检索结果-内蒙古大学图书馆

Enhanced Brain Tumor Detection Using Transfer Learning with Fine-Tuned Efficientnet-B3 Blocks and Graph-Based Spatial Attention Capsule Networks 21

Enhanced Brain Tumor Detection Using Transfer Learning with ...

引用

21st International Computer Conference on Wavelet Active Media technology and Information Processing, ICCWAMTIP 2024

作者： Aggrey, Esther Stacy E.B Zhen, Qin Kodjiku, Seth Larweh Fiasem, Delali Linda Sey, Collins Ejiyi, Chukwuebuka Joseph Ntia, Nsikakabasi Williamson School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China School of Computer Science and Technology Zhejiang Gongshang University Hangzhou China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu China

ISBN: (纸本)9798331519254

Brain tumors are critical medical conditions that require timely and accurate diagnosis to improve survival outcomes. This research proposes a cutting-edge framework for brain tumor classification, combining fine-tuned EfficientNet-B3 blocks with graph-based spatial attention capsule networks. By addressing challenges such as limited data availability, overfitting, and the complex nature of tumor structures, the framework employs partial transfer learning, advanced feature extraction, and attention mechanisms to effectively model spatial relationships in MRI images. Evaluated on a dataset of 3,064 contrast-enhanced brain MRI images, the model demonstrated exceptional performance, achieving 99.85% classification accuracy and notable improvements in precision, recall, and F1 scores for glioma, meningioma, and pituitary tumours. The use of advanced data augmentation techniques significantly improved the model's ability to generalize, while its computational efficiency makes it well-suited for clinical diagnostic applications. © 2024 IEEE.

关键词： Dynamic contrast enhanced MRI

来源：评论

学校读者我要写书评

暂无评论

A digital multi-channel system based on parallel full comparison baseline restoration method 4

A digital multi-channel system based on parallel full compar...

引用

4th International Conference on Electronic Information engineering and Computer Communication, EIECC 2024

作者： Liu, Yang Xu, Mingxing Wang, Guangxi Yang, Yufeng Chengdu University of Technology College of Nuclear Technology and Automation Engineering Cheng Du China Key Laboratory of Sichuan Province Chengdu University of Technology Cheng Du China

ISBN: (纸本)9798331534622

This paper designs a baseline estimation digital energy spectrum measurement system using a parallel full-comparison method, aimed at reducing the impact of baseline drift on the energy resolution of the digital energy spectrum measurement system. The system consists of two parts: an analog baseline adjustment circuit and a digital baseline estimation module. The digital module first performs baseline estimation, then transmits the results to the frontend circuit to adjust the baseline, thereby correcting drift caused by circuit noise and signal pulse stacking. The system is mainly composed of a DAC baseline adjustment circuit, an ADC sampling circuit, and an FPGA-based digital multi-channel analysis system, in which a parallel full-comparison mean baseline estimation method is deployed to calculate the baseline adjustment amount. To verify the reliability of the system, NaI detectors were used in this study, and the energy resolution and response of the system were tested using dual-source137Cs and60Co. The experimental results show that the linear response fitting of the digital multi-channel energy spectrum measurement system exceeds 99.99%. Under high counting rates, the energy resolution without baseline recovery was 8.83% (@0.662 keV), while the energy resolution with the parallel full-comparison baseline recovery method was 7.57% (@0.662 keV), improving by 0.92%. In conclusion, compared to the system without baseline recovery, the parallel full-comparison baseline recovery method effectively alleviates the baseline drift issue of the NaI detector under high counting rates, thereby improving the energy resolution of the system. © 2024 IEEE.

