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.
- Jones Matrix Characterization of Homogeneous Optical Elements via Evolutionary Algorithms(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2021-06-15) De Luna Pámanes, Alejandra; COVANTES OSUNA, EDGAR; 352304; Covantes Osuna, Edgar; tolmquevedo/mscuervo; Amaya Contreras, Iván Mauricio; Ortiz Bayliss, José Carlos; Serrano García, David Ignacio; School of Engineering and Sciences; Campus Monterrey; López Mago, DoriliánJones calculus provides a robust and straightforward method to describe polarized light and polarizing optical systems using two-element vectors (Jones vectors) and 2 X 2 matrices (Jones matrices). Jones matrices are used to determine the retardance and diattenuation introduced by an optical element or a sequence of elements. Moreover, they are the tool of choice to study optical geometric phases, the polarization-dependent phase of the total delay of a light beam acquired when passing through a material. Jones matrix characterization is a technique used to characterize polarizing optical systems. By measuring the geometric phase, Jones matrix characterization can identify the sample's eigenpolarizations, which are those polarization states that exits the sample only scaled by a phase factor. Currently, there is only one existing Jones matrix characterization method available. However, said method is inefficient, since the characterization of any given element is time-consuming given that the method is based on a general sampling strategy. Optimization techniques are used to find a solution to a problem specified by an objective function, where the variables are searched over to find the combination that results in the best objective function value while satisfying the constraints of the problem. Evolutionary Algorithms (EAs) are optimization techniques based on the theory of evolution, which explains the adaptive changes of species in nature through the survival of the fittest, heredity, and mutation. They are all random-based meta-heuristic algorithms that do not require gradient information and typically make use of several points in the search space at a time. Therefore, using the exploration capabilities of EAs, in this study, we present an initial approach for solving the problem of finding the eigenvectors that characterize the Jones matrix of a homogeneous optical element through EAs. We evaluate the analytical performance of an EA with a polynomial mutation (PM) operator and a Genetic Algorithm (GA) with a simulated binary crossover operator and a PM operator, and compare the results with those obtained through a general sampling method. The results show that both the EA and the GA out-performed a general sampling method of 6,000 measurements, by requiring in average 103 and 188 fitness functions measurements respectively, while having a perfect rate of convergence. The present analysis shows that the usage of EAs in the area of optics is a promising research area and as future research, we would like to apply EAs on the more complex case of inhomogeneous optical elements, for which no method of characterization currently exists.
- An indicator-based evolutionary algorithm for the numerical treatment of equality constrained multi-objective optimisation problems(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2020-07-01) Llano García, Jesús Leopoldo; LLANO GARCIA, JESUS LEOPOLDO; 829049; Monroy, Raúl; lagdtorre; Coello Coello, Carlos A.; Amaya Contreras, Ivan Mauricio; Ortiz Bayliss, José Carlos; School of Engineering and Sciences; Campus Estado de México; Sosa Hernández, Víctor AdriánIn many applications, especially those of the real world, we find problems that require for several conflicting objectives to be optimised simultaneously; moreover, these problems may require the consideration of limitations that restrict the space of decisions. These problems arise in the scope of Constrained Optimisation that needs for optimal solutions to follow a set of equality and inequality constraints to be considered valid. While Evolutionary approaches have proven themselves a useful tool for tackling Multi-objective Optimisation Problems (MOPs), they are incapable of accurately approximate the solution when considering Equality Constraints as part of the problem. At the same time, many state-of-the- art algorithms try to incorporate ways to handle Equality Constrained MOPs (ECMOPs) little to none, take into consideration the usage of performance indicators as means for solving this kind of problems. Here, we designed and implemented an EMOA for tackling Equality Constrained MOPs (EC- MOPs). Using a performance indicator as a density estimator, based on an artificially con- structed Reference set that closely resembles the feasible area of a particular ECMOP, the algorithm was able to find Pareto-optimal solutions that both lie within the feasible region and improve the quality of the final approximation. We make an empirical study of our proposed algorithm, testing its capabilities over a set of benchmarking functions composed of bi and three-objective optimisation problems, each with one equality constraint. To give validity to this project, we compare the obtained results against those obtained by two state-of-the-art algorithms. To quantify and compare the performance of each algorithm, we calculated the average Hausdorff distance (∆p) using the actual Pareto front of the benchmark problems, and calculated the ratio of feasible solutions within the final population. The obtained results over the problem set demonstrate that it is possible to approximate the Pareto front of a given ECMOP using only an evolutionary algorithm. We obtain this candidate solution by approximating the shape of the front using an artificially constructed set, which takes into account the information of the constraints to modify the shape. This whole process required no gradient information, preserving the advantages of applying an evolutionary approach to the problems.
- The Use of Evolutionary Algorithms for the Design of Lithium-Ion Battery Packs and Battery Cells(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2013-12-05) Rodríguez Montoya, César Alejandro; Sosa Hernández, Víctor Adrián; emimmayorquin; School of Engineering and Sciences; Campus Estado de MéxicoIn the contemporary landscape, the prevailing shift towards the adoption of electric vehicles for personal transportation has propelled lithium batteries into the spotlight. Consequently, the demand for better-optimized batteries has surged, driven by the aspiration for enhanced performance without compromising cost-effectiveness or longevity. This research delves into the use of evolutionary algorithms in the pursuit of lithium battery optimization. To address this multifaceted challenge, we have formulated the battery design problem as a constrained many-objective optimization problem (CMaOP). Within this context, our set of objective functions encompasses critical battery attributes: the maximization of specific energy, and durability; and the minimization of heat generation, and price. The decision variables encapsulate various physical characteristics of the battery that can be fine-tuned during the manufacturing process. These variables include the choice of materials for the positive electrode, dimensions of individual layers, and geometric characteristics of the battery canister, among others. The investigation is conducted with a specific focus on three distinct applications: electric vehicles, drones, and cell phones. The requirements of these applications establish the constraints of the problem. To tackle this problem, we have extended and adapted the Island-based Multi-Indicator Algorithm (IMIA) framework yielding into the Island-based Multi-Indicator Constraint-handler Algorithm (IMICA). The algorithm relies on the cooperative work of various quality indicators to favor the generation of optimized solutions while meeting the concepts of coverage and distribution in the Pareto front approximation. The algorithm was able to solve the problem efficiently. When compared with the Non-dominated Sorting Genetic Algorithm-III (NSGA-III), the algorithm managed to find a greater number of non-dominated feasible solutions and a greater hypervolume. Furthermore, the solutions found by the algorithm also prove to be competitive against standardized batteries.