检索结果-内蒙古大学图书馆

Deep Fusion of Shifted MLP and CNN for Medical Image Segmentation

学校读者我要写书评

暂无评论

Deep Fusion of Shifted MLP and CNN for Medical Image Segment...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Chengyu Yuan Hao Xiong Guoqing Shangguan Hualei Shen Dong Liu Haojie Zhang Zhonghua Liu Kun Qian Bin Hu Björn W. Schuller Yoshiharu Yamamoto Shlomo Berkovsky College of Computer and Information Engineering Henan Normal University China Key Laboratory of Artificial Intelligence and Personalized Learning in Education Henan China Big Data Engineering Lab of Teaching Resources & Assessment of Education Quality Henan China Centre for Health Informatics Australian Institute of Health Innovation Macquarie University Australia Key Laboratory of Brain Health Intelligent Evaluation and Intervention (BIT) Ministry of Education China School of Medical Technology Beijing Institute of Technology China School of Information Engineering Zhejiang Ocean University China GLAM – Group on Language Audio & Music Imperial College London U.K. Chair of Embedded Intelligence for Health Care and Wellbeing University of Augsburg Germany Educational Physiology Laboratory Graduate School of Education The University of Tokyo Japan

Medical image segmentation is an important task in modern analysis of medical images. Current methods tend to extract either local features with convolutions or global features with Transformers. However, few of them are able to effectively fuse global and local features to facilitate segmentation. In this work, we propose a novel hybrid network that involves three main branches: the Multi-Layer Perception (MLP) branch, the Convolutional Neural Network (CNN) branch, and a Fusion branch. The MLP and CNN branches aim to learn global and local features, respectively. To fuse these, the fusion branch introduces a novel hierarchical fusion that performs multi-layered fusions that generate high-level representations to enhance segmentation. Our evaluation with two datasets shows strong performance of the proposed method compared to state-of-the-art baselines.

关键词：

Behaviour of Geomagnetic storm, horizontal geomagnetic field and solar wind parameters during solar flare and CMEs event. 2

学校读者我要写书评

暂无评论

Behaviour of Geomagnetic storm, horizontal geomagnetic field...

2nd International Conference on Space Weather and Satellite Application, ICeSSAT 2020

作者： Syed Zafar, S.N.A. Hazmin, S.N. Jusoh, M.H. Dagang, A.N. Adzni, M.A.M. Umar, R. East Coast Enviromental Research Institute Universiti Sultan Zainal Abidin Kuala Nerus Terengganu21300 Malaysia School of Fundamental Science Universiti Malaysia Terengganu Kuala Terengganu Terengganu21300 Malaysia Faculty of Electrical Engineering Universiti Teknologi Mara Selangor Shah Alam Malaysia Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Kuala Nerus Terengganu21030 Malaysia

Space weather is driven by solar activities by pulling out the variety of phenomenon such as solar flare and coronal mass ejection (CMEs). It been discovered the CMEs and solar flares have causes disturbance at near-Earth space. This paper is to examined the behaviour of geomagnetic storm, horizontal geomagnetic field and several solar wind parameters during solar flare and CMEs event at minimum of solar cycle of 24. Observational result found that association of strongest solar flare and CMEs have declined the geomagnetic storm until-150nt at 8th September 2017. Following to this, the H component reading also slightly decreased at three magnetometer location respectively. Solar flare and CMEs released the energetic particles that could disturbed the radio communications at the Earth and electronic equipment. Therefore, it was required to study and understanding the solar flare and CMEs event. © 2021 Published under licence by IOP Publishing Ltd.

关键词： Geomagnetism

River quality classification using different distances in k-nearest neighbors algorithm

学校读者我要写书评

暂无评论

Procedia Computer Science 2022年 204卷 180-186页

作者： Nurnadiah Zamri Mohammad Ammar Pairan Wan Nur Amira Wan Azman Siti Sabariah Abas Lazim Abdullah Syibrah Naim Zamali Tarmudi Miaomiao Gao Faculty of Informatics and Computing Universiti Sultan Zainal Abidin Besut Campus Besut Terengganu Malaysia Management Science Research Group Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Kuala Nerus Terengganu Malaysia Management Science Research Group Computer and Information Sciences University of Strathclyde Glasgow United Kingdom Universiti Technology MARA Johor Branch Segamat Johor Malaysia Faculty of Biology Medicine and Health School of Medical Siences University of Manchester Manchester United Kingdom

The practice of river quality classification usually uses Water Quality Index (WQI) to evaluate the WQI values of the river. However, due to huge data collection on river pollution with uncertain water quality parameter values, need to a different approach to classify the river quality. One of the supervised classification algorithms known as K-Nearest Neighbors (KNN) seems to give new approach for river quality classification where each data points are classified according to the k number or the closest data points neighbors. Therefore, the purpose of this paper is to apply different distances and distance-weighted in KNN for finding the most accurate river quality classification. The accuracy results are compared with Support Vector Machine (SVM) and Decision Tree (DT) algorithms. This KNN algorithm will give a different approach in classify the river quality.

