检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

7,403 篇 会议
348 篇 期刊文献
57 册 图书
17 篇 学位论文

馆藏范围

7,825 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

4,450 篇 工学
- 3,422 篇 计算机科学与技术...
- 1,717 篇 软件工程
- 1,076 篇 电气工程
- 714 篇 信息与通信工程
- 343 篇 控制科学与工程
- 342 篇 电子科学与技术（可...
- 304 篇 光学工程
- 233 篇 机械工程
- 224 篇 生物医学工程（可授...
- 178 篇 仪器科学与技术
- 154 篇 生物工程
- 90 篇 测绘科学与技术
- 59 篇 化学工程与技术
- 56 篇 航空宇航科学与技...
- 53 篇 材料科学与工程（可...
- 47 篇 土木工程
- 42 篇 动力工程及工程热...
- 40 篇 力学（可授工学、理...
1,599 篇 理学
- 781 篇 物理学
- 690 篇 数学
- 181 篇 生物学
- 145 篇 统计学（可授理学、...
- 142 篇 系统科学
- 80 篇 化学
556 篇 医学
- 456 篇 临床医学
- 103 篇 特种医学
- 80 篇 基础医学(可授医学...
446 篇 管理学
- 288 篇 管理科学与工程(可...
- 176 篇 图书情报与档案管...
- 74 篇 工商管理
37 篇 法学
36 篇 农学
23 篇 经济学
20 篇 文学
17 篇 教育学
7 篇 艺术学
6 篇 军事学

主题

868 篇 parallel process...
693 篇 image processing
326 篇 image segmentati...
297 篇 concurrent compu...
273 篇 distributed comp...
259 篇 computational mo...
252 篇 computer archite...
250 篇 feature extracti...
215 篇 image reconstruc...
195 篇 image edge detec...
186 篇 image coding
177 篇 graphics process...
170 篇 iterative method...
166 篇 hardware
165 篇 algorithm design...
164 篇 neural networks
160 篇 deep learning
159 篇 computer science
142 篇 pixel
140 篇 graphics process...

机构

47 篇 national laborat...
25 篇 college of compu...
21 篇 natl univ def te...
20 篇 natl univ def te...
19 篇 science and tech...
14 篇 natl univ def te...
13 篇 school of comput...
12 篇 univ chinese aca...
11 篇 king saud univer...
11 篇 university of ch...
11 篇 natl univ def te...
10 篇 national univers...
9 篇 natl univ def te...
9 篇 institute of inf...
9 篇 national laborat...
8 篇 natl univ def te...
8 篇 department of co...
8 篇 national laborat...
8 篇 college of compu...
8 篇 school of comput...

作者

37 篇 dou yong
28 篇 luo zhigang
27 篇 yong dou
21 篇 zhang xiang
19 篇 zhigang luo
18 篇 li dongsheng
17 篇 naiyang guan
17 篇 qiao peng
15 篇 huang xuhui
15 篇 jie liu
14 篇 niu xin
13 篇 yijie wang
13 篇 lan long
13 篇 wang huaimin
12 篇 anon
11 篇 xiang zhang
11 篇 yang yang
11 篇 liu jie
11 篇 wang yijie
11 篇 pesquet jean-chr...

语言

7,657 篇 英文
112 篇 其他
52 篇 中文
7 篇 土耳其文
3 篇 俄文

检索条件"任意字段=Conference on Parallel and Distributed Methods for Image Processing"

共 7825 条记录，以下是1221-1230 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

FEMD: Feature Enhancement-aided Multimodal Feature Fusion Approach for Smart Contract Vulnerability Detection

FEMD: Feature Enhancement-aided Multimodal Feature Fusion Ap...

