Search

This paper is an advance of the research project entitled "Development of hybrid algorithms for data mining" and presents the use of a neural network with the simulated annealing algorithm to perform the prediction of a training data set. First, it addresses the problem to be solved, which is oriented to the analysis of the techniques defined for the hybrid algorithm. Then, the applied research methodology (descriptive-exploratory scientific with experimental approach) is justified. We performed a review of the techniques selected for the hybrid neuronal networks and simulated annealing technique which is applied to a set of experimental data associated with determining in a group of patients whether their spine is normal or abnormal. Then, the tests of analysis and results are presented. [ABSTRACT FROM AUTHOR]

Cluster analysis of climatological data is used in various investigations as it allows interesting results to be obtained for each proposed approach. Therefore, this paper presents the performance evaluation of the K-Means clustering algorithm from the use of standardization applied to a data set with four climatological variables (temperature, precipitation, relative humidity and solar radiation) for a station located in the city of Manizales, Colombia. This in order to determine the effect of applying, or not, the normalization in the quality of the clusters and to evaluate the computational cost of the algorithm according to the established characteristics. For this purpose, six execution scenarios are defined for 2, 3 and 5 clusters with different quantity and grouping of variables using Euclidean distance as a distance measure, Davies-Bouldin as a quality evaluation method of the clusters and the application of normalization with Z-transformation and Range transformation. It is concluded that, through a comparison with k-medoides and STFT application (Fourier Transform of Reduced Time), the normalization improves the results and with Z-transformation the best grouping performances are obtained according to the Davis-Bouldin index. [ABSTRACT FROM AUTHOR]

Open source intelligence (OSINT) is a cyber-intelligence branch used to obtain and analyze information related to potential adversaries, so it can support risk assessments and help to prevent damages against critical assets. This paper presents a research about different OSINT technologies and how these can be used to perform cyber intelligence tasks of a nation. A set of transforms addressed to the Colombian context are presented, which were implemented and contributed to the community allowing to the law enforcement agencies to develop information gathering process from Colombian open sources. However, the real use of the information is given by the implementation of three machine learning models used to perform sentiment analysis over this information, in order to know the opinion of the adversary about certain topic and understand his motivation and, in this way, define proper cyber defense strategies. Finally, some challenges related to the application of OSINT techniques are identified and described regarding its use by state security agencies. [ABSTRACT FROM AUTHOR]

In this paper we development a hybrid algorithm of machine learning for the automatic locking of web pages that incite to violence through content snuff. We describe of the current situation of the problem to be solved, and we give to know the selection process of the techniques for the development of the hybrid algorithm. Also, we show the mathematical model and results analysis. [ABSTRACT FROM AUTHOR]

In this paper we show the realization of a project that involves the creation of a hybrid learning algorithm for supervised computer automatically blocking websites that incite violence through snuff content. In this, there is a description of the current state of the problem to solve and provides a concept of what is mining and computational learning, on this basis, three algorithms are chosen similar to the proposed works, with the to analyze their weaknesses, strengths and applications. [ABSTRACT FROM AUTHOR]