检索结果-内蒙古大学图书馆

Crysformer:An attention-based graph neural network for properties prediction of crystals

Chinese Physics B 2023年第9期32卷 15-20页

作者：王田陈家辉滕婧史金钢曾新华 Hichem Snoussi Institute of Artificial Intelligence SKLSDEBeihang UniversityBeijing 100191China Zhongguancun Laboratory Beijing 100191China School of Aeronautic Science and Engineering Beihang UniversityBeijing 100191China School of Control and Computer Engineering North China Electric Power UniversityBeijing 102206China School of Software Engineering Xi'an Jiaotong UniversityXi'an 710049China Academy for Engineering and Technology Fudan UniversityShanghai 200433China Charles Delaunay Institute University of Technology of TroyesTroyes Cedex 10004France

We present a novel approach for the prediction of crystal material properties that is distinct from the computationally complex and expensive density functional theory(DFT)-based ***,we utilize an attention-based graph neural network that yields high-accuracy *** approach employs two attention mechanisms that allow for message passing on the crystal graphs,which in turn enable the model to selectively attend to pertinent atoms and their local environments,thereby improving *** conduct comprehensive experiments to validate our approach,which demonstrates that our method surpasses existing methods in terms of predictive *** results suggest that deep learning,particularly attention-based networks,holds significant promise for predicting crystal material properties,with implications for material discovery and the refined intelligent systems.

关键词： deep learning property prediction crystal attention networks

来源：评论

学校读者我要写书评

暂无评论

Characterization of the velocity and concentration of pneumatically conveyed particles in the upstream of an acoustic emission waveguide through CFD-DEM modelling and electrostatic sensing

Characterization of the velocity and concentration of pneuma...

引用

作者： Zeng, Xingxing Yan, Yong Qian, Xiangchen Lu, Yunlong School of Control and Computer Engineering North China Electric Power University Beijing China Hangzhou International Innovation Institute Beihang University Hangzhou China

Characterization of the velocity and concentration of pneumatically conveyed particles in the upstream of the waveguide protruded into the flow is essential for measuring the mass flow rate and size distribution of particles using acoustic emission methods. Computational fluid dynamics-discrete element method (CFD-DEM) is employed in this paper to simulate the collisions between particles and waveguides with a varying protrusion depth in a vertical pipe. Then an instrumentation system incorporating electrostatic sensors is developed to measure the particle velocity and concentration in the upstream of the waveguide. Experimental tests were carried out on a particle flow test rig. The experimental and modelling results show that the waveguide protruded into the flow between 2 and 10 mm results in a reduction in particle velocity of approximately 30%–35 %, and an increase in particle concentration of approximately 3%–20 %. The experimental results show a close agreement with the modelling data. © 2024

关键词： Computational fluid dynamics

来源：评论

学校读者我要写书评

暂无评论

Early Functional Safety and PPA Evaluation of Digital Designs

Early Functional Safety and PPA Evaluation of Digital Design...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Michelangelo Bartolomucci David Kingston Teo Cupaiuolo Alessandra Nardi Riccardo Cantoro Department of Control and Computer Engineering Politecnico di Torino Italy Synopsys Inc.

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

The use of semiconductor devices in safety-critical scenarios is increasing in both quantity and complexity. This paper presents a novel approach to support safety requirements from RTL exploration through to implementation, with the aid of a Safety Specification Format (SSF), thereby minimizing costly development iterations and reducing the Time-To-Market. An assessment of the results is given for the CV32E40P open source RISC-V processor.

关键词： Measurement Degradation Runtime Semiconductor devices Time to market Europe Safety Complexity theory Digital circuits Physical design

来源：评论

学校读者我要写书评

暂无评论

Multi-object Crowd Real-time Tracking in Dynamic Environment Based on Neural Network

Journal of Network Intelligence

引用

Journal of Network Intelligence 2022年第2期7卷 386-394页

作者： Zhang, Fu-Quan Ma, Lin-Juan College of Computer and Control Engineering Minjiang University Fuzhou China Digital Media Art Key Laboratory of Sichuan Province Sichuan Conservatory of Music Chengdu China School of Computer Science and Technology Beijing Institute of Technology Beijing China

In this paper, it proposes a new lightweight neural network detection model and tracking algorithm that enables us to perform multi-object crowd tracking. The technique applied in our study is known as object detection and tracking which is based on neural network and can be calculated and reproduced intelligently according to the movement and behavior of the tracked crowd. Also, a number of experiments have been carried out to test the validity of the accuracy in the algorithm. And it is indicated that the results of the experiments have better performance and can contribute to multi-object crowd real-time tracking with high accuracy, which is similar to the state-of-the-art. All our preliminary results throw light on the nature of detection and tracking and result in a solution of multi-object crowd tracking, and it proves to be fruitful and encouraging. © 2022, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Evaluating Different Fault Injection Abstractions on the Assessment of DNN SW Hardening Strategies

Evaluating Different Fault Injection Abstractions on the Ass...

