检索结果-内蒙古大学图书馆

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

Optimization of Coupled ARX-Laguerre Multimodel Parameters Using Genetic Algorithm

Optimization of Coupled ARX-Laguerre Multimodel Parameters U...

引用

International Conference on Systems and Control (ICSC)

作者： Hajer Benamor Marwa Yousfi Larbi Chrifi Alaoui Tarek Garna Laboratory of Automatic Signal and Image Processing (LARATSI) National Engineering School of Monastir Monastir Tunisia Laboratory of Innovative Technology (LTI UR-UPJV 3899) University of Picardie Jules Verne Amiens France Higher Institute of Applied Science and Technology of Sousse Sousse Tunisia

ISBN: (数字)9798331531812

ISBN: (纸本)9798331531829

This work treats parametric optimization of nonlinear systems using genetic algorithms. The authors focus, in this paper, in combining the ARX-Laguerre model and the multimodel approach with its coupled configuration to develop a model named the coupled ARX-Laguerre multimodel. The proposed model is characterized by its Laguerre poles, Fourier coefficients and weighting functions parameters. The complexity of the model is tightly related to the optimal identification of the Laguerre poles characterizing the model. The authors propose an optimization algorithm of the multimodel parameters (Laguerre poles and weighting functions parameters) based on the genetic to guarantee a significant parametric number reduction with regards to the classic ARX multimodel.

关键词： Uncertainty Solids Genetics Control systems Chemical reactions Iterative algorithms Complexity theory Nonlinear systems Optimization Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Single Channel CSAR Moving Target Detection Algorithm Based on Low-rank Sparse Decomposition

Single Channel CSAR Moving Target Detection Algorithm Based ...

引用

2021 CIE International Conference on radar, radar 2021

作者： Zhang, Zhiguo Shen, Wenjie Yue, Xiaoyang Lin, Yun Hong, Wen Aerospace Information Research Institute Chinese Academy of Sciences Key Laboratory of Technology in Geospatial Information Processing and Application System Beijing China School of Information Science and Technology North China University of Technology Radar Monitoring Technology Laboratory Beijing China

ISBN: (纸本)9781665498142

With the goal of detecting moving targets, this paper proposes a new single channel Circular Synthetic Aperture radar (CSAR) moving targets detection algorithm based on Low-rank Sparse Decomposition (LRSD). This algorithm utilizes the correlation among overlap subaperture logarithmic amplitude image sequences, the static clutter is regarded as low-rank component and the moving targets is considered as sparse component. Then, the background image sequence (without moving target) and the foreground image sequence (moving targets) can be extracted by the LRSD. Considering the unknown foreground image distribution, this paper proposes a Local Dynamic Threshold based on Otsu (LDTO) method independent of image distribution to detect moving targets. Finally, the experiment on the X-band airborne Gotcha Data demonstrates the effectiveness of the proposed algorithm. © 2021 IEEE.

关键词： circular synthetic aperture radar local dynamic threshold based on Otsu low rank sparse decomposition moving target detection

来源：评论

学校读者我要写书评

暂无评论

Boosting polyp screening with improved point-teacher weakly semi-supervised

引用

Computers in Biology and Medicine 2025年 191卷 109998-109998页

作者： Du, Xiuquan Zhang, Xuejun Chen, Jiajia Li, Lei Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei China Department of Neurology Shuyang Affiliated Hospital of Nanjing University of Traditional Chinese Medicine Suqian China School of Computer Science and Technology Anhui University Hefei China

Polyps, like a silent time bomb in the gut, are always lurking and can explode into deadly colorectal cancer at any time. Many methods are attempted to maximize the early detection of colon polyps by screening, however, there are still face some challenges: (i) the scarcity of per-pixel annotation data and clinical features such as the blurred boundary and low contrast of polyps result in poor performance. (ii) existing weakly semi-supervised methods directly using pseudo-labels to supervise student tend to ignore the value brought by intermediate features in the teacher. To adapt the point-prompt teacher model to the challenging scenarios of complex medical images and limited annotation data, we creatively leverage the diverse inductive biases of CNN and Transformer to extract robust and complementary representation of polyp features (boundary and context). At the same time, a novel designed teacher–student intermediate feature distillation method is introduced rather than just using pseudo-labels to guide student learning. Comprehensive experiments demonstrate that our proposed method effectively handles scenarios with limited annotations and exhibits good segmentation performance. All code is available at https://***/dxqllp/WSS-Polyp. © 2025 Elsevier Ltd

关键词： Weakly semi-supervised Medical image segmentation Boundary extraction Feature distillation

来源：评论

学校读者我要写书评

暂无评论

Optimized Statistical Model for Complex Chemical Processes Monitoring

Optimized Statistical Model for Complex Chemical Processes M...

