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

32 篇 会议
29 篇 期刊文献

馆藏范围

61 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

43 篇 工学
- 21 篇 计算机科学与技术...
- 19 篇 软件工程
- 15 篇 信息与通信工程
- 7 篇 化学工程与技术
- 7 篇 生物工程
- 5 篇 电气工程
- 4 篇 机械工程
- 4 篇 电子科学与技术（可...
- 4 篇 控制科学与工程
- 3 篇 材料科学与工程（可...
- 3 篇 生物医学工程（可授...
- 3 篇 安全科学与工程
- 1 篇 力学（可授工学、理...
- 1 篇 光学工程
- 1 篇 仪器科学与技术
- 1 篇 冶金工程
- 1 篇 水利工程
28 篇 理学
- 11 篇 生物学
- 9 篇 物理学
- 8 篇 数学
- 7 篇 化学
- 5 篇 统计学（可授理学、...
- 2 篇 大气科学
- 1 篇 地质学
- 1 篇 系统科学
13 篇 管理学
- 9 篇 图书情报与档案管...
- 4 篇 管理科学与工程(可...
6 篇 医学
- 5 篇 基础医学(可授医学...
- 3 篇 公共卫生与预防医...
- 2 篇 临床医学
1 篇 农学

主题

3 篇 integrated optic...
3 篇 convolution
3 篇 accuracy
3 篇 immunosensor
2 篇 image enhancemen...
2 篇 visible light co...
2 篇 wireless communi...
2 篇 insects
2 篇 speech processin...
2 篇 smart contract
2 篇 yolo
2 篇 tarim basin
2 篇 signal processin...
2 篇 change detection
2 篇 data models
2 篇 smart agricultur...
1 篇 image fusion
1 篇 signal amplifica...
1 篇 covid-19
1 篇 obstacle detecti...

机构

11 篇 key laboratory o...
10 篇 school of comput...
7 篇 china mobile res...
5 篇 college of softw...
5 篇 school of inform...
4 篇 key laboratory o...
4 篇 school of inform...
3 篇 the key laborato...
3 篇 key laboratory o...
3 篇 ludong universit...
3 篇 key laboratory o...
3 篇 college of infor...
2 篇 college of compu...
2 篇 xinjiang uygur a...
2 篇 key laboratory o...
2 篇 key laboratory o...
2 篇 xinjiang uygur a...
2 篇 tsinghua univers...
2 篇 key laboratory o...
2 篇 xinjiang univers...

作者

10 篇 jia zhenhong
8 篇 wang jiajia
6 篇 zhou gang
6 篇 chenglin hong
5 篇 chaoyun ma
4 篇 huang xiaohui
4 篇 shi fei
4 篇 ding jupeng
4 篇 xiuwen qiao
4 篇 huang zhihua
4 篇 wang lili
4 篇 wenjun li
4 篇 zhenhong jia
4 篇 qian yurong
3 篇 fuyuan wei
3 篇 yiju song
3 篇 hong chenglin
3 篇 chih-lin i.
3 篇 yuanyuan liao
3 篇 jupeng ding

语言

60 篇 英文
1 篇 德文
1 篇 法文
1 篇 意大利文
1 篇 中文

检索条件"机构=Key Laboratory of Signal Detection and Processing in Xinjiang Uygur Autonomous Region"

共 61 条记录，以下是21-30 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：

Low-Resource Speech keyword Search Based on Residual Neural Network 16th

Low-Resource Speech Keyword Search Based on Residual Neural ...

引用

16th Chinese Conference on Biometric Recognition, CCBR 2022

作者： Wang, Dafei Huang, Zhihua Li, Hui Liu, Wenchen School of Information Science and Engineering Xinjiang University Urumqi830017 China Key Laboratory of Signal Detection and Processing in Xinjiang Uygur Autonomous Region Xinjiang University Urumqi830017 China

ISBN: (纸本)9783031202322

Low-resource speech keyword search is usually based on DTW template matching. However, this method has low precision and is sensitive to speaker or recording environment changes. This paper proposes a low-resource speech keyword search method based on image recognition. Bottleneck features are extract through a pre-trained model based on multi-language to generate similarity matrix images. ResNet is used to classify similarity matrix images. According to the image classification result, it is determined whether the speech keyword appears. This model does not require prior language knowledge and abundant corpus resources, so it is suitable for low-resource speech keyword search. We validate the performance of the model on different datasets. On SWS 2013, the model recall, accuracy, and F1 increased by 20.83%, 17.59%, and 19.18%, respectively. On QUESST 2014, they increased by 24.44%, 24.96%, and 24.70%, respectively. Experimental results show that the propose method is effective. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Template matching

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Recommendation Algorithm with Co-embedded Item Attributes and Ratings 4

A Hybrid Recommendation Algorithm with Co-embedded Item Attr...

