Repositorio Institucional de la Universidad ESAN
Not a member yet
581 research outputs found
Sort by
Social Effect, and Corporate Social Responsibility: An Analysis of the Oil Sector in an Emerging Market
No full textCorporate Social Responsibility (CSR) and social impact are two fundamental pillars of companies' strategy. However, the extent to which these two dimensions affect market performance remains understudied in emerging economies. To fill this gap, this paper examines the relationship between CSR and social impact in the oil industry in an emerging market (Peru). Using an adequate case study approach, together with financial data analysis, and the information provided by companies’ annual reports and CSR reports, our results show that the expected positive relationship varies depending on many diverse factors. Specifically, to achieve social impact, companies must prioritize community and environmental responsibility, as well as stakeholder engagement. Nevertheless, we found that businesses struggling with any of these aspects either completely or partially reject social impact. Our findings have some important ramifications for policymakers as well as managers in the oil sector. This issue is especially relevant in emerging economies like the Peruvian one since they are highly dependent on raw materials exports, which ultimately affects not only the environment but also the local communities. © 2024, AfricaGrowth Institute. All rights reserved
Machine Learning Predictive Model for Thyroid Disease Detection
No full textThe thyroid, a butterfly-shaped gland located in the neck, plays a crucial role in regulating metabolism, energy, and hormonal balance, meeting the peripheral tissues’ needs. Thyroid diseases pose a significant global health problem, affecting millions with varying degrees of severity. Conditions such as hyperthyroidism and hypothyroidism can manifest symptoms due to fluctuations in thyroid hormone levels, impacting individuals’ well-being. Additionally, thyroid disorders may involve the enlargement of the gland, known as goiter, or the formation of thyroid nodules, which can have functional or neoplastic implications. This article explores the development and implementation of a predictive model using advanced Machine Learning techniques to forecast thyroid diseases. By analyzing clinical and relevant biomedical data, we employ sophisticated Machine Learning algorithms to identify hidden patterns and correlations within the data. The goal is to enhance precision and anticipation in diagnosing thyroid diseases, offering healthcare professionals a powerful tool for improved patient care, and optimized clinical outcomes. The results highlight that the Random Forest model achieved remarkable performance with 100% on the accuracy, precision, recall F1 Score and AUC metrics. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024
Implementation of a Web-Based System to Improve the Appointment Process in a Clinic
No full textThe study aims to identify the factors, processes, standards, and analysis that will contribute to the implementation of a Web System for the appointment process. It is highlighted that the analysis will be beneficial since it is expected to improve the quality of care by allowing the migration of in-person appointments to online appointments. The general objective is to develop a web system aimed at optimizing the appointment scheduling process. To carry out this project, the Scrum methodology was adopted, recognized for its ability to guarantee the transparency and visibility of the elements that can influence the results. After the implementation of the web system, a survey was carried out on the sample to obtain statistical data, revealing that in the month of July a time saving of 95% was achieved in people who use the web system. In conclusion, it is expected that the implementation of this system will significantly contribute to improving the efficiency of the appointment process, reducing waiting times and offering better care. © 2024 IEEE
Better Together Than Separate: Prediagnosis of Thyroid Nodules Through Ultrasound Imaging Using CNN, ViT and Hybrid Models
No full textThe increase in thyroid cancer cases registered from 1990 to the last decade by 20 % worldwide, has created a need for faster and more accurate diagnostic tools for thyroid nodules. Deep Learning architectures, including Convolutional Neural Networks and Vision Transformers, have been developed to assist in diagnosing whether nodules are benign or malignant. Data Augmentation techniques such as DCGAN were also utilized. Hybrid models combining these type of architectures were also trained. The hybrid model developed by Google, re-trained with the TNCD dataset, achieved the best results with values of 77.20% for Accuracy, 77.97% for Recall, and 67.65% for Precision. The success of the hybrid approach depends on the architectures combined and whether they have been pre-trained. These findings suggest that a pre-trained model combining CNN and ViT is superior to using them independently, highlighting the potential of combining these architectures for improved the pre-diagnostic accuracy. © 2024 IEEE
Sociodemographic aspects, satisfaction, loyalty, and motivations in religious tourism
No full textThis research concentrated on pilgrimages within the context of religious tourism. It sought to accomplish the following goals: establish the main motivational factors in religious tourism, identify the relationship between sociodemographic aspects and motivations, and determine the relationship between the sociodemographic aspects of pilgrims with their satisfaction and loyalty. The study was conducted during the Christ of Miracles Pilgrimage in Lima, Peru. The sample consisted of 384 tourists who were surveyed on-site. The statistical techniques used included factorial and multiple regression analysis. The findings uncovered five motivational dimensions: religious experience, belief experience, escape experience, tourist experience, and shopping. The sociodemographic variables were correlated with the motivation for the escape experience, thus younger attendees, with higher educational levels or who attended the event fewer times had higher levels of motivation for the Escape. Age was correlated with satisfaction, older attendees were more satisfied and the number of attendees at the event was correlated with loyalty. The results will offer management recommendations for organizers of religious events and add valuable insights to the academic literature. © 2024 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group
Analisis del desempeño innovador de las empresas de servicios intensivos en conocimientos
