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

7,083 篇 会议
76 册 图书
41 篇 期刊文献

馆藏范围

7,200 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

4,054 篇 工学
- 2,470 篇 计算机科学与技术...
- 1,454 篇 控制科学与工程
- 1,255 篇 软件工程
- 1,252 篇 电气工程
- 1,174 篇 信息与通信工程
- 517 篇 仪器科学与技术
- 499 篇 机械工程
- 356 篇 电子科学与技术（可...
- 276 篇 生物医学工程（可授...
- 238 篇 交通运输工程
- 198 篇 生物工程
- 163 篇 光学工程
- 92 篇 动力工程及工程热...
- 85 篇 安全科学与工程
- 81 篇 化学工程与技术
- 61 篇 力学（可授工学、理...
- 57 篇 石油与天然气工程
- 56 篇 土木工程
1,193 篇 理学
- 549 篇 数学
- 441 篇 物理学
- 224 篇 生物学
- 191 篇 系统科学
- 172 篇 统计学（可授理学、...
- 88 篇 化学
550 篇 管理学
- 440 篇 管理科学与工程(可...
- 141 篇 图书情报与档案管...
- 119 篇 工商管理
357 篇 医学
- 321 篇 临床医学
- 133 篇 基础医学(可授医学...
- 83 篇 药学(可授医学、理...
51 篇 法学
40 篇 经济学
22 篇 农学
14 篇 教育学
10 篇 军事学
4 篇 文学
4 篇 艺术学

主题

833 篇 signal processin...
576 篇 signal processin...
569 篇 robot sensing sy...
330 篇 intelligent robo...
320 篇 control systems
276 篇 mobile robots
250 篇 cameras
232 篇 real-time system...
208 篇 sensor systems
203 篇 neural networks
198 篇 estimation
196 篇 image processing
194 篇 feature extracti...
192 篇 modulation
176 篇 ofdm
171 篇 humans
168 篇 robots
167 篇 field programmab...
152 篇 robot vision sys...
150 篇 clocks

机构

32 篇 university of ch...
18 篇 institutes for r...
14 篇 ieee
13 篇 robotics institu...
13 篇 school of electr...
10 篇 department of in...
9 篇 university of an...
9 篇 university of el...
9 篇 shenyang institu...
9 篇 shanghai enginee...
9 篇 school of intell...
9 篇 school of comput...
8 篇 university of sc...
8 篇 key laboratory o...
8 篇 school of inform...
8 篇 state key labora...
7 篇 singapore univer...
7 篇 guangdong provin...
7 篇 university paris...
7 篇 chitkara centre ...

作者

12 篇 g. hirzinger
12 篇 changshui zhang
10 篇 nakadai kazuhiro
10 篇 joonki paik
9 篇 wang wei
9 篇 hanebeck uwe d.
9 篇 qiang huang
9 篇 toshio fukuda
9 篇 kazuhiro nakadai
9 篇 uwe d. hanebeck
9 篇 luo bin
9 篇 fan zhun
8 篇 yang bin
8 篇 janne honkakorpi
8 篇 kurosh madani
8 篇 ming li
8 篇 joaquim filipe
8 篇 anon
8 篇 minje kim
8 篇 juho vihonen

语言

6,561 篇 英文
603 篇 其他
39 篇 中文
1 篇 土耳其文

检索条件"任意字段=IEEE International Conference on Robotics, Intelligent Systems and Signal Processing"

共 7200 条记录，以下是581-590 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：

Learnable Flow Model Conditioned on Graph Representation Memory for Anomaly Detection 48

Learnable Flow Model Conditioned on Graph Representation Mem...

引用

48th ieee international conference on Acoustics, Speech and signal processing, ICASSP 2023

作者： Zhu, Ziyu Liu, Wenlei Deng, Zhidong Tsinghua University Department of Computer Science and Technology Beijing100084 China State Key Laboratory of Intelligent Technology and Systems China

ISBN: (纸本)9781728163277

Anomaly detection could be applied in a wide range of fields from industrial scene to medical imaging analysis. Although invertible flow models are developed to accomplish unsupervised anomaly detection, they are usually hard to train and have limited capabilities of accurately modeling the distribution of normal samples. To address this problem, we propose a novel enhanced flow model conditioned on graph representation memory (FlowGRM) for visual surface defect detection. In our FlowGRM, a graph neural network is trained to query graph embedding features from memory bank and incorporate them into a learnable flow model as conditional information. Such memorized conditional information, together with the invertible flow model, is jointly optimized to give rise to a probability density score. Experimental results obtained on the industrial visual anomaly detection datasets including MVTec and MTD show that the proposed model has state-of-the-art performance, which could even reach up to 99.6% and 99.2% AUROC scores on the above two bench-marks, respectively. Meanwhile, it requires fewer parameters and saves over 80% training time compared to existing flow models. © 2023 ieee.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