引用

Asian Test Symposium (ATS)

作者： Giuseppe Esposito Juan-David Guerrero-Balaguera Josie E. Rodriguez Condia Matteo Sonza Reorda Department of Control and Computer Engineering (DAUIN) Politecnico di Torino Turin Italy

ISBN: (数字)9798331529161

ISBN: (纸本)9798331529178

1 The reliability of Neural Networks has gained significant attention, prompting efforts to develop SW-based hardening techniques for safety-critical scenarios. However, evaluating hardening techniques using application-level fault injection (FI) strategies, which are commonly hardware-agnostic, may yield misleading results. This study for the first time compares two FI approaches (at the application level (APP) and instruction level (ISA)) to evaluate deep neural network SW hardening strategies. Results show that injecting permanent faults at ISA (a more detailed abstraction level than APP) changes completely the ranking of SW hardening techniques, in terms of both reliability and accuracy. These results highlight the relevance of using an adequate analysis abstraction for evaluating such techniques.

关键词： Degradation Fault tolerance Accuracy Simulation Fault tolerant systems Artificial neural networks Color Reliability engineering Safety Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Research and Implementation of Image Defogging Based on Deep Learning 6

Research and Implementation of Image Defogging Based on Deep...

引用

6th International Conference on computer Network, Electronic and Automation, ICCNEA 2023

作者： Li, Ao Wang, Zhongsheng Xi'an Technological University School of Computer Science and Engineering Xi'an710021 China Xi'an Technological University State and Provincial Joint Engineering Lab. of Advanced Network Monitoring and Control Xi'an China

ISBN: (纸本)9798350305388

Image degradation due to fog and haze is a common problem in the field of life and image research. This article will be designed and implemented of image haze removal algorithm. The traditional methods have some problems such as low brightness, artifact, halo and distortion, but the existing methods based on deep learning have better effect. In this paper, we will propose a de-fogging network model, which is based on adversarial network. The generator in adversarial network is a convolutional neural network with residual network, which reduces the model training parameters and improves the parameter utilization. The discriminator uses the full convolutional network as the discriminator, which enhances the spatial sensitivity of the model to the image. In order to improve efficiency, the discriminator is simplified on the original structure. The loss function of the model is improved so that the model can get better training effect. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Sensor Fault Detection and Identification of a Photovoltaic System Based on Sliding Mode Observer

Sensor Fault Detection and Identification of a Photovoltaic ...

引用

IEEE SSD International Multi-Conference on Systems, Signals and Devices

作者： Maouadda Ismail Karim Dahech Laboratory of “sciences and techniques of automatic control & computer engineering ” University of Sfax Sfax Tunisia

ISBN: (数字)9798331542726

ISBN: (纸本)9798331542733

The growing emphasis on sustainability and green energy in electricity generation has led researchers to focus on improving photovoltaic systems. Consequently, a reliable fault diagnosis method is crucial for protecting and maintaining the performance of PV systems. This paper introduces a fault detection approach utilizing a sliding mode observer to detect sensor faults in a standalone photovoltaic system. The method is based on residual generation, which identifies faults by comparing residuals with specific threshold values. The standalone photovoltaic test bench includes a boost converter that facilitates maximum power point tracking using the perturb and observe method for the load. Simulations are carried out in MATLAB/Simulink under stable temperature and varying irradiance conditions to evaluate the effectiveness and robustness of the proposed fault detection technique.

