This preview shows pages 1–2. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: Semantic-Aware and QoS-Aware Image Caching in Ad Hoc Networks Bo Yang, Member , IEEE , and Ali R. Hurson, Senior Member , IEEE Abstract —Semantic caching was originally used for structural data objects such as 2D location data and cannot be directly applied to mobile image data access. First, traditional semantic caching relies on exact match and therefore is not suitable for approximate and similarity-based queries. Second, the semantic description of cached data is defined on query context instead of data content, which leads to inefficient use of cache storage. Third, the semantic description of cached data does not reflect the popularity of the data, making it difficult to conduct popularity-driven content analysis and prediction. To facilitate content-based image retrieval in wireless ad hoc networks, we propose a semantic-aware image caching (SAIC) scheme in this paper. The proposed scheme can efficiently utilize the cache space and significantly reduce the cost of image retrieval. The proposed SAIC scheme is based on several innovative ideas: 1) multilevel representation of the semantic contents, 2) association-based and Bayesian probability-based content prediction, 3) constraint-based representation method showing the semantic similarity between images, 4) nonflooding query processing, and 5) adaptive cache consistency maintenance. The proposed model is introduced, and through extensive simulation, its behavior has been compared against two state-of-the-art ad hoc caching schemes as advanced in the literature. Index Terms —Information search and retrieval, knowledge management, mobile computing, semantics. Ç 1 I NTRODUCTION W IRELESS ad hoc networks are shared-medium multihop networks consisting of radio-equipped mobile nodes that may vary from sensors in the battlefield to laptops mounted on vehicles. The mobile nodes in ad hoc networks are capable of not only storing and forwarding data but also performing complex tasks through their communications and cooperations such as on-demand routing or similarity search of multimedia data. Most of the previous research focused on the path-finding protocols that adapt to the dynamic network topology , , ; however, data processing is an equally significant issue in the applications of ad hoc networks , since the ultimate task of a network is to support data sharing and to allow timely and reliable access to the information. Consequently, there is a great need for novel solutions to the challenging task of data processing in ad hoc networks. One emerging data processing application for ad hoc networks is content-based image retrieval (CBIR). Image information enriches the communications between mobile nodes, making it desirable in many civil and military applications such as visual surveillance, target tracking, environment monitoring, and information sharing. Con- sider, for instance, a vehicular ad hoc network consisting of laptops mounted on vehicles. Some vehicles in the networklaptops mounted on vehicles....
View Full Document
This note was uploaded on 03/19/2012 for the course CS 1313 taught by Professor Aman during the Spring '12 term at Punjab Engineering College.
- Spring '12