On Some Applications of the Orthogonal systems of Functions 3

On Some Applications of the Orthogonal Systems of Functions

引用

3rd ieee international conference on System Analysis and intelligent Computing, SAIC 2022

作者： Voloshyna, Tetiana Karakhanov, Denys Voloshyn, Mychaylo Lesya Ukrainka Volyn National University Faculty of Information Technology and Mathematics Lutsk Ukraine Lesya Ukrainka Volyn National University Faculty of Geography Lutsk Ukraine

ISBN: (数字)9798350396744

ISBN: (纸本)9798350396744

When developing automatic signal processing systems, it is important to determine a set of parameters in order to optimize them and increase their efficiency. In the paper the modified Fourier transformation methods for digital signal processing have been used. A new approach to the construction of special polynomials has been offered by means of which the summing function is realized. The matrix methods of summation with rectangular matrices and their efficiency in comparison with the methods based on the use of triangular matrices have been investigated. Necessary and sufficient conditions for uniform convergence of the constructed trigonometric series for any continuous function on a segment in terms of a system of numerical coefficients have been established. The Lebesgue convergence of the constructed series for any summable periodic function has been studied. The obtained results can be used in digital signal processing systems based on the use of Fourier transformations. © 2022 ieee.

关键词： Digital signal processing

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Segmentation from MRI Scans using 2D U-Net and other U-Net-Based Models

Brain Tumor Segmentation from MRI Scans using 2D U-Net and o...

引用

2023 international conference on Artificial Intelligence robotics, signal and Image processing, AIRoSIP 2023

作者： Magboo, Ma. Sheila A. Coronel, Andrei D. University of the Philippines Manila College of Arts and Sciences Department of Physical Sciences and Mathematics Manila Philippines Ateneo de Manila University School of Science and Engineering Department of Information Systems and Computer Science Quezon City Philippines

ISBN: (纸本)9798350327472

In this study four deep learning-based image segmentation models were constructed to segment brain tumors from FLAIR and T1ce MRI modalities. The four models were 2D U-Net, and the three 2D U-Net based variants which are the U-Net VGG19, U-Net ResNet50, and U-Net InceptionV3. Both qualitative and quantitative methods of assessment were used to evaluate model performance. Qualitative methods include visual presentation of ground truth vis-à-vis the predicted segmentation in order to see how similar is the prediction vis-à-vis the ground truth. As for the quantitative metrics Dice coefficients of the whole tumor, necrotic/core, edema, and enhancing tumors were obtained along with the Mean IOU, Precision, Sensitivity, and Specificity. Generally, all models achieved good performance however in this study 2D U-Net emerged as the best model for getting the highest scores in almost all metrics. Clinical decision-support tools like this can provide timely and accurate information to help radiologists come up with more informed decisions associated with assessment of the tumor's aggressiveness, potential interventions or therapies, and in monitoring of treatment response over time. © 2023 ieee.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

intelligent Malware Detection Using Sentence Transformer and Hybrid Deep Learning Architecture 10

Intelligent Malware Detection Using Sentence Transformer and...

引用

10th international conference on signal processing and Communication, ICSC 2025

作者： Kumar, Sanjeev Sapru, Yudhishthira Sapru, Sugandha Janet, B. Centre for Development of Advanced Computing Cyber Security Technology Division Mohali India Indian Computer Emergency Response Team CERT-In Delhi India Pggc Panjab University Department of Mathematics Chandigarh India National Institute of Technology Department of Computer Application Tiruchirappalli India

ISBN: (纸本)9798331511890

The complex evasion techniques adopted by the malware creator make signature-based malware detection approaches unable to detect unknown malware attacks. This study proposes a new malware detection and classification approach with significantly less dependence on manual feature engineering. The bidirectional encoder representations from transformers (BERT) are used to model the opcode sequences of the malware file as the semantic behavior of malware. After that, the vectorized feature vector is fed to the hybrid one-dimensional convolution neural network (1D-CNN) and the gated recurrent unit (GRU) model for feature reduction and normalization before training a Softmax classifier. A hybrid learning architecture is designed with a custom 1D-CNN and a GRU model to take the strengths of both types of networks. The proposed scheme is evaluated using the Microsoft BIG dataset, consisting of 1625 assembly files belonging to 9 distinct malware families. The proposed method produced 95.77% accuracy even with the smaller dataset, which we believe will boost performance by adding a more diverse dataset. It uses the next-generation BERT language model, which gives a promising future area for malware defenders. This research presents malware detection without much reliance on manual feature engineering or signature-based detection, making it suitable for detecting unknown malware attacks. © 2025 ieee.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Untargeted Backdoor Attack Against Object Detection 48