关键词： Velocity measurement

来源：评论

学校读者我要写书评

暂无评论

Event-triggered predefined-time control for full-state constrained nonlinear systems: A novel command filtering error compensation method

引用

Science China(Technological Sciences) 2024年第9期67卷 2867-2880页

作者： PAN YingNan CHEN YiLin LIANG HongJing College of Control Science and Engineering Bohai UniversityJinzhou 121013China School of Automation Engineering University of Electronic Science and Technology of ChinaChengdu 611731China Laboratory of Electromagnetic Space Cognition and Intelligent Control Beijing 100089China

In this paper, a command filter-based adaptive fuzzy predefined-time event-triggered tracking control problem is investigated for uncertain nonlinear systems with time-varying full-state constraints. By designing a sliding mode differentiator, the inherent computational complexity problem within the predefined-time backstepping framework is solved. Different from the existing command filter-based finite-time and fixed-time control strategies that the convergence time of the filtering error is adjusted through the system initial value or numerous parameters, a novel command filtering error compensation method is presented,which tunes one control parameter to make the filtering error converge in the predefined time, thereby reducing the complexity of design and analysis of processing the filtering error. Then, an improved event-triggered mechanism(ETM) that builds upon the switching threshold strategy, in which an inverse cotangent function is designed to replace the residual term of the ETM,is proposed to gradually release the controller's dependence on the residual term with increasing time. Furthermore, a tan-type nonlinear mapping technique is applied to tackle the time-varying full-state constraints problem. By the predefined-time stability theory, all signals in the uncertain nonlinear systems exhibit predefined-time stability. Finally, the feasibility of the proposed algorithm is substantiated through two simulation results.

关键词： predefined-time control command filtering error compensation method event-triggered mechanism time-varying full-state constraints uncertain nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Comparative Evaluation of Several Types of Passive Damping Branches for Grid-Connected Inverters under Passivity 10

Comparative Evaluation of Several Types of Passive Damping B...

引用

10th IEEE International Power Electronics and Motion Control Conference, IPEMC 2024 ECCE Asia

作者： Ma, Guangda Xie, Chuan Li, Cheng Han, Yang Wang, Weijun Zou, Jianxiao University of Electronic Science and Technology of China School of Automation Engineering Chengdu China University of Electronic Science and Technology of China School of Mechanical and Electrical Engineering Chengdu China

ISBN: (纸本)9798350351330

The passive damping (PD) branches based on passive design can provide sufficient passivity compensation to the output admittance of the grid-connected inverter (GCI) at the cost of low damping loss. However, the type of passivity-based PD branch is only considered on the shunt RC branch in recent reports. This paper investigates the passivity compensation capabilities of several types of PD branches. Furthermore, design guidelines for the different types of PD branches are presented based on their passive properties and damping loss. Finally, the design example is given to verify the correctness of the proposed design guidelines. © 2024 IEEE.

关键词： Design

来源：评论

学校读者我要写书评

暂无评论

FPGA-based acceleration for binary neural networks in edge computing

引用

Journal of Electronic Science and technology 2023年第2期21卷 65-77页

作者： Jin-Yu Zhan An-Tai Yu Wei Jiang Yong-Jia Yang Xiao-Na Xie Zheng-Wei Chang Jun-Huan Yang School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu610054China School of Automation Chengdu University of Information TechnologyChengdu610225China State Grid Sichuan Electric Power Research Institute Chengdu610095China Department of Information Sciences and Technology George Mason UniversityFairfaxVA22030USA

As a core component in intelligent edge computing,deep neural networks(DNNs)will increasingly play a critically important role in addressing the intelligence-related issues in the industry domain,like smart factories and autonomous *** to the requirement for a large amount of storage space and computing resources,DNNs are unfavorable for resource-constrained edge computing devices,especially for mobile terminals with scarce energy *** of DNN has become a promising technology to achieve a high performance with low resource consumption in edge ***-programmable gate array(FPGA)-based acceleration can further improve the computation efficiency to several times higher compared with the central processing unit(CPU)and graphics processing unit(GPU).This paper gives a brief overview of binary neural networks(BNNs)and the corresponding hardware accelerator designs on edge computing environments,and analyzes some significant studies in *** performances of some methods are evaluated through the experiment results,and the latest binarization technologies and hardware acceleration methods are *** first give the background of designing BNNs and present the typical types of *** FPGA implementation technologies of BNNs are then *** comparison with experimental evaluation on typical BNNs and their FPGA implementation is further ***,certain interesting directions are also illustrated as future work.

