检索结果-内蒙古大学图书馆

Accurate Robotic Grasp Detection with Angular Label Smoothing

Journal of Computer Science & technology 2023年第5期38卷 1149-1161页

作者：石敏路昊李兆歆朱登明王兆其 School of Control and Computer Engineering North China Electric Power UniversityBeijing 102206China Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China

Grasp detection is a visual recognition task where the robot makes use of its sensors to detect graspable objects in its *** the steady progress in robotic grasping,it is still difficult to achieve both real-time and high accuracy grasping *** this paper,we propose a real-time robotic grasp detection method,which can accurately predict potential grasp for parallel-plate robotic grippers using RGB *** work employs an end-to-end convolutional neural network which consists of a feature descriptor and a grasp *** for the first time,we add an attention mechanism to the grasp detection task,which enables the network to focus on grasp regions rather than ***,we present an angular label smoothing strategy in our grasp detection method to enhance the fault tolerance of the *** quantitatively and qualitatively evaluate our grasp detection method from different aspects on the public Cornell dataset and Jacquard *** experiments demonstrate that our grasp detection method achieves superior performance to the state-of-the-art *** particular,our grasp detection method ranked first on both the Cornell dataset and the Jacquard dataset,giving rise to the accuracy of 98.9%and 95.6%,respectively at realtime calculation speed.

关键词： robotic grasp detection attention mechanism angular label smoothing anchor box deep learning

来源：评论

学校读者我要写书评

暂无评论

Development of a new gas condensate viscosity model using artificial intelligence

引用

Journal of King Saud University - engineering Sciences 2022年第7期34卷 376-383页

作者： Faraji, F. Ugwu, J.O. Chong, P.L. School of Computing Engineering and Digital Technology Teesside University Middlesbrough United Kingdom

Accurate estimation of gas condensate fluid properties is a challenging task due to the evolving condensate liquid from the gas phase below the saturation pressure. Among the fluid properties, viscosity of condensate liquid has the largest prediction uncertainty. The existing literature methods cannot cope with the nonlinearity and physics of gas condensate mixture (transition from a single phase to two phases) below the saturation pressure. Hence, in this study based on the experimental condensate viscosity data, a simple linear equation as a function of pressure, temperature and solution gas to oil ratio was developed. For this purpose, a comprehensive data source of 1368 experimental data points acquired from open literature has been used. For developing the new condensate viscosity correlation, an artificial intelligence (AI) method known as the Takagi–Sugeno–Kang (TSK) fuzzy algorithm was utilized. The accuracy of the developed correlation was compared with five previously published literature models. The superiority of the new correlation over the existing literature models is confirmed by statistical parameters of a least root mean square error of 0.0194, a mean average error of 0.0163 and an average absolute relative deviation percentage of 7.123. The proposed condensate viscosity correlation is valid in a pressure range of 0.25–75.84 MPa), a temperature range of 303–443.15°K and Rs of 41.96–3496 scf/STB. The proposed correlation can be used as an alternative approach to the existing models for accurately estimating the gas condensate viscosity and for conducting reliable reservoir simulation studies. © 2021 The Authors

关键词： Viscosity

来源：评论

学校读者我要写书评

暂无评论

A Combined Distance Metric Approach with Weight Adjustment For Improving Mixed Data Clustering Quality 6

A Combined Distance Metric Approach with Weight Adjustment F...

引用

6th IEEE International Conference on Artificial Intelligence in engineering and technology, IICAIET 2024

作者： Pyae, Aung Low, Yeh-Ching Chua, Hui Na School of Engineering and Technology Sunway University Department of Computing and Information Systems Subang Jaya Malaysia

ISBN: (纸本)9798350389692

Cluster analysis can be perceived as a problem of grouping data points according to their mutual similarity. Clustering quality largely depends on choosing an effective distance metric, especially when dealing with mixed data that contains both numerical and categorical features. This study introduces a Weighted Combined distance metric using Gower and sqrt-cosine distances to improve clustering quality for mixed data. By combining two individual distance metrics with weights, this unique technique generates an overall similarity score that can improve the clustering quality. Experiments have demonstrated that the Weighted Combined distance metric can yield superior clustering quality compared to individual distance metrics. These findings highlight the potential of this proposed method to effectively cluster mixed data and overcome challenges associated with mixed data clustering. © 2024 IEEE.

关键词： Distance Metrics Hierarchical Clustering Mixed Data Unsupervised Learning

来源：评论

学校读者我要写书评

暂无评论

Chaotic Map-Based Authentication and Key Agreement Protocol with Low-Latency for Metasystem

引用

Computers, Materials & Continua 2024年第3期78卷 4471-4488页

作者： Guojun Wang Qi Liu School of Electronics&Information Engineering Nanjing University of Information Science&TechnologyNanjing210044China Yancheng Polytechnic College Yancheng224000China Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services School of SoftwareNanjing University of Information Science and TechnologyNanjingChina

With the rapid advancement in exploring perceptual interactions and digital twins,metaverse technology has emerged to transcend the constraints of space-time and reality,facilitating remote AI-based *** this dynamic metasystem environment,frequent information exchanges necessitate robust security measures,with Authentication and Key Agreement(AKA)serving as the primary line of defense to ensure communication ***,traditional AKA protocols fall short in meeting the low-latency requirements essential for synchronous interactions within the *** address this challenge and enable nearly latency-free interactions,a novel low-latency AKA protocol based on chaotic maps is *** protocol not only ensures mutual authentication of entities within the metasystem but also generates secure session *** security of these session keys is rigorously validated through formal proofs,formal verification,and informal *** confronted with the Dolev-Yao(DY)threat model,the session keys are formally demonstrated to be secure under the Real-or-Random(ROR)*** proposed protocol is further validated through simulations conducted using VMware workstation compiled in HLPSL language and C *** simulation results affirm the protocol’s effectiveness in resisting well-known attacks while achieving the desired low latency for optimal metaverse interactions.