引用

International conference on parallel and distributed Systems (ICPADS)

作者： Juan Li Rui Li Youshui Lu Bowen Cai Yulin Cao Hang Lin Xingxing Li Chan Li School of Computer Science Qinghai Normal University Xining China School of Computer Science and Technology Xidian University The State Key Laboratory of Tibetan Intelligent Information Processing and Application School of Computer Science Qinghai Normal University Xian China School of the Instrument Science and Technology and School of Electrical Engineering Xi’an Jiaotong University Xian China School of Science and Engineering University of Minnesota - Twin City Minneapolis USA

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Smart contracts, due to their immutability and transparency upon deployment, entail significant economic and systemic risks from any vulnerabilities present. Traditional vulnerability detection methods suffer from low automation and high false positive rates, while existing deep learning-based approaches inadequately extract contract features, thereby limiting detection accuracy. To address these issues, this paper proposes FEMD: a feature-enhanced aided multimodal feature fusion method for smart contract vulnerability detection. Building on the foundation of addressing the low automation of traditional detection tools, our method improves the model’s feature extraction performance and detection capabilities. Specifically, we construct a contract graph through Comprehensive Expert-Graph Fusion, combining multi-modal feature fusion using a multi-head attention mechanism with expert patterns to ensure the capture and effective preservation of all critical information during the fusion process. To delve deeper into potential information within smart contract graphs, we employ a Feature Enhancer that leverages transpose operations on feature matrices to extract complex interaction patterns across different dimensions. Our approach is validated through batches of experiments on the Ethereum open dataset focusing on reentrancy and timestamp dependency vulnerabilities, demonstrating significant improvements in detection accuracy and robustness.

关键词： Economics Automation Accuracy Limiting Smart contracts Buildings Focusing Feature extraction Robustness Data mining

来源：评论

学校读者我要写书评

暂无评论

High-Order Faithful Interpretation methods for Tensor-Based CNNs

High-Order Faithful Interpretation Methods for Tensor-Based ...

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Pengxu Chen Huazhong Liu Hanning Zhang Jihong Ding Yunfan Zhang Dehua Chen School of Comp. Sci. & Tech Hainan University Haikou China Innovation Research Institute China Unicom (Hainan) Haikou China School of Comp. Sci. & Tech Donghua University Shanghai China

Tensor-based Convolution Neural Networks (CNNs) have achieved remarkable success in realizing multi-modal classification while mining the hidden relationships of big data. Nevertheless, these models exhibit high performance but low interpretability due to the numerous intricate and abstract internal network structures. Therefore, this paper focuses on exploring interpretation methods suitable for tensor-based CNN models. Concretely, this paper first presents a general interpretation method called high-order class activation mapping (HO-CAM), which leverages the internal structure of tensor-based CNN with global average pooling (GAP) and generate explanations by highlighting attention regions of prediction result. Then, to apply this high-order interpretation method to tensor-based CNNs with any structures, two advanced interpretation methods, namely high-order gradient-weighted class activation mapping (HOGCAM) and high-order layer class activation mapping (HOLCAM), are proposed by utilizing gradient information with two different weighting strategies. Experimental results demonstrate that HO-CAM performs best in explaining the last layer of specific tensor-based CNNs with GAP, HOG-CAM removes the reliance on GAP and is applicable to any forms of tensor-based CNNs, and HOL-CAM exhibits better interpretation performance than HOG-CAM across arbitrary layers of any models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DCSN: A Flexible and Efficient Lightweight Network for Dense Cell Segmentation

DCSN: A Flexible and Efficient Lightweight Network for Dense...

引用

Medical Artificial Intelligence (MedAI), IEEE International conference on

作者： Futai Pan Fei Wang Shanghai Key Lab of Intelligent Information Processing School of Computer Science and Technology Fudan University Shanghai China

Cells serve as the fundamental building blocks of living organisms and necessitate the utilization of diverse microscopic imaging techniques for observation. Nevertheless, there exist numerous limitations within phase-contrast microscopy imaging technology, leading to indistinct imaging in a considerable number of acquired cell images. Furthermore, the wide range of cell shapes and sizes, often densely distributed, poses challenges for research in the field of cell image analysis. We propose Dense Cell Segmentation Network (DCSN), an anchor-based single-stage instance segmentation method, to address the challenge of dense detection and instance segmentation in high-density cell images. While methods based on transformers have emerged as prominent approaches in natural image detection and segmentation, they are limited in their applicability to cell image analysis due to the scarcity of cell image datasets. Consequently, we aim to introduce a simple yet effective instance segmentation method to further address the challenge of cell image segmentation. DCSN is a lightweight multi-task model, combining object detection and semantic segmentation to achieve accurate instance segmentation. We validate our approach on LIVECell, a publicly available annotated cell dataset, and demonstrate its efficacy. By combining the advantages of anchor-based methods and single-stage methods, DCSN achieves a favorable balance between speed and performance. In comparison to the anchor-based two-stage model Mask R-CNN, DCSN offers a streamlined process and faster inference speed. Compared to the anchor-free single-stage method, CenterMask, our model demonstrates superior segmentation performance and generalization capabilities. Moreover,DCSN is a general end-to-end model that can be applied to various domains beyond cell segmentation tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Large Scale Reverse-time Migration Imaging Computation based on distributed Spark Cluster with GPUs

