检索结果-内蒙古大学图书馆

A Heuristic Radiomics Feature Selection Method Based on Frequency Iteration and Multi-Supervised Training Mode

Computers, Materials & Continua 2024年第5期79卷 2277-2293页

作者： Zhigao Zeng Aoting Tang Shengqiu Yi Xinpan Yuan Yanhui Zhu School of Computer Hunan University of TechnologyZhuzhou412007China Hunan Key Laboratory of Intelligent Information Perception and Processing Technology Zhuzhou412007China

Radiomics is a non-invasive method for extracting quantitative and higher-dimensional features from medical images for *** has received great attention due to its huge application prospects in recent *** can know that the number of features selected by the existing radiomics feature selectionmethods is basically about *** this paper,a heuristic feature selection method based on frequency iteration and multiple supervised training mode is *** on the combination between features,it decomposes all features layer by layer to select the optimal features for each layer,then fuses the optimal features to form a local optimal group layer by layer and iterates to the global optimal combination *** with the currentmethod with the best prediction performance in the three data sets,thismethod proposed in this paper can reduce the number of features fromabout ten to about three without losing classification accuracy and even significantly improving classification *** proposed method has better interpretability and generalization ability,which gives it great potential in the feature selection of radiomics.

关键词： Radiomics feature selection machine learning metaheuristic

来源：评论

学校读者我要写书评

暂无评论

Micro-Expression Recognition Based on Spatio-Temporal Feature Extraction of Key Regions

引用

Computers, Materials & Continua 2023年第10期77卷 1373-1392页

作者： Wenqiu Zhu Yongsheng Li Qiang Liu Zhigao Zeng College of Computer Science Hunan University of TechnologyZhuzhou412007China Intelligent Information Perception and Processing Technology Hunan Province Key LaboratoryZhuzhou412007China

Aiming at the problems of short duration,low intensity,and difficult detection of micro-expressions(MEs),the global and local features of ME video frames are extracted by combining spatial feature extraction and temporal feature *** on traditional convolution neural network(CNN)and long short-term memory(LSTM),a recognition method combining global identification attention network(GIA),block identification attention network(BIA)and bi-directional long short-term memory(Bi-LSTM)is *** the BIA,the ME video frame will be cropped,and the training will be carried out by cropping into 24 identification blocks(IBs),10 IBs and uncropped *** alleviate the overfitting problem in training,we first extract the basic features of the preprocessed sequence through the transfer learning layer,and then extract the global and local spatial features of the output data through the GIA layer and the BIA layer,*** the BIA layer,the input data will be cropped into local feature vectors with attention weights to extract the local features of the ME frames;in the GIA layer,the global features of the ME frames will be ***,after fusing the global and local feature vectors,the ME time-series information is extracted by *** experimental results show that using IBs can significantly improve the model’s ability to extract subtle facial features,and the model works best when 10 IBs are used.

关键词： Micro-expression recognition attention mechanism long and short-term memory network transfer learning identification block

来源：评论

学校读者我要写书评

暂无评论

A miniaturized polarization-insensitive energy absorption metasurface 6

A miniaturized polarization-insensitive energy absorption me...

引用

2024 6th International Conference on Artificial Intelligence Technologies and Applications, ICAITA 2024

作者： Zhen, Fajian Liu, Yunqing School of Electronic Information Engineering Changchun University of Science and Technology Jilin Changchun130022 China Jilin Provincial Science Technology Innovation Center of Intelligent Perception and Information Processing Jilin Changchun130022 China

A novel metasurface structure for energy absorption is proposed. The metasurface structure unit is composed of four bidirectional arrow patches, which are connected by load. In order to achieve unit miniaturization, a humanoid slot structure is proposed, which reduces the unit size to 0.23 λ. The designed metasurface structure can capture more than 90% of the energy at 5.8 GHz, has the characteristics of polarization insensitive, and can maintain 80% of the energy capture efficiency between 0 and 45°. The simulation results show that the structure is nonlinear to the load and can be applied to the design of rectification metasurface structures. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Polarization

来源：评论

学校读者我要写书评

暂无评论

Facial emotion recognition based on auxiliary classifiers and SENet module 4

Facial emotion recognition based on auxiliary classifiers an...