Untargeted Backdoor Attack Against Object Detection

引用

48th ieee international conference on Acoustics, Speech and signal processing, ICASSP 2023

作者： Luo, Chengxiao Li, Yiming Jiang, Yong Xia, Shu-Tao Tsinghua University Tsinghua Shenzhen International Graduate School China Research Center of Artificial Intelligence Peng Cheng Laboratory China

ISBN: (纸本)9781728163277

Recent studies revealed that deep neural networks (DNNs) are exposed to backdoor threats when training with third-party resources (such as training samples or backbones). The back-doored model has promising performance in predicting benign samples, whereas its predictions can be maliciously manipulated by adversaries based on activating its backdoors with pre-defined trigger patterns. Currently, most of the existing backdoor attacks were conducted on the image classification under the targeted manner. In this paper, we reveal that these threats could also happen in object detection, posing threatening risks to many mission-critical applications (e.g., pedestrian detection and intelligent surveillance systems). Specifically, we design a simple yet effective poison-only backdoor attack in an untargeted manner, based on task characteristics. We show that, once the backdoor is embedded into the target model by our attack, it can trick the model to lose detection of any object stamped with our trigger patterns. We conduct extensive experiments on the benchmark dataset, showing its effectiveness in both digital and physical-world settings and its resistance to potential defenses. © 2023 ieee.

关键词： AI Security Backdoor Attack Object Detection Physical Attack Trustworthy ML

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of Radio Frequency Sensing Technology in Obstacle Detection for Driverless Vehicles 6

Research on the Application of Radio Frequency Sensing Techn...

引用

6th ieee international conference on Automation, Electronics and Electrical Engineering, AUTEEE 2023

作者： Zhang, Jialiang Cai, Zhaobo Wuhan University of Technology School of Information Engineering Wuhan China

ISBN: (纸本)9798350305623

In the swiftly evolving realm of intelligent Transportation systems, autonomous driving technology has emerged as a focal point of research, with the precise identification and detection of obstacles being a pivotal technology. Although significant strides have been made with traditional obstacle detection methods such as visual systems, radar, and ultrasonic sensors, challenges persist in complex environments. This study delves into the feasibility of applying Radio Frequency (RF) sensing technology, widely employed in indoor positioning and the Internet of Things, to obstacle detection in autonomous vehicles. Our research indicates that RF sensing technology markedly enhances detection rates and accuracy. The paper comprehensively analyzes the application of RF sensing in obstacle detection, proposing an efficient obstacle detection system based on this technology. Results suggest that this system offers more reliable and safer obstacle detection under varying environmental conditions. © 2023 ieee.

关键词： Autonomous Vehicles intelligent Transportation systems Obstacle Detection Radio Frequency Sensing Technology signal processing

来源：评论

学校读者我要写书评

暂无评论

A Smart Model to Manage Traffic Using Infrared Sensors and Bell Detection System: A Computer Controlled Traffic System 2

A Smart Model to Manage Traffic Using Infrared Sensors and B...

引用

2nd ieee international conference on Communication, Security and Artificial Intelligence, ICCSAI 2023

作者： Saxena, Ashendra Kumar Adlin, Jebakumari S. College of Computing Science and Information Technology Teerthanker Mahaveer University Uttar Pradesh Moradabad India University Karnataka Bangalore India

ISBN: (纸本)9798350369960

The escalating challenge of traffic congestion in urban areas necessitates innovative solutions at the intersection of computer science and artificial intelligence. The main problem is in the outdated nature of conventional traffic signal systems, which function based on predetermined time intervals and fail to appropriately adjust to the ever-changing patterns of urban traffic. This study presents a sophisticated traffic management system that utilizes machine learning and data mining concepts to optimize real-time traffic signal regulation. The suggested system utilizes infrared sensors to constantly monitor the level of traffic congestion at crossings. The data is transmitted to an advanced microcontroller, which utilizes machine learning techniques to forecast traffic patterns and subsequently modify the timing of traffic signals. This approach enables a more seamless and adaptable control of traffic flows, resulting in a substantial decrease in congestion and enhancement of overall traffic efficiency compared to traditional systems. By incorporating computer vision techniques, the system's ability to detect and evaluate several traffic parameters, such as vehicle count, speed, and categorization, is improved. The data is essential for the machine learning models to make well-informed recommendations regarding the durations of traffic lights. Furthermore, the system integrates robotics components to physically manipulate and operate traffic light hardware, guaranteeing smooth functioning and immediate response to the computational decisions made by the microcontroller. This research not only addresses the immediate practical concerns of urban traffic management but also contributes to the broader field of AI and robotics in realworld applications. The synergy of data mining, machine learning, and computer vision within a robust traffic management system exemplifies the transformative potential of AI technologies in urban infrastructure management. © 2023 ieee.

