检索结果-内蒙古大学图书馆

Transformers in Medical Image Analysis: A Review

学校读者我要写书评

暂无评论

arXiv 2022年

作者： He, Kelei Gan, Chen Li, Zhuoyuan Rekik, Islem Yin, Zihao Ji, Wen Gao, Yang Wang, Qian Zhang, Junfeng Shen, Dinggang Medical School of Nanjing University Nanjing China National Institute of Healthcare Data Science Nanjing University Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China BASIRA Lab Faculty of Computer and Informatics Engineering Istanbul Technical University Istanbul Turkey School of Science and Engineering Computing University of Dundee United Kingdom School of Biomedical Engineering ShanghaiTech University Shanghai China Department of Research and Development Shanghai United Imaging Intelligence Co. Ltd. Shanghai China

Transformers have dominated the field of natural language processing, and recently impacted the computer vision area. In the field of medical image analysis, Transformers have also been successfully applied to full-stack clinical applications, including image synthesis/reconstruction, registration, segmentation, detection, and diagnosis. Our paper aims to promote awareness and application of Transformers in the field of medical image analysis. Specifically, we first overview the core concepts of the attention mechanism built into Transformers and other basic components. Second, we review various Transformer architectures tailored for medical image applications and discuss their limitations. Within this review, we investigate key challenges revolving around the use of Transformers in different learning paradigms, improving the model efficiency, and their coupling with other techniques. We hope this review can give a comprehensive picture of Transformers to the readers in the field of medical image analysis. © 2022, CC BY-SA.

关键词： Diagnosis

Insar Time-Series Deformation Forecasting Surrounding Salt Lake Using Deep Transformer Models

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Wang, Jing Li, Chao Li, Lu Huang, Zhihua Wang, Chao Zhang, Hong Zhang, Zhengjia Research Institute of Intelligent Computing Zhejiang Laboratory. Hangzhou311121 China Key Laboratory of Digital Earth Science Aerospace Information Research Institute Chinese Academy of Sciences No.9 Dengzhuang South Road Beijing100094 China International Research Center of Big Data for Sustainable Development Goals Beijing100094 China University of Chinese Academy of Sciences Beijing100049 China Faculty of Information Engineering China University of Geosciences. 388 Lumo Road Wuhan430074 China

The open source strategy of Sentinel-1 SAR images enables Radar interferometry (InSAR) to perform time series surface deformation monitoring over large *** deformation monitoring and prediction can investigate the freeze-thaw cycles of permafrost on the Qinghai-Tibet Plateau (QTP). However, the convolutional and recurrent neural networks cannot accurately model long-term and complex relations in multi-variate time series data, it is challenging to implement time series deformation prediction with high spatial resolution. We propose an InSAR deformation prediction integrated algorithm based on the transformer-based models to predict time series deformation more accurately in permafrost areas. This method takes advantage of the self-attention mechanism to study complicated dynamic deformation features of permafrost caused by temperature and other variables from InSAR time series ***, Sentinel-1 dataset acquired with 12-day repeat are collected to implement the Small Baseline Subset (SBAS) method and retrieve the seasonal and long-term deformation surrounding Salt Lake. Then, the InSAR time series deformation and meteorological data are combined to establish the deformation prediction model using the transformer neural network. These results demonstrated that the InSAR deformation prediction method achieves better prediction performance (the root mean square errors are 3.207mm and 2.27mm) in predicting permafrost deformation trends with a point scale compared with the prediction results of other models. Finally, the predicted time series deformation maps for the period 2021/04/05 to 2022/03/19 are mapped surrounding Salt Lake. Meanwhile the total area of Salt Lake increased by 57.32km 2 during the period 2015-2019 based on the predicted deformation and the water extraction *** the expansion rate of Salt Lake was slow, and the area decreased by 3.26 km 2 from 2019 to 2022. The time series deformation forecasting method provides early warn

关键词： Deformation

Traceable Multiauthority Attribute-Based Encryption with Outsourced Decryption and Hidden Policy for CIoT

学校读者我要写书评

暂无评论

Wireless Communications and Mobile computing 2021年第1期2021卷

作者： Liu, Suhui Yu, Jiguo Hu, Chunqiang Li, Mengmeng School of Computer Science Qufu Normal University Rizhao Shandong276826 China Jinan Shandong250353 China Jinan Shandong250014 China Shandong Laboratory of Computer Networks Jinan250014 China School of Big Data and Software Engineering Chongqing University Chongqing400044 China Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education Chongqing University China

