Search

Micro-earthquakes are frequently associated with volcanic activity and are vital indicators of volcanic processes. These minor seismic events occur within or near volcanic systems, yielding valuable insights into subsurface activities. Geologists meticulously record and analyze these events to monitor volcanoes and forecast eruptions. While recent years have seen several studies proposing automated detection and classification systems of seismic events, approaches based on Manifold Learning techniques could be beneficial in terms of information interpretability and transfer learning to other Machine Learning tasks. This paper presents a novel approach employing audio features and psychoacoustic scales to represent micro-earthquakes at Cotopaxi and Llaima Volcanoes, and these representations are then transformed into low-dimensional latent spaces. We implemented a multi-class classification system for events generated by these volcanoes, incorporating feature selection techniques based on audio-inspired features. This approach enhances the detection of volcanic phenomena triggering eruptions and improves interpretability. Our results indicated high accuracy, with rates of 94.44% for Llaima Volcano and 95.45% for Cotopaxi Volcano when utilizing mutual information to select the most relevant features. Spectral Roll-off Point and Spectral Flux dominate in classifying events for both volcanoes. These findings suggest that low-dimensional latent spaces, particularly when utilizing spectral features, can be a promising foundation for developing transfer learning schemes in general, and new multi-class classification systems in particular, for detecting volcanic micro-earthquakes.

Sudden cardiac death causes multiple deaths annually, and T-wave alternans are a reliable predictor of this fatal event. Detecting alternans is crucial for reducing disease incidence, and electrocardiographic imaging is a promising tool, providing spatial-temporal insights. The absence of references and segmentation methods specific to these data may complicate progress in the field. Therefore, this work aimed to develop a reference for evaluating estimation methods. Initially, a novel T-wave segmentation procedure specific to these data was introduced and compared with a commonly used method. Subsequently, a reference for assessing alternans estimation methods was created by integrating alternans into epicardial signals through a spatial-temporal Gaussian function. Finally, a bootstrap-based classifier for detecting alternans was developed. Results underscored the superiority of the novel T-wave segmentation procedure, with the lowest 95% confidence interval being $[16.57~\mu V, 18.80~\mu V]$ , indicating significant disparities between the two segmentation methodologies. Furthermore, the generated reference demonstrated the distinguishability of T-wave alternans with an amplitude of approximately $55~\mu V$ from noise. Additionally, the classifier exhibited consistency with previous findings, demonstrating its ability to detect alternans with amplitudes around $50~\mu V$ . In conclusion, this study provides a spatial-temporal reference for proper evaluation of estimation methods, contributing to establishing a gold standard.

Data centralization can potentially increase Internet of Things (IoT) usage. The trend is to move IoT devices to a centralized server with higher memory capacity and a more robust management interface. Hence, a larger volume of data will be transmitted, resulting in more network security issues. Cloud IoT offers more advantages for deploying and managing IoT systems through minimizing response delays, optimal latency, and effective network load distribution. As a result, sophisticated network attack strategies are deployed to leverage the vulnerabilities in the extensive network space and exploit user information. Several attempts have been made to provide network intrusion detection systems (IDS) to the cloud IoT interface using machine learning and deep learning approaches on dedicated IDS datasets. This paper proposes a transfer learning IDS based on the Convolutional Neural Network (CNN) architecture that has shown excellent results on image classification. We use five pre-trained CNN models, including VGG16, VGG19, Inception, MobileNet, and EfficientNets, to train on two selected datasets: CIC-IDS2017 and CSE-CICIDS2018. Before the training, we carry out preprocessing, imbalance treatment, dimensionality reduction, and conversion of the feature vector into images suitable for the CNN architecture using Quantile Transformer. Three best-performing models (InceptionV3, MobileNetV3Small, and EfficientNetV2B0) are selected to develop an ensemble model called efficient-lightweight ensemble transfer learning (ELETL-IDS) using the model averaging approach. On evaluation, the findings show that the ELETL-IDS outperformed existing state-of-the-art proposals in all evaluation metrics, reaching 100% in accuracy, precision, recall, and F-score. We use Matthew’s Correlation Coefficient (MCC) to validate this result and compared it to the AUC-ROC, which maintained an exact value of 0.9996. To this end, our proposed model is lightweight, efficient, and reliable enough to be deployed in cloud IoT systems for intrusion detection.

In this paper, we discuss how the use of the recently developed modified tuning pin (MTP) can be extended to the design of filters and diplexers implemented in rectangular waveguide, that can be reconfigured in a number of discrete states, and that can be used in high-power payloads. As an application example, the design of two reconfigurable filters and a reconfigurable diplexer is fully described. The high-power behavior of these components (in particular, with respect to corona and multipaction effects) is also studied in detail, in order to demonstrate that the structures that we discuss can operate correctly under high-power conditions. Furthermore, comparisons between simulations and measurements of several prototypes are also included, showing an excellent agreement between simulated and experimental data, thereby fully validating both the design approach and the filter reconfiguration strategy.

