检索结果-内蒙古大学图书馆

Using NSGA-Ⅲ for optimising biomedical ontology alignment

CAAI Transactions on Intelligence Technology 2019年第3期4卷 135-141页

作者： Xingsi Xue Jiawei Lu Junfeng Chen College of Information Science and Engineering Fujian University of TechnologyFuzhouFujianPeople’s Republic of China Intelligent Information Processing Research Center Fujian University of TechnologyFuzhouFujianPeople’s Republic of China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of TechnologyFuzhouFujianPeople’s Republic of China Fujian Key Laboratory for Automotive Electronics and Electric Drive Fujian University of TechnologyFuzhouFujianPeople’s Republic of China College of IOT Engineering Hohai UniversityChangzhouJiangsuPeople’s Republic of China

To support semantic inter-operability between the biomedical information systems, it is necessary to determine the correspondences between the heterogeneous biomedical concepts, which is commonly known as biomedical ontology matching. Biomedical concepts are usually complex and ambiguous, which makes matching biomedical ontologies a challenge. Since none of the similarity measures can distinguish the heterogeneous biomedical concepts in any context independently, usually several similarity measures are applied together to determine the biomedical concepts mappings. However, the ignorance of the effects brought about by different biomedical concept mapping’s preference on the similarity measures significantly reduces the alignment’s quality. In this study, a non-dominated sorting genetic algorithm (NSGA)-III-based biomedical ontology matching technique is proposed to effectively match the biomedical ontologies, which first utilises an ontology partitioning technique to transform the large-scale biomedical ontology matching problem into several ontology segment-matching problems, and then uses NSGA-III to determine the optimal alignment without tuning the aggregating weights. The experiment is conducted on the anatomy track and large biomedic ontologies track which are provided by the Ontology Alignment Evaluation Initiative (OAEI), and the comparisons with OAEI’s participants show the effectiveness of the authors’ approach.

关键词： ontology ontologies transform together Ontology complex context effects

来源：评论

学校读者我要写书评

暂无评论

An Asynchronous Clustering and Mobile Data Gathering Schema Based on Timer Mechanism in Wireless Sensor Networks

引用

Computers, Materials & Continua 2019年第3期58卷 711-725页

作者： Jin Wang Yu Gao Wei Liu Wenbing Wu Se-Jung Lim Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation School of Computer&Communication EngineeringChangsha University of Science&TechnologyChangsha410114China School of Information Science and Engineering Fujian University of TechnologyFuzhou350000China College of Information Engineering Yangzhou UniversityYangzhou225000China Department of Computer Engineering Chonnam National UniversityYeosu596597Korea.

Recently,Wireless sensor networks(WSNs)have become very popular research topics which are applied to many *** provide pervasive computing services and techniques in various potential applications for the Internet of Things(IoT).An Asynchronous Clustering and Mobile Data Gathering based on Timer Mechanism(ACMDGTM)algorithm is proposed which would mitigate the problem of“hot spots”among sensors to enhance the lifetime of *** clustering process takes sensors’location and residual energy into consideration to elect suitable cluster ***,one mobile sink node is employed to access cluster heads in accordance with the data overflow time and moving time from cluster heads to *** experimental results display that the presented method can avoid long distance communicate between sensor ***,this algorithm reduces energy consumption effectively and improves package delivery rate.

关键词： Internet of things wireless sensor networks clustering mobile data collection timer.

来源：评论

学校读者我要写书评

暂无评论

6D-VNet: End-to-end 6DoF Vehicle Pose Estimation from Monocular RGB Images

6D-VNet: End-to-end 6DoF Vehicle Pose Estimation from Monocu...

