Journal of Communication and Information Systems <p>The Journal of Communication and Information Systems (JCIS) features high-quality, peer-reviewed technical papers in several areas of communications and information systems. The JCIS is jointly sponsored by the Brazilian Telecommunications Society (SBrT) and the IEEE Communications Society (ComSoc). As from June 2020, Prof. Rausley Adriano Amaral de Souza from National Institute of Telecommunications (Inatel) and Prof. José Cândido Silveira Santos Filho from University of Campinas (UNICAMP) are the Editors-in-Chief of the JCIS.&nbsp;</p> <p>There are no article publication or submission charges. Previous editions of the JCIS can be accessed <a href="/index.php/JCIS/issue/archive" target="_blank" rel="noopener">here</a>.</p> <p>This is an open access journal which means that all content is freely available without charge to the user or his/her institution, permanently accessible online immediately upon assignment of the DOI. Users are allowed to read, download, copy, distribute, print, search, or link to the full texts of the articles, or use them for any other lawful purpose, without asking prior permission from the publisher or the author. This is in accordance with the BOAI definition of open access.</p> <p>ISSN: 1980-6604</p> Brazilian Telecommunications Society en-US Journal of Communication and Information Systems 1980-6604 <p><span>Authors who publish with this journal agree to the following terms:</span><br /><br /></p><ol type="a"><ol type="a"><li>Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a <a href="" target="_new">Creative Commons Attribution License</a> that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.</li></ol></ol><p> </p><ol type="a"><ol type="a"><li>Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.</li></ol></ol><p> </p><ol type="a"><ol type="a"><li>Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See <a href="" target="_new">The Effect of Open Access</a>).</li></ol></ol><p>___________</p> User-Level Handover Decision Making Based on Machine Learning Approaches <p>This letter covers a broad comparison of methods for classification and regression applications for a user-level handover decision making in scenarios with adverse propagation conditions involving buildings, coverage holes, and shadowing effects. The simulation campaigns are based on network simulator <em>ns-3</em>. The comparison encompasses classical machine learning approaches, such as KNN, SVM, and neural networks, but also state-of-the-art fuzzy logic systems and latter boosting machines. The results indicate that SVM and MLP are the most suitable for the classification of the best handover target, although fuzzy system SOFL can perform similarly with lower processing time. Additionally, for the download time estimation, LightGBM provides the smallest error with short processing time, even in hard propagation scenarios.</p> João Lima Alvaro Medeiros Eduardo Aguiar VICENTE ANGELO DE SOUSA JUNIOR Tarciana Guerra ##submission.copyrightStatement## 2022-06-22 2022-06-22 37 1 104 108 10.14209/jcis.2022.11 Performance Assessment of DTN and VANET Protocols for Transmitting Periodic Warning Messages in High Vehicular Density Networks <p>In recent years, routing protocols for Delay Tolerant Networks (DTN) have become appealing for vehicular ad-hoc networks (VANET), particularly for communication between vehicles in highly sparse environments. In such scenarios, network disconnections are frequent, and the establishment of stable source-destination links is scarce. This work addresses the performance of four DTN and two traditional VANET protocols when the vehicular density becomes high in a short-scale scenario. In this case, vehicles may need to communicate with near-located neighbors, and traffic conditions can rapidly change from low to high congested areas. Specifically, we evaluate how DTN and traditional VANET routing protocols deal with the transmission of warning messages that require message generation rates higher than usually found in the literature. The results show that the traditional VANET protocols outperform the DTN approaches considered in this work for transmitting warning messages in high vehicular-density scenarios. The results also shed light on features that DTN protocols should consider to improve the performance in such scenarios.