检索结果-内蒙古大学图书馆

2019 International Conference on Artificial Intelligence and Advanced Manufacturing, AIAM 2019

作者： Yan, Guolin Wang, Mei Liu, X. Song, Xiyu Guilin University of Technology College of Information Science and Engineering Guilin China Guilin University of Technology Guangxi Key Laboratory Fund of Embedded Technology and Intelligent System Guilin China Guilin University of Electronic Technology Key Laboratory of Cognitive Radio and Information Processing Guilin China

ISBN: (纸本)9781728146911

In the sound environment of instability noise, the recognition rate of sound events would be reduced if using a single sound feature to train public sound data. To solve this problem, we propose a new method of sound event recognition based in feature combination with low SNR in this paper. It improves the recognition of sound events in real scenes by adding noise to public sound data sets. On the other hand, in order to overcome the inaccuracy of single features in noise recognition and significantly improved the recognition rate, we propose a new combination method which combining multiple features and drawing on the advantages of image recognition. Actual test shows that the public sound data set with noise has good generalization ability to the actual scene. The designed combined features can further improve the classification recognition performance, and the recognition rate of real environmental acoustic events can reach 75%, meeting the requirements of the actual system. © 2019 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Deepfake Detection Method Based on Face Edge Bands 9

Deepfake Detection Method Based on Face Edge Bands

引用

9th International Conference on Digital Home, ICDH 2022

作者： Deng, Zhengjie Zhang, Bao He, Shuqian Wang, Yizhen Hainan Normal University School of Information Science and Technology Haikou China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China Hainan Normal University School of Physics and Electronic Engineering Haikou China

ISBN: (数字)9781665454780

ISBN: (纸本)9781665454780

The rapid development of face forgery technology and the generation of realistic fake videos have caused serious harm to individuals, society and even the country, so it is important to detect deepfake videos. There are many detection methods available for forged videos, but the overall performance is yet to be improved and does not cope well with high quality forged images or videos. Observing that existing forgery algorithms leave synthetic forgery traces at the edges of faces when creating videos, this paper proposes a new method for detecting forged videos. It first finds the face edges from the video frames, then extracts the face edge bands as deep learning inputs and trains them based on EfficientNet-B3 to achieve effective detection of deepfake videos. Experiments show that the method in this paper can achieve more than 99.8% AUC values on all four forgery methods of the Face-Forensics++ dataset. © 2022 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

A Method for Analyzing Teacher Behavior in Classroom Based on the Long- and Short-Term Features of Pose Sequences 9

A Method for Analyzing Teacher Behavior in Classroom Based o...

引用

9th International Conference on Digital Home, ICDH 2022

作者： Li, Yuanzhong Deng, Zhengjie Liu, Meijun He, Shuqian Wang, Yizhen Jiang, Wenjuan Hainan Normal University School of Information Science and Technology Haikou China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China Hainan Normal University School of Physics and Electronic Engineering Haikou China

ISBN: (数字)9781665454780

ISBN: (纸本)9781665454780

The analysis of teachers' behaviors in classroom videos is helpful to objectively evaluate teaching, promote teaching reform, and improve teaching effectiveness. With the continuous introduction of deep learning models, there have been many analysis methods, but the recognition accuracy is not high enough. In this paper, we construct a new model combining convolutional neural network and recurrent neural network to learn and fuse short-term features with long-term features, and use the spatio-temporal information of videos to get the behavior categories. In our experiments, we collected teacher classroom videos in teaching scenarios to construct the dataset. The 2D pose heatmap sequences are extracted from the videos as model inputs, which are used to exclude the interference of environmental noise in the teaching scene. The experimental results show that this method can achieve higher recognition accuracy compared with the PoseR(2+1)D method on the teacher behavior dataset for teacher behavior analysis in teaching scenes. © 2022 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on SDN Multi Controller Deployment based on K-means++

Research on SDN Multi Controller Deployment based on K-means...

引用

2020 International Conference on 5G Mobile Communication and information Science, MCIS-5G 2020

作者： Yue, Li Junyan, Chen Chuxin, Liang Xiaochun, Lei School of Computer and Information Security Guilin University of Electronic Technology Guilin541004 China Guangxi Cloud Computing and Big Data Collaborative Innovation Center Guilin541001 China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 China

In large-scale SDN network, a single centralized controller can not meet the demand, and multiple controllers are needed to deal with the problem, which leads to the problem of multi control balanced deployment. In this paper, the topology of SDN switches and links is known. The main research contents are as follows: The mathematical model of SDN multi controller deployment is established, and the appropriate network topology is selected and the multi controller deployment problem is solved. In the research, the number of controllers needed in the network and the switches managed by each controller is determined by the algorithm results, and the mapping relationship between controllers and switches is established. By analyzing the deployment results of the same network topology under different algorithms, the influence of different clustering algorithms on the experimental results is obtained. At the same time, the better deployment experiment results are simulated. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

The Design of Multi-mode Examinees Identity Verification system for Colleges and Universities

The Design of Multi-mode Examinees Identity Verification Sys...

