In this paper, we propose phraseNet, a neural machine translator with a phrase memory which stores phrase pairs in symbolic form, mined from corpus or specified by human experts. For any given source sentence, phraseNet scans the phrase memory to determine the candidate phrase pairs and integrates tagging information in the representation of source sentence accordingly. The decoder utilizes a mixture of word-generating component and phrase-generating component, with a specifically designed strategy to generate a sequence of multiple words all at once. The phraseNet not only approaches one step towards incorporating external knowledge into neural machine translation, but also makes an effort to extend the word-by-word generation mechanism of recurrent neural network. Our empirical study on Chinese-to-English translation shows that, with carefully-chosen phrase table in memory, phraseNet yields 3.45 BLEU improvement over the generic neural machine translator.
Hemoglobinopathies are the most common monogenic disorders worldwide. Substantial effort has been made to establish databases to record complete mutation spectra causing or modifying this group of diseases. We present a variant database which couples an online auxiliary diagnosis and at‐risk assessment system for hemoglobinopathies (DASH). The database was integrated into the Leiden Open Variation Database (LOVD), in which we included all reported variants focusing on a Chinese population by literature peer review‐curation and existing databases, such as HbVar and IthaGenes. In addition, comprehensive mutation data generated by high‐throughput sequencing of 2,087 hemoglobinopathy patients and 20,222 general individuals from southern China were also incorporated into the database. These sequencing data enabled us to observe disease‐causing and modifier variants responsible for hemoglobinopathies in bulk. Currently, 371 unique variants have been recorded; 265 of 371 were described as disease‐causing variants, whereas 106 were defined as modifier variants, including 34 functional variants identified by a quantitative trait association study of this high‐throughput sequencing data. Due to the availability of a comprehensive phenotype‐genotype data set, DASH has been established to automatically provide accurate suggestions on diagnosis and genetic counseling of hemoglobinopathies. LOVD‐DASH will inspire us to deal with clinical genotyping and molecular screening for other Mendelian disorders.
The support vector machine has received wide acceptance for its high generalization ability in real world classification applications. But a drawback is that it uniquely classifies each pattern to one class or none. This is not appropriate to be applied in classification problem involves overlapping patterns. In this paper, a novel multi-model classifier (DR-SVM) which combines SVM classifier with kNN algorithm under rough set technique is proposed. Instead of classifying the patterns directly, patterns lying in the overlapped region are extracted firstly. Then, upper and lower approximations of each class are defined on the basis of rough set technique. The classification operation is carried out on these new sets. Simulation results on synthetic data set and benchmark data sets indicate that, compared with conventional classifiers, more reasonable and accurate information about the pattern's category could be obtained by use of DR-SVM.
Support vector machine(SVM) has become a powerful and widely used machine learning method in resent years. Gaussian kernel is the most commonly used kernel function. However, model selection including setting the width parameter σ in kernel function and the regularization parameter C is essential to generalization performance of SVM. In this paper we proposed a new parameter selection method for Support Vector Machine. The key idea of our method MSKD in selecting the gaussian kernel parameter is that convergent character between pattern's similarity measurement in feature space will decrease the classification ability of SVM. In addition, We combined MSKD algorithm with one-dimension search strategy based on cross-validation and developed a complex parameters selection method named MSKD-GS. Experiments on eight real world data sets from UCI have been carried out to demonstrate the effectiveness and efficiency of this method.978-1-4244-2765-9/09/$25.00 ©2009 IEEE
To solve the problem of battery capacity degradation caused by high current magnitudes and frequent current variations in electric vehicles (EVs), a hybrid energy storage system (HESS) incorporating high energy density storage (battery) and high power density storage (ultracapacitor) is proposed. The HESS contains a multi-port DC-DC converter, which controls the energy flow among the battery pack, the ultracapacitor (UC) pack, and the port of output. Considering the state of charge (SOC) of UC, the speed, and demand power of EV, an energy management strategy (EMS) based on fuzzy logic control (FLC) for the HESS is proposed in this paper. According to the strategy, the battery pack serves as a base power source while the UC pack serves as a transient power source so as to smooth the battery pack current and prolong the battery life. Simulation and experiment results illustrate the effectiveness of the proposed strategy for UC/battery HESS in EVs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.