检索结果-内蒙古大学图书馆

International Conference on Computer and Communications (ICCC)

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

ISBN: (纸本)9781665409513

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.

关键词： Integrated optics Graphical models Channel capacity Dynamic range Performance analysis Optical beams MIMO communication

来源：评论

学校读者我要写书评

暂无评论

Superhydrophobic Pet-Cu-Ni@Mwcnt with Electropositive Layer to Enhance the Electrical Properties of Teng for Human Wearable Sensors

SSRN

引用

SSRN 2024年

作者： Yu, Shuguo Li, Peng Ding, Hanqin Shi, Fei Li, Xingang Xinjiang Key Laboratory of Solid State Physics and Devices Xinjiang University Urumqi830046 China School of Physical Science and Technology Xinjiang University Urumqi830046 China School of Computer Science and Technology Xinjiang University Urumqi830046 China Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi830046 China

Flexible triboelectric nanogenerator (TENG) are ideal for sustainable and wearable electronics applications due to their excellent performance and non-toxicity. In this study, multiwalled carbon nanotubes (MWCNT) loaded plain anti-radiation shielding cloth (PET-Cu-Ni) electropositive layer (PM) is synthesized, and then assembled with PDMS to make a superhydrophobicity and flexible PM-TENG. The alternating fabric-like PET in PET-Cu-Ni increases the contact area at the tribo-electrode interface, and the bimetallic atomic Cu-Ni layer increases the electrical conductivity and electron transfer capability of triboelectric material. MWCNT surface itself has a positive charge, which promotes the generation of triboelectric charges, and the deposition of the MWCNT layer also increases the contact area of interface. MWCNT with p-type conductive forms a metal-semiconductor junction with the Cu-Ni layer, and MWCNT layer acts as a hole-transporting layer that affects triboelectric charge separation to reduces triboelectric charge loss, which greatly improves the output current of TENG. The superhydrophobic PM prevents the loss of electrostatic charge on TENG surface to the extent that it promotes stable performance output. At 5 Hz operating frequency, the short-circuit current of PM-TENG is boosted to 13.7 μA, and the open-circuit voltage and power reach 231 V and 2.8 mW, respectively. Integration of PM-TENG as a power source with the SnS2 humidity sensor constitutes TENG-driven sensor, which realizes relative humidity detection with high sensitivity and fast response recovery. In addition, a remote human-machine interface (HMI) system is constructed by integrating PM-TENG, circuit module, and APP, which realizes real-time monitoring of finger curvature and promotes the development of biomedicine. © 2024, The Authors. All rights reserved.

关键词： Multiwalled carbon nanotubes (MWCN)

来源：评论

学校读者我要写书评

暂无评论

Speech Topic Classification Based on Pre-trained and Graph Networks

Speech Topic Classification Based on Pre-trained and Graph N...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Fangjing Niu Tengfei Cao Ying Hu Hao Huang Liang He School of Information Science and Engineering Xinjiang University Urumqi China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China Department of Electronic Engineering Tsinghua University Beijing China Beijing National Research Center for Information Science and Technology Beijing China

Speech Topic Classification (STC) automatically classifies audio clips into predefined categories, which is widely used in short video, personalized recommendation and other fields. At present, the common system is composed of two parts: first, the speech is converted into text by automatic speech recognition (ASR), and then the text topic is classified by natural language processing (NLP). Most of them have problems such as error propagation and lack of global structure. So in this paper, we propose a new end-to-end framework based on a pre-trained model and graph network. The pre-trained model is used to extract the semantic features with sequential structure instead of acoustic features, and the combination with the global features of conversational context constructed by graph network has achieved good results on the Fisher dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploration on the mixed practice teaching methods of team experience under the training of new engineering talents

Exploration on the mixed practice teaching methods of team e...

引用

Information Science and Education (ICISE-IE), International Conference on

作者： Shi Fei Jia Zhen Hong Zhou Yan Yun Chen Juan School of information science and engineering Key Laboratory of Signal Detection and Processing Xinjiang University No.666 Shengli Road Tianshan District Urumqi Xinjiang School of information science and engineering Xinjiang University No.666 Shengli Road Tianshan District Urumqi Xinjiang

Facing the requirements of the first-class discipline of electronic information engineering and the construction of new engineering courses, this paper analyzes the characteristics of practice teaching under the background of new engineering, puts forward a team experience hybrid practical teaching method for new engineering talents training, expounds the implementation process of this method in detail, and applies the method to the practice project design course of electronic information engineering experimental class. The results show that this method can improve students' self-learning ability, knowledge application ability, problem-solving ability, and engineering practice ability.

关键词： Training Knowledge engineering Information science Education Problem-solving Engineering education System analysis and design

来源：评论

学校读者我要写书评

暂无评论

LE-CAM++: A Lighter and More Efficient CAM++ for Speaker Verification

LE-CAM++: A Lighter and More Efficient CAM++ for Speaker Ver...

