfer learning experiments by using the U-Net architecture, we showed that even a single labeled image from Sentinel-2 for training was sufficient to allow achieving an $F$-score metric of 84.9% when Landsat-8 knowledge is transferred and further fine-tuned in the machine learning process, while the best hand-crafted algorithm designed for Sentinel-2 achieved an $F$-score of 75.8% in the segmentation task.

Energy efficiency has become a significant challenge for manufacturing companies. Although it is possible to improve efficiency by applying new and more efficient machines, decision makers tend to look for less expensive alternatives. Furthermore, the current reality of manufacturing companies, brought about by Industry 4.0, requires more flexibility of production systems and increase the complexity off machine rescheduling without compromising sustainable requirements. This study contributes to the subject by applying machine learning techniques in a job shop to reduce the makespan and estimate the total energy consumption. First, an artificial neural network (ANN) was trained to estimate the total electrical energy consumption in the system. A new input variable for the network was defined to assist in energy estimation. This variable is called the Priority Factor (PF) and helps capture the different patterns in the job shop. Second, as the ANN was trained, a Genetic Algorithm (GA) was used to reduce the makespan. Therefore, it is possible to reduce the makespan and know in advance the total electricity consumption in production. This solution supports a more sustainable manufacturing process, and is completely developed in a digital manufacturing environment.

This paper introduces the Kabsch Marker Estimation Algorithm (KMEA), a new, robust multi-marker localization method designed for Autonomous Mobile Robots (AMRs) within Industry 4.0 (I4.0) settings. By integrating the Kabsch Algorithm, our approach significantly enhances localization robustness by aligning detected fiducial markers with their known positions. Unlike conventional methods that rely on a limited subset of visible markers, the KMEA uses all available markers, without requiring the camera’s extrinsic parameters, thereby improving robustness. The algorithm was validated in an I4.0 automated warehouse mockup, with a four-stage methodology compared to a previously established marker estimation algorithm for reference. On the one hand, the results have demonstrated the KMEA’s similar performance in standard controlled scenarios, with millimetric precision across a set of error metrics and a mean relative error (MRE) of less than 1%. On the other hand, KMEA, when faced with challenging test scenarios with outliers, showed significantly superior performance compared to the baseline algorithm, where it maintained a millimetric to centimetric scale in error metrics, whereas the other suffered extreme degradation. This was emphasized by the average reduced results of error metrics from 86.9% to 92% in Parts III and IV of the test methodology, respectively. These results were achieved using low-cost hardware, indicating the possibility of even greater accuracy with advanced equipment. The paper details the algorithm’s development, theoretical framework, comparative advantages over existing methods, discusses the test results, and concludes with comments regarding its potential for industrial and commercial applications by its scalability and reliability.

In this paper, we propose iterative interference cancellation schemes with access points selection (APs-Sel) for cell-free massive multiple-input multiple-output (CF-mMIMO) systems. Closed-form expressions for centralized and decentralized linear minimum mean square error (LMMSE) receive filters with APs-Sel are derived assuming imperfect channel state information (CSI). Based on the derived expressions, insights are drawn and general expressions are devised for several cases, namely: firstly, MMSE-SIC filter for the non-scalable CF-mMIMO that uses all APs. Secondly, an MMSE-SIC filter assuming perfect channel state information. Thirdly, in this case we assume no interference cancellation and the linear MMSE filter is obtained. Additionally, we formulate a new Gaussian approximation of the likelihood function by deriving new closed-form expressions for the second order statistics (mean and variance) of the detected signal parameters in presence of channel estimation errors, APs-Sel matrix and multi-user interference (MUI). Since the MMSE-SIC filter experiences error propagation due to erroneous decisions from the previous stages, we develop a list-based detector based on LMMSE receive filters for CF-mMIMO systems that exploits interference cancellation and the constellation points to mitigate the error propagation that occurs in conventional MMSE-SIC receivers. An iterative detection and decoding (IDD) scheme that employs low-density parity-check codes is then developed. Moreover, log-likelihood ratio (LLR) refinement strategies based on censoring and a linear combination of local LLRs are proposed to improve the network performance. We assess the proposed centralized and decentralized IDD schemes against existing approaches in terms of bit error rate performance, complexity, and signaling under perfect CSI and imperfect CSI and verify the superiority of the distributed IDD architecture with LLR refinements.

We propose a transverse magnetic (TM) pass polarizer based on a periodic waveguide on a silicon-on-insulator platform. The design is implemented on a 500nm-thick silicon layer surrounded by SiO2. The polarizer operates in the mid-infrared (MIR) wavelength range of $\mathrm {3.1~ \mu \text {m} }~\text {to}~\mathrm {3.6~ \mu \text {m} }$ , a crucial band for chemical and biological sensing, as well as environmental monitoring. While there is extensive documentation on polarizers in the near-infrared (NIR), there is a significant scarcity of research reports on polarizers in the MIR. This proposed polarizer demonstrates outstanding performance, characterized by ultra-low loss for the transmitted TM mode, minimal reflections of the undesired transverse electric (TE) mode, and exceptionally high loss for the transmitted TE mode. The TM insertion loss remains below 0.5dB over a wavelength range of $\mathrm {3.2~ \mu \text {m} }~\text {to}~\mathrm {3.6~ \mu \text {m} }$ , as the TM mode operates in the subwavelength and low-loss radiation regimes. The transmitted TE power is remarkably small, falling below −30dB over a 300nm wavelength range. This is attributed to the TE mode operating in the high-loss radiation regime and the band gap region of the dispersion diagram. Furthermore, the reflected power of the undesired TE mode is significantly reduced (below −20dB) by incorporating the periodic waveguide in a directional coupler setup. The footprint of the polarizer is compact, measuring just $\mathrm {30\,\, \mu \text {m} }\,\,\times \,\,\mathrm {7\,\, \mu \text {m} }$ .