关键词： Accelerator Binarization Field-programmable gate array(FPGA) Neural networks Quantification

来源：评论

学校读者我要写书评

暂无评论

FEASIBILITY AND SAFETY ANALYSIS OF SOLID-STATE REACTOR FOR LUNAR SURFACE EXPLORATION 31

FEASIBILITY AND SAFETY ANALYSIS OF SOLID-STATE REACTOR FOR L...

引用

2024 31st International Conference on Nuclear engineering, ICONE 2024

作者： Yugao, Ma Jiahao, Lu Yue, Liu Suyi, Zhang Muhao, Zhang Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu610213 China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu610059 China

ISBN: (纸本)9780791888247

The Fission Surface Power System is a feasible solution for future lunar surface exploration energy supply, with the solid-state reactor being considered a primary candidate. This paper presents a modeling and analysis of a solid-state reactor based on publicly available information. Using the reactor Monte Carlo program RMC and the commercial finite element analysis software ANSYS, the reactor is modeled and analyzed. The power distribution of the active zone and reactivity feedback coefficients of the entire core are obtained. The result indicates a negative reactivity feedback coefficient, confirming this reactor design's inherent safety. Furthermore, a two-dimensional reactor model is constructed to obtain the temperature distribution during full-power operation, and non-passive residual heat removal analysis and radiative heat loss failure analysis are performed. At the failure condition of all heat pipes, the maximum core temperature is 742 K, which is below the reactor safety temperature limit, confirming the residual heat removal capability of the solid-state reactor in the loss of heat sink. Additionally, the self-developed transient reactor system analysis program is used for thermal safety analysis. The thermal parameters and heat transfer limits of high-temperature alkali metal heat pipes within the reactor are obtained, with the ratio of heat transfer limit to the heat load of 2.05 demonstrating sufficient safety margins of the heat pipe operation in the reactor. The results manifest that the core is satisfied with the existing criteria for anticipated operating occurrences of solid-state reactors, verifying the excellent safety performance of this reactor design. Based on the analysis and calculations in this study, it is concluded that this reactor design exhibits superior safety performance, which is attributed to the neutron physics design concept of the intermediate neutron spectrum and the thermal-hydraulic design concept of non-passive residual h

关键词： Lunar surface analysis

来源：评论

学校读者我要写书评

暂无评论

Distributed Unknown Input Observer-Based Global Fault-Tolerant Average Consensus Control for Linear Multi-Agent Systems 14

Distributed Unknown Input Observer-Based Global Fault-Tolera...

引用

14th International Conference on Information Science and technology, ICIST 2024

作者： Yang, Ximing Li, Tieshan Long, Yue Yang, Hanqing School of Automation Engineering University of Electronic Science and Technology of China Chengdu611731 China

ISBN: (纸本)9798350353334

The paper mainly investigates the distributed unknown input observer-based global fault-tolerant average consensus control problem for multi-agent systems (MASs). First, a distributed unknown input observer based on relative estimation error is proposed, which can effectively reduce the impact of external disturbances and achieve accurate estimation of the agent states and the faults they suffered. Then, based on the obtained accurate estimations and using the relative estimation error, a global fault-tolerant average consensus controller is proposed. The proposed controller can compensate for the effects of faults and enable the MASs to achieve global average consensus. Finally, simulations are given to verify the effectiveness of the proposed scheme. © 2024 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

High-sensitivity phase imaging eddy current magneto-optical system for carbon fiber reinforced polymers detection

引用

Journal of Electronic Science and technology 2023年第4期21卷 48-59页

作者： Jiang-Shan Ai Quan Zhou Yi-Ping Liang Chun-Rui Feng Bing Long Li-Bing Bai Yong-Gang Wang Chao Ren School of Automation Engineering University of Electronic Science and Technology of ChinaChengdu611731China Department of Mechanical Engineering Catholic University of LeuvenLeuven3001Belgium Chengdu Aircraft Industry Company Ltd. Chengdu610091China

