检索结果-内蒙古大学图书馆

Classification of Domestic Refuse in Medical Institutions Based on Transfer Learning and Convolutional Neural Network

引用

Computer Modeling in engineering & Sciences 2021年第5期127卷 599-620页

作者： Dequan Guo Qiao Yang Yu-Dong Zhang Tao Jiang Hanbing Yan School of Control Engineering Chengdu University of Information TechnologyChengdu610225China College of Automation Chongqing University of Posts and TelecommunicationsChongqing400065China Department of Informatics University of LeicesterLeicesterLE17RHUK

The problem of domestic refuse is becoming more and more serious with the use of all kinds of equipment in medical *** matter arouses people’s *** artificial waste classification is subjective and cannot be put accurately;moreover,the working environment of sorting is poor and the efficiency is ***,automated and effective sorting is *** view of the current development of deep learning,it can provide a good auxiliary role for classification and realize automatic *** this paper,the ResNet-50 convolutional neural network based on the transfer learning method is applied to design the image classifier to obtain the domestic refuse classification with high *** comparing the method designed in this paper with back propagation neural network and convolutional neural network,it is concluded that the CNN based on transfer learning method applied in this paper with higher accuracy rate and lower false detection ***,under the shortage situation of data samples,the method with transfer learning and ResNet-50 training model is effective to improve the accuracy of image classification.

关键词： Domestic refuse image classification deep learning transfer learning convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Formulation of Optimization Problems with Radiation Field Phases as Design Variables for Pattern Synthesis of Linear Antenna Arrays

引用

China Communications 2022年第12期19卷 86-100页

作者： Fei Zhao Jun He Sanyou Zeng Changhe Li Qinghui Xu Zhigao Zeng School of Mechanical Engineering and Electronic Information China University of GeosciencesWuhan 430074China Science and Technology on Blind Signal Processing Laboratory Southwest Electronics and Telecommunication Technology Research InstituteChengdu 610041China School of Automation China University of GeosciencesWuhan 430074China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan 430074China College of Computer Hunan University of TechnologyZhuzhou CityHunan Province412007China

Pattern synthesise of antenna arrays is usually complicated optimization problems,while evolutionary algorithms(EAs)are promising in solving these *** paper does not propose a new EA,but does construct a new form of optimization *** new optimization formulation has two differences from the common *** is the objective function is the field error between the desired and the designed,not the usual amplitude error between the desired and the *** difference is beneficial to decrease complexity in some *** second difference is that the design variables are changed as phases of desired radiation field within shaped-region,instead of excitation *** difference leads to the reduction of the number of design variables.A series of synthesis experiments including equally and unequally spaced linear arrays with different pattern shape requirements are applied,and the effectiveness and advantages of the proposed new optimization problems are *** results show that the proposing a new optimization formulation with less complexity is as significant as proposing a new algorithm.

关键词： pattern synthesis evolutionary algorithms linear antenna arrays

来源：评论

学校读者我要写书评

暂无评论

Effects of Gamma Irradiation on the Nutritional Quality and Physicochemical Properties of Morchella Angusticeps

SSRN

引用

SSRN 2023年

作者： Gao, Peng Meng, Ailian Xu, Pan Jia, Xin He, Jiang Wang, Yan Chen, Qian Zhang, Yanjun Qiu, Yalu Huang, Min Chen, Hao Sichuan Institute of Atomic Energy Sichuan Chengdu610101 China Irradiation Preservation Key Laboratory of Sichuan Province Sichuan Chengdu610101 China College of Life Science and Engineering Southwest University of Science and Technology Sichuan Mianyang621000 China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu610059 China

