Ciencias Exactas y Ciencias de la Salud
Permanent URI for this collectionhttps://hdl.handle.net/11285/551039
Pertenecen a esta colección Tesis y Trabajos de grado de las Maestrías correspondientes a las Escuelas de Ingeniería y Ciencias así como a Medicina y Ciencias de la Salud.
Browse
Search Results
- Improving deep neural networks to identify depression using neural architecture search(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2025-06) Hernández Silva, Erick; Trejo Rodríguez, Luis Ángel; emipsanchez; Cantoral Ceballos, José Antonio; González Mendoza, Miguel; School of Engineering and Sciences; Campus Estado de México; Sosa Hernández, Víctor AdriánA Neural Architecture Search (NAS) framework utilizing Evolutionary Algorithms (EAs) and a regressor model is proposed to improve the classification performance of Deep Neural Net- works (DNNs) for the early detection of Major Depressive Disorder (MDD) from speech data represented by Mel-Spectrograms. The framework automates the design of neural network architectures by systematically exploring a well-defined search space that integrates convo- lutional layers, batch normalization, dropout, max pooling, and self-attention mechanisms, aiming to capture both spatial and temporal features inherent in vocal signals. By optimiz- ing for the F1-score, the framework addresses challenges related to data imbalance, ensuring robust generalization across both depressed and non-depressed samples. The proposed approach employs an integer-based encoding scheme to represent candi- date architectures, coupled with repair and validation processes that ensure all architectures meet specific design constraints. A self-adaptive mechanism dynamically adjusts the muta- tion factor based on evolutionary feedback, improving the balance between exploration and exploitation during the search process. Furthermore, a surrogate model, built using Princi- pal Component Analysis (PCA) and XGBoost regressor, predicts architecture performance, significantly reducing computational costs by avoiding full model training for all candidates. Experimental validation, conducted on publicly available speech datasets, demonstrates that NAS-generated architectures may outperform manually designed state-of-the-art models in terms of F1-score, accuracy, precision, recall, and specificity. The results confirm the effec- tiveness of integrating self-attention mechanisms with convolutional operations for extracting relevant depression-related vocal biomarkers. This research underlines the potential of NAS in advancing non-invasive, scalable, and interpretable AI-driven tools for mental health as- sessment, contributing to early intervention strategies and improving clinical outcomes in depression diagnosis.
- Contrast pattern-based classification on sentiment features for detecting people with mental disorders on social media(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2021-06-22) Gallegos Salazar, Leslie Marjorie; LOYOLA GONZALEZ, OCTAVIO; 553351; Loyola-González, Octavio; emipsanchez; School of Engineering and Science; Campus Estado de México; Medina-Pérez, Miguel AngelMental disorders are a global problem that widely affects different segments of the population. Mental disorders present consequences in the life of those suffering from them as they can have difficulties performing daily tasks normally. However, consequences in the economy, society, human rights, and cultural scope are also present as it is a problem that has been growing for a long time. Diagnosis and treatment are difficult to obtain as there are not enough specialists on the matter, and mental health is not yet a common topic among the population. Specialists in varied areas have proposed multiple solutions for the detection of the risk of depression; the computer science field has proposed some, based on language use and the data obtained through social media. Those solutions are mainly focused on objective features like n-grams and lexicons. We propose a contrast pattern-based classifier for detecting depression by using a new data representation based only on sentiment and emotion analysis extracted from post on social networks. The representation contains 28 different features which include information on sentiment, emotion, polarity, sarcasm, and other subjective information of the text. We then used a classifier that has not been used before in the state-of-the-art and obtained an AUC between 0.71 and 0.72. Finally we reproduced state-of-the-art models and statistically compared them with the result of the proposed model. The results show no significant statistical difference with a reproduction of the models found in the state-of-the-art. Furthermore, with the classifier used we were able to provide an explanation close to the language of an expert on the decision of the classifier.