Earticle

In this paper, on the basis of traditional phonetics, by using the methods of experimental phonetics and voice pattern theory, Analyzed and summarized the vowel pattern of the monosyllables in Uyghur language. The statistical analysis is carried upon the vowel formant frequency values in monosyllables, and discussed by using Joos method in more details. For the first time, with the actual experimental data proves the accordance of tongue location features of Uyghur vowel with the traditional knowledge from hearsay. The research results of this paper will have a high reference value for the study and application development of both Uyghur language and the other languages are belongs Altaic language family.

Educational data mining has received considerable attention in the last few years. Many data mining techniques are proposed to extract the hidden knowledge from educational data. The extracted knowledge helps the institutions to improve their teaching methods and learning process. All these improvements lead to enhance the performance of the students and the overall educational outputs. In this paper, we propose a new student’s performance prediction model based on data mining techniques with new data attributes/features, which are called student’s behavioral features. These type of features are related to the learner’s interactivity with the e-learning management system. The performance of student’s predictive model is evaluated by set of classifiers, namely; Artificial Neural Network, Naïve Bayesian and Decision tree. In addition, we applied ensemble methods to improve the performance of these classifiers. We used Bagging, Boosting and Random Forest (RF), which are the common ensemble methods used in the literature. The obtained results reveal that there is a strong relationship between learner’s behaviors and their academic achievement. The accuracy of the proposed model using behavioral features achieved up to 22.1% improvement comparing to the results when removing such features and it achieved up to 25.8% accuracy improvement using ensemble methods. By testing the model using newcomer students, the achieved accuracy is more than 80%. This result proves the reliability of the proposed model.

As the starting age of English education becomes younger around the world where they teach English as a foreign language, the debate on early English education is an unsettling issue as not only academic research, but also educational policy. To resolve the unsettled issues, a new approach is used: the big data and its analytics. To explore the pros and cons of the early English education, the study uses the analysis of research abstracts collected from scholars.google.com and www.kci.go.kr. It also analyzes the data posted on the discussion sites such as agora, daum café and naver café, plus daily interactions of the early English education using SNS. The study uses opinion mining technique using tools such as Sisense and WEKA to lay out the data and analyze them as basic data analytics. The results show that pro early English education is commonly co-occur with critical period, lateralization, ultimate attainment, universal grammar, fossili-zation, inhibition, acquisition process, bilingualism and exposition. Essays against early English education are related to no critical period, no authentic input, not effective, no universal grammar, national identity loss, self-identity loss and L2 interference. Other extraneous factors are based on practical problems such as social pressure, outcome pressure, political pressure, test reform and statistics.

Increasing access to large-scale, high-dimensional and non-stationary streams in many real applications has made it necessary to design new dynamic classification algorithms. Most existing approaches for the textual stream classification are able to train the model relying on labeled data. However, only a limited number of instances can be labeled in a real streaming environment since large-scale data appear at a high speed. Therefore, it is useful to make unlabeled instances available for training and updating the ensemble models. In this paper, we present a new ensemble framework with partial labeled instances for learning from the textual stream. A new semi-supervised cluster-based classifier is proposed as the sub-classifier in our approach. In order to integrate these sub-classifiers, we propose an adaptive selection method. Empirical evaluation of textual streams reveals that our approach outperforms state-of-the-art stream classification algorithms.

With the rapid development of modern information technology, especially the development of the Internet, network brings a vast amount of data and information. The development of information technology has changed the education and learning methods, greatly improving our work and study efficiency. In this paper, the author analyzes the college wushu teaching reform based on multimedia technology. Based on multimedia platform, this paper constructs the martial arts teaching activities under the background of modern technology. This system realizes the combination of multimedia technology and the martial arts curriculum structure, content, and resources; it changes the traditional classroom teaching mode, and will improve the students' enthusiasm in wushu teaching.

Machine learning is ideal for exploiting the opportunities hidden in big data. It delivers on the promise of extracting value from big and disparate data sources with far less reliance on human direction. It is data driven and runs at machine scale. It is well suited to the complexity of dealing with disparate data sources and the huge variety of variables and amounts of data involved. And unlike traditional analysis, machine learning thrives on growing datasets. The more data fed into a machine learning system, the more it can learn and apply the results to higher quality insights. In this paper we propose a robust machine learning approach for dealing with large data set. Through experimental results, proposed method performs well on large data sets.

This paper presents a data-driven methodology to disambiguate a query by suggesting relevant subcategories within a specific domain. This is achieved by finding correlations between the user’s search history and the context of the current search keyword. We apply automatic categorization on each query to identify a list of categories which can describe the query given. To predict the categories of a user input query, we employed machine learning algorithms. We present the preliminary evaluation results and conclude with future work.

Cloud computing is regarded as a new computing mode in recent years, and has been widely applied. Its task scheduling affects the performance of the cloud computing system directly, and people pay more and more attention to the security problems of cloud computing. The paper introduces the trust in scheduling algorithm, improves and fuses the PSO and SA in order to make them complementary. By applying that to the task scheduling strategy of cloud computing, we can get a higher scheduling efficiency. We implement the proposed algorithm and verify its high efficiency through the simulation platform (CloudSim).

Summaries or abstracts available with medical articles are useful for the physicians, medical students and patients to know rapidly what is the article about and decide whether articles are suitable for in-depth study. Since all medical text documents do not come with author written abstracts or summaries, an automatic medical text summarization system can facilitate rapid medical information access on the web. We approach the problem of automatically generating summary from medical article as a supervised learning task. We treat a document as a set of sentences, which the learning algorithm must learn to classify as positive or negative examples of sentences based on summary worthiness of the sentences. We apply the machine learning algorithm called bagging to this learning task, where a C4.5 decision tree has been chosen as the base learner. We also compare the proposed approach to some existing summarization approaches.

This article comprises a review of various sequential algorithms. The review represents the working nature of the learning methods. It also includes the methods such as Minimal Resource Allocation Network (MRAN), Extreme Learning Machine (ELM), Self-regulated Resource Allocation Network (SRAN) and Meta-Cognitive Neural Network (MCNN) for real –valued neural network. Projection Based Learning with Meta-Cognitive Radial Basis Function Network (PBL-McRBFN) for complex valued neural network. Finally about Meta-Cognitive Fuzzy Inference System (MCFIS) using the Neuro - Fuzzy inference system for learning. The previously said SRAN works on the basis of self – regulatory mechanism in order to reduce the huge loss error and to maximize the class – wise significance. The methods such as MCNN, PBL-McRBFN and MCFIS execute on the human learning strategies such as what – to-learn, when –to-learn and how –to – learn. This review helps to select the learning methods suitable for the data that is to be classified.