Search

Intruders detection in computer networks has some deficiencies from machine learning approach, given by the nature of the application. The principal problem is the modest display of detection systems based on learning algorithms under the constraints imposed by real environments. This article focuses on the machine learning approach for network intrusion detection in batch and data stream environments. First, we propose and describe three variants of KDD99 dataset preprocessing including attribute selection. Secondly, a thoroughly experimentation is performed from evaluating and comparing representative batch learning algorithms on the variants obtained from KDD99 pre processing. Finally, since network traffic is a constant data stream, which can present concept drifting with high rate of false positive, along with the fact that there are not many researches addressing intrusion detection on streaming environments, lead us to make a comparison of various representative data stream classification algorithms. This research allows determining the algorithms that better perform on the proposed variants of KDD99 for both batch and data stream environments., Comment: in Spanish

Data mining has been widely used to identify potential customers for a new product or service. In this article is done a study of previous work relating to the application of data mining methodologies for software projects, specifically for direct marketing projects. Several data sets of demographic and historical customer purchases data available for evaluation of algorithms in this area, some of them very new and current are described. The main contribution of this paper is the proposal of a platform for distributed data stream processing for the processes of targeting customers and building predictive models required response; thus facilitating several of the functional requirements for development environments., Comment: in Spanish

Network intrusion detection is one of the most visible uses for Big Data analytics. One of the main problems in this application is the constant rise of new attacks. This scenario, characterized by the fact that not enough labeled examples are available for the new classes of attacks is hardly addressed by traditional machine learning approaches. New findings on the capabilities of Zero-Shot learning (ZSL) approach makes it an interesting solution for this problem because it has the ability to classify instances of unseen classes. ZSL has inherently two stages: the attribute learning and the inference stage. In this paper we propose a new algorithm for the attribute learning stage of ZSL. The idea is to learn new values for the attributes based on decision trees (DT). Our results show that based on the rules extracted from the DT a better distribution for the attribute values can be found. We also propose an experimental setup for the evaluation of ZSL on network intrusion detection (NID).

With the massive data challenges nowadays and the rapid growing of technology, stream mining has recently received considerable attention. To address the large number of scenarios in which this phenomenon manifests itself suitable tools are required in various research fields. Instance-based data stream algorithms generally employ the Euclidean distance for the classification task underlying this problem. A novel way to look into this issue is to take advantage of a more flexible metric due to the increased requirements imposed by the data stream scenario. In this paper we present a new algorithm that learns a Mahalanobis metric using similarity and dissimilarity constraints in an online manner. This approach hybridizes a Mahalanobis distance metric learning algorithm and a k-NN data stream classification algorithm with concept drift detection. First, some basic aspects of Mahalanobis distance metric learning are described taking into account key properties as well as online distance metric learning algorithms. Second, we implement specific evaluation methodologies and comparative metrics such as Q statistic for data stream classification algorithms. Finally, our algorithm is evaluated on different datasets by comparing its results with one of the best instance-based data stream classification algorithm of the state of the art. The results demonstrate that our proposal is better