Bing Quan Huang

Customer churn prediction in telecommunications

This paper presents a new set of features for land-line customer churn prediction, including 2 six-month Henley segmentation, precise 4-month call details, line information, bill and payment information, account information, demographic profiles, service orders, complain information, etc. Then the seven prediction techniques (Logistic Regressions, Linear Classifications, Naive Bayes, Decision Trees, Multilayer Perceptron Neural Networks, Support Vector Machines and the Evolutionary Data Mining Algorithm) are applied in customer churn as predictors, based on the new features. Finally, the comparative experiments were carried out to evaluate the new feature set and the seven modelling techniques for customer churn prediction. The experimental results show that the new features with the six modelling techniques are more effective than the existing ones for customer churn prediction in the telecommunication service field.

Multi-objective feature selection by using NSGA-II for customer churn prediction in telecommunications

This paper proposes a new multiobjective feature selection approach for churn prediction in telecommunication service field, based on the optimisation approach NSGA-II. The basic idea of this approach is to modify the approach NSGA-II to select local feature subsets of various sizes, and then to use the method of searching nondominated solutions to select the global nondominated feature subsets. Finally, the method FBSM which yields the fitness thresholds is proposed to choose the global solutions with the lowest ranks as the final solutions. In order to evaluate the proposed approach, experiments were carried out and the experimental results show that the proposed feature selection approach is efficient for churn prediction with multiobjectives.

Preprocessing Techniques for Online Handwriting Recognition

This paper proposes a new preprocessing technique for online handwriting. The approach is to first remove the hooks of the strokes by using changed-angle threshold with length threshold, then filter the noise by using a smoothing technique, which is the combination of the cubic spline and the equal-interpolation methods. Finally, the handwriting is normalised. Experiments are carried out using the benchmark UNIPEN database. The experimental results show that our preprocessing technique can improve the recognition rates by at least 10%.

A new feature set with new window techniques for customer churn prediction in land-line telecommunications

In order to improve the prediction rates of churn prediction in land-line telecommunication service field, this paper proposes a new set of features with three new input window techniques. The new features are demographic profiles, account information, grant information, Henley segmentation, aggregated call-details, line information, service orders, bill and payment history. The basic idea of the three input window techniques is to make the position order of some monthly aggregated call-detail features from previous months in the combined feature set for testing be as the same one as for training phase. For evaluating these new features and window techniques, the two most common modelling techniques (decision trees and multilayer perceptron neural networks) and one of the most promising approaches (support vector machines) are selected as predictors. The experimental results show that the new features with the new window techniques are efficient for churn prediction in land-line telecommunication service fields.

A Fast Feature Selection Model for Online Handwriting Symbol Recognition

Many feature selection models have been proposed for online handwriting recognition. However, most of them require expensive computational overhead, or inaccurately find an improper feature set which leads to unacceptable recognition rates. This paper presents a new efficient feature selection model for handwriting symbol recognition by using an improved sequential floating search method coupled with a hybrid classifier, which is obtained by combining hidden Markov models with multilayer forward network. The effectiveness of proposed method is verified by comprehensive experiments based on UNIPEN database

An efficient hybrid approach for online recognition of handwritten symbols

This paper presents an innovative hybrid approach for online recognition of handwritten symbols. The approach is composed of two main techniques. Firstly, fuzzy rules are used to extract a meaningful set of features from a handwritten symbol, and secondly a recurrent neural network uses the feature set as input to recognise the symbol. The extracted feature set is a set of basic shapes capturing what is distinctive about each symbol, thus making the networks classification task easier. We propose a new recurrent neural network architecture, associated with an efficient learning algorithm derived from the gradient descent method. We describe the network and explain the relationship between the network and the Markov chains. The approach has achieved high recognition rates using benchmark datasets from the Unipen database.

Leveraging IMU data for accurate exercise performance classification and musculoskeletal injury risk screening

Inertial measurement units (IMUs) are becoming increasingly prevalent as a method for low cost and portable biomechanical analysis. However, to date they have not been accepted into routine clinical practice. This is often due to a disconnect between translating the data collected by the sensors into meaningful and actionable information for end users. This paper outlines the work completed by our group in attempting to achieve this. We discuss the conceptual framework involved in our work, the methodological approach taken in analysing sensor signals and discuss possible application models. Our work indicates that IMU based systems have the potential to bridge the gap between laboratory and clinical movement analysis. Future studies will focus on collecting a diverse range of movement data and using more sophisticated data analysis techniques to refine systems.

The limb movement analysis of rehabilitation exercises using wearable inertial sensors

Due to no supervision of a therapist in home based exercise programs, inertial sensor based feedback systems which can accurately assess movement repetitions are urgently required. The synchronicity and the degrees of freedom both show that one movement might resemble another movement signal which is mixed in with another not precisely defined movement. Therefore, the data and feature selections are important for movement analysis. This paper explores the data and feature selection for the limb movement analysis of rehabilitation exercises. The results highlight that the classification accuracy is very sensitive to the mount location of the sensors. The results show that the use of 2 or 3 sensor units, the combination of acceleration and gyroscope data, and the feature sets combined by the statistical feature set with another type of feature, can significantly improve the classification accuracy rates. The results illustrate that acceleration data is more effective than gyroscope data for most of the movement analysis.

An agent-based negotiation approach for knowledge exchange in cloud service platforms

A number of cloud service platforms are targeting experts involved in vital decision-making activities that can lead, for example, governments to take precautions or healthcare professionals to perform specific operations. In order for these cloud platforms to operate there exist an underlying knowledge discovery engine that is employing a number of advanced data analytics techniques to derive insightful conclusions. The technical challenges facing designers and developers of such cloud architectures are increasing relatively with the sensitivity of the data in subject and the ranking of the addressees. In this paper, we investigate these challenges and examine the design approaches of these specific cloud service architectures. We propose an agent-based negotiation model for knowledge exchange among service architectures similar to those in subject.