Arabic speech recognition suffers from the scarcity of properly labeled data. In this project, we introduce a pipeline that performs semi-supervised segmentation of audio then— after hand-labeling a small dataset—feeds labeled segments to a supervised learning framework to select, through many rounds of hyperparameter optimization, an ensemble of models to infer labels for a larger dataset; usi...

Social network service (SNS) is a new emerging Web application. With the growth of SNS in application, the web security is facing more serious threats and the leak of individual privacy is a major one. Because of vast number of unlabeled data and small amount of labeled data in SNS web, the availability of data is relatively poor for the study of SNS privacy preservation. In order to solve the ...

Inconsistency and a lack of reproducibility are commonly associated with semi-automated segmentation methods. In this study, we developed an ensemble approach to improve reproducibility and applied it to glioblastoma multiforme (GBM) brain tumor segmentation on T1-weigted contrast enhanced MR volumes. The proposed approach combines samplingbased simulations and ensemble segmentation into a sing...

There are many challenges in mining data streams, such as infinite length, evolving nature and lack of labeled instances. Accordingly, a semi-supervised ensemble approach for mining data streams is presented in this paper. Data streams are divided into data chunks to deal with the infinite length. An ensemble classification model E is trained with existing labeled data chunks and decision bound...

Classifier ensemble generally should combine diverse component classifiers. However, it is difficult to give a definitive connection between diversity measure and ensemble accuracy. Given a list of available component classifiers, how to adaptively and diversely ensemble classifiers becomes a big challenge in the literature. In this paper, we argue that diversity, not direct diversity on sample...

We present a simulation method to assess the quasistatic fracture resistance of materials. Set within semi-grand-canonical Monte Carlo (SGCMC) environment, an auxiliary field---the bond rupture potential---is introduced generate sufficiently large number possible microstates in ensemble, and associated energy fluctuations. The SGCMC approach permits identifying full phase diagram brittle for ha...

Carbon uptake by terrestrial ecosystems is increasing along with the rising of atmospheric CO2 concentration. Embedded in this trend, recent studies suggested that the interannual variability (IAV) of global carbon fluxes may be dominated by semi-arid ecosystems, but the underlying mechanisms of this high variability in these specific regions are not well known. Here we derive an ensemble of gr...

Semi-supervised learning has been recognized as an effective way to improve acoustic model training in cases where sufficient transcribed data are not available. Different from most of existing approaches only using single acoustic model and focusing on how to refine it, this paper investigates the feasibility of using ensemble methods for semi-supervised acoustic modeling training. Two methods...