关键词： Audio signal Detection Machine Learning Algorithms Real-Time Data processing Traffic Optimization Techniques

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of Image processing Technology in Vehicle License Plate Recognition 8

Research on the Application of Image Processing Technology i...

引用

8th international conference on intelligent Computing and signal processing, ICSP 2023

作者： Qiu, Caihua Ding, Feng Guangdong University of Science and Technology 99 Xihu Road Nancheng District Guangdong Dongguan523083 China Guangzhou Xinhua University 248 Yanjianxi Road Machong Town Guangdong Dongguan523133 China

ISBN: (纸本)9798350302455

With the development of artificial intelligence, image recognition technology has been applied to various aspects of life, such as license plate recognition. License plate recognition has many application scenarios in real life, but due to various interferences in daily life, the accuracy of license plate recognition is often affected. In order to improve the accuracy and efficiency of license plate recognition, we need to integrate image processing technology into license plate image recognition pre-processing technology, and use Gaussian filter, grayscale, binarization to complete license plate image pre-processing, so as to reduce the interference of objective conditions on license plate recognition efficiency. Through experiments, we know that using image recognition technology can reduce the computational power consumption of license plate recognition systems, improve image recognition efficiency and accuracy. © 2023 ieee.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Network Traffic Co-Movement Assessment via Oriented Basis signal processing and Ensemble Decision Trees 27

Network Traffic Co-Movement Assessment via Oriented Basis Si...

引用

27th ieee international conference on intelligent Transportation systems, ITSC 2024

作者： Mohebbi, Mohammad Reza Hassan Zada, Mohammad Javad Rostami-Shahrbabaki, Majid Doller, Mario Yamnenko, Iuliia University of Applied Sciences Josef Ressel Center Vision2Move Project Tirol Kufstein Austria University of Passau Department of Computer Science Germany Technical University of Munich Traffic Engineering and Control Germany National Technical University of Ukraine Igor Sikorsky Kyiv Polytechnic Institute Department of Electronic Devices and Systems Kyiv Ukraine

ISBN: (纸本)9798331505929

Accurate short-term network-wide traffic prediction is essential to guarantee high service quality in urban traffic control systems. Nevertheless, traffic state time series represent network-scale spatiotemporal co-movement patterns and location-specific features. Therefore, hybrid statistical machine learning (ml) algorithms could be utilized to accommodate the aforementioned characteristics. In this paper, a hybrid random forest (rf) and extreme gradient boosting tree (XGBoost) model is introduced for network-wide traffic prediction. Moreover, a multi-noise oriented basis wavelet transform (OBT) filter is employed to pre-process the original time series, and improve the predictive accuracy. The RF model captures the traffic co-movements and the XGBoost extracts the local information. Comparative analysis of the hybrid algorithm and deep learning-based benchmarks indicate better performance of the proposed methodology in hourly traffic state prediction of 30 loop detectors, located in the paris city center. Hence, the hybrid decision-tree-based mechanism is a useful framework for real-time network traffic forecasting offering fewer trainable (hyper-)parameters, and thus, lower computational cost. © 2024 ieee.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

intelligent Leakage Inspection Method of Magnetic Mill Workshop based on Lightweight Yolov5 3

Intelligent Leakage Inspection Method of Magnetic Mill Works...

引用

3rd international conference on Image processing, Computer Vision and Machine Learning, ICICML 2024

作者： Yu, Shimao Song, Chunhe Sun, Yong Gao, Pengpei Institute of Automation Chinese Academy of Sciences Key Laboratory of Networked Control Systems Shenyang Shenyang China Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350355413

In the process of mining company beneficiation, large rotating equipment, pipelines and electrical equipment have many complex inspection areas and diverse inspection contents. The lack of intelligent solutions to the problem of pipeline leakage will cause serious consequences such as equipment shutdown if it is not found in time. This paper proposes a lightweight yolov5 intelligent leakage inspection method for the magnetic mill workshop. The inspection robot is used to continuously collect images of possible leakage points and transmit them to the background server. The improved yolov5 algorithm simplifies the model structure and realizes rapid and accurate identification of leakage targets with limited computing resources. The computational efficiency is increased by 44.98% with almost no loss of model accuracy. The mAP-0.5 of identifying large targets at leakage points reaches 97.96%. © 2024 ieee.

关键词： inspection robot leakage inspection light-weight yolov5 object detection

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 << < 55 56 57 58 59 60 61 62 63 64 > >>

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：