检索结果-内蒙古大学图书馆

2nd International Conference on Speech and Language Technologies for Low-Resource Languages, SPELLL 2023

作者： Anil Rahood, Pratik Kumaresan, Prasanna Kumar Chakravarthi, Bharathi Raja School of Computer Science University of Galway Galway Ireland Insight SFI Research Centre for Data Analytics University of Galway Galway Ireland

ISBN: (纸本)9783031584947

Depression presents a significant global mental health challenge affecting countless individuals across the globe. Early detection is of paramount importance, yet conventional methods, such as self-reporting and professional evaluations, possess inherent limitations and subjectivity. With the proliferation of social media and the abundance of user-generated content, novel approaches employing transformer-based models and text-mining techniques hold the potential to reveal signs of depression within social media text. This study delves into the efficacy of transformer-based models and natural language processing techniques in recognizing depressive symptoms within social media text. Social media serves as a distinct window into mental well-being, and this investigation explores the utilization of advanced transformers to tackle this issue. Results indicate that transformers trained on imbalanced datasets outperform those employing data augmentation techniques, like SMOTE, due to their proficiency in discerning intricate patterns and sensitivity to synthetic data. Furthermore, the ensemble model, which amalgamates predictions from multiple transformer models, surpasses individual models, underscoring the potential of harnessing the diverse strengths of these models for enhanced depression classification. Despite certain limitations and privacy considerations, leveraging social media data for early depression detection shows promise in improving the well-being of affected individuals through timely intervention and treatment. Subsequent research endeavors should prioritize hyperparameter optimization and the acquisition of more balanced datasets to further enhance the accuracy and dependability of depression diagnosis via the analysis of social media text. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Masked Theme-Specific Named Entity Recognition Assisted with Large Language Models

Masked Theme-Specific Named Entity Recognition Assisted with...

引用

2024 IEEE International Conference on Computing, ICOCO 2024

作者： Ying, Zhao Weiyu, Chen Longlong, Liao Jie, Liu Hong Kong Quantum AI Lab The University of Hong Kong China School of Computer and Data Science Fuzhou University Fuzhou China

ISBN: (纸本)9798331530303

Existing Named Entity Recognition (NER) methods are required to label relevant samples and train the concrete NER models. Due to the specification of theme-specific documents, these NER models are considerably hard to identify potential theme-specific entities. To address this challenge, we propose an effective two-stage approach of masked theme-specific NER associated with Large Language Models (LLMs), which uses the unsupervised mechanism rather than the supervised one. The approach involves theme-specific entity ontology construction and masked NER in heterogeneous documents. The first stage is associated with LLMs and Wikipedia category pages, and the second one is implemented with the masked NER based on the created ontology in the first stage. Extensive experimental results suggest that the proposed masked NER can precisely locate the known entities in the theme-specific entity ontology while improving the accuracy of NER in the remaining text. Compared to the mainstream NER frameworks such as spaCy 3, the masked NER can identify more valid entities in the input Markdown text and continuously use the newly detected unknown entities to update the created ontology. ©2024 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Boosting Graph Convolution with Disparity-induced Structural Refinement 25

Boosting Graph Convolution with Disparity-induced Structural...

引用

34th ACM Web Conference, WWW 2025

作者： Huang, Sujia Pi, Yueyang Zhang, Tong Liu, Wenzhe Cui, Zhen Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China Fuzhou University College of Computer and Data Science Fuzhou China Huzhou University School of Information Engineering Huzhou China Beijing Normal University School of Artificial Intelligence Beijing China

