Lamprini Pappa

The widespread availability of smartphones and their high processing power have made them powerful mobile tools able to host and run various apps. In addition, wearable devices with low cost and accurate sensors gathering various physiological data and information are now available. Meanwhile, automated activity recognition is a rapidly evolving research area directly related to the mobile Health (mHealth) field. Rapid advancements in the Human Activity Recognition (HAR) field are mainly based on combining smartphones and wearable devices to succeed in advancing health tracking. This paper presents a mobile app designed and developed for monitoring changes in variables related to the physiological health status of an individual when he is moving around. The app tracks the physiological status of a human along with machine learning algorithms able to recognize and identify human activity and produce automatic alerts warning of dangerous health situations.

This paper deals with the problem of identifying and recognizing everyday human activities. The main goal is to compare a variety of implemented classification models founded on diverse machine learning approaches; one that utilizes features extracted from the time and frequency domain and three others that take advantage of the attributes of the symbolic space in order to extract conclusions regarding the performance and the potential usefulness of each of them. To guarantee the impartiality of the comparison, we used the signals contained in a free accessible dataset, which are subjected to the same preprocessing, and divided into equal time-length windows. The Nearest Neighour classifier is applied to compare the four approaches.

Knowledge and skills in the field of Artificial Intelligence (AI), Internet of Things (IoT), and Edge Computing (EC) are more and more important for industry. Therefore, it is crucial to know what current students and future employees can offer to the industry. University students develop their knowledge and skills to support the industry in implementing modern technologies in the future. It can be expected that the first source of information for students will be lectures and other activities at the university. However, they may obtain knowledge from other sources. This article presents the results of research conducted among students assessing their own knowledge and skills in the field of IoT, AI, and EC. The research was preceded by an analysis of curricula at selected universities in terms of topics related to AI, IoT, and EC. Based on the results of the analysis, survey questions were prepared. The developed questionnaire was made available to students. The research sample for the survey participants was 563 students. The results obtained were analyzed. The results of the analysis show which issues are better known to students and which are worse. The information presented in this paper can be a source of information for the industry that can assess the competences that are or will be available on the labor market in the near future. Additionally, universities can obtain information on the areas in which there are competency gaps and which methods of teaching AI, IoT, and EC are better perceived by students.

In this work, we introduce the Slopewise Aggregate Approximation (SAA), an innovative variation of the Piecewise Aggregate Approximation. The Slopewise Aggregate Approximation (SAA) is used as a novel core step for the Symbolic Aggregate Approximation method. SAA efficiently describes the trend at a time series signal since it incorporates information regarding the shape and fluctuation of the time series while simultaneously achieving the problem's dimensionality reduction. Then, by applying the discretization technique, the problem is transformed into a symbolic space problem, and the Intelligent Icons are the features that come out and feed a Near Neighbour classifier for a Human Activity Recognition problem. The results achieved by the proposed method are directly compared to two relevant past implementations and exhibit a considerable increase in classification metrics.

Industry 4.0 has risen as an integrated digital manufacturing environment, and it has created a novel research perspective that has thrust research to interdisciplinarity and exploitation of ICT advances. This work presents and discusses the main aspects of Industry 4.0 and how intelligence can be embedded in manufacturing to create the smart factory. It briefly describes the main components of Industry 4.0, and it focuses on the security challenges that the fully interconnected ecosystem of Industry 4.0 has to meet and the threats for each component. Preserving security has a crucial role in Industry 4.0, and it is vital for its existence, so the main research directions on how to ensure the confidentiality and integrity of the information shared among the Industry 4.0 components are presented. Another view is in light of the security issues that come as a result of enabling new technologies.

In this work, we introduce the Multichannel Intelligent Icons, a novel method for producing and presenting essential patterns of multidimensional bio-signals. The proposed approach is an extension of Symbolic Aggregate Approximation (SAX) along with an innovative variation of Intelligent Icons. The innovation on the approach stands on the grounds of creating a spatial correlation of the inherited information in all dimensions and so it provides extra features for distinguishing the human activities. The proposed model is testing on Human Activity recorded data and for the classification purposes a Nearest Neighbour classifier is applied. The achieved results are compared with the case of applying single-channel intelligent icons approach and it is inferred a noteworthy increase in terms of accuracy and sensitivity with the proposed approach.