Open-set segmentation has caught the community’s attention only in the last few years, and it is a growing and active research area with many challenges ahead. To better identify open-set pixels, we address two known issues by improving data representation and ensuring semantic consistency in open-set predictions. First, we present a method called Open Gaussian Mixture of Models (OpenGMM) that allows for multimodal statistical distributions in known class pixels using a Gaussian Mixture of Models instead of unimodal approaches, like Principal Component Analysis. The second approach improved semantic consistency by applying a post-processing technique that uses superpixels to enforce homogeneous regions to have similar predictions, rectifying erroneously classified pixels within these regions and providing better delineation of object borders. We also developed a novel superpixel method called Fusing Superpixels for Improved Semantic Consistency (FuSC) that produced more homogeneous superpixels and enhanced, even more, the open-set segmentation prediction. We applied the proposed approaches to well-known remote sensing datasets with labeled ground truth for semantic segmentation tasks. The proposed methods improved the highest AUROC quantitative results for the International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen and Potsdam datasets. Using FuSC, we achieved novel open-set state-of-the-art results for both datasets, improving AUROC results from 0.850 to 0.880 (3.53%) for Vaihingen and 0.764 to 0.797 (4.32%) for Potsdam datasets. The official implementation is available at: https://github.com/iannunes/FuSC.

This article reports on the development of key components required for a self-powered oscillator unit designed to wirelessly transmit its signal under full insertion in high-temperature (HT) harsh-environments (HE), such as those present in power plants and industrial settings (metallurgic, oil extraction, molding, and aerospace). The oscillator employed a silicon carbide power transistor and HT passive components on a screen-printed alumina circuit board capable of operation beyond 300 °C. The HT oscillator circuit was powered solely by in-situ energy-scavenging thermoelectric generator (TEG) modules using passive cooling, eliminating the need for an external power supply or active cooling. In addition, a silicon-based external booster circuit was used to achieve the required TEG voltage regulation to test the TEG-powered HT oscillator circuit. The TEG-powered oscillator circuit was tested inside a nonmetallic furnace from room temperature to over 300 °C for transmission of a wireless signal, which was detected outside the furnace at 11 ft (3.4 m). Such a wireless transmitting system powered only by in-situ TEGs, with no requirement for external power or active cooling, is very attractive for flexible, mobile standalone control and sensor units targeted for operation in HT HE conditions found in power plants and industrial settings.

Introducing Myrmex, a hexapod robot designed for autonomous locomotion on unstructured terrains. It was developed a whole-body kinematics model that enables both open-chain and closed-chain control of the robot. This model enhances the flexibility and mobility of the robot. At the moment, Myrmex relies solely on proprioception (encoders and IMU) for adapting its body posture. Despite these sensory limitations, we have successfully applied the model in static and dynamic situations. Static experiments have showcased increased flexibility, allowing the robot to access previously challenging locations. In dynamic scenarios, the hexapod has demonstrated its capability to traverse irregular terrains, effectively exploiting its body mobility. Myrmex adeptly adjusts its posture according to the terrain topology, maintaining the center of gravity projection along the body’s centerline (i.e., same as it in the level walk), thus preserving stability margins during gait. The robot was able to correct its posture on terrain with gradients in any direction relative to the body structure, with only 3 DoF per leg. Importantly, our experiments have underscored the robot’s ability to maintain its posture even in the face of unexpected disturbances in its legs, emphasizing the robustness and reliability of the model.

Intelligent Transport Systems (ITS) have provided new technologies to protect human life, speed up assistance, and improve traffic, to aid drivers, passengers, and pedestrians. Vehicular Ad-hoc Networks (VANET) are the fundamental elements in an ITS ecosystem. However, its characteristics make the system susceptible to numerous attacks, such as Denial of Service (DoS). In this paper, we proposed a security system based on intrusion detection called Detection of Anomalous Behaviour in Smart Conveyance Operations (DAMASCO). We used a statistical approach to detect anomalies in vehicle-to-vehicle communication (V2V). The anomaly detection module addresses the Medium Access Control (MAC) sublayer to assess the number of packages sent to identify potentially malicious nodes, block their activity, and maintain a reputation list. The algorithm calculates the Median Absolute Deviation (MAD) to identify outliers and characteristics of DoS. Our experiments were performed in a simulated environment using a realistic urban mobility model. The results demonstrate that the proposed security system achieved a 3% false positive rate and no false negatives.

The widespread use of smartphones and other low-cost equipment as recording devices, the massive growth in bandwidth, and the ever-growing demand for new applications with enhanced capabilities, made visual data a must in several scenarios, including surveillance, sports, retail, entertainment, and intelligent vehicles. Despite significant advances in analyzing and extracting data from images and video, there is a lack of solutions able to analyze and semantically describe the information in the visual scene so that it can be efficiently used and repurposed. Scientific contributions have focused on individual aspects or addressing specific problems and application areas, and no cross-domain solution is available to implement a complete system that enables information passing between cross-cutting algorithms. This paper analyses the problem from an end-to-end perspective, i.e., from the visual scene analysis to the representation of information in a virtual environment, including how the extracted data can be described and stored. A simple processing pipeline is introduced to set up a structure for discussing challenges and opportunities in different steps of the entire process, allowing to identify current gaps in the literature. The work reviews various technologies specifically from the perspective of their applicability to an end-to-end pipeline for scene analysis and synthesis, along with an extensive analysis of datasets for relevant tasks.

