CRIS

Permanent URI for this communityhttps://scripta.up.edu.mx/handle/20.500.12552/1

Browse

Search Results

Now showing 1 - 7 of 7

Some of the metrics are blocked by your
consent settings
Federated Learning Based on an Internet of Medical Things Framework for a Secure Brain Tumor Diagnostic System: A Capsule Networks Application
(MDPI AG, 2025)
;
Marmolejo-Saucedo, José Antonio
;
Köse, Utku
Artificial intelligence (AI) has already played a significant role in the healthcare sector, particularly in image-based medical diagnosis. Deep learning models have produced satisfactory and useful results for accurate decision-making. Among the various types of medical images, magnetic resonance imaging (MRI) is frequently utilized in deep learning applications to analyze detailed structures and organs in the body, using advanced intelligent software. However, challenges related to performance and data privacy often arise when using medical data from patients and healthcare institutions. To address these issues, new approaches have emerged, such as federated learning. This technique ensures the secure exchange of sensitive patient and institutional data. It enables machine learning or deep learning algorithms to establish a client–server relationship, whereby specific parameters are securely shared between models while maintaining the integrity of the learning tasks being executed. Federated learning has been successfully applied in medical settings, including diagnostic applications involving medical images such as MRI data. This research introduces an analytical intelligence system based on an Internet of Medical Things (IoMT) framework that employs federated learning to provide a safe and effective diagnostic solution for brain tumor identification. By utilizing specific brain MRI datasets, the model enables multiple local capsule networks (CapsNet) to achieve improved classification results. The average accuracy rate of the CapsNet model exceeds 97%. The precision rate indicates that the CapsNet model performs well in accurately predicting true classes. Additionally, the recall findings suggest that this model is effective in detecting the target classes of meningiomas, pituitary tumors, and gliomas. The integration of these components into an analytical intelligence system that supports the work of healthcare personnel is the main contribution of this work. Evaluations have shown that this approach is effective for diagnosing brain tumors while ensuring data privacy and security. Moreover, it represents a valuable tool for enhancing the efficiency of the medical diagnostic process. ©The authors ©MDPI.
Some of the metrics are blocked by your
consent settings
Improving a Biological Extracts Company’s Cash Cycle by Simulating Discrete Events: First Steps Towards Designing a Digital Twin
(Elsevier BV, 2025)
Jarquin-Segovia, Ricardo
;
Marmolejo-Saucedo, José Antonio
;
Companies with consistently positive cash cycles tend to outperform those with negative cycles, which struggle to cover operational and capital expenses. This study focuses on a Mexican company facing financial liquidity challenges due to a high investment in finished product inventory and an 80-day cash conversion cycle, with 73 days tied to inventory. Using discrete event simulation and digital modeling, the production process of fluid extract was analyzed to identify inefficiencies and propose improvements. The simulation, conducted with Anylogic software, revealed significant delays in the percolation operation, contributing to a 20-day production process and substantial work-in-process inventory. This work lays the foundation for implementing a digital twin to evaluate real-time financial impacts of operational changes, ultimately improving the company’s financial performance. ©The authors ©IFAC-PapersOnLine ©ScienceDirect ©Elsevier.
Some of the metrics are blocked by your
consent settings
Modeling responsible technologies using multiagent system for climate crisis and sustainability
(Elsevier, 2025)
Nanda, Pragyan
;
Sahoo, Sipra
;
;
Marmolejo-Saucedo, José Antonio
;
Behera, Itishree
This chapter delves into the dynamic landscape of responsible technologies and their crucial role in addressing the climate crisis and advancing sustainability. It highlights the need to understand the intricate connections between technology adoption, environmental impact, and societal behavior across various dimensions of sustainability, including environmental, social, economic, cultural, technological, political, ethical, health, educational, and adaptive aspects. The chapter introduces the concept of responsible technologies and their key principles, emphasizing real-world experimentation limitations and simulation advantages, particularly through a multiagent system (MAS). It explores different modeling approaches, focusing on the suitability of MAS for studying responsible technologies, along with considerations in its implementation. A step-by-step guide is provided for constructing a tailored MAS model for responsible technologies, incorporating real-world data and environmental factors. Findings and insights from MAS simulations are analyzed, shedding light on the implications of responsible technology adoption across these sustainability dimensions. The chapter also underscores the pivotal role of a MAS in comprehensively modeling responsible technologies and invites further research exploration in this expansive domain, serving as a comprehensive guide for researchers, policymakers, and stakeholders committed to leveraging responsible technologies for climate change mitigation and sustainability advancement. ©The authors ©Elsevier.
