Internet-based identification of anxiety in university students using text and facial emotion analysis.

Background: Anxiety in university students can lead to poor academic performance and even dropout. The Adult Manifest Anxiety Scale (AMAS-C) is a validated measure designed to assess the level and nature of anxiety in college students. Objective: The aim of this study is to provide internet-based alternatives to the AMAS-C in the automated identification and prediction of anxiety in young university students. Two anxiety prediction methods, one based on facial emotion recognition and the other on text emotion recognition, are described and validated using the AMAS-C Test Anxiety, Lie and Total Anxiety scales as ground truth data. Methods: The first method analyses facial expressions, identifying the six basic emotions (anger, disgust, fear, happiness, sadness, surprise) and the neutral expression, while the students complete a technical skills test. The second method examines emotions in posts classified as positive, negative and neutral in the students' profile on the social network Facebook. Both approaches aim to predict the presence of anxiety. Results: Both methods achieved a high level of precision in predicting anxiety and proved to be effective in identifying anxiety disorders in relation to the AMAS-C validation tool. Text analysis-based prediction showed a slight advantage in terms of precision (86.84 %) in predicting anxiety compared to face analysis-based prediction (84.21 %). Conclusions: The applications developed can help educators, psychologists or relevant institutions to identify at an early stage those students who are likely to fail academically at university due to an anxiety disorder.

Augmented Humanity: A Systematic Mapping Review.

Augmented humanity (AH) is a term that has been mentioned in several research papers. However, these papers differ in their definitions of AH. The number of publications dealing with the topic of AH is represented by a growing number of publications that increase over time, being high impact factor scientific contributions. However, this terminology is used without being formally defined. The aim of this paper is to carry out a systematic mapping review of the different existing definitions of AH and its possible application areas. Publications from 2009 to 2020 were searched in Scopus, IEEE and ACM databases, using search terms "augmented human", "human augmentation" and "human 2.0". Of the 16,914 initially obtained publications, a final number of 133 was finally selected. The mapping results show a growing focus on works based on AH, with computer vision being the index term with the highest number of published articles. Other index terms are wearable computing, augmented reality, human-robot interaction, smart devices and mixed reality. In the different domains where AH is present, there are works in computer science, engineering, robotics, automation and control systems and telecommunications. This review demonstrates that it is necessary to formalize the definition of AH and also the areas of work with greater openness to the use of such concept. This is why the following definition is proposed: "Augmented humanity is a human-computer integration technology that proposes to improve capacity and productivity by changing or increasing the normal ranges of human function through the restoration or extension of human physical, intellectual and social capabilities".

Parallel Niche Pareto AlineaGA--an evolutionary multiobjective approach on multiple sequence alignment.

Multiple sequence alignment is one of the most recurrent assignments in Bioinformatics. This method allows organizing a set of molecular sequences in order to expose their similarities and their differences. Although exact methods exist for solving this problem, their use is limited by the computing demands which are necessary for exploring such a large and complex search space. Genetic Algorithms are adaptive search methods which perform well in large and complex spaces. Parallel Genetic Algorithms, not only increase the speed up of the search, but also improve its efficiency, presenting results that are better than those provided by the sum of several sequential Genetic Algorithms. Although these methods are often used to optimize a single objective, they can also be used in multidimensional domains, finding all possible tradeoffs among multiple conflicting objectives. Parallel AlineaGA is an Evolutionary Algorithm which uses a Parallel Genetic Algorithm for performing multiple sequence alignment. We now present the Parallel Niche Pareto AlineaGA, a multiobjective version of Parallel AlineaGA. We compare the performance of both versions using eight BAliBASE datasets. We also measure up the quality of the obtained solutions with the ones achieved by T-Coffee and ClustalW2, allowing us to observe that our algorithm reaches for better solutions in the majority of the datasets.