检索结果-内蒙古大学图书馆

Research on Quality Control of Marine Monitoring Data Based on Extreme Learning Machine 6th

学校读者我要写书评

暂无评论

Research on Quality Control of Marine Monitoring Data Based ...

6th International Conference on Artificial Intelligence and Security, ICAIS 2020

作者： Li, Yuanshu Liu, Feng Wang, Kai Huang, Hai Wei, Fenglin Qi, Hong College of Computer Science and Technology Jilin University Changchun China Department of Computer Science and Technology College of Information and Controlling Engineering Jilin Institute of Chemical Technology Jilin China

ISBN: (纸本)9783030578831

The collection and research of marine monitoring data are the main work of marine science. How to obtain the observation data of un-known sea area is of great significance to marine scientific research. Using the data provided by the Argo project, in this work we aim to effectively predict the marine monitoring data with the extreme learning machine which is simple in structure with short training time, in order to achieve the accuracy of marine information. According to the size of the sample for adjusting the corresponding model parameters, the pre-diction of marine data can be achieved. By comparing the forecast data of the unknown sea area and the data originally provided by the Argo plan, the accuracy of the ocean data is higher and the trend of the reflected data is more detailed. © 2020, Springer Nature Switzerland AG.

关键词： Forecasting

Wms-Based Near-Infrared On-Chip Acetylene Sensor Using Polymeric Su8 Archimedean Spiral Waveguide with Euler S-Bend

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Zhao, Huan Zheng, Chuantao Pi, Mingquan Liang, Lei Song, Fang Zhang, Yu Wang, Yiding Tittel, Frank K. State Key Laboratory of Integrated Optoelectronics College of Electronic Science and Engineering Jilin University Changchun130012 China State Key Laboratory of Luminescence and Applications Changchun Institute of Optics Fine Mechanics and Physics Chinese Academy of Sciences Changchun130033 China Department of Electrical and Computer Engineering Rice University 6100 Main Street HoustonTX77005 United States

Polymeric SU8 waveguide is suitable for large-scale fabrication due to its simple fabrication process and low cost, but it has never been employed for on-chip gas measurement based on infrared absorption. A near-infrared on-chip acetylene (C2H2) sensor using SU8 polymer spiral waveguide was proposed, and the sensing performances based on wavelength modulation spectroscopy (WMS) was verified experimentally for the first time to our knowledge. The proposed Euler-S bend and Archimedean spiral SU8 waveguide reduces the sensor size by more than a half. By virtue of WMS technique, the C2H2 sensing performances of a 7.4cm- and a 13cm-long SU8 waveguide were derived at 1532.83 nm, and the obtained limit of detection (LoD) are 2197.1 and 425.5 parts-per-million (ppm) with an averaging time of 0.2 s, respectively. The experimentally obtained optical power confinement factor (PCF) is 0.0172, which is close to the simulated value of 0.016, and the measured waveguide loss is 3 dB/cm. The rise time and fall time are ~ 2.05 s and ~ 3.27 s, respectively. This work proves that SU8 waveguide has the potential of high-performance on-chip gas sensing in the near-infrared waveband. © 2023, The Authors. All rights reserved.

关键词： Infrared devices

Fast Computation of Electrostatic Interactions for a Charged Polymer with Applied Field

学校读者我要写书评

暂无评论

Chinese Journal of Polymer science 2020年第6期38卷 665-672页

作者： Hao Lin Zi-Tong Lei Ming-Ming Ding Hong-Jun Wang Tong-Fei Shi School of Mathematics Jilin Normal UniversityChangchun 130103China State Key Laboratory of Polymer Physics and Chemistry Changchun Institute of Applied ChemistryChinese Academy of SciencesChangchun 730022China College of Computer Jilin Normal UniversitySi ping 136000China School of Applied Chemistry and Engineering University of Science and Technology of ChinaHefei230026China

Using a hybrid simulation approach that combines a finite difference method with a Brownian dynamics,we investigated the motion of charged *** to the fact that polymer-solution systems often contain a large number of particles and the charged palymer chains are in a state of random motion,it is a time consuming task to calculate the electrostatic interaction of the ***,we propose a new strategy to shorten the CPU time by reducing the iteration *** simulation results ilustrate the effect of preset parameters on CPU time and accuracy,and demonstrate the feasibility of the"local iteration"***,we find that the increase in the number of charged beads has no signifiant infuence on the time of global iterations and local *** a number of 80×80×80 grids,when the relative error is controlled below 1.5%,the computational efficiency is increased by 8.7 times in the case that contains 500 charged *** adition,for a number of 100×100×100 grids with 100 charged beads,the computational efciency can be increased up to 12 *** work provides new insights for the optimization of iterative algorithms in special problems.