This study aimed to evaluate the effects of gamma irradiation on the storage quality of Morchella angusticeps, specifically focusing on nutritional quality and physicochemical properties. The mushrooms were exposed to doses of 1, 2, 3, and 4 kGy, and their properties were analyzed under storage conditions of 4°C. The results indicated that different irradiation doses had varying effects on the nutritional quality and physicochemical properties of Morchella angusticeps during storage. At doses of 1 and 2 kGy, the content of phenolic compounds increased, while the activity of peroxidase and catalase decreased. Consequently, browning and softening were effectively delayed. Furthermore, with increased storage time, soluble protein content exhibited a downward trend. However, the 1 and 2 kGy irradiation doses effectively reduced the decomposition of soluble protein. As the irradiation dose increased, the content of aldehydes initially increased and then decreased. In addition, the fatty acid content exhibited an increase at irradiation doses of 1 and 2 kGy. During the storage period, the release of unsaturated fatty acids was promoted, particularly in the later stages. Furthermore, the shrinkage of Morchella angusticeps increased over time. However, a dose of 1 kGy was found to effectively maintain cell morphology. The experimental results demonstrated that treatment with 1 and 2 kGy irradiation doses effectively delayed the quality loss of the fruiting body and inhibited browning-related enzyme activities. This study highlights the potential of irradiation as a method to preserve the storage quality of Morchella angusticeps. © 2023, The Authors. All rights reserved.

关键词： Irradiation

来源：评论

学校读者我要写书评

暂无评论

Experimental study of tree ground fault discharge characteristics of 35 kV transmission lines

Experimental study of tree ground fault discharge characteri...

引用

2021 IEEE Sustainable Power and Energy Conference, iSPEC 2021

作者： Yang, Chunlan Chen, Tianxiang Yang, Bowen Zhang, Xinghai Fan, Songhai Chengdu University of Technology School of Nuclear Technology and Automation Engineering Chengdu China Institute of Electric Power Science State Grid Sichuan Electric Power Company Chengdu China

ISBN: (纸本)9781665414395

In recent years, forest fires have been frequent, leading to many major casualties and major losses to the national economy, but also affect the operational safety of the power grid. When forest fires occur, in addition to external weather and human factors, whether it is caused by grid line failure is also a controversial issue when finding the cause of the accident. In the paper, three common tree discharge characteristics under 35 kV transmission lines in Sichuan are studied, and a test platform and test program are designed to study the discharge characteristics of trees near the line and the fault characteristics of trees hitching on the transmission line circuit due to external factors, analyze the causes of related accidents, and propose the identification basis for the sequence of hill fires and line faults. The current range of trees ignited by tree grounding within 20 minutes is also obtained to provide ideas for later anti-accident measures. A theoretical model of tree grounding fault is proposed, which can predict the magnitude of tree grounding leakage current. © 2021 IEEE.

关键词： Electric lines

来源：评论

学校读者我要写书评

暂无评论

Design of magnetic shielding structures for non-contact measurement of current in triangularly arranged cables

Design of magnetic shielding structures for non-contact meas...

引用

Electrical engineering (CIYCEE), IEEE China International Youth Conference on

作者： Xingyu Zhou Dongsheng Cai Zhengyuan Zhang Peng Wang Arsalan Habib Khawaja Qi Huang College of Nuclear Technology and Automation Engineering Chengdu University of Technology China Sichuan Provincial Key Lab of Power System Wide-Area Measurement and Control School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu China School of Information Engineering Southwest University of Science and Technology Mianyang China

The triangular arrangement of cables has the advantages of good magnetic field balance and compact structure, making it a commonly used arrangement in tunnel power cable lines. Accurate measurement of its current helps to make accurate judgment of the line operation status. However, the tunnel transmission method involves a complex line arrangement in a small space. Therefore, non-contact wide-range current measurement based on magnetic sensors is a better solution. In the face of uncertain magnetic interference in transmission tunnels, the use of magnetic shielding can suppress its effect on magnetic sensors. In this paper, an M-shaped magnetic shield structure is proposed for current measurement in a triangular arrangement with strong magnetic interference at random locations. Then, the thickness, position, axial length, gap width and location of the sensing areas of the structure were investigated. The effectiveness of the structure was verified by finite element analysis methods for measured currents of 200 to 2000 A. The structure was also validated by the finite element analysis method. The mean shielding uncertainty (MSU) of the shielding structure is verified to be 0.19% under the uncertainty of strong magnetic interference for a measured current of 2000 A. The M-shaped shielding structure is more resistant to interference than the C-shaped shielding structure and fits better into the triangular arrangement of the cable geometry.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Preserving Location Privacy of IoT Devices in Heterogeneous Edge Computing Architecture Through Deniability-Based Authentication