ISBN: (纸本)9798400712746

Graph Neural Networks (GNNs) have expressed remarkable capability in processing graph-structured data. Recent studies have found that most GNNs rely on the homophily assumption of graphs, leading to unsatisfactory performance on heterophilous graphs. While certain methods have been developed to address heterophilous links, they lack more precise estimation of high-order relationships between nodes. This could result in the aggregation of excessive interference information during message propagation, thus degrading the representation ability of learned features. In this work, we propose a Disparity-induced Structural Refinement (DSR) method that enables adaptive and selective message propagation in GNN, to enhance representation learning in heterophilous graphs. We theoretically analyze the necessity of structural refinement during message passing grounded in the derivation of error bound for node classification. To this end, we design a disparity score that combines both features and structural information at the node level, reflecting the connectivity degree of hopping neighbor nodes. Based on the disparity score, we can adjust the aggregation of neighbor nodes, thereby mitigating the impact of irrelevant information during message passing. Experimental results demonstrate that our method achieves competitive performance, mostly outperforming advanced methods on both homophilous and heterophilous datasets. © 2025 Copyright held by the owner/author(s).

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A federated learning scheme meets dynamic differential privacy

引用

CAAI Transactions on Intelligence Technology 2023年第3期8卷 1087-1100页

作者： Shengnan Guo Xibin Wang Shigong Long Hai Liu Liu Hai Toong Hai Sam State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyangChina School of Big Data Key Laboratory of Electric Power Big Data of Guizhou ProvinceGuizhou Institute of TechnologyGuiyangChina School of Information Guizhou University of Finance and EconomicsGuiyangChina Faculty of Business and Communication INTI International UniversityNilaiMalaysia

Federated learning is a widely used distributed learning approach in recent years,however,despite model training from collecting data become to gathering parameters,privacy violations may occur when publishing and sharing models.A dynamic approach is pro-posed to add Gaussian noise more effectively and apply differential privacy to federal deep ***,it is abandoning the traditional way of equally distributing the privacy budget e and adjusting the privacy budget to accommodate gradient descent federation learning dynamically,where the parameters depend on computation derived to avoid the impact on the algorithm that hyperparameters are created *** also incorporates adaptive threshold cropping to control the sensitivity,and finally,moments accountant is used to counting the∈consumed on the privacy‐preserving,and learning is stopped only if the∈_(total)by clients setting is reached,this allows the privacy budget to be adequately explored for model *** experimental results on real datasets show that the method training has almost the same effect as the model learning of non‐privacy,which is significantly better than the differential privacy method used by TensorFlow.

关键词： data privacy machine learning security of data

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid Approach-Based on Heartbeat and Accelerometer Signals for Enhanced Security in WBSNs

引用

IEEE Sensors Journal 2025年第6期25卷 10295-10308页

作者： Yan, Guixiang Zhang, Guanghe Liu, Fanghua Williams Samuel, Oluwarotimi Aborokbah, Majed Guo, Jiquan Zhu, Liqing Wei, Sikang Jiangxi Normal University School of Computer and Information Engineering Nanchang330022 China University of Derby School of Computing and Data Science Research Centre DerbyDE22 3AW United Kingdom INTI International University Faculty of Data Science and Information Technology Nilai71800 Malaysia University of Tabuk Faculty of Computers and Information Technology Tabuk71491 Saudi Arabia Jiangxi Normal University School of Digital Industry Shangrao334000 China

In wireless body sensor networks (WBSNs), ensuring secure and efficient key distribution is critical, particularly given the limited computational and energy resources of the sensors. Existing methods often struggle to balance security with these resource constraints, especially in environments involving physiological data such as acceleration (ACC) and electrocardiogram (ECG) signals. For the first time, this study proposes a novel hybrid approach that integrates fuzzy commitment with ACC signal noise and ECG features for efficient key generation and distribution in WBSNs. By employing a low-pass filter to process ACC signal noise, we generated highly random binary sequences (BSs), leveraging the inherent randomness of the signal for secure key generation. Concurrently, an optimized coding scheme was built for ECG feature construction to ensure secure key distribution between devices. Extensive experiments, including entropy analysis and National Institute of Standards and Technology (NIST) statistical tests, confirm the robustness and security of our method. The proposed scheme achieves a false acceptance rate (FAR) of 5.23%, demonstrating superior performance across multiple databases in comparison to benchmark approaches. This novel dual-key generation strategy that combines the unpredictability of ACC noise with the individual-specific traits of ECG signals can significantly enhance the security, applicability, and versatility of WBSNs. © 2001-2012 IEEE.