关键词： Finite dfference method Brownian dynamics Charged polymers Electrostatic interaction Local iteration

Efficient Self-Learning Evolutionary Neural architecture Search

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Qiu, Zhengzhong Bi, Wei Xu, Dong Guo, Hua Ge, Hongwei Liang, Yanchun Lee, Heow Pueh Wu, Chunguo Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Jilin Changchun130012 China YGSOFT INC Guangdong Zhuhai519085 China Department of Electrical Engineering and Computer Science Informatics Institute Christopher S. Bond Life Sciences Center University of Missouri ColumbiaMO65211 United States College of Computer Science and Technology Dalian University of Technology Liaoning Dalian116081 China School of Computer Science Zhuhai College of Science and Technology Guangdong Zhuhai519041 China Department of Mechanical Engineering National University of Singapore 9 Engineering Drive 1 117575 Singapore

The evolutionary algorithm has become a major method for neural architecture search recently. However, the fixed probability distribution adopted by the traditional evolutionary algorithm makes the algorithm unable to control the increase or decrease of the individual architecture size and thus cannot guarantee the lightweight and inference efficiency of the candidate architecture. In addition, the existing approaches cannot learn the optimal sampling probability distribution relevant to the specific problem from the empirical information accumulated through the search process. What’s more, the algorithm needs to evaluate the performance of all the individual architectures, which requires huge computing resources and time overhead. To overcome these problems and challenges, an Efficient Self-learning Evolutionary Neural architecture Search method, called ESE-NAS, is presented in this paper. Firstly, we propose a Model Size Control module, which generates the probability distribution for sampling the type of mutation operators according to the current model size, so as to control both the node number of network architecture and the sparsity of links, therefore ensuring that neural architectures can remain compact and efficient as they evolve. Thereafter, a Mutation Candidate Credit Assignment method is proposed, which enables the algorithm to dynamically adjust the probability distribution for available types of node operations and directed links according to the empirical information from individuals’ performance evaluation, which can guide the evolutionary direction of neural architecture and shorten the first hitting time of the optimal architecture. Finally, a neural architecture performance predictor is formulated, and the accuracy of each individual architecture is predicted by using the simplified input features, to further improve the efficiency of neural architecture search. Experiments show that the ESE-NAS method proposed in this paper can learn a highly i

关键词： Evolutionary algorithms

A comparison study of Ce/La and Ca microalloying on the bio-corrosion behaviors of extruded Mg-Zn alloys

学校读者我要写书评

暂无评论

Journal of Magnesium and Alloys 2020年第4期8卷 1269-1280页

作者： J.H.Chu L.B.Tong Z.H.Jiang D.N.Zou Q.J.Wang S.F.Liu H.J.Zhang School of Metallurgical Engineering Xi'an University of Architecture and TechnologyXi'an 710055China State Key Laboratory of Rare Earth Resources Utilization Changchun Institute of Applied ChemistryChinese Academy of SciencesChangchun 130022China Key Lab of Automobile Materials College of Materials Science and EngineeringJilin UniversityNanling CampusChangchun 130025China

The influences of Ca and Ce/La microalloying on the microstructure evolution and bio-corrosion resistances of extruded Mg-Zn alloys have been systematically investigated in the current *** with single Ca or Ce/La addition,the Ca-Ce/La cooperative microalloying results in an outstanding grain refinement,because the fine secondary phase particles effectively hinder the recrystallized grain *** coarse Ca2Mg6Zn3 phases promote the formation of Ca3(PO4)2 or hydroxyapatite particles during the immersion process and accelerate the dissolution of the corrosion product film,which destroys its integrity and results in the deterioration of anti-corrosive *** Ce/La elements can be dispersed within the conventional Mg7Zn3 phases,which reduce the internal galvanic corrosion between Mg matrix and the secondary phases,leading to an obvious improvement of corrosion ***,the Ca-Ce/La cooperative microalloying achieves a homogenous fine-grained microstructure and improves the protective ability of surface film,which will pave a new avenue for the design of biomedical Mg alloys in the coming future.

关键词： Extruded Mg-Zn alloy Ca and Ce/La microalloying Microstructure evolution Bio-corrosion behaviors

Finite Element Analysis of Induction Heating of 06ni9dr Steel Based on Electromagnetic Thermal Coupling

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Wu, Baigong Zhou, Zhenhu Liang, Darong Zhang, Xiao Zhou, Weipeng Marine Equipment and Technology Institute Jiangsu University of Science and Technology Jiangsu Province Zhenjiang212003 China School of Naval Architecture and Ocean Engineering Jiangsu University of Science and Technology Jiangsu Province Zhenjiang212003 China School of Energy and Power Engineering Changchun Institute of Technology Changchun Jilin130012 China ZhenJiang Intelligent Convergence Marine Technology Co. Ltd Jiangsu Province Zhenjiang212003 China

