Search

The objective of this research is provide to the specialists in skin cancer, a premature, rapid and non-invasive diagnosis of melanoma identification, using an image of the lesion, to apply to the treatment of a patient, the method used is the architecture contrast of Convolutional neural networks proposed by Laura Kocobinski of the University of Boston, against our architecture, which reduce the depth of the convolution filter of the last two convolutional layers to obtain maps of more significant characteristics. The performance of the model was reflected in the accuracy during the validation, considering the best result obtained, which is confirmed with the additional data set. The findings found with the application of this base architecture were improved accuracy from 0.79 to 0.83, with 30 epochs, compared to Kocobinski's AlexNet architecture, it was not possible to improve the accuracy of 0.90, however, the complexity of the network played an important role in the results we obtained, which was able to balance and obtain better results without increasing the epochs, the application of our research is very helpful for doctors, since it will allow them to quickly identify if an injury is melanoma or not and consequently treat it efficiently.

Having a well-defined control of the change processes in the configuration management in the software development life cycle, before and after being put into production environment, implies an effort of development personnel and an additional cost in the maintenance system. The objective of this paper is to establish the guidelines to regulate the activities and tasks during the process of development and maintenance of software-based systems in order to control the changes, integrity and traceability of its configuration, for this purpose it is taken as a reference the peruvian technical standards NTP-ISO/IEC 12207: 2016 for Software and systems engineering, NTPISO/IEC 27001: 2014 for Information security management systems and the methodology MÉTRICA version 3 for the systematization of life cycle of the software activities. The proposal defines the roles and responsibilities, the activities of each thread and the use of control templates, the validation of the was achieved through the analysis of three software systems with results that show that there is a better organization in the development, maintenance, control of the versions of the elements and the percentage of error in the configuration.

The quality of food is associated with a set of properties and characteristics that can be considered from its chemical and nutritional physical composition that have the ability to meet the needs of the consumer. The paper aims to evaluate the application of fuzzy logic in the evaluation and classification of the selection of pecans in the post harvest process using tests and instruments that determine their best quality. Fuzzy logic has proven to be very effective with matlab/simulink to develop and simulate the entire system, through an appropriate choice of rules and membership functions and applying the Mamdani method to defuzzification the results considering they are positive.

This paper describes how to improve the academic performance of engineering university students through an Adaptive Educational Hypermedia System (AEHS). The psychological basis, learning styles and MOOMH methodology for the development of the system are exposed, which with its implementation achieves adaptability and works for students as an “intelligent tutor”, allowing them to guide their education as academic tutor. Not only shows its content that meets the needs of the student, but it is also represented in elements such as color adaptation, work tools and even academic recommendations based on the interactions that the user makes within the system, the system recognizes its pattern of use, and when the student is logged in again, it presents a friendlier interface that the student prefers use, it is wider in content and, above all, easy to use and understand. In addition, the AEHS allows to extend education allowing the assignment of more domain areas, in the field of engineering, that is, the SHAE can be adapted to various engineering specialties such as: industrial, software, telecommunications, mechanics and other.

This paper proposes to improve the process of technological renewal in data centers with the implementation of hyperconverged systems, through the virtualization of physical equipment, networks, storage and systems, to achieve cost reduction in critical areas such as: maintenance, consumption of energy, data center space and the optimization of the resources necessary for the administration and specialization of the IT team. The proposed methodology HSA (Hyperconverged Systems Applied), considers the planning and implementation of an integral IT architecture that combines software with high-level servers that can host systems capable of providing support and continuity of IT services, to design, implement and manage the technology in an orderly manner, reducing management efforts and increasing the organization's ability to support new projects. According to the results obtained with the application of the HSA methodology, it was reduced the size of virtualized systems by an average of 33.33% and the amount of non-virtualized technology by an average of 44.33%, depending on the cases evaluated was increased the level of IT team experience at 56.67% when managing more technology with less staff

The automatic detection of facial expressions is an active research topic, since its wide fields of applications in human-computer interaction, games, security or education. However, the latest studies have been made in controlled laboratory environments, which is not according to real world scenarios. For that reason, a real time Facial Expression Recognition System (FERS) is proposed in this paper, in which a deep learning approach is applied to enhance the detection of six basic emotions: happiness, sadness, anger, disgust, fear and surprise in a real-time video streaming. This system is composed of three main components: face detection, face preparation and face expression classification. The results of proposed FERS achieve a 65% of accuracy, trained over 35558 face images..