Atrial fibrillation (AF) remains a significant health challenge as the number of patients increases with the aging of the population worldwide. AF detection continues to be a significant challenge, particularly in the long term, to improve the quality of life of people suffering from the disease and reduce treatment costs. In recent decades, machine learning and deep learning have provided promising results in classifying heart conditions with moderate interpretability. We hypothesized that the complexity of AF could be handled in low-dimensional latent spaces in terms of non-Gaussian manifolds and that feature selection techniques on an audio-inspired feature set could improve the detection and interpretability of the AF phenomenon. Therefore, we used long-term monitoring databases in which noise-reduction filters preprocessed the signals and extracted their RR-value sequences. From these datasets, several audio spectral characteristics were calculated and used as input vectors for different types of manifold estimators. We also used the least absolute shrinkage and selection operator (LASSO) regression, a feature selection technique. Our experiments showed that these spectral representations of AF segments can yield better-defined low-dimensional embedding manifolds and acceptable intrinsic separability of AF from sinus rhythm. Moreover, including supervised stages and LASSO regression improved the overall performance of this proposal. The performance obtained in classifying AF signals versus normal ones reaches a precision of 91.2%, a recall of 95.5%, and an accuracy of 94.5%. These results pave the way for manifold learning and low-dimensional latent spaces in AF applications, and they support the advantage of using machine learning methods in different AF problems.

The ionospheric storm time responses during August 2018 are investigated over South American region using multiple observables, for example, Global Navigation Satellite System (GNSS) derived vertical total electron content (VTEC) from International GNSS Service, magnetic field data, geomagnetic indices, global ionospheric maps, thermospheric mass density (TMD), and [O/N2] ratio measurement. Strong-ionospheric and upper-atmospheric disturbances affected the ionospheric variables with long duration during the storm recovery phase and following after. First, daytime VTEC (9:00–20:00 UT) presented variations of >15 TECU during days 25 to 30 of August 2018 in low and middle latitudes of South America, this after sudden storm commencement (SSC). Furthermore, nighttime (21:00–24:00 and 00:00–05:00 UT) VTEC presented low values (58 TECU) in the recovery phase. Second, the ionospheric values during the storm main phase and following after, at low- and mid-latitudes, caused the equatorial ionization anomaly to expand due to prompt penetration electric field. Furthermore, VTEC enhancements are likely to occur few hours after the SSC of 25 August 2018, while enhancements of TMD and [O/N2] ratio started to appear later on 26 and 27 of August 2018.

The growing demand for Internet of Things (IoT) applications in agribusiness increases the necessity of reliable and secure connectivity in rural areas. Thus, in the particular case of Brazil, some initiatives aim to take advantage of frequency bands dedicated to limited private services. For instance, cellular networks based on orthogonal frequency-division multiple access (OFDMA) in 250 MHz bands require specialized adaptations because the interference between cells increases when these systems operate in the Very High Frequency (VHF) band. This work presents an analysis based on a reliable simulation of interference mitigation in OFDMA systems at 250 MHz using a network simulator. The simulator is calibrated with data obtained in the field by an extensive and rigorous drive test. Therefore, the analysis is based on a comparison of traditional frequency reuse schemes with a machine learning approach based on deep reinforcement learning (DRL) to reduce inter-cell interference. The numerical results indicate that the DRL approach outperforms the traditional frequency reuse (FR) schemes in four different typical agribusiness scenarios.

Virtual Reality (VR) video games have become popular in recent years with the emergence of a wide variety of enhanced VR hardware systems. Typically, current VR video games incorporate high-quality auditory and video feedback along with vibro-tactile cues to provide an immersive experience. However, the ongoing VR hardware and software do not consider the state of the user to determine whether the video game is generating an enjoyable experience, or if it has become a stressing or boring experience. This work provides an assessment of stress level estimation from features extracted from Electrocardiography (ECG), Electrodermal Activity (EDA), and Electromyography (EMG) signals of users while playing a VR video game with different difficulty levels. Statistical differences were found between the rest and gaming stages for several extracted features. Regardless of the fact that no significant statistical differences between the three levels of difficulty were found by analyzing the EDA and ECG features, an 83.1% accuracy was obtained for the classification between the three levels with a KNN model. For the EMG signal, the obtained accuracy ranged between 99% and 100% for the distinction between a difficult level 1 and rest stage for all models. When all features from the ECG, EDA and EMG signals were used, an accuracy of 99% was obtained for the differentiation between the three difficulty levels and a resting stage. The presented work results may serve as a reference for future work regarding feature extraction and game difficulty adaptation for user experience enhancement.