关键词： Supervised classification k-nearest neighbors (KNN) river quality classification accuracy

A comparison of unsupervised and supervised machine learning algorithms to predict water pollutions

学校读者我要写书评

暂无评论

Procedia Computer Science 2022年 204卷 172-179页

Clean and safe water is vital for our lives and public health. In recent decades, population growth, agriculture, industries, and climate change have worsened freshwater resource depletion and clean water pollution. Several studies have focused on water pollutions risk simulation and prediction in the presence of pollution hotspots. However, the increase and complexity of big data caused by uncertain water quality parameters led to a new efficient algorithm to trace the most accurate pollution hotspots. Therefore, this study proposes to offer different algorithms and comparative studies using Machine Learning (ML) algorithms. Ten different most widely used algorithms, including unsupervised and supervised ML, will be employed to categorize the pollution hotspots for the Terengganu River. Besides, we also validate algorithms’ accuracies by improving and changing each parameter in ML algorithms. Our results list all the accurate and efficient ML algorithms for the classification of river pollutions. These results help to facilitate river prediction using efficient and accurate algorithms in various water quality scenario.

关键词： Machine Learning Deep Learning Water Pollutions Terengganu River

Deep Learning Methods for Calibrated Photometric Stereo and Beyond

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ju, Yakun Lam, Kin-Man Xie, Wuyuan Zhou, Huiyu Dong, Junyu Shi, Boxin School of Electrical and Electronic Engineering Nanyang Technological University Singapore The Department of Electrical and Electronic Engineering The Hong Kong Polytechnic University Hong Kong The Research Institute for Future Media Computing Shenzhen University Shenzhen China The Department of Informatics University of Leicester Leicester United Kingdom The Faculty of Information Science and Engineering The Institute for Advanced Ocean Study Ocean University of China Qingdao China The National Key Laboratory for Multimedia Information Processing National Engineering Research Center of Visual Technology School of Computer Science Peking University Beijing China

Photometric stereo recovers the surface normals of an object from multiple images with varying shading cues, i.e., modeling the relationship between surface orientation and intensity at each pixel. Photometric stereo prevails in superior per-pixel resolution and fine reconstruction details. However, it is a complicated problem because of the non-linear relationship caused by non-Lambertian surface reflectance. Recently, various deep learning methods have shown a powerful ability in the context of photometric stereo against non-Lambertian surfaces. This paper provides a comprehensive review of existing deep learning-based calibrated photometric stereo methods utilizing orthographic cameras and directional light sources. We first analyze these methods from different perspectives, including input processing, supervision, and network architecture. We summarize the performance of deep learning photometric stereo models on the most widely-used benchmark data set. This demonstrates the advanced performance of deep learning-based photometric stereo methods. Finally, we give suggestions and propose future research trends based on the limitations of existing models. Copyright © 2022, The Authors. All rights reserved.

关键词： Light sources

PREFACE: Proceedings of the 1st International Conference on Material Processing and technology (ICMProTech, 2021) 14-15 July 2021

学校读者我要写书评

暂无评论

Journal of Physics: Conference Series 2021年第1期2129卷

作者： Muhammad, Noorhafiza Bin Wan Ibrahim, Wan Abdul Rahman Assyahid Bin Abd Rahim, Irfan Rosli, Muhamad Farizuan Bin Mat Saad, Mohd Nasir Omar, Mohd Firdaus Rahman, Rozyanty Salleh, Mohd Arif Anuar Mohd Fathullah, Mohd Shuaib, Norshah Afizi Leman, Abdul Mutalib Bin Kamarudin, Khairu Maarof, Mohd Rashidi Bin Ali, Mohd Basri Saad, Mohd Sazli Suhaimi, Mohd Azlan Sharif, Safian Zaharuddin, Mohd Faridh Ahmad bin Ghazali, Che Mohd Ruzaidi Centre of Excellence Geopolymer and Green Technology Universiti Malaysia Perlis Malaysia Faculty of Chemical Engineering Technology Universiti Malaysia Perlis Malaysia Faculty of Mechanical Engineering Technology Universiti Malaysia Perlis Malaysia Faculty of Engineering Technology Universiti Tun Hussein Onn Malaysia Johor Malaysia Faculty of Mechanical Engineering Universiti Malaysia Pahang Malaysia Faculty of Mechanical and Manufacturing Engineering Technology Universiti Teknikal Melaka Malaysia School of Mechanical Engineering Universiti Teknologi Malaysia Malaysia Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Malaysia

