Attention can be directed at features and feature dimensions to facilitate perception. Here, we investigated whether feature-based-attention (FBA) can also dynamically weight feature-specific representations within multi-feature objects held in visual working memory (VWM). Across three experiments, participants retained coloured arrows in working memory and, during the delay, were cued to eithe...

Protein subcellular localization prediction plays an important role for understanding the functions and biological processes that proteins are involved in. By using protein sequence information, we can predict where a protein belongs to. In this paper, we propose a new linear classifier for predicting subcellular localizations of proteins using improved features extracted from protein sequences...

Recommender systems have been emerging as a powerful technique of e-commerce. The majority of existing recommender systems uses an overall rating value on items for evaluating user’s preference opinions. Because users might express their opinions based on some specific features of the item, recommender systems solely based on a single criterion could produce recommendations that do not meet use...

In action recognition recently prototype-based classification methods became popular. However, such methods, even showing competitive classification results, are often limited due to too simple and thus insufficient representations and require a long-term analysis. To compensate these problems we propose to use more sophisticated features and an efficient prototype-based representation allowing...

Feature extraction is the important prerequisite of classifying text effectively and automatically. TF· IDF is widely used to express the text feature weight. But it has some problems. TF•IDF can’t reflect the distribution of terms in the text, and then can’t reflect the importance degree and the difference between categories. This paper proposes a new feature weighting method—TF•IDF•Ci to whic...

In a real-world data set there is always the possibility, rather high in our opinion, that different features may have different degrees of relevance. Most machine learning algorithms deal with this fact by either selecting or deselecting features in the data preprocessing phase. However, we maintain that even among relevant features there may be different degrees of relevance, and this should ...