This paper proposed a high-sensitivity phase imaging eddy current magneto-optical (PI-ECMO) system for carbon fiber reinforced polymer (CFRP) defect detection. In contrast to other eddy current-based detection systems, the proposed system employs a fixed position excitation coil while enabling the detection point to move within the detection region. This configuration effectively mitigates the interference caused by the lift-off effect, which is commonly observed in systems with moving excitation coils. Correspondingly, the relationship between the defect characteristics (orientation and position) and the surface vertical magnetic field distribution (amplitude and phase) is studied in detail by theoretical analysis and numerical simulations. Experiments conducted on woven CFRP plates demonstrate that the designed PI-ECMO system is capable of effectively detecting both surface and internal cracks, as well as impact defects. The excitation current is significantly reduced compared with traditional eddy current magneto-optical (ECMO) systems.

关键词： Carbon fiber reinforced polymers Defect detection Eddy current magneto-optical Nondestructive testing Phase imaging

来源：评论

学校读者我要写书评

暂无评论

A Fast Measurement Method of Temperature Field on High Temperature Surface Based on Color CCD 7

A Fast Measurement Method of Temperature Field on High Tempe...

引用

7th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2024

作者： Tan, Xutong Yin, Chun Liu, Junyang Gao, Yan Yan, Zhongbao School of Automation Engineering University of Electronic Science and Technology of China Chengdu611731 China

ISBN: (纸本)9798350350890

The rapid and accurate measurement of high-temperature fields holds significant implications in the realms of aero-engine measurement, metal welding, and the metallurgical industry. This paper proposes a method for rapid temperature field measurement in high-temperature environments, leveraging a color CCD. Initially, we analyze the sources of error in high-temperature measurement scenarios. Subsequently, we design a rapid temperature field measurement method for high-temperature environments using a Multi-layer Perceptron, which includes model construction and dataset creation that takes into account the sources of high-temperature errors. Using the proposed method, we invert the temperature field to obtain visualization data. The efficacy of the temperature field measurement method is validated and tested through high-temperature experiments using a standard blackbody furnace. Experimental results indicate that the proposed temperature measurement method can measure up to 2000^C, while maintaining a relative low measurement error. This represents a substantial improvement over traditional least squares fitting temperature measurement methods in high-temperature scenarios. © 2024 IEEE.

关键词： Thermography (temperature measurement)

来源：评论

学校读者我要写书评

暂无评论

Study on a Non-collecting Atmospheric Radon Concentration Measurement System 23rd

Study on a Non-collecting Atmospheric Radon Concentration Me...

引用

23rd Pacific Basin Nuclear Conference, PBNC 2022

作者： Tang, Chuanfeng Ge, Liangquan Guo, Shengliang Deng, Zhipeng Li, Jin College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu China College of Nuclear Technology and Automation Engineering Applied Nuclear Technology in Geosciences Key Laboratory of Sichuan Province Chengdu University of Technology Sichuan Chengdu China Chengdu Newray Technology Technology Co. Ltd. Sichuan Chengdu China

ISBN: (纸本)9789819910229

Radon in the atmosphere is an important tracer in meteorology and geology and an important index of environmental radioactivity level evaluation. In this paper, NaI (Tl) scintillator detector was developed to directly measure radon concentration in the atmosphere, and a mathematical model of atmospheric radon gamma measurement was proposed, which solved the technical problem of online real-time monitoring of atmospheric radon concentration. It has important scientific and practical value. In this paper, the characteristic gamma peaks of radon daughters 214Bi (609.31 keV) and 214Pb (351.92 keV) are respectively selected to calculate the radon concentration in the atmosphere. During the measurement period, the variation trend of radon concentration is the same as the theory, which suggests a higher concentration in the morning and a lower in the evening. Finally, the experimental measurement results were compared with the RAD7 radon measuring instrument. The error range of this detection system is 79.73% smaller than that of RAD7 on average, and its detection limit reaches 0.29 Bq/m3 with a 30-min-measurement at room temperature. This paper proves that it is feasible to directly measure the activity concentration of radon in the atmosphere. The atmospheric radon measurement method proposed in this paper can accurately obtain the concentration of atmospheric radon and has the advantages of convenience, large measuring range, low detection limit, and online measurement. © 2023, The Author(s).

关键词： Radioactivity

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：