检索结果-内蒙古大学图书馆

5th International Conference on intelligent Computing and Human-Computer Interaction, ICHCI 2024

作者： Liu, Chuangye Huang, Guimin School of Computer Science and Information Security Guilin University of Electronic Technology Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 China

ISBN: (纸本)9798350368284

Genetic algorithms have been widely used in intelligent test paper generation systems. However, traditional genetic algorithms cannot ensure that the difficulty of test questions is normally distributed, and are prone to falling into local optimal solutions. To address the above problems, we proposed an intelligent test paper generation algorithm that combines normal distribution and parallel genetic algorithms. In the population initialization stage, we use the cumulative distribution function (CDF) of the normal distribution to initialize the population. In the subsequent genetic operations, we designed a directed mutation mechanism and added KL divergence as a penalty number in the design of the fitness function to ensure that the difficulty of the test questions is normally distributed. At the same time, in order to speed up the efficiency of the algorithm and escape from the local optimal solution, an adaptive migration strategy was introduced. Experimental results show that the difficulty of the test questions generated by this algorithm is normally distributed, and the algorithm performance is better than other algorithms. © 2024 IEEE.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

引用

4th International Conference on Computer Science and Blockchain, CCSB 2024

作者： Huang, Guimin Shi, Canjun School of Computer Science and Information Security Guilin University of Electronic Technology Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 China

ISBN: (纸本)9798350356502

Short textual similarity has been more and more widely used in the field of natural language processing. However, people tend to pay more attention to the semantic similarity of sentences and ignore the word order similarity in sentences. For this reason, we propose a short text similarity computation model that fuses semantics and word order. In terms of semantics, we propose a adjacency-aware similarity model based on deep convolutional neural networks, which effectively exploits the adjacency relationship in sentences and extracts text features from multiple perspectives for similarity prediction. In terms of word order, a word order model incorporating an external knowledge base is proposed, which uses an external knowledge base with pointwise mutual information to construct word order dense vectors to assess word order similarity. Ultimately, we propose a comprehensive assessment model for short text similarity that incorporates semantic and word order information. We conducted experiments on the public dataset MRPC, and the experimental results show that our model outperforms existing models in terms of performance. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Convolutional Knowledge Tracking Model with Forgetting Behavior and Graph Embedding 3

A Convolutional Knowledge Tracking Model with Forgetting Beh...

引用

3rd International Conference on Electronics and Information Technology, EIT 2024

作者： Huang, Guimin Huang, Zhiqing Guilin University of Electronic Technology School of Computer Science and Information Security Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 China

ISBN: (纸本)9798350369151

With the prevalence of various intelligent educational systems, it is imperative to uncover learners' proficiency in mastering knowledge points through their prior practice circumstances. Knowledge tracking is an extremely beneficial instrument in this regard. Among them, Convolutional Knowledge Tracking (CKT) has demonstrated excellent performance in numerous KT tasks, while it does not take into account the phenomenon of forgetting and the interconnection between knowledge points. In order to tackle these problems, we propose a model called FGE-CKT, which integrates forgetting behavior and graph embedding with CKT. Our model addresses the drawbacks of forgetting characteristics by modelling three key factors affecting students' forgetting behaviors through a fully connected neural net: repeated knowledge learning times, adjacent learning interval and interval between visits to repeat knowledge. At the same time, convolutional neural networks are used to simultaneously extract and incorporate connections between knowledge points into the model's input portion. It was confirmed by experiments on two well-established datasets that FGE-CKT achieved significant improvements in AUC performance. © 2024 IEEE.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Non-intrusive load monitoring based on a combination of Transformer and CNN 4

Non-intrusive load monitoring based on a combination of Tran...

引用

4th International Conference on Energy, Power and Electrical Engineering, EPEE 2024

作者： Cheng, Yiqi Zhong, Yanru Guilin University of Electronic Technology College of Computer and Information Security Guangxi Guilin China Guilin University of Electronic Technology Guangxi Key Laboratory of Image And Graphic Intelligent Processing Guangxi Guilin China

ISBN: (纸本)9798331518066

Non-intrusive load monitoring (NILM) estimates the energy usage of individual devices by analyzing the total power meter data from a household. To address the issue of decreased monitoring accuracy with an increasing number of electricity meters, this paper proposes a solution for single appliance load monitoring (Tra-CNN). The solution uses the UK-DALE dataset, which contains high and low frequencies electricity consumption data of multiple households in the UK and the electricity consumption data of each household appliance, and uses the active power of the appliance as the input of the algorithm. The first part of the model consists of a convolutional layer, a normalization layer, and a dropout layer, with the primary task of capturing local dependencies in the data. The second part consists of a Transformer, whose self-attention mechanism associates features at different positions in the sequence to achieve modeling of long-term dependencies. The third part introduces a convolutional neural network, which uses a sliding window for convolution operations to extract local features from different positions and further extract features from sequence data. The final decoder consists of a transposed convolutional layer and a normalization layer, designed to revert the learned features to their original dimensions. Through experimental verification, the effectiveness and superiority of Tra-CNN are shown, which provides important ideas and methods for the further development of NILM technology. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

