In this study, we propose an improved semi-supervised support vector machine (SVM) based translation algorithm for brain-computer interface (BCI) systems, aiming at reducing the time-consuming training process and enh...
详细信息
ISBN:
(纸本)0769525210
In this study, we propose an improved semi-supervised support vector machine (SVM) based translation algorithm for brain-computer interface (BCI) systems, aiming at reducing the time-consuming training process and enhancing the adaptability of BCI systems. In this algorithm, we apply a semi-supervised SVM, which builds a SVM classifier based on small amounts of labeled data and large amounts of unlabeled data, to translating the features extracted from the electrical recordings of brain into control signals. For reducing the time to train the semi-supervised SVM, we improve it by introducing a batch-mode incremental training method, which also can be used to enhance the adaptability of online BCI systems. the off-line data analysis results demonstrated the effectiveness of our algorithm
Ontology is a crucial building block of semantic web, which is accepted as the most advanced knowledge representation model. But ontology learning is a big obstacle for its complexity and labor-denseness. We use rule-...
详细信息
Ontology is a crucial building block of semantic web, which is accepted as the most advanced knowledge representation model. But ontology learning is a big obstacle for its complexity and labor-denseness. We use rule-based information extraction (IE) to get instances from text. there is great challenge for the adaptivity of IE for ontology learning, so we put forward RGA-CIE - a rule generation algorithm which applies supervised learning with bottom-up strategy. RGA-CIE is a rule generalization process with a heuristic method to decide rule generalization path and laplacian* formula to evaluate the performance of rules. Empirical results show that our approach does be of use in learning of ontology instances.
Missing value imputation is an actual yet challenging issue confronted by machinelearning and datamining. Existing missing value imputation is a procedure that replaces the missing values in a dataset by some plausi...
详细信息
Missing value imputation is an actual yet challenging issue confronted by machinelearning and datamining. Existing missing value imputation is a procedure that replaces the missing values in a dataset by some plausible values. the plausible values are generally generated from the dataset using a deterministic, or random method. In this paper we propose a new and efficient missing value imputation based on data clustering, called CRI (clustering-based random imputation). In our approach, we fill up the missing values of an instance withthose plausible values that are generated from the data similar to this instance using a kernel-based random method. Specifically, we first divide the dataset (exclude instances with missing values) into clusters. And then each of those instances with missing-values is assigned to a cluster most similar to it. Finally, missing values of an instance A are thus patched up withthose plausible values that are generated using a kernel-based method to those instances from A's cluster. Our experiments (some of them are withthe decision tree induction system C 5.0) have proved the effectiveness of our proposed method in missing value imputation task.
By identifying characteristic regions in which classes are dense and also relevant for discrimination a new, intuitive classification method is set up. this method enables a visualized result so the user is provided w...
详细信息
ISBN:
(纸本)3540269231
By identifying characteristic regions in which classes are dense and also relevant for discrimination a new, intuitive classification method is set up. this method enables a visualized result so the user is provided with an insight into the data with respect to discrimination for an easy interpretation. Additionally, it outperforms Decision trees in a lot of situations and is robust against outliers and missing values.
In this work, we proposes a novel method for mining frequent disjunctive patterns on single data sequence. For this purpose, we introduce a sophisticated measure that satisfies anti-monotonicity, by which we can discu...
详细信息
ISBN:
(纸本)3540269231
In this work, we proposes a novel method for mining frequent disjunctive patterns on single data sequence. For this purpose, we introduce a sophisticated measure that satisfies anti-monotonicity, by which we can discuss efficient mining algorithm based on APRIORI. We discuss some experimental results.
Support Vector machines have received considerable attention from the patternrecognition community in recent years. they have been applied to various classical recognition problems achieving comparable or even superi...
详细信息
ISBN:
(纸本)3540269231
Support Vector machines have received considerable attention from the patternrecognition community in recent years. they have been applied to various classical recognition problems achieving comparable or even superior results to classifiers such as neural networks. We investigate the application of Support Vector machines (SVMs) to the problem of road recognition from remotely sensed images using edge-based features. We present very encouraging results from our experiments, which are comparable to decision tree and neural network classifiers.
this paper proposes an unsupervised algorithm for learning a finite Dirichlet mixture model. An important part of the unsupervised learning problem is determiningthe number of clusters which best describe the data. W...
详细信息
ISBN:
(纸本)3540269231
this paper proposes an unsupervised algorithm for learning a finite Dirichlet mixture model. An important part of the unsupervised learning problem is determiningthe number of clusters which best describe the data. We consider here the application of the Minimum Message length (MML) principle to determine the number of clusters. the Model is compared with results obtained by other selection criteria (AIC, MDL, MMDL, PC and a Bayesian method). the proposed method is validated by synthetic data and summarization of texture image database.
this article addresses the task of mining concepts from biomedical literature to index and search through this documents base. this research takes place within the Telemakus project, which has for goal to support and ...
详细信息
ISBN:
(纸本)3540269231
this article addresses the task of mining concepts from biomedical literature to index and search through this documents base. this research takes place within the Telemakus project, which has for goal to support and facilitate the knowledge discovery process by providing retrieval, visual, and interaction tools to mine and map research findings from research literature in the field of aging. A concept mining component automating research findings extraction such as the one presented here, would permit Telemakus to be efficiently applied to other domains. the main principle that has been followed in this project has been to mine from the legends of the documents the research findings as relationships between concepts from the medical literature. the concept mining proceeds through stages of syntactic analysis, semantic analysis, relationships building, and ranking.
We present how the supervised machinelearning techniques can be used to predict quality characteristics in an important chemical engineering application: the wine distillate maturation process. A number of experiment...
详细信息
ISBN:
(纸本)3540269231
We present how the supervised machinelearning techniques can be used to predict quality characteristics in an important chemical engineering application: the wine distillate maturation process. A number of experiments have been conducted with six regression-based algorithms, where the M5' algorithm was proved to be the most appropriate for predicting the organoleptic properties of the matured wine distillates. the rules that are exported by the algorithm are as accurate as human expert's decisions.
Research in protein structure and function is one of the most important subjects in modem bioinformatics and computational biology. It often uses advanced datamining and machinelearning methodologies to perform pred...
详细信息
ISBN:
(纸本)3540269231
Research in protein structure and function is one of the most important subjects in modem bioinformatics and computational biology. It often uses advanced datamining and machinelearning methodologies to perform prediction or patternrecognition tasks. this paper describes a new method for prediction of protein secondary structure content based on feature selection and multiple linear regression. the method develops a novel representation of primary protein sequences based on a large set of 495 features. the feature selection task performed using very large set of nearly 6,000 proteins, and tests performed on standard non-homologues protein sets confirm high quality of the developed solution. the application of feature selection and the novel representation resulted in 14-15% error rate reduction when compared to results achieved when standard representation is used. the prediction tests also show that a small set of 5-25 features is sufficient to achieve accurate prediction for both helix and strand content for non-homologous proteins.
暂无评论