The objective of this paper is to show how inductive quadruplets with diagonal cross-couplings can be used as building blocks for filters in rectangular waveguide. Starting with the coupling matrix synthesis, we show how very general transfer functions can be easily implemented with a very simple step-by-step procedure. In addition to coupling matrix theory, we also describe distributed networks that can be effectively used to carry out the transition from coupling matrix descriptions to actual waveguide structures. Several filter design examples are also described in detail. Finally, measured results are also discussed showing excellent agreement with simulations, thereby fully validating both the new family of filter structures and the related design procedures.

The routing mechanisms in flying ad-hoc networks (FANETs) using unmanned aerial vehicles (UAVs) have been a challenging issue for many reasons, such as its high speed and different directions of use. In FANETs, the routing protocols send hello messages periodically for the maintenance of routes. However, the hello messages that are sent in the network increase the bandwidth wastage on some occasions and the excessive number of hello messages can also cause the problem of energy loss. Scarce works deal with the problem of excessive hello messages in dynamic UAVs scenarios, and treat several other problems, such as bandwidth and energy wastage simultaneously. Generally, the existing solutions configure the hello interval to an excessive long or short time period originating delay in neighbors discovery. Thus, a self-acting approach is necessary for calculating the exact number of hello messages with the aim to reduce the bandwidth wastage of the network and the energy loss; this approach needs to be low complex in terms of computational resource consumption. In order to solve this problem, an intelligent Hello dissemination model, AI-Hello, based on reinforcement learning algorithms, that adapts the hello message interval scheme is proposed to produce a dense reward structure, and facilitating the network learning. Experimental results, considering FANET dynamic scenarios of high speed range with 40 UAVs, show that the proposed method implemented in two widely adopted routing protocols (AODV and OLSR) saved 30.86% and 27.57% of the energy consumption in comparison to the original AODV and OLSR protocols, respectively. Furthermore, our proposal reached better network performance results in relation to the state-of-the-art methods that are implemented in the same protocols, considering parameters, such as routing overhead, packet delivery ratio, throughput and delay.

Distributed intelligence is a well-known approach for optimizing interactions among numerous smart devices that interconnect and operate together as Internet of Things (IoT) systems. A modern form of human-machine collective intelligence emerges when humans interact with IoT systems in sociotechnical environments such as smart homes. Fifth-generation (5G) communication networks are designed for high-speed reliable wireless connectivity and expected to boost IoT and (distributed) collective intelligence by revolutionizing human–device–human interactions. In this paper, we contribute a comprehensive review of state-of-the-art sociotechnical environments that exhibit collective intelligence, supported by 5G-enabled IoT. We discuss the latest developments in 5G and their implications for collective intelligence. Further, we explain the key challenges for using 5G to support collective intelligence, e.g., data processing, security, and radio resource management. Finally, we describe four practical applications of collective intelligence to sociotechnical environments—road traffic control, unmanned aerial vehicles, electrical load demand response, and augmented democracy.

The application of flying base stations (FBS) in wireless communication is becoming a key enabler to improve cellular wireless connectivity. Following this tendency, this research work aims to enhance the spectral efficiency of FBSs using the radio access network (RAN) slicing framework; this optimization considers that FBSs’ location was already defined previously. This framework splits the physical radio resources into three RAN slices. These RAN slices schedule resources by optimizing individual slice spectral efficiency by using a deep reinforcement learning approach. The simulation indicates that the proposed framework generally outperforms the spectral efficiency of the network that only considers the heuristic predefined FBS location, although the gains are not always significant in some specific cases. Finally, spectral efficiency is analyzed for each RAN slice resource and evaluated in terms of service-level agreement (SLA) to indicate the performance of the framework.

Currently, with the increasing number of devices connected to the Internet, search for network vulnerabilities to attackers has increased, and protection systems have become indispensable. There are prevalent security attacks, such as the Distributed Denial of Service (DDoS), which have been causing significant damage to companies. However, through security attacks, it is possible to extract characteristics that identify the type of attack. Thus, it is essential to have fast and effective security identification models. In this work, a novel Intrusion Detection System (IDS) based on the Tree-CNN hierarchical algorithm with the Soft-Root-Sign (SRS) activation function is proposed. The model reduces the training time of the generated model for detecting DDoS, Infiltration, Brute Force, and Web attacks. For performance assessment, the model is implemented in a medium-sized company, analyzing the level of complexity of the proposed solution. Experimental results demonstrate that the proposed hierarchical model achieves a significant reduction in execution time, around 36%, and an average detection accuracy of 0.98 considering all the analyzed attacks. Therefore, the results of performance evaluation show that the proposed classifier based on Tree-CNN is of low complexity and requires less processing time and computational resources, outperforming other current IDS based on machine learning algorithms.

