检索结果-内蒙古大学图书馆

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

Adaptive Gaussian Regularization Constrained Sparse Subspace Clustering for Image Segmentation

Adaptive Gaussian Regularization Constrained Sparse Subspace...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Sensen Song Dayong Ren Zhenhong Jia Fei Shi School of Computer Science and Technology Xinjiang University Urumqi China Key Laboratory of Signal Detection and Processing Xinjiang Uygur Autonomous Region Urumqi China College of Mathematics and System Science Xinjiang University Urumqi China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China

Sparse Subspace Clustering (SSC) is integral to image processing, drawing from spectral clustering foundations. However, prevalent methods, relying on an l 1 -norm constraint, fail to capture nuanced inter-region correlations, affecting segmentation efficacy. To remedy this, we introduce an Adaptive Gaussian Regularization Constrained SSC for enhanced image segmentation. This method begins with superpixel preprocessing to enrich local information. Given the Gaussian nature of the SSC’s sparse coefficient matrix, a Gaussian probability density function is infused as a regularization term, reinforcing regional image ties and facilitating similarity matrix creation. Using spectral clustering, we then define superpixel clusters leading to the final segmentation. When tested against the BSDS500 and SBD datasets and other leading algorithms, our model showcases marked improvements in natural image segmentation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Speaker Recognition Based on Pre-Trained Model and Deep Clustering

Speaker Recognition Based on Pre-Trained Model and Deep Clus...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Liang He Zhida Song Shuanghong Liu Mengqi Niu Ying Hu Hao Huang School of Computer Science and Technology Xinjiang University Urumqi China School of Intelligence Science and Technology Xinjiang University Urumqi China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China Department of Electronic Engineering Tsinghua University Beijing China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

In this paper, we propose a novel loss by integrating a deep clustering (DC) loss at the frame-level and a speaker recognition loss at the segment-level into a single network without additional data requirements and exhaustive computation. The DC loss implicitly generates soft pseudo-phoneme labels for each frame-level feature, which facilitates extracting more discriminant speaker representation by suppressing phonetic content information. We study the DC loss not only on the acoustic feature, but also on the features extracted by the pre-trained models, such as wav2vec 2.0, HuBERT and WavLM. Experimental results on the VoxCeleb dataset shows that the overall system performance based on the pre-trained model features are better than the one on the acoustic feature. The proposed loss is significantly effective for systems on the acoustic feature and has a marginal improvement for systems on the pre-trained model feature.

关键词： Training Costs Computational modeling System performance Phonetics Multimedia databases Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Multi-View Speaker Embedding Learning for Enhanced Stability and Discriminability

Multi-View Speaker Embedding Learning for Enhanced Stability...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Liang He Zhihua Fang Zuoer Chen Minqiang Xu Ying Meng Penghao Wang School of Computer Science and Technology Xinjiang University Urumqi China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China Department of Electronic Engineering Tsinghua University Beijing China iFly Digital Technology Hefei China

Deep neural network models based on x-vector have become the most popular framework for speaker recognition, and the quality of speaker features (embeddings) is important for open-set tasks such as speaker verification and speaker diarization. Currently, the most popular loss function is based on margin penalty, however, it only considers enlarging the inter-class distance while neglecting to reduce the intra-class feature differences. Therefore, we propose a multi-view learning approach that divides the training process into two views from the speaker embedding level. The classification view focuses on distinguishing the discriminability of different speakers, while the clustering view focuses on shrinking the feature boundaries of the same speaker, making intra-class differences smaller. The combined effect of the two perspectives achieves large inter-class distance and small intra-class distances, resulting in the extraction of more discriminative and stable speaker embeddings. We test the performance of the method on both speaker verification and speaker diarization tasks, and the results demonstrate the effectiveness of our approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Asffuse: Infrared and Visible Image Fusion Model Based on Adaptive Selection Feature Maps

SSRN

引用

SSRN 2023年

作者： Liu, Kuizhuang Li, Min Zuo, Enguang Chen, Chen Chen, Cheng Wang, Bo Lv, Yi Xiao Wang, Yunling College of Software Xinjiang University XinJiang Urumqi830046 China College of Information Science and Engineering Xinjiang University XinJiang Urumqi830046 China Key Laboratory of Signal Detection and Processing Xinjiang University XinJiang Urumqi830046 China Department of Radiology The First Affiliated Hospital of Xinjiang Medical University XinJiang Urumqi830000 China

Scientists are constantly modifying the architecture of deep learning networks to achieve better fusion results, but few people pay attention to the impact of noise feature maps generated in the convolution process on fusion results. Here, we aim to minimize the influence of noisy feature maps on fusion results and propose a fusion model, namely infrared and visible image fusion model based on adaptive selection feature maps (ASFFuse), which incorporates an adaptive selection feature maps module (ASFM). The ASFM effectively filters out noisy feature maps to enhance the fusion performance. Additionally, we introduce a feature enhancement module (FEM) to enrich fusion image with more source image information. For unsupervised training of the proposed model, We propose a gradient loss function based on contrast learning. This loss function can keep the texture information we need and discard the texture information we do not want. By using this gradient loss function, our fused images can have more gradient information and discard unwanted texture information, which makes the fusion images have better visual effects. Our ASFFuse model has been shown to outperform state-of-the-art models in both quantitative and qualitative evaluations in extensive experiments on TNO and RoadScene datasets. Code is available at https://***/LKZ1584905069/ASFFuse. © 2023, The Authors. All rights reserved.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