AES-AUDIO: An Encryption Scheme for Audio Supporting Differentiated Decryption

引用

IEEE Transactions on Multimedia 2025年 27卷 2268-2280页

作者： Zhao, Ruoyu Zhang, Yushu Ji, Junhao Yi, Shuang Wen, Wenying Lan, Rushi Jiangxi University of Finance and Economics School of Computer and Artificial Intelligence Nanchang330013 China Jiangxi Provincial Key Laboratory of Multimedia Intelligent Processing Nanchang330013 China Southwest University of Political Science and Law Criminal Investigation School Chongqing401120 China Guilin University of Electronic Technology Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 China Guilin University of Electronic Technology Guangxi Key Laboratory of Trusted Software Guilin541004 China

In this paper, we propose an audio encryption scheme that supports differentiated decryption, called AES-AUDIO, in which an audio only needs to be encrypted once and can be decrypted into different resolutions as needed. First, we design four security levels, confidential, harsh, noisy, and clear, based on the audio resolution perceived by human auditory perception. Second, the audio data in decimal floating-point numbers (D-FPNs) are unfolded to 32 bits (B-FPNs). Third, we design a region of interest (RoI) encryption algorithm for the audio with the B-FPN format, where the result preserves some perceptual information as needed. Fourth, we construct the AES-AUDIO scheme based on the RoI encryption algorithm, which allows the audio to be encrypted once and then decrypted into different security levels. It supports changing parameters to alter the perception effect corresponding to the security level. Overall, it achieves a balance between the security and usability of the protected audio. User experiments verify that the audios produced by differential decryption can achieve the expected security levels. Some security tests also yielded excellent results, such as an NSCR value of 1. © 1999-2012 IEEE.

关键词： Encryption algorithms

来源：评论

学校读者我要写书评

暂无评论

Short-Term Smart Grid Load Forecasting Based on CNN-BiLSTM with Attention Mechanism 6

Short-Term Smart Grid Load Forecasting Based on CNN-BiLSTM w...

引用

6th International Conference on Energy, Power and Grid, ICEPG 2024

作者： Sun, Feihu Zhong, Yanru Guilin University of Electronic Technology School of Computer Science and Information Security Guangxi Guilin China Guilin University of Electronic Technology Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guangxi Guilin China

ISBN: (纸本)9798350377798

The existing power load data exhibits complex multidimensionality, while existing techniques often focus on learning and forecasting from single load data. To fully exploit the complex multidimensionality of the existing power load data and enhance the accuracy of short-term load forecasting, a smart grid short-term load forecasting model based on attention mechanism and CNN-BiLSTM is proposed. Firstly, the one-dimensional convolutional network (1D-CNN) slides along the temporal dimension to extract multidimensional features such as temperature and humidity from the raw power load data. Secondly, the Bidirectional Long Short-Term Memory network (BiLSTM) captures both historical and future information of the data through gate mechanisms and the bidirectional network structure. Lastly, the attention mechanism allocates weights to focus on important parts of the load sequence data, enhancing the model's ability to identify key information and further improving the accuracy of short-term power load forecasting. The method is experimented on a real-world multivariate load dataset and compared with existing learning methods. The proposed model achieved lower RMSE in 24-hour load forecasting compared to CNN-LSTM, CNN-BiLSTM, LSTM-Attention, BiLSTM-Attention and CNN-LSTM-Attention models by 13.2%, 10.6%, 6.7%, 5.7% and 5.9% respectively. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

MATL: A deep neural network using multi-scale convolutions and transformer for transcription factor binding site prediction

MATL: A deep neural network using multi-scale convolutions a...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Fan, Jinli Shen, Ruyi Huang, Xiaodi Zhang, Yanju Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China College of Computer Science and Technology Huaqiao University Xiamen China

