检索结果-内蒙古大学图书馆

Computing Salient Feature Points of 3D Model Based on Geodesic Distance and Decision Graph Clustering

Recent Advances in Computer science and Communications 2021年第8期14卷 2489-2494页

作者： Sun, Dechao Chen, Nenglun Wang, Renfang Liu, Bangquan Liang, Feng College of Big Data and Software Engineering Zhejiang Wanli University Ningbo China Department of Computer Science Hong Kong University Hong Kong College of Digital Technology and Engineering Ningbo University of Finance & Economics Ningbo China

Introduction: Computing Salient Feature Points (SFP) of 3D models has important application value in the field of computer graphics. In order to extract the SFP more effectively, a novel SFP computing algorithm based on geodesic distance and decision graph clustering is proposed. Methods: Firstly, the geodesic distance of model vertices is calculated based on the heat conduction equation, and then the average geodesic distance and importance weight of vertices are calculated. Finally, the decision graph clustering method is used to calculate the decision graph of model vertices. Results and Discussion: 3D models in SHREC 2011 dataset are selected to test the proposed algorithm. Compared with the existing algorithms, this method calculates the SFP of the 3D model from a global perspective. Results show that it is not affected by model posture and noise. Conclusion: Our method maps the SFP of the 3D model to the 2D decision-making diagram, which simplifies the calculation process of SFP, improves the calculation accuracy and possesses strong robustness. © 2021 Bentham science Publishers.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

SAM-Swin: SAM-Driven Dual-Swin Transformers with Adaptive Lesion Enhancement for Laryngo-Pharyngeal Tumor Detection

arXiv

引用

arXiv 2024年

作者： Wei, Jia Li, Yun Fan, Xiaomao Ma, Wenjun Qiu, Meiyu Chen, Hongyu Lei, Wenbin College of Big Data and Internet Shenzhen Technology University Shenzhen China The First Affiliated Hospital Sun Yat-Sen University Guangzhou China Aberdeen Institute of Data Science and Artificial Intelligence South China Normal University Foshan China

Laryngo-pharyngeal cancer (LPC) is a highly lethal malignancy in the head and neck region. Recent advancements in tumor detection, particularly through dual-branch network architectures, have significantly improved diagnostic accuracy by integrating global and local feature extraction. However, challenges remain in accurately localizing lesions and fully capitalizing on the complementary nature of features within these branches. To address these issues, we propose SAM-Swin, an innovative SAM-driven Dual-Swin Transformer for laryngo-pharyngeal tumor detection. This model leverages the robust segmentation capabilities of the Segment Anything Model 2 (SAM2) to achieve precise lesion segmentation. Meanwhile, we present a multi-scale lesion-aware enhancement module (MS-LAEM) designed to adaptively enhance the learning of nuanced complementary features across various scales, improving the quality of feature extraction and representation. Furthermore, we implement a multi-scale class-aware guidance (CAG) loss that delivers multi-scale targeted supervision, thereby enhancing the model’s capacity to extract class-specific features. To validate our approach, we compiled three LPC datasets from the First Affiliated Hospital (FAHSYSU), the Sixth Affiliated Hospital (SAHSYSU) of Sun Yat-sen University, and Nanfang Hospital of Southern Medical University (NHSMU). The FAHSYSU dataset is utilized for internal training, while the SAHSYSU and NHSMU datasets serve for external evaluation. Extensive experiments demonstrate that SAM-Swin outperforms state-of-the-art methods, showcasing its potential for advancing LPC detection and improving patient outcomes. The source code of SAM-Swin is available at the URL of https://***/VVJia/SAM-Swin. Copyright © 2024, The Authors. All rights reserved.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

A modified FCN-based method for Left Ventricle endocardium and epicardium segmentation with new block modules 8

A modified FCN-based method for Left Ventricle endocardium a...