Efficient Large Scale Reverse-time Migration Imaging Computa...

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Suhui Wangzhang Ruizhang Yang Rong Gu Bo Li Dingjin Liu Zhaokang Wang State Key Laboratory for Novel Software Technology Nanjing University China Sinopec Geophysical Research Institute China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China

The reverse-time migration (RTM) imaging algorithm, which is used for complex underground structure analysis, is known as one of the current mainstream method of high-precision seismic imaging. Nowadays, as the fast development of seismic data acquisition technology, there exists large amount of seismic data. Thus, the requirement for the efficient computation of the reverse-time migration (RTM) imaging algorithms over large-scale data have been increased greatly. To address this problem, in this paper, we propose a distributed reverse-time migration imaging algorithm based on the widely-used Spark platform first. Based on that, we design and implement a RTM computation solution based on Spark and GPU with several optimizations, including pre-shuffle&caching and load balancing. We also analyze the fault tolerance capability of the proposed distributed algorithm. We evaluate the proposed methods on the typical three-dimensional wavefild benchmark dataset. Experimental results show that the performance of the Spark based reverse-time migration imaging algorithm can scale up near linearly with computing nodes. In addition, the GPU+Spark based version has significant performance improvement on execution efficiency over the Spark-based algorithm. Moreover, the proposed optimization strategies also take effect. In addition, the method proposed in this paper has been applied in the real-world environment of one of the top oil exploration companies world wide, and has achieved significant improvement under the premise of the algorithm correctness guarantee.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Revenue Forecasting Using distributed Machine Learning In Online Advertising Systems

Revenue Forecasting Using Distributed Machine Learning In On...

引用

Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering (RMKMATE), International conference on

作者： Murugan P Esakkiammal S N. Kanagavalli P. Krishna Priya Jason Elroy Martis P. Kavitha Department of BBA Vels Institute of Science Technology and Advanced Studie (VISTAS) Pallavaram Chennai Tamilnadu India Department of Library Central University of Tamil Nadu Neelakudi Thiruvarur Tamilnadu India Department of CSE Rajalakshmi Institute of Technology Kuthambakkam Chennai Tamilnadu India KL Business School KL Education Foundation Vaddeswaram Guntur Andrha Pradesh India Department of Information Science and Engineering NMAM Institute of Technology Nitte Deemed to be University Karkala Karnataka India Department of Computer Science and Engineering R.M.K. Engineering College Tamilnadu India

This research delves into the utilization of distributed machine learning methods for revenue forecasting in the realm of online advertising systems. As the domain of digital advertising continues to expand rapidly, the accurate prediction of revenue becomes indispensable for optimizing resource allocation and making well-informed decisions. Conventional approaches frequently encounter difficulties in managing the sheer volume and intricacy of advertising data. In contrast, distributed machine learning harnesses the capabilities of parallel processing and distributed computing to efficiently process and analyze large datasets. This investigation explores diverse distributed machine learning algorithms, including gradient boosting, random forests, and neural networks, within the context of revenue forecasting. The research assesses their performance, scalability, and precision in comparison to traditional techniques. Through empirical experiments and case studies, we showcase the potential of distributed machine learning to elevate the accuracy of revenue forecasting in online advertising systems, ultimately contributing to more informed business strategies and enhanced revenue generation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

image homogenization based on gray level co-occurrence matrix and region-growing for spaceborne Martian exploration SAR calibration

Image homogenization based on gray level co-occurrence matri...

