DSpace Collection:https://hdl.handle.net/10316/982024-03-29T05:36:12Z2024-03-29T05:36:12ZComputational methods applied to syphilis: where are we, and where are we going?Albuquerque, GabrielaFernandes, FelipeBarbalho, Ingridy M. P.Barros, Daniele M. S.Morais, Philippi S. G.Morais, Antônio H. F.Santos, Marquiony M.Galvão-Lima, Leonardo J.Sales-Moioli, Ana Isabela L.Santos, João Paulo Q.Gil, PauloHenriques, JorgeTeixeira, César A.Lima, Thaísa S.Coutinho, Karilany D.Pinto, Talita K. B.Valentim, Ricardo A. M.https://hdl.handle.net/10316/1144832024-03-28T10:52:56Z2023-01-01T00:00:00ZTitle: Computational methods applied to syphilis: where are we, and where are we going?
Authors: Albuquerque, Gabriela; Fernandes, Felipe; Barbalho, Ingridy M. P.; Barros, Daniele M. S.; Morais, Philippi S. G.; Morais, Antônio H. F.; Santos, Marquiony M.; Galvão-Lima, Leonardo J.; Sales-Moioli, Ana Isabela L.; Santos, João Paulo Q.; Gil, Paulo; Henriques, Jorge; Teixeira, César A.; Lima, Thaísa S.; Coutinho, Karilany D.; Pinto, Talita K. B.; Valentim, Ricardo A. M.
Abstract: Syphilis is an infectious disease that can be diagnosed and treated cheaply. Despite being a curable condition, the syphilis rate is increasing worldwide. In this sense, computational methods can analyze data and assist managers in formulating new public policies for preventing and controlling sexually transmitted infections (STIs). Computational techniques can integrate knowledge from experiences and, through an inference mechanism, apply conditions to a database that seeks to explain data behavior. This systematic review analyzed studies that use computational methods to establish or improve syphilis-related aspects. Our review shows the usefulness of computational tools to promote the overall understanding of syphilis, a global problem, to guide public policy and practice, to target better public health interventions such as surveillance and prevention, health service delivery, and the optimal use of diagnostic tools. The review was conducted according to PRISMA 2020 Statement and used several quality criteria to include studies. The publications chosen to compose this review were gathered from Science Direct, Web of Science, Springer, Scopus, ACM Digital Library, and PubMed databases. Then, studies published between 2015 and 2022 were selected. The review identified 1,991 studies. After applying inclusion, exclusion, and study quality assessment criteria, 26 primary studies were included in the final analysis. The results show different computational approaches, including countless Machine Learning algorithmic models, and three sub-areas of application in the context of syphilis: surveillance (61.54%), diagnosis (34.62%), and health policy evaluation (3.85%). These computational approaches are promising and capable of being tools to support syphilis control and surveillance actions.2023-01-01T00:00:00ZLocal Periodicity-Based Beat Tracking for Expressive Classical Piano MusicChiu, Ching-YuMüller, MeinardDavies, Matthew E. P.Su, Alvin Wen-YuYang, Yi-Hsuanhttps://hdl.handle.net/10316/1144822024-03-28T10:46:28Z2023-01-01T00:00:00ZTitle: Local Periodicity-Based Beat Tracking for Expressive Classical Piano Music
Authors: Chiu, Ching-Yu; Müller, Meinard; Davies, Matthew E. P.; Su, Alvin Wen-Yu; Yang, Yi-Hsuan
Abstract: Tomodel the periodicity of beats, state-of-the-art beat
tracking systems use “post-processing trackers” (PPTs) that rely
on several empirically determined global assumptions for tempo
transition, which work well for music with a steady tempo. For
expressive classical music, however, these assumptions can be too
rigid. With two large datasets of Western classical piano music,
namely the Aligned Scores and Performances (ASAP) dataset and
a dataset of Chopin’s Mazurkas (Maz-5), we report on experiments
showing the failure of existing PPTs to cope with local
tempo changes, thus calling for new methods. In this paper, we
propose a new local periodicity-based PPT, called predominant
local pulse-based dynamic programming (PLPDP) tracking, that
allows formore flexible tempo transitions. Specifically, the newPPT
incorporates a method called “predominant local pulses” (PLP)
in combination with a dynamic programming (DP) component to
jointly consider the locally detected periodicity and beat activation
strength at each time instant. Accordingly, PLPDP accounts for the
local periodicity, rather than relying on a global tempo assumption.
