Schema integration is the problem of creating a unified target schema based on a set of existing source schemas and based on a set of correspondences that are the result of matching the source schemas. Previous methods for schema integration rely on the exploration, implicit or explicit, of the multiple design choices that are possible for the integrated schema. Such exploration relies heavily on user interaction; thus, it is time consuming and labor intensive. Furthermore, previous methods have ignored the additional information that typically results from the schema matching process, that is, the weights and in some cases the directions that are associated with the correspondences.

A dual-channel 3D MRI segmentation technique based on grouping artificial immune networks (GAIN) is introduced to detect MS lesion in MR images. The technique demonstrates the ability of artificial immune networks to handle MS lesions detection in T1- and T2-weighted brain MRI. The GAIN-based MRI segmentation technique was evaluated using simulated MS brain images from the McConnell Brain Imaging Centre, Montreal Neurological Institute of McGill University. 3D anisotropic filtering is used to handle noise artifacts in the simulated 3D MRI data sets. Experimental results demonstrated that dual channel MS segmentation approach exhibited high accuracy in segmenting the simulated MS brain data and an even higher accuracy when compared to techniques based on single channel 3D MRI data sets in terms of the Dice coefficient, an objective measure of overlap.

Mobile Ad hoc networking is evolving to form the basis for future military and disaster relief network architecture. In such high dynamic networks, such Mobile Ad hoc NETworks (MANETs) are formed over wireless links that are susceptible to failure. Strict requirements on managing security and reliability combined with the dynamic nature of the network provide a strong motivation for proactive self- organizing, self configuring, and self healing management capabilities in the network. This paper describes a Proactive Management Algorithm (PMA) for MANETs. PMA is based on the effective integration of autonomous, predictive and adaptive distributed management strategies to provide proactive fault tolerance management algorithm. Proactive management is achieved through the distributed analysis of the current performance of the mobile nodes utilizing an optimistic discrete event simulation method, which is used to predict the mobile nodes future status and to execute a proactive fault tolerant management scheme. PMA take advantage of distributed parallel processing, flexibility and intelligence of active packets to minimize the management overhead, while adapting to the highly dynamic and resource-constrained nature of MANETs. The simulation results demonstrate that PMA not only significantly reduce management control overhead, but also substantially improves both the performance and the stability of the MANETs

Cardiac cavity labeling is crucial for the detection of heart abnormalities and estimation of numerous heart indexes. A deformable model-based splitting technique is presented that improves on our segmentation algorithm and provides labeling of cardiac chambers. Experiments show that the presented work provides accuracy as well as versatility.

A new noncumulative layered multicast congestion control algorithm is proposed that can identify the location of congested branch(es) in the multicast tree and intelligently assign a dropping preference for each candidate layer. These preferences are assigned in a way that minimizes the number of affected receivers by dropping the corresponding layer. The algorithm assigns higher dropping preferences to the layers that cause simultaneous congestion in the multicast tree. It also minimizes the effect of receivers intentionally ignoring the congestion control algorithm, which provides tighter control of the receivers, and a bounded TCP-friendly behavior. Complexity analysis proves that the proposed algorithm has a linear computation time complexity. Simulation results show that the proposed congestion control algorithm in conjunction with a suitable layer coordination mechanism can increase the average normalized throughput of the receivers in the multicast session by more than 24%.

Rapid developments in the Internet and multimedia applications allow us to access large amounts of image and video data. While significant progress has been made in digital data compression, content-based functionalities are still quite limited. Many existing techniques in content-based retrieval are based on global visual features extracted from the entire image. In order to provide more efficient content-based functionalities for video applications, it is necessary to extract meaningful video objects from scenes to enable object-based representation of video content. Object-based representation is also introduced by MPEG-4 to enable content-based functionality and high coding efficiency. In this paper, we propose a new algorithm that automatically extracts meaningful video objects from video sequences. The algorithm begins with the robust motion segmentation on the first two successive frames. To detect moving objects, segmented regions are grouped together according to their spatial similarity. A binary object model for each moving object is automatically derived and tracked in subsequent frames using the generalized Hausdorff distance. The object model is updated for each frame to accommodate for complex motions and shape changes of the object. Experimental results using different types of video sequences are presented to demonstrate the efficiency and accuracy of our proposed algorithm.

A fault-tolerant architecture for an automatic navigation system is presented. The system employs a mixed type of architecture in which the speed advantages of both pipelined and parallel architectures are exploited to achieve real-time navigation. The fault-tolerant architecture is presented using two reconfiguration strategies. To evaluate the proposed architecture, its reliability, availability, and safety are investigated using Markov models. The feasibility of implementing the proposed architecture is studied. It is found that the architecture be implemented to perform the required real-time navigation of the automatic vision-guided vehicle.>