Search

Rung động trong trục quay là một hiện tượng phổ biến thường gặp trong các hệ thống rotor. Việc xác định các yếu tố gây rung động để qua đó thực hiện các biện pháp giảm rung nhằm đảm bảo cho rotor vận hành ổn định là một trong những yêu cầu cấp thiết hiện nay. Trong bài báo này, một mô hình đánh giá rung động của rotor đã được thiết lập cho phép khảo sát các thông số chính ảnh hưởng đến rung động của rotor bao gồm tốc độ tới hạn, độ lệch tâm gây ra do mất cân bằng và góc pha ban đầu. Các kết quả thực nghiệm cho thấy: khi tốc độ quay gần tốc độ tới hạn sự rung động trở nên không ổn định và biên độ dao động tăng mạnh; lượng mất cân bằng tăng dẫn đến biên độ dao động tăng; góc pha ban đầu của vị trí đặt tải nếu bị thay đổi trong quá trình hoạt động sẽ dẫn đến các biến đổi khác nhau của giai đoạn rung động dẫn đến sự tăng hoặc giảm các ứng suất uốn có thể dẫn đến hiện tượng mỏi xuất hiện trên trục quay.

Nowadays, smartphones, camcorders, and security cameras are extensively used in many areas of daily life, such as offices, traffic lights, houses, dormitories, and more. Besides that, video content editing software like Window Movie Maker, Video Editor, Adobe Photoshop, Adobe After Effect, etc., are also widely available. They have many methods for editing video content easily. So, anyone can edit video content at their willing; even edited content contrast with original content. Recently, the rapid development of deep learning-based techniques have created deepfake videos with characters' faces replaced by other faces automatically, such as FakeApp, Faceswap, etc. That leads to "seeing is no longer believing.". Also, an authentic video provides stronger evidence in court. Therefore, video forgery detection proves that video authenticity has become an urgent requirement today. Keywords: Video forgery detection; Video forensic; Deepfake video detection; Deep learning; convolutional neural network. Title: Video Forgery Detection: State-of-The-Art Review Author: Xuan Hau Nguyen, Thai Son Tran International Journal of Recent Research in Mathematics Computer Science and Information Technology ISSN 2350-1022 Vol. 9, Issue 1, April 2022 - September 2022 Page No: 1-9 Paper Publications Website: www.paperpublications.org Published Date: 10-May-2022 DOI: https://doi.org/10.5281/zenodo.6536002 Paper Download Link (Source): https://www.paperpublications.org/upload/book/Video%20Forgery%20Detection-10052022-3.pdf, International Journal of Recent Research in Mathematics Computer Science and Information Technology, ISSN 2350-1022, Paper Publications, Website: www.paperpublications.org, {"references":["[1]\tMilani, S., et al., An overview on video forensics. APSIPA Transactions on Signal and Information Processing, 2012. 1.","[2]\tBestagini, P., et al., REWIND Video: copy -move forgeries dataset.https://sites.google.com/site/rewindpolimi/ downloads/datasets/video-copy-move-forgeries-dataset. 2012.","[3]\tQadir, G., S. Yahaya, and A.T. Ho, Surrey university library for forensic analysis (SULFA) of video content. 2012.","[4]\tSitara, K. and B.M. Mehtre, Digital video tampering detection: An overview of passive techniques. Digital Investigation, 2016. 18: p. 8-22.","[5]\tFan, J., C. Ma, and Y. Zhong, A selective overview of deep learning. arXiv preprint arXiv:1904.05526, 2019.","[6]\t2.2.0, F., https://www.malavida.com/en/soft/fakeapp/#gref.","[7]\tVincent, P., et al., Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of machine learning research, 2010. 11(12).","[8]\tGoodfellow, I., et al. Generative adversarial nets. in Advances in neural information processing systems. 2014.","[9]\tWang, W. and H. Farid. Exposing digital forgeries in video by detecting double MPEG compression. in Proceedings of the 8th workshop on Multimedia and security. 2006.","[10]\tWang, W. and H. Farid. Exposing digital forgeries in video by detecting double quantization. in Proceedings of the 11th ACM workshop on Multimedia and security. 2009. ACM.","[11]\tSubramanyam, A. and S. Emmanuel. Pixel estimation based video forgery detection. in 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. 2013. IEEE.","[12]\tRavi, H., et al. Compression noise based video forgery detection. in 2014 IEEE International Conference on Image Processing (ICIP). 2014. IEEE.","[13]\tHuang, Z., F. Huang, and J. Huang. Detection of double compression with the same bit rate in MPEG-2 videos. in 2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP). 2014. IEEE.","[14]\tWang, Q., et al., Video inter-frame forgery identification based on consistency of correlation coefficients of gray values. Journal of Computer and Communications, 2014. 2(04): p. 51.","[15]\tWang, W. and H. Farid. Exposing digital forgeries in video by detecting duplication. in Proceedings of the 9th workshop on Multimedia & security. 2007. ACM."]}

This paper presents a new framework for severely distorted image and video recovery via tensor augmentation and completion. By considering the task of representing a matrix by a high-order- $n$ tensor as that of encoding the matrix's 2-D indices $(i,j)$ by $n$ -digit words $i_1i_2\dots i_n$ , we develop a new high order tensor augmentation to cast a third order tensor of color images or video sequences containing missing pixels into a higher order tensor, which is similar to the ket augmentation of quantum physics, is capable of capturing all correlations and entanglements between entries of the original third order tensor. Accordingly, the resuling high-order tensor is completed by our previously developed parallel matrix factorization via tensor train decomposition. Simulations are provided to show the clear advantages of our approach in enhancing important metrics of visual quality such as relative square error and structural similarity index in image and video processing that help to achieve high recovery rates even for high-definition images and videos with 95% missing pixels.