Compared to existing PPTs, PLPDP particularly enhances the
recall values at the cost of a lower precision, resulting in an overall
improvement of F1-score for beat tracking in ASAP (from 0.473 to
0.493) and Maz-5 (from 0.595 to 0.838).2023-01-01T00:00:00ZFAIR-FATE: Fair Federated Learning with MomentumSalazar, TeresaFernandes, MiguelAraújo, HelderAbreu, Pedro Henriqueshttps://hdl.handle.net/10316/1144262024-03-27T12:43:01Z2023-01-01T00:00:00ZTitle: FAIR-FATE: Fair Federated Learning with Momentum
Authors: Salazar, Teresa; Fernandes, Miguel; Araújo, Helder; Abreu, Pedro Henriques
Abstract: While fairness-aware machine learning algorithms have been
receiving increasing attention, the focus has been on centralized machine
learning, leaving decentralized methods underexplored. Federated
Learning is a decentralized form of machine learning where clients train
local models with a server aggregating them to obtain a shared global
model. Data heterogeneity amongst clients is a common characteristic of
Federated Learning, which may induce or exacerbate discrimination of
unprivileged groups defined by sensitive attributes such as race or gender.
In this work we propose FAIR-FATE: a novel FAIR FederATEd Learning
algorithm that aims to achieve group fairness while maintaining high
utility via a fairness-aware aggregation method that computes the global
model by taking into account the fairness of the clients. To achieve that,
the global model update is computed by estimating a fair model update
using a Momentum term that helps to overcome the oscillations of nonfair
gradients. To the best of our knowledge, this is the first approach
in machine learning that aims to achieve fairness using a fair Momentum
estimate. Experimental results on real-world datasets demonstrate
that FAIR-FATE outperforms state-of-the-art fair Federated Learning
algorithms under different levels of data heterogeneity2023-01-01T00:00:00ZA retrospective analysis and systematic review of the areas of entertainment computing and persuasive technologies for healthSilva, Paula AlexandraBermúdez I Badia, SergiCameirão, Mónica S.https://hdl.handle.net/10316/1144202024-03-27T11:44:34Z2023-01-01T00:00:00ZTitle: A retrospective analysis and systematic review of the areas of entertainment computing and persuasive technologies for health
Authors: Silva, Paula Alexandra; Bermúdez I Badia, Sergi; Cameirão, Mónica S.
Abstract: The areas of entertainment computing and persuasive technologies are
interdisciplinary fields that have gained increasing attention in the last decades.
Health is one of the domains that has leveraged the benefits of fun to
improve the results of its technology-enabled interventions. Previous work has
reviewed the area of health entertainment from many dierent perspectives;
however, an integrative analysis across disciplines (health sciences and computer
science and engineering) throughout the development and validation cycle of
technologies in this domain is missing. Having such an in-depth retrospective
analysis would shed light on how research on entertainment computing and
persuasive technologies for health has evolved, acknowledging its contributions,
recognizing its strengths and limitations, and, as a result, allowing for the definition
of ways forward. This paper engages in an unprecedented systematic review
of the work produced between 2004 and 2017 in this area. From an initial
total of 10,350 retrieved results, a total of 1,307 full-texts were included in this
review and were thoroughly examined to gain a retrospective understanding of
the type of studies that have been produced. Among others, this systematic
review reports on the trends, venues of publication, and the characteristics of the
studies including methodologies, sample characteristics, study design, the type of
solutions produced, the conditions and domains of application, and the purpose of
the studies. Results show that there is a growing body of research in the area, with
most studies being published in roughly the same venues, and where the lion’s
share of solutions fall into the area of health rehabilitation and motor conditions.
With regards to the most addressed health domains, our review shows that most
solutions produced are aimed at stroke and fitness, followed by balance training.
Most studies (82.3%) are conducted with their target population, mostly adults
(18–49 y), and are conducted either in the lab or in clinical settings. However, the
median sample size of the studies has remained stable (N = 20) in the last decades.
Regarding technology, 2D and 3D solutions are equally used, and most systems
employ movement sensors and are single-user. Finally, only 21.4% of the studies
are performed using validated instruments.2023-01-01T00:00:00Z