Cloud-assisted Internet of Things (IoT) significantly facilitate IoT devices to outsource their data for high efficient management. Unfortunately, some unsettled security issues dramatically impact the popularity of IoT, such as illegal access and key escrow problem. Traditional public-key encryption can be used to guarantees data confidentiality, while it cannot achieve efficient data sharing. The attribute-based encryption (ABE) is the most promising way to ensure data security and to realize one-to-many fine-grained data sharing simultaneously. However, it cannot be well applied in the cloud-assisted IoT due to the complexity of its decryption and the decryption key leakage problem. To prevent the abuse of decryption rights, we propose a multiauthority ABE scheme with white-box traceability in this paper. Moreover, our scheme greatly lightens the overhead on devices by outsourcing the most decryption work to the cloud server. Besides, fully hidden policy is implemented to protect the privacy of the access policy. Our scheme is proved to be selectively secure against replayable chosen ciphertext attack (RCCA) under the random oracle model. Some theory analysis and simulation are described in the end. © 2021 Suhui Liu et al.

关键词： Internet of things

Disentangled Cascaded Graph Convolution Networks for Multi-Behavior Recommendation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Cheng, Zhiyong Dong, Jianhua Liu, Fan Zhu, Lei Yang, Xun Wang, Meng School of Computer Science and Information Engineering Hefei University of Technology No. 485 Danxia Road Anhui Hefei230009 China Shandong Artificial Intelligence Institute Qilu University of Technology Shandong Academy of Sciences No. 19 Keyuan Road Shandong Jinan250014 China School of Computing National University of Singapore 21 Lower Kent Ridge Road Singapore119077 Singapore School of Electronic and Information Engineering University of Tongji No. 4800 Caoan Road Shanghai201804 China School of Information Science and Technology University of Science and Technology of China No. 443 Huangshan Road Anhui Hefei230027 China Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Institute of Artificial Intelligence Hefei Comprehensive National Science Centery No. 485 Danxia Road Anhui Hefei230009 China

Multi-behavioral recommender systems have emerged as a solution to address data sparsity and cold-start issues by incorporating auxiliary behaviors alongside target behaviors. However, existing models struggle to accurately capture varying user preferences across different behaviors and fail to account for diverse item preferences within behaviors. Various user preference factors (such as price or quality) entangled in the behavior may lead to sub-optimization problems. Furthermore, these models overlook the personalized nature of user behavioral preferences by employing uniform transformation networks for all users and items. To tackle these challenges, we propose the Disentangled Cascaded Graph Convolutional Network (Disen-CGCN), a novel multi-behavior recommendation model. Disen-CGCN employs disentangled representation techniques to effectively separate factors within user and item representations, ensuring their independence. In addition, it incorporates a multi-behavioral meta-network, enabling personalized feature transformation across user and item behaviors. Furthermore, an attention mechanism captures user preferences for different item factors within each behavior. By leveraging attention weights, we aggregate user and item embeddings separately for each behavior, computing preference scores that predict overall user preferences for items. Our evaluation on benchmark datasets demonstrates the superiority of Disen-CGCN over state-of-the-art models, showcasing an average performance improvement of 7.07% and 9.00% on respective datasets. These results highlight Disen-CGCN’s ability to effectively leverage multi-behavioral data, leading to more accurate recommendations. Copyright © 2024, The Authors. All rights reserved.

关键词： Recommender systems

Asymmetric CNN for image super-resolution

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Tian, Chunwei Xu, Yong Zuo, Wangmeng Lin, Chia-Wen Zhang, David The Bio-Computing Research Center Harbin Institute of Technology ShenzhenShenzhenGuangdong518055 China Shenzhen Key Laboratory of Visual Object Detection and Recognition ShenzhenGuangdong518055 China The School of Computer Science and Technology Harbin Institute of Technology HarbinHeilongjiang150001 China The Peng Cheng Laboratory ShenzhenGuangdong518055 China Shenzhen Key Laboratory of Visual Object Detection and Recognition Shenzhen Guangdong518055 China The Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Hsinchu Taiwan ShenzhenGuangdong518172 China The Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