引用

8th NAFOSTED Conference on Information and Computer science, NICS 2021

作者： Nham, Do-Hai-Ninh Trinh, Minh-Nhat Tran, Tien-Thanh Pham, Van-Truong Tran, Thi-Thao Hanoi University of Science and Technology School of Applied Mathematics and Informatics Vingroup Big Data Institute Smart Health Center

ISBN: (纸本)9781665410014

Cardiac segmentation of medical magnetic resonance images has been crucial nowadays owing to its necessity for cardiac problems diagnosis. In the increasing demand of advanced procedures for cardiac disease diagnosis and inspired by the structure of receptive field block;in this paper, we propose a new block module then further assembling into a deep fully convolutional neural network to deal with automated left ventricle segmentation. With only one learning stage, our proposed model is trained end-to-end, pixels-to-pixels and validated on two popular cardiac MRI benchmarks, ACDC and SunnyBrook datasets. Several experiments have proved that our new model architecture has a better performance than previous segmentation methods with enhanced feature discriminability and robustness, despite having much less training parameters. © 2021 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Learning a Low-Rank Feature Representation: Achieving Better Trade-Off Between Stability and Plasticity in Continual Learning

Learning a Low-Rank Feature Representation: Achieving Better...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhenrong Liu Yang Li Yi Gong Yik-Chung Wu Department of Electrical and Electronic Engineering Southern University of Science and Technology Shenzhen China Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Shenzhen Research Institute of Big Data Shenzhen China

In continual learning, networks confront a trade-off between stability and plasticity when trained on a sequence of tasks. To bolster plasticity without sacrificing stability, we propose a novel training algorithm called LRFR. This approach optimizes network parameters in the null space of the past tasks’ feature representation matrix to guarantee the stability. Concurrently, we judiciously select only a subset of neurons in each layer of the network while training individual tasks to learn the past tasks’ feature representation matrix in low-rank. This increases the null space dimension when designing network parameters for subsequent tasks, thereby enhancing the plasticity. Using CIFAR-100 and TinyImageNet as benchmark datasets for continual learning, the proposed approach consistently outperforms state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Basketball Win Percentage Prediction using Ensemble-based Machine Learning 6

Basketball Win Percentage Prediction using Ensemble-based Ma...

引用

6th International Conference on Electronics, Communication and Aerospace technology, ICECA 2022

作者： Sikka, Dhruv Rajeswari, D. School of Computing College of Engineering and Technology Srm Institute of Science and Technology Department of Networking and Communications Kattankulathur603203 India School of Computing Srm Institute of Science and Technology Department of Data Science and Business Systems Kattankulathur603203 India

ISBN: (纸本)9781665482714

Basketball is a prominent team sport played on a rectangular court between two teams of five players each. The goal is to shoot the ball through the defender's hoop, which is high on a backboard at each end of the court, while stopping the other team from shooting through its own hoop. Predicting how sports will turn out is an interesting sports analytics problem because it gives valuable data for running the sports market. In this work, data from NBA (National Basketball Association) basketball teams is analyzed, and a machine learning model is made that uses advanced statistical measures and performance data to evaluate and predict the winning percentage of different teams. Voting Regression is used to put together algorithms like Random Forest, Decision Trees, Linear Regression, Gaussian Regression, and Gradient Boosting into a single unit that can predict a team's win percentage over the course of a season with 93.3% accuracy. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Two-dimensional transition metal chalcogenide nanomaterials for cancer diagnosis and treatment

引用

Chinese Chemical Letters 2022年第10期33卷 4437-4448页

作者： Jingjing Wu Tingting Hu Guoping Zhao Anran Li Ruizheng Liang State Key Laboratory of Chemical Resource Engineering Beijing Advanced Innovation Center for Soft Matter Science and EngineeringBeijing University of Chemical TechnologyBeijing 100029China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine School of Engineering MedicineBeihang UniversityBeijing 100191China Department of Orthopedics Guilin People's HospitalGuilin 541002China