The primary material used to construct LNG carriers is 06Ni9DR, which exhibits nonlinear variations in physical properties with temperature. Traditional pyrotechnics pollute the environment and are dangerous to the workers, and their ability to fix thin plates is highly dependent on the experience of the employees. The investigation of the electromagnetic induction heating properties for this material is therefore crucial for the heat treatment process involved in building LNG *** work develops a numerical calculation model for the T-shaped coil-based electromagnetic induction heating of 06Ni9DR steel plate. Conduct an investigation of the electric, magnetic, and thermal multi-physics couplings using the COMSOL Multi-physics finite element programme. The distribution of the temperature field during induction heating was calculated in accordance with the parameters of various current intensity, current frequency, magnetizer thickness, air gap, and T-shaped coil distance in the heating process, and an experimental platform was built to verify the accuracy of the numerical calculation of the model, demonstrating that electromagnetic heating can entirely replace conventional pyrotechnics. © 2023, The Authors. All rights reserved.

关键词： Multiphysics

Multi-site MRI classification using Weighted federated learning based on Mixture of Experts domain adaptation

学校读者我要写书评

暂无评论

Multi-site MRI classification using Weighted federated learn...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Tian Bai Yingfang Zhang Yuzhao Wang Yanguo Qin Fa Zhang College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun China The Department of Orthopaedics The Second Hospital of Jilin University Changchun China School of Medical Technology Beijing Institute of Technology Beijing China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Deep learning often requires large amounts of data from different institutions. Federated learning, as a distributed training framework, enables multiple participants to collaboratively train models without collecting data together and hence protecting data privacy, but the datasets from different institutions usually bring the problem of domain shift, which affects the performance of the model. When addressing domain shift, previous works often use a single global model to share parameters. Therefore, we propose a novel method to train multiple public models with different structures under the federated framework to improve the reliability and robustness of the public models. And each participant keeps its own domain-tuned private model, the private model does not share parameters with other participants. We use Mixture of Experts (MoE) domain adaptation to dynamically combine different public models and private model, which utilizes the similarity between different datasets to update the parameters of the public models. We apply the proposed method to the multi-site Magnetic resonance imaging (MRI) end-to-end classification, and the experiments demonstrate its effectiveness.

关键词： Weight measurement Training Adaptation models Three-dimensional displays Federated learning Magnetic resonance imaging Biological system modeling

AoI-Sensitive Data Forwarding with Distributed Beamforming in UAV-Assisted IoT

学校读者我要写书评

暂无评论

arXiv

arXiv 2025年

作者： Lang, Zifan Liu, Guixia Sun, Geng Li, Jiahui Sun, Zemin Wang, Jiacheng Leung, Victor C.M. College of Computer Science and Technology Jilin University Changchun130012 China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore Artificial Intelligence Research Institute Shenzhen MSU-BIT University Shenzhen518115 China Department of Electrical and Computer Engineering The University of British Columbia VancouverV6T 1Z4 Canada

This paper proposes a UAV-assisted forwarding system based on distributed beamforming to enhance age of information (AoI) in Internet of Things (IoT). Specifically, UAVs collect and relay data between sensor nodes (SNs) and the remote base station (BS). However, flight delays increase the AoI and degrade the network performance. To mitigate this, we adopt distributed beamforming to extend the communication range, reduce the flight frequency and ensure the continuous data relay and efficient energy utilization. Then, we formulate an optimization problem to minimize AoI and UAV energy consumption, by jointly optimizing the UAV trajectories and communication schedules. The problem is non-convex and with high dynamic, and thus we propose a deep reinforcement learning (DRL)-based algorithm to solve the problem, thereby enhancing the stability and accelerate convergence speed. Simulation results show that the proposed algorithm effectively addresses the problem and outperforms other benchmark algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

An Enhanced Attentive Implicit Relation Embedding for Social Recommendation

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Ma, Xintao Dong, Liyan Wang, Yuequn Li, Yongli Liu, Zhen Zhang, Hao College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China School of Information Science and Technology Northeast Normal University Changchun130117 China Graduate School of Engineering Nagasaki Institute of Applied Science 536 Aba-machi Nagasaki851-0193 Japan

Nowadays, recommendation system incorporating social networks has attracted a lot of research attention and is widely used to understand user preferences regarding social relations. Besides, graph neural networks(GNNs) have proven to learn graph-structured data effectively. Thus, integrating GNN into social recommendations has become one challenge. Many approaches encode both the user-item interaction and social relations to learn user preference. However, the implicit relations are also crucial to understanding the features of users and items. Thus, we propose the attentive implicit relation embedding for social recommendation(SR-AIR), which models the user-item interaction and social networks, utilizing a graph attention mechanism on implicit relations of users and items. We evaluate our framework on two real-world datasets and demonstrate that our framework performs the best compared with state-of-the-art baselines © 2022, The Authors. All rights reserved.

关键词： Recommender systems