检索结果-内蒙古大学图书馆

A genetic programming approach with adaptive region detection to skin cancer image classification

Journal of Automation and Intelligence 2024年第4期3卷 240-249页

作者： Kunjie Yu Jintao Lian Ying Bi Jing Liang Bing Xue Mengjie Zhang School of Electrical and Information Engineering Zhengzhou UniversityZhengzhou450001China State Key Laboratory of Intelligent Agricultural Power Equipment Luoyang471000China Longmen Laboratory Luoyang471000China School of Electrical Engineering and Automation Henan Institute of TechnologyXinxiang453000China School of Engineering and Computer Science&Centre for Data Science and Artificial Intelligence Victoria University of WellingtonWellington6201New Zealand

Dermatologists typically require extensive experience to accurately classify skin *** recent years,the development of computer vision and machine learning has provided new methods for assisted *** skin cancer image classification methods have certain limitations,such as poor interpretability,the requirement of domain knowledge for feature extraction,and the neglect of lesion area information in skin *** paper proposes a new genetic programming(GP)approach to automatically learn global and/or local features from skin images for *** achieve this,a new function set and a new terminal set have been *** proposed GP method can automatically and flexibly extract effective local/global features from different types of input images,thus providing a comprehensive description of skin images.A new region detection function has been developed to select the lesion areas from skin images for feature *** performance of this approach is evaluated on three skin cancer image classification tasks,and compared with three GP methods and six non-GP *** experimental results show that the new approach achieves significantly better or similar performance in most *** analysis validates the effectiveness of our parameter settings,visualizes the multiple region detection functions used in the individual evolved by the proposed approach,and demonstrates its good convergence ability.

关键词： Genetic programming Skin cancer image classification Region detection Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Research on Grape Disease Recognition Based on Improved YOLOv5s in Complex Environment 5

Research on Grape Disease Recognition Based on Improved YOLO...

引用

5th International Conference on Artificial Intelligence Technologies and Applications, ICAITA 2023

作者： Zhou, Zili Gu, Shenming School of Information Engineering Zhejiang Ocean University Zhou Shan China Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhejiang Ocean University Zhou Shan China

ISBN: (纸本)9781643684840

Aiming at the problems of low recognition accuracy of detector algorithm caused by occlusion interference of grape disease spot in natural complex background, non-significant visual features of grape spot, small target of disease spot and uneven number of sample categories, this study proposed an improved model method based on YOLOv5s. The new WiseIoU is used as the loss function to calculate the positioning loss, so as to improve the accuracy of the algorithm to predict the positioning and speed up the convergence of the model. CA attention mechanism was added to the basic network to enhance grape lesion feature extraction. A small target detection layer was added to the head network of the model to improve the recognition and detection ability of grape small target lesions. IDADP-grape disease recognition image dataset is taken as the main dataset of this study, and combined with self-collected grape disease images, the experimental data set is composed and the training test is carried out. The experimental results show that the improved algorithm mAP0.5 reaches 84.40%, which is 1.30% higher than the baseline model. Compared with other detector algorithms, mAP0.5 and recognition accuracy have improved to different degrees. This method has strong anti-interference robustness and can be used for rapid and accurate identification of grape diseases in complex field environment. © 2024 The Authors.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Multiscale Bilateral Attention Fusion Network for Pansharpening

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5828-5843页

作者： Guo, Zhongyuan Li, Jiawei Lei, Jia Liu, Jinyuan Zhou, Shihua Wang, Bin Kasabov, Nikola K. Dalian University Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian116622 China University of the Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Dalian University of Technology School of Mechanical Engineering Dalian116024 China Auckland University of Technology Knowledge Engineering and Discovery Research Institute Auckland1061 New Zealand University of Ulster Intelligent Systems Research Center LondonderryBT48 7JL United Kingdom Bulgarian Academy of Sciences IICT Sofia1000 Bulgaria

High-resolution multispectral (HRMS) images combine spatial and spectral information originating from panchromatic (PAN) and reduced-resolution multispectral (LRMS) images. Pansharpening performs well and is widely used to obtain HRMS images. However, most pansharpening approaches determine the ratio of PAN and LRMS images through direct interpolation, which may introduce artifacts and distort the color of the fused results. To address this issue, an unsupervised progressive pansharpening framework, MSBANet, is proposed, which adopts a multistage fusion strategy. Each stage contains an attention interactive extraction module (AIEM) and a multiscale bilateral fusion module (MBFM). The AIEM extracts spatial and spectral features from input images and captures the correlations between features. The MBFM can efficiently integrate information from the AIEM and improve MSBANet context awareness. We design a hybrid loss function that enhances the ability of the fusion network to store spectral and texture details. In qualitative and quantitative experimental studies on four datasets, MSBANet outperformed state-of-the-art pansharpening techniques. The code will be released. © 2024 IEEE.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Learned Video Compression With Refined Adaptive Flow Pyramid And Coordinate-Aware Attention

