检索结果-内蒙古大学图书馆

6th ACM International Conference on Multimedia in Asia, MMAsia 2024

作者： Chen, Yiran Liu, Haoran Liu, Mingzhe Liu, Yanhua Wang, Ruili Li, Peng Chengdu University of Technology Chengdu China Wenzhou University of Technology Chengdu China Massey University Palmerston North New Zealand Southwestern Institute of Physics Chengdu China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu610059 China

ISBN: (纸本)9798400712739

Moving object tracking on cost-effective hardware is a crucial need in numerous research and industrial applications. However, current deep learning-based tracking algorithms usually prioritize exceptional performance at the expense of increased computational load. Due to the unavailability of expensive GPUs for many tracking tasks, these popular trackers often fall short in providing robust tracking capabilities with affordable computational resources. This study introduces RCNNshift, a kernel-based tracker that relies on feature extraction from a random-coupled neural network. This visual cortex inspired neural model can extract image features without requiring cumbersome pre-training or deep neural connections. By utilizing an enhanced one-dimensional feature representation, RCNNshift demonstrates superior performance compared to other kernel-based object tracking methods, even those employing higher-dimensional feature spaces. Its improvement in precision and success plots of OPE, compared to the Meanshift and Camshift in the HSV and RGB color spaces, exceeds over 160% and 190% respectively. Comparative experiments have validated the robustness of RCNNshift, showcasing its superior performance over various kernel-based and particle filter trackers. Its combination of robustness and computational efficiency makes RCNNshift an ideal choice for mid to low-end object tracking tasks such as surveillance and underwater tracking. The source code is available at https://***/HaoranLiu507/RCNNshift. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Study on Beam Trajectory Deflection and Spatial Dose Distribution in Magnetic Resonance-Guided Proton Therapy 23rd

Study on Beam Trajectory Deflection and Spatial Dose Distrib...

引用

23rd Pacific Basin nuclear Conference, PBNC 2022

作者： Ren, Xiao-Qing Wang, Ming Wang, Xin-Chen Li, Meng Li, Guo-Dong Zhang, Lei School of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu China

ISBN: (纸本)9789811988981

Proton therapy can significantly inhibit the radiation damage of additional tissues, which is the development trend of cancer radiotherapy. At present, the randomness of range fluctuation of proton beam in the body is a technical bottleneck that limits the high-precision dose distribution of proton therapy. The targeting accuracy of proton therapy for moving soft-tissue tumours is expected to greatly improve by real-time magnetic resonance imaging (MRI) guidance. However, the magnetic field introduced by MRI will affect the transmission trajectory of proton beam, and then cause the deposition dose distortion in the body. Therefore, it is necessary to accurately evaluate the beam deflection trajectory under the three-dimension magnetic field. In this paper, with the help of Monte Carlo code TOPAS, the proton beam trajectory deflection under different magnetic field parameters is carried out, and the calculation accuracy of the mathematical model is verified by Monte Carlo algorithm. Then, the trajectories of primary protons and secondary particles (consider electrons and secondary protons) under different magnetic field are investigated. Moreover, comparison diagram of dose distribution before and after correction is presented in the paper. The analysis results of this paper will provide data reference for the dose correction of later MRI guided proton therapy device. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Proton beams

来源：评论

学校读者我要写书评

暂无评论

Super-resolution Localization Problem Based on the Mobile Scenario 7

Super-resolution Localization Problem Based on the Mobile Sc...

引用

2023 7th International Conference on Mechanics, Mathematics and Applied Physics, ICMMAP 2023

作者： Zhu, Ying Hao X.C., Wei X.Y., Jiang The College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu610059 China Chengdu University of Traditional Chinese Medicine China

Target positioning has always been a hot research topic in the field of sensors. In recent years, radar detection technology has become increasingly mature, resulting in a large number of radar sensors have begun to be used in traffic, security, medical and other fields for target detection. This paper mainly studies the super-resolution localization problem of FMCW FMCW in moving scenes. It analyzes the echo data by mathematical modeling to obtain the distance and angle information of the object to find the place of the object. To restore the motion trajectory of objects more realistically and achieve super-resolution positioning, a super-resolution radar positioning model based on Kriging interpolation based on the Fourier spectrum is established. By constructing a frame of intermediate frequency data Fourier spectrum tensor space, Fourier spectrum analysis is used to obtain the spectral characteristics of spatiotemporal changes when objects move. The Fourier spectrum surface is reasonably predicted through the statistical method - kriging interpolation. More Fourier spectrum information of objects in the time dimension can be obtained, and then more object points can be restored to achieve super-resolution positioning. This is widely used in the automotive field, which develops autonomous driving systems to help drivers better control the vehicle and reduce the probability of car accidents. © Published under licence by IOP Publishing Ltd.

