检索结果-内蒙古大学图书馆

Enhancing Entity Relationship Extraction in Dialogue Texts Using Hypergraph and Heterogeneous Graph

Chinese Journal of Electronics 2025年第1期34卷 295-308页

作者： Shunmiao Zhang Siyuan Zheng Degen Huang Dan Li School of Computer Science and Mathematics Fujian University of Technology Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology School of Computer Science and Technology Dalian University of Technology Elsevier

Dialogue-based relation extraction(DialogRE) aims to predict relationships between two entities in dialogue. Current approaches to dialogue relationship extraction grapple with long-distance entity relationships in dialogue data as well as complex entity relationships, such as a single entity with multiple types of connections. To address these issues, this paper presents a novel approach for dialogue relationship extraction termed the hypergraphs and heterogeneous graphs model(HG2G). This model introduces a two-tiered structure, comprising dialogue hypergraphs and dialogue heterogeneous graphs, to address the shortcomings of existing methods. The dialogue hypergraph establishes connections between similar nodes using hyper-edges and utilizes hypergraph convolution to capture multi-level features. Simultaneously, the dialogue heterogeneous graph connects nodes and edges of different types, employing heterogeneous graph convolution to aggregate cross-sentence information. Ultimately, the integrated nodes from both graphs capture the semantic nuances inherent in dialogue. Experimental results on the DialogRE dataset demonstrate that the HG2G model outperforms existing state-of-the-art methods.

关键词： Convolution Aggregates Semantics Feature extraction Data mining

来源：评论

学校读者我要写书评

暂无评论

Explaining the better generalization of label distribution learning for classification

引用

Science China(Information Sciences) 2025年第5期68卷 348-361页

作者： Jing WANG Xin GENG School of Computer Science and Engineering Southeast University Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications(Southeast University) Ministry of Education

Label distribution learning(LDL) has shown advantages over traditional single-label learning(SLL) in many realworld applications, but its superiority has not been theoretically understood. In this paper, we attempt to explain why LDL generalizes better than SLL. Label distribution has rich supervision information such that an LDL method can still choose the sub-optimal label from label distribution even if it neglects the optimal one. In comparison, an SLL method has no information to choose from when it fails to predict the optimal label. The better generalization of LDL can be credited to the rich information of label distribution. We further establish the label distribution margin theory to prove this explanation; inspired by the theory,we put forward a novel LDL approach called LDL-LDML. In the experiments, the LDL baselines outperform the SLL ones, and LDL-LDML achieves competitive performance against existing LDL methods, which support our explanation and theories in this paper.

关键词： label distribution learning classification generalization label distribution margin label ambiguity neural network

来源：评论

学校读者我要写书评

暂无评论

A Hybrid ANN Random Forest Regression Method of Feature Extraction in Time Series Data

引用

SN computer Science 2025年第1期6卷 1-8页

作者： Rekha, M.P. Perumal, K. Department of Computer Applications School of Information Technology Madurai Kamaraj University Tamilnadu Madurai India

A time series is a logical grouping of values about time gleaned from numerous applications. The fundamental properties of the time series data (TSD) include their enormous quantity, high complexity, and traits like trend, cycle, seasonality, and irregularity. Data mining has seen a significant amount of research and development efforts due to the cumulative use of TSD. The effectiveness of various methods of data mining used for time series analysis is closely correlated to the dimension of the time series. In this proposed method, the weather forecasting dataset has been used. The dataset has more number of dimensions and it has been reduce dimensionality using Artificial Neural Network (ANN) and extract the feature with accuracy using Random Forest regression algorithm The study aims to utilize the deep learning (DL) method and feature extraction to minimize the dimensionality in time series data. The proposed approach improves the extraction's effectiveness in reaching our research's goal. The proposal seeks to minimize time series data's high dimensionality. The idea also emphasizes the importance of accurately lowering the dimensionality of time series data. The proposed Random Forest regression method with MAPE (13%), RMSE (9%), and MSE (15%) effectively decreases the dimensionality and extract the feature effectively when compared to existing techniques. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Data mining Deep learning Dimensionality reduction Random Forest Time series data

来源：评论

学校读者我要写书评

暂无评论

Unveiling factuality and injecting knowledge for LLMs via reinforcement learning and data proportion

引用

Science China(Information Sciences) 2024年第10期67卷 389-390页

作者： Wenjun KE Ziyu SHANG Zhizhao LUO Peng WANG Yikai GUO Qi LIU Yuxuan CHEN School of Computer Science and Engineering Southeast University Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications(Southeast University) Beijing Institute of Technology Zhuhai Beijing Institute of Computer Technology and Application

Large language models(LLMs) have demonstrated remarkable effectiveness across various natural language processing(NLP) tasks, as evidenced by recent studies [1, 2]. However, these models often produce responses that conflict with reality due to the unreliable distribution of facts within their training data, which is particularly critical for applications requiring high credibility and accuracy [3].

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of SDN-Assisted Fog Computing System with State-Dependent Service 7th

Performance Evaluation of SDN-Assisted Fog Computing System ...

引用

7th International Conference on Advanced Computing and Intelligent Engineering, ICACIE 2022

作者： Mishra, M.R. Goswami, Veena Patra, S.S. Barik, R. School of Computer Applications Kalinga Institute of Industrial Technology Bhubaneswar India

ISBN: (纸本)9789819950140

The exponential growth of Internet of Things devices combined with the limitations of cloud computing in terms of latency and quality of service for time-sensitive applications led to the development of a new technology called fog computing. By lowering the effective distance between IoT/end-user devices and the cloud, fog computing gets around the limitations of the cloud. Fog computing confronts issues for remote job offloading. Fog computing focuses on optimizing task offloading. One of the key ideas of fog computing is task offloading, which reduces latency and increases system efficiency. This article presents a novel analytical model that investigates state-dependent service queuing systems and the effect of state-dependent service time on the system’s overall performance. We outline some of the properties of the system, and numerical evaluations and simulations demonstrate the validity of the proposed model. The evaluation findings indicate that the proposed model achieves an acceptable level of accuracy and makes it possible to offload tasks effectively in using SDN-assisted fog computing systems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Aggregated Relative Similarity (ARS): a novel similarity measure for improved personalised learning recommendation using hybrid filtering approach

引用

Multimedia Tools and applications 2024年 1-48页

作者： Pal, Saurabh Dutta Pramanik, Pijush Kanti Choudhury, Prasenjit Department of Computer Science and Engineering National Institute of Technology Durgapur West Bengal Durgapur India School of Computer Applications and Technology Galgotias University Uttar Pradesh Greater Noida India Department of Computer Science and Engineering School of Engineering Brainware University Kolkata India

To improve the effectiveness of online learning, the learning materials recommendation is required to be personalised to the learner material recommendations must be personalized to learners. The existing approaches are ineffective in recommending learning materials according to the learner’s learning situation, the learner’s internal learning characteristics, and fitting to the learner’s preferences and learning suitability. In this work, we propose a hybrid recommendation approach cthat combines the advantages of knowledge-based and collaborative filtering approaches. The knowledge-based filtering approach enables us to find the most suitable learning materials that fit the learner’s situation and learning state by appropriately mapping the learners’ contexts with the metadata of the learning materials. We use collaborative filtering to refine learning material selection by considering learner-learner similarity. We propose a novel similarity measure, aggregated relative similarity (ARS), to determine similar learners based on implicit learner characteristics such as education, knowledge, cognitive ability, and learning style. The experimental results show that the proposed ARS algorithm outperforms popular similarity measures such as Jaccard similarity, Sorensen-Dice coefficient, and overlap coefficient. The overall recommendation performance of the proposed hybrid approach attained mean absolute error (MAE) and root mean square error (RMSE) of 0.681 and 0.9198, respectively. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Learner’s intention analysis to mitigate the cold start problem in personalized learning recommendation systems

引用

Multimedia Tools and applications 2024年 1-55页

作者： Pal, Saurabh Pramanik, Pijush Kanti Dutta Choudhury, Prasenjit Department of Computer Science and Engineering School of Engineering Brainware University Kolkata India School of Computer Applications and Technology Galgotias University Uttar Pradesh Greater Noida India Department of Computer Science & amp Engineering National Institute of Technology Durgapur West Bengal India

Understanding the learner’s requirements and status is important for recommending relevant and appropriate learning materials to the learner in personalized learning. For this purpose, the learning recommendation system must include the learner’s contextual and behavioral information. However, in the case of cold start problems, the system has no prior information about a new user. Moreover, the system cannot acquire the required information instantly because the automated and instantaneous acquisition of this information is not trivial. This hinders the personalized recommendation for a new learner. Engaging the learner in a questionnaire session may allow the learning system to acquire most of the required information. However, this makes the learner uninterested and disengaged with the system. To address this, we propose a recommendation system for personalized learning that mitigates the cold start problem by acquiring important information by analyzing the learner’s questions submitted to the learning system. By analyzing the meta-information of a question, we identified the learner’s exact requirements, domain and topic knowledge, and expected knowledge gain from the learning material. Ontology, BiLSTM, and context mapping are used for learner modelling and topic classification, and identifying suitable learning materials, respectively. Furthermore, MCDM techniques are used for ranking the learning materials. Our experimental assessment and validation suggest that the information acquired based on our proposed approach is sufficient for understanding a new learner’s needs and suitability and, accordingly, for recommending suitable personalized learning materials. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of IoST–Mist–Fog–Cloud Framework for Geospatial Crime Data Visualization: A State Dependent Queueing Approach

引用

SN computer Science 2024年第1期5卷 85页

作者： Panigrahi, Sunil K. Goswami, Veena Mund, G.B. Barik, Rabindra K. School of Computer Engineering Kalinga Institute of Industrial Technology Odisha Bhubaneswar 751024 India School of Computer Applications Kalinga Institute of Industrial Technology Odisha Bhubaneswar 751024 India

Modern Information and Communication technology, Internet of Spatial Things(IoT), cloud, fog, and mist computing enable an expansion of real-time geospatial applications in crime analysis. Due to their sensitivity to latency and QoS, these applications must process at the network’s edge, not on the central cloud servers. Mist nodes have the ability to cache low-volume geographical data that is regularly requested and then process that data using lightweight applications. Display the results of the geospatial data processing on the client’s devices or systems in accordance with their *** in the mist and fog have been the focus of a significant amount of study recently, particularly in geospatial application contexts such as crime analysis and visualization. Real-time geospatial crime data visualization can be more efficient and productive through the mist computing framework. By keeping this in mind, the present research paper proposes the IoST-Mist–Fog–Cloud framework for the visualization of crime data. With the help of this proposed framework, it visualizes the geospatial crime data through the thin client and mobile client environment. In addition to this, it provides a one-of-a-kind analytical model that investigates a state-dependent service queuing strategy using the IoST–Mist–Fog–Cloud framework and the influence of state-dependent service time on the system’s overall performance. It explains some of the system’s characteristics, and numerical evaluations and simulations validate the system’s functionality. According to the evaluation’s findings, it can attain an adequate degree of precision and successfully offload tasks when it uses the framework presented. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Cloud computing Fog computing Geospatial crime data IoST Mist computing Performance analysis Queueing model State-dependent Visualization

来源：评论

学校读者我要写书评

暂无评论

UV-Mamba: A DCN-Enhanced State Space Model for Urban Village Boundary Identification in High-Resolution Remote Sensing Images

UV-Mamba: A DCN-Enhanced State Space Model for Urban Village...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Li, Lulin Chen, Ben Zou, Xuechao Xing, Junliang Tao, Pin School of Computer Technology and Applications Qinghai University Xining China School of Computer Science and Technology Beijing Jiaotong University Beijing China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9798350368741

Due to the diverse geographical environments, intricate landscapes, and high-density settlements, the automatic identification of urban village boundaries using remote sensing images remains a highly challenging task. This paper proposes a novel and efficient neural network model called UV-Mamba for accurate boundary detection in high-resolution remote sensing images. UV-Mamba mitigates the memory loss problem in lengthy sequence modeling, which arises in state space models (SSM) with increasing image size, by incorporating deformable convolutions (DCN). Its architecture utilizes an encoder-decoder framework and includes an encoder with four deformable state space augmentation (DSSA) blocks for efficient multi-level semantic extraction and a decoder to integrate the extracted semantic information. We conducted experiments on two large datasets showing that UV-Mamba achieves state-of-the-art performance. Specifically, our model achieves 73.3% and 78.1% IoU on the Beijing and Xi'an datasets, respectively, representing improvements of 1.2% and 3.4% IoU over the previous best model while also being 6× faster in inference speed and 40× smaller in parameter count. Source code and pre-trained models are available at https://***/Devin-Egber/UV-Mamba. © 2025 IEEE.

关键词： High-Resolution Remote Sensing Images Semantic Segmentation State Space Model (SSM) Urban Village

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Privacy Protection Model in Advanced Metering Infrastructure Based on Cloud and Fog Assistance

引用

computers, Materials & Continua 2024年第8期80卷 3193-3219页

作者： Linghong Kuang Wenlong Shi Jing Zhang School of Computer Science and Mathematics Fujian University of TechnologyFuzhou350118China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fuzhou350118China

The Advanced Metering Infrastructure(AMI),as a crucial subsystem in the smart grid,is responsible for measuring user electricity consumption and plays a vital role in communication between providers and ***,with the advancement of information and communication technology,new security and privacy challenges have emerged for *** address these challenges and enhance the security and privacy of user data in the smart grid,a Hierarchical Privacy Protection Model in Advanced Metering Infrastructure based on Cloud and Fog Assistance(HPPM-AMICFA)is proposed in this *** proposed model integrates cloud and fog computing with hierarchical threshold encryption,offering a flexible and efficient privacy protection solution that significantly enhances data security in the smart *** methodology involves setting user protection levels by processing missing data and utilizing fuzzy comprehensive analysis to evaluate user importance,thereby assigning appropriate protection ***,a hierarchical threshold encryption algorithm is developed to provide differentiated protection strategies for fog nodes based on user IDs,ensuring secure aggregation and encryption of user *** results demonstrate that HPPM-AMICFA effectively resists various attack strategies while minimizing time costs,thereby safeguarding user data in the smart grid.

关键词： AMI cloud and fog assistance fuzzy comprehensive analysis hierarchical threshold encryption

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：