Yo-Ping Huang

Survey of fraud detection techniques

Due to the dramatic increase of fraud which results in loss of billions of dollars worldwide each year, several modern techniques in detecting fraud are continually developed and applied to many business fields. Fraud detection involves monitoring the behavior of populations of users in order to estimate, detect, or avoid undesirable behavior. Undesirable behavior is a broad term including delinquency, fraud, intrusion, and account defaulting. This paper presents a survey of current techniques used in credit card fraud detection, telecommunication fraud detection, and computer intrusion detection. The goal of this paper is to provide a comprehensive review of different techniques to detect frauds.

The integration and application of fuzzy and grey modeling methods

Abstract An integrated fuzzy and grey model and its applications to the prediction control problems are presented. The basic grey model GM(1,1) is accompanied with the adaptive fuzzy method to improve its prediction capability. The gradient descent scheme is applied to the fuzzy rules to determine whether the predicted results from the grey model should be adjusted. The quantity of adjustment is judged from the degrees of the correlation between the past data and the current input. We select a few most correlated patterns to decide the direction of adjustment. Due to the simplicity of the structure and its fast learning characteristics, this model is good as a real-time controller. Under the proposed methodology, the simulation results are shown to be superior to those systems which exploit complicated control variables and rules. A well-known difference equation and the weather forecast prediction problems are depicted to verify the superiority of the proposed method.

A template-based model for license plate recognition

Using video camera to manage the cars is gradually adopted in many lands of applications, such as electric payment in the tailgate and car parking management. An automatic recognition model of automobiles license plate number is proposed in this paper. The designed system is expected to have high recognition accuracy and reliability such that the goal of automatic recognition can be achieved. We present a system to recognize the license number in the acquired image captured from a video camera. The recognition process of our system contains four major steps. First, the system tries to locate the probable position of the license plate within the acquired image by using gradient analysis and image processing. Second, our model estimates the image parameters needed to normalize the license plate and uses the cross-correlation to detect the skew of the license plate and rectify the tilt. Third, we use a template technique to recognize the characters in the license plate. Finally, we use the information gained from the previous step to analyze the probable license numbers. We illustrate the designing processes and give the experimental results from the proposed model. Based on the experimental results, the proposed system can effectively recognize the license number. The time needed to recognize a license plate takes only 1.5 seconds.

The hybrid grey-based models for temperature prediction

In this paper several grey-based models are applied to temperature prediction problems. Standard normal distribution, linear regression, and fuzzy techniques are respectively integrated into the grey model to enhance the embedded GM(1, 1), a single variable first order grey model, prediction capability. The original data are preprocessed by the statistical method of standard normal distribution such that they will become normally distributed with a mean of zero and a standard deviation of one. The normalized data are then used to construct the grey model. Due to the inherent error between the predicted and actual outputs, the grey model is further supplemented by either the linear regression or fuzzy method or both to improve the prediction accuracy. Results from predicting the monthly temperatures for two different cities demonstrate that each proposed hybrid methodology can somewhat reduce the prediction errors. When both the statistics and fuzzy methods are incorporated with the grey model, the prediction capability of the hybrid model is quite satisfactory. We repeat the prediction problems in neural networks and the results are also presented for comparison.

Real-valued genetic algorithms for fuzzy grey prediction system

Abstract A genetic-based fuzzy grey prediction model is proposed in this paper. Instead of working on the conventional bit by bit operation, both the crossover and mutation operators are real-valued handled by the presented algorithms. To prevent the system from turning into a premature problem, we select the elitists from two groups of possible solutions to reproduce the new populations. To verify the effectiveness of the proposed genetic algorithms, two simple functions are first tested. The results show that our method outperforms the conventional one no matter whether from the viewpoint of the number of iterations required to find the optimum solutions or from the final solutions obtained. The real-valued genetic algorithms are then exploited to optimize the fuzzy controller which is designed to perform the compensation job. Two different types of fuzzy inference rules are considered to compensate for the predicted errors from the grey model. The difficulty encountered in applying the genetic algorithms to adjusting the fuzzy parameters is also discussed. Based on the simulation results from the problems of the weather forecast, we found that the proposed methodology is very effective in determining the quantity of compensation for the predicted outputs from the traditional grey approach.

