检索结果-内蒙古大学图书馆

4th International Seminar on Artificial Intelligence, Networking and Information technology, AINIT 2023

作者： Zhang, Jie Zheng, Fuzhong Li, Zhonghao Lu, Yuting Wang, Shan Cao, Qiang Intelligent Manufacturing and Automobile School Chongqing College of Electronic Engineering Chongqing China School of Automation Chengdu University of Information Technology Chengdu China College of Mechanical Engineering Sichuan University of Science and Engineering Chengdu China PetroChina Changqing Oilfield Company NO.7 Oil Production Plant Qingyang China

ISBN: (纸本)9798350314526

The non-contact strain sensor based on the single-walled carbon nanotube (SWCNT) photoluminescence effect has a great potential that attracted extensive research from both domestic and international scholars. In order to research the non-contact strain sensor, the current paper proposed a fluorescence excitation and acquisition system platform for SWCNT strain sensors, and designed the structures of its optical components. The design, installation, and debugging of this system are conducted. Results show that the fluorescence excitation and acquisition system established in this paper is a suitable platform for SWCNT optical full field strain measurement. Based on this system, the fluorescence excitation and acquisition of the SWCNT film are simulated and analyzed by using OpticStudio software. Simulation results show that the fluorescence intensity is in partial positively correlated with the excitation light intensity, and the light spot diameter could be controlled within 0.1mm. The light spot scanning resolution of the SWNT film achieved the expected effect. © 2023 IEEE.

关键词： Photoluminescence

来源：评论

学校读者我要写书评

暂无评论

BCDNet: A Fast Residual Neural Network For Invasive Ductal Carcinoma Detection

arXiv

引用

arXiv 2024年

作者： Lin, Yujia Lian, Aiwei Liao, Mingyu Yuan, Shuangjie Glasgow College University of Electronic Science and Technology of China Chengdu China School of Automation Engineering University of Electronic Science and Technology of China Chengdu China

It is of great significance to diagnose Invasive Ductal Carcinoma (IDC) in early stage, which is the most common subtype of breast cancer. Although the powerful models in the Computer-Aided Diagnosis (CAD) systems provide promising results, it is still difficult to integrate them into other medical devices or use them without sufficient computation resource. In this paper, we propose BCDNet, which firstly upsamples the input image by the residual block and use smaller convolutional block and a special MLP to learn features. BCDNet is proofed to effectively detect IDC in histopathological RGB images with an average accuracy of 91.6% and reduce training consumption effectively compared to ResNet 50 and ViT-B-16. © 2024, CC BY.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

PETRFusion: Multi-Sensor Fusion Based BEV Semantic Segmentation Network for Autonomous Driving

PETRFusion: Multi-Sensor Fusion Based BEV Semantic Segmentat...

引用

International Conference on Intelligent Transportation

作者： Yang Zhao Jingyu Du Qihang Yang Ningze Cai Zhinan Peng Huiqin Zhan Hong Cheng School of Automation Engineering University of Electronic Science and Technology of China Chengdu China Glasgow College University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798331505929

ISBN: (纸本)9798331505936

Bird's Eye View (BEV) based perception algorithms are receiving increasing attention in the field of autonomous driving, how to more effectively utilize multi-sensor data in BEV is a challenge. In this paper, we propose PETRFusion, a BEV segmentation network that integrates multiple cameras with a LiDAR sensor. We focus on the task of BEV segmentation, designing the network architecture based on the similarity between LiDAR point clouds and semantic segmentation maps. The proposed method uses point cloud features as queries for semantic segmentation and employs Transformers to fuse image features with point cloud features, thereby maximizing the preservation of 3D spatial information from the point cloud. Additionally, we enhance the 3D positional encoder of PETR to provide more reliable 3D image features. We conduct detailed validation on the nuScenes dataset and achieve state-of-the-art results.

关键词： Point cloud compression Three-dimensional displays Laser radar Semantic segmentation Network architecture Cameras Transformers Reliability Autonomous vehicles Intelligent transportation systems

来源：评论

学校读者我要写书评

暂无评论

A Digital Noise Signal Synthesis Method Based on a Combination of Table Look-up and Transformation 22

A Digital Noise Signal Synthesis Method Based on a Combinati...

引用

22nd IEEE International Conference on Communication technology, ICCT 2022

作者： Xiao, Yindong Peng, Bo Liu, Ke Fu, Zaiming Hu, Cong School of Automation Engineering University of Electronic Science and Technology of China Chengdu China Guilin University of Electronic Technology Guangxi Key Laboratory of Automatic Testing Technology and Instruments Guilin China

ISBN: (纸本)9781665470674

Digital noise signal synthesis methods have good scalability and flexibility, and can be divided into table look-up and transform methods depending on the implementation method. The accuracy of noise distribution synthesized by the look-up table method is limited by the storage depth, on the other hand, the maximum synthesis speed of the transform method is limited by the hardware computation speed. In this paper, we propose a new implementation method for digital noise signal synthesis, which divides the noise output into high probability intervals and low probability intervals by probability. The high probability interval noise generation is based on the look-up table method, and the low probability interval noise generation is based on the transformation method for real-time computation. The method is validated experimentally in terms of distribution accuracy, storage space occupation and output speed. The results show that the method has higher output accuracy than the look-up table method and faster output speed compared to the transformation method. © 2022 IEEE.

