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

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

DNN-STACK: a stacking technique based on deep neural network for detecting copy-move forgery

引用

Neural Computing and applications 2025年第6期37卷 4989-5004页

作者： Krishnalal, G. Jagathy Raj, V.P. Madhu, G. Arun, K.S. School of Engineering Cochin University of Science and Technology Kerala Cochin682022 India School of Management Studies Cochin University of Science and Technology Kerala Cochin682022 India Department of Computer Applications Cochin University of Science and Technology Kerala Cochin682022 India

In recent years, detecting image forgery has become an important topic because of the availability of efficient and sophisticated image-editing software. Copy-move forgery, which involves copying a section of an image and pasting it to a different location inside the same image, is one of the most popular tampering techniques that alter the identity of a given image. This paper presents DNN-STACK, a deep neural network-based stacking scheme to identify copy-move forgery by effectively combining the predictions yielded by different base-level models. To extract hierarchical representations from the given images and generate base-level predictions, the proposed approach uses five distinct but complementary deep learning-based base-level models. After that, a consensus prediction is generated using the proposed DNN-STACK model, which can infer the nonlinear relationship between the base-level predictions. Experimental evaluation on three publicly available datasets, such as MICC-F600, MICC-F2000, and FAU, reveals the fact that the proposed DNN-STACK model outperforms the existing forgery detection techniques, significantly improving detection accuracy across varying image resolutions and attack types, including rotation, scaling, noise, and compression levels. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

An Arrhythmia Intelligent Recognition Method Based on a Multimodal Information and Spatio-Temporal Hybrid Neural Network Model

引用

computers, Materials & Continua 2025年第2期82卷 3443-3465页

作者： Xinchao Han Aojun Zhang Runchuan Li Shengya Shen Di Zhang Bo Jin Longfei Mao Linqi Yang Shuqin Zhang School of Computer Science Zhongyuan University of TechnologyZhengzhou450007China International Joint Laboratory for AI Interpretability and Reasoning Applications Zhengzhou450007China School of Foreign Languages Zhengzhou University of Economics and BusinessZhengzhou450099China

Electrocardiogram (ECG) analysis is critical for detecting arrhythmias, but traditional methods struggle with large-scale Electrocardiogram data and rare arrhythmia events in imbalanced datasets. These methods fail to perform multi-perspective learning of temporal signals and Electrocardiogram images, nor can they fully extract the latent information within the data, falling short of the accuracy required by clinicians. Therefore, this paper proposes an innovative hybrid multimodal spatiotemporal neural network to address these challenges. The model employs a multimodal data augmentation framework integrating visual and signal-based features to enhance the classification performance of rare arrhythmias in imbalanced datasets. Additionally, the spatiotemporal fusion module incorporates a spatiotemporal graph convolutional network to jointly model temporal and spatial features, uncovering complex dependencies within the Electrocardiogram data and improving the model’s ability to represent complex patterns. In experiments conducted on the MIT-BIH arrhythmia dataset, the model achieved 99.95% accuracy, 99.80% recall, and a 99.78% F1 score. The model was further validated for generalization using the clinical INCART arrhythmia dataset, and the results demonstrated its effectiveness in terms of both generalization and robustness.

关键词： Multimodal learning spatio-temporal hybrid graph convolutional network data imbalance ECG classification

来源：评论

学校读者我要写书评

暂无评论

Wavelet-Enhanced Deep Learning Ensemble for Accurate Stock Market Forecasting: A case study of Nifty 50 Index

引用

IEEE Access 2025年 13卷 87036-87047页

作者： Singh, Priya Jha, Manoj Patel, Harshita Maulana Azad National Institute of Technology Department of Mathematics Bioinformatics & Computer Applications Bhopal 462003 India Vellore Institute of Technology School of Computer Science Engineering and Information Systems Vellore India

Portfolio theory underpins portfolio management, a much-researched yet uncharted field. Stock market prediction is a challenging and essential endeavour in financial research, owing to the nonlinear, volatile, and stochastic characteristics of financial time series data. Conventional statistical techniques often fall short to encapsulate complex interdependencies, resulting in diminished predictive accuracy. This research proposes an ensemble model that integrates Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), and Temporal Convolutional Networks (TCN) for effective stock market prediction. The Nifty 50 index dataset is utilized for the empirical evidences. Wavelet-based denoising is utilised as a preprocessing measure to mitigate the intrinsic noise in stock market data. The model’s efficacy is assessed utilising error metrics, such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R²). The five-fold cross-validation is utilized to establish the robustness of the models. Furthermore, we ascertain the statistical significance of performance enhancements by parametric t-tests, including normality assessments via the Shapiro-Wilk test. Moreover, current state-of-the-art models advocates in favour of proposed study. © 2013 IEEE.

