Hong Kong Polytechnic University

About: Hong Kong Polytechnic University is a education organization based out in Hong Kong, China. It is known for research contribution in the topics: Computer science & Tourism. The organization has 29633 authors who have published 72136 publications receiving 1956312 citations. The organization is also known as: HKPU & PolyU.

TOEFL preparation courses: a study of washback:

Abstract: 'Washback' (sometimes also known as 'backwash') is the influence that writers on language testing, syllabus design and language teaching believe a test will have on the teaching that precedes it. Much has been written about the influence of testing on teaching. To date, however, little empirical evidence is available to support the assertions of either positive or negative washback.The English proficiency test TOEFL (Test of English as a Foreign Language: ETS) is among the best-known examinations in the field of ELT. The study reported in this article set out to investigate common claims that the TOEFL exerts an undesirable influence on language teaching. Our data consist of interviews with teachers and students, and observations made of two sorts of classes: 'normal' language proficiency classes, and parallel classes intended for students preparing to take the TOEFL. We observed both TOEFL preparation classes and non-TOEFL preparation classes by the same teachers in order to be able to separate washback ...

Customer churn prediction using improved balanced random forests

Abstract: Churn prediction is becoming a major focus of banks in China who wish to retain customers by satisfying their needs under resource constraints. In churn prediction, an important yet challenging problem is the imbalance in the data distribution. In this paper, we propose a novel learning method, called improved balanced random forests (IBRF), and demonstrate its application to churn prediction. We investigate the effectiveness of the standard random forests approach in predicting customer churn, while also integrating sampling techniques and cost-sensitive learning into the approach to achieve a better performance than most existing algorithms. The nature of IBRF is that the best features are iteratively learned by altering the class distribution and by putting higher penalties on misclassification of the minority class. We apply the method to a real bank customer churn data set. It is found to improve prediction accuracy significantly compared with other algorithms, such as artificial neural networks, decision trees, and class-weighted core support vector machines (CWC-SVM). Moreover, IBRF also produces better prediction results than other random forests algorithms such as balanced random forests and weighted random forests.

Neural network and genetic programming for modelling coastal algal blooms

Abstract: In the recent past, machine learning (ML) techniques such as artificial neural networks (ANN) have been increasingly used to model algal bloom dynamics. In the present paper, along with ANN, we select genetic programming (GP) for modelling and prediction of algal blooms in Tolo Harbour, Hong Kong. The study of the weights of the trained ANN and also the GP-evolved equations shows that they correctly identify the ecologically significant variables. Analysis of various ANN and GP scenarios indicates that good predictions of long-term trends in algal biomass can be obtained using only chlorophyll-a as input. The results indicate that the use of biweekly data can simulate long-term trends of algal biomass reasonably well, but it is not ideally suited to give short-term algal bloom predictions.

Evolutionary V2X Technologies Toward the Internet of Vehicles: Challenges and Opportunities

Abstract: To enable large-scale and ubiquitous automotive network access, traditional vehicle-to-everything (V2X) technologies are evolving to the Internet of Vehicles (IoV) for increasing demands on emerging advanced vehicular applications, such as intelligent transportation systems (ITS) and autonomous vehicles. In recent years, IoV technologies have been developed and achieved significant progress. However, it is still unclear what is the evolution path and what are the challenges and opportunities brought by IoV. For the aforementioned considerations, this article provides a thorough survey on the historical process and status quo of V2X technologies, as well as demonstration of emerging technology developing directions toward IoV. We first review the early stage when the dedicated short-range communications (DSRC) was issued as an important initial beginning and compared the cellular V2X with IEEE 802.11 V2X communications in terms of both the pros and cons. In addition, considering the advent of big data and cloud-edge regime, we highlight the key technical challenges and pinpoint the opportunities toward the big data-driven IoV and cloud-based IoV, respectively. We believe our comprehensive survey on evolutionary V2X technologies toward IoV can provide beneficial insights and inspirations for both academia and the IoV industry.

A Level Set Approach to Image Segmentation With Intensity Inhomogeneity

Abstract: It is often a difficult task to accurately segment images with intensity inhomogeneity, because most of representative algorithms are region-based that depend on intensity homogeneity of the interested object. In this paper, we present a novel level set method for image segmentation in the presence of intensity inhomogeneity. The inhomogeneous objects are modeled as Gaussian distributions of different means and variances in which a sliding window is used to map the original image into another domain, where the intensity distribution of each object is still Gaussian but better separated. The means of the Gaussian distributions in the transformed domain can be adaptively estimated by multiplying a bias field with the original signal within the window. A maximum likelihood energy functional is then defined on the whole image region, which combines the bias field, the level set function, and the piecewise constant function approximating the true image signal. The proposed level set method can be directly applied to simultaneous segmentation and bias correction for 3 and 7T magnetic resonance images. Extensive evaluation on synthetic and real-images demonstrate the superiority of the proposed method over other representative algorithms.