引用

4th International Conference on Applied Machine Learning, ICAML 2022

作者： Xin, Gaowei Qin, Jiwei Zheng, Jiong School of Information Science and Engineering Xinjiang University Urumqi830046 China Key Laboratory of Signal Detection and Processing Xinjiang Uygur Autonomous Region Xinjiang University Urumqi830046 China

ISBN: (纸本)9781665462655

In today's recommendation algorithm field, attribute feature information of users or items is usually introduced as auxiliary information to alleviate the sparsity problem, which can achieve good recommendation results to some extent. To make better use of the auxiliary information for data compression and dimensionality reduction, autoencoder models are usually employed. However, existing autoencoder-based models require the same input and output dimensions, resulting in data information loss and poor autoencoder scalability, which ultimately leads to low recommendation line performance. To cope with this problem, we propose a hybrid collaborative recommendation algorithm with co-embedded item attributes and ratings (HCR-item). By one-hot encoding the discrete item attribute features and then fusing the rating features with the item attribute features as the input of the autoencoder, the autoencoder completes the data compression and reconstructs the rating interaction prediction matrix. The algorithm proposed in this paper integrates item attribute features and rating features together, flexibly uses different feature information, extends the feature space, and solves the problem of low recommendation performance caused by sparsity. The algorithm has been extensively experimented on several real datasets and compared with other algorithms, and the results show that HCR-item has better recommendation performance. © 2022 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Unsupervised wide field-of-view video image change detection

Unsupervised wide field-of-view video image change detection

引用

2024 International Conference on Image processing and Artificial Intelligence, ICIPAl 2024

作者： Liu, Rui Jia, Zhenhong Huang, Xiaohui Wang, Jiajia Zhou, Gang Shi, Fei School of Computer Science and Technology Xinjiang University Urumqi830046 China Key Laboratory of Signal Detection and Processing Xinjiang Uygur Autonomous Region Xinjiang University Urumqi830046 China

ISBN: (纸本)9781510681514

Video surveillance requires simultaneous monitoring of multiple areas. Consequently, real-time automatic change detection of the monitored areas becomes very important. In the context of wide field-of-view conditions, the combination of a wide field-of-view, intricate environmental factors, and a substantial presence of random noise can lead to the degradation of visual fidelity and a diminished signal-to-noise ratio in the video images acquired through the image sensor. As a consequence, the task of detecting subtle changes becomes challenging for the surveillance system. To address the above problems, we have proposed a change detection method that leverages improved difference images and super fast and robust fuzzy c-means with constraints clustering. Initially, we employ an improved log-ratio operator and an improved mean-ratio operator to generate two distinct difference images. Subsequently, the wavelet fusion algorithm is applied to merge these two difference images, effectively integrating their distinctive features and producing a fused difference image with differentiability. Then, the new difference image is subjected to soft threshold primary classification and a cumulative distribution function normalization to obtain the difference image after primary classification. Finally, the super fast and robust fuzzy c-means with constraints clustering algorithm is employed for the ultimate classification, enabling the separation of changed and unchanged areas within the image. © 2024 SPIE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Coarse-to-fine change detection in low-illumination video sequences via classifier trained on ResNet18

Coarse-to-fine change detection in low-illumination video se...

引用

2024 International Conference on Image processing and Artificial Intelligence, ICIPAl 2024

作者： Lin, Jiajun Jia, Zhenhong School of Computer Science and Technology Xinjiang University Urumqi830046 China Key Laboratory of Signal Detection and Processing Xinjiang Uygur Autonomous Region Xinjiang University Urumqi830046 China

ISBN: (纸本)9781510681514

In low-illumination environments, the contrast between targets and the background sharply decreases, and imaging sensors introduce complex random noise while capturing more light, leading to severe distortion in the target features of visible light images. Under these conditions, target feature-based detection algorithms face significant challenges. In this paper, we propose a coarse-to-fine change detection algorithm that detects targets in low-illumination environments by focusing on the change features generated by the targets. First, a binary classifier based on ResNet18 is trained with a specially curated dataset of targets and noise. Second, this classifier is applied to identify potential change objects in test data, preserve targets, and extract corresponding bi-temporal local regions of interest. Third, novel difference feature extraction operators are employed to generate local difference images. Next, a Laplacian-of-Gaussian-based graph cut algorithm is used to perform binary segmentation, distinguishing foreground from background in the images. We validated the feasibility of this algorithm in three challenging night scenes. Compared with the current state-of-the-art unsupervised change detection algorithms, the proposed algorithm shows overall better detection performance. © 2024 SPIE.

