Now showing 1 - 10 of 75
No Thumbnail Available
Publication

Ethical Design Framework for Artificial Intelligence Healthcare Technologies

2024-01-01 , Martinez-Villaseñor, Lourdes , Ponce, Hiram

The healthcare industry has undergone a profound transformation with the integration of artificial intelligence(AI) and emerging technologies, leading in a new era of personalized treatments and healthcare solutions. However, this technological advancement has not been without its ethical and practical challenges, which have hindered the real-world application of intelligent systems in clinical settings. Numerous international entities have published principles, guidelines, and regulations to tackle these issues, yet a significant gap persists between theoretical initiatives and the practical incorporation of ethical design in intelligent systems. Within this study, we delineate the substantial transformation taking place in the healthcare landscape due to artificial intelligence. We provide a condensed overview of the opportunities and challenges that accompany this disruptive shift. The main goal of this work is introducing an ethical design framework tailored to healthcare technologies and delineating the ethical design process for a machine learning-based support tool designed for Age-related Macular Degeneration risk assessment. To the best of our knowledge, this work represents one of the few documented instances of the practical implementation of ethical design principles in intelligent healthcare systems. © 2024 Springer Nature

No Thumbnail Available
Publication

Editorial: Artificial intelligence in brain-computer interfaces and neuroimaging for neuromodulation and neurofeedback

2022 , Ponce, Hiram , Yinong, Chen , Martinez-Villaseñor, Lourdes

Neuromodulation and neurofeedback are two alternative non-pharmacological ways of treating neurological related diseases and disorders (Grazzi et al., 2021; Hamed et al., 2022). Neuromodulation refers to as the modulation of brain function via the application of weak direct current (Lewis et al., 2016). Neurofeedback is a psychophysiological procedure that provides models of neural activity to subjects aiming to control them online (Marzbani et al., 2016). Both alternatives have been successfully applied in a variety of neurological conditions including Parkinson's disease, chronic pain, epilepsy, depression, essential tremor, among many others (Tsatali et al., 2019; Baptista et al., 2020; Hamed et al., 2022). Typical challenges in these types of treatment are related to the way of collecting data, the improvement in the efficiency of the methods, the interpretability of feedback signals, to name a few (Johnson et al., 2013; Lewis et al., 2016; Marzbani et al., 2016; Papo, 2019). © 2023 Frontiers Media S.A. All rights reserved

No Thumbnail Available
Publication

Design and Analysis for Fall Detection System Simplification

2020 , Martinez-Villaseñor, Lourdes , Ponce, Hiram

This paper presents a methodology based on multimodal sensors to configure a simple, comfortable and fast fall detection and human activity recognition system that can be easily implemented and adopted. The methodology is based on the configuration of specific types of sensors, machine-learning methods and procedures. The protocol is divided into four phases: (1) database creation (2) data analysis (3) system simplification and (4) evaluation. Using this methodology, we created a multimodal database for fall detection and human activity recognition, namely UP-Fall Detection. It comprises data samples from 17 subjects that perform 5 types of falls and 6 different simple activities, during 3 trials. All information was gathered using 5 wearable sensors (tri-axis accelerometer, gyroscope and light intensity), 1 electroencephalograph helmet, 6 infrared sensors as ambient sensors, and 2 cameras in lateral and front viewpoints. The proposed novel methodology adds some important stages to perform a deep analysis of the following design issues in order to simplify a fall detection system: a) select which sensors or combination of sensors are to be used in a simple fall detection system, b) determine the best placement of the sources of information, and c) select the most suitable machine learning classification method for fall and human activity detection and recognition. Even though some multimodal approaches reported in literature only focus on one or two of the above-mentioned issues, our methodology allows simultaneously solving these three design problems related to a human fall and activity detection and recognition system. ©2020 Journal of visualized experiments : NLM (Medline)

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.

No Thumbnail Available
Publication

Enrichment of Learner Profile with Ubiquitous User Model Interoperability

2014 , Martinez-Villaseñor, Lourdes , González-Mendoza, Miguel , Danvila Del Valle, Ignacio

Nowadays, there is a constant need of acquiring new knowledge and skills to keep up with the demands of changing environment. The design and development of training and educational systems that enable effective personalized learning help obtaining changing skills and fill competence gaps. The computational effort to create a user model that represents user’s knowledge, characteristics, interests, goals, background and preferences is repeatedly done by many systems and applications in several domains. Each system ends up with a partial view of the user. Researchers in user modeling foresee the need of sharing and reusing user model information in order to obtain a better understanding of the user and be able to provide personalized and proactive services. In this paper we present an application scenario of sharing and reusing information scattered in most commonly used applications to enhance learner profiles. ©Instituto Politécnico Nacional