引用

2018 International Conference on Computer Modeling, Simulation and Algorithm（CMSA2018）

作者： Jia Chen Cong Chen Guangxi Colleges and Universities Key Laboratory of Image Processing and Intelligent Information System Wuzhou University Guangxi Colleges and Universities Key Laboratory of Professional Software Technology Wuzhou University

With the rapid development of information management in colleges and universities, traditional eyeobserving verification methods cannot satisfy today's requirement for examination management any more. Examinees' identities need to be verified more effectively and accurately. In recent years, biometric recognition has been becoming an essential component of effective person identification solutions because biometric identifiers intrinsically represent individuals' bodily identity. In this paper, we present a multi-mode verification system that not only takes advantage of biometric recognition to improve efficiency and accuracy, but also incorporates eye-observing verification to deal with the case when biometric recognition fails. Accordingly, an original portable verification device was designed to implement this multi-mode verification system. Our experiment shows that this verification system can meet the practical requirement of examination management in colleges and universities.

关键词： identity verification multi-mode verification comprehensive judgment original verification device

来源：评论

学校读者我要写书评

暂无评论

NPIPVis:A visualization system involving NBA visual analysis and integrated learning model prediction

引用

Virtual Reality & intelligent Hardware 2022年第5期4卷 444-458页

作者： Zhuo SHI Mingrui LI Meng WANG Jing SHEN Wei CHEN Xiaonan LUO Department of Art and Design University of Guilin Electronic TechnologyGuilin 541004China Department of Computer and Information Security University of Guilin Electronic TechnologyGuilin 541004China Department of Guangxi Key Laboratory of Image and Graphic Intelligent Processing University of Guilin Electronic TechnologyGuilin 541004China Department of State Key Laboratory of CAD&CG University of ZhejiangHangzhou 310058China

Background Data-driven event analysis has gradually become the backbone of modern competitive sports analysis. Competitive sports data analysis tasks increasingly use computer vision and machine-learning models for intelligent data analysis. Existing sports visualization systems focus on the player–team data visualization, which is not intuitive enough for team season win–loss data and game time-series data visualization and neglects the prediction of all-star players. Methods This study used an interactive visualization system designed with parallel aggregated ordered hypergraph dynamic hypergraphs, Calliope visualization data story technology,and i Storyline narrative visualization technology to visualize the regular statistics and game time data of players and teams. NPIPVis includes dynamic hypergraphs of a team’s wins and losses and game plot narrative visualization components. In addition, an integrated learning-based all-star player prediction model, SRR-voting, which starts from the existing minority and majority samples, was proposed using the synthetic minority oversampling technique and Random Under Sampler methods to generate and eliminate samples of a certain size to balance the number of allstar and average players in the datasets. Next, a random forest algorithm was introduced to extract and construct the features of players and combined with the voting integrated model to predict the all-star players, using GridSearch CV, to optimize the hyperparameters of each model in integrated learning and then combined with five-fold cross-validation to improve the generalization ability of the model. Finally, the SHapley Additive ex Planations(SHAP) model was introduced to enhance the interpretability of the model. Results The experimental results of comparing the SRR-voting model with six common models show that the accuracy, F1-score, and recall metrics are significantly improved, which verifies the effectiveness and practicality of the SRR-voting model. Conc

关键词： Sports visualization Parallel aggregated ordered hypergraph Calliope IStoryline Integrated learning SHAP model

来源：评论

学校读者我要写书评

暂无评论

Chinese Summary Generation Algorithm Based on Contrastive Attention Mechanism 4

Chinese Summary Generation Algorithm Based on Contrastive At...

引用

4th International Symposium on Computer Engineering and intelligent Communications, ISCEIC 2023

作者： Guo, Liupeng Xiao, Yannan Wen, Yayuan Wen, Peizhi Guilin University of Electronic Technology School of Computer and Information Security Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China Guilin University of Electronic Technology School of Computer and Information Security Guilin China Guangxi Normal University School of Electronic and Information Engineering School of Integrated Circuits Guilin China

ISBN: (纸本)9798350306323

Generative summarization based on the seq2seq model has gained widespread adoption due to the advancements and efficacy of the sequence-to-sequence framework. However, these models encounter challenges in handling out-of-vocabulary words and may produce summaries with factual inaccuracies. This paper addresses these issues by proposing a summarization generation model, MBC, which is built upon the Transformer as the baseline model. Additionally, it incorporates the BERT pre-trained model, pointer generation network, contrastive attention mechanism, and coverage loss. The model employs a pointer generation network to augment its vocabulary coverage capabilities by generating new terms. To enhance the representation of key information from the source text, a contrastive attention mechanism is employed during summary generation. In addition, by introducing coverage loss, the model can reduce repetitive content in the summary. To assess the model's performance, this paper employs ROUGE values as evaluation metrics and conducts comparative experiments with other models using the LCSTS dataset. The experimental results demonstrate that, in comparison with other models, this model is more adept at attending to salient information within the source text and generating summaries of greater accuracy. © 2023 IEEE.