This paper proposes a generalized predictive control (GPC) with constraints and orthonormal Laguerre functions using the simplified model of the primary system (reactor core and intermediate heat exchanger (IHX)) of a prototypical sodium fast reactor (SFR). This paper develops a multiple-input multiple-output (MIMO) GPC with input constraints able to track polynomial references of any degree applied in coolant temperature difference across the core and fractional power. The manipulated variables of the GPC-SFR are the reactivity and the sodium flow rate of the primary and secondary pipes. Moreover, orthonormal Laguerre functions and step down condition number techniques were also applied to avoid the numerical ill-conditioning issue in quadratic programming of large systems. Thus, a GPC type-2 was designed to control fractional power, coolant temperature difference across the core and sodium tank temperature of the SFR primary system when temperature references change according to a linear ramp after reaching their steady-state operation, sustaining 100% power operation on the reactor. In order to analyze the load tracking capability of the GPC-SFR type-2, the load following from 100% fractional power (FP) to 60% FP at 0.8% FP/min rate is simulated. Constraints on the rate of coolant temperature difference across the core and reactivity were applied for the design safety. For comparison criteria, this paper compares the GPC-SFR type-2 with the GPC-SFR type-1, i.e, standard model predictive control (MPC), to verify the viability and superior performance of the proposal regarding: (a) ramp-tracking capability of temperature and load; (b) the rejections of a reactivity disturbance of -1 cent and a secondary sodium inlet temperature disturbance of $+10 ^{o}F$ ; and (c) a simulation with uncertainty in reactor design. The simulations show that the GPC-SFR type-2 overcome the GPC-SFR type-1 robustness and performance.

The aim of this study is to introduce a virtual laboratory platform with metadata-based API for the creation of dynamic software components. Also, the study seeks to assess the platform’s validity and technological acceptance among the community of system developers. The platform is referred to as Esfinge Virtual Lab, and it has been developed utilizing the Java programming language. The platform has a general purpose and is demonstrated in this work in the context of system prototyping. Using declarative programming techniques and a metadata-based APIs, a software developer may focus on business principles and processes rather than expend energy on the retrieval of information or the programming of the user interface. The Esfinge Virtual Lab platform enables developers to efficiently produce diverse forms of data visualization with minimal coding effort. This includes the rapid generation of tables, graphs, maps, and personalized outputs. The components are packaged as Java Archive (JAR) files and uploaded onto the platform. The components that have been loaded can be accessed for execution and can be either injected or dynamically invoked for a new component, thereby facilitating code reuse. This study provides a comprehensive explanation of the platform, including its internal architecture and features. The deployment of the Esfinge Virtual Lab was demonstrated through two practical applications in Brazilian institutions, namely INPE and CEMADEN. A survey was performed to determine the validity of the platform, consisting of open-ended and closed-ended questions. The research used the Technology Acceptance Model (TAM) as a quantitative analytical instrument and thematic analysis as a qualitative analytical approach.

Organizations have been responding to possible disruptions in the organization and, at the same time, trying to increase customer satisfaction through digitising their processes. Thus, Intelligent Process Automation has been catching the latest trends in intelligent process automation due to the ease of use associated with data and requirements compliance; intelligent process automation is a step above regular automation as it mimics human behaviours and thought patterns to automate intelligently streamlines workflows and business processes. However, the constant introduction of technology via process automation in organizations can have positive and negative impacts on business continuity that need to be addressed. Although there are recent best practices, frameworks, guidelines, and standards, few studies focus on the relationship between these realms. The relationship between two sets of requirements, one for implementation practice and management methodology for intelligent software-based process automation, found in IEEE 2755.2-2020 and the other, ISO 22301-2019, about the business, to implement, maintain, and improve a management system to protect, reduce the likelihood of occurrence, prepare, respond, and recover from outages when they arise. This research is integrated into forthcoming areas for investigating the interplay between intelligent process automation and the continuity of business operations. Both are analysed and explained so that users can develop intelligent software-based process automation that complies with both frameworks in a way to embed continuity practices in an organization while optimizing business processes using Intelligent Process Automation. The study provides a bi-directional mapping for IEEE 2755.2:2020 and ISO 22301:2019, along with introducing a visual model to enhance their utility. It offers versatile applications, benefiting a wide range of stakeholders.

In the current golden age of multimedia, human visualization is no longer the single main target, with the final consumer often being a machine which performs some processing or computer vision tasks. In both cases, deep learning plays a fundamental role in extracting features from the multimedia representation data, usually producing a compressed representation referred to as latent representation. The increasing development and adoption of deep learning-based solutions in a wide area of multimedia applications have opened an exciting new vision where a common compressed multimedia representation is used for both man and machine. The main benefits of this vision are two-fold: i) improved performance for the computer vision tasks, since the effects of coding artifacts are mitigated; and ii) reduced computational complexity, since prior decoding is not required. This paper proposes the first taxonomy for designing compressed domain computer vision solutions driven by the architecture and weights compatibility with an available spatio-temporal computer vision processor. The potential of the proposed taxonomy is demonstrated for the specific case of point cloud classification by designing novel compressed domain processors using the JPEG Pleno Point Cloud Coding standard under development and adaptations of the PointGrid classifier. Experimental results show that the designed compressed domain point cloud classification solutions can significantly outperform the spatial-temporal domain classification benchmarks when applied to the decompressed data, containing coding artifacts, and even surpass their performance when applied to the original uncompressed data.

Recently, the two-dimensional (2D) fast Fourier transform (2D-FFT) filter bank (FB) technique was proposed as an alternative to new wireless communication technologies covering several application scenarios. This technique presents similar characteristics to orthogonal time-frequency space modulation (OTFS), such as lower PAPR and robustness in high mobility scenarios; in addition, thanks to the use of filter bank modulation, the technique has a good spectral localization. In this work, we present the generalization of the 2D-FFT FB system by making changes in the waveform structure to obtain advantages in the symbol detection process. The proposed idea allows the use of low-complexity equalizers in the time-frequency (TF) domain, bringing a good performance/complexity trade-off and obtaining bit error rate (BER) results of the same order than delay-Doppler domain receivers for OTFS. Theoretical and simulation results show that it is possible to obtain a good error performance in high mobility scenarios even using simple equalizers in the TF domain combined with waveform structure adjustments.

