JSJose Luis Herrera Salazar

Jose Luis Herrera Salazar

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Jose Luis Herrera Salazar has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Neural Network-Based Support System to Improve Alzheimer's Detection Using Magnetic Resonance Imaging

    by Gustavo Enrique Meza Salcedo, James Gino Evangelista Vilela, José Luis Herrera Salazar, Fabricio Alexandro Navarro Fabian

    Early and accurate detection of Alzheimer’s is crucial for the quality of life of patients and families. Given the limitations of traditional methods, neural networks offer a promising alternative. This study implemented a neural network- based system to analyze brain magnetic resonance imaging (MRI) scans and detect Alzheimer’s. Using the SCRUM methodology, data acquisition and preparation, network training, and system evaluation were managed. The Inception V3 model achieved 98% accuracy, outperforming other models. This efficacy suggests that convolutional neural networks can significantly improve early detection, reducing the time to diagnosis. The findings support the use of advanced artificial intelligence to improve clinical outcomes and enable more timely interventions in Alzheimer’s patients.

  • Open Access

    Mobile Application with Artificial Intelligence Assistant to Improve the Logistical Process in Pharmaceutical Companies

    by Rosa Menéndez Mueras, Esteban Julio Medina Rafaile, José Luis Herrera Salazar

    According to the World Bank (WB), an estimated 60% of pharmaceutical companies in developing countries report significant problems in their supply chain, often resulting in delays and financial losses. The objective of this study is to develop a mobile application with an artificial intelligence assistant to improve the logistics process in a pharmaceutical company. In this sense, the Cascada methodology was used, together with various computer tools, to develop the prototype. Favorable results were obtained with respect to the criteria of functionality, usability, innovation and technology. Concluding that the application meets all the necessary conditions to mitigate the problem of the logistics process in pharmaceutical companies.


  • Open Access

    Mobile Application with Artificial Intelligence Chatbots for Dengue Information and Management

    by Rosa Menéndez Mueras, Esteban Julio Medina Rafaile, José Luis Herrera Salazar

    Dengue fever has intensified in recent years, affecting millions, with an estimated 100 to 400 million people yearly; approximately 80% of these cases have been reported in the Americas. This develops a prototype of a mobile application that includes artificial intelligence (AI) chatbots for dengue management and information. The design thinking methodology was applied, which was useful due to its focus on user needs, allowing the identification of key problems in dengue management and the design of innovative and functional solutions. The results were validated by experts using criteria such as technology, innovation, and feasibility with an average score of 4.26 and users using criteria such as functionality, usability, and accessibility with an average score of 4.28, showing a high level of acceptance. This tool has the potential to improve early disease detection, facilitating data collection and real-time interaction with patients. Through the use of AI, the application aims to optimize case management, reduce serious complications, and support health systems in at-risk areas.


  • Open Access

    Predicting Heart Failure: A Comparative Approach between Artificial Neural Networks and Support Vector Machines

    by José Luis Herrera Salazar, Magdalena Talla Linderman, Orlando Iparraguirre-Villanueva

    In recent years, cardiovascular diseases have become increasingly important as a leading cause of death globally. heart failure (HF), a chronic disease affecting some 26 million people worldwide, has become a growing pandemic. Its prevention is a national and global emergency. In India, between 1.3 and 4.6 million adults suffer from HF, and despite advances in therapy and prevention, mortality and morbidity remain high, with significant costs to the healthcare system. The purpose of this study is to conduct a comparative evaluation of ML models for predicting HF. The support vector machine (SVM) and artificial neural network (ANN) models were analyzed to determine which model offers superior accuracy. A dataset from the Kaggle platform with x records and x features was used to train the models. The results indicated that the SVM model is the best predictor of HF with an accuracy of 79%, which far exceeds the ANNs with 77%. It is concluded that the machine learning (ML) method known as SVM shows outstanding and effective performance in the task of predicting heart failure.

  • Open Access

    Cybersecurity in health sector: a systematic review of the literature

    by Catherine Vanessa Peve Herrera, Jonathan Steve Mendoza Valcarcel, Mónica Díaz, Jose Luis Herrera Salazar, Laberiano Andrade-Arenas

    Currently, health centers are being affected by various cyberattacks putting at risk the confidential information of their patients and the organization because they do not have a plan or tools to help them mitigate these cyberattacks, which is important to know what measures to take to protect the privacy of personal data. The present work was carried out under a systematic literature review, which aims to show the importance of cybersecurity in the health sector knowing which tools are the most used and efficient to prevent a cyberattack. A systematic review of 301 articles was carried out, 79 of which are aligned with the objective set, fulfilling the inclusion and exclusion criteria. The search for information was carried out in the Scopus and Dimensions databases. The analysis carried out has resulted in good information that was compiled for the development of this topic, being favorable thanks to the different research of different authors.


  • Open Access

    Search and classify topics in a corpus of text using the latent dirichlet allocation model

    by Orlando Iparraguirre-Villanueva, Fernando Sierra-Liñan, Jose Luis Herrera Salazar, Saul Beltozar-Clemente, Félix Pucuhuayla-Revatta, Joselyn Zapata-Paulini, Michael Cabanillas-Carbonell

    This work aims at discovering topics in a text corpus and classifying the most relevant terms for each of the discovered topics. The process was performed in four steps: first, document extraction and data processing; second, labeling and training of the data; third, labeling of the unseen data; and fourth, evaluation of the model performance. For processing, a total of 10,322 "curriculum" documents related to data science were collected from the web during 2018-2022. The latent dirichlet allocation (LDA) model was used for the analysis and structure of the subjects. After processing, 12 themes were generated, which allowed ranking the most relevant terms to identify the skills of each of the candidates. This work concludes that candidates interested in data science must have skills in the following topics: first, they must be technical, they must have mastery of structured query language, mastery of programming languages such as R, Python, java, and data management, among other tools associated with the technology.


  • Mobile App for the Promotion of Home Services

    by David Israel Nicolas Quispe, Josue Martin Nicolas Quispe, Jose Luis Herrera Salazar, Johny Pretell Cruzado

    Home services advertising presents difficulties to the worker who has as an obstacle the cost of the advertising used to promote his services so that a large amount of people can see it, as well as the deficient training in technological tools has brought as consequence the usage of traditional methods which made being located and hired in real time more difficult. In this sense, the objective of this research was to develop and implement a mobile application that allows home services advertising and is able to fulfill all the previous mentioned factors; XP methodology was used for the development of the application; ten cases were used as evidence where demonstrated it was capable of advertising household services, which concludes that the mobile application can advertise household services.


  • Geobook: Mobile App with Augmented Reality for Learning Geometry

    by Johny Pretell Cruzado, Tatiana Llajaruna Cespedes, Gian Pierre Bohorquez Coria, Jose Luis Herrera Salazar

    This study shows the results obtained after the application of augmented reality - AR in the learning of descriptive geometry in elementary level students. The use of Mobile-D methodology facilitated the rapid development of mobile applications with augmented reality called Geobook. The statistical sample involved two sections in 6th-grade elementary school students from a public school in Lima city, where the experimental group improved by 82.18% with respect to the learning levels of the control group. It is concluded that the use of an AR-based mobile application significantly enhances learning in three aspects of descriptive geometry, included in the experimental and test dimensions.