关键词： Photovoltaic systems Fault diagnosis Temperature sensors Maximum power point trackers Uncertainty Fault detection System performance Observers Robustness Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Hunger games search optimization with deep learning model for sustainable supply chain management

引用

Discover Internet of Things 2023年第1期3卷 10页

作者： Xu, Zheng Jain, Deepak Kumar Neelakandan, S. Abawajy, Jemal School of Computer and Information Engineering Institute for Artificial Intelligence Shanghai Polytechnic University Shanghai201209 China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian116024 China School of Artificial Intelligence Dalian China Symbiosis Institute of Technology Symbiosis International University Pune India Department of Computer Science and Engineering R.M.K Engineering College Taluk India Deakin University Geelong Australia

The supply chain network is one of the most important areas of focus in the majority of business circumstances. Blockchain technology is a feasible choice for secure information sharing in a supply chain network. Despite the fact that maintaining security at all levels of the blockchain is difficult, cryptographic methods are commonly used in existing works. Effective supply chain management (SCM) offers various benefits to organizations, such as enhanced customer satisfaction, increased operational efficiency, competitive advantage, and cost reduction. Potential SCM for agricultural and food supply chains needs distributors, coordination and collaboration among farmers, retailers, and stakeholders. The use of technology like Block Chain (BC), sensors, and data analytics, can boost traceability and visibility, decrease waste, and ensure safety and quality throughout the supply chain. Therefore, this study develops a Hunger Games Search Optimization with Deep Learning Model for Sustainable agricultural and food Supply Chain Management (HGSODL-ASCM) technique. The fundamental goal of the HGSODL-ASCM technique is to improve decision-making processes for agricultural and food commodity production and storage in order to optimise revenue. In the provided HGSODL-ASCM technique, a bidirectional long short-term memory (Bi-LSTM) model is built to determine the amount of productivity and storage required to maximise profit. In order to boost the performance of the Bi-LSTM classification process, the HGSO algorithm has been utilized in this work. The presented HGSODL-ASCM technique can independently achieve the SCM policies via interaction with complicated and adaptive environments. A brief set of simulations were performed to ensure the improved performance of the HGSODL-ASCM technique. The simulation results demonstrated how superior the HGSODL-ASCM method is to other methods already in use. © The Author(s) 2023.

关键词： Food supply

来源：评论

学校读者我要写书评

暂无评论

Optimisation of occlusion data based on graph neural networks with joint objectives 4

Optimisation of occlusion data based on graph neural network...

引用

4th International Conference on Machine Learning, Big Data and Business Intelligence, MLBDBI 2022

作者： Lu, Lianwen Cui, Yuhan Lu, Xinghua Qiu, Jitao Ye, Zongyuan Institute of Computer Control Technology Guangzhou Huali College Guangzhou China Guangzhou Huali College School of Computer and Information Engineering Guangzhou China

ISBN: (纸本)9798350333947

This paper proposes a data federation multiobjective tracking (MOT) method based on a graph neural network framework, where a graph-based approach merges the optimisation data between multiple objects in the same frame and between objects in the preceding and following frames into the feature learning task. This approach uses the data logic and topological properties of graphs, combined with detectors to encapsulate the neighbourhood information of each node, in order to construct an association graph between multi-objective multi-features with the inference logic of optimised occlusion data, which is then learned by linear filtering to constrain feature score similarity. Finally, this paper conducts comparative experiments on the MOT dataset. By comparing the experimental index data of MOT15/17/20, the outstanding performance of this paper's method can be effectively demonstrated. © 2022 IEEE.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation of a Coriolis flowmeter for measuring mass flow rate of CO2 with impurities under CCS conditions

Performance evaluation of a Coriolis flowmeter for measuring...

引用

作者： Wang, Qin Yan, Yong Zhang, Wenbiao Zhang, Yichen Li, Haoyang School of Control and Computer Engineering North China Electric Power University Beijing China Hangzhou International Innovation Institute Beihang University Hangzhou China

Accurate mass flowrate measurement of CO2 with impurities in CCS transportation pipelines is challenging. The presence of impurities affects the phase behavior and physical properties of CO2-rich mixtures. This increases the difficulty in flow metering for financial accounting and custody transfer. In this paper, the performance of a Coriolis flowmeter for measuring the mass flowrate of CO2 with impurities is evaluated. Experiments were conducted on a 50 mm bore horizontal pipeline on a purpose-built gas-liquid two-phase flow test rig for fluid temperature of 10∼18 °C and pressure of 50∼70 bar. The mass flowrate of liquid CO2 is between 1000 kg/h and 3000 kg/h, and the gas volume fraction of the impurity gas is up to 15 %. Pure N2 was injected into the test section as an impurity gas. An MLP model is established to reduce the errors in CO2 mass flowrate measurement with impurities. © 2024

关键词： Flowmeters

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：