关键词： Table lookup

来源：评论

学校读者我要写书评

暂无评论

A reconfigurable calibration-free digital-to-time converter based on a high-speed transceiver

arXiv

引用

arXiv 2024年

作者： Kong, Dexuan Fu, Zaiming Deng, Yujie Wang, Ruiqi University of Electronic Science and Technology of China School of Automation Engineering Chengdu611731 China

This paper proposes a high-speed transceiver-based method for implementing a digital-to-time converter (DTC). A real-time decoding technique is introduced to inject time information into high-speed pattern data. The stability of the high-speed clock ensures the high precision of the synthesized timing signal without the need for calibration. The reconfigurability of the clock resources provides the DTC with variable resolution and enhanced flexibility for various applications. Based on this approach, a multifunctional DTC is designed to offer both timing sequence and random timing signal functionalities, catering to a wide range of application scenarios. The timing sequence function generates a continuously variable timing signal stream, while the random timing signal function produces random signals with uniformly distributed time intervals. Experimental results, using a Xilinx Kintex-7 FPGA, validate the effectiveness of the proposed methodology. The system achieves a resolution of 100 ps, a dynamic range from 1 ns to 40 µs, a DNL of -0.02/0.02 LSB, an INL of -0.04/0.03 LSB across the entire range. This approach can be readily adapted to various high-precision timing signal applications. Copyright © 2024, The Authors. All rights reserved.

关键词： Radio transceivers

来源：评论

学校读者我要写书评

暂无评论

Research On Low-Temperature Risk Assessment for Spatial and Temporal Distribution in Northeast and South China

Research On Low-Temperature Risk Assessment for Spatial and ...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Min Chen Lei He Bin Liu Yuxia Li Han Luo Jialin Tao Binyang Yang School of Software Engineering Chengdu University of Information Technology Chengdu China Sichuan Province Engineering Technology Research Centre of Support Software of Informatization Application Chengdu China School of Automation University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Low-temperature disasters seriously affect the ecological environment and people's daily lives. In the research, the spatial distribution of low-temperature risk over 30 years has been obtained by collecting meteorological and socio-economic data from 1991 to 2020, and then a risk assessment model based on hazard, exposure, and vulnerability indicators is built. The results show that the high-risk areas are mainly concentrated in the central, eastern, and southern parts of Northeast China, and the overall risk shows an increasing trend; the regions at high risk are primarily found in Hunan Province and the central part of Jiangxi Province in south China. Further, the change in risk is most obvious between 1991-2005, and the overall risk value decreased about 41.28%. The Contribution to low-temperature risk in Northeast China comes mainly from vulnerability. While, In South China, the contribution of various factors to risk is more evenly distributed.

关键词： Graphical models Disasters Biological system modeling Geoscience and remote sensing Market research Hazards Data models

来源：评论

学校读者我要写书评

暂无评论

ATEDU-NET: An Attention-Embedded Deep Unet for multi-disease diagnosis in chest X-ray images, breast ultrasound, and retina fundus

引用

Computers in Biology and Medicine 2025年 186卷 109708-109708页

作者： Ejiyi, Chukwuebuka Joseph Qin, Zhen Agbesi, Victor K. Ejiyi, Makuachukwu Bennedith Chikwendu, Ijeoma A. Bamisile, Oluwatoyosi F. Onyekwere, Favour Ezinne Bamisile, Olusola O. College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan 610059 China Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Sichuan Chengdu China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Pharmacy Department University of Nigeria Nsukka Enugu State Nsukka Nigeria School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China

In image segmentation for medical image analysis, effective upsampling is crucial for recovering spatial information lost during downsampling. This challenge becomes more pronounced when dealing with diverse medical image modalities, which can significantly impact model performance. Plain and standard skip connections, widely used in most models, often fall short of maintaining high segmentation accuracy across different modalities, because essential spatial information transferred from the encoder to the decoder is lost. Inspired by these limitations, the Attention-Embedded Deep UNet (ATEDU-Net) is presented here, an innovative framework designed and tested on diverse medical image modalities, including X-ray, breast ultrasound, and retinal fundus images. ATEDU-Net features a unique architecture that combines progressive context refinement modules (PCRM) and global context modules (GCM) within a U-shaped network structure with Convgroup blocks which facilitate the integration of convolutional operations. This allows ATEDU-Net to autonomously capture rich spatial details and crucial contextual information from input images. The GCM captures essential contextual information for informed decision-making, while the PCRM enhances feature attention, resulting in precise and robust segmentation. The experimentation and analysis demonstrate that ATEDU-Net promises to be a powerful tool for medical professionals, aiding in the early detection of chest-related diseases, accurate localization of breast tumors, and early identification of eye diseases. This, in turn, contributes significantly to the formulation of optimal therapeutic strategies, enhancing patient care and outcomes. The versatility of ATEDU-Net is further highlighted by its ability to analyze medical images across various modalities, making it well-suited for the complex task of medical image analysis in diverse clinical scenarios. © 2025 Elsevier Ltd

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A New Chip-Scale Magnetic Field Sensor Based on Oscillation Mode Optomechanical Detection

A New Chip-Scale Magnetic Field Sensor Based on Oscillation ...