SMMA-Net: An Audio Clue-Based Target Speaker Extraction Network with Spectrogram Matching and Mutual Attention

SMMA-Net: An Audio Clue-Based Target Speaker Extraction Netw...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Ying Hu Haitao Xu Zhongcun Guo Hao Huang Liang He Key Laboratory of Signal Detection and Processing Xinjiang Urumqi China School of Computer Science and Technology Xinjiang University Urumqi China HiSilicon Technologies Co. Limited Department of Electronic Engineering Tsinghua University Beijing China

We propose a deep neural network with spectrogram matching and mutual attention (SMMA-Net) for audio clue-based target speaker extraction (TSE). To effectively use the auxiliary speech, we proposed spectrogram matching (SM) strategy and mutual attention (MA) block. We conducted all experiments on the WSJ0-2mix-extr dataset. The ablation and comparison studies verified the effectiveness of SM strategy and MA block. The experimental results show that our proposed method outperforms the state-of-the-art methods by a sizable margin of 1.3 dB on the metric of scale-invariant signal-to-distortion ratio improvement. Additionally, SMMA-Net achieved that the performance of model for TSE task exceeds that for speaker separation task under the similar architecture. The main code will be available at https://***/Ht-Xu/SMMA-Net.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sle Diagnosis Research Based on Sers Combined with a Multi-Modal Fusion Method

SSRN

引用

SSRN 2023年

作者： Huang, Yuhao Chen, Chen Chang, Chenjie Cheng, Zhiyuan Liu, Yang Chen, Cheng Lv, Xiaoyi College of Software Xinjiang University Xinjiang 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 Xinjiang Cloud Computing Engineering Technology Research Center Karamay834000 China

As artificial intelligence technology gains widespread adoption in biomedicine, the exploration of integrating biofluidic Raman spectroscopy for enhanced disease diagnosis opens up new prospects for the practical application of Raman spectroscopy in clinical settings. However, for Systemic Lupus Erythematosus (SLE), the relatively weak signals from a single Raman spectroscopic data make it difficult to obtain desirable classification results. Although the surface enhancement technique can enhance the scattered signal of Raman spectroscopic data, the sensitivity of the SERS substrate to airborne impurities and the non-uniform distribution of hotspots degrade some of the signals. To fully utilize both types of data, this paper proposes a two-branch residual-attention network (DBRAN) fusion technique that allows the original spectra to complement the degraded portion, improving the model's classification accuracy. The residual module is used to extract features, which preserves the original features while extracting the deep ones. At the same time, the study incorporates the attention module in both the upper and lower branches to handle the weight assignment of the two modal features more efficiently. The experimental results demonstrated that both the low-level fusion method and the intermediate-level fusion method significantly improved the diagnostic accuracy of SLE disease classification when compared with a single modality, and the intermediate-level fusion DBRAN achieved 100% classification accuracy, sensitivity, and specificity. Compared with the raw Raman spectrum single mode and SERS single mode, the improvement is 10% and 7%, respectively. This experiment realized the rapid diagnosis of SLE disease by fusing the spectral data of multiple modes, which provides a reference idea in the Raman spectroscopy field. © 2023, The Authors. All rights reserved.

关键词： Raman spectroscopy

来源：评论

学校读者我要写书评

暂无评论

HIGF-Net: Hierarchical information-guided fusion network for polyp segmentation based on transformer and convolution feature learning

引用

Computers in Biology and Medicine 2023年第1期161卷 107038-107038页

作者： Wang, Junwen Tian, Shengwei Yu, Long Zhou, Zhicheng Wang, Fan Wang, Yongtao College of Software Xinjiang University Urumqi830000 China Key Laboratory of Software Engineering Technology Xinjiang University Urumqi830000 China College of Network Center Xinjiang University Urumqi830000 China Signal and Signal Processing Laboratory College of Information Science and Engineering Xinjiang University Urumqi830000 China

Polyp segmentation plays a role in image analysis during colonoscopy screening, thus improving the diagnostic efficiency of early colorectal cancer. However, due to the variable shape and size characteristics of polyps, small difference between lesion area and background, and interference of image acquisition conditions, existing segmentation methods have the phenomenon of missing polyp and rough boundary division. To overcome the above challenges, we propose a multi-level fusion network called HIGF-Net, which uses hierarchical guidance strategy to aggregate rich information to produce reliable segmentation results. Specifically, our HIGF-Net excavates deep global semantic information and shallow local spatial features of images together with Transformer encoder and CNN encoder. Then, Double-stream structure is used to transmit polyp shape properties between feature layers at different depths. The module calibrates the position and shape of polyps in different sizes to improve the model's efficient use of the rich polyp features. In addition, Separate Refinement module refines the polyp profile in the uncertain region to highlight the difference between the polyp and the background. Finally, in order to adapt to diverse collection environments, Hierarchical Pyramid Fusion module merges the features of multiple layers with different representational capabilities. We evaluate the learning and generalization abilities of HIGF-Net on five datasets using six evaluation metrics, including Kvasir-SEG, CVC-ClinicDB, ETIS, CVC-300, and CVC-ColonDB. Experimental results show that the proposed model is effective in polyp feature mining and lesion identification, and its segmentation performance is better than ten excellent models. © 2023

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Sle Diagnosis Research Based on Sers Combined with a Multi-Modal Fusion Method

SSRN

引用

SSRN 2023年

关键词： Raman spectroscopy

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

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：