检索结果-内蒙古大学图书馆

36th International Conference on Software engineering and Knowledge engineering, SEKE 2024

作者： Weng, Jiawen Xia, Zeke Li, Ran Hu, Ming Chen, Mingsong Software/Hardware Co-Design Engineering Research Center Ministry of Education East China Normal University Shanghai China School of Software Nanjing University of Information Science and Technology Nanjing China Research Lab for Intelligent Software Engineering Singapore Management University Singapore

ISBN: (纸本)1891706594

Due to the advantages of privacy-preserving, Federated Learning (FL) is widely used in distributed machine learning systems. However, existing FL methods suffer from low-inference performance caused by data heterogeneity. Specifically, due to heterogeneous data, the optimization directions of different local models vary greatly, making it difficult for the traditional FL method to get a generalized global model that performs well on all clients. As one of the state-of-the-art FL methods, the mutation-based FL method attempts to adopt a stochastic mutation strategy to guide the model training towards a well-generalized area (i.e., flat area in the loss landscape). Specifically, mutation allows the model to shift within the solution space, providing an opportunity to escape areas with poor generalization (i.e., sharp area). However, the stochastic mutation strategy easily results in diverse optimal directions of mutated models, which limits the performance of the existing mutation-based FL method. To achieve higher performance, this paper proposes a novel mutation-based FL approach named FedQP, utilizing a quadratic programming strategy to regulate the mutation directions wisely. By biasing the model mutation towards the direction of gradient update rather than traditional random mutation, FedQP can effectively guide the model to optimize towards a well-generalized area (i.e., flat area). Experiments on multiple well-known datasets show that our quadratic programming-guided mutation strategy effectively improves the inference accuracy of the global model in various heterogeneous data scenarios. © 2024 Knowledge Systems Institute Graduate School. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Risk and Reliability Analysis for MASS A Bibliometric Review of literature from 2015 to 2021 8th

Risk and Reliability Analysis for MASS A Bibliometric Review...

引用

8th International Symposium on Reliability engineering and Risk Management, ISRERM 2022

作者： Li, Zhihong Zhang, Di Han, Bing Wan, Chengpeng Intelligent Transportation Systems Research Center Wuhan University of Technology Wuhan China Wuhan China School of Transportation and Logistics Engineering Wuhan University of Technology Wuhan China Inland Port and Shipping Industry Research Co Ltd. of Guangdong Province Shaoguan China Shanghai Ship and Shipping Research Institute Co Ltd Shanghai China

ISBN: (纸本)9789811851841

Recently, researchers have shown a soared interest in maritime autonomous surface ships (MASSs). High reliability is required to support unmanned operations. Hence, the reliability design and risk evaluation of MASSs are crucial. It is necessary and critical to keep abreast of emerging trends of the development of MASS’s safety and reliability-related technologies. Based on the 54 most relevant articles identified from Website of Science between 2015 and 2021, content analyses and science mapping were conducted in this study from the aspects of journal sources, keywords, countries and institutions, authors, and citation of these publications. The qualitative analysis arrives at the following results: Firstly, the most influential journals and knowledge contributors in this field are Reliability engineering and System Safety (RESS), Ocean engineering (OE), Safety Science (SS). Secondly, previous studies reveals that some most widely discussed research topics include collision avoidance, hazard identification, and risk modelling. Thirdly, the research trend of risk and reliability analysis for MASS in recent years has been extended from the traditional navigational risk assessment ahead to machinery, cyber and human reliability and maintenance. Finally, the Model-Based System engineering (MBSE) and Function Resonance Analysis Method (FRAM) are reckoned as two possible practical methods for future research risk and reliability analysis for MASS. © 2022 ISRERM Organizers. Published by research Publishing, Singapore.

关键词： Ocean engineering

来源：评论

学校读者我要写书评

暂无评论

Different types of drug abusers prefrontal cortex activation patterns and based on machine-learning classification

引用

Journal of Innovative Optical Health Sciences 2022年第2期15卷 83-92页

作者： Banghua Yang Xuelin Gu Shouwei Gao Lin Feng Yan Ding Xu Wen Wang School of Mechanical and Electrical Engineering and Automation Shanghai University Shanghai 200444P.R.China Shanghai Drug Rehabilitation Administration Bureau Shanghai 200080 P.R.China Department of Radiology&Functional and Molecular Imaging Key Lab of Shaanxi Province Tangdu Hospital Fourth Military Medical University Xi'anShaanxi 710038P.R.China Engineering Research Center of Traditional Chinese Medicine Intelligent Rehabilitation Ministry of Education ShanghaiP.R.China Shanghai Intelligent Engineering Technology Research Center for Addiction and Rehabilitation Minhang District 200240 ShanghaiP.R.China

