检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wang, Fanyu Zhu, Hangyu Xie, Zhenping The School of Artificial Intelligence and Computer Science the Jiangsu Key Laboratory of Media Design and Software Technology Jiangnan University Jiangsu Wuxi214122 China

Deep learning has shown promising performance on various machine learning tasks. Nevertheless, the uninterpretability of deep learning models severely restricts the usage domains that require feature explanations, such as text correction. Therefore, a novel interpretable deep learning model (named AxBERT) is proposed for Chinese spelling correction by aligning with an associative knowledge network (AKN). Wherein AKN is constructed based on the co-occurrence relations among Chinese characters, which denotes the interpretable statistic logic contrasted with uninterpretable BERT logic. And a translator matrix between BERT and AKN is introduced for the alignment and regulation of the attention component in BERT. In addition, a weight regulator is designed to adjust the attention distributions in BERT to appropriately model the sentence semantics. Experimental results on SIGHAN datasets demonstrate that AxBERT can achieve extraordinary performance, especially upon model precision compared to baselines. Our interpretable analysis, together with qualitative reasoning, can effectively illustrate the interpretability of AxBERT. © 2025, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Validating the Integrity for Deep Learning Models Based on Zero-Knowledge Proof and Blockchain 1st

Validating the Integrity for Deep Learning Models Based on Z...

引用

1st Conference on Blockchain and Web3.0 technology Innovation and Application, BWTAC 2024

作者： Zhan, Qianyi Liu, Yuanyuan Xie, Zhenping Liu, Yuan Jiangsu Key Laboratory of Media Design and Software Technology Jiangnan University Wuxi China School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China

ISBN: (纸本)9789819794119

With the development of MLaaS in recent years, the integrity and data security have also faced challenges. Ensuring the consumers receive correct services and safeguarding the data security is important. In this paper, we designed algorithms for each module, using depthwise separable convolution to optimize the convolution module and using the minimum polynomial method to optimize the circuit design of the activation function. Additionally, this paper proposes the SSHC algorithm for deeper network connections and combines blockchain to verify the correctness of the proofs. The experimental results demonstrate that our approach reduces proof time by 54.6% and storage by 58.1% compared to the original solution, while maintaining high efficiency and practicality. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Rule-based Differentiable Representation Learning

arXiv

引用

arXiv 2025年

作者： Zhang, Wei Deng, Zhaohong Wang, Guanjin Choi, Kup-Sze School of Artificial Intelligence and Computer Science Nantong University Nantong226019 China School of Artificial Intelligence and Computer Science Jiangnan University Wuxi214122 China School of Artificial Intelligence and Computer Science Jiangnan University Jiangsu Key Laboratory of Media Design and Software Technology Wuxi214122 China School of Information Technology Murdoch University WA Australia The Centre for Smart Health The Hong Kong Polytechnic University Hong Kong

Representation learning has emerged as a crucial focus in machine and deep learning, involving the extraction of meaningful and useful features and patterns from the input data, thereby enhancing the performance of various downstream tasks such as classification, clustering, and prediction. Current mainstream representation learning methods primarily rely on non-linear data mining techniques such as kernel methods and deep neural networks (DNNs) to extract abstract knowledge from complex datasets. However, most of these methods are black-box, lacking transparency and interpretability in the learning process, which constrains their practical utility. To this end, this paper introduces a novel representation learning method grounded in an interpretable fuzzy rule-based model. Specifically, it is built upon the Takagi-Sugeno-Kang fuzzy system (TSK-FS) to initially map input data to a high-dimensional fuzzy feature space through the antecedent part of the TSK-FS. Subsequently, a novel differentiable optimization method is proposed for the consequence part learning which can preserve the model’s interpretability and transparency while further exploring the nonlinear relationships within the data. This optimization method retains the essence of traditional optimization, with certain parts of the process parameterized corresponding differentiable modules constructed and a deep optimization process implemented. Consequently, this method not only enhances the model’s performance but also ensures its interpretability. Moreover, a second-order geometry preservation method is introduced to further improve the robustness of the proposed method. Extensive experiments conducted on various benchmark datasets validate the superiority of the proposed method, highlighting its potential for advancing representation learning methodologies. © 2025, CC BY-NC-ND.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Blockchain Based System for Secure Production Information Management 8

Blockchain Based System for Secure Production Information Ma...

