Automatically discovering fatigue patterns from sparsely labelled temporal data

In many problems, we would like to find relation between data and description. However, this description, or label information, may not always be explicitly associated with the data. In this paper, we deal with the data with incomplete label information. In other words, the label only represents a general concept of a bag of data vectors instead of a specific information of one data vector. Our approach assumed that the feature vectors generated from the bag of data can be partitioned into baglabel relevant and irrelevant parts. Under this assumption, we give an algorithm that allows for efficiently extracting meaningful features from a large pool of features, and learning a multipleinstance based predictor. We applied our algorithm to the monkey fixation data to predict the monkeys' quit behavior. Our algorithm outperforms other standard classification methods such as binary classifier and one-class classifier. In addition, the microsaccade is interpreted from a large set of features using our method. We find that it is the most effective element to predict the quit behavior.