引用

Signal, Information and Data processing (ICSIDP), IEEE International conference on

作者： Zhoujie He Wei Guo Xiaoping Li School of Aerospace Science and Technology Xidian University Xi’an China Guangzhou Institute of Technology Xidian University Guangzhou China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Researchers use radar echoes to probe the ionosphere, with synthetic aperture radar (SAR) being one of the current methods for Mars ionosphere detection. The accuracy of radar echoes affects the ionosphere detection results, making radiometric calibration of radar echoes necessary. Due to the size of point targets and the harsh Martian environment, deploying artificial calibrators on Mars is challenging. Thus, there is a need for a distributed SAR target radiometric calibration method suitable for the unique Martian landscape. The antenna pattern is a major influencing factor in radiometric calibration. Homogenized targets are essential for spaceborne synthetic aperture radar (SAR) to obtain antenna patterns using flat and uniform areas. Mountainous desert geology is widespread on Mars and can be utilized for radiometric calibration, but these areas are not uniform and require the removal of non-uniform regions. This paper presents a homogenization method that employs the Gray-Level Co-occurrence Matrix (GLCM) and a region-growing algorithm to generate a mask, effectively achieving the uniformization of non-uniform surface targets. Consequently, the coefficient of variation (CV), a metric used to assess data dispersion, exhibited a reduction of 34%.

关键词： Mars Spaceborne radar Geology Radar detection Radiometry Radar antennas Calibration Indexes Synthetic aperture radar Ionosphere

来源：评论

学校读者我要写书评

暂无评论

distributed Spacecraft Architecture for Persistent Autonomous Orbital Navigation in SCB Missions

Distributed Spacecraft Architecture for Persistent Autonomou...

引用

IEEE Aerospace conference (AeroConf)

作者： Elankumaran, Kawsihen Dempster, Andrew G. Univ New South Wales Australian Ctr Space Engn Res Sydney NSW Australia

ISBN: (纸本)9781728174365

Establishing a sustainable human presence beyond the cis-lunar space is undoubtedly the major focus of space agencies and commercial space organizations at present. Small celestial bodies (SCBs) like near-Earth asteroids (NEAs) have been widely recognized as a crucial stepping stone in this process. An essential requirement for any mission to SCBs is the ability of the spacecraft to navigate in the proximity of these bodies. Proximity navigation is practically very challenging and the need for target relative autonomous navigation is imperative. Since the current methods used for navigation are not completely autonomous, alternative solutions based on SLAM have been proposed in the past. For the SLAM-based solutions to be viable, the algorithm should have a computational complexity scalable with time. Although SLAM can be formulated to exhibit some parallelism, suitable architectures are essential to exploit this property. This paper presents an orbital architecture of two types of spacecraft to accomplish a persistent autonomous navigation. The architecture presents mission spacecraft in an orbit around a SCB that formulate their navigation requirement as a SLAM problem and support spacecraft in a different type of orbit that perform concurrent determination of the navigation solution. The simulation presents the numerically propagated orbits of all the spacecraft and using an empirical evaluation, reveals the utility of the distributed architecture.

关键词： Space vehicles Simultaneous localization and mapping Navigation Computer architecture Organizations parallel processing Orbits

来源：评论

学校读者我要写书评

暂无评论

Cloud-Enhanced Transfer Learning Framework for Medical image Analysis: Advancing Diagnostic Speed and Accuracy in Healthcare

Cloud-Enhanced Transfer Learning Framework for Medical Image...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International conference on

作者： S. Prabu N. Subhash Chandra M Bhavani V K Chaitanya Varma Mukesh Soni Department of Electronics and Communication Engineering Mahendra Institute of Technology Namakkal India Department of Computer Science and Engineering CVR College of Engineering Mangalpalle India Department of Artificial Intelligence and Data Science Rajalakshmi Institute of Technology Chennai India Department of Mechanical Engineering Sagi Rama Krishnam Raju Engineering College Bhimavaram India Dr. D. Y. Patil Vidyapeeth Dr. D. Y. Patil School of Science & Technology Pune India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

When it comes to medical image analysis, problems arise due to the scarce amount of data and computational resources in medical environments. This is because, as earlier stated, cloud settings demand efficient models capable of delivering more reliable diagnostic results without straining the cloud's computing resources. In this work, we presented a transfer learning based on DenseNet-201 as well ResNet-152 architectures with a new large dataset containing 15,000 medical images of different modality. By utilizing the distributed cloud computing and hypermeters precision strategy, the proposed model was found to have 95.8 % of accuracy, 94.2% sensitivity, and 96.3%specificity. It also reduced the processing time by sixty-eight percent over standard methods across the facilities. Five different datasets validated the proposed approach, achieving an external accuracy of 92.4%, indicating improved generalization performance. The enhancement of accuracy to approximately 90% and the reduction in required computation demonstrate its feasibility for extensive clinical applications on the cloud, spanning across hospitals.

