Development of Intelligent 3D Solid Modeler Based on Artificial Intelligence Technique (79093)
This study investigates the problem of constructing three-dimensional boundary representation solid models of two-dimensional data. Features extraction of line drawing involves process of deriving three basic entities namely T-junction, line and region. This concept is applied to derive a region by connecting corners and T-junctions that bound a region. A mathematical model is needed to model this problem then it solved by mathematical formulation. The propose method is to detect the accurate skewed symmetrical axes of not only polygonal pattern but also curved patterns in complex image even if some parts of the patterns are occluded.

The Development of Virtual Product Life Cycle Design Tool Using Artificial Intelligence Technique
Virtual Manufacturing (VM) is the use of computer models and to aid the design and production of manufacturing products. VM was first used in 1982 by McLean et. al. when they were looking at ways to extend Group Technology (GT). This term has also been used more recently by Mills et al. who investigated software for designing and simulating manufacturing cells for products designed on CAD packages or geometric modelers, and by Kimura, who has coupled the use of knowledge-based design with the modeling of engineering objects and the simulation of manufacturing on computers. VM implies interaction with a manufacturing environment as achieved by Barrus with the creation of a Virtual Workshop containing a selection of manually operated machines. The system uses the ACIS geometric modeler, exploiting the internal roll-back mechanism to perform multiple undo and redo of operations. VM is expected provide accurate estimates for processing times, cycle times and cost, as well as product quality. Three AI techniques are fuzzy logic (FL), genetic algorithm (GA) and neural network (NN). The application of AI can be found in many areas such as in comsumer clasification, diagnosis system, longevity modeling, and vision tracking. Therefore, the application of AI technique in development of virtual product life cycle design tool should be considered. The combination of NN, GA and FL might be considered based on the work[12] that combine GA and FL.

Failure prediction of cancellous bone using morphological data of trabeculae structure
Trabecular architecture has been considered as an important determinant of osteoporosis and other pathological conditions in bone. The microstructure of the trabecular network is often measured using measures such as bone volume fraction (BV/TV), trabecular number (Tb.N), trabecular thickness (Tb.Th), separation (Tb.Sp), and surface-to-volume ratio of bone (BS/BV). These parameters have been examined for different anatomical sites and physiological conditions such as aging, bone disease, and recently, remodeling caused by chemical treatments. A related parameter, the degree of anisotropy of trabecular bone, was observed to highly correlate with increase in fracture risk of the hip. Trabecular connectivity based on topological measurements has also been useful for predicting changes in mechanical properties with bone loss. Microcomputed tomography (micro-CT) was introduced to explore the three-dimensional (3D) architecture of bone. Due to its high resolution (as small as a few micrometers), micro-CT can obtain precise 3D images at the microlevel of trabecular structure. For in vitro micro- CT studies, different voxel sizes have been used, ranging from 8 to 120 microns. Although high resolution is achievable using micro-CT, scanning large specimens such as a whole vertebral body may require use of a spatial resolution corresponding to a voxel size greater than 100 microns. Because 100 microns is in the order of typical trabecular thickness, partial volume effects will cause errors when computing the morphological parameters for trabecular bone. Ding and Hvid found that the magnitudes of stereological parameters were strongly dependent on voxel size for voxel size larger than 100 microns. Ruegsegger et al. indicated that the morphological values could be corrected to a specific resolution up to 200 microns voxel size based on the monotonic dependence of morphological parameters on image resolution. However, the effect of scanning and reconstruction voxel size has not been considered separately in previous studies. The separate and combined effects of these voxel sizes on morphological variables need to be evaluated. Scanning voxel size is a measure of the quality of the raw data images and determines the best level of detail that can be resolved in the image. The raw data can be appropriately reconstructed at any reconstruction voxel size that is larger than (or equal to) the scanning voxel size. Reconstruction voxel size is the actual voxel size chosen for the 3D image reconstruction. It is 22 ordinarily assumed that a larger reconstruction voxel size will decrease the accuracy of the image. Nevertheless, mainly to avoid large computational costs, images may have to be coarsened using greater reconstruction voxel sizes than scanning voxel size in some applications such as micro-CT-based, large-scale finite element models (note that choosing a reconstruction voxel size smaller than the scanning voxel size cannot improve the quality of the reconstructed image because the raw data do not support the smaller reconstructed voxels). The contribution of microstructure to the mechanical properties of cancellous bone has been widely accepted, and to this end, many indices have been devised to further describe the influence of changes in bone microstructure onto its mechanical properties. However, these methods present an average number for the entire specimen and do not take into consideration general inhomogeneities and local variations in bone microstructure. Therefore, it is imperative that the weakest link in cancellous bone is identified, and its contribution to the failure properties of whole bone evaluated.

Head of computer Computer Industry research : Dr Habibollah Haron