引用

Data Driven Control and Learning Systems (DDCLS)

作者： Jian Zhang Xiaohe Qu Zhiwei Lei Haifeng Zhang Kai Zhong Datang East China Electric Power Test and Research Institute Hefei China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Mathematical Science Anhui University Hefei China Key Laboratory of Intelligent Computing and Signal Processing of the Ministry of Education Institutes of Physical Science and Information Technology Anhui University Hefei Anhui China

The traditional kernel principal components analysis (KPCA) and linear discriminant analysis (LDA) have been verified to be two effective approaches for fault detection and diagnosis in recent years. Nevertheless, the conventional method and corresponding improved ones still exposed their deficiencies in some ways. Facing this dilemma, this paper presents a combination of optimized KPCA and modified LDA (OKPCA-MLDA), in which the OKPCA avoids the loss of original features after centralizing data in the eigenspace by adjusting covariance matrix's eigenvalue and transforming the distribution of variables thus providing representative and abundant principal components for the classifier. In addition, the MLDA maximizes a brand new objective function in feature space which achieves better classification performance than the conventional LDA, then utilizing diagnostic thresholds and similarity coefficients to identify the fault types. Based on the combined model, not only the fault detection and diagnosis can be realized simultaneously but also the accuracy of detection and diagnosis can be guaranteed. Furthermore, the simulation experiments on Tennessee Eastman (TE) benchmark process clearly illustrated the superiority of our proposed strategy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GateM2Former: Gated Feature Selection and Expert Modeling in Multimodal Emotion Recognition

GateM2Former: Gated Feature Selection and Expert Modeling in...

引用

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

作者： Weixiang Xu Zhongren Dong Runming Wang Xinzhou Xu Zixing Zhang College of Computer Science and Electronic Engineering Hunan University China School of Information Science and Engineering Hunan Normal University China Signal Processing and Speech Communication Laboratory Graz University of Technology Austria Shenzhen Research Institute Hunan University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In recent years, multimodal emotion recognition (MER) has gained significant attention due to its potential to integrate information from diverse signals. However, existing methods often struggle to effectively capture complex interactions and contextual information both inter- and intra-modalities, and even to extract the salient representations from pre-trained models. To address these issues, we propose a novel model, gated Mixture of Multimodal Experts (MoME) and Mixtral of Experts (MixMoE) models, namely GateM 2 Former. The gate mechanism is used to select the most relevant representations from pre-trained models. The MoME and MixMoE expert modules respectively learn the individual characteristics of each modality and the intrinsic alignment and potential interactions between modalities. Besides, we design a hierarchical merge structure to better suit the long sequence scenario (i. e., speech in our case). To verify the effectiveness of the introduced model, we conducted extensive experiments on the IEMOCAP and MELD datasets. The results show that GateM 2 Former, with a universal multimodal structure, is able to achieve the best results on IEMOCAP and MELD compared with other latest approaches.

关键词： Adaptation models Emotion recognition Semantics Speech recognition Logic gates signal processing Transformers Feature extraction Robustness Speech processing

来源：评论

学校读者我要写书评

暂无评论

Denoising Algorithm of Environmental Sound Fused NMF and OMLSA in Non-Stationary Noise Environment 5

Denoising Algorithm of Environmental Sound Fused NMF and OML...

引用

5th IEEE Advanced Information technology, Electronic and Automation Control Conference, IAEAC 2021

作者： Guo, Shuting Luo, Liyan Wang, Mei Zhou, Zou Deng, Xiaofang Bai, Lu Zhao, Dancheng Provincial Ministry of Education Key Laboratory of Cognitive Radio and Signal Processing Guilin University of Electronic Technology Guilin Guangxi541004 China Guilin University of Electronic Technology Guangxi Key Laboratory of Wireless Broadband Communication and Signal Processing Guilin541004 China College of Information Science and Engineering Guilin University of Technology Guilin Guangxi541007 China

