Filters








19,909 Hits in 7.8 sec

CNN-Based Suppression of False Contour and Color Distortion in Bit-Depth Enhancement

Changmeng Peng, Luting Cai, Xiaoyang Huang, Zhizhong Fu, Jin Xu, Xiaofeng Li
2021 Sensors  
Based on the convolution-combined-with-deconvolution codec and global skip of BE-AUTO, this method can effectively suppress false contour and color distortion, thus achieving the state-of-the-art objective  ...  To solve these problems, a Bit-depth Enhancement method with AUTO-encoder-like structure (BE-AUTO) is proposed in this paper.  ...  CRR finds out all upper/lower boundaries and then estimates the pixel value of the current location based on step_ratio defined by the distances from the current pixel to its closest upper boundary and  ... 
doi:10.3390/s21020416 pmid:33435533 pmcid:PMC7826856 fatcat:msktwhb2drhudavf2bkylerlsm

A novel method of predictive collision risk area estimation for proactive pedestrian accident prevention system in urban surveillance infrastructure [article]

Byeongjoon Noh, Hwasoo Yeo
2021 arXiv   pre-print
The proposed system applied trajectories of vehicles and pedestrians from video footage after preprocessing, and then predicted their trajectories by using deep LSTM networks.  ...  A breakthrough for proactively preventing pedestrian collisions is to recognize pedestrian's potential risks based on vision sensors such as CCTVs.  ...  Materials and methods: Descriptions of a predictive collision risk area estimation system based on deep LSTM networks and statistical inference method. 2.  ... 
arXiv:2105.02572v1 fatcat:c2uzm4wmwrh3jmyxsi36tgwdhe

Deep Learning Method Based on Physics Informed Neural Network with Resnet Block for Solving Fluid Flow Problems

Chen Cheng, Guang-Tao Zhang
2021 Water  
Solving fluid dynamics problems mainly rely on experimental methods and numerical simulation.  ...  The results show that the PINN with Resnet blocks (Res-PINN) has stronger predictive ability than traditional deep learning methods.  ...  Data Availability Statement: Data available on request due to restrictions e.g., privacy or ethical. The data presented in this study are available on request from the corresponding author.  ... 
doi:10.3390/w13040423 fatcat:o7xlwshyrfghvkhczwvssxh5ly

Hybrid Bidirectional LSTM model for Short-Term Wind Speed Interval Prediction

Adnan Saeed, Chaoshun Li, Mohd Danish, Saeed Rubaiee, Geng Tang, Zhenghao Gan, Anas Ahmed
2020 IEEE Access  
We also demonstrate that for time series prediction tasks, feature extraction through autoencoder is more effective than making deep residual networks.  ...  In our experiments which involve eight cases distributed among two wind fields, the proposed method is able to generate narrow prediction intervals with high prediction interval coverage and achieve an  ...  One common way of communicating the uncertainty is to indicate the expected upper and lower bounds of the forecasts or in other words generating the prediction intervals (PIs).  ... 
doi:10.1109/access.2020.3027977 fatcat:raqubymaqrcwdh2wwybxvm2vnu

Rapid localization of gravitational wave sources from compact binary coalescences using deep learning [article]

Chayan Chatterjee, Linqing Wen, Damon Beveridge, Foivos Diakogiannis, Kevin Vinsen
2022 arXiv   pre-print
Specifically, we train and test a normalizing flow model on matched-filtering output from gravitational wave searches.  ...  In this paper, we propose the first deep learning-based approach for rapid and accurate sky localization of all types of binary coalescences, including neutron star-neutron star and neutron star-black  ...  This research used data obtained from the Gravitational Wave Open Science Center (https://www.gwopenscience.org), a service of LIGO Laboratory, the LIGO Scientific Collaboration and the Virgo Collaboration  ... 
arXiv:2207.14522v1 fatcat:sdwbbaf3sjf7tnhxasqvrh25qq

Artificial intelligence velocimetry and microaneurysm-on-a-chip for three-dimensional analysis of blood flow in physiology and disease