关键词： Change detection

来源：评论

学校读者我要写书评

暂无评论

Tor encrypted traffic recognition and classification technology based on flow information graph and deep learning

Tor encrypted traffic recognition and classification technol...

引用

2024 International Conference on Image processing and Artificial Intelligence, ICIPAl 2024

作者： Zhang, Yu Jia, Zhenhong Huang, Xiaohui Wang, Jiajia Zhou, Gang Shi, Fei Lu, Changwu School of Computer Science and Technology Xinjiang University Urumqi830046 China Key Laboratory of Signal Detection and Processing Xinjiang University Xinjiang Uygur Autonomous Region Urumqi830046 China

ISBN: (纸本)9781510681514

Internet traffic analysis is the core approach to network management and security. In the rapidly changing environment of encrypted traffic, traditional plaintext-based analysis methods have become obsolete. Although there are currently some methods for analysing encrypted traffic, they overlook the inherent logic and hierarchy of different encrypted traffic analysis requirements and lack research into the essential characteristics of encrypted *** article proposes a framework FM-ENet based on Graph Neural Network and Deep learning for Tor encrypted traffic classification to meet the practical needs of network management and security monitoring.A Flow Information Graph has been designed on the basis of Graph Neural Network, which can effectively alleviate the problem of concept *** the area of deep neural networks, we have developed an end-to-end multi-level spatio-temporal feature fusion enhanced network module ST-FENet, which has the advantage of automatically learning the non-linear relationship between input and output data without the need for manual feature extraction,this structure can complement each other in classification performance and solve the problem of low classifier efficiency. We compared FM-ENet to current popular methods using the public ISCX-Tor dataset. FM-ENet can achieve higher performance while saving costs, with a 9% improvement in accuracy compared to FlowPrint and a 4.4%, 4.5% and 4.4% improvement in PR, RC and F1 indicators compared to TSCRNN. © 2024 SPIE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Heterogeneous Optical Beams based MIMO Visible Light Communication System 7

Performance Analysis of Heterogeneous Optical Beams based MI...

引用

7th International Conference on Computer and Communications, ICCC 2021

作者： Ding, Jupeng Chih-Lin, I. Wang, Lili Zhao, Kai Zheng, Jiong Xinjiang University Key Laboratory of Signal Detection and Processing In Xinjiang Uygur Autonomous Region School of Information Science and Engineering Uygur China China Mobile Research Institute Beijing China Ludong University School of Information and Electrical Engineering Yantai China

ISBN: (纸本)9781665409506

To a large extent, the multiple input multiple output (MIMO) visible light communication (VLC) is still restricted in homogeneous Lambertian research paradigm. In this work, the heterogeneous optical beams configuration is proposed for the MIMO VLC system. Specifically, two typical non-Lambertian optical beams i.e. LUXEON Rebel UB and LB patterns are introduced to heterogeneous MIMO beams configurations. In typical indoor scenario, the channel capacity of the proposed heterogeneous MIMO VLC system is evaluated and compared with the counterpart of the homogeneous Lambertian MIMO VLC system. Numerical results illustrate that the LUXEON Rebel UB based heterogeneous configuration could provide more than 9.7% average MIMO VLC capacity gain. Respectively, the capacity dynamic range is elevated to about 74.0-156.2 Mbps from the original about 75.9-116.2 Mbps of homogeneous configuration. © 2021 IEEE.

关键词： Visible light communication

来源：评论

学校读者我要写书评

暂无评论

keyword Spotting Based on Efficient Neural Architecture Search

Keyword Spotting Based on Efficient Neural Architecture Sear...