引用

International Symposium on Chinese Spoken Language processing

作者： Shuanghong Liu Zhida Song Zhihua Fang Liang He School of Computer Science and Technology Xinjiang University Urumqi Xinjiang Key Laboratory of Signal Detection and Processing Urumqi School of Intelligence Science and Technology Xinjiang University Urumqi Department of Electronic Engineering and Beijing National Research Center for Information Science and Technology Tsinghua University Beijing

ISBN: (数字)9798331516826

ISBN: (纸本)9798331516833

Due to its superior performance and fewer parameters, CAM++ has become the state-of-the-art model for speaker verification tasks. This model uses 2D convolutional blocks to extract front-end features, which are then fed into a densely connected time-delay neural network backbone to extract deep features. However, the simple stacking of 2D convolutions may lead to the generation of a significant amount of redundant features, which is detrimental to efficient feature extraction. Furthermore, although CAM++ already has a relatively small number of parameters, there is still room for further optimization. To address these issues, this paper first employs depthwise separable convolutions to replace the dilated convolutions in the back-end network of CAM++, making the model more lightweight. Next, we introduce spatial and channel reconstruction convolution (SCConv) in the ResBlock module of CAM++ to reduce redundant features and optimize the feature extraction process. Finally, after SCConv, we apply squeeze and excitation attention mechanism to model the interdependencies between channels and recalibrate each channel, further enhancing the model's representational capacity. We name the resulting model LE-CAM++. Our proposed model achieves an EER of 0.686 and a minDCF of 0.084 on the VoxCeleb1–O dataset. Compared to the baseline model CAM ++, the EER is reduced by 11%, and the minDCF is reduced by 28%. Additionally, the model parameters are reduced by 8%.

关键词： Attention mechanisms Stacking Neural networks Feature extraction Optimization

来源：评论

学校读者我要写书评

暂无评论

Simplified Skip-Connected UNet for Robust Speaker Verification Under Noisy Environments

Simplified Skip-Connected UNet for Robust Speaker Verificati...

引用

International Symposium on Chinese Spoken Language processing

作者： Zonghui Wang Zhihua Fang Zhida Song Liang He School of Computer Science and Technology Xinjiang University Urumqi Xinjiang Key Laboratory of Signal Detection and Processing Urumqi School of Intelligence Science and Technology Xinjiang University Urumqi Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing

ISBN: (数字)9798331516826

ISBN: (纸本)9798331516833

In recent years, deep neural network based methods for speaker verification have made remarkable progress in clean environments. However, background noise significantly reduces the accuracy and reliability of speaker verification systems by masking or changing the voice characteristics of the speaker. In this paper, we propose a cascaded framework optimized with multiobjective loss to mitigate the interference of different levels and types of noise on the speaker verification task. The proposed architecture consists of two components: a speech enhancement module based on improved 2D-UNet, which reduces the structural limitations of directly using classical UNet for noise reduction, and a back-end speaker embedding extraction module. We carry our experiments on the VoxCeleb1 and VOiCES datasets, as well as in the presence of out-of-domain noise conditions. The evaluations have demonstrated this method shows great potential for speaker verification in noisy environments.

关键词： Training Semantics Noise reduction Interference Speech enhancement Complexity theory Noise measurement Reliability Optimization signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

STransFuse: Fusing swin transformer and convolutional neural network for remote sensing image semantic segmentation

TechRxiv

引用

TechRxiv 2021年

作者： Gao, Liang Liu, Hui Yang, Minhang Chen, Long Wan, Yaling Qian, Yurong Xiao, Zhengqing College of Software Xinjiang University Urumqi830008 China Key Laboratory of signal detection and processing in Xinjiang Uygur Autonomous Region Urumqi830014 China the Key Laboratory of Software Engineering Urumqi830008 China College of Information Science and Engineering Xinjiang University Urumqi830014 China College of Mathematics and Systems Science Xinjiang University Urumqi830014 China

The convolutional neural network (CNN) bolstered the application study of remote sensing images. However, the fixed size of the receptive field limits CNN’s ability in semantic modelling. Although the Transformer model based on self-attention may model global semantic information, it remains a challenge to work effectively in the remote sensing field with limited data. Leveraging the benefits of both Transformer and CNN, a new model is proposed in this article as a semantic segmentation method for remote sensing images which is constructed by fusing Swin Transformer and CNN and is thus named as STransFuse model. On the one hand, the STransFuse model makes use of the capability of the transformer network to model global semantic information in remote sensing images. On the other hand, it utilized the capability of the CNN with pre-training weights to solve the problem of low performance of the Transformer network when the amount of remote sensing image data is small and to provide the contextual location information of the image. An Adaptive Fusion Module (AFM) is created to adaptively fuse the feature maps produced by the Transformer network and CNN to improve the model’s feature representation capacity. The OA (Overall Accuracy) of the STransFuse model is 1.36% higher than the baseline on the Vaihingen dataset, and 1.27% higher than baseline on the Potsdam dataset. When compared with other state-of-the-art models, the STransFuse model performed competitively. © 2021, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Rapid diagnosis of osteoarthritis using serum Raman spectroscopy based on MFCC transformation combined with MCNN 4

Rapid diagnosis of osteoarthritis using serum Raman spectros...

