Percorrer por autor "Leithardt, Valderi Reis Quietinho"
A mostrar 1 - 5 de 5
Resultados por página
Opções de ordenação
- Complex graph neural networks for medication interaction verificationPublication . Westarb, Gustavo; Stefenon, Stefano Frizzo; Hoppe, Aurélio Faustino; Sartori, Andreza; Klaar, Anne Carolina Rodrigues; Leithardt, Valderi Reis QuietinhoThis paper presents the development and application of graph neural networks to verify drug interactions, consisting of drug-protein networks. For this, the DrugBank databases were used, creating four complex networks of interactions: target proteins, transport proteins, carrier proteins, and enzymes. The Louvain and Girvan-Newman community detection algorithms were used to establish communities and validate the interactions between them. Positive results were obtained when checking the interactions of two sets of drugs for disease treatments: diabetes and anxiety; diabetes and antibiotics. There were found 371 interactions by the Girvan-Newman algorithm and 58 interactions via Louvain.
- Dimensionality-reducing classifiers for Spanish winter maintenance of roadwaysPublication . Jiménez-Bravo, Diego M.; Bajo, Javier; Dopazo, Esther; De Paz, Juan F.; Leithardt, Valderi Reis QuietinhoPublic administrations try to maintain and guarantee safety as one of their priorities. Road networks are one of the environments where most incidents usually happen; therefore, it is very important to maintain the safety of drivers and passengers. This safety must be maintained even in adverse circumstances, such as winter weather conditions. Thus, chemical treatments are incorporated to be applied on roads when certain conditions are met. Determining which treatment to apply can be automated through the use of sensors and machine learning techniques. To this end, the article proposes a classifier model capable of predicting the most appropriate chemical treatment based on the environmental properties of the road and its surroundings. The achieved solution offers good results in terms of evaluation metrics.
- Enhancing the interoperability of heterogeneous hardware in the Industry: a Multi-Agent System ProposalPublication . Alejano, Fernando Lobato; Iglesia, Daniel H. de la; Mateos, Mariano Raboso; Rivero, Alfonso J. López; Leithardt, Valderi Reis QuietinhoThe unstoppable growth of technological solutions, especially in relation to communication processes and industrial environments, has led to the rise of the term Industry 4.0. In this new reality, data converted into knowledge is the main protagonist. However, the existence of heterogeneous technologies results in complex processes and ends up hindering the implementation of new environments. In order to simplify this casuistry, this work defines an agent-based system that integrates mature technologies for the intercommunication of devices and de facto standards such as Modbus, as well as state-of-the-art solutions related to fields such as Computer Vision and other low-cost ones, such as those provided by those based on IoT. Finally, a case study is proposed that focuses on a circular economy model that, taking advantage of the benefits of the described mechanisms and in a simple way, shows the possibility of generating a positive impact on the environment. Specifically, the case proposes mechanisms for processing and sorting waste components - lithium batteries - making it easier to give them a second life before they become permanent and highly polluting waste.
- Identification of Abnormal Behavior in Activities of Daily Life Using Novelty DetectionPublication . Freitas, Mauricio; de Aquino Piai, Vinicius; Dazzi, Rudimar; Teive, Raimundo; Parreira, Wemerson; Fernandes, Anita; Pires, Ivan Miguel; Leithardt, Valderi Reis QuietinhoThe world population is aging at a rapid pace. According to the WHO (World Health Organization), from 2015 to 2050, the proportion of elderly people AQ1 will practically double, from 12 to 22%, representing 2.1 billion people. From the individual’s point of view, aging brings a series of challenges, mainly related to AQ2 health conditions. Although, seniors can experience opposing health profiles. With advancing age, cognitive functions tend to degrade, and conditions that affect the physical and mental health of the elderly are disabilities or deficiencies that affect Activities of Daily Living (ADL). The difficulty of carrying out these activities within the domestic context prevents the individual from living independently in their home. Abnormal behaviors in these activities may represent a decline in health status and the need for intervention by family members or caregivers. This work proposes the identification of anomalies in the ADL of the elderly in the domestic context through Machine Learning algorithms using the Novelty Detection method. The focus is on using available ADL data to create a baseline of behavior and using new data to classify them as normal or abnormal daily. The results obtained using the E-Health Monitoring database, using different Novelty Detection algorithms, have an accuracy of 91% and an F1-Score of 90%.
- LoRaWAN Applied to Agriculture: A Use Case for Automated Irrigation SystemsPublication . Hernández, Esteban Sánchez; García, Alberto González; Izquierdo, Lidia Rozas; González, José Torreblanca; Silva, Luís Augusto; Ovejero, Raúl García; Leithardt, Valderi Reis Quietinho