Deep convolutional neural networks (CNNs) have been widely applied for low-level vision over the past five years. According to nature of different applications, designing appropriate CNN architectures is developed. However, customized architectures gather different features via treating all pixel points as equal to improve the performance of given application, which ignores the effects of local power pixel points and results in low training efficiency. In this paper, we propose an asymmetric CNN (ACNet) comprising an asymmetric block (AB), a memory enhancement block (MEB) and a high-frequency feature enhancement block (HFFEB) for image super-resolution. The AB utilizes one-dimensional asymmetric convolutions to intensify the square convolution kernels in horizontal and vertical directions for promoting the influences of local salient features for SISR. The MEB fuses all hierarchical low-frequency features from the AB via residual learning (RL) technique to resolve the long-term dependency problem and transforms obtained low-frequency features into high-frequency features. The HFFEB exploits low- and high-frequency features to obtain more robust super-resolution features and address excessive feature enhancement problem. Additionally, it also takes charge of reconstructing a high-resolution (HR) image. Extensive experiments show that our ACNet can effectively address single image super-resolution (SISR), blind SISR and blind SISR of blind noise problems. The code of the ACNet is shown at https://***/hellloxiaotian/ACNet. © 2021, CC BY-NC-ND.

关键词： Image enhancement

Hybrid attention network based on progressive embedding scale-context for crowd counting

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Fusen Sang, Jun Wu, Zhongyuan Liu, Qi Sang, Nong Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education Chongqing University Chongqing400044 China School of Big Data and Software Engineering Chongqing University Chongqing401331 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430000 China

The existing crowd counting methods usually adopted attention mechanism to tackle background noise, or applied multi-level features or multi-scales context fusion to tackle scale variation. However, these ap- proaches deal with these two problems separately. In this paper, we propose an Hybrid Attention Network (HAN) by employing Progressive Embedding Scale-context (PES) information, which enables the network to simultaneously suppress noise and adapt head scale variation. We build the hybrid attention mechanism through paralleling spatial attention and channel attention module, which makes the network to focus more on the human head area and reduce the interference of background objects. Besides, we embed certain scale-context to the hybrid attention along the spatial and channel dimensions for alleviating these count- ing errors caused by the variation of perspective and head scale. Finally, we propose a progressive learning strategy through cascading multiple hybrid attention modules with embedding diαerent scale-context, which can gradually integrate diαerent scale-context information into the current feature map from global to local. Ablation experiments provides that the network architecture can gradually learn multi-scale features and suppress background noise. Extensive experiments demonstrate that HANet obtain state-of-the-art counting performance on four mainstream datasets. Copyright © 2021, The Authors. All rights reserved.

关键词： Embeddings

Multi-sensor Fusion Detection Method for Vehicle Target Based on Kalman Filter and data Association Filter 7th

学校读者我要写书评

暂无评论

Multi-sensor Fusion Detection Method for Vehicle Target Base...

7th International Conference on Artificial Intelligence and Security, ICAIS 2021

作者： Duan, Xuting Sun, Chengming Tian, Daxin Zheng, Kunxian Zhou, Gang E, Wenjuan Zhang, Yundong Beijing Advanced Innovation Center for Big Data and Brain Computing School of Transpotation Science and Engineering Beihang University Beijing100191 China Research Institute of Highway Ministry of Transport of the People’s Republic of China Beijing100088 China School of Rail Transportation Soochow University Suzhou215000 China Suzhou Automotive Research Institute Tsinghua University Suzhou215000 China State Key Laboratory of Digital Multimedia Chip Technology Chongqing Vimicro AI Chip Technology Co. Ltd. Chongqing400722 China

ISBN: (纸本)9783030786175

Multi-sensor data fusion is an emerging technology, which has been widely used in medical diagnosis, remote sensing, inertial navigation and many other fields. What’s more, the implementation and application of automatic driving system rely heavily on target detection technology. Due to the high mobility and unpredictability of vehicle-mounted equipment, for automatic vehicles, it is arduous to achieve real-time and accurate vehicle target detection by a single sensor means, thus it is difficult to reliably guarantee the safety and stability. This paper proposes a novel object detection method based on a multi-sensor fusion mechanism, which considers the real-time sensing data from two types of sensors including radar and camera. It collects multi-vehicle speed and position information efficiently and reliably. Then, it filters and integrates data according to Extended Kalman Filter, data Association Filter and some other methods. Furthermore, vehicle-borne equipment makes intelligent decision based on the data. In addition to theoretical support, the designed simulation results also show that the multi-sensor fusion mechanism can detect target vehicles efficiently and accurately, and it has superiority in the stability and accuracy of perception than single sensor sensing method. © 2021, Springer Nature Switzerland AG.