引用

Pattern Recognition and Machine Learning (PRML), IEEE International Conference on

作者： Wenchen Liu Zhihua Huang Dafei Wang Key Laboratory of Signal Detection and Processing in Xinjiang Uygur Autonomous Region Xinjiang University Urumchi China

In this paper, neural architecture search (NAS) technique is used to develop an efficient and low consumption keyword spotting model on Uyghur language dataset. The model obtained in this paper using NAS on the Google speech command dataset has advantages compared with other models. The model obtained by applying the ProxylessNAS technique to optimize the neural architecture search achieves more than 95% accuracy on the Uyghur dataset with less than 400 Kb memory *** factors affecting the model performance are also explored in this *** experimental results show that decreasing the model weights can significantly reduce the model memory, and the accuracy rate decreases slightly. Meanwhile, increasing the feature dimension of the input MFCC can improve the model accuracy, and the accuracy can reach 96.80% at 40 MFCC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MetricGAN+ Speech Enhancement Model Combining Multi-scale and Multi-resolution Feature Network and Joint Perception Loss

MetricGAN+ Speech Enhancement Model Combining Multi-scale an...

引用

Pattern Recognition and Machine Learning (PRML), IEEE International Conference on

作者： Chuangjian Guo Zhihua Huang Hui Li Jingyi Song Key Laboratory of Signal Detection and Processing in Xinjiang Uygur Autonomous Region Xinjiang University Urumchi China

Recently, generative adversarial networks have been widely used in speech enhancement. However, some existing speech enhancement methods only aim to optimize a single perceptual metric, which may cause other perceptual metrics to be suboptimal. In this paper, we propose a joint perceptual loss function to guide the training of speech enhancement models. In addition, we use a multi-scale and multi-resolution feature extraction network in the discriminator of MetriGAN+model, so that the model can make full use of high-level context information and low-level time-frequency features, so as to improve the prediction performance of the discriminator and guide the training of the generator better. The evaluation results on the VoiceBank-DEMAND dataset show that the proposed model can effectively improve speech quality and intelligibility, and can improve the PESQ score by 0.19 compared to the previous MetricGAN+.

关键词：

来源：评论

学校读者我要写书评

暂无评论

End-to-End Residual Stage Network for COVID-19 detection

End-to-End Residual Stage Network for COVID-19 Detection

引用

Pattern Recognition and Machine Learning (PRML), IEEE International Conference on

作者： Hongwei Chen Zhihua Huang Kexin Lu Hanzheng Liu Key Laboratory of Signal Detection and Processing in Xinjiang Uygur Autonomous Region Xinjiang University Urumchi China

Currently, the COVID-19 virus is in a low-level epidemic state but still spreading in society. To timely cut off the transmission chain, early screening for COVID-19 is crucial. However, adding extra network modules during training may lead to module stacking errors and increased complexity. In this paper, we propose an optimization method based on residual stage networks (ResStage) and polarized self-attention mechanism to improve the detection ability of the model. This method provides better paths for information propagation across different layers of the network and extraction more refined and high-quality features. Results show that the fusion model based on ResStage and polarized self-attention can improve the detection accuracy of COVID-19 without increasing excessive parameters, achieving an AUC score of 86.53%. Moreover, this paper also subdivides the training tasks, including COVID-19 positive patients, COVID-19 positive patients with coughing, healthy individuals with coughing, asthma patients with coughing, and healthy asymptomatic individuals. These different tasks help to evaluate the performance of model and provide more references for practical applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Visible Light Wireless Data Center Links with Distinct Beam Configurations 11

Visible Light Wireless Data Center Links with Distinct Beam ...

引用

11th International Conference on Electronics, Communications and Networks, CECNet 2021

作者： Ding, Jupeng Chih-Lin, I. Wang, Lili Key Laboratory of Signal Detection and Processing in Xinjiang Uygur Autonomous Region School of Information Science and Engineering Xinjiang University Urumqi China China Mobile Research Institute Beijing China School of Information and Electrical Engineering Ludong University Yantai China

ISBN: (纸本)9781643682402

Visible light communication (VLC) is being explored as one promising approach to enable wireless data centers (WDC). Up to now, the visible light wireless data center links are still limited to the conventional Lambertian beam paradigm. The potential coverage gain relevant to the optical beam space is waiting for sufficient investigation. For addressing this issue, in this paper, the dynamic optical beam based WDC coverage enhancement scheme is introduced, and for each transmitter, the best candidate asymmetrical optical beam is selected to load the data signal. Numerical evaluation shows that, compared with the conventional static beam configuration, up to 6.76 dB peak signal to noise ratio (SNR) gain and 4.46 dB average SNR gain could be provided by the proposed dynamic beam scheme. Moreover, this SNR dynamic range is reduced to 36.65 dB while the counterpart of the static non-Lambertian beam configuration is up to 44.78 dB. © 2022 The authors and IOS Press.

关键词： Visible light communication

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7页 << < 1 2 3 4 5 6 7 > >>

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：