关键词： BERT pre-training model contrastive attention mechanism coverage loss pointer generation network seq2seq model

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Chinese Summarization Generation Method Based on Knowledge Distillation 4

A Lightweight Chinese Summarization Generation Method Based ...

引用

4th International Conference on information Science, Parallel and Distributed systems, ISPDS 2023

作者： Liu, Shiyue Xiao, Yannan Wang, Xueyong Huang, Wenming Deng, Zhenrong School of Computer and Information Security Guilin University of Electronic Technology Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China School of Computer and Information Security Guilin University of Electronic Technology Guilin China Guilin Xintong Technology Co. Guilin China

ISBN: (纸本)9798350337181

In recent years, large-scale pretrained natural language processing models such as BERT, GPT3 have achieved good results in processing tasks. However, in daily applications, these large-scale language models usually exist large model size or long running time, and the model portability and application are not very convenient. To settle this problem, we come up with a lightweight summarization generation method based on knowledge distillation (LW-BERT-KD, abbreviated as LBK model) to prove that complex neural network knowledge (taking BERT model as an example) can be extracted to lightweight language processing models (taking BiLSTM model as an example), thus achieving the purpose of complex knowledge extraction and model compression. In this paper, the BERT model is regarded as the teacher model, and the BiLSTM is regarded as the student model. The knowledge distillation technology is the transfer of knowledge from teacher models to student models, so that the generated model is effective, lightweight, and easy to port. On the Chinese abstract generation dataset, the training effect of this model is significantly better than the basic Transformer baseline. The experimental results show that if the training parameters are increased by 100 times, the model achieves comparable results with complex preprocessing language models. © 2023 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

A fractal image coding method combined with compressed sensing algorithm

Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu

引用

Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu 2016年第4期 78-83页

作者： Guo, Hui He, Jie Hu, Defa Jiang, Weijin Guangxi Colleges and Universities Key Lab. of Image Processing and Intelligent Information System Wuzhou University Wuzhou Guangxi China School of Computer and Information Engineering Hunan University of Commerce Changsha Hunan China

Purpose. Since fractal image coding is time-consuming and is prone to causing "blocking artifact", the article aims to combine fractal image coding, wavelet transform and compressed sensing to put forward a method which can shorten the coding time effectively and improve the quality of a reconstructed image. Methodology. The compressed sensing algorithm can quickly compress and highly restore sparse matrixes. The paper made use of this feature to conduct fractal coding for a low-frequency sub-image after wavelet transform, followed by recoding the samples of low-frequency differential sub-graphs and high-frequency sub-images by means of the compressed sensing algorithm for the purpose of compensating the quality of reconstructed images. Findings. Compared to the traditional fractal coding method, the algorithm in the paper (hereinafter referred to as "this Algorithm") can shorten the time considerably and get a maximum speed-up ratio by up to 6.45 times. Compared to the compressed sensing coding method, the quality of the reconstructed images is improved significantly. Originality. The innovation of the paper lies in applying the compressed sensing theory to the fractal coding algorithm to compensate the quality of the reconstructed images obtained by means of fractal coding based on wavelet transform. Practical value. This Algorithm can shorten the coding time on the basis of ensuring the quality of a reconstructed image, and has certain significance for promoting the fractal coding method. © Hui Guo, Jie He, Defa Hu, Weijin Jiang, 2016.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Reconstruction of compressed sensing images based on Lpnorm and modified quasi-Newton method

Boletin Tecnico/Technical Bulletin

引用

Boletin Tecnico/Technical Bulletin 2017年第15期55卷 482-488页

作者： Gong, Ping Li, Guohua Li, Jian School of Information and Electronic Engineering Wuzhou Universtity Wuzhou Guangxi543002 China Guangxi Colleges and Universities Key Laboratory of Image Processing and Intelligence Information System Wuzhou Universtity Wuzhou Guangxi543002 China

The Lpnorm which combines the advantages of L1and L0norms (0pnorm and its first-order derivative is computed. A quasi-Newton method is generated using the globally converging modified CBFGS formula and the inexact Wolfe linear search strategy. Experiments are performed under different sampling rates and image features. Experimental results show that the visual effects of images reconstructed using the proposed algorithm are better than existing methods and that the proposed algorithm achieves performance gain in terms of PSNR and SSIM.

关键词： image reconstruction

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：