Browsing by Issue Date, starting with "2023-09-01"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
- Evaluation of machine learning algorithms in the classification of multispectral images from the Sentinel-2A/2B Orbital Sensor for mapping the environmental dynamics of Ria Formosa (Algarve, Portugal)Publication . Souza, Flavo Elano Soares de; Rodrigues, José InácioWith the growing availability of remote sensing orbital spatial data, the applications of machine learning (ML) algorithms have been leveraging the field of process automation in image classification. The present work aimed to evaluate the precision and accuracy of ML algorithms in the classification of Sentinel 2A/2B images from an area of high environmental dynamics, such as Ria Formosa (Algarve, Portugal). The images were submitted to classification by groups of ML algorithms such as the Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbors (KNN), and Decision Tree (DT). The Orfeo Toolbox (OTB) open-source programming package made the algorithms available. Ten samples were collected for each of the 14 land use and cover classes in the Ria Formosa area, totaling 140 samples. Of these, 70% were for training and 30% for validating the classification. The evaluation metrics used were the class discrimination measures: Recall (R), the Global Kappa Index (k), and the General Accuracy Index (OA). The results showed that the KNN and DT algorithms demonstrated a greater discrimination capacity for most classes. SVM and RF significantly improved class discrimination when using larger samples for training. Merging the classified images significantly improved the classification accuracy, ranging from 71% to 81%. This evaluation made it possible to define sets of ML algorithms sensitive to change detection for mapping and monitoring dynamic environments.
- Pharmacogenetic analysis of inter-ethnic variability in the uptake transporter SLCO1B1 gene in Colombian, Mozambican, and Portuguese populationsPublication . Nega, Mulata Haile; Berhe, Derbew F.; Ribeiro, VeraBackground Statin-induced myopathy is reported to be associated with the solute carrier organic anion transporter family member 1B1 gene single nucleotide polymorphism, c.521 T > C. There is no epidemiologic data on this gene polymorphism in several countries. Therefore, this study aimed at assessing the genotype and allele frequencies of the gene variant in three countries. Methods This study involved healthy individuals from Colombia, Mozambique, and Portugal. Genomic DNA was isolated from blood samples using the Qiamp DNA Extraction Kit (Qiagen). The isolated DNA was genotyped using novel Polymerase Chain Reaction—Restriction Fragment Length Polymorphism. Microstat and GraphPad QuickCal software were used for the Chi-square test and the evaluation of Hardy–Weinberg equilibrium respectively. Results A total of 181 individuals’ blood samples were analyzed. Overall, the TT (74.0%) genotype was the highest and the CC (7.8%) was the lowest. Country wise genotypic frequencies were Colombia 47(70.2%) TT, 12(17.9%) TC and 8(11.9%) CC; Mozambique 47(88.7%) TT, 5(9.4%) TC, and 1(1.9%) CC; and Portugal 40(65.6%) TT, 16(26.2%) TC, and 5(8.2%) CC. The reference (T) allele was highest among Mozambicans (93.4%) compared to Colombians (79.1%) and Portuguese (78.7%). Mozambicans showed statistically significant genotypic and allelic frequency differences compared to Colombians (p < 0.01) and Portuguese (p < 0.01). Conclusions Overall and country-wise, CC genotype was less frequent and it is relatively high for Colombians and Portuguese populations. This finding may imply statins risk–benefit variability associated with CC genotype among these populations that needs further understanding.
- A long-term survivors of glioblastoma: a single-centre retrospective studyPublication . Fortuna, A.; Luz, P.; Cordeiro, M.Glioblastoma (GBM) is the most common primary malignant brain tumor in adults, yet, despite advancements in understanding its biology, it remains an incurable disease with a high mortality rate. Less than 5% of patients survive beyond 5 years, making identification of factors associated with long-term survival critical in improving outcomes for patients with glioblastoma.