Chronic diseases account for 7 of the 10 leading causes of death worldwide, including heart disease, cancer, chronic respiratory diseases, and diabetes. This study presents B-Track, a computational model designed to support non-communicable disease (NCD) care through behavior analysis. Using machine learning and data from wearable devices, B-Track creates user behavior profiles and provides personalized recommendations to promote healthier lifestyles. The model was evaluated through a prototype tested with 10 patients undergoing treatment, many of whom had existing risk factors or diagnoses such as heart disease, hypertension, or diabetes. Five patients demonstrated sustained behavioral improvements, including increased consumption of healthy foods and higher physical activity levels. Three others showed short-term improvements, and one patient showed no significant change. Evaluation using the Technology Acceptance Model indicated that 83% of users found B-Track useful, and 80% found it easy to use. These results suggest that B-Track may support long-term behavior change in managing chronic disease risk factors.

The use of game design elements in non-game contexts, defined as gamification, is being used to increase user engagement in non-game environments, such as workplaces, schools, or software applications. However, the challenge developers face when implementing gamification is identifying which game elements will engage users. Besides, the proposals often tend to support only the most common user types and engagement factors. In response to this challenge, this study proposes a generic gamification model, GamiProM. GamiProM helps to design gamified solutions by using an ontology that encompasses knowledge about gamification elements and mechanics, user types, and types of motivations. Using profile management, GamiProM aims to provide knowledge representation and add semantic value to user characteristics and the information generated by gamification. A case study allowed the evaluation of the model through the gamification of an existing application using GamiProM. The results indicate that GamiProM can identify user profiles that support personalization through a combination of software, rules, and ontologies.

Anxiety and stress are common emotional responses for human beings, but their chronic manifestation can lead to physical and psychological illnesses. The advancement of sensing technologies, such as Internet of Things, has contributed to the understanding and assisting events related to anxiety and stress. However, the main challenge is knowing which approaches can be used to better monitor these emotions and assist people. Based on a systematic literature review, this work analyzed studies both to determine how data is collected, and to monitor anxiety and stress levels. Two taxonomies synthesize the techniques mapped. The results indicated more emphasis on studying stress than anxiety and more focus on detecting anxiety and stress levels than on assisting the user. Among the main techniques to collect data, 62.5% of the studies used physiological data like heart data, and for data analysis techniques, 48% of the studies used Decision Trees.

Noncommunicable diseases (NCDs) or chronic diseases are responsible for 41 million deaths each year, equivalent to 71% of all worldwide deaths. Many technologies are used to aid the treatment of NCDs, and data analysis has been used as an approach to improve the understanding of human behaviour related to risk factors. This study aims to distinguish how human behaviour data analysis has been applied to support the treatment and prevention of NCDs, what technologies are currently used, and what gaps are still left unexplored. We conducted a systematic mapping study to analyse academic articles published from 2010 to September 2021. A filtering process mitigated article bias by reviewing, analysing, and classifying 41 works from 12,395 collected. The main results obtained presented that 43% applied data analysis in depression, 17% applied for general NCDs, and 12% for diabetes. Whereas, machine learning represents 60% of technologies found in the articles, mobile devices 58%, and wearables 29%. This study proposes two taxonomies obtained from the analysis of the selected articles that allow systematised guides to access the knowledge produced in the study. In addition, the taxonomies link technologies used to identify human behaviour with associated NCDs.

Abstract The usage of recommenders systems is already widespread. Every day people are exposed to different item offerings based on the prediction of their interests and decisions. Context information, such as location, goals, and close entities, plays a key role in the recommendations' accuracy. The use of context histories allows one to identify similar context histories and predict contexts. This article proposes Vulcont, a recommender system based on a context histories' ontology. Vulcont merges the benefits of ontology reasoning with context histories to measure the context history similarity, based on the semantic and ontology properties provided by the context’s domain. Vulcont considers synonymous and classes' relations to measure similarity. After that, a collaborative filtering approach identifies sequences' frequency to identify potential items for recommendation. The proposed recommendation is evaluated and discussed in four scenarios in an offline experiment, which explores the semantic value of context histories. The main contribution of Vulcont is the use of semantic relations and the properties of ontology in a similarity measurement of context histories, which is a data structure more complete than that of single contexts.

With the growing availability of devices capable of capturing information about their surroundings and the expansion of mobile connectivity, Internet of Things (IoT) solutions are increasingly been integrated into society. For IoT solutions to emerge successfully on the market, they will employ more than traditional mobile computing, but they will also require the use of everyday objects in an interconnected way. This interconnected world will support the intelligence in environments. In order to provide this infrastructure for environments, it will be necessary to propose platforms for software development based on context awareness and context processing. In this sense, this article proposes CMFrame, a framework for managing contextual information captured from physical environments using hierarchical and dynamic entities. CMFrame allows that entities to modify their hierarchical organization to manage environments and their related contexts. Contexts linked to each entity are also dynamic and can store different amounts of values at any time. The article presents the proposed framework and its evaluation through two applications focused on intelligent environments. The first is dedicated to monitor the movements of entities in an environment, and the second addresses energy monitoring. The scientific contribution of CMFrame is the proposal to abstract the management of dynamic and hierarchical context histories through a framework.