Multivariate Stream Data Classification Using Simple Text Classifiers

Abstract

Abstract. We introduce a classification framework for continuous multivariate stream data. The proposed approach works in two steps. In the preprocessing step, it takes as input a sliding window of multivariate stream data and discretizes the data in the window into a string of symbols that characterize the signal changes. In the classification step, it uses a simple text classification algorithm to classify the discretized data in the window. We evaluated both supervised and unsupervised classification algorithms. For supervised, we tested Naïve Bayes Model and SVM, and for unsupervised, we tested Jaccard, TFIDF, Jaro and JaroWinkler. In our experiments, SVM and TFIDF outperformed the other classification methods. In particular, we observed that classification accuracy is improved when the correlation of attributes is also considered along with the n-gram tokens of symbols.

Adaptive pattern mining model for early detection of botnet‐propagation scale

“…In this research, a simple text classifier (STC) is used to classify scanning traffic consisting of multivariate data streams into specific strategies. The STC simplifies the data‐stream encoding problem for complex and extensive network traffic by using specific symbols, especially for detecting aspects of abnormal behavior (such as port scanning).…”

“…Before introducing the proposed model, it is necessary to provide a brief review of multivariate data‐stream classification using the STC representation of time series, as discussed in , as well as of HMM.…”

“…Using and , Seo et al . introduced the idea referred to here as multivariate data‐stream classification using STC. As shown in Figure , an n ‐gram model frame is used to generate various patterns, which are represented as U , u , D , d , and S ; U is used when the collected value dramatically increases during the time interval from t i to t i + k , where k is a constant between 1 and the window size p , while u is used to denote a trivial increase.…”