</p> Alvaro Torres Amaya Mauro Sergio Fonseca Alexandre Pohl Ricardo Lüders ##submission.copyrightStatement## 2022-06-20 2022-06-20 37 1 91 103 10.14209/jcis.2022.10 A New Approach for FSS Design in 3.5GHz Based on General Neural Network Model by using Multi-objective Sailfish Optimization Algorithm <p><span class="fontstyle0">This work approaches a bioinspired hybrid multiobjective optimization technique associated with a general regression neural network as a proposal to synthesize the geometry and the dimensions of a frequency selective surface (FSS) for electromagnetic wave filtering in 5G applications. This new hybrid technique associates the bio-inspired algorithm known as the Sailfish Optimizer (SFO), together with a GRNN net to obtain the parameters for constructing the filter.In this study, the focus is on the application of the technique as a tool for the design and the synthesis of FSS, which has the shape of a square spiral unitary cell, printed on a fiberglass substrate plate (FR4). The objectives of the optimization process are to set the resonant frequency of the FSS to 3.5 GHz and the&nbsp; perating bandwidth to 0.8 GHz. It is reported a good agreement between&nbsp;the simulated and measured results.</span></p> Nelson Mateus Santos Miercio Neto Jasmine Araujo Fabricio Barros Gervasio Cavalcante Edemir Matos Rafael Vieira ##submission.copyrightStatement## 2022-05-29 2022-05-29 37 1 86 90 10.14209/jcis.2022.9 New Reversible Data Hiding Algorithm Based on Edge Detection and PVO Mechanisms <p>Reversible data hiding technique is able to restore the cover data exactly after data extraction. This paper presents a new reversible data hiding scheme based on the combination of edge detection and pixel value ordering mechanism is proposed. In the proposed scheme, the cover image is divided into smooth or rough areas by Canny edge detection algorithm. Then, the secret data is embedded into pixels in the smooth areas based on pixel value ordering algorithm to obtain better image quality of marked images. The experimental results demonstrate that our scheme achieves better visual quality than those of state-of-the-art schemes while guaranteeing the reversibility.</p> Thai-Son Nguyen Hoang-Nam Tram ##submission.copyrightStatement## 2022-04-18 2022-04-18 37 1 77 85 10.14209/jcis.2022.8 Understanding Ransomware Actions Through Behavioral Feature Analysis <p>Crypto ransomware attacks have substantially increased in recent years, and owing to their highly profitable&nbsp; nature, this growth will evidently escalate in the future. To better understand this malware and help developers of ransomware detection systems build more robust and reliable solutions, this study investigates ransomware actions during the destruction phase through behavioral feature analysis. We used a dataset with 1524 samples and 30 967 features representing the actions conducted using 582 types of ransomware and 942 good applications (goodware). Six representative and widely used classification algorithms were applied as auxiliary tools to investigate the behavior of these attacks: Naive Bayes (NB), K-Nearest Neighbors (KNN), Logistic Regression (LR), Random Forest (RF), Stochastic Gradient Descent (SGD), and Support Vector Machine (SVM). We achieved an accuracy of 98.48%, balanced accuracy of 98.35%, precision of 98.17%, recall of 97.82%, F-measure of 97.98%, and ROC AUC of 99.87% by using RF for 462 features of the resultant dataset. We propose a new criterion to determine the feature group relevance and a method to distinguish the features that are most related to ransomware and goodware. Our main conclusions are as follows: Application Programming Interface (API) calls are the most relevant feature group, achieving alone a balanced accuracy of 96.49%; native encryption Windows APIs are not crucial for ransomware classification; and the most significant features of ransomware tend to involve handling the thread/process, physical memory operation, and communication, whereas goodware features are more likely to indicate virtual memory, files, directories, and resource operations.</p> Caio Carvalho Moreira Claudomiro de Souza de Sales, Jr. Davi Carvalho Moreira ##submission.copyrightStatement## 2022-03-10 2022-03-10 37 1 61 76 10.14209/jcis.2022.7 Digital TV Channel Prediction using Clustering Algorithms and Statistical Learning <p>Due to the rise of new communication services, more portions of the electromagnetic spectrum must be relocated and their distribution optimized. With the digitization of the open TV service, it was observed that the distribution of channels in&nbsp; he frequency band destined for this service generated an inefficient use of the radio spectrum. These unused frequency bands are the so-called void spaces. To establish efficient spectrum use, it is important to identify these spectrum gap&nbsp; opportunities and use according to certain criteria. In this article, machine learning algorithms are proposed to identify new spectrum opportunities, through the signal levels received in the UHF frequency range of the Digital TV system. These&nbsp; spectrum opportunities are generated from natural or artificial obstacles present in the propagation environment. Two measurement campaigns were carried out in a suburban area to obtain the level of the signal received in an area of approximately 240,000 square meters. From the received power values, machine learning algorithms were used to make prediction of the received signal levels. By using a reception threshold, it is possible to identify the shadow regions and possible&nbsp; spectrum opportunities.