关键词： Cloud computing Accuracy image analysis Sensitivity Computational modeling Transfer learning Computer architecture Medical diagnostic imaging Tuning Standards

来源：评论

学校读者我要写书评

暂无评论

Real-Time Binary Cell Phone Usage Detection and Classification on Vehicular Edge Devices

Real-Time Binary Cell Phone Usage Detection and Classificati...

引用

International Wireless Communications and Mobile Computing conference, IWCMC

作者： Murat Arda Onsu Pankti Shah Murat Simsek Mark Fobert Burak Kantarci School of Electrical Engineering and Computer Science University of Ottawa Ottawa ON Canada Raven Connected Ottawa ON Canada

ISBN: (数字)9798350361261

ISBN: (纸本)9798350361278

IoT binary classification tasks can benefit significantly from edge computing because it allows for real-time processing and decision-making. By gathering and processing data locally, edge devices can lower latency and enable quicker response times, which is beneficial for applications whose main aims are safety and security. Cell phone usage while driving is one of the worst scenarios that decreases traffic safety and causes accidents. A wide range of new applications and services could be possible with the convergence of IoT and cell phone detection in the car while in driving mode. Machine learning methods, which include the ability to track people and objects in realtime, increase public safety by identifying and preventing potential security threats and improve transportation system efficiency by streamlining traffic and easing congestion. Although object detection is the most common approach for cell phone detection, the binary classification approach has been proposed because of its fast processing ability and easy deployment on edge devices. The device, in consideration, incorporates an inside camera to gather driver image data to perform binary classification. After collecting images from edge devices, these data are prepared in detail in an IID (independently and identically distributed) manner for better training for deep learning models. After training, test results are obtained by interpolation and extrapolation analyses. Results show that interpolation accuracy increases by $1.1 \%$ and extrapolation accuracy increases by $16.5 \%$.

关键词： Training Performance evaluation Extrapolation Interpolation Cellular phones image edge detection Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Major Depressive Disorder Detection based on parallel Spatiotemporal Convolution Network 23

Major Depressive Disorder Detection based on Parallel Spatio...

引用

Proceedings of the 2023 6th International conference on Digital Medicine and image processing

作者： Jianye Liu Haoran Li Qiang Wu Zihan Diao Zhao Sun Lina Zheng Shandong University China University of Kentucky USA Msunhealth Technology Group Corp Ltd China

ISBN: (纸本)9798400709425

In recent years, the number of patients with depression has grown rapidly. The traditional diagnosis of depression includes mental scales, clinical inquiry etc., which is time consuming and lacks objective confirmation of relevant physiology indicators. In order to overcome the drawback of traditional methods, brain imaging techniques such as electroencephalogram (EEG) have provided new tools for diagnosing depression and shown excellent performance. In this paper, a major depressive disorder (MDD) detection framework is proposed based on parallel spatiotemporal convolution network and mix-multilayer perceptron. First, the wavelet entropy and differential entropy features of EEG were extracted and then parallel spatial temporal convolutional network and mix-multilayer perceptron were employed for further feature representation and extraction. In this process, mmd-loss was creatively added to shorten the gap between the training dataset and the test dataset. Further extracted features were fused and multilayer-perceptron (MLP) was used to perform binary classification. This experiment was evaluated on the MODMA dataset and achieved an accuracy of 0.7832. The experimental results show that the model proposed in our paper is effective in MDD detection and provides better performance compared with the baseline systems.

关键词： Deep Learning EEG Feature Fusion. Graph Neural Network Major Depressive Disorder

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 119 120 121 122 123 124 125 126 127 128 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：