The traditional denoising algorithm can reduce the noise from environment, yet an evident downside of this is the sharp decrease of efficacy under non-stationary noise with low signal to noise ratio (SNR). In this case, this paper presents a denoising algorithm for environmental sound based on non-negative matrix factorization (NMF) and optimally-modified log-spectral amplitude (OMLSA). First of all, prior information is obtained from the noise and environmental sound dataset to separate the noise from noisy sound using supervised NMF. Then, decision-direction approach (DD) is used to calculate a priori SNR estimation according to the power spectral density (PSD) of the separated noise. Finally, under the log minimum mean square error criterion, the OMLSA gain function is obtained to filter out the noise in the environment. In this paper, the performance of the proposed algorithm is tested with white noise, F16 and babble under -5dB, 0dB and 5dB SNR conditions respectively. The experimental results show that this algorithm has strong ability of filtering out the noise superimposed in the environmental sound and improving the SNR gains. Moreover, comparing with other noise suppression algorithms, the proposed algorithm preforms better in preserving weak environmental sound, significantly reducing environmental sound distortion and avoiding the introduction of musical noise. © 2021 IEEE.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Instruction Tuning-free Visual Token Complement for Multimodal LLMs

arXiv

引用

arXiv 2024年

作者： Wang, Dongsheng Cui, Jiequan Li, Miaoge Lin, Wang Chen, Bo Zhang, Hanwang College of Computer Science and Software Engineering Shenzhen University China School of Computer Science and Engineering Nanyang Technological University Singapore Department of Computing Hong Kong Polytechnic University Hong Kong College of Computer Science and Technology Zhejiang University China National Key Lab of Radar Signal Processing Xidian University China

As the open community of large language models (LLMs) matures, multimodal LLMs (MLLMs) have promised an elegant bridge between vision and language. However, current research is inherently constrained by challenges such as the need for high-quality instruction pairs and the loss of visual information in image-to-text training objectives. To this end, we propose a Visual Token Complement framework (VTC) that helps MLLMs regain the missing visual features and thus improve response accuracy. Specifically, our VTC integrates text-to-image generation as a guide to identifying the text-irrelevant features, and a visual selector is then developed to generate complementary visual tokens to enrich the original visual input. Moreover, an iterative strategy is further designed to extract more visual information by iteratively using the visual selector without any additional training. Notably, the training pipeline requires no additional image-text pairs, resulting in a desired instruction tuning-free property. Both qualitative and quantitative experiments demonstrate the superiority and efficiency of our VTC. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual BASIC

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Content Caching Strategy in Cell-Free Massive MIMO Networks with Reinforcement Learning

Energy-Efficient Content Caching Strategy in Cell-Free Massi...

引用

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： Yuan Peng Fangqing Tan Qiang Liu Guangxi Key Laboratory of Wireless Wideband Communication and Signal Processing Guilin University of Electronic Technology Guilin China College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao China

To reduce the burden of transmission delay on the fronthaul link, this paper investigates an energy-efficient content caching, access point (AP) clustering and digital-to-analog converter resolution selection strategy in cell-free massive multiple-input multiple-output (CF-mMIMO) network with cache enabled are investigated. Specifically, we first give the signaling transmission model, cache model and power model. Furthermore, we formulated an optimization problem for maximizing the energy-efficiency of the considered system by optimizing the content caching, AP clustering and ADC/DAC resolution. Finally, a reinforcement learning method-a deep deterministic policy gradient algorithm is adopted to acquire the optimal solution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Azimuth Direction of Arrival Estimation Using Near-Surface Tilted Arrays in Deep-Sea Bottom-Bounce Area

Azimuth Direction of Arrival Estimation Using Near-Surface T...

引用

OCEANS

作者： Bo Zhang Yu Li Cheng Chi Haining Huang Guanqun Wang Institute of Acoustics Chinese Academy of Sciences Beijing Key Laboratory of Science and Technology on Advanced Underwater Acoustic Signal Processing Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350362077

ISBN: (纸本)9798350362084

The bottom bounce mode plays a crucial role in underwater acoustic detection in the shadow zone of deep water. When both the source and hydrophone are situated at depths of 300 meters or shallower, the main contributions to the sound field come from four multipath rays that reflected by the bottom only once. The sound field in the shadow zone mostly consists of larger- angle rays. Under such conditions, when the bottom bounce sound is received by a vertical line array, the lack of azimuthal resolution prevents obtaining source azimuth information. When the bottom bounce sound is received by a horizontal line array, an azimuth deviation appears because of the coupling effect between elevation angle and azimuth angle. This paper explains the reasons for the deviation. Then based on the trigonometric relation between the elevation angle and the azimuth angle, the deviation could be modified by the tilted array. The method is demonstrated with the simulated result.

关键词： Meters Couplings Direction-of-arrival estimation Accuracy Azimuth Echo sounders Oceans

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：