检索结果-内蒙古大学图书馆

International Conference on intelligent Control and Information processing (ICICIP)

作者： Sen Li Fang Li Xiaonan Luo School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China Center for Applied Mathematics of Guangxi (GUET) Guilin China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798331516147

ISBN: (纸本)9798331516154

The k-means method is widely utilized for clustering. Its simplicity, efficacy, and swiftness make it a favored choice among clustering algorithms. It faces the challenge of sensitivity to the initial class center. The enhancement strategy for the k-means algorithm focuses on refining the initial selection of cluster centroids, no longer using its random selection of initial class center points, but starting from the entire dataset, choosing the most distant point to serve as the starting cluster centroid. This can also prevent the local optimization problem of the k-means algorithm. The improved algorithm proposed in this article is an effective method that can select the initial class center point from a global perspective and reduce computation time. The suggested approach has undergone rigorous testing and comparative analysis across multiple datasets, yielding commendable outcomes.

关键词： Sensitivity Stability criteria Refining Neural networks key performance indicator Clustering algorithms Classification algorithms Optimization Testing intelligent control

来源：评论

学校读者我要写书评

暂无评论

Tomato Leaf Disease Identification and Growth Dataset Augmentation Based on UAE-GAN

Tomato Leaf Disease Identification and Growth Dataset Augmen...

引用

International Conference on intelligent Control and Information processing (ICICIP)

作者： Xin Li Fang Li Xiaonan Luo School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China Center for Applied Mathematics of Guangxi (GUET) Guilin China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798331516147

ISBN: (纸本)9798331516154

To delve into the characterization of growth disorders in different crops, it is important to support the model with a large amount of image data that includes a variety of disease types and disease levels to capture the typical and subtle differences of various diseases on plant leaves. However, the actual process of gathering data is challenging, sample coverage is challenging to accomplish, data capture is impeded, and the quality of the data is subpar. This work aims to address the issue of data shortages by employing technical methods. In particular, we creatively investigated the UAE-GAN approach, which naturally combines CycleGAN, U-Net, Variational Autoencoder VAE, and Autoencoder to increase the data. Among these, U-Net can precisely extract the small details of disease locations in crop photos and provide a strong basis for further processing thanks to its special codec architectural benefits. The Variational Autoencoder (VAE) significantly enhances the diversity of data by mapping the image to the latent space and sampling based on a certain probability distribution, so producing new image samples that are distinct from the original image yet inherently connected. Learning the coding and decoding of the original image is the foundation of autoencoders. If a mild disruption is introduced into the coding process, it can achieve data augmentation in another dimension and create a sequence of new images with just little modifications to the original image. The aforementioned models are closely linked with CycleGAN to efficiently map and convert in a variety of picture domains and to fully leverage CycleGAN's remarkable unsupervised image conversion capabilities. The perception ability, feature capture ability, and information conversion ability of the fusion model for crop image data are significantly improved, and the key elements of each link in the data enhancement process are comprehensively considered to ensure that the generated new image data can not o

关键词： Training Image coding Autoencoders Data enhancement Crops Generators Data models Stability analysis Probability distribution Diseases

来源：评论

学校读者我要写书评

暂无评论

引用

Big Data & Artificial Intelligence & Software Engineering (ICBASE), International Conference on

作者： Ya Zhou Chen Chen Guimin Huang School of Computer Science and Information Security Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798331506612

ISBN: (纸本)9798331506629

In the research methods of sentence similarity, sentence similarity is often calculated from the semantic aspect, while the influence of syntactic structure is ignored. We propose an enhanced knowledge language representation model (ExtKBRCNN) based on CNN and Bi-GRU, which effectively uses the fine-grained word relations in the knowledge base to evaluate semantic similarity and models the relationship between knowledge structure and text structure. In order to make full use of the syntactic information of the sentence, we also propose a dependency tree kernel-based method (Dep-SIF), which combines syntactic information and semantic features to evaluate syntactic similarity. Finally, we propose a comprehensive model that integrates semantic and syntactic information to comprehensively evaluate sentence similarity. Experimental results show that the accuracy of the model on the MRPC dataset is 77.63% and the F1 value is 83.90%.

关键词： Knowledge engineering Accuracy Semantics Knowledge based systems Syntactics Natural language processing Software engineering

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Grammatical Error Correction Model

Context-Aware Grammatical Error Correction Model

引用

Big Data & Artificial Intelligence & Software Engineering (ICBASE), International Conference on

作者： Jianxing Lin Guimin Huang JiaHao Wang School of Computer Science and Information Security Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798331506612

ISBN: (纸本)9798331506629

The pursuit of accurate and fluent English communication is the cornerstone of global academic exchange and expression. The accuracy of written English is crucial for effective discourse; however, despite advancements in grammatical error correction (GEC) technology, these systems often fall short when analyzing coherent text. This paper delves into the complexities of English writing and the challenges posed by current GEC systems, advocating for a shift toward understanding document-level context in error correction. We propose a dual-encoder architecture within an encoder-decoder model, referred to as the Context-Aware Grammatical Error Correction (CAGEC) model. The CAGEC model employs an innovative dual-encoder structure, combining the encoder of the Transformer model with a Bi-GRU (Bidirectional Gated Recurrent Unit) neural network, and integrates encoding into the decoder through attention and gating mechanisms to achieve a deep understanding of the source sentence and its context.

