Abstract
Data has increased in a large scale in various fields leading to the coin of the term Big Data. Big data is mainly used to describe enormous datasets that typically includes masses of unstructured data that may need real-time analysis. As human behaviour and personality can be captured through human-computer interaction a massive opportunity opens for providing wellness services. Through the use of interaction data, behavioral biometrics can be obtained. The usage of biometrics has increased due to several factors such as the rise of power and availability of computational power. One of the challenges in this kind of approaches has to do with handling the acquired data. The growing volumes, variety and velocity brings challenges in the tasks of pre-processing, storage and providing analytics. In this sense, the problem can be framed as a Big Data problem. In this work it is intended to provide an architecture that accommodates the data pipeline of data generated by human-computer interaction, providing real time data analytics on behavioral biometrics.

Abstract
There is currently a significant interest in consumer electronics in applications and devices that monitor and improve the user's well-being. This is one of the key aspects in the development of ambient intelligence systems. Nonetheless, existing approaches are generally based on physiological sensors, which are intrusive and cannot be realistically used, especially in ambient intelligence in which the transparency, pervasiveness and sensitivity are paramount. We put forward a new approach to the problem in which user behavioral cues are used as an input to assess inner state. This innovative approach has been validated by research in the last years and has characteristics that may enable the development of true unobtrusive, pervasive and sensitive ambient intelligent systems. © 2017 by SCITEPRESS - Science and Technology Publications, Lda.

Abstract
Learning styles are strongly connected with learning and when it comes to acquiring new knowledge, attention is one the most important mechanisms. The learner's attention affects learning results and can define the success or failure of a student. When students are carrying out learning activities using new technologies, it is extremely important that the teacher has some feedback from the students' work in order to detect potential learning problems at an early stage and then to choose the appropriate teaching methods. In this paper we present a nonintrusive distributed system for monitoring the attention level in students. It is especially suited for classes working at the computer. The presented system is able to provide real-time information about each student as well as information about the class, and make predictions about the best learning style for a student using an ensemble of neural networks. It can be very useful for teachers to identify potentially distracting events and this system might be very useful to the teacher to implement more suited teaching strategies. (C) 2017 Published by Elsevier B.V.

Abstract
Usually, Machine Learning systems are seen as something fully automatic. Recently, however, interactive systems in which human experts actively contribute towards the learning process have shown improved performance when compared to fully automated ones. This may be so in scenarios of Big Data, scenarios in which the input is a data stream, or when there is concept drift. In this paper, we present a system for supporting auditors in the task of financial fraud detection. The system is interactive in the sense that the auditors can provide feedback regarding the instances of the data they use, or even suggest new variables. This feedback is incorporated into newly trained Machine Learning models which improve over time.

Abstract
Machine Learning systems are generally thought of as fully automatic. However, in recent years, interactive systems in which Human experts actively contribute towards the learning process have shown improved performance when compared to fully automated ones. This may be so in scenarios of Big Data, scenarios in which the input is a data stream, or when there is concept drift. In this paper we present a system for supporting auditors in the task of financial fraud detection. The system is interactive in the sense that the auditors can provide feedback regarding the instances of the data they use, or even suggest new variables. This feedback is incorporated into newly trained Machine Learning models which improve over time. In this paper we show that the order by which instances are evaluated by the auditors, and their feedback incorporated, influences the evolution of the performance of the system over time. The goal of this paper is to study of different instance selection strategies for Human evaluation and feedback can improve the learning speed. This information can then be used by the system to determine, at each moment, which instances would improve the system the most, so that these can be suggested to the users for validation. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
Machine Learning has been evolving rapidly over the past years, with new algorithms and approaches being devised to solve the challenges that the new properties of data pose. Specifically, algorithms must now learn continuously and in real time, from very large and possibly distributed sets of data. In this paper we describe a learning system that tackles some of these novel challenges. It learns and adapts in realtime by continuously incorporating user feedback, in a fully autonomous way. Moreover, it allows for users to manage features (e.g. add, edit, remove), reflecting these changes on-the-fly in the Machine Learning pipeline. The paper describes some of the main functionalities of the system, which despite being of general-purpose, is being developed in the context of a project in the domain of financial fraud detection.