引用

IEEE/CVF Conference on Computer Vision and pattern recognition Workshops

作者： Di Wu Zhaoyong Zhuang Canqun Xiang Wenbin Zou Xia Li The Guangdong Key Laboratory of Intelligent Information Processing College of Information Engineering Shenzhen University

ISBN: (数字)9781728125060

ISBN: (纸本)9781728125077

We present a conceptually simple framework for 6DoF object pose estimation, especially for autonomous driving scenario. Our approach efficiently detects traffic participants in a monocular RGB image while simultaneously regressing their 3D translation and rotation vectors. The method, called 6D-VNet, extends Mask R-CNN by adding customised heads for predicting vehicle's finer class, rotation and translation. The proposed 6D-VNet is trained end-to-end compared to previous methods. Furthermore, we show that the inclusion of translational regression in the joint losses is crucial for the 6DoF pose estimation task, where object translation distance along longitudinal axis varies significantly, e.g., in autonomous driving scenarios. Additionally, we incorporate the mutual information between traffic participants via a modified non-local block. As opposed to the original non-local block implementation, the proposed weighting modification takes the spatial neighbouring information into consideration whilst counteracting the effect of extreme gradient values. Our 6D-VNet reaches the 1 st place in ApolloScape challenge 3D Car Instance task. Code has been made available at: .

关键词： pose estimation end-to-end red-green-blue colour model vehicle rotation vector six degrees of freedom Translation Translation Process task codes

来源：评论

学校读者我要写书评

暂无评论

Multi-scale feature fusion for breast tumor grading using dual-adaptive attention mechanisms

引用

pattern recognition 2026年 169卷

作者： Israr Hussain Zhihui Lai Heng Kong Fazil Hussain College of Computer Science and Software Engineering Shenzhen University Shenzhen 518060 China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen 518060 China Department of Thyroid and Breast Surgery BaoAn Central Hospital of Shenzhen Shenzhen 518102 China Department of Medicine Provincial Head Quarter (PHQ) Hospital Gilgit 15711 Pakistan

Breast cancer is the most common malignant tumor in women worldwide. Early detection and timely treatment are crucial for improving survival rates and ensuring effective treatment planning. While existing methods primarily focus on classifying benign versus malignant tumors, accurate tumor grading remains underexplored. The scarcity of high-quality annotated datasets for advanced tumor grades, combined with their inherent similarity, limits model robustness and precise grading. To address these challenges, we propose a novel framework for breast tumor grading diagnosis that leverages multi-scale feature fusion with dual-adaptive attention mechanisms. This framework enhances grading performance by capturing both local and global information. It integrates information across multiple scales, improves feature representation, and enables the detection of subtle differences between grades. The framework consists of three primary modules: deep hybrid feature extraction, multi-scale feature fusion, and dual-adaptive attention mechanisms. Together, these modules enhance feature representation, capture salient information, and highlight discriminative features, ultimately improving grading accuracy. In addition, we constructed two distinct image datasets consisting of 17,058 ultrasound images and 1571 MRI images for breast tumor grading. Experimental results demonstrated the effectiveness of our framework, achieving a test accuracy of 0.89, a macro-average F1-score of 0.82, and a micro-average precision of 0.93, outperforming existing 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

Multi-scale Generative Adversarial Network for Automatic Sublingual Vein Segmentation

Multi-scale Generative Adversarial Network for Automatic Sub...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Qingyue Xiong Xinlei Li Dawei Yang Wei Zhang Ye Zhang Yajie Kong Fufeng Li Wenqiang Zhang Academy for Engineering and Technology Fudan University Shanghai China Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China Changchun Institute of Optics Fine Mechanics and Physics Chinese Academy of Sciences Laboratory of TCM four Processing Shanghai university of TCM Shanghai China

