Tecnura

13 - 26

Authors: José Antonio Valero Medina, Beatriz Elena Alzate Atehortúa

Context: Nowadays, the images of the Earth surface and the algorithms for their classification are widely available. In particular, the algorithms are promising in the differentiating of cotton crops stages, but it is necessary to establish the capabilities of the different algorithms in order to identify their advantages, and disadvantages. Method: This paper describes the assessment process in which the Support Vector Machines (SVM) and random-forest technique (decision trees) are compa-red with the maximum likelihood estimation when differentiating the stages of cotton crops. A RapidEye satellite image of a geographic area in the municipa-lity of San Pelayo, Cordoba (Colombia), is used for the study. Using a set of sampling polygons, a ran-dom sample of 6000 pixels was taken (2000 training and 4000 for validating the classifications.) Confu-sion matrices, and R (data processing and analysis software) were used during the validation process Results: The maximun likelihood estimation presen-ted a correct classification percentage of 68.95%. SVM correctly classified 81.325% of the cases and the decision trees correctly classified 78.925%. The confidence test for the classifications showed non-overlapping intervals, and SVM obtained the highest values. Conclusions: It was possible to confirm the supe-riority of the technique based on support vector machines for the proposed verification zones. How-ever, this technique requires a number of classes that comprehensively represent the variations of the im-age (in order to guarantee a minimum number of support vectors) to avoid confusion in the classifi-cation of non-sampled areas. This was less evident in the other two classification techniques analysed.

47 - 59

Authors: Camilo Alberto Torres Parra, Janneth Arias Hernandez

Context: This paper presents a participative educa-tional proposal led by the cooperation network ca-lled “Construya Seguro y Sostenible,” to which the University Corporation Minuto de Dios, the Catholic University of Colombia, and the Pilot University of Colombia belong. Methodology: This research was developed from a non-experimental descriptive quantitative method, where forty-four (44) bad practices related to habita-bility in informal housing were identified Results: These bad practices were translated into ins-tructional objectives through learning units framed in a course proposal oriented to communities under the instructional model of Jerrold and Kemp. Conclusion: This initiative allowed to link 25 fami-lies of the Villas de Kennedy neighborhood in Bogo-tá, Colombia, with students and teachers linked to the Network who, through participatory work, socia-lized their findings and experiences.

68 - 79

Authors: Julián Andrés Mera Paz

Context: Currently the University Universidad Coo-perativa de Colombia in Popayán does not have a space or laboratory for software testing; however, the testing is a fundamental element of quality con-trol focused on the product and the process. A tech-nological diagnosis is proposed in order to validate the relevance of its implementation Method: The article presents a technological diagno-sis on the concept, techniques, methods, tools, and characteristics to be taken into account during the implementation of a testing laboratory, based on the CMMI and TMMI reference framework. The research takes as reference the scientific bibliography, which focuses on the role of higher education institutions and the teaching of software testing. Results: The technological diagnosis is a tool that, in an agile, efficient and effective way, allows to ob-tain clarity in the needs and opportunities, to pro-pose real solutions, as a fundamental element in the pertinence and viability of implementing a space for practices and experimentation regarding softwa-re testing and quality, at the University Universidad Cooperativa de Colombia, in Popayán. Conclusions: The technological diagnosis opens the doors to deepen the context of quality control and its relevance from academic environments, contri-buting cohesion between the software industry and the teaching-learning model of software.