检索结果-内蒙古大学图书馆

AFuNet: an attention-based fusion network to classify texts in a resource-constrained language

Neural Computing and Applications 2025年第9期37卷 6725-6748页

作者： Hossain, Md. Rajib Hoque, Mohammed Moshiul Dewan, M. Ali Akber Hoque, Enamul Siddique, Nazmul Department of Computer Science & Engineering Chittagong University of Engineering & Technology Chittagong4349 Bangladesh School of Computing and Information Systems Faculty of Science and Technology Athabasca University AthabascaABT9S 3A3 Canada School of Information Technology York University TorontoONM3J 1P3 Canada School of Computing Engineering and Intelligent Systems Ulster University Coleraine United Kingdom

In the era of widespread Internet use and extensive social media interaction, the digital realm is accumulating vast amounts of unstructured text data. This unstructured data often contain undesirable information, necessitating time-consuming manual classification efforts. An intelligent text classification system capable of automatically categorizing digitized texts based on semantic meaning is crucial. However, this task is particularly challenging for low-resource languages like Bengali due to a shortage of annotated corpora, issues with out-of-vocabulary words, lack of domain-specific hyperparameter tuning, limited ability to extract generalized text features, and class imbalances within the corpus. AFuNet: an attention-based fusion network to classify texts in a resource-constrained language. AFuNet undergoes a comprehensive four-phase experimental process, including baseline model evaluation and hyperparameter tuning, late fusion and model selection, attention-based early fusion and model identification, and an ablation study with impact analysis. Fine-tuned based on five Bengali text classification corpora, AFuNet achieves impressive accuracies: 96.60 ± 0.2 (BTCC11), 85.37 ± 0.2 (OSBC), 97.35 ± 0.2 (BARD), 93.74 ± 0.2 (IndicNLP), and 96.51 ± 0.2 (ProthomAlo). In comparison with previous state-of-the-art models on these corpora, AFuNet demonstrates significant accuracy improvements ranging from 0.54% to 4.49%, showcasing its effectiveness in advancing text classification capabilities for the Bengali language. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Prior-Boosted GRL: Microarchitecture Design Space Exploration via Graph Representation Learning

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and systems 2025年第3期44卷 1141-1154页

作者： Wu, Zheng Shen, Jinyi Yi, Xiaoling Shang, Li Yang, Fan Zeng, Xuan Fudan University State Key Laboratory of Integrated Circuits and Systems The School of Microelectronics Shanghai200433 China Fudan University State Key Laboratory of Integrated Circuits and Systems Shanghai200433 China KU Leuven Department of Electrical Engineering Microelectronics Circuits and Systems Leuven3000 Belgium Fudan University State Key Laboratory of Integrated Circuits and Systems The School of Computer Science Shanghai200433 China

The design space exploration (DSE) of contemporary microprocessors faces a significant challenge of high-computational cost. In this context, we introduce Prior-boosted graph representation learning (GRL), a novel framework for the DSE of the microarchitectures the microprocessors underpinned by graph embeddings. Using GRL, Prior-boosted GRL constructs a compact and continuous vector space for design representation. This framework is further boosted by an efficient sampling algorithm informed by prior knowledge, which is instrumental in generating a superior set of initial designs to accelerate the exploration process. A well-designed ensemble surrogate model is combined with the multiobjective Bayesian optimization to explore the design space holistically within this graph-embedding domain. Rigorous experimental evaluations conducted on the RISC-V Berkeley-Out-of-Order Machine (BOOM) platform demonstrate that Prior-boosted GRL substantially surpasses preceding methods, achieving a 107.79% enhancement in Pareto front quality compared to the state-of-the-art DSE algorithm. It also outstrips manual designs on performance, power, and area metrics. As of this writing, Prior-boosted GRL holds the first place in the ICCAD 2022 CAD Contest evaluation platform. © 2024 IEEE.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Offsets Reconstruction Method for Clock Skew Measurement Over High-Jitter Communication

引用

SN computer science 2025年第5期6卷 1-14页

作者： Sastra, Nyoman Putra Saputra, Komang Oka Teng, Wei-Chung Study Program of Electrical Engineering Faculty of Engineering Udayana University Jalan Raya Kampus Bukit Jimbaran Bali Badung 80361 Indonesia Department of Computer Science and Information Engineering National Taiwan University of Science and Technology No. 43 Section 4 Keelung Rd Taipei 106 China