关键词： Acceptance tests

来源：评论

学校读者我要写书评

暂无评论

To Train, or Not to Train: Exploring Foundation Models for TBAD Segmentation 26

To Train, or Not to Train: Exploring Foundation Models for T...

引用

26th Irish Machine Vision and Image Processing Conference, IMVIP 2024

作者： Abaid, Ayman Ullah, Ihsan School of Computer Science University of Galway Galway Ireland Insight SFI Research Centre for Data Analytics University of Galway Galway Ireland

ISBN: (纸本)9781837242672

Recent advancements in biomedical image analysis have been significantly influenced by vision foundation models (FMs) originally designed for general computer vision tasks. These models, such as the Segment Anything Model (SAM) have quickly transitioned into applications in medical image processing. This study evaluates three cutting-edge segmentation FMs using Type B Aortic Dissection (TBAD) CTA images. Our experiments critically assess their strengths and weaknesses compared to traditional methods, emphasizing their potential to enhance efficiency in medical image analysis. However, our findings also indicate that these FMs have not surpassed traditional segmentation models in terms of performance, suggesting limitations in their adaptability for medical image segmentation tasks straight out of the box. © This is an open access article published by the IET under the Creative Commons Attribution License (http://***/licenses/by/3.0/)

关键词： Dissection

来源：评论

学校读者我要写书评

暂无评论

Incentive Mechanism of Selfish Nodes Based on Energy Optimization and Game Theory

Incentive Mechanism of Selfish Nodes Based on Energy Optimiz...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Dong, XiangJia Cheng, Yuan Seah, Winston K. G. Zhang, Feng Xu, Gang College of Computer Science Inner Mongolia University Engineering Research Center of Ecological Big Data Ministry of Education Hohhot China School of Engineering & Computer Science Victoria University of Wellington Wellington New Zealand School of Computer and Information Technology Shanxi University Taiyuan China

ISBN: (纸本)9781665410205

With the proliferation of mobile intelligent terminals, opportunistic networks have attracted widespread attention as a complementary technology to multi-network convergence. Different from traditional wireless networks, message delivery in opportunistic networks does not rely on a fixed infrastructure, but rather storing messages in a cache and utilizing the movement and encounters of nodes to relay messages. However, in practical application scenarios, nodes have limited storage space and energy and will easily exhibit selfishness. An increase in the number of selfish nodes will drastically degrade the performance of the network. To solve the problem of significant network performance degradation when the number of selfish nodes is high, this paper proposes an Incentive mechanism of Selfish nodes based on Energy optimization and Game Theory (ISEGT). The mechanism abstracts the process of forwarding messages by nodes into a bargaining game process, and selectively forwards messages based on nodes' remaining energy and other circumstances. The experimental results show that the ISEGT mechanism can motivate selfish nodes to actively participate in message forwarding, which improves the success rate of message delivery and the survival rate of nodes, and optimizes the overall performance of the network. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SYSTEM THINKING MEETS data science/ENGINEERING 67

SYSTEM THINKING MEETS DATA SCIENCE/ENGINEERING

引用

67th Annual Meeting of the International Society for the Systems sciences, ISSS 2023

作者： Malele, Vusumuzi Unit for Data Science and Computing School of Computer Science and Information Systems North-West University Vanderbijlpark Campus South Africa

ISBN: (纸本)9781713893455

With the advent of data 3.0 and analytics 3.0, system thinkers are in the position to provide a bigger picture in data science and data engineering. In the data life cycle, a system thinking approach emphasises data-driven decision-making. A System Thinker approaches problem-solving by viewing the problems as part of a wider, data-resourced and dynamic system, and a data Practitioner supports the data life cycle by collecting, transforming, and analyzing data, and communicating results to inform and guide decision-making. This paper uses explanatory research and a pragmatic case study approach to look at the (i) What is the role of system thinking and data science/engineering skill in data-driven decision-making or organisation? (ii) Does the combination of system thinking and data science/engineering give rise to a new discipline? (iii) What are the skills needed in this new discipline? The research shows that the system thinking skills in the data life cycle are important. System thinkers meet data practitioners to provide a bigger picture of data-driven decision-making. The latter ascertains the position of a system thinker in any industrial revolution (i.e. industry 4.0. and industry 5.0). Furthermore, a data-System Thinker is proposed as a new career field. © Copyright, Author (Creative Commons), 2023.