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Ali, Ikram Li, Jianqiang Chen, Jie Chen, Yong Ullah, Shamsher Wakeel, Abdul Shenzhen University National Engineering Laboratory of Big Data System Computing Technology Shenzhen518060 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China University of Electronic Science and Technology of China School of Automation Engineering Chengdu611731 China National University of Sciences and Technology Military College of Signals Department of Electrical Engineering Islamabad Pakistan

Edge computing moves cloud services closer to consumer Internet of Things (IoT) devices, reducing latency and bandwidth usage. This setup enables faster responses but also introduces new security challenges, particularly concerning location privacy when sender and receiver use different security techniques. The authentication process in such architectures can expose the location of IoT devices. To address this issue, researchers have proposed various privacy-preserving schemes. However, these are computationally heavy for IoT devices. To tackle this issue, we propose two novel heterogeneous deniable authentication schemes: HDA-IoT-I and HDA-IoT-II. These schemes use public-key infrastructure and identity-based cryptography to protect the location privacy of IoT devices in heterogeneous edge computing environments. Our schemes enable the designated edge device to verify the source of a message without being able to prove its origin to a third party, thus preserving privacy. Additionally, they incorporate a batch verification method, which speeds up the verification of multiple deniable authenticators. The proposed schemes are formally proven secure in the random oracle model based on the hardness assumption of elliptic curve inverse computational Diffie-Hellman problem. The performance evaluation demonstrate that our schemes significantly enhance computational and communication efficiency, making them suitable for IoT devices. © 2025 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Fractal Converters with Boundless Current and Voltage Ratings

Fractal Converters with Boundless Current and Voltage Rating...

引用

Power Systems and Electrical technology (PSET), IEEE International Conference on

作者： Jingyang Fang Qin Jiang Hanqing Yang School of Control Science and Engineering Shandong University Jinan China College of Electrical Engineering Sichuan University Chengdu China School of Automation University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798350353204

ISBN: (纸本)9798350353211

Extremely high current/voltage stresses challenge power electronics. This paper proposes a novel series of power converters, collectively referred to as Fractal (F) converters. F converters consist of several identical layers, which further comprise many identical cells or submodules. Salient benefits of F converters include but not limited to 1) modularity and scalability; 2) boundless current and voltage ratings; 3) high power quality; 4) unified control applied to various layers; 5) high reliability; 6) control flexibility, e.g., for efficiency optimization. F converters will quickly find their applications in 1) high-voltage dc/ac transmissions; 2) renewable energy generation; 3) power quality enhancement equipment; 4) electric vehicles; 5) marine and aircraft propulsion; 6) medical applications such as noninvasive magnetic stimulators; 7) high-frequency high-power power supplies; 8) plasma applications; 9) future distributed power grids. For validations, simulation results are presented, demonstrating that F converters operate well as high-voltage and high-current inverters as well as arbitrary pulse generators.

关键词： Pulse generation Renewable energy sources Simulation Scalability Power quality High-voltage techniques Fractals Reliability Voltage control Stress

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven Residual Life Prediction Method For Rolling Bearings

A Data-Driven Residual Life Prediction Method For Rolling Be...