Shengze Cai, He Li, Fuyin Zheng, Fang Kong, Ming Dao, George Em Karniadakis, Subra Suresh
2021 Proceedings of the National Academy of Sciences of the United States of America  
Given the limitations of technologies available for assessing in vivo flow fields, in vitro methods based on traditional microfluidic platforms have been developed to mimic physiological conditions.  ...  predictions.  ...  We enforce the no-slip boundary condition on the upper and lower surfaces (z = ±12.5 µm) and the lateral channel walls such that (u, v , w ) ∂Ω = 0.  ... 
doi:10.1073/pnas.2100697118 pmid:33762307 fatcat:hi473wr4drglfod3psphwmyo5q

Cyber-attack Detection Strategy Based on Distribution System State Estimation

Huan Long, Zhi Wu, Chen Fang, Wei Gu, Xinchi Wei, Huiyu Zhan
2020 Journal of Modern Power Systems and Clean Energy  
An improved iterative algorithm (IIA) is developed to solve the interval DSSE model and to obtain the lower and upper bounds of the interval.  ...  This paper proposes a cyber-attack detection strategy based on distribution system state estimation (DSSE).  ...  Thus, a cyber-attack detection strategy is proposed based on interval DSSE. Interval DSSE estimates the lower and upper boundaries of the bus state, which is regarded as the predetermined threshold.  ... 
doi:10.35833/mpce.2019.000216 fatcat:p53ahx7d2be5xdx6r642mx56iu

DiffPoseNet: Direct Differentiable Camera Pose Estimation [article]

Chethan M. Parameshwara, Gokul Hari, Cornelia Fermüller, Nitin J. Sanket, Yiannis Aloimonos
2022 arXiv   pre-print
Current deep neural network approaches for camera pose estimation rely on scene structure for 3D motion estimation, but this decreases the robustness and thereby makes cross-dataset generalization difficult  ...  In particular, normal flow is used to estimate relative camera pose based on the cheirality (depth positivity) constraint.  ...  The final self-adaptive pose estimation is performed as a bi-level minimization in the network [18] , in which an upper-level problem is solved subject to constraints imposed by a lower-level problem  ... 
arXiv:2203.11174v1 fatcat:igylra4w3jabroto7ogsc4qunq

Coronary Wall Segmentation in CCTA Scans via a Hybrid Net with Contours Regularization [article]

Kaikai Huang and Antonio Tejero-de-Pablos and Hiroaki Yamane and Yusuke Kurose and Junichi Iho and Youji Tokunaga and Makoto Horie and Keisuke Nishizawa and Yusaku Hayashi and Yasushi Koyama and Tatsuya Harada
2020 arXiv   pre-print
Recently, several deep learning-based methods have been proposed for boundary detection and segmentation in a medical image.  ...  In this paper, we propose a novel boundary detection method for coronary arteries that focuses on the continuity and connectivity of the boundaries.  ...  Fig. 2 shows a qualitative comparison of the predicted boundaries between our method and the aforementioned methods.  ... 
arXiv:2002.12263v1 fatcat:mjnrxdevhjesfgupw3od5yf4bq

Improving deep learning-based protein distance prediction in CASP14 [article]

Zhiye Guo, Tianqi Wu, Jian Liu, Jie Hou, Jianlin Cheng
2021 bioRxiv   pre-print
The prediction method uses deep residual neural networks with the channel-wise attention mechanism to classify the distance between every two residues into multiple distance intervals.  ...  We developed several protein distance predictors based on a deep learning distance prediction method and blindly tested them in the 14th Critical Assessment of Protein Structure Prediction (CASP14).  ...  The project is partially supported by two NSF grants (DBI 1759934 and IIS1763246), one NIH grant (GM093123), two DOE grants (DE-SC0020400 and DE-SC0021303), and the computing allocation on the Summit supercomputer  ... 
doi:10.1101/2021.02.02.429462 fatcat:22ib2fupjfc35gnatlfmcyc6iy

DeepVel: Deep learning for the estimation of horizontal velocities at the solar surface