Learned Video Compression With Refined Adaptive Flow Pyramid...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Huang, Qian Liu, Wenting Li, Xin Wang, Yiming College of Computer Science and Software Engineering Hohai University Nanjing China Key Laboratory of Water Big Data Technology Ministry of Water Resources Hohai University Nanjing China

ISBN: (纸本)9798350368741

In video compression, motion estimation and motion compensation are critical for achieving efficient encoding. Although the commonly used SpyNet and bilinear interpolation have contributed in improving the compression efficiency, they still have limitations. SpyNet often loses details and fails to fully utilize the feature extraction capabilities of deep networks. Furthermore, bilinear interpolation inherently attenuates high-frequency information, leading to frame blurring and distortion. In this paper, we propose a novel video compression algorithm. To overcome the limitations of SpyNet, we propose a refined adaptive flow pyramid network. This network uses a multi-scale feature pyramid to capture more details. Moreover, we use an iterative cost volume refinement engine that improves the feature representation of the network and iteratively improve the accuracy of motion estimation. In addition, to overcome the limitation of bilinear interpolation, we propose a coordinate-aware attention module, which captures more high-frequency information to improve the accuracy of motion compensation. Experimental results show that our method outperforms VTM-13.2 (LDP) in terms of PSNR. © 2025 IEEE.

关键词： coordinate network cross attention flow pyramid learned video compression

来源：评论

学校读者我要写书评

暂无评论

BKA optimization algorithm based on sine-cosine guidelines 4

BKA optimization algorithm based on sine-cosine guidelines

引用

4th International Symposium on Computer Technology and Information Science, ISCTIS 2024

作者： Zhou, Yanqiu Wu, Xiao Liu, Yuxiang Jiang, Xinghe Jiangnan Institute of Mechanical and Electrical Design Guiyang China Guizhou University School of Mechanical Engineering Guiyang China Guizhou University State Key Laboratory of Public Big Data Guiyang China

ISBN: (纸本)9798350354560

In order to address the limitations of traditional BKA optimization algorithms in terms of stability, data processing capability, and computational speed, this study proposes a new and improved BKA algorithm that combines the sine-cosine criterion, i.e., SCBKA. This new algorithm significantly enhances its solution accuracy and convergence speed by integrating the sine-cosine oriented mechanism. We conducted systematic comparison experiments of the SCBKA algorithm with six recognized classical algorithms on the highest challenge dimension of the CEC 2020 benchmark test function, the 20th dimension. The experimental results clearly show that SCBKA not only obtains significant improvement in convergence and accuracy, but also demonstrates significant advantages in the stability of the algorithm. In addition, by applying the Friedman rank sum test, we further confirm the efficiency and reliability of the SCBKA algorithm. © 2024 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

An improved branching algorithm for the proper interval edge deletion problem

引用

Frontiers of Computer Science 2022年第2期16卷 178-180页

作者： Wenjun LI Xiaojing TANG Yongjie YANG School of Computer and Communication Engineering Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on TransportationChangsha University of Science and TechnologyChangsha 410015China School of Computer Science and Engineering Central South UniversityChangsha 410083China

1 Introduction For a graph class G,the G-EDGE DELETION problem is to determine whether a given graph can be transformed into a graph in G by deleting at most k *** G-EDGE DELETION problem for a large body of graph cla... 详细信息

关键词： branching problem transformed

来源：评论

学校读者我要写书评

暂无评论

The Method of Object Saliency Detection in Remote Sensing Images Based on Gestalt Theory and Visual Attention 5

The Method of Object Saliency Detection in Remote Sensing Im...

