Examinando por Autor "Mejia Cabrera, Heber I."
Mostrando1 - 3 de 3
Resultados por página
Opciones de clasificación
- PublicaciónSólo datosAutomatic Detection of Injection Attacks by Machine Learning in NoSQL Databases(Lecture Notes in Computer Science, 2021-06-16) Mejia Cabrera, Heber I.; Paico Chileno, Daniel; Valdera Contreras, Jhon H.; Tuesta Monteza, Victor A.; Forero, Manuel G.NoSQL databases were created for the purpose of manipulating large amounts of data in real time. However, at the beginning, security was not important for their developers. The popularity of SQL generated the false belief that NoSQL databases were immune to injection attacks. As a consequence, NoSQL databases were not protected and are vulnerable to injection attacks. In addition, databases with NoSQL queries are not available for experimentation. Therefore, this paper presents a new method for the construction of a NoSQL query database, based on JSON structure. Six classification algorithms were evaluated to identify the injection attacks: SVM, Decision Tree, Random Forest, K-NN, Neural Network and Multilayer Perceptron, obtaining an accuracy with the last two algorithms of 97.6%.
- PublicaciónSólo datosDiagnosis of SARS-CoV-2 Based on Patient Symptoms and Fuzzy Classifiers(Communications in Computer and Information Science, 2021-04-12) Becerra Suarez, Fray L.; Mejia Cabrera, Heber I.; Tuesta Monteza, Víctor A.; Forero, Manuel G.The contention, mitigation and prevention measures that governments have implemented around the world do not appear to be sufficient to prevent the spread of SARS-CoV-2. The number of infected and dead continues to rise every day, putting a strain on the capacity and infrastructure of hospitals and medical centers. Therefore, it is necessary to develop new diagnostic methods based on patients' symptoms that allow the generation of early warnings for appropriate treatment. This paper presents a new method in development for the diagnosis of SARS-CoV-2, based on patient symptoms and the use of fuzzy classifiers. Eleven (11) variables were fuzzified. Then, knowledge rules were established and finally, the center of mass method was used to generate the diagnostic results. The method was tested with a database of clinical records of symptomatic and asymptomatic SARS-CoV-2 patients. By testing the proposed model with data from symptomatic patients, we obtained 100% sensitivity and 100% specificity. Patients according to their symptoms are classified into two classes, allowing for the detection of patients requiring immediate attention from those with milder symptoms.
- PublicaciónSólo datosNew Agile Enterprise Architecture Methodology for Small Latin American Organizations(Communications in Computer and Information Science, 2021-03-01) Mejia Cabrera, Heber I.; Tuesta Monteza, Victor A.; Samillan Ayala, Alberto E.; Forero, Manuel G.Information technologies (IT) promise great benefits. However, companies have business alignment problems, affecting investment, performance and agility. To achieve alignment, enterprise architecture (EA) reference models called Frameworks have been developed. These proposals were born in large companies and their design has a traditional approach to these realities. However, in Peru most companies are micro-enterprises, i.e. small organizations (SOs), with their own characteristics. SOs have a low Networked Readiness Index (NRI), generating little impact on Peru’s development. Therefore, this paper proposes a new business architecture methodology conceived for the reality of small Peruvian and Latin American organizations. A general method based on EA and SO criteria was developed, thus generating a metamodel, from which the elements of the methodology are instantiated, which integrates four approaches to IT management. The methodology developed was validated in a Peruvian SO and by experts. The preliminary results show that its use generates benefits with respect to the competition.