INESCC-DL - Artigos em Revistas Internacionais
URI permanente para esta coleção:
Navegar
Percorrer INESCC-DL - Artigos em Revistas Internacionais por Domínios Científicos e Tecnológicos (FOS) "Ciências Naturais::Ciências da Computação e da Informação"
A mostrar 1 - 10 de 10
Resultados por página
Opções de ordenação
- Data Integration in the Brazilian Public Health System for Tuberculosis: Use of the Semantic Web to Establish InteroperabilityPublication . Pellison, Felipe Carvalho; Rijo, Rui Pedro Charters Lopes; Lima, Vinicius Costa; Crepaldi, Nathalia Yukie; Bernardi, Filipe Andrade; Galliez, Rafael Mello; Kritski, Afrânio; Abhishek, Kumar; Alves, DomingosBackground: Interoperability of health information systems is a challenge due to the heterogeneity of existing systems at both the technological and semantic levels of their data. The lack of existing data about interoperability disrupts intra-unit and inter-unit medical operations as well as creates challenges in conducting studies on existing data. The goal is to exchange data while providing the same meaning for data from different sources. Objective: To find ways to solve this challenge, this research paper proposes an interoperability solution for the tuberculosis treatment and follow-up scenario in Brazil using Semantic Web technology supported by an ontology. Methods: The entities of the ontology were allocated under the definitions of Basic Formal Ontology. Brazilian tuberculosis applications were tagged with entities from the resulting ontology. Results: An interoperability layer was developed to retrieve data with the same meaning and in a structured way enabling semantic and functional interoperability. Conclusions: Health professionals could use the data gathered from several data sources to enhance the effectiveness of their actions and decisions, as shown in a practical use case to integrate tuberculosis data in the State of São Paulo.
- A Data-Driven Approach to Forecasting Heating and Cooling Energy Demand in an Office Building as an Alternative to Multi-Zone Dynamic SimulationPublication . Godinho, Xavier; Bernardo, Hermano; Sousa, João C. de; Oliveira, Filipe T.Nowadays, as more data is now available from an increasing number of installed sensors, load forecasting applied to buildings is being increasingly explored. The amount and quality of resulting information can provide inputs for smarter decisions when managing and operating office buildings. In this article, the authors use two data-driven methods (artificial neural networks and support vector machines) to predict the heating and cooling energy demand in an office building located in Lisbon, Portugal. In the present case-study, these methods prove to be an accurate and appealing alternative to the use of accurate but time-consuming multi-zone dynamic simulation tools, which strongly depend on several parameters to be inserted and user expertise to calibrate the model. Artificial neural networks and support vector machines were developed and parametrized using historical data and different sets of exogenous variables to encounter the best performance combinations for both the heating and cooling periods of a year. In the case of support vector regression, a variation introduced simulated annealing to guide the search for different combinations of hyperparameters. After a feature selection stage for each individual method, the results for the different methods were compared, based on error metrics and distributions. The outputs of the study include the most suitable methodology for each season, and also the features (historical load records, but also exogenous features such as outdoor temperature, relative humidity or occupancy profile) that led to the most accurate models. Results clearly show there is a potential for faster, yet accurate machine-learning based forecasting methods to replace well-established, very accurate but time-consuming multi-zone dynamic simulation tools to forecast building energy consumption.
- Decision Support System to Diagnosis and Classification of Epilepsy in ChildrenPublication . Rijo, Rui; Silva, Catarina; Pereira, Luis; Gonçalves, Dulce; Agostinho, MargaridaClinical decision support systems play an important role in organizations. They have a tight relation with the information systems. Our goal is to develop a system to support the diagnosis and the classification of epilepsy in children. Around 50 million people in the world have epilepsy. Epilepsy diagnosis can be an extremely complex process, demanding considerable time and effort from physicians and healthcare infrastructures. Exams such as electroencephalograms and magnetic resonances are often used to create a more accurate diagnosis in a short amount of time. After the diagnosis process, physicians classify epilepsy according to the International Classification of Diseases, ninth revision (ICD-9). Physicians need to classify each specific type of epilepsy based on different data, e.g., types of seizures, events and exams' results. The classification process is time consuming and, in some cases, demands for complementary exams. This work presents a text mining approach to support medical decisions relating to epilepsy diagnosis and ICD-9-based classification in children. We put forward a text mining approach using electronically processed medical records, and apply the K-Nearest Neighbor technique as a white-box multiclass classifier approach to classify each instance, mapping it to the corresponding ICD-9-based standard code. Results on real medical records suggest that the proposed framework shows good performance and clear interpretations, albeit the reduced volume of available training data. To overcome this hurdle, in this work we also propose and explore ways of expanding the dataset.