引用

IEEE Instrumentation and Measurement technology Conference

作者： Zhe Li Pengju Kuang Chengwei Xian Yifan Wang Kai Chen Yongjun Huang School of Automation Engineering Electronic Test Technology and Instrument Institute University of Electronic Science and Technology of China Chengdu China School of Information and Communication Engineering Sichuan Provincial Engineering Research Center of Communication Technology for Intelligent IoT University of Electronic Science and Technology of China Chengdu China School of Automation Engineering University of Electronic Science and Technology of China Chengdu China School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798350380903

ISBN: (纸本)9798350380910

In this paper, we demonstrate a chip-scale optomechanical resonator driven into oscillation mode for new magnetic field sensing. The new sensing device based on nanofabrication uses the slot-type photonic crystal cavity for detection, which has the advantages of high sensitivity, high detection precision and frequency readout. Firstly, combined with the principle of the optomechanical system, the overall structure design of the optomechanical sensor based on Lorentz force for magnetic field detection is proposed. Then, the detection sensitivity of the designed optomechanical magnetic field sensor is analyzed. The simulation results show that the magnetic field detection sensitivity is 7.9Hz/,.. T when the input laser intensity is 199,.. W. Finally, the mechanical mode of the magnetic field sensor is simulated and designed, and the resonant data of the operating mode is obtained by testing. The results show that the new optomechanical magnetic field sensor has the characteristics of high sensitivity, low noise and can be widely used in future miniaturization, high precision, weak magnetic field and other applications.

关键词： Sensitivity Simulation Photonic crystals Laser modes Software Sensors Magnetic fields

来源：评论

学校读者我要写书评

暂无评论

Unisort:Tracking with Unified Cue Integration and Refined Association

SSRN

引用

SSRN 2024年

作者： Li, Modi Li, Rui Liang, Shaofeng Shi, Yingjing School of Automation Engineering University of Electronic Science and Technology of China Chengdu611731 China

Multi-object tracking (MOT) aims to detect and associate all objects of interest across frames in a video sequence. Despite the impressive performance achieved by existing tracking methods, crowded and frequent occlusions remain challenging issues in MOT. In response to these challenges, we introduce a novel approach, which leverages unified cue integration and refined association techniques to enhance tracking performance in occlusion scenarios. Our method integrates both strong and weak cues, incorporating weak cues such as confidence, pseudo-depth, and height to compensate for the failure of strong cues (geometric and appearance features) when objects are occluded. Moreover, we design a multi-stage association mechanism based on the classification score of detections, separating objects with clear appearances in low-score detections, thus selecting more suitable cost matrices for different subsets of detection boxes. Our method achieves outstanding performance across multiple test set benchmarks, including MOT17, MOT20, and DanceTrack, where interactions and occlusions are prevalent and severe. © 2024, The Authors. 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

Adaptive rapid defect identification in ECPT based on K-means and automatic segmentation algorithm

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第11期14卷 1-18页

作者： Huang, Xuegang Yin, Chun Dadras, Sara Cheng, Yuhua Bai, Libing Hypervelocity Aerodynamics Institute China Aerodynamics Research and Development Center Mianyang621000 China School of Automation Engineering University of Electronic Science and Technology of China Sichuan Chengdu China Electrical and Computer Engineering Department Utah State University LoganUT84321 United States

To enhance the detection efficiency in eddy current pulsed thermography, an adaptive feature extraction algorithm for defect identification is developed in this paper. The proposed algorithm involves four stages, namely, the thermal image segmentation, the variable interval search, the distance correlation clustering analysis and the between-class distance decision making. The transient thermal responses (TTRs) with similar characteristics are collected into one data block. The thermal image segmentation and variable interval search can help reduce the repetitive calculation in defect identification by choosing local optimums in each data block. The global optimum that has the largest sum of the between-class distance, is derived by first classifying the local optimums and then calculating the correlation distance of the thermal responses with the center points of each class. Finally, the TTRs with the largest between-class distance are regarded as the typical ones which can be used to identify the discriminative defect features of infrared image sequence. Finally, the comparison experiments are carried out to demonstrate the effectiveness and advantages of the proposed approach. © 2018, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： K-means clustering

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：