Martinez-Villaseñor, Lourdes
Thumbnail Image
Preferred name
Martinez-Villaseñor, Lourdes
Official Name
Martínez Villaseñor, María de Lourdes
Alternative Name
lmartine
Main Affiliation
ORCID
Scopus Author ID
55521085100
Researcher ID
N-7607-2018

Research Output
Now showing 1 - 10 of 30
No Thumbnail Available
Publication

Explainable artificial hydrocarbon networks classifier applied to preeclampsia

2024 , Ponce, Hiram , Martinez-Villaseñor, Lourdes , Martínez Velasco, Antonieta Teodora

Explainability is crucial in domains where system decisions have significant implications for human trust in black-box models. Lack of understanding regarding how these decisions are made hinders the adoption of so-called clinical decision support systems. While neural networks and deep learning methods exhibit impressive performance, they remain less explainable than white-box approaches. Artificial Hydrocarbon Networks (AHN) is an effective black-box model that can be used to support critical clinical decisions if accompanied by explainability mechanisms to instill confidence among clinicians. In this paper, we present a use case involving global and local explanations for AHN models, provided with an automatic procedure so-called eXplainable Artificial Hydrocarbon Networks (XAHN). We apply XAHN to preeclampsia prognosis, enabling interpretability within an accurate black-box model. Our approach involves training a suitable AHN model using the cross-validation with ten repetitions, followed by a comparative analysis against four well-known machine learning techniques. Notably, the AHN model outperformed the others, achieving an F1-score of 74.91%. Additionally, we assess the efficacy of our XAHN explainer through a survey applied to clinicians, evaluating the goodness and satisfaction of the provided explanations. To the best of our knowledge, this work represents one of the earliest attempts to address the explainability challenge in preeclampsia prediction.© 2024 The Author(s). Published by Elsevier Inc.

View
No Thumbnail Available
Publication

A 2020 perspective on “A novel methodology for optimizing display advertising campaigns using genetic algorithms”

2020 , Miralles-Pechuán, Luis , Ponce, Hiram , Martinez-Villaseñor, Lourdes

Online advertising has become the most important area of publicity. From a post-2020 perspective, we identify three trends in online advertising comprising: the rapid evolution of online advertising mainly over mobile networks, how to cope with big companies leading digital marketing, and the exploration of new methods to handle the dynamics of the e-commerce ecosystem. We proposed a new methodology for online advertising in small ad networks using supervised machine learning and metaheuristic methods. Our research will be beneficial for addressing the above-mentioned trends in online advertising focusing on small ad networks. It contributes to the establishment of an information system technology and practice within the scope of the development of marketing business strategies in e-commerce. Currently, we are exploring how to improve the flexibility of our approach to make it easier to adapt to new ad campaigns, analyzing and comparing different computational methods, and how to increase the performance of presenting custom ads to users when dealing with small data sets. Online advertising in small ad networks will be very useful in the following years. Hence, there are still many challenges to be dealt with in order to implement it in the business strategies of the new digital marketing. © 2020 Elsevier B.V.

View
No Thumbnail Available
Publication

Assessment of CFH and HTRA1 polymorphisms in age-related macular degeneration using classic and machine-learning approaches

2020 , Martínez Velasco, Antonieta Teodora , Pérez Ortiz, Andric Christopher , Antonio-Aguirre, Bani , Martinez-Villaseñor, Lourdes , Palacio-Pastrana, Claudia , Lira, Esmeralda , Zenteno, Juan Carlos , Ramírez-Sánchez, Israel , Zepeda-Palacio, Claudia , Mendoza Vera, Cristina Azucena , Camacho-Ordóñez, Azyadeh , Ortiz Bibriesca, Daniela , Estrada Mena, Francisco Javier