引用

4th International Conference on Digital Signal and Computer Communications, DSCC 2024

作者： Shang, Yujie Yan, Fei Liu, Yunqing Li, Qi School of Electronic Information Engineering Changchun University of Science and Technology Jilin Province Changchun China Jilin Provincial Science and Technology Innovation Center of Intelligent Perception and Information Processing Jilin Province Changchun China

ISBN: (纸本)9781510681538

When using convolutional neural networks (CNNs) for facial emotion recognition, downsampling in the convolutional layers often leads to the loss of many features. These lost features also play a role in emotion recognition and can affect the effectiveness of emotion recognition. Therefore, we propose a facial emotion recognition method based on auxiliary classifiers and SENet modules to effectively alleviate the problem of feature loss during the convolution process. By using SENet modules, the model enhances its focus on different channel features during the feature extraction process, enabling the model to pay better attention to important features. Subsequently, auxiliary classifiers are introduced into the model to effectively utilize features extracted from different layers for auxiliary classification. Finally, the auxiliary classification results are adaptively weighted and fused with the main classifier's classification results. Experimental results demonstrate that introducing auxiliary classifiers and SENet modules further improves the model's accuracy, reaching 68.87%. © 2024 SPIE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Aerial Tracking based on Vision Transformer

Aerial Tracking based on Vision Transformer

引用

2022 International Conference on Electronic information Engineering and Computer Science, EIECS 2022

作者： Jiang, Siping Liu, Yunqing Wang, Liang Xu, Yulong Changchun University of Science and Technology College of Electronic and Information Engineering Jilin Province Changchun China Intelligent Perception and Processing Technology Laboratory Beijing China

ISBN: (纸本)9781510663312

In recent years, object tracking depends upon deep networks or complex architectures made great progress in accuracy, but less attention has been paid to tracking speed. On edge platforms with limited resources are used on UAVs, trackers are difficult to meet the requirements of real-time processing. To address the above problems, we proposed UAV object tracking based on vision transformer. Firstly, a lightweight neural network ResNet18 is used for feature extraction. Secondly, a transformer encoder is used to fully enhance fused features of the template features and the search features to improve feature expression, then, the enhanced features output from encoder are used for target prediction. Finally, further weighted fusion at decision level is used to obtain final tracking result, and a multi-supervised strategy is used. The proposed method achieves better results on three challenging large-scale tracking datasets, UAV123, LaSOT, and TrackingNet, reaching the success score(AUC) of 66.82, 64.26, and 81.2, respectively. In addition, our model tested speed on UAV123's test dataset, running at 116.2fps on NVIDIA 1660TI and 20.2fps on NVIDIA Jetson Xavier NX, which basically meets UAV's demand for real-time performance. © 2023 SPIE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Abstractive Text Summarization Model Based on BERT Vectorization and Bidirectional Decoding

Abstractive Text Summarization Model Based on BERT Vectoriza...

引用

2023 International Conference on Cyber Security, Artificial Intelligence, and Digital Economy, CSAIDE 2023

作者： Teng, Keliang Qiang, Baohua Wang, Yufeng Yang, Xianyi Wang, Yuemeng Wang, Chen Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China Hebei Key Laboratory of Intelligent Information Perception and Processing The 54th Research Institute of CETC Shijiazhuang050081 China

ISBN: (纸本)9781510666597

Facing the pressure of the extremely inflated network information and data overload surplus, it is extremely important to locate "valuable information" efficiently and accurately. Text summarization technology in the field of Natural Language processing (NLP) is an effective means to analyze and process network information. In this paper, we propose an abstractive text summarization model based on bidirectional encoder representations from transformers (BERT) vectorization and bidirectional decoding. The BERT is adopted to obtain a more global vector representation, which helps the subsequent encoder and decoder to fuse the full-text information to generate a summary with high generality. The decoding phase adopts a bidirectional decoding structure and combines the attention mechanism to maintain the bilateral decoding result to generate summaries. The bidirectional decoding structure can be fine-tuned according to the bidirectional results, which can overcome the tilt problem of the unidirectional structure, and the generated summaries are more consistent. The experimental results on the NLPCC2017 text summarization dataset show that the summaries generated by our model have the higher coherence at the word and sentence level, and the stronger generalization of the full text. © 2023 SPIE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Chinese Event Extraction Algorithm of Multi-information Semantic Enhancements 12

Chinese Event Extraction Algorithm of Multi-Information Sema...

引用

12th International Conference on Computing and Pattern Recognition, ICCPR 2023

作者： Qiang, Baohua Tang, Feng Zhou, Xiangyu Wang, Yuanchun Yang, Xianyi Li, Kai Guilin University of Electronic Technology Guilin China The 54th Research Institute of Cetc Shijiazhuang China Hebei Key Laboratory of Intelligent Information Perception and Processing Shijiazhuang China

ISBN: (纸本)9798400707988

To address the problems of inaccurate event element extraction, inability to directly handle long texts and errors in the fine-tuning stage of the task due to insufficient semantic information and incomplete semantic feature samples in the current Chinese domain event extraction model, this paper proposes the Chinese Event Extraction Algorithm of Multi-information Semantic Enhancements (MiSE). In the embedding stage, the algorithm is designed a coding structure that fusing multiple information: Using the Roformer model based on rotational encoding for word embedding and text embedding, and augment the Roformer word embedding matrix by mapping the word embedding matrixs of event trigger, argument information and their location information to it , forming an vector matrix that incorporates multiple information;the matrix is then placed into the BiLSTM for forward and backward chain calculation to enhance the model's ability to extract semantic information from Chinese text. In the decoding stage, using the decoding structure to obtain the set of tags with the highest probability. Comparing this algorithm with several Chinese event extraction algorithms on the Baidu DuEE dataset and its extraction results outperformed other event extraction algorithms in all evaluation metrics. © 2023 ACM.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Semantic Matching Algorithm for Legal Issues Based on BERT and Graph Convolution with Multi-granularity Features 12

Semantic Matching Algorithm for Legal Issues Based on BERT a...

