Efficient linear dimensionality reduction and optimal multi-dimensional clustering

点击翻译按钮获取中文摘要

Pattern recognition (PR) is a field of artificial intelligence, which involves the process of taking raw data and making a decision to assign a sample to a category or class. PR systems have been extensively studied by researchers for many years, in both theoretical and application aspects - the latter includes a variety of disciplines such as medicine, molecular biology, bioinformatics, genomics, proteomics, biometrics, security and manufacturing, just to mention a few. The essence of a PR system is to devise and evaluate an efficient classifier which is able to accurately classify unknown objects. Whether or not the classes are known, the recognition process is called supervised or unsupervised. In any case, devising a classifier requires the underlying objects be represented by means of features, typically, as multi-dimensional vectors, and the underlying classifiers are derived in terms of functions or algorithms on the corresponding multi-dimensional space.