CFH: and HTRA1 are pivotal genes driving increased risk for age-related macular degeneration (AMD) among several populations. Here, we performed a hospital-based case-control study to evaluate the effects of three single nucleotide polymorphisms (SNPs) among Hispanics from Mexico. Materials and methods: 122 cases and 249 controls were genotyped using Taqman probes. Experienced ophthalmologists diagnosed AMD following the American Association of Ophthalmology guidelines. We studied CFH (rs1329428, rs203687) and HTRA1 (rs11200638) SNPs thoroughly by logistic regression models (assuming different modes of inheritance) and machine learning-based methods (ML). HTRA1: rs11200638 is the most significant polymorphism associated with AMD in our studied population. In a multivariate regression model adjusted for clinically and statistically meaningful covariates, the A/G and A/A genotypes increased the odds of disease by a factor of 2.32 and 7.81, respectively (P < .05) suggesting a multiplicative effect of the polymorphic A allele. Furthermore, this observation remains statistically meaningful in the allelic, dominant, and recessive models, and ML algorithms. When stratifying by phenotype, this polymorphism was significantly associated with increased odds for geographic atrophy (GA) in a recessive mode of inheritance (12.4, p < .05). Conclusions: In sum, this work supports a strong association between HTRA1 genetic variants and AMD in Hispanics from Mexico, especially with GA. Moreover, ML was able to replicate the results of conventional biostatistics methods unbiasedly. © 2020 Taylor & Francis Group, LLC.

View
No Thumbnail Available
Publication

An enhanced process of concept alignment for dealing with overweight and obesity

2013 , Martinez-Villaseñor, Lourdes , González-Mendoza, Miguel

A major challenge for creating personalized diet and activity applications is to capture static, semi-static and dynamic information about a person in a user-friendly way. Sharing and reusing information between heterogeneous sources like social networking applications, personal health records, specialized applications for diet and exercise monitoring, and personal devices with attached sensors can achieve a better understanding of the user. Gathering distributed user information from heterogeneous sources and making sense of it to enable user model interoperability entails handling the semantic heterogeneity of the user models. In this paper, we enhance the process of concept alignment to automatically determine semantic mapping relations to enable interoperability between heterogeneous health and fitting applications. We add an internal structure similarity measure to increase the quality of generated mappings of our previous work. We show that the addition of an internal structure analysis of source data in the process of concept alignment improves the efficiency and effectiveness of measuring results. Constrain and data type verification done in the internal structure analysis proved to be useful when dealing with common conflicts between concepts.

View
No Thumbnail Available
Publication

Distributed evolutionary learning control for mobile robot navigation based on virtual and physical agents

2020 , Ponce, Hiram , Moya-Albor, Ernesto , Martinez-Villaseñor, Lourdes , Brieva, Jorge

This paper presents a distributed evolutionary learning control based on social wound treatment for mobile robot navigation using an integrated multi-robot system comprised of simulated and physical robots. To do so, this work proposes an extension of the population-based metaheuristic wound treatment optimization (WTO) method into a distributed scheme. In addition, this distributed WTO method is implemented on the multi-robot system allowing them to experience the environment in their own and communicate their findings, resulting in an emergence intelligence. We implemented our proposal using the combination of five simulated robots with one physical robot for tuning a navigation controller to move freely in a workspace. Results showed that the solution found by this multi-robot system aims using the output controller in the physical robot for successfully achieving the goal to move the robot around a U-maze, without applying any transfer learning approach. We consider this proposal useful in evolutionary robotics, and of great importance to decrease the gap related to transfer knowledge in robotics from simulation to reality. © 2019 Elsevier B.V.

View
No Thumbnail Available
Publication

Consumer Acceptance of an SMS-Assisted Smoking Cessation Intervention: A Multicountry Study

2013 , Martinez-Villaseñor, Lourdes , González-Mendoza, Miguel

A major challenge for creating personalized diet and activity applications is to capture static, semi-static and dynamic information about a person in a user-friendly way. Sharing and reusing information between heterogeneous sources like social networking applications, personal health records, specialized applications for diet and exercise monitoring, and personal devices with attached sensors can achieve a better understanding of the user. But gathering distributed user information from heterogeneous sources and making sense of it to enable user model interoperability entails handling the semantic heterogeneity of the user models. In this paper we describe a flexible user modeling ontology to provide representation for a ubiquitous user model and a process of concept alignment for interoperability between heterogeneous sources to address the lack of interoperability between profile suppliers and consumers. We provide an example of how information of different profile suppliers can be used to enrich fitness applications and personalize web services.

