This article presents a systematic review of the literature concerning scientific publications on wrist wearables that can help to identify stress levels. The study is part of a research project aimed at modeling a stress surveillance system and providing coping recommendations. The investigation followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. In total, 38 articles were selected for full reading, and 10 articles were selected owing to their alignment with the study proposal. The types of technologies used in the research stand out amongst our main results after analyzing the articles. It is noteworthy that stress assessments are still based on standardized questionnaires, completed by the participants. The main biomarkers collected by the devices used in the selected works included: heart rate variation, cortisol analysis, skin conductance, body temperature, and blood volume at the wrist. This study concludes that developing a wrist wearable for stress identification using physiological and chemical sensors is challenging but possible and applicable.
23 February 2022 in Journal of Internet Services and Applications
Macroprogramming's primary goal is to increase developers' productivity by providing high-level specifications of applications' behaviour at the system level. Macroprogramming may be a viable solution for developing complex IoT applications, such as those manipulating high data volume and heterogeneity. This paper updates a recent work identifying and analysing primary research on macroprogramming in IoT through a systematic literature mapping (SLM). We extended the search strategy scope by conducting an automatic search over five new databases and also performed the snowballing technique. As a result, besides the 38 studies group found in previous SLM, nine new papers were classified as relevant and rigorously analysed, totalising forty-seven studies. In comparison to previous work, results still point out the recurrence of abstractions in the network infrastructure, highlighting the use of frameworks in one-third of the applications and contributing with an overview of macroprogramming by researchers in different knowledge areas.
Context: Tabular data predominate in machine learning applications; however, data scarcity, class imbalance, and privacy-related constraints often impair the model performance. Therefore, AI-centric data-synthesis techniques have been adopted to mitigate these challenges. Objective: To systematically map the state of the art in AI-driven tabular-data augmentation, identifying trends, methodological gaps, and best practices. Method: The review followed Kitchenham’s guidelines and covered the ACM Digital Library, Compendex, IEEE Xplore, ScienceDirect, and Scopus for the period 2020–2024. After deduplication and application of the inclusion and exclusion criteria, 55 primary studies were selected and analyzed with respect to the eight research questions. Results: Of the 55 studies, 210 quantitative results were extracted: 70.95% employed utility metrics, and only 7.14% assessed privacy. To organize this heterogeneous landscape, we propose a taxonomic framework: solution type $\times $ evaluation $\times $ metric, highlighting gaps and redundancies. Conclusions: Although research has progressed from conventional synthesizers to hybrid and novel architectures, metric standardization and systematic privacy assessments remain limited. Future work should address these gaps and apply fidelity and privacy metrics to underrepresented tasks such as regression problems and ultra-rare-class datasets.
10 October 2024 in Journal of Systems and Software
IoT infrastructures are becoming increasingly more difficult to manage. One of the main issues is the high volatility present in the infrastruture, which increasingly demands self-adaptive solutions. As a proposal to handle this challenge, this paper presents STEER (Sdn-based inTEnt drivEn iot netwoRks), a new approach for the dynamic adaptation of IoT networks for indoor monitoring applications, based on the unification of Intent-Driven Networks (IDN) and Software-Defined Networks (SDN). Particularly, we explore the ability of IDNs to dynamically interpret an application’s intent, using an IDN-based mediator attached to an SDN-controller to autonomously adapt the IoT network behavior at runtime, thus realizing the intent according to the current operating context of the network. We demonstrate the approach using a representative application scenario related to IoT indoor environment monitoring in the domain of indoor air quality monitoring. The experiments allowed us to validate the applicability of the approach and show the system-wide effect of dynamic adaptation to the current operating environment on improving performance according to the metric under consideration, in this case, the number of application-level messages exchanged in the network.
5 October 2023 in Revista de Informática Teórica e Aplicada
Health applications received more attention with the use of the Internet of Things - IoT, due to the use of sensors for remote monitoring, not only in hospital environments but also in domestic environments and in meditative and routine activities. Wearable chemical sensors have been proposed in the health area for the continuous monitoring of the individual's well-being, however, the challenges related to the convergence of these two areas still require a lot of research for the solutions to be effectively applied. This article aims to present the results of a systematic literature review (SLR) carried out to highlight applications that employ the use of wearable chemical sensors in IoT contexts. The results presented several challenges and open questions of a promising research field involving IoT and wearable chemical sensors. The review was performed on the same basis used to make the original SLR, in which the period from December 2021 to February 2023 was adopted as an interval. As a result, in addition to the 15 (fifteen) studies found in the previous SLR, 7 (seven) new articles were classified as relevant, totaling 22 (twenty-two) studies. Regarding the previous.