Training deep learning models for object detection usually requires a large amount of data, a condition that is not common for most real-world applications, especially in the context of aerial imagery. One possible solution is the use of simulators to generate synthetic data. For a good generalization, the model must be able to learn on the simulated data and perform correctly on the real data, process known as sim-to-real transfer. In this work, we analyze the generation of synthetic data to account for a data-scarce real-world scenario, which includes aerial imagery and object detection of transmission towers and their components. We evaluate the impact of image-to-image translation methods as domain adaptation techniques. In this analysis, we explore training strategies to mitigate the domain shift between synthetic and real data. According to our experimental results, the use of domain-adapted data through image-to-image translation could slightly improve the detection performance in real test data when compared to training with raw synthetic images only or with small datasets of real data, although it was noted through a visual analysis that objects with small bounding boxes, like clamp, anchoring clamp and ball link, could be distorted or vanished by the application of image-to-image translation methods. Additionally, when only a small subset of real data is available, training with both real and synthetic data at once led to better detection results, surpassing combinations of pre-training on synthetic and fine-tuning on real data.

This work addresses the application of the Genetic Algorithm (GA) technique to optimize the commutation angles of a 2 kW 8/6 switched reluctance machine (SRM). The primary goal is to reduce the well-known drawback of SRMs: the torque ripple. Firstly, the machine was modeled in Matlab /Simulink Ⓡ using lookup tables obtained via finite element method (FEM) simulations. Subsequently, the model was used to perform the GA routine aiming to find the optimal phase commutation angles that minimize the torque ripple factor. Notably, the torque performance of the SRM was significantly affected by the commutation angles during the search for the optimal solution. Afterwards, the GA results for four different operation points were verified experimentally through a developed drive platform with digital signal processor-based (DSP) control and an asymmetric bridge converter. As showed by the experiments, the proposed approach was suitable to reduce the torque ripple by more than 50% for one of the evaluated operating points. Furthermore, it was confirmed that the torque ripple mitigation led to acoustic noise improvement.

As society evolves as a whole, new demands arise with increasingly demanding prerequisites, consequently requiring more significant effort to be met. Such demands cover emerging applications, such as remote surgeries in Smart Health use cases, whose latency and reliability network requirements cannot be met by current communication systems; or simply improving current applications with more challenging requirements to be achieved, such as increasing the transmission rate in a mobile network, offering Quality of Service (QoS), and consequently, better user experience. Therefore, enabling technologies must be chosen to design an appropriate 6G architecture to address such demands. However, the explosion of emerging applications focused on different scopes and requirements to be met makes choosing these enabling technologies extremely complex and unpredictable. Thus, this article aims to create a methodology for analyzing the relevance of enabling technologies and use it to design an optimal architecture capable of meeting the 6G demands. For this purpose, two methods named as Average (AVG) and Analytic Hierarchy Process (AHP) have been selected, whose objective is to determine the relevance of an enabler for the 6G architecture, taking into account different degrees of influencing variables for this analysis, such as adherence to a certain architectural model; popularity in the research area; degree of innovation; synergy with other enablers; and support for requirements. Each of these methods presents a particular result. In the case of the AVG method, the criteria and variables are evaluated independently, and the arithmetic mean is employed to combine the evaluations into a single measure of suitability. In contrast, the AHP method considers the relative importance of criteria and variables in order to classify an optimal set of enabling technologies capable of fulfilling the key roles to be performed by a 6G architecture, and consequently meeting the main 6G demands. Our evaluation provides a unique perspective on 6G enablers, identifying issues and fostering research for future mobile architectures. The results obtained also provide researchers with the necessary information to stay updated on emerging enabling technologies and their suitability for designing new optimized 6G architectures.

In this article we carry out a comparison between early (feature) and late (score) multimodal fusion, for the two-class problem. The comparison is made first from a general perspective, and then from a specific mathematical analysis. Thus, we deduce the error probability expressions for the uncorrelated and correlated multivariate Gaussian distribution, assuming perfect model knowledge (Bayes error rates). We also deduce the corresponding expressions when the model is to be learned from a finite training set, demonstrating its convergence to the Bayes error rates as the training set size goes to infinite. These expressions also demonstrates that early fusion is the best option with model knowledge, and that both early and late fusion degrade due to a finite training set. This degradation is showed to be greater for early fusion due to the dimensionality increase of the feature space, so, eventually, late fusion could be a better option in a practical setting. The mathematical analysis also suggests the convenience of using a, so called, convergence factor, to quantify if a training set size is appropriate for the error probability to be close enough to the Bayes error rate. Different simulated experiments have been made to verify the validity of the mathematical analysis, as well as its possible extension to non-Gaussian models.

This paper presents a Graphical User Interface (GUI) Builder for embedded systems and Cyber-Physical Systems (CPSs). The hardware platforms used in CPSs may employ physical devices without graphical and user-input capabilities, or devices that may be placed on multiple remote locations, often with difficult physical access, that brings new challenges to GUI design. The proposed tool, integrated within the IOPT-Flow framework, enables a new approach to answer these challenges. This framework supports the development of embedded systems and distributed CPSs, offering a set of web-based tools for model edition, simulation, and implementation on physical devices. Systems are designed using graphical models combining Data-flows, Signals, and Petri nets, that permit the specification of remote communication channels just by drawing arcs. The new GUI Builder tool uses this infrastructure to automate the creation of graphical user interfaces for embedded systems and distributed CPSs, benefiting from a development with combined design, validation and automatic code generation methods. Finally, an application example of a power wheelchair controller integrating a GUI, is presented.