Drug addiction can cause abnormal brain activation changes,which are the root cause of drug craving and brain function *** study enrolled drug abusers to determine the effects of different drugs on brain activation.A functional near-infrared spectroscopy(fNIRS)device was used for the *** study was designed with an experimental paradigm that included the induction of resting and drug addiction *** collected the fNIRS data of 30 drug users,including 10 who used heroin,10 who used Methamphetamine,and 10 who used mixed ***,using Statistical Analysis,the study analyzed the activations of eight functional areas of the left and right hemispheres of the prefrontal cortex of drug addicts who respectively used heroin,Methamphetamine,and mixed drugs,including Left/Right-Dorsolateral prefrontal cortex(L/R-DLPFC),Left/Right-Ventrolateral prefrontal cortex(L/R-VLPFC),Left/Right-Fronto-polar prefrontal cortex(L/R-FPC),and Left/Right Orbitofrontal Cortex(L/R-OFC).Second,referencing the degrees of activation of oxyhaemoglobin concentration(HbO2),the study made an analysis and got the specific activation patterns of each group of the ***,after taking out data which are related to the addicts who recorded high degrees of activation among the three groups of addicts,and which had the same channel numbers,the paper classified the different drug abusers using the data as the input data for Convolutional Neural Networks(CNNs).The average three-class accuracy is 67.13%.It is of great significance for the analysis of brain function errors and personalized rehabilitation.

关键词： Drug addiction fNIRS machine-learning di®erent drug users brain regions activation

来源：评论

学校读者我要写书评

暂无评论

Federated Learning-Driven intelligent Algorithm Platform for Power Grid Inspection Equipment: Design and Implementation 3

Federated Learning-Driven Intelligent Algorithm Platform for...

引用

3rd International Conference on Digital Society and intelligent Systems, DSInS 2023

作者： Lai, Jiayang Yang, Yingyi Wu, Hao Mai, Xiaoming Li, Zhuyun Mei, Peng Intelligent Operation and Inspection Division China Southern Power grid Technology Co. Ltd. Guangzhou510000 China Guangdong Provincial Special Industry Special Robot Engineering Technology Research Center Guangzhou China

ISBN: (纸本)9798350331387

para>This study introduces a novel intelligent Algorithm Platform for Power Grid Inspection Equipment, innovatively designed and implemented leveraging Federated Learning. Traditionally, artificial intelligence algorithms utilized in power grids predominantly follow a centralized architecture, which, unfortunately, poses a substantial risk of data leakage during the transmission process from device terminal to server. Further compounding this issue is the prevailing mistrust between various power suppliers and users, often culminating in a challenging "data island" phenomenon. To address these complications, we propose an innovative solution, integrating federated learning with power grid inspection equipment. This solution ensures the disconnection of data between each regional power grid while performing independent model training on local grid nodes. Utilizing differential privacy technology grounded in the Laplace mechanism, we strategically add noise to the obtained parameters. These noise-infused model parameters are subsequently transmitted to the central node for integration, facilitating a comprehensive and effective utilization of the entire network data. Finally, the central node disseminates the globally refined model parameters to each regional power grid node for regional model enhancement. Comparative results drawn from the traditional centralized training system and the proposed federated learning system reveal remarkable outcomes. Despite maintaining the fundamental accuracy of the model, the federated learning method significantly reduces the communication overhead from 11.86GB to 3.97GB and decreases the model generalization error from 0.96% to a mere 0.82%. Most notably, federated learning offers robust privacy protection for data, thereby substantially mitigating the risk of data leakage. © 2023 IEEE.

关键词： Inspection

来源：评论

学校读者我要写书评

暂无评论

A Convolutional Neural Network Accelerator with High-level Synthesis 4

A Convolutional Neural Network Accelerator with High-level S...

引用

4th IEEE International Conference on Electronic technology, Communication and Information, ICETCI 2024

作者： Yang, Tongxin Li, Chuping Zhang, Ya Luo, Kuan Dong, Zhicheng Li, Jie School of Intelligent Technology and Engineering Chongqing University of Science and Technology Chongqing China Chongqing Taishan Cable Co. Ltd. Chongqing China Chongqing Research Institute Shanghai Jiao Tong University Chongqing China Advanced Technology Research Center Tibet University Xizang China

ISBN: (纸本)9798350361643

The use of hardware description languages (HDLs) and the implementation of techniques like pipelining and dataflow optimization significantly increase the complexity of designing field-programmable gate arrays (FPGAs). This added complexity poses challenges in translating hardware descriptive code into FPGA-recognizable bitstreams. Despite high-level synthesis (HLS) facilitating the translation of C or C++ into HDL and enhancing deployment efficiency, current HLS optimization schemes remain limited, necessitating complex processes and prolonged simulation times. Addressing these challenges, we propose an HLS-based convolutional neural network (CNN) accelerator that constructs various CNN models, including convolutional and pooling modules, using the C language and optimizes resource utilization via diverse HLS directives. Resource utilization is subsequently visualized through simulation and synthesis. Conducting experiments with Vitis 2021.1, our accelerator effectively converts the C-constructed CNN into HDL, markedly reducing resource utilization metrics such as lookup tables and latency. © 2024 IEEE.