ISBN: (数字)9781728162157

ISBN: (纸本)9781728162164

Sublingual vein segmentation is an essential yet challenging task in computer-aided Traditional Chinese Medicine (TCM) tongue diagnosis. The most intricate part of sublingual vein segmentation is the strong diversity of sublingual vein images (e.g., various exposure of vein and complex background) and the natural connectivity of veins. To this end, we propose a novel and effective approach based on generative adversarial networks (GANs). Specifically, the framework comprises two modules: a segmentation generator network with multi-scale outputs and a scale-consistent discriminator. The former segmentation generator learns the overall structure of the segmentation, which reduces the training difficulties of stride 1 output by multi-scale outputs. The latter scale-consistent discriminator regularizes the segmentation maps from different output strides, which keeps the natural connectivity of veins and avoids generated noise. Additionally, we have constructed and publicized a well-annotated sublingual vein dataset (FDU-SV) which we believe will promote the significant development of this area. Extensive experimental results confirm that our method outperforms other representative segmentation models with a remarkable margin, achieving the state-of-the-art performance of 64.53% mIoU score. Code and dataset are available at https://***/echobear313/FDUVEIN.

关键词： Image segmentation Veins Training Generators Tongue Feature extraction Task analysis

来源：评论

学校读者我要写书评

暂无评论

Fruit detection using faster R-CNN based on deep network 2nd

Fruit detection using faster R-CNN based on deep network

引用

2nd International Conference on Smart Vehicular Technology, Transportation, Communication and Applications, VTCA 2018

作者： Ma, Linjuan Zhang, Fuquan Xu, Lin School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China Key Laboratory of Nondestructive Testing Fuqing Branch of Fujian Normal University Fuzhou350300 China

ISBN: (纸本)9783030045845

Fruit detection is of great significance in the agriculture. Recently, deep neural network has been widely studied in fruit detection. In our paper, we present a new approach of fruit detection, which uses Faster R-CNN based on deep network AlexNet. Our aim is to develop a fast, accurate and convenient model to detect and classify the fruit. Data augmentation is also used to increase the fruit dataset and avoid the overfitting in some degree. We use the fruits-360 dataset to perform the experiments. © Springer Nature Switzerland AG 2019.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Multilevel Characteristic Basis Function Method with ACA for Accelerated Solution of Electrically Large Scattering Problems

引用

Transactions of Nanjing university of Aeronautics and Astronautics 2018年第3期35卷 449-454页

作者： Li Chenlu Sun Yufa Wang Zhonggen Wang Guohua Key Laboratory of Intelligent Computing & Signal Processing Ministry of EducationAnhui University College of Electrical and Information Engineering Anhui University of Science and Technology

The multilevel characteristic basis function method(MLCBFM)with the adaptive cross approximation(ACA)algorithm for accelerated solution of electrically large scattering problems is studied in this *** the conventional MLCBFM based on Foldy-Lax multiple scattering equations,the improvement is only made in the generation of characteristic basis functions(CBFs).However,it does not provide a change in impedance matrix filling and reducing matrix calculation procedure,which is *** reality,all the impedance and reduced matrix of each level of the MLCBFM have low-rank property and can be calculated ***,ACA is used for the efficient generation of two-level CBFs and the fast calculation of reduced matrix in this *** results are given to demonstrate the accuracy and efficiency of the method.

关键词： multilevel characteristic basis function method(MLCBFM) adaptive cross approximation(ACA) characteristic basis functions(CBFs) electromagnetic scattering

来源：评论

学校读者我要写书评

暂无评论

Observer-like Model Reference Adaptive Augmenting based fixed-wing UAV Control

Observer-like Model Reference Adaptive Augmenting based fixe...

引用

第三十九届中国控制会议

作者： Jizhang Xiong Ye Yang Zhongtao Cheng Lei Liu Yongji Wang Huijin Fan National Key Laboratory of Science and Technology on Multispectral Information Processing School of Artificial Intelligence and AutomationHuazhong University of Science and Technology Science and Technology on Aerospace Intelligent Control Laboratory Beijing Aerospace Automatic Control Institute

This paper proposed an observer-like model reference adaptive augmenting control(OMRAAC) design method for a class of multi-input multi-output systems with uncertainty, which can improve the dynamic performance of the system. This control system design method can perform adaptive augmenting control design without changing the original baseline controller of the system(such as PID control, LQR control, etc.), to cope with possible uncertainty in the system and improve the tracking performance of the system. At the same time, in order to suppress the transient oscillation of the system caused by the large adaptive rates, the state tracking error is introduced into the reference model, and an observer-like reference model is designed to improve the dynamic process of the system. Finally, in order to verify the effectiveness of the method, simulation and analysis are performed on the longitudinal short-period model of the fixed-wing UAV, to verify the effectiveness of the method. The simulation compares the tracking performance of the control system based on the LQR controller, the traditional Model Reference Adaptive augmented Augmented Controller, and the proposed OMRAAC method. The simulation results show that the observer-like adaptive augmenting control can effectively suppress the system uncertainties, and improve the dynamic response performance of the system.