引用

4th International Conference on Optics and Image processing, ICOIP 2024

作者： Xu, Hongze Chen, Chen Tian, Xuecong He, Liang Zuo, Enguang Chen, Xiaomei Wu, Lijun Chen, Cheng Lv, Xiaoyi College of Software Xinjiang University Urumqi830046 China College of Information Science and Engineering Xinjiang University Urumqi830046 China Key Laboratory of signal detection and processing Xinjiang University Urumqi830046 China Xinjiang Cloud Computing Application Laboratory Karamay834099 China Department of Rheumatology and Immunology People's Hospital of Xinjiang Uygur Autonomous Region Urumqi830001 China Xinjiang Clinical Research Center for Rheumatoid Arthritis Urumqi830001 China Department of Electronic Engineering Tsinghua National Laboratory for Information Science and Technology Tsinghua University Beijing China School of Information Science and Engineering Xinjiang University Ürümqi China

ISBN: (纸本)9781510682481

Osteoarthritis (OA) is a common chronic degenerative disease worldwide. Currently, traditional diagnostic methods for OA have disadvantages such as high cost and long time consumption. For this reason, it is urgent to have a method that can diagnose osteoarthritis quickly and accurately. During this study, we suggest a multi-column convolutional neural networks (MCNN) model based on Mel-frequency cepstral coefficient (MFCC). We first compare the effectiveness of Partial Least Squares (PLS) and MFCC in preprocessing the data and comprehensively evaluate the performance of the model by five-fold cross-validation. To further improve the ability of recognizing spectral features, We utilize the Spectral Segmentation Method (SSM) to construct the MFCC feature sequences into 2D spectral feature maps and input them into the MCNN for classification. The final experimental results show that our proposed mfc - ssm - mcnn model has a high classification efficiency in diagnosing osteoarthritis with an accuracy of 95.0%. © 2024 SPIE.

关键词： Raman spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Qualitative Analysis of Vibrational Spectroscopic Based on Ensemble Convolutional Neural Networks

SSRN

引用

SSRN 2022年

作者： Sun, Penghui Wang, Jiajia Liu, Pei Dong, Zhilin School of Information Science and Engineering Xinjiang University Urumqi China The Key Laboratory of Signal Detection and Processing Xinjiang Uygur Autonomous Region Xinjiang University China Post-Doctoral Workstation Xinjiang Xinjiang Uygur Autonomous Region Product Quality Supervision and Inspection Institute Urumqi China

Vibrational spectroscopy qualitative analysis technology has shown excellent potential in pharmaceuticals, food science, and other fields. In this paper, we proposed an ensemble convolutional neural network more suitable for spectral data feature extraction. Firstly, this paper presents the Alexnet-BN model;the model fully utilizes the feature to enhance the feature representation ability by removing the pooling layer of the Alexnet;we utilize BN layers multiple times to improve the training speed of the model and reduce the number of filters per convolutional layer of the model to weaken the redundant information. Secondly, to further improve the recognition accuracy of spectral data, 5 deep convolutional neural networks (DCNNs) models were built by adjusting the parameters of AlexnetBN, and the DCNN-EL model was constructed utilizing these 5 DCNNs using an ensemble machine learning approach. Finally, four publicly available datasets (Tablet푁퐼푅, Meats퐹 푇 퐼푅, Fruits퐹 푇 퐼푅, and Tablet푅푎푚푎푛) were used to validate the accuracy and generalization of the model. The results show that the DCNN-EL model achieves 100%, 100%, 99.32%, and 91.67% accuracy on the four datasets, which verifies that the method has high analytical accuracy and generalization. Therefore, the ensemble convolutional neural network has crucial practical value in the qualitative detection of vibration spectra. © 2022, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Tablet Identification Using Ensemble Convolutional Neural Networks and Vibrational Spectroscopy

SSRN

引用

SSRN 2023年

作者： Sun, Penghui Wang, Jiajia Liu, Pei Dong, Zhilin School of Computer Science and Technology Xinjiang University Urumqi China The Key Laboratory of Signal Detection and Processing Xinjiang Uygur Autonomous Region Xinjiang University China Post-doctoral workstation of Xinjiang Xinjiang Uygur Autonomous Region Product Quality Supervision and Inspection Institute Urumqi China

Vibrational spectroscopy reflects molecular vibrational data, facilitating tablet identification. This paper introduces the DCNN-EL model, which integrates vibrational spectroscopy to accurately discern tablet categories. The DCNN-EL model is built upon the Alexnet framework, starting with the proposal of the Alexnet-BN model, enhancing model training speed and robustness by iteratively applying the BN layer in lieu of the pooling layer. Subsequently, by adjusting the parameters of Alexnet-BN, five deep convolutional neural network (DCNN) models are established and combined using an integrated machine learning approach to form the DCNN-EL model. Evaluating the DCNN-EL model with two public datasets (Tablets_Nir and Tablets_Raman) demonstrates its 100% and 91.67% accuracy, affirming its efficacy and generalizability in tablet identification. Consequently, the amalgamation of convolutional neural networks and vibrational spectroscopy bears significant practical relevance in the qualitative detection of tablets. © 2023, The Authors. All rights reserved.

关键词： Convolution

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：