关键词： Computer hardware description languages

来源：评论

学校读者我要写书评

暂无评论

Visual-Language Collaborative Representation Network for Broad-Domain Few-Shot Image Classification 24

Visual-Language Collaborative Representation Network for Bro...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Guo, Qianyu Ren, Jieji Wang, Haofen Wu, Tianxing Ge, Weifeng Zhang, Wenqiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China School of Mechanical Engineering Shanghai Jiao Tong University Shanghai China College of Design and Innovation Tongji University Shanghai China School of Computer Science and Engineering Southeast University Nanjing China School of Computer Science Fudan University Shanghai China Engineering Research Center of AI & Robotics Ministry of Education Academy for Engineering & Technology Fudan University Shanghai China

ISBN: (纸本)9798400706868

Visual-language models based on CLIP have shown remarkable abilities in general few-shot image classification. However, their performance drops in specialized fields such as healthcare or agriculture, because CLIP's pre-training does not cover all category data. Existing methods excessively depend on the multi-modal information representation and alignment capabilities acquired from CLIP pre-training, which hinders accurate generalization to unfamiliar domains. To address this issue, this paper introduces a novel visual-language collaborative representation network (MCRNet), aiming at acquiring a generalized capability for collaborative fusion and representation of multi-modal information. Specifically, MCRNet learns to generate relational matrices from an information fusion perspective to acquire aligned multi-modal features. This relationship generation strategy is category-agnostic, so it can be generalized to new domains. A class-adaptive fine-tuning inference technique is also introduced to help MCRNet efficiently learn alignment knowledge for new categories using limited data. Additionally, the paper establishes a new broad-domain few-shot image classification benchmark containing seven evaluation datasets from five domains. Comparative experiments demonstrate that MCRNet outperforms current state-of-the-art models, achieving an average improvement of 13.06% and 13.73% in the 1-shot and 5-shot settings, highlighting the superior performance and applicability of MCRNet across various domains. © 2024 ACM.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of UAV obstacle avoidance based on STM32 3

Design and implementation of UAV obstacle avoidance based on...

引用

3rd International Conference on Mechatronics and Mechanical engineering, ICMME 2024

作者： Hu, Xusheng Liu, Juan Ma'anshan Engineering Technology Research Center for Wireless Sensor Network and IntelliSense Ma’anshan243031 China Anhui Provincial Engineering Laboratory on Information Fusion and Control of Intelligent Robot Wuhu241002 China Ma'anshan Technical College Ma'anshan243030 China

ISBN: (纸本)9781510681651

With the development of remote control and telemetry technology, the application of UAV is more and more extensive, and the requirement of UAV flight control is higher and higher. In order to enhance the stability of UAV hardware system, the power supply part is protected in various ways;a spare chip is added to ensure the effectiveness of attitude calculation;SPI peripheral interface is reserved to expand GPS, ultrasonic and other sensors. Through the mathematical model, the calibration method of accelerometer and gyroscope is introduced, and the importance of this step for flight control system is emphasized. The software flow chart of the system is designed, and the mathematical model of obstacle avoidance algorithm is given. The classic PID control algorithm and simulation method are used to realize the obstacle avoidance of UAV. Considering the problems that may be encountered in UAV obstacle avoidance, the mathematical model is established, the evaluation index is given, and the control experiment is designed. Experimental results show that the algorithm has good obstacle avoidance effect and strong robustness in low speed and complex environment. © 2024 SPIE.

关键词： Three term control systems

来源：评论

学校读者我要写书评

暂无评论

A Dynamics-Constrained Rapid Path-Planning Method for Shipping in Arctic Waters 34th

A Dynamics-Constrained Rapid Path-Planning Method for Shippi...