For more than a decade,the exfoliation of graphene and other layered materials has led to a tremendous amount of research in two-dimensional(2D)materials,among which 2D transition metal chalcogenides(TMCs)nanomaterials have attracted much attention in a wide range of applications including photoelectric devices,lithium-ion batteries,catalysis,and energy conversion and storage owing to their unique photoelectric physical *** such large specific surface area,strong near-infrared(NIR)absorption and abundant chemical element composition,2D TMCs nanomaterials have become good candidates in biomedical imaging and cancer *** review systematically summarizes recent progress on 2D TMCs nanomaterials,which includes their synthesis methods and applications in cancer *** the end of this review,we also highlight the future prospects and challenges of 2D TMCs *** is expected that this work can provide the readers with a detailed overview of the synthesis of 2D TMCs and inspire more novel functional biomaterials based on 2D TMCs for cancer treatment in the future.

关键词： Two-dimensional(2D)nanomaterials Transition metal chalcogenides(TMCs) Synthesis method Biomedical imaging Cancer treatment

来源：评论

学校读者我要写书评

暂无评论

Utilizing Machine Learning in Medical Diagnosis: Systematic Review and Empirical Analysis 24

Utilizing Machine Learning in Medical Diagnosis: Systematic ...

引用

24th International Arab Conference on Information technology, ACIT 2023

作者： Alazaidah, Raed Hassan, Mohammad Al-Rbabah, Lara Samara, Ghassan Yusof, Marina Al-Sherideh, Ala'a Saeb Zarqa University Ai Faculty of Information Technology Department of Data Science Zarqa Jordan Zarqa University Faculty of Information Technology Department of Computer Science Zarqa Jordan The Hashemite University Faculty of Engineering Department of Computer Engineering Zarqa Jordan Selanger Malaysia Zarqa University Faculty of Information Technology Department of Cyber Security Zarqa Jordan

ISBN: (纸本)9798350384307

During the last few years, several real-life applications have attempted to utilize the proven high capabilities of artificial intelligence in general and machine learning in particular. Machine learning has been utilized in several domains, such as spam detection, image recognition, recommendation systems, self-driving cars, and medical diagnosis. This paper aims to survey the most related work of utilizing machine learning in the domain of medical diagnosis. Moreover, the paper proposes a comparative analysis for identifying and determining the best classification model and feature selection method in mind of handling medical datasets. Hence, four different medical datasets have been used to train twenty-three classification models and four well-known feature selection methods with respect to several evaluation metrics such as Accuracy, True Positive ratio, False Positive ratio, Precision, and Recall. The results reveal that RandomForest, J48, and SMO classifiers are the best classifiers when it comes to handling medical datasets respectively. Furthermore, the Gain Ratio method is the best choice for handling the step of feature selection. © 2023 IEEE.

关键词： Classification Feature Selection Machine Learning Medical Diagnosis Prediction

来源：评论

学校读者我要写书评

暂无评论

A Power-System Economic Dispatching Based on Enhanced Group Search Optimizer 1

引用

18th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2022

作者： Pan, Jeng-Shyang Nguyen, Trong-The Nguyen, Trinh-Dong Nguyen, Vinh-Tiep Dao, Thi-Kien College of Computer Science and Engineering Shandong University of Science and Technology Qing-Dao266590 China Department of Information Management Chaoyang University of Technology Taichung41349 Taiwan University of Information Technology Ho Chi Minh City700000 Viet Nam Vietnam National University Ho Chi Minh City700000 Viet Nam Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China

ISBN: (数字)9789819901050

ISBN: (纸本)9789819901043

Economic dispatch (ED) is one of the critical tasks in a power system’s optimization issues, but its characteristics with non-convex, high-dimensional, non-linear, and non-differentiable, so that caused solutions are more challenging in reality. This paper suggests an enhanced group search optimizer (EGSO) for solving the ED model with the valve-point effect and the different fuels. The EGSO adopts the original group search optimizer (GSO) by changing polar to Cartesian coordinate’s conversion and adding cyclic translation operators to the search behavior of the finder and walker to avoid falling into local optimal and slow convergence of the GSO. In the experiment section, the testing power systems of the ED model are used to validate the EGSO performance. The experimental results reveal that EGSO outperformed the other algorithms regarding convergence speed, the time required to complete calculations, and impacts with lower fuel cost. Additionally, with excellent outcomes in optimization issues involving multiple local optimal values show the EGSO is practical, quick, and efficient in addressing the challenging ED model. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

YOLOv5 Algorithm Optimization: Precise Target Detection Amidst Background Interference

YOLOv5 Algorithm Optimization: Precise Target Detection Amid...