- Development of CART model for prediction of tuberculosis treatment loss to follow up in the state of São Paulo, Brazil: A case–control studyPublication . Yamaguti, Verena Hokino; Alves, Domingos; Rijo, Rui Pedro Charters Lopes; Miyoshi, Newton Shydeo Brandão; Ruffino-Netto, AntônioBackground: Tuberculosis is the leading cause of infectious disease-related death, surpassing even the immunodeficiency virus. Treatment loss to follow up and irregular medication use contribute to persistent morbidity and mortality. This increases bacillus drug resistance and has a negative impact on disease control. Objective: This study aims to develop a computational model that predicts the loss to follow up treatment in tuberculosis patients, thereby increasing treatment adherence and cure, reducing efforts regarding treatment relapses and decreasing disease spread. Methods: This is a case-controlled study. Included in the data set were 103,846 tuberculosis cases from the state of São Paulo. They were collected using the TBWEB, an information system used as a tuberculosis treatment monitor, containing samples from 2006 to 2016. This set was later resampled into 6 segments with a 1-1 ratio. This ratio was used to avoid any bias during the model construction. Results: The Classification and Regression Trees were used as the prediction model. Training and test sets accounted for 70% in the former and 30% in the latter of the tuberculosis cases. The model displayed an accuracy of 0.76, F-measure of 0.77, sensitivity of 0.80 and specificity of 0.71. The model emphasizes the relationship between several variables that had been identified in previous studies as related to patient cure or loss to follow up treatment in tuberculosis patients. Conclusion: It was possible to construct a predictive model for loss to follow up treatment in tuberculosis patients using Classification and Regression Trees. Although the fact that the ideal predictive ability was not achieved, it seems reasonable to propose the use of Classification and Regression Trees models to predict likelihood of treatment follow up to support healthcare professionals in minimising the loss to follow up.
- Managing Data in Screening Programs: Challenges and SolutionsPublication . Monteiro, Hugo; Oliveira, Mariana; Martinho, Ricardo; Martins, CarlosPopulation-based screening programs are vital public health initiatives that enable the early detection of diseases, significantly reducing both morbidity and healthcare costs. As these programs expand, the management of the extensive data they generate becomes increasingly complex, highlighting the need for structured digital solutions. This narrative review article presents a pragmatic framework aimed at clarifying big data analytics tailored to the needs and practices of healthcare professionals and administrators, focusing on effective integration into routine screening workflows. To achieve effective data utilization, the process begins with systematic archiving, which involves cloud-based storage solutions capable of securely maintaining various data formats in compliance with regulatory standards, thus ensuring long-term accessibility and continuity. Subsequent real-time processing of screening data facilitates rapid decision-making and patient management by providing immediate validation and analysis, essential for maintaining the responsiveness of screening services. Transformation processes play a critical role in converting diverse data inputs into standardized, consistent formats, enabling seamless communication and exchange among multiple healthcare systems. Integration further builds upon this standardization, merging data from different healthcare providers and diagnostic centers into centralized analytical platforms. This unified approach enables comprehensive patient monitoring and supports predictive modeling for early identification of at-risk individuals. Advanced analytics, particularly process mining and predictive techniques, reveal inefficiencies within screening workflows, highlighting areas needing improvement. These methods help healthcare managers to streamline operations, optimize resources, and enhance overall program performance. Real-time visualization tools provide administrators with continuous, practical insights into operational dynamics, despite existing challenges related to data governance and system interoperability. This article illustrates these concepts through concrete examples from the colorectal cancer screening program in Northern Portugal and the response to the COVID-19 pandemic. The colorectal cancer screening scenario demonstrates how structured data management significantly boosts operational efficiency and healthcare accessibility. Meanwhile, the COVID-19 experience highlights the importance of having flexible digital infrastructures capable of quickly adapting to unexpected crises. Finally, ongoing investments in digital infrastructure, professional training, and comprehensive data governance are crucial for sustaining these improvements. This review provides clear, actionable knowledge to support healthcare professionals in adopting big data analytics effectively within preventive healthcare programs.
- A multi-objective genetic algorithm applied to autonomous underwater vehicles for sewage outfall plume dispersion observationsPublication . Moura, Ana; Rijo, Rui; Silva, Pedro; Crespo, SidónioThis work presents a multi-objective genetic algorithm to solve route planning problem for multiple autonomous underwater vehicles (AUVs) for interdisciplinary coastal research. AUVs are mobile unmanned platforms that carry their own energy and are able to move themselves in the water without intervention from an external operator. Using AUVs one can provide high-quality measurements of physical properties of effluent plumes in a very effective manner under real oceanic conditions. The AUV's route planning problem is a combinatorial optimization problem, where the vehicles must travel through a three-dimensional irregular space with all dimensions known. Therefore, minimization of the total travel distance while considering the maximum number of water samples is the main objective. Besides the AUV kinematics restrictions other considerations must be taken into account to the problem, like the ocean currents. The practical applications of this approach are the environmental monitoring missions which typically require the sampling of a volume of water with non-trivial geometry for which parallel line sweeping might be a costly solution. Some real-life test problems and related solutions are presented.