An intelligent strategy for checking the annual inspection status of motorcycles based on license plate recognition

License plate recognition techniques have been successfully applied to the management of stolen cars, management of parking lots and traffic flow control. This study proposes a license plate based strategy for checking the annual inspection status of motorcycles from images taken along the roadside and at designated inspection stations. Both a UMPC (Ultra Mobile Personal Computer) with a web camera and a desktop PC are used as hardware platforms. The license plate locations in images are identified by means of integrated horizontal and vertical projections that are scanned using a search window. Moreover, a character recovery method is exploited to enhance the success rate. Character recognition is achieved using both a back propagation artificial neural network and feature matching. The identified license plate can then be compared with entries in a database to check the inspection status of the motorcycle. Experiments yield a recognition rate of 95.7% and 93.9% based on roadside and inspection station test images, respectively. It takes less than 1s on a UMPC (Celeron 900MHz with 256MB memory) and about 293ms on a PC (Intel Pentium 4 3.0GHz with 1GB memory) to correctly recognize a license plate. Challenges associated with recognizing license plates from roadside and designated inspection stations images are also discussed.

Ubiquitous information transfer across different platforms by QR codes

In this paper we present an event driven surveillance system that uses multiple cameras. The purpose of this system is to enable thorough exploration of surveillance events. The system uses a client-server web architecture as this provides scalability for further development of the system infrastructure. The system is designed to be accessed by surveillance operators who can review and comment on events generated by our event detection processing modules. We do not just focus on event detection, but are working towards the optimization of event detection. A multiple camera network system that tracks a moving object (or person) and decides if this is an event of interest is also examined. Dynamic switching of the cameras is implemented to aid in human monitoring of the network. The camera displayed in the main view should be the camera with the most interesting activity occurring. Unusual activity is defined as activity occurring that is not of the norm. Normal activity is considered to be everyday repeated activity. Further thought will be given to the extension of this system into a distributed system that would effectively create an event web system. Our contributions are to the development of automated real-time switching of camera views to aid camera operators in the effort of effective video surveillance, and also the detection of events of interest within a surveillance environment, with appropriate alerts and storage of these events. To the best of our knowledge this system provides a novel approach to the technological surveillance paradigm.

The Role of Electronic Pocket Dictionaries as an English Learning Tool among Chinese Students

This study addressed the role of electronic pocket dictionaries as a language learning tool among university students in Hong Kong and Taiwan. The target groups included engineering and humanities students at both undergraduate and graduate level. Speed of reference was found to be the main motivator for using an electronic pocket dictionary. Next, the functionality used was found to be connected to the language proficiency of the learner. Finally, multimedia content was ranked least important. The results of this study have implications for the design of electronic dictionaries and for the teaching of second languages with electronic dictionaries. In particular, device developers should focus on improving the accessing speed and pay less attention to multimedia functionality. Educators should ensure that the device functionality matches the language proficiency level of the students.

A BACK PROPAGATION BASED REAL-TIME LICENSE PLATE RECOGNITION SYSTEM

License plate recognition systems have been used extensively for many applications including parking lot management, tollgate monitoring, and for the investigation of stolen vehicles. Most researches focus on static systems, which require a clear and level image to be taken of the license plate. However, the acquisition of images that can be successfully analyzed relies on both the location and movement of the target vehicle and the clarity of the environment. Moreover, only few studies have addressed the problems associated with instant car image processing. In view of these problems, a real-time license plate recognition system is proposed that recognizes the video frames taken from existing surveillance cameras. The proposed system finds the location of the license plate using projection analysis, and the characters are identified using a back propagation neural network. The strategy achieves a recognition rate of 85.8% and almost 100% after the neural network has been retrained using the erroneously recognized characters, respectively.

Decomposing banyan networks for performance analysis

A general form of input-destination distribution matrix increases state space exorbitantly, thus making any buffer at every state statistically different from another. Certain specific forms of input-destination distribution matrix to which many real-life cases may conform, are analyzed. The idea called decomposition is applied here for specific nonhomogeneous flows. State space is not allowed to increase significantly; also the reduction in network size at successive stages is utilized to increase the computational efficiency. >