关键词： CNN Ensemble learning LSTM Random Forest Statistical Analysis Stock Market TCN

来源：评论

学校读者我要写书评

暂无评论

Improving chart question answering through integration of figure captions and visual-textual co-attention

引用

Journal of Electronic Imaging 2025年第2期34卷

作者： Agrawal, Mayank Jalal, Anand Singh Sharma, Himanshu GLA University Mathura Department of Computer Engineering and Applications Uttar Pradesh Mathura India Devi Ahilya Vishwavidyalaya School of Computer Science and Information Technology Madhya Pradesh Indore India

The proposed work for chart question answering (CQA) addresses crucial aspects particularly those associated with questions requiring complex reasoning and visual references to charts and those related to optical character recognition (OCR) noise. Existing methods focused majorly on image features, neglecting the unique characteristics of the visual representation which consequently not able to answer complex reasoning questions. The proposed model employs structural embedding, question embedding, and visual-textual co-attention to address complex reasoning questions, effectively capturing the robust correlation between visual and textual features. The incorporation of the reading component and visual component using bidirectional encoder representations from transformers (BERT) encoding leverages both textual and visual information which overcomes the OCR noise-related issue. Furthermore, the proposed model uses the knowledge acquired during the image captioning task. Moreover, experiments are conducted on five datasets: data visualization question answering (DVQA), FigureQA, PlotQA, LEAFQA++, and ChartQA which makes the assessment robust and generalized. The overall accuracy of our model is increased by 1.17% compared with structure-based transformers with localization for chart question answering (STL-CQA) on Test-Familiar of DVQA, 0.57% compared with PReFIL on FigureQA, 8.16% compared with Plot-QA, 2.33% compared with STL-CQA Test-Familiar Split of LEAFQA++, and 0.79% compared with ChartLlama on ChartQA, which shows the effectiveness and superiority of the proposed model over existing methods on these datasets. © 2025 SPIE and IS&T.

关键词： chart question answering co-attention image captioning self-attention

来源：评论

学校读者我要写书评

暂无评论

Leveraging Big Data Analytics and Applied Mathematics for Predictive Maintenance in Industrial Automation Systems 4

Leveraging Big Data Analytics and Applied Mathematics for Pr...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Lungu, Nelson Patra, Sudhansu Shekhar Dash, Bibhuti Bhusan De, Utpal Chandra National Institute of Public Administration Information Communication Technology Lusaka Zambia Deemed to Be University School of Computer Applications Odisha Bhubaneswar India

ISBN: (纸本)9798331523923

Predictive maintenance of industrial automation systems has attracted much interest recently, owing to the potential benefits of reducing downtime and improving production efficiency. However, existing solutions are affected by many different types of problems, such as managing heterogeneous and huge-scale data from dispersed industrial sensors, realising real-time analysis in high-speed data streams, and, at the same time, preserving interpretability while employing advanced techniques like deep learning and distributed machine learning. The recent approaches also use deep neural networks for fault detection and anomaly-based models for early warning signal identification with federated learning to ensure privacy-preserving data sharing. These have inherent complications such as a high rate of false positives and data imbalance handling difficulty;besides that, it is not flexible enough with the changing dynamics of the industrial processes. This paper addresses these limits by introducing an innovative architecture that merges big data analytics with applied mathematics to enhance predictive maintenance tasks effectively. To this end, one integrates machine-learning models with physics-based models across diverse datasets to enhance prediction accuracy while reducing false alarms and thus enabling proactive maintenance scheduling. In so doing, this approach will aim at shattering the present system's weaknesses by delivering robust anomaly detection along with decreased operational expenses in a scalable manner, thereby playing an important role towards further smarter, self-configurable manufacturing within the Industry 4.0 movement. © 2025 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

SMS Spam Detection using Advance Naive-Bayes Approach

SMS Spam Detection using Advance Naive-Bayes Approach

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Arora, Yojna Gupta, Neha Rathore, Yogesh Singh Bansal, Nidhi Mehta, Aina Chadha, Shikha Kumar, Ashwani Sharda University Department of Computer Science and Engineering Greater Noida India Symbiosis University of Applied Sciences School of Computer Science & Information Technology Madhya Pradesh Indore India Sharda University School of Engineering and Technology Department of Computer Science and Applications Uttar Pradesh Greater Noida India School of Engineering and Technology Department of Computer Science & Engineering Haryana Faridabad India Bennett University School of Computer Science Engineering and Technology India

ISBN: (纸本)9798331508685

Recently, with increased use of mobile phones, it has transformed into a multibillion-dollar Short Message Service or SMS. However, the drop in the cost of messaging services has led to an increased number of unsolicited commercial messages, or spam, being delivered to mobile phones. Several reasons exist for which traditional algorithms used in email filtering may not efficiently classify the spam in SMS such as the absence of strong SMS spam databases, with the short length and features of the message, the informal language used, etc. This paper uses a real SMS spam database After preprocessing the data and extraction of relevant features, Naïve Bayes machine learning techniques is applied to get the results. Then it is analyzed using confusion matrix, accuracy, precision and recall values. A learning curve with clearly defined relationship between the training and testing data set and overall error at the end. © 2025 IEEE.

关键词： Adversarial machine learning

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：