引用

34th International Ocean and Polar engineering Conference, ISOPE 2024

作者： Sun, Youguo Wu, Da Zhang, Jinfen Lang, Xiao Ringsberg, Jonas W. Mao, Wengang Cui, Meng State Key Laboratory of Maritime Technology and Safety Wuhan University of Technology Wuhan China National Engineering Research Center for Water Transport Safety Wuhan University of Technology Wuhan China Intelligent Transportation Systems Research Center Wuhan University of Technology Wuhan China Department of Mechanics and Maritime Sciences Chalmers University of Technology Gothenburg Sweden Marine Design and Research Institute of China Shanghai China

ISBN: (纸本)9781880653784

The challenge of Arctic sea ice environments is crucial for Arctic shipping. To address this concern, we propose an innovative method for ship path planning to enhance navigation safety and efficiency in Arctic waters. Firstly, a 3D risk grid map for path planning is developed based on POLARIS. The JPS algorithm searchesfor key nodes on the 2D layers sliced from the 3D risk grid map with given risk values. Secondly, key nodes indicating different risk values are pruned to form a roadmap for path-finding. Then, the Dijkstra algorithm is employed to find the reference path yielding the lowest navigation risk from the roadmap. Finally, the ship's trajectory is optimized through optimal control to guarantee the ship's maneuver feasibility. Experiments are carried out to demonstrate the performance of the optimized trajectory, and the outcomes validate the proposed method, demonstrating its capability of rapidly planning safe and executable paths for Arctic shipping. © 2024 by the International Society of Offshore and Polar Engineers (ISOPE).

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

The effect of laser shock peening on surface characteristics of titanium alloy 7

The effect of laser shock peening on surface characteristics...

引用

Advanced Laser Processing and Manufacturing VII 2023

作者： Wang, Hao Ma, Yongxin Lu, Yue Zhu, Jiaxi Bai, Yongtao Guo, Qingchuan Hu, Lunzhen Zhang, Xuanjun Song, Xiaohang Shanghai Engineering Research Center of Laser Intelligent Manufacturing Shanghai Institute of Laser Technology Co. Ltd. Shanghai200233 China State Key Laboratory of Solidification Processing Northwestern Polytechnical University Xi’an710072 China School of Civil Engineering/Research Center of Steel Structures Chongqing University 400045 China Center for Laser and Optics Anhui University Hefei230088 China Shanghai Academy of Science and Technology Shanghai200233 China

ISBN: (纸本)9781510667730

Laser shock peening is an effective surface technology for improving the surface mechanical properties of metals. Many studies have been performed to process different kinds of metallic material that can induce compressive residual stress in the top layer of samples, which would extend the fatigue life of metal parts in the industry. The titanium alloy samples are treated by laser shock peening with water layer as constraint layer and without protective coating in this research, after which the titanium alloy samples are observed and analyzed with a scanning electron microscope, hardness tester, laser confocal microscope, and wear tester. The surface roughness, surface microstructure, and other properties of untreated and treated titanium alloy are compared to study the effect on titanium alloy of laser shock peening process without protective coating. © 2023 SPIE.

关键词： Surface roughness

来源：评论

学校读者我要写书评

暂无评论

Two-dimensional Microwave Through-wall Imaging Algorithm Based on Total Variational Compressive Sensing

Two-dimensional Microwave Through-wall Imaging Algorithm Bas...

引用

Progress in Electromagnetic research Symposium (PIERS)

作者： C. Zhou C. X. Yang M. S. Tong Shanghai Engineering Research Center of Intelligent Education and Bigdata Shanghai Normal University China Shanghai Institute of Intelligent Science and Technology Tongji University China

ISBN: (数字)9798350375909

ISBN: (纸本)9798350375916

Microwave imaging is a technique that uses information as a carrier. It enables non-contact acquisition of information from unknown targets, playing a pivotal role in various applications such as radar detection, medical imaging, and industrial inspection. However, practical applications often face challenges in meeting the requirements of traditional imaging algorithms due to limitations imposed by observation environments or economic constraints. Therefore, it is of great research value to explore how limited measurement data can be effectively utilized for reconstructing the target under test. Compressed sensing technology enables high-precision signal reconstruction with sampling frequencies lower than the Nyquist frequency, but its application scope is greatly restricted by the requirement for sparse target distribution measurements, particularly in non-uniform background imaging scenarios. In this study, we propose an inverse scattering method utilizing the total variation-based compressed sensing technique. And through-wall imaging scenes are chosen to validate the robustness of the algorithm. Firstly, by incorporating the gradient of the contrast function as a sparse prior, we reformulate the two-dimensional inverse scattering problem in a time-harmonic regime into an equivalent augmented Lagrange problem with the use of the first-order Born approximation. Subsequently, we construct a compressed sensing matrix. Then, we repeat the aforementioned steps and iteratively solve for the unknown total field and target to be reconstructed alternatively using the distorted Born iteration method framework until meeting certain convergence criteria. The proposed method effectively addresses the reconstruction problem of scattering targets with piecewise constant contrast, while remaining unaffected by non-uniform background. Numerical simulation results validate both the feasibility and efficiency of our proposed method.

关键词： Inverse problems Imaging Scattering Radar imaging Microwave theory and techniques Frequency measurement Sparse matrices

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：