Distributed databases and data transformation mechanisms are highly relevant to Business Intelligence and Data Analytics. Most enterprise systems today have multiple and distributed databases, and the growing dissemination of Edge-Oriented architectures is driving this trend across many industries and business domains. The Entity-Relationship (ER) model is fundamental to modeling complex enterprise systems, but it has shortcomings. In particular, the ER model cannot represent data transport between different locations (or databases) of a system, nor can it conceptually express data transformation operations, such as aggregate and line functions, that are standard in data analytics. Therefore, we propose ER+, an extension of the ER model, where data distribution, data transport, data transformation, and information generation for distributed operational and analytical systems can be visually identified. The new ER+ representation has another important benefit, it provides the basis for transforming conceptual models into physical implementations of distributed data-oriented systems. This work introduces new concepts in ER modeling and illustrates their application. The practicality of the ER+ model is also demonstrated through the TPC-H benchmark.

Keyword Spotting (KWS) has been the subject of research in recent years given the increase of embedded systems for command recognition such as Alexa, Google Home, and Siri. Performance, model size, processing time, and robustness to noise are fundamental in these systems. Furthermore, applications in embedded systems demand computationally efficient models that can be implemented in current technology. In this work, an approach for keyword recognition is evaluated using three deep learning models namely LeNet-5, SqueezeNet, and EfficientNet-B0. We evaluate transfer learning, pruning and quantization strategies in training and test using noisy and clean speech signals. In addition, compression techniques such as pruning and quantization were assessed in terms of the size reduction of the model footprint and the accuracy obtained in each case. Using the Google’s Speech Commands dataset and additive babble noise signal, our keyword recognition approach achieves an accuracy of 94.6% using an unstructured pruning of 80% of the parameters of the original SqueezeNet network with a reduction of 70% in the model size.

This article aims to contribute for the improvement of low-power Radio Frequency Energy Harvesting (RFEH) designs based on Schottky Barrier Diode (SBD) rectifiers, presenting a study of the relationship between RF-DC Power Conversion Efficiency (PCE) and circuit temperature, which is directly related to the non-linear behavior of the metal-semiconductor junction of SBDs. For this purpose, SPICE diode models were revisited, evaluating the temperature dependence and its effects on forward and reverse conduction modes. The SBDs SMS7621 and SMS7630 temperature dependent characteristics are evaluated according the proposal, and their use is explored through analytical modeling and simulation analyzes of an RFEH system for temperatures ranging from 240 to 360 K. Hence, after an initial formulation of the optimum operation in terms of PCE, two series RF rectifiers are designed based on the mentioned diodes, aiming at an efficient operation over different temperature ranges according to each component optimum PCE, at 300 K for the SMS7630 and over 340 K for the SMS7621. For the SMS7630 prototype, the maximum measured PCE is 25.33% around 293 K, but decreases to 3.65% around 353 K, and for the SMS7621 the measured PCE goes from 11.56% to 16.34% in the same temperature range, considering −20 dBm as Input Power ( $P_{in}$ ) due to the low-power RFEH premise. The results leads to a higher PCE stability for the SMS7621 through the whole analyzed range, despite the overall PCE that is limited by the matching network losses intrinsic to the design.

Agriculture accounts for approximately 70% of the world’s freshwater consumption. Furthermore, traditional irrigation practices, which rely on empirical methods, result in excessive water usage. This, in turn, leads to increased working hours for irrigation pumps and higher electricity consumption. The main objective of this study is to develop and evaluate periodic model predictive control structures that explicitly account for on-off irrigation, a characteristic of drip irrigation systems where watering can be turned on and off, but flow cannot be regulated. While both proposed control structures incorporate an economic upper layer (Real Time Optimizer, RTO), they differ in the costs associated with the lower layer. The first structure, called Model Predictive Control for Tracking (MPCT), focuses on tracking effectiveness, while the second structure, called Economic Model Predictive Control for Tracking (EMPCT), incorporates the economic cost into the tracking term. These proposed structures are tested in a realistic case study, specifically in a strawberry greenhouse, and both show satisfactory performance. The choice of the best option will depend on specific conditions.

High mobility and intermittent connectivity of nodes are the main characteristics of Vehicular Ad-Hoc Networks (VANETs). These two aspects cause problems in traditional IP networking. Named Data Networking (NDN) is presented as one of the most promising paradigms for the future Internet. NDN is a data-centric architecture. It relies on data names instead of the host’s location to make forwarding decisions. In NDN, any node can be a candidate for supplying the desired content. This feature makes the NDN architecture appealing for VANET scenarios (V-NDN). This paper presents a strategy for applying NDN to VANETs with support for geographical-based forwarding. For this purpose, an additional layer called Vehicular Adaptation Layer (VAL), is proposed to illustrate how this can be performed without altering the NDN primitives and core structure. VAL provides: 1) a mechanism to bind NDN data names to the producers’ and consumers’ geographic areas; 2) a discovery mechanism to find producers’ areas and 3) the capability of implementing, in a plug-and-play manner, geo-forwarding algorithms capable of guiding Interests towards data producers and Data packets towards data consumers.

Diabetic retinopathy is one of the main causes of vision loss, and it can be identified through ophthalmological examinations that aim to locate the presence of retinal lesions such as Microaneurysms, Hemorrhages, Soft Exudates, and Hard Exudates. The development of computerized approaches to perform the instance segmentation of these lesions can help in the early diagnosis of the disease. However, the segmentation of instances of artifacts in the retina is a complex task due to factors such as object size and morphological characteristics. This article proposes a new approach based on a Mask Regions with Convolutional Neural Network features (Mask R-CNN) architecture to perform instance segmentation of lesions associated with diabetic retinopathy. The proposed approach was trained, adjusted, and tested using different public datasets of diabetic retinopathy, which were implemented with the Detectron2 libraries and OpenCV. The best result obtained by the proposed approach in the Dataset for Diabetic Retinopathy (DDR) was using Tilling and Adam optimizer, reaching a mean Average Precision ( $mAP$ ) of 0.2903 in the detection of fundus lesions for the limit of Intersection Over Union ( $IoU$ ) of 0.5 in the validation stage and an $mAP$ of 0.1670 in the detection of fundus lesions to the limit of $IoU$ of 0.5 in the test step. The results obtained in the experiments demonstrate that the proposed approach presented promising results in the instance segmentation of microaneurysms with an increase in precision, which in our case reaches approximately 16%.