引用

5th International Conference on Intelligent Computing and Human-Computer Interaction, ICHCI 2024

作者： Liu, Huan Xiao, Genfu College of Electronic and Information Engineering Jinggangshan University Key Laboratory of Jiangxi Electronic Data Control and Forensics Jiangxi Ji'An343009 China Jiangxi Engineering Laboratory of IoT Technologies for Crop Growth Jiangxi Ji'An343009 China College of Mechanical and Electronic Jinggangshan University Jiangxi Ji'An343009 China

ISBN: (纸本)9798350368284

There are some shortcomings in existing salient object detection methods of remote sensing images. For example, the extracting features are insufficient and they are always seriously interfered by complex background information. To solve these problems, a visual attention model based on Gestalt theory is proposed. First, a pyramid anisotropic scale space model is built, followed by the extraction of multi-scale, multi-directional low-And high-frequency visual features to construct multi-space saliency maps. Then each spatial saliency map can be adaptively fused based on the similarity principle of Gestalt theory. Comparison and analysis are implemented among our proposed method and some existing methods on the public natural image dateset ECSSD and remote sensing image dateset ORSSD. The experimental results show that the proposed method has higher detection accuracy than existing saliency detection methods, especially in the detection of remote sensing images. It is greatly demonstrated that the effectiveness and feasibility of the proposed method. © 2024 IEEE.

关键词： Optical remote sensing

来源：评论

学校读者我要写书评

暂无评论

Propagation of terahertz waves in nonuniform plasma slab under “electromagnetic window”

引用

Chinese Physics B 2022年第3期31卷 399-405页

作者： Hao Li Zheng-Ping Zhang Xin Yang College of Big Data and Information Engineering Guizhou UniversityGuiyang 550025China Semiconductor Power Device Reliability Engineering Research Center of Ministry of Education Guizhou UniversityGuiyang 550025China Key Laboratory of Micro-Nano-Electronics and Software Technology of Guizhou Province Guiyang 550025China

The application of magnetic fields, electric fields, and the increase of the electromagnetic wave frequency are upand-coming solutions for the blackout problem. Therefore, this study considers the influence of the external magnetic field on the electron flow and the effect of the external electric field on the electron density distribution, and uses the scattering matrix method(SMM) to perform theoretical calculations and analyze the transmission behavior of terahertz waves under different electron densities, magnetic field distributions, and collision frequencies. The results show that the external magnetic field can improve the transmission of terahertz waves at the low-frequency end. Magnetizing the plasma from the direction perpendicular to the incident path can optimize the right-hand polarized wave transmission. The external electric field can increase the transmittance to some extent, and the increase of the collision frequency can suppress the right-hand polarized wave cyclotron resonance caused by the external magnetic field. By adjusting these parameters, it is expected to alleviate the blackout phenomenon to a certain extent.

关键词： terahertz wave scattering matrix method(SMM) nonuniform magnetized plasma electric field

来源：评论

学校读者我要写书评

暂无评论

High-resolution and High-rate Dual-comb FMCW Lidar with Coherent Comb Stitching

High-resolution and High-rate Dual-comb FMCW Lidar with Cohe...

引用

2024 Conference on Lasers and Electro-Optics, CLEO 2024

作者： Cao, Xianyi Wang, Long Li, Tianyi Cai, Minglu Wu, Guiling Chen, Jianping Wu, Kan Shanghai Institute for Advanced Communication and Data Science State Key Laboratory of Advanced Optical Communication Systems and Networks Department of Electronic Engineering Shanghai Jiao Tong University Shanghai200240 China

A dual-comb FMCW Lidar with coherent comb stitching (CCS) technique is firstly demonstrated. CCS can simultaneously achieve 65 GHz high frequency sweeping range, millimeter-level ranging resolution and 100 kHz high vo... 详细信息

ISBN: (纸本)9781957171395

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

Monolithic 50 GHz tunable microwave signal generation based on erbium-doped lithium niobate dual lasers

Monolithic 50 GHz tunable microwave signal generation based ...

引用

2024 Conference on Lasers and Electro-Optics, CLEO 2024

作者： Cai, Minglu Zhang, Xujia Li, Tianyi Shi, Hao Li, Tieying Cao, Xianyi Cui, Zekun Chen, Jianping Wu, Kan Shanghai Institute for Advanced Communication and Data Science State Key Laboratory of Advanced Optical Communication Systems and Networks Department of Electronic Engineering Shanghai Jiao Tong University Shanghai200240 China

The monolithic erbium-doped lithium niobate lasers can achieve a tunable wavelength range of 56.25 GHz and generate a 50 GHz microwave signal with a side-mode suppression ratio of 35 dB by dual lasers. © Optica P... 详细信息

ISBN: (纸本)9781957171395

关键词： Microwave generation

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：