Linear classification is a useful tool in machine learning and data mining. For some data in a rich dimensional space, the performance (i.e., testing accuracy) of linear classifiers has shown to be close to that of nonlinear classifiers such as kernel methods, but training and testing speed is much faster. Recently, many research works have developed efficient optimization methods to construct linear classifiers and applied them to some large-scale applications. In this paper, we give a comprehensive survey on the recent development of this active research area.

Improving the performance of classifiers using pattern mining techniques has been an active topic of data mining research. In this work we introduce the recent temporal pattern mining framework for finding predictive patterns for monitoring and event detection problems in complex multivariate time series data. This framework first converts time series into time-interval sequences of temporal abstractions. It then constructs more complex temporal patterns backwards in time using temporal operators. We apply our frame-work to health care data of 13,558 diabetic patients and show its benefits by efficiently finding useful patterns for detecting and diagnosing adverse medical conditions that are associated with diabetes.

We study the problem of learning classification models from complex multivariate temporal data encountered in electronic health record systems. The challenge is to define a good set of features that are able to represent well the temporal aspect of the data. Our method relies on temporal abstractions and temporal pattern mining to extract the classification features. Temporal pattern mining usually returns a large number of temporal patterns, most of which may be irrelevant to the classification task. To address this problem, we present the Minimal Predictive Temporal Patterns framework to generate a small set of predictive and non-spurious patterns. We apply our approach to the real-world clinical task of predicting patients who are at risk of developing heparin induced thrombocytopenia. The results demonstrate the benefit of our approach in efficiently learning accurate classifiers, which is a key step for developing intelligent clinical monitoring systems.

Abstract not found

P-Type ATPases are part of the regulatory system of the cell where they are responsible for transporting ions and lipids through the cell membrane. These pumps are found in all eukaryotes and their malfunction has been found to cause several severe diseases. Know-ing which substrate is pumped by a certain P-Type ATPase is therefore vital. The P-Type ATPases can be divided into 11 subtypes based on their specificity, that is, the substrate that they pump. Determining the subtype experimentally is time-consuming. Thus it is of great interest to be able to accurately predict the subtype based on the amino acid sequence only. We present an approach to P-Type ATPase sequence classification based on the k-nearest neighbors, similar to a homology search, and show that this method pro-vides performs very well and, to the best of our knowledge, better than any existing method despite its simplicity. The classifier is made available as a web service at