View
No Thumbnail Available
Publication

Advances in Computational Intelligence : Preface

2020 , Ponce, Hiram , Martinez-Villaseñor, Lourdes

The Mexican International Conference on Artificial Intelligence (MICAI) is a yearly international conference series that has been organized by the Mexican Society of Artificial Intelligence (SMIA) since 2000. MICAI is a major international artificial intelligence forum and the main event in the academic life of the country’s growing artificial intelligence community. MICAI conferences publish high-quality papers in all areas of artificial intelligence and its applications. The proceedings of the previous MICAI events have been published by Springer in its Lecture Notes in Artificial Intelligence series, vol. 1793, 2313, 2972, 3789, 4293, 4827, 5317, 5845, 6437, 6438, 7094, 7095, 7629, 7630, 8265, 8266, 8856, 8857, 9413, 9414, 10061, 10062, 10632, and 10633. Since its foundation in 2000, the conference has been growing in popularity and improving in quality. ©2018 Springer Verlag.

View
No Thumbnail Available
Publication

Design of a Soft Gripper Using Genetic Algorithms

2021 , Ponce, Hiram , Martinez-Villaseñor, Lourdes , Mayorga-Acosta, Carlos

In this paper, we present an artificial intelligence-assisted design of a soft robotic gripper. First, we formulate the design of the soft gripper as an optimization problem. Then, we design and configure a genetic algorithm (GA) method to solve the problem under design constraints. Lastly, we implement the whole system in co-simulation between the GA and a computer-aided design software that evaluates the candidate solutions using finite element analysis. A network-attached storage server connecting multiple nodes runs the GA method in parallel, to accelerate the process. After experimentation, we present simulation results to validate our approach. © 2021 Instituto Politécnico Nacional. All rights reserved.

View
No Thumbnail Available
Publication

Special issue on Mexican International Conference on Artificial Intelligence, MICAI 2014 and 2015

2017 , Ponce, Hiram , González-Mendoza, Miguel , Martinez-Villaseñor, Lourdes

This special issue of the journal Soft Computing offers extended versions of some of the best-awarded, high-reviewed and invited papers presented on the 13th Mexican International Conference on Artificial Intelligence, MICAI 2014, held in Tuxtla Gutiérrez, Chiapas, Mexico, on November 16–22, 2014, under the organization of the Mexican Society for Artificial Intelligence (SMIA) in cooperation with the Instituto Tecnológico de Tuxtla Gutiérrez and Universidad Autónoma de Chiapas, and on the 14th Mexican International Conference on Artificial Intelligence, MICAI 2015, held in Cuernavaca, Morelos, Mexico, on October 25–31, 2015, under the organization of the SMIA in cooperation with the Instituto de Investigaciones Eléctricas. ©2017 Soft Computing, Springer Verlag.

View
No Thumbnail Available
Publication

A concise review on sensor signal acquisition and transformation applied to human activity recognition and human–robot interaction

2019 , Martinez-Villaseñor, Lourdes , Ponce, Hiram

Human activitiy recognition deals with the integration of sensing and reasoning aiming to understand better people’s actions. Moreover, it plays an important role in human interaction, human–robot interaction, and brain–computer interaction. When these approaches have to be developed, different efforts from signal processing and artificial intelligence are considered. In that sense, this article aims to present a concise review of signal processing in human activitiy recognition systems and describe two examples and applications both in human activity recognition and robotics: human–robot interaction and socialization, and imitation learning in robotics. In addition, it presents ideas and trends in the context of human activity recognition for human–robot interaction that are important when processing signals within that systems. ©2019 SAGE Publications Ltd, The Author(s).

View