Abstract
Interactive Voice Assistants (IVAs) are intelligent conversational agents capable of communicating with users using natural language. Although IVAs are more frequent in our lives, customer experience research with these agents is still in its infancy. This article aims to identify the factors that form the customer experience (CX) with Alexa and assesses its impact on traditional marketing outcomes: satisfaction and recommendation. This research presents a conceptual model of CX with IVAs and an empirical validation of the model using Structural Equation Modelling based on a sample of 580 IVA users. The results confirm that CX is a multidimensional higher-order construct composed of six factors (usefulness, ease of use, trust, privacy concerns, communication skills, and enjoyment). We also highlight the positive impact of experience on satisfaction and recommendation. Finally, we test the enthusiasm moderating role, showing its negative influence on the investigated relationships. Theoretical and practical implications are discussed.

Abstract
The aspect of energy constraint and simulation of battery behavior in robotic simulators has been partially neglected by most of the available simulation software and is offered unlimited energy instead. This lack does not reflect the importance of batteries in robots, as the battery is one of the most crucial elements. With the implementation of an adequate battery simulation, it is possible to perform a study on the energy requirements of the robot through these simulators. Thus, this paper describes a Lithium-ion battery model implemented on SimTwo robotic simulator software, in which various physical parameters such as internal resistance and capacity are modeled to mimic real-world battery behavior. The experiments and comparisons with a real robot have assessed the viability of this model. This battery simulation is intended as an additional tool for the roboticists, scientific community, researchers, and engineers to implement energy constraints in the early stages of robot design, architecture, or control.

Abstract

Abstract
The public transport system is responsible for the displacement of a large part of the population, particularly in developing countries. This fact makes it relevant to evaluate the performance of public transport to provide an efficient and effective service. The purpose of this study is to conduct a performance evaluation of the public transport operation in the Metropolitan Region of Fortaleza (MRF), in the State of Ceara, Brazil. The analysis is based on DEA and the Malmquist index, based on three inputs (total operating time, fleet age, and the mileage traveled) and two outputs (fare revenue and number of passengers). Data were obtained through automated fare collection systems (AFCs) that were implemented in the MRF. Although there were no major fluctuations in performance during the analyzed period, the results indicate that the system's performance declined in certain years. In addition, the analysis enables a better understanding of route performance, considering the operating company or the area of operation, which helps to diagnose and comprehend the operation more effectively. By analyzing the operational performance over time, the proposed approach provides an additional contribution by offering a comprehensive overview to the involved stakeholders, fostering decision-making processes based on evidence.

Abstract
Background and objective: Traumatic Brain Injury (TBI) is one of the leading causes of injury-related mortality in the world, with severe cases reaching mortality rates of 30-40%. It is highly heterogeneous both in causes and consequences making more complex the medical interpretation and prognosis. Gathering clinical, demographic, and laboratory data to perform a prognosis requires time and skill in several clinical specialties. Artificial intelligence (AI) methods can take advantage of existing data by performing helpful predictions and guiding physicians toward a better prognosis and, consequently, better healthcare. The objective of this work was to develop learning models and evaluate their capability of predicting the mortality of TBI. The predictive model would allow the early assessment of the more serious cases and scarce medical resources can be pointed toward the patients who need them most. Methods: Long Short Term Memory (LSTM) and Transformer architectures were tested and compared in performance, coupled with data imbalance, missing data, and feature selection strategies. From the Medical Information Mart for Intensive Care III (MIMIC-III) dataset, a cohort of TBI patients was selected and an analysis of the first 48 hours of multiple time series sequential variables was done to predict hospital mortality. Results: The best performance was obtained with the Transformer architecture, achieving an AUC of 0.907 with the larger group of features and trained with class proportion class weights and binary cross entropy loss. Conclusions: Using the time series sequential data, LSTM and Transformers proved to be both viable options for predicting TBI hospital mortality in 48 hours after admission. Overall, using sequential deep learning models with time series data to predict TBI mortality is viable and can be used as a helpful indicator of the well-being of patients.

Abstract
Multiple studies show an association between anxiety disorders and dysregulation in the Autonomic Nervous System (ANS). Thus, understanding how informative the physiological signals are would contribute to effectively detecting anxiety. This study targets the classification of anxiety as an imbalanced binary classification problem using physiological signals collected from a sample of healthy subjects under a neutral condition. For this purpose, the Electrocardiogram (ECG), Electrodermal Activity (EDA), and Electromyogram (EMG) signals from the WESAD publicly available dataset were used. The neutral condition was collected for around 20 min on 15 participants, and anxiety scores were assessed through the shortened 6-item STAI. To achieve the described goal, the subsequent steps were followed: signal pre-processing; feature extraction, analysis, and selection; and classification of anxiety. The findings of this study allowed us to classify anxiety with discriminatory class features based on physiological signals. Moreover, feature selection revealed that ECG features play a relevant role in anxiety classification. Supervised feature selection and data balancing techniques, especially Borderline SMOTE 2, increased the performance of most classifiers. In particular, the combination of feature selection and Borderline SMOTE 2 achieved the best ROC-AUC with the Random Forest classifier.