Recent advances in unmanned aerial vehicles (UAVs), or drones, have made them able to communicate and collaborate, forming flying ad hoc networks (FANETs). FANETs are becoming popular in many application domains, including precision agriculture, goods delivery, construction, environment and climate monitoring, and military surveillance. These interesting new avenues for the use of UAVs are motivating researchers to rethink the existing research on FANETs. Therefore, this paper provides a comprehensive and thorough review of the different types of UAVs used in FANETs, their mobility models, main characteristics, and applications, as well as the routing protocols used in this type of network. Other important contributions of this paper include the investigation of emerging technologies integrated with FANETs.

Channel estimation is a crucial problem for massive multiple input multiple output (MIMO) systems to achieve the expected benefits in terms of spectrum and energy efficiencies. However, a considerable number of pilots are usually distributed over a large number of time-frequency resources using orthogonal frequency division multiplexing (OFDM) to effectively estimate a large number of channel coefficients in the space and frequency domains, sacrificing spectral efficiency. In this work, by assuming MIMO-OFDM transmission, we start by proposing a tensor-based minimum mean square error (MMSE) channel estimator that exploits the multidimensional nature of the frequency-selective massive MIMO channel in the frequency-domain, being a low-complexity alternative to the well-known vector-MMSE channel estimation. Then, by incorporating a 3D sparse representation into the tensor-based channel model, a tensor compressive sensing (tensor-CS) model is formulated by assuming that the channel is compressively sampled in space (radio-frequency chains), time (symbol periods) and frequency (pilot subcarriers). This tensor-CS model is used as the basis for the formulation of a () estimator that solves a greedy problem per dimension of the measured tensor data. The proposed channel estimator has two variants which may either resort to a joint search per tensor dimension or to a sequential search that progressively reduces the search space across the tensor dimensions. The complexities of the different tensor-based algorithms are studied and compared to those of the traditional vector-MMSE and vector-CS estimators. Our results also corroborate the performance-complexity tradeoffs between T-MMSE and T-OMP estimators, both being competing alternatives to their vector-based MMSE and OMP counterparts.

Phishing is a type of fraud attempt in which the attacker, usually by e-mail, pretends to be a trusted person or entity in order to obtain sensitive information from a target. Most recent phishing detection researches have focused on obtaining highly distinctive features from the metadata and text of these e-mails. The obtained attributes are then used to feed classification algorithms in order to determine whether they are phishing or legitimate messages. In this paper, it is proposed an approach based on machine learning to detect phishing e-mail attacks. The methods that compose this approach are performed through a feature engineering process based on natural language processing, lemmatization, topics modeling, improved learning techniques for resampling and cross-validation, and hyperparameters configuration. The first proposed method uses all the features obtained from the Document-Term Matrix (DTM) in the classification algorithms. The second one uses Latent Dirichlet Allocation (LDA) as a operation to deal with the problems of the "curse of dimensionality", the sparsity, and the text context portion included in the obtained representation. The proposed approach reached marks with an F1-measure of 99.95% success rate using the XGBoost algorithm. It outperforms state-of-the-art phishing detection researches for an accredited data set, in applications based only on the body of the e-mails, without using other e-mail features such as its header, IP information or number of links in the text.

Managing and evolving a chatbot’s content is a laborious process and there is still a lack of standardization. In this context of standardization, the absence of a management process can lead to bad user experiences with a chatbot. This work proposes the Chatbot Management Process, a methodology for content management on chatbot systems. The proposed methodology is based on the experiences acquired with the development of Evatalk, the chatbot for the Brazilian Virtual School of Government. The focus of this methodology is to evolve the chatbot content through the analysis of user interactions, allowing a cyclic and human-supervised process. We divided the proposed methodology into three distinct phases, namely, manage, build, and analyze. Moreover, the proposed methodology presents a clear definition of the roles of the chatbot team. We validate the proposed methodology along with the creation of the Evatalk chatbot, whose amount of interactions was of 22,771 for the 1,698,957 enrolled attendees in the Brazillian Virtual School of Government in 2020. The application of the methodology on Evatalk’s chatbot brought positive results: we reduced the chatbot’s human hand-off rate from 44.43% to 30.16%, the chatbot’s knowledge base examples increased by 160% whilst maintaining a high percentage of confidence in its responses and keeping the user satisfaction collected in conversations stable.

Audio authentication is a critical task in multimedia forensics demanding robust methods to detect and identify tampered audio recordings. In this paper, a new technique to detect adulterations in audio recordings is proposed by exploiting abnormal variations in the electrical network frequency (ENF) signal eventually embedded in a questioned audio recording. These abnormal variations are caused by abrupt phase discontinuities due to insertions and suppressions of audio snippets during the tampering task. First, we propose an ESPRIT-Hilbert ENF estimator in conjunction with an outlier detector based on the sample kurtosis of the estimated ENF. Next, we use the computed kurtosis as an input for a support vector machine classifier to indicate the presence of tampering. The proposed scheme, herein designated as SPHINS, significantly outperforms related previous tampering detection approaches in the conducted tests. We validate our results using the Carioca 1 corpus with 100 unedited authorized audio recordings of phone calls.