Skyline Computation for Low-Latency Image-Activated Cell Identification

摘要

Because of breakthroughs in the field of deep learning, the accuracy of image classification and multimedia recognition in Artificial Intelligence (AI) research has improved rapidly. In this study, the objective is the classification of high-dimensional data, and, in particular, the screening of very rare entries from a large population. In general, the initial set of vectors is divided into several groups by using a clustering method, and an outlier detection method identifies distinct entries such as noise. Our focus is on a new cognitive research problem in which the aim is to detect boundary entries, namely entries that are geometrically located near the outer edges of a population in multidimensional space.