关键词： Spectrum analysis

来源：评论

学校读者我要写书评

暂无评论

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

The Impact of Neutron Energy on Laser Simulation technology in Transient Synergistic Damage 3

The Impact of Neutron Energy on Laser Simulation Technology ...

引用

3rd International Symposium on Semiconductor and Electronic technology, ISSET 2024

作者： Zhang, Fuwang Tang, Ge Zhu, Siji Liu, Jingrui Zhao, Wenjiao Zhang, Zhenkang Li, Mo College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan610059 China School of Electronic Science and Engineering University of Electronic Science and Technology of China Pidu Sichuan Chengdu611731 China

ISBN: (纸本)9798350390285

The study explores the impact of neutrons with different energies on laser simulation of silicon bipolar junction transistors (Si BJTs) under transient synergistic damage. By simulating the energy deposition distribution and transient current response of low-energy and high-energy photons at different neutron energies (ranging from 1 e V to 2 MeV), the following results are revealed: For high-energy neutron surroundings (energy > 100 keV), low-energy photons can effectively simulate high-energy photons to cause transient synergistic damage effects with neutrons. In contrast, for low-energy neutron surroundings (energy © 2024 IEEE.

关键词： Photons

来源：评论

学校读者我要写书评

暂无评论

Real-Time Monitoring of Meteorological Data at In-Situ GCW Remediation Sites

引用

Journal of Geoscience and Environment Protection 2024年第9期12卷 152-166页

作者： Qinghai Wu Xiaofeng Yang Jun Liu Ruiqi Wang Quanyou Fu College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu China

To optimize the self-organization network, self-adaptation, real-time monitoring, remote management capability, and equipment reuse level of the meteorological station supporting the portable groundwater circulation wells, and to provide real-time and effective technical services and environmental data support for groundwater remediation, a real-time monitoring system design of the meteorological station supporting the portable groundwater circulation wells based on the existing equipment is proposed. A variety of environmental element information is collected and transmitted to the embedded web server by the intelligent weather transmitter, and then processed by the algorithm and stored internally, displayed locally, and published on the web. The system monitoring algorithm and user interface are designed in the CNWSCADA development environment to realize real-time processing and analysis of environmental data and monitoring, control, management, and maintenance of the system status. The PLC-controlled photovoltaic power generating panels and lithium battery packs are in line with the concept of energy saving and emission reduction, and at the same time, as an emergency power supply to guarantee the safety of equipment and data when the utility power fails to meet the requirements. The experiment proves that the system has the characteristics of remote control, real-time interaction, simple station deployment, reliable operation, convenient maintenance, and green environment protection, which is conducive to improving the comprehensive utilization efficiency of various types of environmental information and providing reliable data support, theoretical basis and guidance suggestions for the research of groundwater remediation technology and its disciplines, and the research and development of the movable groundwater cycling well monitoring system.

关键词： Groundwater Circulation Well Weather Station Real-Time Monitoring Embedded Web Server

来源：评论

学校读者我要写书评

暂无评论

An Improved Convolutional Networks Model for Carbon Emission Prediction in Power Systems

An Improved Convolutional Networks Model for Carbon Emission...

引用

2024 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2024

作者： Cai, Dongsheng Acen, Caroline Ukwuoma, Chiagoziem C. Zhang, Nan Liu, Wei Zhang, Zhenyuan Huang, Qi College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu China School of Computing and Cyber Security Chengdu University of Technology Chengdu China 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

ISBN: (纸本)9798350352290

In response to the imperative need for carbon reduction, tracking the carbon footprint of power systems has emerged as a critical concern. Traditional methods have struggled to accurately capture the nuances of carbon emissions, necessitating a fresh approach. To address this gap, the study introduces a pioneering deep learning-based model. We contend that the rapid advancement of deep learning offers a solution by harnessing neural network models, particularly the temporal convolutional networks (TCN) and gated recurrent units (GRU). These models are adept at handling the intricate patterns and dependencies inherent in carbon emission data, which exhibit both short-term fluctuations and long-term trends. Sequel to that, we propose a novel TCN-GRU-ATT neural network model designed explicitly for carbon footprint data. This innovative model combines TCN, GRU, and attention mechanisms to comprehensively capture both short-term variations and long-term dependencies within carbon emission patterns. Using power generation data from a gas-fired unit within the power grid as a foundation, the model calculates carbon emissions across various time intervals. Results demonstrate the model's exceptional performance, with a low Mean Absolute Percentage Error (MAPE) of 1.7123%, a Root Mean Square Error (RMSE) of 8.8436 kg/CO2, and a high Coefficient of Determination R2 of 0.9802. © 2024 IEEE.

关键词： Low emission

来源：评论

学校读者我要写书评

暂无评论

Exploring the Performance Test of Smart Substation Auxiliary Control System Test Platform Based on B/S Architecture 4th

Exploring the Performance Test of Smart Substation Auxiliary...