No full textObjetivo. Evaluar la relación entre las fuentes de información y la capacidad de absorción y cómo esta capacidad mejora el desempeño innovador de una empresa. Metodología. El estudio presenta evidencias basadas en una muestra de 212 P-ESIC y 355 T-ESIC peruanas. En la investigación se aplicó un enfoque de modelo de ecuaciones estructurales por medio del software AMOS; mientras que para el análisis de mediación se utilizó el software PROCESS. Resultados. Se encontró que cuando las ESIC son expuestas a fuentes de información internas, del mercado, institucionales, así como a otras fuentes, están en mejores condiciones para desarrollar innovaciones. Sin embargo esta condición no es suficiente, pues es necesario desarrollar la capacidad dinámica (denominada capacidad de absorción). Conclusiones. Este estudio contribuye a comprender mejor el comportamiento innovador de las ESIC en una economía emergente como la peruana, ya que tiene en cuenta que las economías emergentes presentan características diferentes a las de las economías más desarrolladas. También se verificó que la capacidad de absorción no media en la relación entre las fuentes de información y el desempeño innovador en los dos grupos de empresas ESIC analizadas
Telemedicine in Peru: origin, implementation, pandemic escalation, and prospects in the new normal
No full textAbstract
For many countries telemedicine was speedily adopted as a result of the COVID-19 pandemic, though for some countries telemedicine may have been implemented in a context of limited regulations or few plans or strategies to scale quickly. This article recounts how telemedicine was developed in Peru as a measure to support the country's Universal Health Coverage and service access to rural and locations with low workforce numbers and its deployment. From a range of data, we find that Peru's development of telehealth began before the pandemic, which by 2020 was sufficient to be able to foster a rapid and wider deployment and while the telemedicine service volumes quickly grew from the pandemic onset, these numbers then begin to reduce suggesting that telemedicine was considered more as a pandemic emergency measure rather than a change to the mix of health provision. From these data we offer two lessons, (i) that Peru's preparedness in terms of telemedicine policy and regulation were helpful to rapidly expand telemedicine at a time of necessity and (ii) that due to this investment and with a better understanding, Peru now has a short-run window of opportunity for the Peruvian Government to continue its regulatory development and investment to further deploy telemedicine services as a UHC improvement measure and to better align the health system to the country’s health needs.</jats:p
Predicting Anemia in Patients Through Clinical and Hematological Data Using Machine Learning Algorithms
No full textAnemia is a prevalent condition affecting millions of individuals worldwide. Notably, Peru has witnessed a concerning increase in anemia cases. This study aims to delves into an extensive analysis of the role of machine learning within healthcare, particularly in the early identification and management of anemia using maching learning. The proposed Methodology consists of five phases: Obtained the dataset, Preprocessing, Model Implementations, Evaluation and Validation. In the proposed method, anemia detection is performed by reviewing relevant studies, encompassing Rodríguez's data analysis methodology, Gómez's exploration of AI applications, Hernández's optimization-based SVM model, Díaz's email classification, and Dávila's algorithms for discerning between healthy and anemic blood samples. The approach involves comprehensive data collection, meticulous preprocessing, feature extraction employing techniques such as cell count and crucial factor identification, and data classification using a range of machine learning algorithms. The results highlight the Artificial Neural Network model as the most optimal, achieving a noteworthy accuracy rate of 90.3\% in correctly identifying anemic blood samples. Finally, this study underscores the pivotal role of machine learning techniques in advancing the diagnosis and treatment of anemia, especially in regions experiencing escalated incidences like Peru, offering promising avenues for addressing this pressing global health concern. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024
Biometric Facial Recognition System and Expression Classifier Using Deep Learning
No full textThe recognition of emotions through facial expressions is difficult for computer systems, unlike humans who can easily do it in various contexts, such as interaction with computers. Studies indicate that the most effective approach to automatic emotion recognition is machine learning, and deep learning in particular offers greater accuracy. This research focuses on determining the level of stress and fatigue based on the facial features predicted by a proposed model, grouping indicators such as anger, sadness, and fear as signs of stress. A model was trained using convolutional networks to analyze facial patterns and relate them to emotions. A Kaggle dataset containing various facial expressions was used for testing and training. Special attention was paid to extracting and processing the captured video camera images to remove noise, which allowed for accurate classification of many facial reactions. This, in turn, helped predict burnout indicators such as stress and fatigue, with greater than 90% accuracy. © 2024 IEEE
Segmentation by motivations in religious tourism: A study of the Christ of Miracles Pilgrimage, Peru
No full textThe present study, focused on pilgrimages as part of religious tourism, aimed to achieve the following objectives: Identify the motivations of the demand for religious tourism focused on pilgrimages; analyze the segmentation of the demand; identify the relationship between demand segments with satisfaction and loyalty; and establish the sociodemographic aspects that characterize demand segments. The study was conducted during the Pilgrimage of the Christ of Miracles in Lima, Peru. The sample was taken on-site from 384 tourists. The statistical techniques used were factor analysis and the k-means clustering method. The results reveal five motivational dimensions: Religious Experience, Belief Experience, Escape, Touristic Experience, and Shopping. Three attendee segments were also identified: Believers, related to belief experience; Religious, related to religious experience; and Passive, tourists with low motivations. The Religious segment had the highest satisfaction and loyalty levels among these groups. Sociodemographic differences were also found in the demand segments. The findings will contribute to management guidelines for destination administrators with religious events and provide insights into academic literature.</jats:p