Carrera de Biotecnología

Permanent URI for this collectionhttp://repositorio.uta.edu.ec/handle/123456789/34800

Browse

Subject: search.filters.subject.MACHINE LEARNING

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Evaluación de un modelo de aprendizaje automático basado en redes neuronales para el diagnóstico temprano de la enfermedad de Alzheimer
    (Universidad Técnica de Ambato. Facultad de Ciencia e Ingeniería en Alimentos y Biotecnología. Carrera de Biotecnología, 2025-02) Sarabia Ortiz, Lilián Catalina; Galarza Galarza, Cristian Fernando
    Alzheimer's disease, as the leading cause of dementia, poses a critical challenge in its early detection, where timely interventions can delay its progression. This issue is addressed by evaluating deep learning models based on neural networks to classify magnetic resonance imaging (MRI) scans into different stages of the disease using data from the OASIS and ADNI databases. The importance lies in the need for precise and automated tools to improve early diagnosis, particularly in stages such as mild cognitive impairment. The methodology included constructing a dataset from preprocessed images and applying it to the EfficientNet B7 and ResNet50 architectures. These were trained with advanced techniques such as data augmentation and validated across scenarios involving controlled data, modified images, and new data. Performance metrics such as precision, recall, specificity, F1-score, and ROC-AUC curves were analyzed. The results showed that the EfficientNet B7 architecture outperformed ResNet50 in precision, sensitivity, and specificity, especially in classifying early stages of Alzheimer's disease. EfficientNet B7 demonstrated greater generalization ability, achieving high precision with preprocessed and new images, while ResNet50 showed limitations when working with heterogeneous data. This highlights the importance of modern architectures in solving complex problems like early Alzheimer’s detection, although it also evidences that relying solely on controlled datasets like OASIS and ADNI may limit applicability in real clinical scenarios.
  • No Thumbnail Available
    Item
    Influencia del procesamiento de semillas de diferentes variedades de Chenopodium quinoa en su perfil nutraceútico y metabólico
    (Universidad Técnica de Ambato. Facultad de Ciencia e Ingeniería en Alimentos y Biotecnología. Carrera de Biotecnología, 2022-09) Carrillo Hidalgo, Doménica Carolina; Lalaleo Córdova, Liliana Paulina
    The purpose of this research consisted of the NMR metabolomics analysis performed with three quinoa cultivars with 5 treatments including the control. The results obtained by Lalaleo et al., (2020) in the project Differentiating, evaluating, and classifying three quinoa ecotypes by washing, cooking and germination treatments, using proton nuclear magnetic resonance-based metabolomic approach, were the basis for the development of this study. The raw data obtained were values resulting from the integration of the spectrum peaks of each sample analyzed and data from the correct grouping of each ecotype. The exploratory analysis of data groups from different quinoa cultivars allowed us to identify the normally distributed metabolites in the control group and in those that received some type of treatment. Discrimination between the type of seed processing and cultivar was performed using Random Forest. When the variety was analyzed as an important variable, it was determined that amino acids and certain nutrients are the most relevant to evaluate the accuracy of the model. Finally, the nutraceutical contribution of each variety and treatment was evaluated, based on the categorization. In the amino acids, it was identified that the germination treatment (G) has greater metabolic activity in the three varieties. In organic acids, formic and pyruvic acid show the greatest direct correlation in Ck and WCk. In carbohydrates, treatment G with the highest direct correlation exhibited galactose. The treatment (G) with the highest direct correlation in all its varieties with several metabolites in the other nutrients group.