Gang Xiao

A methodology to support platform parameters determination through considering main factors in product life cycle

How to determine platform parameters properly is a key technique in product platform design, which is an effective tactic for mass customisation. First, product platform was defined as a set of modules, platform parameters and individual parameters. Modules and platform parameters embody economy of scale and individual parameters embody economy of scope. Second, a methodology about determining platform parameters, which considers seven factors such as design, die, machining, assembly, management, service and performance because different platform parameters result in different product scheme and would lead production change in product life cycle, was proposed. Third, an improved fuzzy comprehensive evaluation was employed to formalise the problem and arithmetic of determining platform parameters was also developed. Finally, the strategy and method are demonstrated applicable and effective in an instance of determining platform parameters for motorcycle-hydraulic-disk brake platform planning.

Vision-Based Perceptive Framework for Fish Motion

It is an intuitive and efficient method to monitor the water quality using the biological characteristics of aquatic organisms. The paper studies a vision-based perceptive framework for fish motion, of which some modules are studied, such as video data capture, moving object detection and multiple object tracking and so on. A multi-object tracking using particle filter with interacting observing model is proposed, and some related kinematical data, i.e., velocity and acceleration, are defined and analyzed to represent the real-time fish activity. The experimental results show that it is efficient and accurate.

Spam Filtering Method Based on an Artificial Immune System

This paper presents a spam immune method to effectively filter the unsolicited email messages. The idea is to classify messages using the trained antibodies, which are produced by the artificial immune system based on the gene fragment library. The approach focuses on the libraries used to generate the detectors, the training of antibody and the filtering application. The experimental results show the spam filtering is accurate and effective.

Recognition approach for ballot symbol based on run features: Recognition approach for ballot symbol based on run features

Recognition of hand-written ballot symbols is crucial in vote-counting system based on image understanding.To improve the accuracy of ballot symbol recognition,a symbol recognition approach based on run feature was proposed.Firstly,the concept of run was presented and a discriminant model was established based on run features of ballot symbols.Secondly,the relative positions of runs were described with a ternary tree.In addition,the main run regions were extracted in noisy environment by merging run regions,and an approach of recognizing ambiguous symbols was also given.Finally,the experimental results show that the run features can accurately reflect the geometrical features of ballot symbols.The proposed approach achieves high accuracy,and its accuracy is 6.07% higher than that of template matching algorithm.

A Rapid Vote-Counting System Based on Image Understanding

This paper proposes a system, which can rapidly count votes in traditional elections based on image understanding. Firstly, the system gets ballot images through high-speed scanner and preprocesses the images. Then, it recognizes the geometric structure and layout of ballot image through detecting table lines. In addition, it also recognizes the logical structure of ballot image through analyzing the relative positions of candidates and vote symbols. Thirdly, it locates candidates and symbols on the ballot table, and recognizes the specific symbols based on run features. The system has been implemented, which shows high counting speed, high recognition accuracy with wide applicability.