The use of Unmanned Aerial Vehicles (UAVs) in different inspection tasks is increasing. This technology reduces inspection costs and collects high quality data of distinct structures, including areas that are not easily accessible by human operators. However, the reduced energy available on the UAVs limits their flight endurance. To increase the autonomy of a single flight, it is important to optimize the path to be performed by the UAV, in terms of energy loss. Therefore, this work presents a novel formulation of the Travelling Salesman Problem (TSP) and a path planning algorithm that uses a UAV energy model to solve this optimization problem. The novel TSP formulation is defined as Asymmetric Travelling Salesman Problem with Precedence Loss (ATSP-PL), where the cost of moving the UAV depends on the previous position. The energy model relates each UAV movement with its energy consumption, while the path planning algorithm is focused on minimizing the energy loss of the UAV, ensuring that the structure is fully covered. The developed algorithm was tested in both simulated and real scenarios. The simulated experiments were performed with realistic models of wind turbines and a UAV, whereas the real experiments were performed with a real UAV and an illumination tower. The inspection paths generated presented improvements over 24% and 8%, when compared with other methods, for the simulated and real experiments, respectively, optimizing the energy consumption of the UAV.

Radio frequency (RF) energy harvesting and wireless power transmission (WPT) technologies —both near-field and far-field—have attracted significant interest for wireless applications and RFID systems. We already utilize near-field WPT products in our life and it is expected that RF EH and far-field WPT systems can drive the future low-power wireless systems. In this article, we initially present a brief historical overview of these technologies. The main technical challenges of rectennas and WPT transmitters are discussed. Furthermore, this paper presents the recent advances on the development of these technologies, including the possibility of powering RFID systems through the millimeter wave power from 5G networks, the trends in flexible rectennas design and the technological developments on the simultaneous wireless information and power transfer (SWIPT).

Light fields are one of the emerging 3D representation formats with an effective potential to offer very realistic and immersive visual experiences. This capability comes at the cost of a very large amount of acquired data which practical use requires efficient coding solutions. This need was already addressed by the JPEG Pleno Light Field Coding standard for static light fields, which has specified two coding modes, named 4D-Transform and 4D-Prediction. While the first offers better compression performance for smaller baseline light fields, the second excels for larger baseline light fields. This paper intends to propose a novel light field coding mode, the Slanted 4D-Transform coding mode, which extends the 4D-Transform coding mode based on the conventional 4D-DCT, to offer better compression performance than both the available JPEG Pleno coding modes, independently of the baseline. The key idea is to apply first to each 4D block in the light field an adaptive, hierarchical geometric transformation, which makes the data in the block more energy-compaction friendly for the following 4D-DCT. The rate-distortion performance results show that the proposed Slanted 4D-Transform codec is able to outperform both the already standardized JPEG Pleno coding modes, showing BD-Rates gains of 31.03% and 28.30% for the 4D-Transform and 4D-Prediction modes, respectively, thus implying that a single coding mode can efficiently code all types of light fields.

Coding conventions are a means to improve the reliability of software systems, and they are especially useful to avoid the introduction of known bugs or security flaws. However, coding rules typically come in the form of text written in natural language, which makes them hard to manage and to enforce. Following the model-driven engineering principles, in this paper we propose an approach for the management and enforcement of coding conventions using structured models. We define the Coding Conventions Specification Language (CCSL), a language to define coding rules as structured specifications, from which checkers are derived automatically by code generation. To evaluate our approach, we run a thorough experiment on 8 real open-source projects and 77 coding rules for the Java language, comparing the violations identified by our checkers with those reported by the PMD static analysis tool. The obtained results are promising and confirm the feasibility of the approach. The experiment also revealed that textual coding rules rarely document all the necessary information to write a reliable checker.

This work proposes a methodology for evaluating the antenna array diversity and resultant radiation pattern from digitally-processed-based beamforming systems. Our approach enables to interpret the advanced antenna systems (AAS) coverage and massive multiple-input multiple output (mMIMO) spatial resolution, by the inspection of the array resultant multiple beams. Particularly, the impact on the mMIMO spatial resolution is conducted as a function of the channel correlation, by means of an exclusively radiofrequency (RF) approach, with the advantage of not considering the system-level features, and using a new figure of merit ( $\Lambda $ factor). The new figure of merit enables to evaluate the antenna array diversity from two- and three-dimensional (2D and 3D) beamforming, by computing the number of lobes with gain higher than a unique element. In the 3D case, the figure of merit is based on a differential calculation, which enables performing an infinitesimal counting of lobes per antenna element beamwidth. Such parameter is initially applied to a theoretical dipole-based array, with the purpose of quantifying the created multiple beams by the overlapped radiation patterns from mMIMO systems. Furthermore, the $\Lambda $ factor is exploited for analyzing the performance of a 64-element and dual-polarized SICL-based slot antenna array and a 64-element dipole-based antenna prototypes, both previously developed by our research group. Finally, it is demonstrated that the $\Lambda $ factor increases as diversity increases and dipole-based antenna array could be used as an upper limit, attaining 11.46 lobes/rad

Online judges (OJ) are a popular tool to support programming learning. However, one major issue with OJs is that problems are often put together without any associated meta-information that could, for example, be used to help classify problems. This meta-information could be extremely valuable to help users quickly find what types of problems they need most. To face this problem, several OJ administrators have recently begun manually annotating the topics of problems based on computer science-related subjects, such as dynamic programming, graphs, and data structures. Initially, these topics were used to support programming competitions and experienced learners. However, with OJs being increasingly used to support CS1 classes, such topic annotation needs to be extended to suit CS1 learners and instructors. In this work, for the first time, to the best of our knowledge, we propose and validate a predictive model that can automatically detect fine-grained topics of problems based on the CS1 syllabus. After experimenting with many shallow and deep learning models with different word representations based on cutting-edge NLP techniques, our best model is a CNN, achieving an F1-score of 88.9%. We then present how our model can be used for various applications, including (i) facilitating the search process of problems for CS1 learners and instructors and (ii) how it can be integrated into a system to recommend problems in OJs.

