Pub. online:1 Jan 2017Type:Research ArticleOpen Access
Volume 28, Issue 2 (2017), pp. 359–374
In recent years, the growth of marine traffic in ports and their surroundings raise the traffic and security control problems and increase the workload for traffic control operators. The automated identification system of vessel movement generates huge amounts of data that need to be analysed to make the proper decision. Thus, rapid self-learning algorithms for the decision support system have to be developed to detect the abnormal vessel movement in intense marine traffic areas. The paper presents a new self-learning adaptive classification algorithm based on the combination of a self-organizing map (SOM) and a virtual pheromone for abnormal vessel movement detection in maritime traffic. To improve the quality of classification results, Mexican hat neighbourhood function has been used as a SOM neighbourhood function. To estimate the classification results of the proposed algorithm, an experimental investigation has been performed using the real data set, provided by the Klaipėda seaport and that obtained from the automated identification system. The results of the research show that the proposed algorithm provides rapid self-learning characteristics and classification.
Pub. online:1 Jan 2012Type:Research ArticleOpen Access
Volume 23, Issue 2 (2012), pp. 191–201
Regarding the complexity of actual software systems, including web portals, it is becoming more and more difficult to develop software systems such that their real usage will satisfy their intended usage. To tackle this problem, we can compare the a priori assumptions about how the system should be used with the actual user behavior in order to decide how the system could be improved. For this aim, we propose to employ the same formalism to express the intended usage, the web portal model and the real usage extracted from system usage traces by data mining algorithms. Inspired from BioCham, we propose to use temporal logic and Kripke structure as such a common formalism.
Pub. online:1 Jan 2011Type:Research ArticleOpen Access
Volume 22, Issue 4 (2011), pp. 507–520
The most classical visualization methods, including multidimensional scaling and its particular case – Sammon's mapping, encounter difficulties when analyzing large data sets. One of possible ways to solve the problem is the application of artificial neural networks. This paper presents the visualization of large data sets using the feed-forward neural network – SAMANN. This back propagation-like learning rule has been developed to allow a feed-forward artificial neural network to learn Sammon's mapping in an unsupervised way. In its initial form, SAMANN training is computation expensive. In this paper, we discover conditions optimizing the computational expenditure in visualization even of large data sets. It is shown possibility to reduce the original dimensionality of data to a lower one using small number of iterations. The visualization results of real-world data sets are presented.