- No polarization–Expected Values of Climate Change Impacts among European Forest Professionals and ScientistsPublication . Persson, Johannes; Blennow, Kristina; Gonçalves, Luisa; Borys, Alexander; Dutcă, Ioan; Hynynen, Jari; Janeczko, Emilia; Lyubenova, Mariyana; Martel, Simon; Merganic, Jan; Merganičová, Katarína; Peltoniemi, Mikko; Petr, Michal; Reboredo, Fernando H.; Vacchiano, Giorgio; Reyer, Christopher P. O.The role of values in climate-related decision-making is a prominent theme of climate communication research. The present study examines whether forest professionals are more driven by values than scientists are, and if this results in value polarization. A questionnaire was designed to elicit and assess the values assigned to expected effects of climate change by forest professionals and scientists working on forests and climate change in Europe. The countries involved covered a north-to-south and west-to-east gradient across Europe, representing a wide range of bio-climatic conditions and a mix of economic-social-political structures. We show that European forest professionals and scientists do not exhibit polarized expectations about the values of specific impacts of climate change on forests in their countries. In fact, few differences between forest professionals and scientists were found. However, there are interesting differences in the expected values of forest professionals with regard to climate change impacts across European countries. In Northern European countries, the aggregated values of the expected effects are more neutral than they are in Southern Europe, where they are more negative. Expectations about impacts on timber production, economic returns, and regulatory ecosystem services are mostly negative, while expectations about biodiversity and energy production are mostly positive.
- Removing Barriers to Promote Social Computing among Senior PopulationPublication . Marcelino, Isabel; Laza, Rosalía; Fdez-Riverola, Florentino; Pereira, AntónioSmartphones and tablets proliferation enabled by accessible prices and also by the inclusion of sensing abilities promotes their use in several areas, such as healthcare. It opens new horizons in the field of continuous and noninvasive monitoring and support to population, namely, to seniors. Despite the great benefits that mobile sensing and social computing could provide to increase elderly’s quality of life, many studies have shown that elderlies deal with difficulty with Information and Communication Technology (ICT). In this paper we present a solution to overcome barriers between elderlies and their ICT usage in order to potentiate all the benefits provided from mobile sensing and social computing. A survey on guidelines, standards, and advice regarding usability and accessibility issues when developing solutions for elderly people was carried out. This survey was made having in mind that senior population have singular requirements due to age related changes and also frequently technological illiteracy. We have identified and applied the most important guidelines to our solution. A prototype was made using responsive design in order to be adaptable to any type of devices. Regarding evaluation, usability tests and semistructured interviews were conducted in real scenario.
- A simple heuristic for the identification of the case ID attribute in unlabelled process mining event logsPublication . Vicente, André; Grilo, Carlos; Rijo, Rui; Martinho, RicardoThis study addresses the critical challenge of identifying and labelling the case ID attribute in unlabelled event logs, a fundamental task in process mining. Case IDs uniquely associate events with individual process instances, enabling accurate analysis and discovery of operational insights. Manual identification of case IDs is error-prone and labour-intensive, often hindering the scalability and reliability of process mining analyses. This paper introduces a novel heuristic method that automates case ID identification, improving efficiency and accuracy for diverse real-world datasets. The proposed heuristic leverages unique temporal patterns observed in event logs to distinguish case ID attributes from other attributes. It calculates a weighted average of temporal spans and applies customisable parameters to prioritise relevant attributes. The method was validated using 27 datasets from the Business Process Intelligence (BPI) Challenge, representing a variety of industries and event log complexities. Performance metrics, including success rates and computational efficiency, were benchmarked against existing approaches. The heuristic achieved an 85.2% top-1 success rate, and remains effective provided at least one repeating categorical attribute is present - a condition met by virtually all publicly available business and industrial logs. It consistently ranked case IDs among the top attributes even in challenging scenarios, such as cyclic processes and multi-correlated data. The method demonstrated robustness across diverse datasets, processing large event logs within seconds, highlighting its practicality for real-world applications. This research contributes an innovative and explainable approach to case ID identification that requires only raw event logs, contrasting with existing methods reliant on pre-labelled data or complex pipelines. Its simplicity, efficiency, and adaptability to various process types make it a valuable tool for advancing process mining capabilities.
- The small world of efficient solutions: empirical evidence from the bi-objective {0,1}-knapsack problemPublication . Silva, Carlos Gomes da; Clímaco, João; Filho, Adiel AlmeidaThe small world phenomenon, Milgram (1967) has inspired the study of real networks such as cellular networks, telephone call networks, citation networks, power and neural networks, etc. The present work is about the study of the graphs produced by efficient solutions of the bi-objective {0,1}-knapsack problem. The experiments show that these graphs exhibit properties of small world networks. The importance of the supported and non-supported solutions in the entire efficient graph is investigated. The present research could be useful for developing more effective search strategies in both exact and approximate solution methods of {0,1} multi-objective combinatorial optimization problems.