ARTIFICIAL INTELLIGENCE ORDERED 3D VERTEX IMPORTANCE

Iva Vasić, Bata Vasić, Zorica Nikolić

Abstract


Ranking nodes of multidimensional networks is crucial in many areas of research, including selecting and determining the importance of decisions. Some decisions are significantly more important than others, and so is their weight categorization. This paper defines a new method for determining the weight of decisions using a completely new method of using artificial intelligence for weight ranking of three-dimensional network nodes, improving the existing Ordered Statistics Vertex Extraction and Tracking Algorithm (OSVETA) based on modulation of quantized indices (QIM) and error correction codes. The technique we propose in this paper offers significant improvements in the efficiency of deciding on the importance of network nodes in relation to statistical OSVETA criteria, replacing heuristic methods with methods of precise prediction of modern neural networks. The new technique of using artificial intelligence enables a significantly better definition of the geometric network and a better assessment of topological characteristics. The contributions of the new method result in greater precision in defining stable decision nodes, significantly reducing the probability of deleting decision nodes.


Keywords


Artificial intelligence, 3D geometry, Information theory, Hiding information.

Full Text:

PDF (Serbian)

References


Fausett L.V. (1994) Fundamentals of Neural Networks: Architectures, Algorithms and Applications. Prentice-Hall, Inc. Upper Saddle River, NJ, USA. https://dl.acm.org/doi/book/10.5555/197023

Huang H., Kalogerakis E., Chaudhuri S., Ceylan D., Kim V. & Ymer E. (2017) Learning local shape descriptors from part correspondences with multiview convolutional networks. ACM Transactions on Graphics, 37(1), 6. https://doi.org/10.1145/3137609

Kauffman M. (2009) Optimizing Your Autodesk® 3ds Max® Design Models for Project Newport. Autodesk University 2009. http://au.autodesk.com/?nd=material&session_material_id=6296

Krizhevsky A., Sutskever I., & Hinton G. E. (2012) Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6). https://doi.org/10.1145/3065386

Maturana D. & Scherer S. (2015) VoxNet: A 3D convolutional neural network for real-time object recognition. Proceedings of the 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, Germany, 922-928. DOI: 10.1109/IROS.2015.7353481

McIvor A.M. & Valkenburg R.J.(1997) A comparison of local surface geometry estimation methods. Machine Vision and Applications, 10(1), 17 – 26. https://doi.org/10.1007/s001380050055

Meyer M., Desbrun M., Schröder P., & Barr A.H. (2003) Discrete differential-geometry operators for triangulated 2-manifolds. Visualization and Mathematics III, 12, 35 – 57. Springer, Berlin, Heidelberg, https://doi.org/10.1007/978-3-662-05105-4_2

Simonyan K. & Zisserman A. (2015, May 7-9) Very deep convolutional networks for large-scale image recognition. Proceedings of the 3rd International Conference on Learning Representations (ICLR2015). San Diego, USA. https://arxiv.org/abs/1409.1556.

Spivak M. (1999) A comprehensive introduction to differential geometry. 1(3), Publish or Perish. DOI:10.2307/2319112

Vasic B. (2012) Ordered Statistics Vertex Extraction and Tracing Algorithm (OSVETA). Advances in Electrical and Computer Engineering, 12(4), 25 -32. DOI: 10.4316/AECE.2012.04004

Vasic B. & Vasic B. (2013) Simplification Resilient LDPC-Coded Sparse-QIM Watermarking for 3D-Meshes. IEEE Transactions on Multimedia, 15(7),1532-1542.https://doi.org/10.1109/TMM.2013.2265673

Vasic B., Raveendran N., & Vasic B. (2019, October 21-24) Neuro-OSVETA: A robust watermarking of 3D meshes. Proceedings. of the International Telemetering Conference (ITC 2019), Las Vegas, USA, 55, 387 – 396. http://hdl.handle.net/10150/635232

Wang K., Savva M., Chang A. X. & Ritchie D. (2018) Deep convolutional priors for indoor scene synthesis. ACM Transactions on Graphics, 37(4), 70. https://doi.org/10.1145/3197517.3201362

Wang P-S., Liu Y., Guo Y.-X., Sun C.-Y., & Tong X. (2017) O-CNN: Octree-based convolutional neural networks for 3D shape analysis. ACM Transactions on Graphics, 36(4), 72. https://doi.org/10.1145/3072959.3073608

Wu J., Yu Y., Huang C., & Yu K. (2015) Deep multiple instance learning for image classification and auto-annotation. Proceedings of the Computer Vision and Pattern Recognition (CVPR 2015), Boston, USA, 3460–3469. DOI: 10.1109/CVPR.2015.7298968


Refbacks

  • There are currently no refbacks.