关键词： Extended Kalman filters

Machine Learning and Physics-Driven Modelling and Simulation of Multiphase Systems

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Basha, Nausheen Arcucci, Rossella Angeli, Panagiota Anastasiou, Charitos Abadie, Thomas Casas, César Quilodrán Chen, Jianhua Cheng, Sibo Chagot, Loïc Galvanin, Federico Heaney, Claire E. Hossein, Fria Hu, Jinwei Kovalchuk, Nina Kalli, Maria Kahouadji, Lyes Kerhouant, Morgan Lavino, Alessio Liang, Fuyue Nathanael, Konstantia Magri, Luca Lettieri, Paola Materazzi, Massimiliano Erigo, Matteo Pico, Paula Pain, Christopher C. Shams, Mosayeb Simmons, Mark Traverso, Tullio Valdes, Juan Pablo Wolffs, Zef Zhu, Kewei Zhuang, Yilin Matar, Omar K. Department of Chemical Engineering Imperial College London United Kingdom Department of Earth Science & Engineering Imperial College London United Kingdom Department of Chemical Engineering University College London United Kingdom School of Chemical Engineering University of Birmingham United Kingdom Data Science Institute Department of Computing Imperial College London United Kingdom State Key Laboratory of Multiphase Complex Systems Institute of Process Engineering Chinese Academy of Sciences Beijing China Centre for AI-Physics Modelling Imperial-X White City Campus Imperial College London United Kingdom The Alan Turing Institute British Library 96 Euston Road LondonNW1 2DB United Kingdom Department of Aeronautics Imperial College London United Kingdom Institute of Physics University of Amsterdam Science Park Amsterdam904 Netherlands Nikhef Science Park Amsterdam105 Netherlands Department of Computer Science University of York United Kingdom

We highlight the work of a multi-university collaborative programme, PREMIERE (PREdictive Modelling with QuantIfication of UncERtainty for MultiphasE Systems), which is at the intersection of multi-physics and machine learning, aiming to enhance predictive capabilities in complex multiphase flow systems across diverse length and time scales. Our contributions encompass a variety of approaches, including the Design of Experiments for nanoparticle synthesis optimisation, Generalised Latent Assimilation models for drop coalescence prediction, Bayesian regularised artificial neural networks, eXtreme Gradient Boosting for microdroplet formation prediction, and a sub-sampling based adversarial neural network for predicting slug flow behaviour in two-phase pipe flows. Additionally, we introduce a generalised latent assimilation technique, Long Short-Term Memory networks for sequence forecasting mixing performance in stirred and static mixers, active learning via Bayesian optimisation to recover coalescence model parameters for high current density electrolysers, Gaussian process regression for drop size distribution predictions for sprays, and acoustic emission signal inversion using gradient boosting machines to characterise particle size distribution in fluidised beds. We also offer perspectives on the development of a shape optimisation framework that leverages the use of a multi-fidelity multiphase emulator. The results presented have applications in chemical synthesis, microfluidics, product manufacturing, and green hydrogen generation. © 2024, The Authors. All rights reserved.

关键词： Forecasting

A DECOUPLING TWO-GRID METHOD FOR THE STEADY-STATE POISSON-NERNST-PLANCK EQUATIONS

学校读者我要写书评

暂无评论

Journal of Computational Mathematics 2019年第4期37卷 556-578页

作者： Ying Yang Benzhuo Lu Yan Xie School of Mathematics and Computing Science Guangxi Colleges and Universities Key Laboratory of Data Analysis and Computation Guilin University of Electronic Technology Guilin 541004 China LSEC Institute of Computational Mathematics and Scientific/Engineering Computing the National Center for Mathematics and Interdisciplinary Sciences Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing 100190 China LSEC Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing 100190 China

Poisson-Nernst-Planck equations are widely used to describe the electrodiffusion of ions in a solvated biomolecular system. Two kinds of two-grid finite element algorithms are proposed to decouple the steady-state Poisson-Nernst-Planck equations by coarse grid finite element approximations. Both theoretical analysis and numerical experiments show the efficiency and effectiveness of the two-grid algorithms for solving Poisson-Nernst-Planck equations.

关键词： Poisson-Nernst-Planck equations Two-grid finite element method Decoupling method Error analysis Gummel iteration