The popularity of tracking devices continues to contribute to increasing volumes of spatio-temporal data about moving objects. Current approaches in analysing these data are unable to capture collective behaviour and correlations among moving objects. An example of these types of patterns is moving flocks. This article develops an improved algorithm for mining such patterns following a frequent pattern discovery approach, a well-known task in traditional data mining. It uses transaction-based data representation of trajectories to generate a database that facilitates the application of scalable and efficient frequent pattern mining algorithms. Results were compared with an existing method (Basic Flock Evaluation or BFE) and are demonstrated for both synthetic and real data sets with a large number of trajectories. The results illustrate a significant performance increase. Furthermore, the improved algorithm has been embedded into a visual environment that allows manipulation of input parameters and interactive recomputation of the resulting flocks. To illustrate the visual environment a data set containing 30 years of tropical cyclone tracks with 6 hourly observations is used. The example illustrates how the visual environment facilitates exploration and verification of flocks by changing the input parameters and instantly showing the spatio-temporal distribution of the resulting flocks in the Space-Time Cube and interactively selecting, querying and saving the resulting flocks for further analysis and verification.

This study describes the decision making process used by the residents of Villavicenciodepartment of Meta, central Colombia-to choose among different means of transport for their daily needs. This study constitutes an attempt to bring the attention to the traffic problem in Villavicencio, where the increase in the use of cars and motorcycles in the last decade has been exponential, with the result of generating a number of unresolved challenges -road accidents, traffic congestion, pollution and occupation of public space.This study uses data from the survey 'Encuesta domiciliaria origen-destino' conducted in the municipality of Villavicencio in 2008 and applies a multinomial logit model to establish the probability of choosing the mean of transport conditioned on a number of controls related to the individuals' socioeconomic characteristics, to the location of the work and that of the dwelling.The results of both the descriptive statistics and the econometric model show that the variables related to the age of the resident, his/her socioeconomic level, time and cost of the journey are among the variables which mostly influence the resident decisions when choosing the mean of transport. In view of the constant increase in the traffic congestion and road related accidents recorded in the last decade in the area, the priority of the both the central and local Government should be the improvement of the public transport service -which is almost absent-and the creation of a safer environment to allow residents to cycle and to walk without impending danger.

Resumen En este artículo se presentan los primeros resultados del proyecto de investigación cuyo objetivo es detectar patrones de deserción estudiantil a partir de los datos socioeconómicos, académicos, disciplinares e institucionales de los estudiantes de los programas de pregrado de la Universidad de Nariño e Institución Universitaria IUCESMAG, dos instituciones de educación superior de la ciudad de Pasto (Colombia), utilizando técnicas de Minería de Datos. Los resultados obtenidos corresponden a la Universidad de Nariño. Se descubrieron perfiles socioeconómicos y académicos de los estudiantes que desertan utilizando la técnica de clasificación basada en árboles de decisión. El conocimiento generado permitirá soportar la toma de decisiones eficaces de las directivas universitarias enfocadas a formular políticas y estrategias relacionadas con los programas de retención estudiantil que actualmente se encuentran establecidos. Palabras claveExtracción de Perfiles, Deserción Estudiantil, Minería de Datos, Clasificación, Árboles de Decisión   Abstract The first results of the research project that aims to identify patterns of student dropout from socioeconomic, academic, disciplinary and institutional data of students from undergraduate programs at the University of Nariño and IUCESMAG University, two higher education institutions in the city of Pasto (Colombia), using data mining techniques are presented. The results correspond to the University of Nariño. Socioeconomic and academic profiles were discovered of students who drop using classification technique based on decision trees. The knowledge generated will support effective decision-making of university staff focused to develop policies and strategies related to student retention programs that are currently set.KeywordsExtraction of Profiles, Student Dropout, Data Mining, Classification, Decision Trees

This paper studies the effects that oil extraction activities in Colombia have on the number of dead/injured people as a consequence of road-related accidents. Starting in 2004, the increasing exploitation of oil wells in some Colombian departments has worsened the traffic conditions due to the increased presence of trucks transporting crude oil from the wells to the refineries; this phenomenon has not been accompanied by an improvement in the road system with dramatic consequences in terms of road viability. The descriptive and empirical analysis presented here focuses on the period 2004-2011; results from descriptive statistics indicate a positive relationship between the presence of oil extraction activities and the number of either dead/injured people. Panel regressions for the period 2004-2011 confirm that, among other factors, the presence of oil-extraction activities did play a positive and statistical significant role in increasing the number of dead/injured people.

No abstract