关键词： Accuracy Neural networks Writing Logic gates Transformers Encoding Error correction Context modeling Synthetic data Software engineering

来源：评论

学校读者我要写书评

暂无评论

Dynamic Student Classification with Forgetting Mechanisms on Memory Networks for Knowledge Tracing

Dynamic Student Classification with Forgetting Mechanisms on...

引用

intelligent Computing and Human-computer Interaction (ICHCI), International Conference on

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

ISBN: (数字)9798350368284

ISBN: (纸本)9798350368291

Knowledge Tracing (KT), a technique for modeling students' knowledge levels and predicting their future question-answering performance based on their historical answer data, is one of the key research areas to strengthen the ability of personalized education. In recent years, memory networks have received more and more attention and application in the field of KT, however, the current KT model based on memory networks ignores the effect of students' learning sequence on the level of forgetting, and fails to model the forgetting behavior of students in the process of learning by using the characteristics of time intervals in the interaction data. Therefore, in this paper, we propose a dynamic student classification with forgetting mechanisms on memory networks model (DSCFMN), which enhance the existing model by dynamically classifying students similar to their learning abilities at specified time intervals, incorporating forgetting factors and introducing a weight decay strategy. Experiments show that our model performs well on online education datasets, and the proposed model achieves better prediction results than existing knowledge tracking methods.

关键词： Knowledge engineering Human computer interaction Computational modeling Education Predictive models Data models

来源：评论

学校读者我要写书评

暂无评论

Multi-Dimensional Knowledge Tracing Based on Multi-Concept and Temporal Embedding

Multi-Dimensional Knowledge Tracing Based on Multi-Concept a...

引用

Digital Society and intelligent Systems (DSInS), International Conference on

作者： Xialong Wei Ya Zhou Guangxi Key Laboratory of Image and Graphic Intelligent Processing School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798331528829

ISBN: (纸本)9798331528836

Knowledge tracing is fundamental to intelligent educational systems, as it predicts future learning outcomes by analyzing learners' historical performance related to specific knowledge concepts. While advancements have been made through deep learning techniques in the knowledge tracing domain, traditional research faces two significant limitations: insufficient consideration of temporal factors, which impacts the accurate depiction of knowledge retention and mastery dynamics; and the assumption of a one-to-one correspondence between practice and a single knowledge concept, disregarding the complexity of coexisting multiple knowledge concepts. To address these issues, this paper proposes the MulTKT model, which integrates response intervals, response durations, and the synergistic effects of multiple knowledge concepts, while incorporating a temporal decay factor into the self-attention mechanism to precisely capture learning dynamics. Experimental results indicate that MulTKT more accurately represents knowledge states and predicts student performance.

关键词： Deep learning Accuracy Complexity theory intelligent systems Faces

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

A Convolutional Knowledge Tracking Model with Forgetting Beh...

引用

International Conference on Electronics and Information Technology (EIT)

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

ISBN: (数字)9798350369151

ISBN: (纸本)9798350369168

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.

关键词： Knowledge engineering Instruments Neural networks Predictive models Vectors Complexity theory Convolutional neural networks Information technology

来源：评论

学校读者我要写书评

暂无评论

intelligent Test Paper Generation Algorithm Integrating Normal Distribution and Parallel Genetic Algorithm

Intelligent Test Paper Generation Algorithm Integrating Norm...

引用

intelligent Computing and Human-computer Interaction (ICHCI), International Conference on

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

ISBN: (数字)9798350368284

ISBN: (纸本)9798350368291

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.

关键词： Human computer interaction Heuristic algorithms Gaussian distribution Genetics Genetic algorithms Distribution functions Convergence

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

AN ADVERSARIAL AND DEEP HASHING-BASED HIERARCHICAL SUPERVISED CROSS-MODAL IMAGE AND TEXT RETRIEVAL ALGORITHM

引用

International Journal of Robotics and Automation 2024年第1期39卷 77-86页

作者： Chen, Ruidong Qiang, Baohua Zhou, Mingliang Zhang, Shihao Zheng, Hong Tang, Chenghua Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China School of Computer Science Chongqing University Chongqing400044 China

With the rapid development of robotics and sensor technology, vast amounts of valuable multimodal data are collected. It is extremely critical for a variety of robots performing automated tasks to find relevant multimodal information quickly and efficiently in large amounts of data. In this paper, we propose an adversarial and deep hashing-based hierarchical supervised cross-modal image and text retrieval algorithm to perform semantic analysis and association modelling on image and text by making full use of the rich semantic information of the label hierarchy. First, the modal adversarial block and the modal differentiation network both perform adversarial learning to keep different modalities with the same semantics closest to each other in a common subspace. Second, the intra-label layer similarity loss and inter-label layer correlation loss are used to fully exploit the intrinsic similarity existing in each label layer and the correlation existing between label layers. Finally, an objective function for different semantic data is redesigned to keep data with different semantics away from each other in a common subspace, thus avoiding interference of retrieval by data of different semantics. The experimental results on two cross-modal retrieval datasets with hierarchically supervised information show that the proposed method substantially enhances retrieval performance and consistently outperforms other state-of-the-art methods. © 2024 Acta Press. All rights reserved.

关键词： Semantics

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：