Martinez-Villaseñor, Lourdes
Main Affiliation
Preferred name
Martinez-Villaseñor, Lourdes
Official Name
Martínez Villaseñor, María de Lourdes
ORCID
0000-0002-9038-7821
Researcher ID
N-7607-2018
Scopus Author ID
55521085100
95 results
Now showing 1 - 10 of 95
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Data-Driven Innovation for Intelligent Technology : Perspectives and Applications in ICT(Springer Cham, 2024); ; ; ; This book focuses on new perspectives and applications of data-driven innovation technologies, applied artificial intelligence, applied machine learning and deep learning, data science, and topics related to transforming data into value. It includes theory and use cases to help readers understand the basics of data-driven innovation and to highlight the applicability of the technologies. It emphasizes how the data lifecycle is applied in current technologies in different business domains and industries, such as advanced materials, healthcare and medicine, resource optimization, control and automation, among others. This book is useful for anyone interested in data-driven innovation for smart technologies, as well as those curious in implementing cutting-edge technologies to solve impactful artificial intelligence, data science, and related information technology and communication problems. ©Springer. ©The authors. ©The editors28 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, 17 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Towards an ontology for ubiquitous user modeling interoperability(2012); González-Mendoza, MiguelIn order to obtain a broader understanding of the user, some researchers in the community of user modeling envision the need to share information of user models between applications. But gathering distributed user information from heterogeneous sources to obtain user models interoperability implies handling syntactic and semantic heterogeneity. It is also important to provide means for a ubiquitous user model to evolve over time. We present U2MIO a dynamic ontology with flexible structure for user modeling interoperability based in SKOS ontology. The U2MIO provides mediation based user modeling for sharing and reusing information from heterogeneous user models. A two-tier matching strategy is proposed for the process of concept alignment that permits the interoperability between profile suppliers and consumers.1 47 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Special Issue on Interdisciplinary Artificial Intelligence: Methods and Applications of Nature-Inspired Computing(2022); Inspiration in nature has been widely explored, from the macro to micro-scale. From a scientific perspective, these methods inspired by nature have proven to be efficient tools for tackling real-world problems because most of the latter are highly complex or the resources are limited to analyze them. This inspiration is justified by the fact that natural phenomena mainly emphasize adaptability, optimization, robustness, and organization, among other properties, to deal with complexity. In that sense, three methodologies are commonly considered: human-designed problem-solving techniques inspired by nature, the synthesis of natural phenomena to develop algorithms, and the use of nature-inspired materials to perform computations. Some applications of nature-inspired computing include data mining, machine learning, optimization, robotics, engineering control systems, human–machine interaction, healthcare, the Internet of Things, cloud computing, smart cities, and many others.|| This Special Issue aimed to cover original research works with emphasis on the methodologies and applications of nature-inspired computing to handle the above-mentioned complex systems. We received a total of 38 submitted papers, and 18 papers were accepted (covering 47% of acceptance rate).|| The Special Issue presents different works related to metaheuristic optimization methods and their applications of human brain inspiration and neural networks, natural language processing-based applications, and fuzzy-logic-based applications. ©2022 Applied Sciences, MDPI.1 6 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, An Intelligent Human Fall Detection System Using a Vision-Based StrategyElderly people is increasing dramatically during the current years, and it is expected that this population reaches 2.1 billion of individuals by 2050. In this regard, new care strategies are required. Assisted living technologies have proposed alternatives to support professional caregivers and families to take care of elderly people, such as in risk of falls. Currently, fall detection systems are able to alleviate the latter problem and reduce the time a person who suffered a fall receives assistance. Thus, this paper proposes a fall detection system based on image processing strategy to extract motion features through an optical flow method. For classification, we use these features as inputs to a convolutional neural network. We applied our approach in a dataset comprises video recordings of one subject performing different types of falls. In experimental results, our approach showed 92% accuracy on the dataset used. © 2019 IEEE.1 29Scopus© Citations 9 