引用

8th International Conference on Communication, Image and Signal Processing, CCISP 2023

作者： Yuanyuan, Liu Qianyi, Zhan Zhenping, Xie Yuan, Liu College of Artificial Intelligence and Computer Jiangnan University WuXi China Jiangnan University Jiangsu Key Laboratory of Media Design and Software Technology WuXi China Jiangnan University Jiangsu Key Laboratory of Media Design and Software WuXi China

ISBN: (纸本)9798350305838

In the field of production, the collection, transmission, and storage of production information have a significant impact on production management. This paper proposes a blockchain-based secure production information storage and management system to address the issues of incomplete information collection, unreliable data transmission, and data isolation in traditional production information management systems. The system leverages the immutability and decentralization properties of blockchain technology to enable secure and efficient storage and transmission of the data. Moreover, a 'step-hyperledger' structural mode is established for various business links in the pre-production, during-production, and post-production processes of safety production to achieve hierarchical management of data storage and full-process traceability. Combined with big data analysis techniques, the system facilitates effective pre-warning and efficient accountability after an incident. Simulation experiments and stress tests are conducted to validate the traceability interface of the system. The results indicate that the system demonstrates good stability even under the condition of multiple concurrent users, meeting the expected requirements and exhibiting certain advantages over traditional safety production systems. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

A text classification model for hypergraph convolutional neural networks with multi-feature fusion 4

A text classification model for hypergraph convolutional neu...

引用

4th International Conference on Artificial Intelligence and Electromechanical Automation, AIEA 2023

作者： Wang, Keyao Xia, Hongbin Liu, Yuan School of Digital Media Jiangnan University Wuxi214122 China Jiangsu Key Laboratory of Media Design and Software Technology Wuxi214122 China

ISBN: (纸本)9781510666412

To address the problem, existing graph neural network-based text classification models can only effectively learn pairwise binary relationships between words while ignoring the multivariate higher-order relationships between phrases and their inadequate representation of semantic information and local features in the text context. This paper proposes a text classification model for hypergraph attention networks with multi-feature fusion. Firstly, this paper learns multivariate higher-order relations between words by introducing a hypergraph structure instead of the original graph structure. Second, this paper constructs sequential hypergraphs, syntactic hypergraphs, and semantic hypergraphs based on textual information to enrich the textual representation of the graph neural network, thus compensating for the inadequate information representation of the graph neural network. A dual graph attention neural network is then used to learn the embedding representation of word nodes in the hypergraph and the embedding representation of relational hyperedges, respectively. At the same time, an attention-based text pooling module is used to extract discriminative and critical word nodes to help the graph neural network capture the deep local feature information of the text so that the model can better represent the text information. Finally, an adaptive fusion method fuses the three different types of text features to generate a final text feature representation for more effective text classification. The accuracy of this paper's approach on the publicly available datasets Ohsumed, R8, R56, MR, and 20NG reached 71.22%, 98.42%, 96.55%, 79.82%, and 88.32%, respectively, and the experimental results all outperformed the compared baseline models. © 2023 SPIE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Particle Swarm Optimization Algorithm for Container Deployment 5

Particle Swarm Optimization Algorithm for Container Deployme...

引用

2020 5th International Conference on Intelligent Computing and Signal Processing, ICSP 2020

作者： Wu, Libin Xia, Hongbin School of Digital Media Jiangnan University Wuxi JIANGSU214122 China Jiangsu Key Laboratory of Media Design and Software Technology Wuxi JIANGSU214122 China

In recent years, with the development of cloud computing, virtualization technology has received widespread attention. As a new representative of virtualization technology, containers have been widely used in software development, operation and maintenance, testing and other aspects, such as microservices and Docker Cloud. In cloud data centers, containers have gradually replaced virtual machines (VMs) as a new carrier for cloud tasks. However, with the increasing number of cloud products, the scale of tasks requested by users in cloud data centers continues to expand. The economic cost of tasks in the process of containerized deployment has become a concern of various cloud service vendors. The container deployment cost usually includes the data exchange cost, the image pull cost and the server energy cost. In order to solve the containerized deployment of application tasks in the container cloud environment with the lowest possible container deployment cost, this paper proposes a new cost calculation model in a container cloud environment, and then presents an improved particles swarm algorithm, namely a particle swarm optimization (PSO) algorithm for container deployment (CD-PSO) to provide the best solution for application task loading. Experimental results show that the proposed algorithm has a lower deployment cost than other scheduling algorithms. © 2019 Published under licence by IOP Publishing Ltd.

关键词： Electronic data interchange

来源：评论

学校读者我要写书评

暂无评论

A new method to analyze visual efficiency in interactive web environment

A new method to analyze visual efficiency in interactive web...