Proposing a novel hybrid uniform theory of diffraction-physical optics (UTD-PO) formulation, we develop a method to calculate the E-plane radiation pattern of corrugated E-plane rectangular horn antennas with rectangular corrugations. We derive the technique from the estimation of the total field that reaches the emitting source (a magnetic current line), thereby assuming the impingement of a plane wave above the horn (reciprocity is applied). To validate our method, we compare the performance of the UTD-PO analysis with that of the electric field integral equation (EFIE) solved using the method of moments (MoM). Our method shows improved computational efficiency over EFIE and other numerical techniques that fully discretize the geometry.

In some scenarios, a single input image may not be enough to allow the object classification. In those cases, it is crucial to explore the complementary information extracted from images presenting the same object from multiple perspectives (or views) in order to enhance the general scene understanding and, consequently, increase the performance. However, this task, commonly called multi-view image classification, has a major challenge: missing data. In this paper, we propose a novel technique for multi-view image classification robust to this problem. The proposed method, based on state-of-the-art deep learning-based approaches and metric learning, can be easily adapted and exploited in other applications and domains. A systematic evaluation of the proposed algorithm was conducted using two multi-view aerial-ground datasets with very distinct properties. Results show that the proposed algorithm provides improvements in multi-view image classification accuracy when compared to state-of-the-art methods. The code of the proposed approach is available at https://github.com/Gabriellm2003/remote_sensing_missing_data.

The Multi-Swarm approach allows the use of multiple configurations between two or more populations of particles, where each one can present different approaches (e.g. lbest, gbest, Unified, Guaranteed-Convergence) directed towards improving the optimization process. This article presents a proposal for local/global stochastic interconnection applied to the context of the Multi-Swarm algorithm, as well as for incrementing a local search method for refining previously obtained solutions. Two proposals are introduced for this new Multi-Swarm PSO (MSO). The first one is the inclusion of “counterpart particles”, which establishes a sub-topology between inter-swarm particles, accessed by migration and evaluability rules. The other involves using customized crossover operators and is based on the BLX scheme (Blend Crossover) with direction information used as a reference for establish a subspace search around the particles. Performance and robustness of the new approaches were assessed by ten constrained engineering design optimization problems (COPs), as is compared to other solutions already published in the scientific literature. Results indicate significant performance improvements for all 10 COPs when compared to concurrent-based MSOs. By making available new references from other swarms, the counterpart particles approach tends to improve the optimization process in the search space, while an intermediate layer of local search based on a modified directed BLX crossover should provide an extra search around the particle, and thus, refining previously obtained solutions.

The sixth generation of mobile communication (6G) systems is recently rising a lot of interest, introducing new futuristic and challenging use cases that will demand much more than just communications to become a reality. Higher throughput, lower latencies, higher number of connections will push the requirement of the future mobile networks to a new level, but also sensing, positioning and imaging will play an important role in the new foreseen use cases. The integration of techniques developed for wireless communications with those conceived for optical links will be essential to provide the infrastructure for the 6G networks. In this context, this paper presents a review on wireless and optical convergent access solutions towards the 6G systems. The manuscript brings the use cases, requirements and enablers for 6G networks including a discussion about the state-of-the-art on THz and sub-THz communications, wireless and optical convergence, visible light communication, integrated and free-space optics, new antenna designs, power-over-fiber deployments and the use of machine learning in the physical layer of future networks. By reviewing the most relevant contributions available in the literature for wireless and optical communications and presenting their main contributions, this paper clearly shows that, more than a technological trend, the convergence of wireless and optical technologies is a fundamental step towards the development of the 6G network infrastructure.

The pandemic brought about an unprecedented number of virtual conferences, given the heavy restrictions on travel to in-person meetings. Despite all the advances in technology, people still complain about virtual events. There is Zoom fatigue, confinement malaise, and a longing for personal social interactions. This paper discusses our experience organizing the IEEE Virtual Reality Conference (IEEE VR) as a virtual event. IEEE VR was a success with 1200+ registered paying participants, dozens of workshops and tutorials, and hundreds of technical papers. We used (1) a virtual environment platform, together with (2) discussion tools and (3) videoconferencing/broadcast/online tools to further provide effective social interaction and increase engagement. In this paper, we explore the synergies between virtual environments and other online tools and assess user engagement by analyzing the messages exchanged between participants across different genders and geographical regions. To this end, we apply diverse engagement metrics for online conferences. Our analysis shows that these metrics have the potential to highlight engagement, diversity, and inclusion by combining textual messages, participant geographic and gender information, communities of participants, and visitation patterns in a virtual environment. Drawing on our results and experiences, we propose guidelines for organizing technical virtual events to increase diversity and social interaction.