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Orientación a padres para aprender a utilizar Internet como medio educativo(2006); Villalobos Torres, Elvia MarveyaSi se pretende hacer un buen uso de la Internet logrando que este medio sirva realmente al perfeccionamiento de las personas y por ende al mejoramiento de las familias y de la sociedad, es preciso reflexionar en torno a los nuevos retos educativos que este medio conlleva. Con respecto a las bondades de Internet se debe aprender cómo identificar información valiosa en un espacio en donde el exceso de fuentes, no todas confiables, puede llevar a la desinformación o pérdida de tiempo y esfuerzo en búsquedas inútiles. Por otro lado, es imperioso diseñar estrategias personalizadas para combatir las influencias negativas de la red y minimizar los riesgos sobre todo en los cibernautas más jóvenes permitiéndoles usar Internet asegurando su integridad física, mental y moral. Algunos padres y educadores tienen una sensación de aislamiento con respecto a las actividades que realizan los niños, adolescentes y jóvenes en la red dada la brecha digital que va creciendo entre los "enchufados" y los "desenchufados". Esta ignorancia del mundo digital en el que sus hijos y alumnos viven, virtualmente hablando, y la comunidad global con la que conviven, acarrea problemas para la familia que si no se atienden pueden terminar deteriorando las relaciones familiares, acabando con la comunicación en la familia y tirando literalmente por la "borda digital" toda la labor educativa de años. Con la finalidad de enfrentar los retos de la era de la digitalización se debe estudiar primeramente Internet para identificar las oportunidades y amenazas de este medio revolucionario con respecto a la familia9 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, A Reinforcement Learning Method for Continuous Domains Using Artificial Hydrocarbon Networks(2018); 1 16Scopus© Citations 4 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Contrastive Steering Vectors for Autoencoder ExplainabilityGenerative models, particularly autoencoders, often function as black boxes, making it challenging for non-expert users to effectively control the generation process and understand how inputs affect outputs. Existing methods for improving interpretability and control frequently require specific model training regimes or labeled data, limiting their applicability. This work introduces a novel approach to enhance the controllability and explainability of generative models, specifically tested on autoencoders with entangled latent spaces. We propose using a semi-supervised contrastive learning setup to learn steering vectors. These vectors, when added to an input’s latent representation, effectively manipulate specific attributes in the generated output without conditional training of the model or attribute classifiers, thus being applicable to pretrained models and avoiding compound classification errors. Furthermore, we leverage these learned steering vectors to interpret and explain the decoding process of a target attribute, allowing for efficient exploration of feature dimension interactions and the construction of an interpretable plot of the generative process, while lowering scalability limitations of perturbation-based Explainable AI (XAI) methods by reducing the search space. Our method provides an efficient pathway to controllable generation, offers an interpretable result of the model’s internal mechanisms, and relates the interpretations to human-understandable explanation questions. ©The authors ©MDPI AG ©Electronics.14 1 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Sensor Location Analysis and Minimal Deployment for Fall Detection System(2020); ; Nuñez-Martinez, JoséHuman falls are considered as an important health problem worldwide. Fall detection systems can alert when a fall occurs reducing the time in which a person obtains medical attention. In this regard, there are different approaches to design fall detection systems, such as wearable sensors, ambient sensors, vision devices, and more recently multimodal approaches. However, these systems depend on the types of devices selected for data acquisition, the location in which these devices are placed, and how fall detection is done. Previously, we have created a multimodal dataset namely UP-Fall Detection and we developed a fall detection system. But the latter cannot be applied on realistic conditions due to a lack of proper selection of minimal sensors. In this work, we propose a methodological analysis to determine the minimal number of sensors required for developing an accurate fall detection system, using the UP-Fall Detection dataset. Specifically, we analyze five wearable sensors and two camera viewpoints separately. After that, we combine them in a feature level to evaluate and select the most suitable single or combined sources of information. From this analysis we found that a wearable sensor at the waist and a lateral viewpoint from a camera exhibits 98.72% of accuracy (intra-subject). At the end, we present a case study on the usage of the analysis results to deploy a minimal-sensor based fall detection system which finally reports 87.56% of accuracy (inter-subject).2 17Scopus© Citations 24