引用

2023 International Conference on Computer Graphics, Artificial Intelligence, and Data Processing, ICCAID 2023

作者： Lv, Wen Li, Tingting Xie, Zhenping School of Artificial Intelligence and Computer Science Jiangnan University China Jiangsu Key Laboratory of Media Design and Software Technology China

ISBN: (纸本)9781510677685

Interactive web interfaces are widely used, yet users often struggle to discover important and useful information. Psychologists have pointed out that in the process of human visual perception, the global topological characteristics of objects will be perceived first. In this study, we propose a cognitive experiment system to explore what object properties affect visual efficiency in interactive web environments. Our experimental results showed that, first, if a small number of colors are allocated to different objects, these objects could be more effectively memorized than no color or too many colors. Second, in static single-page, different topology structures will not cause apparently different visual attraction, however, topological structural differences could be stronger memorized. Third, in dynamic HTML, the motion changes will induce stronger visual attention and memory intensity, than their own topology changes. Subsequently, we verified the feasibility of the experiment system in real webpages and demonstrated that the above results can theoretically guide better web interaction design works with less cognitive load of users, higher operation efficiency and more natural user experience. In addition, some design reference suggestions are also provided in our study. © 2024 SPIE.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

mdixon-based synthetic ct generation via patch learning 2nd

mdixon-based synthetic ct generation via patch learning

引用

2nd EAI International Conference on Multimedia technology and Enhanced Learning, ICMTEL 2020

作者： Song, Xin Zheng, Jiamin Fan, Chao Yu, Hongbin School of Digital Media Jiangnan University Wuxi214122 China Jiangsu Key Laboratory of Media Design and Software Technology Jiangnan University Wuxi214122 China

ISBN: (纸本)9783030511029

We proposed a new method for generating synthetic CT on abdomen from modified Dixon (mDixon) MR data of abdomens to address the challenges of PET/MR attenuation correction (AC). AC is necessary in process of PET/MR but MR data lack photon attenuation, thus multiple methods are proposed to generate synthetic CT. However, these existing methods requires advantaged MR sequences which needs fine acquisition and huge cost consumption. To address this problem, we proposed a new method for generating synthetic CT using Patch Learning (SCG-PL). Global model of SCG-PL is transfer learning and patch model is semi-supervised classification. The advantages of our method can be summarized into two points. (1) Patch learning is a gradual learning process with gradually updating global model on remodeling patch model, so our SCG-PL method is gradually capable of generating synthetic CT. (2) Semi-supervised classification adopted in the process of patch learning, only small amount of labeled data is needed in SCG-PL, which greatly reduced the workload of radiologists. The experimental results indicate that proposed SCG-PL method can effectively generate synthetic CT image from challenging abdomen images using mDixon MR sequence data only. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2020.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Influence Maximization Based on True Threshold in Social Networks 3rd

Influence Maximization Based on True Threshold in Social Net...

引用

3rd EAI International Conference on Multimedia technology and Enhanced Learning, ICMTEL 2021

作者： Hao, Wei Zhan, Qianyi Liu, Yuan School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China Jiangsu Key Laboratory of Media Design and Software Technology Wuxi China

ISBN: (纸本)9783030825614

As E-marketing based on online social networks develops fast, the influence maximization problem draws attention from both academics and industries. This problem focuses on which subset of users should be selected as seed users so that based on the specific information diffusion model, the advertising companies can maximize word-of-mouth effect. Exisiting related work assume there is no cost to choose these seed users, or the cost is given in the problem setting. While in real situation, it is crucial but difficult to elicit users’ true attitude over being seeds. Moreover, we notice "threshold" as users’ private information in the Linear Threshold model can represent individual’s preference. Thus we propose a new model in which users, willing to be seeds, are asked to report their threshold information. The method called TREE is designed to solve this model, especially the payment mechanism should make sure all users tell truth. Experiments on real social network data to verify the effectiveness of TREE. © 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

No-Reference Stereoscopic Video Quality Assessment Based on Tchebichef Moment 14

No-Reference Stereoscopic Video Quality Assessment Based on ...

引用

14th International Conference on Digital Image Processing, ICDIP 2022

作者： Chen, Yuxin Wen, Mingyang School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China Jiangsu Key Laboratory of Media Design and Software Technology Jiangnan University Wuxi214122 China

ISBN: (纸本)9781510657564

We propose a no-reference (NR) stereoscopic video quality assessment (SVQA) model based on Tchebichef moment in this paper. Specifically, we extract keyframes according to mutual information between adjacent frames, and then the extracted keyframes are segmented to patches to calculate low-order Tchebichef moments. Since the strong description ability of Tchebichef moment, and different order of Tchebichef moment can represent independent features with minimal information redundancy, we extract statistical features of Tchebichef moment on computed patches as spatial features. Considering the influence of distortions in spatiotemporal domain to video quality, we use the three-dimensional derivative of Gaussian filters to calculate the spatiotemporal energy responses and extract statistical features from the responses as spatiotemporal features. Finally, we combine the spatial and spatiotemporal features to predict the quality of stereoscopic videos. The proposed model is evaluated on the NAMA3DS1-COSPAD1, SVQA and Waterloo IVC phase I databases. The experimental results show that the proposed model achieved competitive performance as compared with existing SVQA models. © 2022 SPIE.

关键词： Stereo image processing

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：