引用

Consumer Electronics and Computer Engineering (ICCECE), 2021 IEEE International Conference on

作者： Bingbing Xiong Wenxi Shi Yanyun Fu Zhansheng Zhu Deyong Wang Bin Jia School of Computer Science and Technology Xinjiang University Urumqi China Key Laboratory of Big Data of Xinjiang Social Security Risk Xinjiang Lianhaichuangzhi Information Technology Co. Ltd. Beijing China Beijing Academy of Science and Technology Beijing China Key Laboratory of Big Data of Xinjiang Social Security Risk Xinjiang Lianhaichuangzhi Information Technology Co. Ltd. Urumqi China

This paper solves the challenge that the target is submerged in the background in the border security scenario, and proposes the enhancement of YOLOv5 algorithm. EfficientViT replaces the DarkNet backbone, leveraging Transformer models for improved feature extraction. Modifications to the Spatial Pyramid Pooling-Fast (SPPF) module enhance the algorithm's robustness to scale variations. Introducing SCYLLA-IoU (SIoU) in the loss function improves model convergence speed and accuracy. Validated on a custom border security dataset, the enhancements show an improved average precision mean (mAP) of 48.3%, a 2.2 percentage point increase over the original YOLOv5s model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Three-layer Model for Investigating the Effect of Clothing Made of Fleece, Denim, and Leather on the Interaction of Millimetre Wave Radiation on the Skin 8

A Three-layer Model for Investigating the Effect of Clothing...

引用

Emerging Imaging and Sensing Technologies for Security and Defence VIII 2023

作者： Owda, Amani Yousef Salmon, Neil Owda, Majdi Department of Natural Engineering and Technology Sciences Arab American University Ramallah Palestine MMW Sensors Limited Manchester United Kingdom Faculty of Data Science Arab American University Ramallah Palestine

ISBN: (纸本)9781510667099

This paper proposes a three-layer electromagnetics model for investigating the interaction of millimetre wave radiation with human skin and clothing as a means to improve security screening technology. Progress in this spectral band is only possible with a deep understanding of the interaction of this radiation with the human body, the clothing and threat items;the proposed model in this paper is implemented to provide us with this information. The model consists of three layers namely;1) air (a semi-infinite layer and lossless layer), 2) clothing layer (finite thickness layer ranging from 0.0 mm-1.2 mm), and 3) skin layer (semi-infinite layer). Three types of clothing are investigated by the model, these being: 1) Fleece, 2) Denim, and 3) Leather. Simulation results indicate that a clothing layer, in direct contact with human skin, enhances the transmission of radiation between air and skin. This is due to the clothing layer acting as an impedance-matching transformer. The simulation results indicate that the power transmission coefficient varies with the frequency and thickness of the clothing layer. For the Fleece, the power transmission coefficient was found to increase fractionally, ranging from 0.05 to 0.112 at 90 GHz when the thickness of the fleece varied between 0.5mm and 1.2 mm. For the Denim, the difference in the transmission coefficient was found to increase with the thickness of the Denim, up to a factor of 0.095, when the thickness of the Denim layer varied from 0.5 mm to 1.2 mm at 60 GHz. For the beige leather, the variation in the transmission coefficient between different thicknesses was substantial and it could be up ~10.0% when the thickness of the material varied from 0.5 mm to 1.0 mm at 60 GHz. However, when the thickness of the leather was 1.2 mm, the maximum value of the transmission coefficient of 0.83 was achieved at around 45 GHz. Simulation results obtained from the three-layer model presented in this paper are in good agreement with the

关键词： Millimeter waves

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：