The objective of this paper is to describe the design of an innovative and low-cost diplexer for Ka-band multi-beam satellite applications. The device is based on the use of two quadruplets to implement a number of transmission zeros (TZs) thus obtaining high-selectivity quasi-elliptic transfer functions. The resulting diplexer structure is particularly flexible in terms of layout, does not require tuning and has an excellent high-power behavior. In addition to theory, we compare the results of our simulations with the measurements obtained with a manufactured breadboard. The comparison shows excellent agreement thereby fully validating both the design procedure, and the new diplexer structure.

This article surveys emerging technologies related to pervasive edge computing (PEC) for industrial internet-of-things (IIoT) enabled by fifth-generation (5G) and beyond communication networks. PEC encompasses all devices that are capable of performing computational tasks locally, including those at the edge of the core network (edge servers co-located with 5G base stations) and in the radio access network (sensors, actuators, etc.). The main advantages of this paradigm are core network offloading (and benefits therefrom) and low latency for delay-sensitive applications (e.g., automatic control). We have reviewed the state-of-the-art in the PEC paradigm and its applications to the IIoT domain, which have been enabled by the recent developments in 5G technology. We have classified and described three important research areas related to PEC-distributed artificial intelligence methods, energy efficiency, and cyber security. We have also identified the main open challenges that must be solved to have a scalable PEC-based IIoT network that operates efficiently under different conditions. By explaining the applications, challenges, and opportunities, our paper reinforces the perspective that the PEC paradigm is an extremely suitable and important deployment model for industrial communication networks, considering the modern trend toward private industrial 5G networks with local operations and flexible management.

The development of the Internet of Things (IoT) benefits from 1) the connections between devices equipped with multiple sensors; 2) wireless networks and; 3) processing and analysis of the gathered data. The growing interest in the use of IoT technologies has led to the development of numerous diverse applications, many of which are based on the knowledge of the end user's location and profile. This paper investigates the characterization of Bluetooth signals behavior using 12 different supervised learning algorithms as a first step toward the development of fingerprint-based localization mechanisms. We then explore the use of metaheuristics to determine the best radio power transmission setting evaluated in terms of accuracy and mean error of the localization mechanism. We further tune-up the supervised algorithm hyperparameters. A comparative evaluation of the 12 supervised learning and two metaheuristics algorithms under two different system parameter settings provide valuable insights into the use and capabilities of the various algorithms on the development of indoor localization mechanisms.

Electrocardiographic Imaging (ECGI) aims to estimate the intracardiac potentials noninvasively, hence allowing the clinicians to better visualize and understand many arrhythmia mechanisms. Most of the estimators of epicardial potentials use a signal model based on an estimated spatial transfer matrix together with Tikhonov regularization techniques, which works well specially in simulations, but it can give limited accuracy in some real data. Based on the quasielectrostatic potential superposition principle, we propose a simple signal model that supports the implementation of principled out-of-sample algorithms for several of the most widely used regularization criteria in ECGI problems, hence improving the generalization capabilities of several of the current estimation methods. Experiments on simple cases (cylindrical and Gaussian shapes scrutinizing fast and slow changes, respectively) and on real data (examples of torso tank measurements available from Utah University, and an animal torso and epicardium measurements available from Maastricht University, both in the EDGAR public repository) show that the superposition-based out-of-sample tuning of regularization parameters promotes stabilized estimation errors of the unknown source potentials, while slightly increasing the re-estimation error on the measured data, as natural in non-overfitted solutions. The superposition signal model can be used for designing adequate out-of-sample tuning of Tikhonov regularization techniques, and it can be taken into account when using other regularization techniques in current commercial systems and research toolboxes on ECGI. [ABSTRACT FROM AUTHOR]

This work is concerned with the modelling and control of the state of presence of a user in a virtual reality system (VRS). The manner how the state of a user interacting with the VRS is measured by some of its physiological signals is discussed. Based on the user-VRS interaction, a novel feedback control schema to manipulate the user state is proposed. In this, the error between the required and the actual user behavior is used by a controller to select the appropriate stimulus that must be executed by the VRS core scenario to reduce the error. The schema includes the modelling of the presence state by a discrete event strategy based on Petri Nets. Based on the obtained model, the control strategy to select the appropriate stimuli is devised. Finally, some real experiments with a VRS prototype are carried out to show the effectiveness of the proposal. [ABSTRACT FROM AUTHOR]