Deep learning based on mixed-variable physics informed neural network for solving fluid dynamics without simulation data

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Guang-Tao Cheng, Chen Liu, Shu-Dong Chen, Yang Li, Yong-Zheng Department of Mathematics Faculty of Science and Technology University of Macau Macau China School of Naval Architecture and Ocean Engineering Jiangsu University of Science and Technology Jiangsu China College of Mathematics and Informatics South China Agricultural University Guangdong China

Deep learning method has attracted tremendous attention to handle fluid dynamics in recent years. However, the deep learning method requires much data to guarantee the generalization ability and the data of fluid dynamics are deficient. Recently, physics informed neural network (PINN) is popular to solve the fluid flow problems, which basic concept is to embed the governing equation and continuity equation into loss function, with the requirement of less dataset for obtaining a reliable neural network. In this paper, the mixed-variable PINN method, which convert the governing equation into continuum and constitutive formulations, is proposed to solve the fluid dynamics (flow past cylinder) without any labeled data. The initial/boundary conditions with penalty factors are also embedded into the loss function to become a well-imposed problem. The results show that mixed-variable PINN has better predictive ability to construct the flow field than traditional PINN scheme. Furthermore, the transfer learning method is adopted to is solve the fluid solutions with different Reynold numbers with less computational cost. The results also demonstrate that the transfer learning method can well simulate the different Reynolds number in a short *** Codes 76F65 Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

Deep learning based on PINN for solving 2 D0F vortex induced vibration of cylinder with high reynolds number

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cheng, Chen Xu, Peng-Fei Li, Yong-Zheng Zhang, Guang-Tao College of Harbor Coastal and Offshore Engineering Hohai University Jiangsu China College of Mathematics and Informatics South China Agricultural University Guangdong China School of Naval Architecture and Ocean Engineering Jiangsu University of Science and Technology Jiangsu China

Vortex-induced vibration (VIV) exists widely in natural and industrial fields. The main approaches for solving VIV problems are numerical simulations and experimental methods. However, experiment methods are difficult to obtain the whole flow field information and also high-cost while numerical simulation is extraordinary time-consuming and limited in low Reynolds number and simple geometric configuration. In addition, numerical simulations are difficult to handle the moving mesh technique. In this paper, physics informed neural network (PINN) is proposed to solve the VIV and wake-induced vibration (WIV) of cylinder with high Reynolds number. Compared to tradition data-driven neural network, the Reynolds Average Navier-Stokes (RANS) equation, by implanting an additional turbulent eddy viscosity, coupled with structure’s dynamic motion equation are also embedded into the loss function. Training and validation data is obtained by computational fluid dynamic (CFD) technique. Three scenarios are proposed to validate the performance of PINN in solving VIV and WIV of cylinders. In the first place, the stiffness parameter and damping parameter are calculated via limited force data and displacement data;secondly, the flow field and lifting force/drag force are inferred by scattered velocity information;eventually, the displacement can be directly predicted only through lifting forces and drag forces based on LSTM. Results demonstrate that, compared with traditional neural network, PINN method is more effective in inferring and re-constructing the unknown parameters and flow field with high Reynolds number under VIV and WIV circumstances. Copyright © 2021, The Authors. All rights reserved.

关键词： Fluid structure interaction

Incorporating Lambertian priors into surface normals measurement

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ju, Yakun Jian, Muwei Guo, Shaoxiang Wang, Yingyu Zhou, Huiyu Dong, Junyu Department of Computer Science and Technology Ocean University of China Qingdao China School of Information Science and Engineering Linyi University Linyi China School of Computer Science and Technology Shandong University of Finance and Economics Jinan China Department of Informatics University of Leicester Leicester United Kingdom

The goal of photometric stereo is to measure the precise surface normal of a 3D object from observations with various shading cues. However, non-Lambertian surfaces influence the measurement accuracy due to irregular shading cues. Despite deep neural networks have been employed to simulate the performance of non-Lambertian surfaces, the error in specularities, shadows, and crinkle regions is hard to be reduced. In order to address this challenge, we here propose a photometric stereo network that incorporates Lambertian priors to better measure the surface normal. In this paper, we use the initial normal under the Lambertian assumption as the prior information to refine the normal measurement, instead of solely applying the observed shading cues to deriving the surface normal. Our method utilizes the Lambertian information to reparameterize the network weights and the powerful fitting ability of deep neural networks to correct these errors caused by general reflectance properties. Our explorations include: the Lambertian priors (1) reduce the learning hypothesis space, making our method learn the mapping in the same surface normal space and improving the accuracy of learning, and (2) provides the differential features learning, improving the surfaces reconstruction of details. Extensive experiments verify the effectiveness of the proposed Lambertian prior photometric stereo network in accurate surface normal measurement, on the challenging benchmark dataset. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks