检索结果-内蒙古大学图书馆

A numerical magnitude aware multi-channel hierarchical encoding network for math word problem solving

Neural computing and Applications 2025年第3期37卷 1651-1672页

作者： Xu, Junjie Chen, Yuzhong Xiao, Lingsheng Liao, Hongmiao Zhong, Jiayuan Dong, Chen College of Computer and Data Science Fuzhou University Fujian Province Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fujian Province Fuzhou350108 China

Math word problem (MWP) represents a critical research area within reading comprehension, where accurate comprehension of math problem text is crucial for generating math expressions. However, current approaches still grapple with unresolved challenges in grasping the sensitivity of math problem text and delineating distinct roles across various clause types, and enhancing numerical representation. To address these challenges, this paper proposes a Numerical Magnitude Aware Multi-Channel Hierarchical Encoding network (NMA-MHEA) for math expression generation. Firstly, NMA-MHEA implements a multi-channel hierarchical context encoding module to learn context representations at three different channels: intra-clause channel, inter-clause channel, and context-question interaction channel. NMA-MHEA constructs hierarchical constituent-dependency graphs for different levels of sentences and employs a Hierarchical Graph Attention Neural network (HGAT) to learn syntactic and semantic information within these graphs at the intra-clause and inter-clause channels. NMA-MHEA then refines context clauses using question information at the context-question interaction channel. Secondly, NMA-MHEA designs a number encoding module to enhance the relative magnitude information among numerical values and type information of numerical values. Experimental results on two public benchmark datasets demonstrate that NMA-MHEA outperforms other state-of-the-art models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An Anti-Degenerative Approach for FCM Neural network Classifier in Complex Classification Tasks 23

An Anti-Degenerative Approach for FCM Neural Network Classif...

引用

6th International Conference on Big Data Technologies, ICBDT 2023

作者： Fan, Jiawei Zhang, Xiaojing Ren, Xianghui Ma, Huisheng Wei, Xinlei Zhang, Hao Yue, Yifeng The 15th Research Institute of China Electronics Technology Group Corporation Beijing100080 China Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan250022 China

ISBN: (纸本)9798400707667

In this paper, an anti-degenerative approach based on the floating centroids method (FCM) is introduced to enhance the robustness of a neural network classifier. Although a gradient-based floating centroids method (GDFC) has adopted the gradient descent method instead of evolutionary computation to optimize the FCM, this method excessively pursues maximizing inter-class distances and minimizing the intra-class distances to cause the floating centroids to degenerate into the fixed centroids, resulting in pseudo-floating centroids phenomenon. Therefore, we propose an anti-degenerative approach to solve this problem. It can soft clean up the mapping sample features on both sides of the decision boundary and forcefully recall the mapping samples close to the partition space so that a more flexible centroid distribution is generated. Experimental results show that the proposed method not only achieves excellent performance on accuracy and average f-measure in some complex classification tasks but also facilitates data visualization and dimensionality reduction. © 2023 ACM.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

A gesture recognition algorithm for smart gloves 2

A gesture recognition algorithm for smart gloves

引用

2nd International Conference on Computer Graphics, Image and Virtualization, ICCGIV 2022

作者： Cui, Hong University of Jinan School of Information Science and Engineering Jinan China Shandong Provincial Key Laboratory of Network Based Intelligent Computing Jinan250022 China

ISBN: (纸本)9781665492508

This paper proposes a gesture recognition algorithm for smart gloves. The main innovations of the method are: (a) When the slope method is used to fit the curve, the two curve equations are assumed, and then the error size of the two curves is judged, and the curve where the smaller error is located is the fitted curve. (b) Jaccard coefficient is introduced into the gesture recognition algorithm, and by comparing the trend of two gestures in the same position segmentation interval, it judges whether they are the same gesture. Compared with the previous trend determination condition[1] the determination condition is simpler and the output result is more intuitive. The experiment was conducted by this algorithm, and better experimental results were achieved. © 2022 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

DICO-NEEP: NEEP with Distance Information and Constant Optimization

DICO-NEEP: NEEP with Distance Information and Constant Optim...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Chen Liu Chaoran Pang Lin Wang Bo Yang Shandong Provincial Key Laboratory of Network Based Intelligent Computing Unversity of Jinan Jinan China Quan Cheng Laboratory Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Symbolic regression represents a critical challenge in computer science, aiming to derive accurate equations for given datasets. The classical symbolic regression algorithm, Neuro-Encoded Expression Programming (NEEP), mitigates the inherent issue of output volatility due to input perturbations caused by the discrete coding in previous evolutionary algorithms. It achieves this by converting discrete coding into continuous coding through neural networks. However, the NEEP model itself confronts two significant challenges. Firstly, it disregards the distance relationships among symbols during the mapping process, thus complicating the post-mapping search. Secondly, it neglects the issue of constant optimization, making the discovery of precise expressions challenging. Addressing these concerns, this study proposes an embedding module during pre-training to impart distance information to symbols, inspired by pre-training methodologies in Natural Language Processing (NLP). This enhancement expedites the search process. Furthermore, to tackle constant optimization challenges, this paper proposes a novel encoding approach to overcome the limitations of traditional placeholder methods that impede expressive capabilities. This new encoding facilitates constant optimization without disrupting the original equation. Experimental results substantiate a significant enhancement in the convergence of DICO-NEEP across various symbolic regression problems.

关键词： Accuracy Heuristic algorithms Neural networks Symbols Encoding Mathematical models Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Improving OPT-GAN by Smooth Scale Mapping and Adaptive Exploration

Improving OPT-GAN by Smooth Scale Mapping and Adaptive Explo...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Bo Zhang Lin Wang Bo Yang Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan China Quan Cheng Laboratory Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

In Black Box Optimization, traditional Estimation of Distribution Algorithms (EDAs) are limited by strong prior assumptions. To address this, deep generative model-based EDAs, particularly OPT-GAN using Generative Adversarial networks, show promise due to their adaptability across diverse problems. However, OPT-GAN’s search efficiency and balance between exploration and exploitation remain challenging. This study introduces an improved version of OPT-GAN. By integrating smoothing scale mapping and an adaptive exploration mechanism, it mitigates existing limitations, effectively balancing the E-E trade-off and improving search efficiency. Our experimental results, validated on the COCO benchmark, demonstrate that this improved OPT-GAN outperforms existing neural network-based optimization algorithms, highlighting its potential for wider application in complex optimization scenarios.

关键词： Adaptation models Smoothing methods Closed box Optimization methods Estimation Space mapping Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Information Filter Encoding network for Multi-Label Text Classification

Multi-Information Filter Encoding Network for Multi-Label Te...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Leping Li Kun Ma Benkuan Cui Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan China

Multi-label text classification (MLTC) is essential in natural language processing. For real applications, MLTC is challenging when class distribution is long-tailed, that is, a few of labels (head labels) have many documents while most labels (tail labels) have a few documents. In this paper, we propose a Multi-Information Filter Encoding network (MIFEN) to address the issue of long-tailed distribution. Specifically, MIFEN constructs Multi-Information Filter Encoder to filter useless information and optimize the text space and label space. Then, MIFEN enriches the tail label-related features by extracting filtered text-specific label information for each document and highlights significant features of the corresponding text and label information to generate the final document representation. Experiment results have demonstrated that our MIFEN outperforms better than the state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Resource Allocation in Edge computing to Reduce Delay based on Multi-Layer Particle Swarm Optimization

Optimizing Resource Allocation in Edge Computing to Reduce D...

引用

networks, Communications and intelligent computing (NCIC), International Conference on

作者： Xiaoman Kong Bo Yang Yamin Han Shandong Provincial Key Laboratory of Network-Based Intelligent Computing University of Jinan Jinan China Shandong Provincial Key Laboratory of Network-Based Intelligent Computing University of Jinan Jinan China Quan Cheng Laboratory Jinan Shandong China

ISBN: (数字)9798350371949

ISBN: (纸本)9798350371956

With the popularity of Internet of Things (IoT) applications and the explosion of mobile devices, the computation demands of data have increased. All compute requests are sent to a remote cloud server for processing, leading to more delay. The emergence of edge computing (EC) can store and compute data generated by network edge devices directly on that device. Nevertheless, implementing compute-intensive tasks on edge devices with limited storage and compute resources makes task allocation more challenging. The complexity of resource allocation can lead to problems such as system performance degradation and time delay. This paper proposes a resource allocation strategy optimized by multi-layer particle swarm optimization (MLPSO) for edge computing to reduce delay. First, we adopt an EC scenario where multiple mobile users are allocated to multiple edge servers dynamically. Then, to construct the delay minimization model, a non-orthogonal multiple access (NOMA) protocol and resource allocation strategy are adopted, which considers the interference between channels. Finally, the delay minimization model is optimized by using MLPSO, that have great potential to help particle swarms jump out of local optima, enhancing the ability to obtain optimal resource allocation strategy for EC. The simulation results, along with comparisons to other methods, clearly demonstrate the effectiveness of the proposed approach in significantly reducing the delay of the EC model.

关键词： Computational modeling Delay effects Simulation Minimization Delays Resource management Servers

来源：评论

学校读者我要写书评

暂无评论

HybridFL: Hybrid Approach Toward Privacy-Preserving Federated Learning 6th

HybridFL: Hybrid Approach Toward Privacy-Preserving Federate...