引用

12th International Conference on Computing and Pattern Recognition, ICCPR 2023

作者： Qiang, Baohua Pang, Shijie Teng, Keliang Liu, Zhiguang Liu, Weigang Guilin University of Electronic Technology Guilin China The 54th Research Institute of Cetc Shijiazhuang China Hebei Key Laboratory of Intelligent Information Perception and Processing Shijiazhuang China

ISBN: (纸本)9798400707988

In recent years, pre-training models represented by BERT have shown amazing text semantic representation capabilities supported by large-scale corpus, and now have become one of the mainstream solutions for semantic matching tasks in legal Q&A systems. However, pre-training models generally do not set specific pre-training tasks in terms of syntactic information, but implicitly and incidentally learn in large-scale unsupervised, which does not make good use of syntactic information as an important factor for representing semantics. To address this problem, this paper proposes a multi-granularity feature semantic matching model based on BERT and graph convolution. The model first obtains syntactic features of sentences in the form of dependent syntactic trees using existing tools, and then fuses syntactic features with word features and sentence features of BERT using an attention mechanism and graph convolutional neural network to enhance the characterization of text semantics and make the model better for semantic matching tasks. Experimental results show that the algorithm achieves significant improvements in the semantic matching task and outperforms the five comparison methods in the DIAC2019 dataset. Compared to the baseline model Sentenct-BERT, the accuracy, precision, recall and F1 values are improved by 0.33%, 1.18%, 1.03% and 1.05% improvement. © 2023 ACM.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional imaging of through-wall radar based on compressed sampling in the frequency domain

Three-dimensional imaging of through-wall radar based on com...

引用

2022 International Conference on Informatics, Networking and Computing, ICINC 2022

作者： Xu, Dongpo Liu, Yunqing Wang, Liang Li, Xiaolong Electronics and Information Engineering Changchun University of Science and Technology Changchun130022 China Intelligent Perception and Processing Technology Laboratory Beijing100124 China

ISBN: (纸本)9798350309690

Three-dimensional imaging of through-the-wall radar is an important branch in the field of covert target identification, and the commonly used technique is backward projection imaging, which compensates for the time delay information between the transceiver antennas and coherently superimposes the echo signals of each aperture in space to finally project a three-dimensional image. Because of its unique characteristics, the imaging algorithm is computationally huge and difficult to be applied in practical engineering. In this paper, we address this situation by focusing the image reconstruction problem in the framework of compressive sampling based on SFCW-MIMO radar, and propose a 3D imaging technique for through-wall radar with compressive sampling in the frequency domain. Through actual measurement data verification, it is proved that this method has faster image reconstruction speed and better imaging quality, which promotes the practical application of through-wall radar 3D imaging. © 2022 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Anchored Monotonic Alignment and Representation Substitution for Rare Spontaneous Behaviors in Spontaneous Speech Synthesis

Anchored Monotonic Alignment and Representation Substitution...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Wu, Ning-Qian Hu, Ya-Jun Chen, Liping Ling, Zhen-Hua National Engineering Research Center of Speech and Language Information Processing University of Science and Technology of China Hefei China iFLYTEK Research iFLYTEK Co. Ltd. China MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition University of Science and Technology of China China

ISBN: (纸本)9798350368741

Spontaneous behaviors in speech pose significant challenges for speech synthesis. Existing research has not adequately addressed these behaviors, with most studies relying on specially recorded datasets. In contrast, real-world data more accurately reflects the natural, spontaneous speaking styles in everyday life and encompasses a wider range of spontaneous behaviors. However, such data is often of lower quality, and the distribution of spontaneous behaviors is highly imbalanced. In this study, we explore spontaneous speech synthesis using real-world data within the VITS2 framework. To overcome these challenges, we introduce two techniques: anchored monotonic alignment and spontaneous hidden representation substitution. Experimental results demonstrate that these methods enhance model alignment and improve the naturalness of the generated speech. Our proposed approach successfully addresses the challenge of synthesizing rare spontaneous behaviors and offers users flexible control over the synthesized speech. © 2025 IEEE.

关键词： real-world data speech synthesis spontaneous behaviors spontaneous speech synthesis VITS

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：