ISBN: (纸本)9798350386226

Transcription factors bind to specific sequences of DNA known as transcription factor binding sites (TFBSs) in order to regulate gene expression. Identifying TFBSs is crucial for deciphering gene expression mechanisms, understanding in vitro life characteristics, and drug design. In recent years, many deep learning methods that utilize only the sequence features or a combination of sequence and shape features have been developed to predict TFBSs. However, these methods have not fully considered the characteristics of TFBSs, and their encoding strategies are relatively simplistic, thereby failing to capture the complex dependencies hidden within TFBSs. To address these issues, we propose a novel deep neural network model called MATL, which integrates sequence and shape features for TFBSs prediction. The model employs techniques such as multi-scale convolution and Transformer, and combines different modules for feature extraction based on the distribution patterns of different feature matrices. Additionally, we introduce transfer learning to address the issue of unsatisfactory prediction results due to insufficient training data in some datasets. As the results indicate, MATL exhibits excellent predictive performance on 165 validated ChIP-seq datasets, surpassing state-of-the-art methods. We also conducted ablation experiments on sequence encoding, feature extraction, and shape modules used in this study, and demonstrated that these modules play a positive role in predicting TFBSs. Moreover, the results also indicated that transfer learning can improve prediction accuracy for some TFBSs datasets with small amounts of data. The source code of MATL is available at https://***/LittleWhiteKing/MATL. © 2024 IEEE.

关键词： Transcription

来源：评论

学校读者我要写书评

暂无评论

A personalized test paper generation model for English examination based on knowledge tracking 5

A personalized test paper generation model for English exami...

引用

5th International Conference on Artificial Intelligence and Computer Science, AICS 2023

作者： Zhou, Ya Shao, Xiuli Huang, Guimin Guo, Qingkai Deng, Nanxiao Lin, Jianxing School of Computer Science and Information Security Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guangxi Guilin541004 China

ISBN: (纸本)9781510668621

In recent years, personalized paper grouping is a hot research topic in the field of intelligence education. In this paper, we propose an optimized deep knowledge tracking model Mul-MAKT combined with a genetic algorithm for personalized paper grouping with English practice as the target. Firstly, we use students’ records (exercise labels, response results, learning behaviors, exercise attributes) as input to the knowledge tracking model to predict students’ performance at the next moment and also to obtain students’ mastery level of knowledge points. Based on the students’ mastery levels, we adjust the students’ ability in each type of English exercise and calculate the students’ weaknesses in each type of question, so as to extract the questions from the test bank with the difficulty matching the students’ ability and containing the students’ weaknesses. © 2023 SPIE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Multimodal emotion recognition based on multilevel acoustic and textual information 5

Multimodal emotion recognition based on multilevel acoustic ...

引用

5th International Conference on Artificial Intelligence and Computer Science, AICS 2023

作者： Zhou, Ya Xing, Yuyi Huang, Guimin Guo, Qingkai Deng, Nanxiao School of Computer Science and Information Security Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guangxi Guilin541004 China

ISBN: (纸本)9781510668621

The study and application of multimodal emotion recognition have gained significant popularity in recent years, representing one of the challenging tasks in the field of affective computing. We propose a multimodal speech emotion recognition model that utilizes multiple acoustic and textual information layers. This model incorporates transcribed textual data to complement speech data and enable accurate emotion recognition. In the unimodal model, we employ AlexNet, BiGRU, and HuBERT to extract multi-layer acoustic feature information from speech, and the RoBERTa encoder to extract text features. Additionally, we perform fusion between speech and text by utilizing the co-attentive mechanism to extract complementary information across modalities and eliminate inter-modality noise. This process ultimately enhances the emotional representation of the target modality. Finally, the fused features are utilized to predict the emotion category. Our model achieved a weighted sentiment recognition accuracy of 77.41% and an unweighted accuracy of 78.66%. © 2023 SPIE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Efficient Construction of Delaunay Triangulations on Riemannian Manifolds with the Bowyer-Watson Method

Efficient Construction of Delaunay Triangulations on Riemann...

引用

2024 International Symposium on Digital Home, ISDH 2024

作者： Dejiangmo Wang, Qian Zhou, Li Zhang, Xinyun Luo, Dawei Northwest Minzu University Colleage of Mathematics and Computer Science Lanzhou China Guilin University of Electronic Technology Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China

ISBN: (纸本)9798331509873

This paper explores the application of the Bowyer-Watson algorithm for constructing Delaunay triangulations on Riemannian manifolds, with a particular focus on karst terrain and channel detection scenarios. We define geodesic disks with sufficiently small radii and demonstrate the existence of a net within these disks that allows for the construction of triangles satisfying the Delaunay condition. By analyzing the insertion of points both inside and outside of triangles, we ensure proper point placement and perform edge flips as necessary to maintain the Delaunay property. Compared to other algorithms, the Bowyer-Watson approach offers notable advantages for achieving Delau-nay triangulation on Riemannian manifolds due to its flexibility and locality. This method effectively manages complex geometric structures by adaptively adjusting the triangulation, ensuring both accuracy and efficiency in non-Euclidean spaces. It is particularly well-suited for modeling karst terrain features and detecting channels, providing a crucial theoretical foundation and practical guidance for future numerical computations and geometric modeling on curved surfaces. © 2024 IEEE.

关键词： Triangulation

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：