This study was to present a methodology for analyzing the distribution and spatial-time dependence of the supply of forest bioelectricity in Brazil, from 2000 to 2019. The data for the granting of forest biomass thermoelectric plants were obtained from the National Electric Energy Agency (in Portuguese Agência Nacional de Energia Elétrica –ANEEL). It used the exploratory analysis of spatial data, and as neighborhood criteria the spatial weighting matrices of k-neighbors closest and based on distance, as well as the global and local Moran indices to detect the presence of spatial dependence. The analysis of the situation, by quartile, showed the states of the central-southern portion of Brazil as the main locations of forest thermals. $\text{I}_{\mathrm {Moran\_{}Global}}$ highlighted the decrease in spatial autocorrelation between the years 2000 and 2019, associated with the implementation of new thermoelectric plants by the large groups Fibria, Klabin and Suzano Celulose throughout the national territory. The local index ( $\text{I}_{\mathrm {Moran\_{}Local}}$ ) pointed out high-powered clusters, especially in the early years, highlighting: the Bahia, Espírito Santo and Minas Gerais axis, the Paraná thermal plants and Mato Grosso do Sul thermal plants. The local index also pointed outliers, which indicated possibility of associating thermoelectric plants with other activities, such as wood production and industries in the steel and paper and cellulose segment. The knowledge of the spatial pattern of the forest bioelectricity sector presented can help new feasibility studies for the implementation in bioelectricity and/or stimulate the development of public policies, focused on cluster regions and adjacent areas, which results in the growth of forest generation.

An observable microgrid may become unobservable when sensors are at fault, sensor data is missing, or data has been tampered by malicious agents. In those cases, state estimation cannot be performed using traditional approaches without pseudo-measurements. To address the lack of observability, this article presents the design and implementation of a novel three-phase state estimation method for unobservable and unbalanced AC microgrids, using machine learning techniques, without pseudo-measurements, and under heteroscedastic (i.e., non-constant variance) noise. The proposed machine learning state estimation (MLSE) makes full use of multiple candidate models trained with a small number of power flow simulations via OpenDSS, through random levels of demand and renewable generation in every simulation, enhanced through a proposed Tikhonov regularization operator. To deal with the heteroscedastic nature of measurements, a recursive average model is proposed to accurately estimate the state variables. Results are obtained using real data from a microgrid located on the main campus of the State University of Campinas (UNICAMP), in Brazil. The method can be easily adapted to microgrids with different configurations, distributed energy resources, and measurements. It is shown that the proposed MLSE outperforms the traditional weighted least square (WLS) state estimator.

The present survey seeks to contribute to the existing discussion about the changing of current Public Protection and Disaster Relief (PPDR) networks (TETRA, TETRAPOL, P25, and DMR) to commercial cellular networks (4G and 5G). The availability and robustness of these commercial networks are challenging current PPDR networks and creating opportunities for a successful transition of existing systems to commercial cellular networks. Specifically, 5G networks aim to support a massive number of heterogeneous devices while providing ultra-reliable low latency communications, higher mobility, and the capability of customised support of applications via network slicing, thus providing a natural contribution to mission critical systems. This survey details the essential mission requirements of security of PPDR systems, describes the state of the art of the most used technologies and discusses their evolution to 4G and 5G cellular networks. Furthermore, it analyses future research directions that may contribute to a successful transition of current systems to the newer cellular networks.

Deep Learning (DL) based classification algorithms have been shown to achieve top results in clinical diagnosis, namely with lung cancer datasets. However, the complexity and opaqueness of the models together with the still scant training datasets call for the development of explainable modeling methods enabling the interpretation of the results. To this end, in this paper we propose a novel interpretability approach and demonstrate how it can be used on a malignancy lung cancer DL classifier to assess its stability and congruence even when fed a low amount of image samples. Additionally, by disclosing the regions of the medical images most relevant to the resulting classification the approach provides important insights to the correspondent clinical meaning apprehended by the algorithm. Explanations of the results provided by ten different models against the same test sample are compared. These attest the stability of the approach and the algorithm focus on the same image regions.

In recent years, the use of artificial neural network applications to perform object classification and event prediction has increased, mainly from research about deep learning techniques running on hardware such as GPU and FPGA. The interest in the use of neural networks extends to embedded systems, due to the development of applications in smart mobile devices, such as cell phones, drones, autonomous cars and industrial robots. In this article, a methodology is proposed that allows to reduce a spiking neural network, applying the discrete cosine transform (DCT) and elegant pairing. The Izhikevich model was used as a basis for the architecture of the spiking neural network. The simulation results demonstrate the effectiveness of the methodology, showing the feasibility of reducing synapses, applying the DCT transform, and of reducing neurons from the intermediate layers, using the elegant pairing technique of the coefficients, and maintaining the accuracy of the response of the spiking neural network. The results also demonstrate the contribution of the proposed methodology to the scalability of the neural network, with the increase in the storage capacity of the coefficients of the SNN layers.

This work presents a contribution to advance current solutions for the problem of melanoma detection based on deep learning (DL) approaches. This is an active research field, which aims to aid on the detection and classification of melanoma (the most lethal type of skin cancer) with non-invasive solutions. By exploiting both 2D and 3D characteristics of the skin lesion surface, the proposed approach advances beyond commonly used colour features of dermoscopic images. Two competing classification methods are exploited, namely Multiple Instance Learning (MIL) and DL, which are combined using an uncertainty-aware decision function. The DL method performs classification resorting to RGB data, while MIL performs 3D feature extraction, selects the most significant set, and performs classification at two different learning instances. The novel aspects of this work include DL uncertainty evaluation mechanisms along with MIL to train a robust ensemble classifier, and also the use of dense light-fields for skin lesion classification. Despite the large class imbalance (often present in medical image datasets), the ensemble model achieves cross-validated melanoma classification accuracy of 84.00% when trained against nevus lesions, and 90.82% accuracy when discriminating against all present lesion types. The results show that, in the absence of discriminative 2D characteristics, the 3D surface provides redeeming results, demonstrating that existing methods can benefit from the proposed method by looking beyond 2D image characteristics.