引用

Data Driven Control and Learning Systems (DDCLS)

作者： Shangrui Li Meng Li Zhilong Liu Minggang Li School of Automation Engineering University of Electronic Science and Technology of China Chengdu China Institute of Reactor Power Engineering Nuclear Power Institute of China Chengdu China

Rolling bearing is a key component of rotating machinery, which affects the reliability of the equipment. In order to make the equipment intelligent, facilitate the maintenance of the equipment, and improve the operation efficiency of the equipment, a data-driven residual life prediction method of rolling bearing is proposed, which is used to intelligently predict the remaining service life of the equipment, providing great convenience for the maintenance of the equipment. First, wavelet packet de-noising method is used to remove the noise in the original signal, and then extract the time-domain and frequency-domain features of the de-noised signal, after that PCA is used to reduce the dimension of the feature information and fuse it into the comprehensive life characteristics of the bearing. Last, with the input of the subsequent life prediction features, the residual life prediction model based on PCA-SVR is finally constructed. The experimental results show that the residual life prediction model based on PCA-SVR has low error rate and high accuracy which can accurately predict the residual life of rolling bearings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simple Online Real-Time Tracking Algorithm with Improved YOLOV4 as Extractor

Simple Online Real-Time Tracking Algorithm with Improved YOL...

引用

2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021

作者： Li, Fei Deng, Xiaotong Shi, Feifei Zhou, Xiaoxue Xia, Kaijun Hu, Guangdi Mechanical Engineering Southwest Jiaotong University Chengdu China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu China School of Nuclear Science and Technology Lanzhou University Chengdu China Jiangsu Xintongda Electronic Technology Co. Ltd Jiangsu China Zhejiang Geely New Energy Commercial Vehicle Group Co. Ltd Zhejiang China

ISBN: (纸本)9781665437554

Multiple target tracking algorithm is an important research field of computer vision. We improve the YOLOV4 algorithm by using the MatrixNets feature extraction module to obtain a better target detection and feature extractor and then uses the improved YOLOV4 algorithm to improve the deep sort algorithm to improve the performance of the algorithm to propose the Deep SORT-Y algorithm. The Deep SORT-Y algorithm can track the lost target object through a longer occlusion period, which greatly reduces the target loss rate. Compared with sort and deep sort algorithms, the score is reduced by 61 and 18%. Experimental evaluation shows that this algorithm still maintains the overall competitive advantage compared with other online real-time tracking algorithms at a high frame rate. © 2021 IEEE.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Geochemical records of the sediments and their significance in Dongping Lake Area,the lower reach of Yellow River,North China

引用

Journal of Groundwater Science and engineering 2021年第2期9卷 140-151页

作者： Lin-song Yu Hong-bo Liu Fang Wan Zun-fang Hu Huai-dong Luo Xiu-wen Zhang Applied Nuclear Technology in Geosciences Key Laboratory of Sichuan Province Chengdu Universtity of TechnologyChengdu 610059China College of Earth Sciences Chengdu University of TechnologyChengdu 610059China Shandong Institute of Geophysical and Geochemical Exploration Jinan 250013China

Dongping Lake area,located in the lower reaches of Yellow River,is an ideal place to study the changes of modern river and lake sedimentary *** sediment samples of Dawen River,Yellow River,and Dongping Lake were collected,and the major elements,trace elements and organic matter geochemical composition of the samples were *** analysis,characteristic element ratio method and graphic method were used to explore the geochemical characteristics of sediments and their environmental *** results show that the contents of SiO_(2),Na_(2)O,TiO_(2) and Zr in sediments of Dawen River and Yellow River are relatively high,and the contents of iron and manganese oxides,organic matter,CaO,P2O5 and Sr in lake sediments are relatively *** reveals the differences of sedimentary environments between the rivers and the *** contents of Sr and Zr in Dawen River are affected by the rapid migration of clastic materials in the upstream carbonate source area during the flood season;the δCe,ΣREE and REE’s ratios in the sediments of the Yellow River reflect the influence of the Loess source;and the distribution of elements changes along the flow direction during the flood *** characteristics of pH,element composition and LREE&HREE fractionation of the lake sediments indicate that the sediment source is complex,and the lake environment is affected by the flood *** study shows that the geochemical content and its variation characteristics of sediments effectively reveal the sedimentary environment,material composition and characteristics of flood season of rivers and the lake in the study area.

关键词： Dongping Lake Yellow River Sediments Organic matter Element geochemistry

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：