Search

The paper proposes a novel hierarchical classification approach with dynamic-threshold SVM ensemble. At training phrase, hierarchical structure is explored to select suit positive and negative examples as training set in order to obtain better SVM classifiers. When predicting an unseen example, it is classified for all the label classes in a top-down way in hierarchical structure. Particulary, two strategies are proposed to determine dynamic prediction threshold for different label class, with hierarchical structure being utilized again. In four genomic data sets, experiments show that the selection policies of training set outperform existing two ones and two strategies of dynamic prediction threshold achieve better performance than the fixed thresholds. [ABSTRACT FROM AUTHOR]

Cultural heritage forms the local and national identities. It shapes relationships between neighbors and other communities around the world. The sweet wine named ˵Commandaria″ is part of Cypriot heritage and currently holds a protected destination of origin within European Union, USA and Canada. In the framework of the Commandaria project we managed to gather an enormous amount of data, related to Commandaria wine, corresponding to photographs, scanned documents and videos. The need of a method for efficient retrieval of these data based on their actual content was mandatory. The data were appropriately indexed through a multilevel labeling scheme allowing access from various modalities and for a variety of applications. Despite the huge efforts for automatic characterization and classification human intervention is the only way for reliable multimedia data annotation. Manual data annotation is an extremely laborious process and efficient tools developed for this purpose can make, in many cases, the true difference. In this paper we present the CulHIAT, a cultural heritage item annotation tool, which uses structured knowledge, in the form of XML dictionaries, combined with a hierarchical classification scheme, to attach semantic labels to image and video segments at various levels of granularity. Finally, XML dictionary creation and editing tools are available during annotation allowing the user to always use the semantic label she/he wishes instead of the automatically created ones. [ABSTRACT FROM AUTHOR]

As the data bases grow bigger, the data mining becomes more and more important. In order to explore and understand the data, the help of computers and data mining methods, like clustering, is a necessity. This paper introduces some information theory based distances and how they can be used for clustering. More precisely, we want to classify a finite set of discrete random variables. This classification has to be based on the correlation between these random variables. In the design of a clustering system, the choice of the notion of distance is crucial, some information distances and classification methods are provided. We also show that in order to have distances over clusters, the variables that are functions of other variables have to be removed from the starting set. The last part gives some applications run on Matlab. [ABSTRACT FROM AUTHOR]

This paper proposes a novel Ant Colony Optimisation algorithm for the hierarchical problem of predicting protein functions using the Gene Ontology (GO). The GO structure represents a challenging case of hierarchical classification, since its terms are organised in a direct acyclic graph fashion where a term can have more than one parent – in contrast to only one parent in tree structures. The proposed method discovers an ordered list of classification rules which is able to predict all GO terms independently of their level. We have compared the proposed method against a baseline method, which consists of training classifiers for each GO terms individually, in five different ion-channel data sets and the results obtained are promising. [ABSTRACT FROM AUTHOR]

Recent advances in digital video technology have resulted in an explosion of digital video data which are available through the Web or in private repositories. Efficient searching in these repositories created the need of semantic labeling of video data at various levels of granularity, i.e., movie, scene, shot, keyframe, video object, etc. Through multilevel labeling video content is appropriately indexed, allowing access from various modalities and for a variety of applications. However, despite the huge efforts for automatic video annotation human intervention is the only way for reliable semantic video annotation. Manual video annotation is an extremely laborious process and efficient tools developed for this purpose can make, in many cases, the true difference. In this paper we present a video annotation tool, which uses structured knowledge, in the form of XML dictionaries, combined with a hierarchical classification scheme to attach semantic labels to video segments at various level of granularity. Video segmentation is supported through the use of an efficient shot detection algorithm; while shots are combined into scenes through clustering with the aid of a Genetic Algorithm scheme. Finally, XML dictionary creation and editing tools are available during annotation allowing the user to always use the semantic label she/he wishes instead of the automatically created ones. [ABSTRACT FROM AUTHOR]

In this paper, a novel method for web page hierarchical classification is addressed. In our approach, SVM is used as the basic algorithm to separate any two sub-categories under the same parent node. In order to alleviate the ill shift of SVM classifier caused by imbalanced training data, we try to combine the original SVM classifier with BEV algorithm to create classifier called VOTEM. Then, a web document is assigned to a sub-category based on voting from all category-to-category classifiers. This hierarchical classification algorithm starts its work from the top of the hierarchical tree downward recursively until it triggers a stop condition or reaches the leaf nodes. And our experiment reveals that proposed algorithm obtains better results. [ABSTRACT FROM AUTHOR]

In this paper we propose a new method to improve the performance of hierarchical classification. We use a swarm intelligence algorithm to select the type of classification algorithm to be used at each ˵classifier node″ in a classifier tree. These classifier nodes are used in a top-down divide and conquer fashion to classify the examples from hierarchical data sets. In this paper we propose a swarm intelligence based approach which attempts to mitigate a major drawback with a recently proposed local search-based, greedy algorithm. Our swarm intelligence based approach is able to take into account classifier interactions whereas the greedy algorithm is not. We evaluate our proposed method against the greedy method in four challenging bioinformatics data sets and find that, overall, there is a significant increase in performance. [ABSTRACT FROM AUTHOR]

Data models that are induced in classifier construction often consist of multiple parts, each of which explains part of the data. Classification methods for such multi-part models are called multimodal classification methods. The model parts may overlap or have insufficient coverage. How to deal best with the problems of overlapping and insufficient coverage? In this paper we propose a hierarchical or layered approach to this problem. Rather than seeking a single model, we consider a series of models under gradually relaxing conditions, which form a hierarchical structure. To demonstrate the effectiveness of this approach we consider two classifiers that construct multi-part models – one based on the so-called lattice machine and the other one based on rough set rule induction, and we design hierarchical versions of the two classifiers. The two hierarchical classifiers are compared through experiments with their non-hierarchical counterparts, and also with a method that combines k-nearest neighbors classifier with rough set rule induction as a benchmark. The results of the experiments show that this hierarchical approach leads to improved multimodal classifiers. [ABSTRACT FROM AUTHOR]