关键词： adaptive augmenting control fixed-wing UAV control oscillation suppression

来源：评论

学校读者我要写书评

暂无评论

Analysis and Prediction of Commercial Big Data Based on WIFI Probe 4th

Analysis and Prediction of Commercial Big Data Based on WIFI...

引用

4th International Conference on Smart Computing and Communications, SmartCom 2019

作者： Zeng, Xiao Guo, Hong Liu, Zhe College of Computer Science and Technology Wuhan University of Science and Technology WuhanHubei China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China

ISBN: (纸本)9783030341381

With the development of the Internet economy, offline physical transactions are facing a huge test. The number of merchants in many shopping malls has decreased, and the volume of physical transactions has fallen sharply. As an important data of the operation status of the shopping mall, passenger traffic can grasp the best operating time, arrange employees reasonably, and judge the marketing volume of the shopping mall. Therefore, excellent mall operators need to know the status of the passenger flow in the market in a timely manner, and analyze the overall operation situation and make reasonable operational decisions. Based on the above problems, this paper designs and implements a commercial big data analysis and prediction system based on WIFI probe, obtains basic data through WIFI probe hardware sensor, and provides relatively accurate passenger flow information for commercial field, combined with big data analysis and machine learning prediction. The algorithm analyzes a series of information about passenger flow, store quantity, bounce rate, dwell time and other forecasting trend of passenger flow in the future, providing reliable data support for the commercial field and becoming the reference for various decisions. © 2019, Springer Nature Switzerland AG.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Advanced geometry surface coding for dynamic point cloud compression

arXiv

引用

arXiv 2021年

作者： Xiong, Jian Gao, Hao Wang, Miaohui Li, Hongliang Ngan, King Ngi Lin, Weisi College of Telecommunications and Information Engineering Nanjing University of Posts and Telecommunications Nanjing210003 China College of Artificial Intelligence Nanjing University of Posts and Telecommunications Nanjing210003 China School of Computer Science and Cyberspace Security Hainan University China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University China School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu611731 China School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore

In video-based dynamic point cloud compression (V-PCC), 3D point clouds are projected onto 2D images for compressing with the existing video codecs. However, the existing video codecs are originally designed for natural visual signals, and it fails to account for the characteristics of point clouds. Thus, there are still problems in the compression of geometry information generated from the point clouds. Firstly, the distortion model in the existing rate-distortion optimization (RDO) is not consistent with the geometry quality assessment metrics. Secondly, the prediction methods in video codecs fail to account for the fact that the highest depth values of a far layer is greater than or equal to the corresponding lowest depth values of a near layer. This paper proposes an advanced geometry surface coding (AGSC) method for dynamic point clouds (DPC) compression. The proposed method consists of two modules, including an error projection model-based (EPM-based) RDO and an occupancy map-based (OM-based) merge prediction. Firstly, the EPM model is proposed to describe the relationship between the distortion model in the existing video codec and the geometry quality metric. Secondly, the EPM-based RDO method is presented to project the existing distortion model on the plane normal and is simplified to estimate the average normal vectors of coding units (CUs). Finally, we propose the OM-based merge prediction approach, in which the prediction pixels of merge modes are refined based on the occupancy map. Experiments tested on the standard point clouds show that the proposed method achieves an average 9.84% bitrate saving for geometry compression. Copyright © 2021, The Authors. All rights reserved.

关键词： Signal distortion

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：