This paper introduces a new similarity measure, termed Binary Weighted Cosine (BWC) metric, for anomaly-based intrusion detection schemes that rely on using sequences of system calls. The new similarity measure considers both the number of shared system calls between two processes as well as frequencies of those calls. The k nearest neighbor (kNN) classifier is used to categorize a process as e...

This paper presents a classifier that is based on a modified version of the well known K-Nearest Neighbors classifier (K-NN). The original K-NN classifier was adjusted to work with category representatives rather than training documents. Each category was represented by one document that was constructed by consulting all of its training documents and then applying feature selection so that only...

We show that excluding outliers from the training data significantly improves kNN classifier, which in this case performs about 10% better than the best know method—Centroid-based classifier. Outliers are the elements whose similarity to the centroid of the corresponding category is below a threshold.

Whether and to what extent our conceptual structure is universal is of great importance for our understanding of the nature of human concepts. Two major factors that might affect our concepts are language and culture. In this research, we tested whether these two factors affect our concepts of everyday objects in any significant ways. For this purpose we compare adults of three cultural/languag...

This paper presents two metrics for the Nearest Neighbor Classifier that share the property of being adapted, i.e. learned, on a set of data. Both metrics can be used for similarity search when the retrieval critically depends on a symbolic target feature. The first one is called Local Asymmetrically Weighted Similarity Metric (LASM) and exploits reinforcement learning techniques for the comput...

The aim of this paper is to introduce improvements made to a classifier based on the fuzzy similarity [1]. Improvements are based on the use of generalized Łukasiewicz-structure and weight optimization. We are presenting some new results and a more detailed description of the theoretical background and fixing some terminology compared in to our previous work [2]. The main benefits of the classi...

For shot boundary detection, our approach combines pairwise similarity analysis and supervised classification. Using primitive low-level image features, we build secondary features based on inter-frame dissimilarity. The secondary features are motivated by prior work on media segmentation in which a kernel function is correlated along the main diagonal of a similarity matrix to construct a fram...

We deal with the issue of combining dozens of classifiers into a better one, for concept detection in videos. We compare three fusion approaches that share a common structure: they all start with a classifier clustering stage, continue with an intra-cluster fusion and end with an inter-cluster fusion. The main difference between them comes from the first stage. The first approach relies on a pr...

The generalization abilities of machine learning algorithms often depend on the algorithms' initialization, parameter settings, training sets, or feature selections. For instance, SVM classifier performance largely relies on whether the selected kernel functions are suitable for real application data. To enhance the performance of individual classifiers, this dissertation proposes classifier fu...

For a classification problem described by the joint density P (ω,x), models of P (ω = ω′|x, x′) (the “Bayesian similarity measure”) have been shown to be an optimal similarity measure for nearest neighbor classification. This paper analyzes demonstrates several additional properties of that conditional distribution. The paper first shows that we can reconstruct, up to class labels, the class po...