A. Asensio Ramos, I. S. Requerey, N. Vitas
2017 Astronomy and Astrophysics  
These components are typically estimated using methods based on local correlation tracking.  ...  We have designed DeepVel, an end-to-end deep neural network that produces an estimation of the velocity at every single pixel and at every time step and at three different heights in the atmosphere from  ...  J. de Cos Juez for very useful comments on an early version of the paper. We also thank R. Abreu for initial discussions on the subject of deep learning.  ... 
doi:10.1051/0004-6361/201730783 fatcat:xj7eujwt5bha3bu32yelee63cm

Velocity structure of the lithosphere on the 2003 Mongolian-Baikal transect from SV waves

V. V. Mordvinova, A. Deschamps, T. Dugarmaa, J. Deverchére, M. Ulziibat, V. A. Sankov, A. A. Artem'ev, J. Perrot
2007 Izvestiya, Russian Academy of Sciences. Physics of the Solid Earth  
The S wave velocity distribution in the Earth's crust and the first two hundred kilometers of the upper mantle is inferred from data of a seismological linear network including 18 broadband stations installed  ...  The most intense low velocity anomalies (from -3 to -6%) in the crust and upper mantle are identified beneath the Sayan, Khamar-Daban, and Khangai highlands and the Djida fold zone and agree both with  ...  Calais (France) and B. Bekhtur (Mongolia), the leaders of the international project; K.G. Levi, Deputy Director of the Institute of the Earth's Crust; and D. Anhtzutzug, Kh. Urtnasan, Ch.  ... 
doi:10.1134/s1069351307020036 fatcat:ynnvpfqxq5hfljupzjugu57pn4

Evolution Regularity Mining and Gating Control Method of Urban Recurrent Traffic Congestion: A Literature Review

Changxi Ma, Jibiao Zhou, Xuecai (Daniel) Xu, Jin Xu
2020 Journal of Advanced Transportation  
inadequate, especially regarding deep learning, and considering the space-time correlation for congestion evolution trend prediction; and (c) quantitative research methods, dynamic determination of gating  ...  , evolution trend prediction, and urban road network gating control.  ...  Zhu [27] used the fusion data of current traffic flow data and traffic flow prediction data as traffic state recognition input data and constructed a traffic state recognition method that is based on  ... 
doi:10.1155/2020/5261580 fatcat:sjut6kgytrdibhgrbz6j22jc3a

Hidden Fluid Mechanics: A Navier-Stokes Informed Deep Learning Framework for Assimilating Flow Visualization Data [article]

Maziar Raissi, Alireza Yazdani, George Em Karniadakis
2018 arXiv   pre-print
The proposed algorithm achieves accurate predictions of the pressure and velocity fields in both two and three dimensional flows for several benchmark problems motivated by real-world applications.  ...  Our approach towards solving the aforementioned data assimilation problem is unique as we design an algorithm that is agnostic to the geometry or the initial and boundary conditions.  ...  Moreover, all data and codes used in this manuscript will be publicly available on GitHub at https://github.com/maziarraiss/HFM.  ... 
arXiv:1808.04327v1 fatcat:43lfrnzcprhijjnoqig5axi3w4

Deeply Self-Supervised Contour Embedded Neural Network Applied to Liver Segmentation [article]

Minyoung Chung, Jingyu Lee, Minkyung Lee, Jeongjin Lee, Yeong-Gil Shin
2019 arXiv   pre-print
Objective: Herein, a neural network-based liver segmentation algorithm is proposed, and its performance was evaluated using abdominal computed tomography (CT) images.  ...  The discriminative contour, shape, and deep features were internally merged for the segmentation results. Results and Conclusion: 160 abdominal CT images were used for training and validation.  ...  Without residuals, the design of more complex and deep transition layers is required for the shape estimation, which may lead to an over-fitting.  ... 
arXiv:1808.00739v5 fatcat:24r7mzcbsfdz7njb2jttsgkewm
« Previous Showing results 1 — 15 out of 19,909 results