No Thumbnail Available
Publication

Approaching Fall Classification Using the UP-Fall Detection Dataset: Analysis and Results from an International Competition

2020 , Ponce, Hiram , Martinez-Villaseñor, Lourdes

This chapter presents the results of the Challenge UP – Multimodal Fall Detection competition that was held during the 2019 International Joint Conference on Neural Networks (IJCNN 2019). This competition lies on the fall classification problem, and it aims to classify eleven human activities (i.e. five types of falls and six simple daily activities) using the joint information from different wearables, ambient sensors and video recordings, stored in a given dataset. After five months of competition, three winners and one honorific mention were awarded during the conference event. The machine learning model from the first place scored$$82.47\%$$ in$$F:1$$-score, outperforming the baseline of$$70.44\%$$. After analyzing the implementations from the participants, we summarized the insights and trends of fall classification. © 2020, Springer Nature Switzerland AG.

No Thumbnail Available
Publication

A novel methodology for optimizing display advertising campaigns using genetic algorithms

2018 , Miralles-Pechuán, Luis , Ponce, Hiram , Martinez-Villaseñor, Lourdes

Online advertising campaigns have attracted the attention of many advertisers willing to promote their business on the Internet. One of the main problems faced by advertisers, especially by those who have little experience in Internet advertising, is configuring their campaigns in an efficient way. To configure a campaign properly it is required to select the appropriate target, so it is guaranteed a high acceptance of users to adverts. It is also required that the number of visits that satisfy the configuration requirements is high enough to cover the advertisers’ campaigns. Thus, this paper presents a novel methodology for optimizing the micro-targeting technique in direct response display advertising campaigns by using genetic algorithms as the basis optimization model and a machine-learning based click-through rate (CTR) model. We implement our methodology to optimize display advertising campaigns on mobile devices using a real dataset. Results show that our methodology is feasible to optimize the campaigns by selecting the set of the best features required. Also, customization of the advertising campaign selecting some features by an advertiser, e.g. applying micro-targeting, can be optimized efficiently. © 2017 Elsevier B.V.

No Thumbnail Available
Publication

Sensor Location Analysis and Minimal Deployment for Fall Detection System

2020 , Ponce, Hiram , Martinez-Villaseñor, Lourdes , Nuñez-Martinez, José

Human 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).

No Thumbnail Available
Publication

The Language of Nature and Artificial Intelligence in Patient Care

2023 , Enríquez, Teresa , Alonso-Stuyck, Paloma , Martinez-Villaseñor, Lourdes

Given the development of artificial intelligence (AI) and the conditions of vulnerability of large sectors of the population, the question emerges: what are the ethical limits of technologies in patient care? This paper examines this question in the light of the "language of nature" and of Aristotelian causal analysis, in particular the concept of means and ends. Thus, it is possible to point out the root of the distinction between the identity of the person and the entity of any technology. Nature indicates that the person is always an end in itself. Technology, on the contrary, should only be a means to serve the person. The diversity of their respective natures also explains why their respective agencies enjoy diverse scopes. Technological operations (artificial agency, artificial intelligence) find their meaning in the results obtained through them (poiesis). Moreover, the person is capable of actions whose purpose is precisely the action itself (praxis), in which personal agency and, ultimately, the person themselves, is irreplaceable. Forgetting the distinction between what, by nature, is an end and what can only be a means is equivalent to losing sight of the instrumental nature of AI and, therefore, its specific meaning: the greatest good of the patient. It is concluded that the language of nature serves as a filter that supports the effective subordination of the use of AI to its specific purpose, the human good. The greatest contribution of this work is to draw attention to the nature of the person and technology, and about their respective agencies. In other words: listening to the language of nature, and attending to the diverse nature of the person and technology, personal agency, and artificial agency.

No Thumbnail Available
Publication

Fuzzy aggregation of similarity values for electronic health record interoperability

2019 , Martinez-Villaseñor, Lourdes , Ponce, Hiram , González-Mendoza, Miguel

Schema matching is used for data integration, mediation, and conversion between heterogeneous sources. Nevertheless, mappings identified with an automatic or semi-automatic process can never be completely certain. In a process of concept alignment, it is necessary to manage uncertainty. In this paper, we present a fuzzy-based process of concept alignment for uncertainty management in schema matching problem. The ultimate goal is to enable interoperability between different electronic health records. Data integration of health information is done through the mediation of our ubiquitous user model framework. Results look promising and fuzzy theory proved to be a good fit for modeling uncertain schema matching. Fuzzy combined similarities can handle uncertainty in the schema matching process to enable interoperability between electronic health records improving the quality of mappings and diminishing the human error to verify the mappings. © 2019 - IOS Press and the authors. All rights reserved