</p> Daniel da Costa Vidal Tadeu Ferreira Pedro Castellanos ##submission.copyrightStatement## 2022-03-08 2022-03-08 37 1 52 60 10.14209/jcis.2022.6 Spreading Factor Assignment Strategy for Coverage and Capacity Flexible Tradeoff <p>LoRa is a physical layer technology with the ability to connect multiple devices in a wide area of coverage, with low power consumption and with interference robustness.&nbsp;In this Letter, we investigate the efficiency of LoRa to send multiple uplink streams, analyzing strategies of allocating the spreading factor for coverage or capacity enhancement.</p> Luiz Filho Alvaro Medeiros Jéssika Silva VICENTE ANGELO DE SOUSA JUNIOR Níbia Bezerra ##submission.copyrightStatement## 2022-02-28 2022-02-28 37 1 47 51 10.14209/jcis.2022.5 A New O-RAN Compression Approach for Improved Performance on Uplink Signals <p>This work evaluates the O-RAN compression methods specified for in-phase and quadrature (IQ) data compression, which are applied to transport the frequency domain representation of the radio signals. The methods were evaluated in terms of computational cost and quantization-noise ratio vs IQ bit-width. It was found that the O-RAN compression algorithm with the best performance highly depends on the signal power. Thus, one of the contributions of this work is a compression method that selects the best method for each physical resource block (PRB) instead of using a single compression method for a set of PRBs as in the current O-RAN specification. A complete description of how to implement the proposed method meeting the O-RAN standard is also provided in the paper. The selection of the best method for each PRB is particularly important for the uplink signals, where the power of the received signals can be very different depending on the UE channel.</p> Marcos Davi Lima Silva Leonardo Ramalho Igor Almeida Eduardo Medeiros Miguel Berg Aldebaro Klautau ##submission.copyrightStatement## 2022-02-25 2022-02-25 37 1 30 41 10.14209/jcis.2022.3 Video Quality Loss Model on Communication Networks: An Approach Based on Frame Loss <p>This letter proposes a mathematical model capable of estimating video quality loss in error-prone networks through Peak Signal-to-Noise (PSNR ) ratio metric. Also, it presents experimental results by correlating the frame losses, the video resolution, and the received video visual complexity to obtain video quality loss models. The results show that frame loss satisfies the model to predict the PSNR loss for three resolutions.</p> Edemir Marcus Carvalho Matos Thiago de Araujo Costa Miércio Cardoso Alcântara Neto Bruno Souza Lyra Castro Fabricio de Souza Farias Jasmine Priscyla Leite de Araujo Fabrício José Brito Barros ##submission.copyrightStatement## 2022-02-25 2022-02-25 37 1 42 46 10.14209/jcis.2022.4 Spectrum Sensing <p>Spectrum sensing, combined or not with database information on radio-frequency (RF) spectrum occupation, is envisaged as part of the solution to the spectrum scarcity inherited by the fixed spectrum allocation policy currently adopted around the world. The solution is grounded on the premise of spectrum sharing between primary (incumbent) and secondary networks under a new dynamic spectrum access (DSA) paradigm. This tutorial presents basic concepts, fundamentals and state-of-the-art techniques related to spectrum sensing. Thought as a short course material, it covers from concepts regarding the forms of spectrum sensing and basic fundamentals on detection theory, to modern cooperative spectrum sensing techniques and research challenges, passing through the mathematical model for the signal and the sensing channel, the signal-to-noise ratio wall, practical issues regarding signal processing tasks, and performance metrics. A complete DSA framework is also addressed, which makes use of Internet of things devices equipped with spectrum sensing modules as a means to feed spectrum occupation databases.</p> Dayan Adionel Guimarães ##submission.copyrightStatement## 2022-02-21 2022-02-21 37 1 10 29 10.14209/jcis.2022.2