Measuring clock skew of devices over a network fully relies on the offsets, the differences between sending and receiving times. Offsets that shape a thick line are the most ideal one as their slope is directly the clock skew sought. When some outliers separate from the thick line due to higher delay jitter, current advanced approaches use the lower bound or the majority of offsets to derive accurate clock skew. However, outliers in offsets that shape parallel dotted lines, reduce the availability of offsets in the lower region, and scatter widely the offsets from their majority zone. These conditions drive the current skew estimation approaches to lose their accuracy. This paper then developed a new method, which reconstructs back the outliers into their origin positions, in order to provide ideal offsets for clock skew measurement. The experimental evaluations have demonstrated that the clock skew accuracy of dotted-lines offsets tampered by outliers was improved from 2.1 to 0.9 ppm by the proposed reconstruction method. For a broader purpose, the reconstruction method has been adjusted to be implemented also on non-dotted-lines offsets. The robustness of the proposed method for this case has also been exhibited by the very ideal reconstructed offsets that shape like a thick line. © The Author(s) 2025.

关键词： Clock skew Delay jitter Dotted lines Hough transform

来源：评论

学校读者我要写书评

暂无评论

Gupacker: Generalized Unpacking Framework for Android Malware

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 4338-4352页

作者： Zheng, Tao Hou, Qiyu Chen, Xingshu Ren, Hao Li, Meng Li, Hongwei Shen, Changxiang Sichuan University School of Cyber Science and Engineering Chengdu610065 China Sichuan University School of Cyber Science and Engineering Cyber Science Research Institute Key Laboratory of Data Protection and Intelligent Management Ministry of Education Chengdu610065 China Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Intelligent Interconnected Systems Laboratory of Anhui Province School of Computer Science and Information Engineering Hefei230002 China University of Padua Department of Mathematics HIT Center Padua35131 Italy University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China Sichuan University Cyber Science Research Institute Key Laboratory of Data Protection and Intelligent Management Ministry of Education Chengdu610065 China

Android malware authors often use packers to evade analysis. Although many unpacking tools have been proposed, they face two significant challenges: 1) They are easily impeded by anti-analysis techniques employed by packers, preventing efficient collection of hidden Dex data. 2) They are typically designed to unpack a specific packer and cannot handle malware packed with mixed packers. Consequently, many packed malware samples evade detection. To bridge this gap, we propose Gupacker , a novel generalized unpacking framework. Gupacker offers a generic solution for first-generation holistic packer by customizing the Android system source code. It identifies the type of packer and selects an appropriate unpacking function, constructs a deeper active call chain to achieve generic unpacking of second-generation function extraction packers, and uses JNI function and instruction monitoring to handle third-generation virtual obfuscation packer. On this basis, we counteract a diverse array of anti-analysis techniques. We conduct extensive experiments on 5K packed Android malware samples, comparing Gupacker with 2 commercial and 4 state-of-the-art academic unpacking tools. The results demonstrate that Gupacker significantly improves the efficiency of Android malware unpacking with acceptable system overhead. We analyze real packed applications based on Gupacker and found several are second-packed by attackers, including WPS for Android, with tens of millions of users. We receive and responsibly report 13 0day vulnerabilities and also assist in the remediation of all vulnerabilities. © 2005-2012 IEEE.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of various classification algorithms for providing competency training to workplace risk prevention

引用

Multimedia Tools and Applications 2025年第15期84卷 15123-15149页

作者： Garg, Shruti Murugan, Prabhu Manimaran, A. Sundar, Ramesh Dakshinamoorthy, Prabakar Rajaram, Gnanajeyaraman Birla Institute of Technology Ranchi Mesra India Department of ECE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai602105 India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai602105 India Department of Networking and Communication School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur India Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur India

In the workplace, risk prevention helps detect the risks and prevent accidents. To achieve this, workers' mental and physical parameters related to their health should be focused on and analyzed. It helps improve the workers' mental health and thus improves organizational performance. There are a lot of mental illnesses due to excess work and a lack of professional knowledge. It affects the performance of the worker. So, the organization needs to conduct competency training programs to improve their professional skills and the mindset to tackle the work pressure. There are several competency training programs given in various organizations to mold the workers, and it considerably reduces workplaces risks. Competency training in the workplace teaches integrity, honesty, managerial skills, and other workers. Developing organizational skills is the primary concern in this competency training. This paper enabled one of the best machine learning algorithms to be chosen to predict the hazards in the workplace and provide a healthy environment to the workers. For that, several classification methods such as Logistic Regression, Decision trees, AdaBoost classifier, Random Forest, Gradient Boosting classifier, and XGBoost classifier are implemented experimented with, and the performance is verified with python software. From the comparison, it has been found that the XGBoost classifier is selected as the best classifier and identified that it is highly suitable for analyzing and predicting workplace risks data. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Occupational risks

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Mobile Healthcare: Societal Impact, Workforce Adaptation, and Enhanced Predictive Modeling for Diabetes Risk Assessment

AI-Driven Mobile Healthcare: Societal Impact, Workforce Adap...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Hole, Shreyas Rajendra Kolluru, Vinothkumar Gangul, Ranita Kolekar, Sagar Chintakunta, Advaitha Naidu Mungara, Sudeep Bangalore India Institute of Technology Department of Data Science Stevens HobokenNJ07030 United States Delaware State University Computer Science & Engineering Bangalore India Department of Civil Engineering Pune India University of North Carolina at Charlotte Department of Computer Science CharlotteNC28223 United States Masters in Information Systems Stevens Institute of Technology HobokenNJ07030 United States

ISBN: (纸本)9798331508685

With advancements in artificial intelligence, it is natural for the health industry to focus on IOT devices. AI could promote a paradigm shift in how doctors and patients interact through immediate updates, predictive features, and remote access. The focus of this study is the outreach and employment aspects revolving around AI-enabled health care, with special attention to mHealth solutions. We searched through published data and came across 112 relevant studies identifying keywords such as accessibility, empowerment, and workforce. One of the most interesting findings was the fact that AI targeting mobile applications has the possibility of increasing access to health services by approximately 60 percent for rural areas, as well as increasing the patient cooperative rate by approximately 45%, where a predictive health tracking device has been utilized. We proposed two new measures: the Physical Activity and Nutrition Index (PANI) and Health Status Index (HSI), allowing for better diabetes risk predictions with a 0.82 AUC-ROC and better generalizability than traditional baselines, with an improvement of 12%. When identifying the best available ML models, including Logistic Regression, Random Forest, XGBoost, LightGBM, and Bayesian Neural Networks, we found that the hybrid Random Forest + Linear SVC model had the best performance with recall and accuracy of 0.77 and 0.72, respectively. The ability of the model to demonstrate both interpretability and specificity was evident. It was also observed that synthetic data augmentation (SMOTE) increased the recall for minority class predictions by 18% but did not reduce specificity. © 2025 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Government Digital Transformation: A Tailor-Made Digital Maturity Assessment Framework

引用

IEEE Access 2025年 13卷 71120-71132页

作者： Alfadhli, Muna Kucukvar, Murat Onat, Nuri C. Al-Maadeed, Somaya Abdessadok, Abdelhamid Engineering Management Program College of Engineering Qatar University Doha Qatar Daniels College of Business University of Denver DenverCO80208 United States Qatar Transportation and Traffic Safety Center College of Engineering Qatar University Doha Qatar Department of Computer Science and Engineering College of Engineering Qatar University Doha Qatar Ministry of Social Development and Family Doha Qatar

Governments seek to implement digital transformation initiatives to improve the effectiveness of their public services. To achieve this, governments need to assess their IT environment and evaluate their digital maturity. The conventional digital maturity assessment frameworks, mainly constructed by consulting firms, often fail when applied to the public sector due to the differences between the business and government sectors in terms of their operational missions and activities. Therefore, a maturity assessment framework that accommodates the unique requirements of governments and their operating environments is necessary. The novelty of this research lies in its contribution to digital transformation in the public sector by presenting a framework specifically designed to assess the digital transformation maturity of government organizations. This research is based on analyzing the factors of maturity assessment models developed by industry leaders from three leading global consulting firms. Insights from the academic literature on these factors were extracted, and a comprehensive survey was conducted with 88 IT experts from government institutes across six countries to ensure their relevance and applicability in real-world government settings. In this research, we tested our hypothesis on whether there is a significant relationship between the importance of digital transformation factors and their implementation. The analysis indicated that there is no strong statistical relationship between the importance of digital transformation maturity factors and their implementation. The framework helps assess digital maturity and supports the formulation of effective strategies to drive successful digital transformation initiatives in government. © 2013 IEEE.

关键词： Digital transformation Organizations Government Capability maturity model Industries Biological system modeling Technological innovation Stakeholders Planning Current measurement

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Prediction for Start-Up Success through Deep Learning based Stacked DAE Model 3

Probabilistic Prediction for Start-Up Success through Deep L...