引用

6th International Conference on Security and Privacy in New computing Environments, SPNCE 2023

作者： Ali, Sheraz Mamoon, Saqib Usman, Areeba Abidin, Zain ul Zhao, Chuan School of Information Science and Engineering University of Jinan Jinan250022 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China University of Sargodha Sargodha Pakistan Shandong Provincial Key Laboratory of Network-Based Intelligent Computing University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Software Engineering University of Jinan Jinan250022 China

ISBN: (纸本)9783031736988

In this study, we introduce a novel Hybrid Federated Learning (HybridFL) approach aimed at enhancing privacy and accuracy in collaborative machine learning scenarios. Our methodology integrates Differential Privacy (DP) and secret sharing techniques to address inference risks during training and protect against information leakage in the output model. Drawing inspiration from recent advances, we present a HybridFL framework that combines the strengths of Homomorphic Encryption (HE) and Multi-Party Computation (MPC) to achieve secure computation without the computational overhead of pure HE methods. Our contributions include a privacy-preserving design for Federated Learning (FL) that ensures local data privacy through secret sharing while leveraging DP mechanisms for noise addition. The system offers resilience against unreliable participants and is evaluated using various machine learning models, including Convolutional Neural networks (CNN), Multi-Layer Perceptrons (MLP), and linear regression. Furthermore, we address potential external threats by deploying predictive model outputs as robust services against inference attacks. Experimental results demonstrate improved accuracy and convergence speed, establishing the viability of HybridFL as an effective solution for collaborative machine learning with enhanced privacy guarantees. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

3D Freehand Tracking based on Relevancy Among Local Motion Models

引用

Chinese Journal of Electronics 2023年第3期22卷 530-536页

作者： FENG Zhiquan YANG Bo ZHENG Yanwei XU Tao School of Information Science and Engineering University of Jinan Jinan China Provincial Key Laboratory for Network Based Intelligent Computing Jinan China

A novel 3D freehand tracking algorithm based on relevancy among local motion models is put forward. Firstly, a specification of the Cognitive and behavioral model (CBM) called PAMT is proposed. Secondly, we regard PAMT as a data structure upon which freehand tracking algorithm is designed, and we describe the PAMT in detail. Lastly, the experimental results are provided. The proposed algorithm is tested in a virtual assembly platform and two other application systems. The highlights of this paper are as follows: (1) A new cognitive and behavioral model, called PAMT, is presented; (2) The PAMT is explained with cognitive model; (3) Focus on describing ‘Attractor’ in PAMT with the relevancy among local motion models; (4) Shows us how the PAMT is shaped and used to design the 3D freehand tracker. One of the advantages of PAMT and RLMM model is that it is easier to explore some of the complex correlations among the variables of the 3D hand model. Our experimental results show that, compared with the particle filter and the annealed particle filter, our algorithm effectively reduces dimensionality and can track 3D hand in real-time.

关键词： Solid modeling Three-dimensional displays Correlation Annealing Tracking Data structures Particle filters

来源：评论

学校读者我要写书评

暂无评论

3D Vision Transformer for Postoperative Recurrence Risk Prediction of Liver Cancer

3D Vision Transformer for Postoperative Recurrence Risk Pred...

引用

International Conference on Image, Vision and intelligent Systems, ICIVIS 2021

作者： Li, Fan Zhou, Xueying Gao, Xizhan Zhao, Hui Niu, Sijie School of Information Science and Engineering University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Network-Based Intelligent Computing Jinan250022 China

ISBN: (纸本)9789811669620

Hepatocellular carcinoma (HCC) is a kind of malignant tumor with a high fatality rate, and it has a serious impact on the patient’s normal life. Although the diagnostic scheme for liver cancer has been gradually improved in recent years, the prognosis of patients with liver cancer is still not very ideal. Due to the high recurrence rate and poor prognosis after surgery, intrahepatic metastasis plays an important role in the survival cycle of patients with liver cancer, which is also a significant guiding factor in the selection of preoperative treatment and the planning of postoperative follow-up. In this paper, a classification method based on 3D Vision Transformer is proposed to determine whether intrahepatic metastasis occurs after the operation. Specifically, in this study, 161 patients who were diagnosed as HCC by puncture pathology or clinical diagnosis and received Transcatheter Arterial Chemoembolization (TACE) treatment were selected as the study subjects, and the patients were divided into non-metastasis group (79 cases) and intrahepatic metastasis group (82 cases). By comparing 3D Vision Transformer with the 3D forms of multiple deep learning classification models, the predictive value of 3D Vision Transformer in predicting intrahepatic metastasis after transarterial chemoembolization in HCC patients was verified. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Pathology

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：