引用

4th International Conference on Power and Electrical engineering, ICPEE 2023

作者： Feng, Fuyong Cai, Dongsheng Chang, Zhengwei Wu, Jie Bamisile, Olusola Huang, Qi The College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu China State Grid Sichuan Electric Power Company Electric Power Research Institute Chengdu China

ISBN: (纸本)9789819716739

Smart substation is an important infrastructure for the development of the power industry, in which the auxiliary control system plays a vital role, and the performance of the auxiliary control system of smart substations affects power security. Aiming at this problem, this paper uses the object-oriented programming language Java technology to develop a set of smart substation auxiliary control system test platforms based on the IEC61850 protocol, which is used for performance tests of auxiliary control system. By using Jmeter to simulate the multi-sensor data interaction test environment, the test platform tests the stability, response speed, and data processing capability of the auxiliary control system. The test data results indicate that the response time of the system is basically less than 80 ms, with a maximum deviation of only 10.05. The auxiliary control system testing platform designed in this article has shown satisfactory performance in different concurrent data interaction testing environments, providing a solid guarantee for the reliability and stability of the equipment. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Control systems

来源：评论

学校读者我要写书评

暂无评论

Automatic Fruit Detection Based on Robotic Vision 5

Automatic Fruit Detection Based on Robotic Vision

引用

5th International Conference on Big Data and Artificial Intelligence and Software engineering, ICBASE 2024

作者： Chen, Yiran Yao, Rui Liu, Haoran Liu, Bingqi Liu, Mingzhe Wenzhou University of Technology School of Data Science and Artificial Intelligence Wenzhou China Chengdu University of Technology College of Nuclear Technology and Automation Engineering Chengdu China Norla Institute of Technical Physics Chengdu China

ISBN: (纸本)9798331506612

Automatic fruit detection has greatly reduced labor costs and crop damage rates, contributing to the progress of agricultural modernization. It involves real-time assessment of the surrounding environment and recognition of target fruit categories. However, fruit detection faces challenges due to the similarities in shape, color, and other features among different types of fruits, as well as the impact of environmental factors such as inadequate lighting, occlusion, and background variations on recognition accuracy. This project focuses on the simulation of the robotic fruit harvesting process, which includes environmental image acquisition, image processing, and robot control. The robot utilizes its integrated camera to capture real-time images of the surrounding environment. These images are then processed on a computer, employing color recognition based on traditional algorithms. The images are segmented based on the identified color regions and subjected to object detection using YOLO v5. By discerning the presence of the target objects, the results are transmitted to the robot, which responds accordingly. The real-time performance is enhanced by filtering and narrowing down the target regions, reducing the time required for object recognition. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Separated Ionic-Electronic Conduction in Hydrophobic Conjugated Polymer/Hydrophilic Photocrosslinker Blends for Organic Electrochemical Transistors

引用

SmartMat 2025年第2期6卷 224-234页

作者： Yueping Lai Yimin Sun Jie Tian Jianhua Chen Wei Huang Liang-Wen Feng Key Laboratory of Green Chemistry&Technology of Ministry of Education College of ChemistrySichuan UniversityChengduChina Department of Chemical Science and Technology Yunnan UniversityKunmingChina School of Automation Engineering University of Electronic Science and Technology of ChinaChengduChina

Ionic-electronic coupling serves as the core process enabling the operation of organic mixed ionic-electronic(semi)conductors(OMIECs)based devices,for instance,organic electrochemical transistors(OECTs).Replacing hydrophobic side chains of conjugated polymers with hydrophilic ethylene glycol/ionic ones is a well-developed approach to enable transistor channels with coupled ionic and electronic ***,in contrast,we introduce a hydrophilic glycol chain-modified photocrosslinker(DtFGDA)for the direct photolithography process and blend it with various representative hydrophobic conjugated *** precise patterning of blended films by direct photolithography is achieved while tremendous enhancements of OECTs performance are attained,with maximum six orders of magnitude higher transconductance,significantly decreased hysteresis,and lower threshold *** spectroelectrochemical characterization,surprisingly,no obvious variations in polaron absorption peaks are observed in all conjugated polymer/crosslinker *** ionic-electronic separated conduction mechanism,which is never reported in OECTs before,is further proposed based on the characterization of the transmission electron microscope,wherein ions primarily migrate within the crosslinker while holes transport within the semiconducting *** work proposes an efficient strategy,which involves incorporating hydrophilic chains into the photocrosslinker necessary for direct photolithography and blending it with hydrophobic semiconducting polymers,achieving synergistic ionic-electronic transport in the blended film.

关键词： direct photolithography hydrophilic photocrosslinker hydrophobic polymer ionic-electronic separated conduction organic electrochemical transistor

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：