引用

3rd International Conference on Integrated Circuits and Communication systems, ICICACS 2025

作者： Syed, Shakir Sondinti, Lakshminarayana Reddy Kothapalli Sapra, Puneet Joshi, Amit Shobana, M. Deepan Chakravarthi, A.V. Shivam hills India Us Bank LB. Nagar India Rayat Bahara University Department of Computer Science Engineering Mohali India Isma University Department of Information Technology Rīga Latvia M.Kumarasamy College of Engineering Department of Computer Science and Business Systems Karur India Velammal College of Engineering and Technology Department of Civil Engineering Madurai India

ISBN: (纸本)9798331508456

Researchers and financial entities have long been fascinated by the ability to accurately predict the success of start-ups. Modern start-ups, which are creative, tech-focused, and quickly growing companies, face this challenge more than most. This study introduces a deep learning Stacked Denoising Autoencoder (SDAE) model that uses important technology domains to forecast the likelihood of a startup's success. The three primary steps of the proposed approach are as follows: preprocessing, feature extraction, and training the model. To ensure statistical independence of signal components in multivariate datasets, preprocessing steps include min-max normalisation for data standardisation and Independent Component Analysis (ICA) for feature extraction. The predictive power of the SDAE model is then enhanced by training. The proposed model outperforms traditional methods like Decision Trees (DT) and Denoising Autoencoders (DAE) with an average accuracy of 94.28%, according to the experimental data. This makes it a strong contender for predicting startup success in changing technical contexts. © 2025 IEEE.

关键词： Independent component analysis

来源：评论

学校读者我要写书评

暂无评论

Emerging Trends in AI-Powered IoT: Innovations, Key Challenges, and Future Directions

Emerging Trends in AI-Powered IoT: Innovations, Key Challeng...

引用

2025 IEEE SoutheastCon, SoutheastCon 2025

作者： Abdelraouf, Hussien Abouyoussef, Mahmoud Fouda, Mostafa M. Fadlullah, Zubair Md Ibrahem, Mohamed I. School of Computer and Cyber Sciences Augusta University AugustaGA30912 United States North Carlina A&T State University Department of Computer Systems Technology GreensboroNC27411 United States Idaho State University Department of Electrical and Computer Engineering PocatelloID83209 United States Western University Department of Computer Science LondonON Canada

ISBN: (纸本)9798331504847

This survey provides a comprehensive overview of recent emerging technologies in artificial intelligence (AI) applied to the Internet of Things (IoT), highlighting their significance and applications across various domains. Our study covers key advancements, including Concept Drift, Transformers, TinyML, Explainable AI (XAI), and Federated Learning (FL). Concept Drift addresses changes in data patterns to maintain the accuracy of machine learning models in dynamic environments. Transformers revolutionize Natural language processing (NLP) by efficiently capturing long-range dependencies. TinyML enables smart IoT applications on low-power devices, while XAI promotes transparency in AI decisions. FL facilitates decentralized model training while preserving data privacy. Our discussion also covers challenges, limitations, and future research directions to improve AI and IoT integration. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Protecting Your Attention during Distributed Graph Learning: Efficient Privacy-Preserving Federated Graph Attention Network

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 1949-1964页

作者： Zhou, Jinhao Wu, Jun Ni, Jianbing Wang, Yuntao Pan, Yanghe Su, Zhou Waseda University Graduate School of Information Production and Systems Fukuoka808-0135 Japan Queen's University Department of Electrical and Computer Engineering KingstonONK7L 3N6 Canada Xi'An Jiaotong University School of Cyber Science and Engineering Xi'an710049 China

Federated graph attention networks (FGATs) are gaining prominence for enabling collaborative and privacy-preserving graph model training. The attention mechanisms in FGATs enhance the focus on crucial graph features for improved graph representation learning while maintaining data decentralization. However, these mechanisms inherently process sensitive information, which is vulnerable to privacy threats like graph reconstruction and attribute inference. Additionally, their role in assigning varying and changing importance to nodes challenges traditional privacy methods to balance privacy and utility across varied node sensitivities effectively. Our study fills this gap by proposing an efficient privacy-preserving FGAT (PFGAT). We present an attention-based dynamic differential privacy (DP) approach via an improved multiplication triplet (IMT). Specifically, we first propose an IMT mechanism that leverages a reusable triplet generation method to efficiently and securely compute the attention mechanism. Second, we employ an attention-based privacy budget that dynamically adjusts privacy levels according to node data significance, optimizing the privacy-utility trade-off. Third, the proposed hybrid neighbor aggregation algorithm tailors DP mechanisms according to the unique characteristics of neighbor nodes, thereby mitigating the adverse impact of DP on graph attention network (GAT) utility. Extensive experiments on benchmarking datasets confirm that PFGAT maintains high efficiency and ensures robust privacy protection against potential threats. © IEEE.

关键词： Differential privacy

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：