关键词： Systems thinking

来源：评论

学校读者我要写书评

暂无评论

Optimizing Coverage in Wireless Sensor Networks Using the Tumbleweed Algorithm

Journal of Network Intelligence

引用

Journal of Network Intelligence 2025年第1期10卷 250-261页

作者： Zhang, Mengfei Chu, Shu-Chuan Liu, Nengxian Huang, Kuan-Chun Pan, Jeng-Shyang College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China College of Computer and Data Science Fuzhou University Fuzhou350108 China Department of Industrial and Systems Engineering Chung Yuan Christian University Taoyuan320314 Taiwan School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing210044 China Department of Information Management Chaoyang University of Technology Taichung41349 Taiwan

Wireless sensor networks (WSNs) have found extensive applications across various fields, significantly enhancing the convenience in our daily lives. Hence, an in-creasing number of researchers are directing their attention toward the performance of sensor nodes, with a particular emphasis on addressing the coverage challenges in WSNs. Node coverage plays a crucial role in determining the detection performance of WSNs, making it imperative to attain maximum coverage with a given number of sensor nodes. This paper applies the Tumbleweed Algorithm (TA) to the coverage problem in WSNs and validates its effectiveness through simulation experiments. The results demonstrate its unique advantages in global search and avoiding local optima, providing a new solution for the WSN coverage problem and offering valuable references for future research and practical applications. The TA algorithm simulates the lifecycle of tumbleweed from seedling to mature plant and includes the concept of growth cycles. This paper compares the TA algorithm with PSO, GWO, DE, BOA, SCA, and AOA, setting different numbers of wireless sensor nodes and varying sensing radii for the experiments. The experimental results show that the TA algorithm significantly improves coverage rates under various configurations and consistently outperforms other commonly used algorithms. © 2025, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

PentaPen: Combining Penalized Models to Identify Important SNPs on Whole-genome Arabidopsis thaliana data 24

PentaPen: Combining Penalized Models to Identify Important S...

引用

16th International Conference on Bioinformatics and Biomedical Technology, ICBBT 2024

作者： Kohli, Nikita Tomal, Jabed H. Lin, Wenjun Yan, Yan Program of Data Science Thompson Rivers University KamloopsBC Canada Department of Mathematics and Statistics Thompson Rivers University KamloopsBC Canada School of Computer Science and Technology Algoma University BramptonON Canada School of Computer Science University of Guelph GuelphON Canada

ISBN: (纸本)9798400717666

In the rapidly advancing field of genomics, the identification of Single Nucleotide Polymorphisms (SNPs) plays a crucial role in understanding complex phenotypic *** study introduces "PentaPen", an innovative computational workflow which combines the strengths of five penalized models to achieve improved accuracy in SNP *** compare the performance of PentaPen with existing models, highlighting its advantages in solving problems arising from when the number of predictors exceeds the number of *** model comparison, we provide insights into PentaPen's effectiveness in utilizing all SNPs as input, streamlines data pre-processing, and leverages parallel computation, enabling the workflow a considerable stride in SNP ***, a thorough evaluation and comparison of computational complexities signifies competitive edge of the workflow over individual penalized *** future research directions, we propose applications of PentaPen to plant-specific characteristics and suggest further explorations to assess the robustness of its *** summary, this manuscript presents the genomics community with a tool that combines computational efficiency with high-precision SNP detection, making a strong contribution to the field of genomic research. © 2024 Copyright held by the owner/author(s).

关键词： Genome

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：