Zeng / Wang Advances in Neural Network Research and Applications

1. Auflage 2010
ISBN: 978-3-642-12990-2
Verlag: Springer
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, Band 67, 936 Seiten, eBook

Reihe: Lecture Notes in Electrical Engineering

This book is a part of the Proceedings of the Seventh International Symposium on Neural Networks (ISNN 2010), held on June 6-9, 2010 in Shanghai, China. Over the past few years, ISNN has matured into a well-established premier international symposium on neural networks and related fields, with a successful sequence of ISNN series in Dalian (2004), Chongqing (2005), Chengdu (2006), Nanjing (2007), Beijing (2008), and Wuhan (2009). Following the tradition of ISNN series, ISNN 2010 provided a high-level international forum for scientists, engineers, and educators to present the state-of-the-art research in neural networks and related fields, and also discuss the major opportunities and challenges of future neural network research. Over the past decades, the neural network community has witnessed significant breakthroughs and developments from all aspects of neural network research, including theoretical foundations, architectures, and network organizations, modeling and simulation, empirical studies, as well as a wide range of applications across different domains. The recent developments of science and technology, including neuroscience, computer science, cognitive science, nano-technologies and engineering design, among others, has provided significant new understandings and technological solutions to move the neural network research toward the development of complex, large scale, and networked brain-like intelligent systems. This long-term goals can only be achieved with the continuous efforts from the community to seriously investigate various issues on neural networks and related topics.

Zielgruppe

Research

Autoren/Hrsg.

Zeng, Zhigang

Wang, Jun

Inhaltsverzeichnis

Prediction and Forecasting.- Fuzzy Neural Networks.- Optimization and Planning.- Pattern Recognition.- Signal and Image Processing.- Robotics and Control.- Transportation Systems.- Industrial Applications.- Real-World Applications.

Leseproben

"A Novel Prediction Mechanism with Modified Data Mining Technique for Call Admission Control in Wireless Cellular Network (S. 1-2)

Abstract. It is an important issue to allocate appropriate resources to mobile calls for wireless cellular networks owe to scarce wireless spectrums. The call admission control (CAC) will maintain better performance metrics of mobile call such as call dropping probability (CDP) and call blocking probability (CBP) if the future utilization of wireless spectrums can be predicted and provided to the decision of CAC. Therefore, a prediction mechanism which can predict most information such as system utilization is proposed in this paper.

The techniques of data mining and pattern matching which adopts gradient to fuzz time series data for representations of chain code are applied to mining a possible repetitive pattern. Our proposed prediction mechanism can provide prediction information in advance whether the repetitive time series pattern of information exists or not. Furthermore, an update of confident level will be conducted continuously for performing each prediction in the proposed scheme.

Our proposed mechanism is developed and tested with four cases which can be regarded as using scenarios of wireless cellular network. The experimental results show that the proposed scheme can capture repetitive time series patterns and perform following predictions with these repetitive time series patterns. Besides, the required storage is less than traditional schemes and lower computation power is required for the proposed scheme. Keywords: Call Admission Control (CAC), data mining, time series, pattern matching, prediction.

1 Introductions

Although there has been a rapid development in wireless cellular communications, the QoS guarantee remains one of the most challenging issues [1]. One of the key elements in providing QoS guarantees is an effective CAC policy, which not only has to ensure that the network meets the QoS of the newly arriving calls if accepted, but also guarantees that the QoS of the existing calls does not deteriorate. The variable user mobility has made that it becomes more complex to predict the appropriate cell for handoff.

The past research [2] showed the impact of mobility on cellular network and provided a modeling method for configuring cellular networks to study the dynamics of mobility. The improvement of radio bandwidth is always thought as a dynamic channel (code) allocation problem in literatures [3]. Although there were some schemes for bandwidth reservation proposed to reduce the CDP, such as the study [4], seldom literature has developed to satisfy QoS and lower CBP issues at the same time. Furthermore, the past researches mentioned at the above focused on individual mobility prediction, and they may cause mass load focusing on the MSC.

According to the study [5], final information is a prediction of users’ number in a given cell, and it leads to use a global approach that only observes variations of system utilization and users’ flows. There are many advantages for [5]: it does not require any control message and additional load for the MSC; cells generate their own statistics independently from others; it is sensitive to geographical constrains and to users’ common habits. According to [12], the final information is a quantity prediction of users in a given cell, and it leads to use a global approach that only observes variations of system utilization and users’ flows.

There are many advantages of the scheme presented in [12]: it does not require any control message and additional load for the MSC; cells generate their own statistics independently from others; it is sensitive to geographical constraints and to users’ common habits. Besides, the concept of aggregated history has been also applied to acquire user mobility profile in [13] so that a user mobility profile framework is developed for estimating service patterns and tracking mobile users, including descriptions of location, mobility, and service requirements. Therefore, in order to provide suitable statistical prediction information which may be system utilization, CBP, or other system resources to the CAC, a prediction mechanism which can predict most information is proposed in this paper."