Some of the metrics are blocked by your
consent settings
Sales predictive analysis for improving supply chain drug sample
(Elsevier BV, 2025)
Téllez-Ballesteros, Susana Casy
;
Torres-Mendoza, Ricardo
;
Marmolejo-Saucedo, José Antonio
;
The delivery of drug samples allows increasing sales of pharmaceutical products [6]. However, we discovered some problems that can be improved in the supply chain that delivers drug samples (used for the treatment of excess glucose). Databases were integrated; then we apply data extraction and transformation; and finally we apply multiple regression analysis to explain drug sales. The first analysis evaluates the integration of regional data and the second analysis refers to data dis-aggregated by region. We identify the region with the greatest impact on sales and the impact of the delivery of drug samples in the Mexican market. ©The authors ©Elsevier ©Procedia Computer Science.
Some of the metrics are blocked by your
consent settings
A Greenfield Analysis for Supply Chains Enhanced with Agent-Based Simulation
(Springer, 2024-01-01)
García-Roa, Eduardo
;
Marmolejo-Saucedo, José Antonio
;
Martínez, Ana Paula
;
Elizarrarás, Fernando
This chapter presents a strategy to improve the greenfield analysis of a supply chain. The proposed strategy is based on a multiparadigm simulation model that uses discrete event simulation and agent-based simulation for vehicles used in freight transport. The modeling was carried out using Anylogic software, which is the only software that allows the integration of different simulation methods in the same project. A hypothetical case study was developed to implement the strategy. © 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
33 1
Some of the metrics are blocked by your
consent settings
Resilience in Supply Chains: A Strategy Based on Inventory Policies
(Springer, 2024-01-01)
Eyssautier-Alvarado, Rodrigo
;
Marmolejo-Saucedo, José Antonio
;
García-Roa, Eduardo
The resilience of supply chains is an increasingly important factor today. The effects of the COVID-19 pandemic have highlighted the importance of generating new strategies to reduce the risk of supply chain disruption. This paper proposes an inventory policy modeled in a simulation context. The case study is a hypothetical two-stage supply chain. The solution is given by the simulation of different scenarios where different data and policies are being taking into account to see different results and discard those policies that were not useful for this case study; all the simulations are made in anyLogistix software, which is a supply chain analytics software for designing and optimizing a supply chain. The results show the performance of the proposal in several disruption scenarios similar to those experienced in the COVID-19 pandemic. The solution proposal can serve as a reference in the functioning of supply chains in the post-COVID-19 era. ©Springer.
23 2
Some of the metrics are blocked by your
consent settings
Strategy, Power and CSR: Practices and Challenges in Organizational Management
(2020)
;
García Casas, Claudia María
;
;
;
Organizational management, along with strategy, is the most important part of business administration. Directors must know how to manage people, make decisions and, above all, have the ability to create strategies that help organizations achieve their objectives, greater strategic competitiveness, and above-average returns. In today’s global and complex environment, traditional views towards organizational management are not enough for businesses to thrive. It’s only by bringing together different approaches can management styles develop fast enough to keep pace with the ever-changing big picture. In this innovative new look at organizational management, expert authors Santiago García-Álvarez and Connie Atristain-Suárez explore how looking through lenses of philosophy, health, communication, law, engineering, pedagogy and policy can affect a modern organization’s prospects. Built through the collective and collaborative work of the research professors at the Universidad Panamericana, this work includes interdisciplinary approaches to real-world problems. For students and researchers of business and management, this is an unmissable read. ©2020 Emerald Publishing Limited.
Scopus© Citations 1 47 1

CRIS

Browse

Filters

Settings

Sort By

Results per page

Search Results