Business platform models frequently require continuous adaptation and agility to allow new experiences to be created and delivered to customers. To understand user behavior in online systems, researchers have taken advantage of a combination of traditional and recently developed analysis techniques. Earlier studies have shown that user behavior monitoring data, as obtained by mouse tracking, can be utilized to improve user experience (UX). Many mouse-tracking solutions exist; however, the vast majority is proprietary, and open-source packages do not provide the resources and data needed to support UX research. Thus, this paper presents: 1) the development of an interaction monitoring application titled Artificial Intelligence and Mouse Tracking-based User eXperience Tool (AIMT-UXT); 2) the validation of the tool in a case study conducted on the Website of the Brazilian Federal Revenue Service (BFR); 3) the definition of a new relationship pattern of variables that determine user behavior; 4) the construction of a fuzzy inference system for measuring user performance using the defined variables and the data captured in the case study; and 5) the application of a clustering algorithm to complement the analysis. A comparison of the results of the applied quantitative methodologies indicates that the developed framework was able to infer UX scores similar to those reported by users in questionnaires.

User eXperience (UX) has been used to achieve improvements in digital information systems based on how people perceive them. In particular, this paper establishes a framework that employs methods for eye and mouse tracking, keyboard input, self-assessment questionnaire and artificial intelligence algorithms to evaluate user experience and categorize users in terms of performance profiles. The results obtained with this framework are artifacts that can be used to support customizations of the User Interface (UI) on the websites. Moreover, the established framework is generic and flexible and can be applied to any information system, such as the case study shown in the website of the Federal Revenue of Brazil (RFB). The main objectives of this paper are as follows: (i) to set out a powerful UX framework based on three tracking techniques – the AIT2-UX; (ii) to provide the T2-UXT to collect, collate, process and visualize data obtained from users’ interactions (iii) to use and compare machine learning algorithms with the classification of user performance profiles; (iv) to use the artifacts generated by the framework to manually customize the UI with the website.

Handover (HO) is designed to facilitate user mobility and ensure quality of service in mobile networks. In multiple base station (eNodeBs) scenarios, the HO priority process is a problem that has been studied in many surveys, as neglecting the use of priority-based schemes can result in high amounts of HO and, consequently, a decrease in the quality of services provided. This paper presents a Heuristic for Handover based on AHP-TOPSIS-FUZZY (H2ATF), which generates a priority ranking of eNodeBs from the use of (a) the analytical hierarchical process (AHP) to define the weights of the criteria; (b) the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to rank the selected target cells; and (c) the use of an adaptive hysteresis calculated through a fuzzy inference system based on parameters that directly impact the HO process. Through this proposal, it was possible to define the best time and, together, the best antenna to perform the HO. The results demonstrate a decrease of up to 43% in HO ping pong (HPP), a widely used metric in the literature to evaluate HO heuristics.

This article presents a study on the variables promoting student retention in distance undergraduate courses at Federal University of Pará, aiming to help school managers minimize student attrition and maximize retention until graduation. The theoretical background is based on Rovai's Composite Model and the methodological approach is conditional probability analysis using the Bayesian Networks graphical model. Network modeling has shown that among internal factors after admission to the course (as defined in the Composite Model) face-to-face tutorial sessions need to be better planned and executed, learning materials are still not adequate to online course specificities and the support structure needs to be remodeled.

Understanding emotions is one of the greatest capabilities of human beings, as it allows the understanding of facial expressions that facilitate the capture of important information about other individuals, which are used for the perception of mental or emotional states. Advances in Artificial Intelligence and Visual Computing, more specifically in Deep Learning with the advent of Artificial Neural Networks, have enhanced the ability of machines to infer human emotions through image analysis. This paper presents a Systematic Literature Review (SLR) with the purpose of researching, mapping and summarizing studies that address techniques or algorithms more efficiently. The convolutional neural network models analyzed in this review are based on deep learning with an emphasis on expression and microexpression recognition. The results suggest that database uses, with laboratory controlled images, combined with CNN’s such as VGG and ResNet, have excellent performances in their tests. For better understanding, we will detail and compare all the methods obtained in the review.