关键词： Metasystem authentication and key agreement chaotic map secure communication

来源：评论

学校读者我要写书评

暂无评论

Telugu Language Analysis with XLM-RoBERTa: Enhancing Parts of Speech Tagging for Effective Natural Language Processing

引用

SN Computer Science 2025年第2期6卷 1-13页

作者： Bharathi Mohan, G. Prasanna Kumar, R. Krishna Jayanth, K. Doss, Srinath Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Faculty of Engineering and Technology Botho University Gaborone Botswana

This research investigates the efficacy of XLM-RoBERTa, a potent deep learning architecture rooted in transformer networks, for Part-of-Speech (POS) tagging—a foundational task in Natural Language Processing (NLP). The study narrows its focus to address the formidable UCD Telugu dataset, renowned for its intricate morphological characteristics that pose challenges to accurate tagging. Through meticulous fine-tuning of the pre-trained XLM-RoBERTa model. This study adeptly discerns and exploit intricate syntactic and semantic patterns underpinning the interplay between lexical elements and their respective POS tags. The rigorous evaluation regimen, complemented by a comprehensive statistical comparison with the Multilingual BERT model, conclusively establishes XLM-RoBERTa’s superiority. This advanced model attains a remarkable accuracy score of 91%, decisively surpassing the Multilingual BERT model, which achieves an accuracy of 88%. These findings not only underscore XLM-RoBERTa’s prowess in precise POS tagging, especially in the context of morphologically rich languages like Telugu, but also carry significant implications for the broader NLP community. This research unlocks valuable insights and positions XLM-RoBERTa as an exemplar of reliability and robustness in POS tagging. Furthermore, it extends an invitation for further exploration and innovation in deep learning architectures within the NLP domain. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Bert Multilingual Bert NLP Parts-of-speech tagging Telugu XLM-RoBERTa

来源：评论

学校读者我要写书评

暂无评论

Improving Entity Linking in Chinese Domain by Sense Embedding Based on Graph Clustering

引用

Journal of Computer Science & technology 2023年第1期38卷 196-210页

作者：张照博钟芷漫袁平鹏金海 National Engineering Research Center for Big Data Technology and System Huazhong University of Science and Technology Wuhan 430074China Service Computing Technology and System Laboratory Huazhong University of Science and Technology Wuhan 430074China Cluster and Grid Computing Laboratory Huazhong University of Science and TechnologyWuhan 430074China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China

Entity linking refers to linking a string in a text to corresponding entities in a knowledge base through candidate entity generation and candidate entity *** is of great significance to some NLP(natural language processing)tasks,such as question *** English entity linking,Chinese entity linking requires more consideration due to the lack of spacing and capitalization in text sequences and the ambiguity of characters and words,which is more evident in certain *** Chinese domains,such as industry,the generated candidate entities are usually composed of long strings and are heavily *** addition,the meanings of the words that make up industrial entities are sometimes *** semantic space is a subspace of the general word embedding space,and thus each entity word needs to get its exact ***,we propose two schemes to achieve better Chinese entity ***,we implement an ngram based candidate entity generation method to increase the recall rate and reduce the nesting ***,we enhance the corresponding candidate entity ranking mechanism by introducing sense *** the contradiction between the ambiguity of word vectors and the single sense of the industrial domain,we design a sense embedding model based on graph clustering,which adopts an unsupervised approach for word sense induction and learns sense representation in conjunction with *** test the embedding quality of our approach on classical datasets and demonstrate its disambiguation ability in general *** confirm that our method can better learn candidate entities’fundamental laws in the industrial domain and achieve better performance on entity linking through experiments.

关键词： natural language processing(NLP) domain entity linking computational linguistics word sense disambiguation knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Deep Learning to Effectively Detect and Eliminate Real-Time Network Intrusions 3

Deep Learning to Effectively Detect and Eliminate Real-Time ...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Harikesh, S. Sujatha, G. Department of Networking and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu Chennai India

ISBN: (纸本)9798331527549

Network traffic has been growing exponentially for the past several years. As a result, it has become more and more difficult to detect cyber intrusions - especially in unbalanced environments, where the attacks are usually covered up by normal traffic. This investigation is set to deal with the problem by coming up with an intrusion detection system that uses a deep learning approach to effectively find and eliminate the unbalanced network intrusions. The process includes data preprocessing for balancing the classes, feature engineering for choosing optimal features, and comparison of CNN and RNN models for improving detection accuracy. The tests have shown precision of 93% and recall of 88% which in total brought 99.8% accuracy. Also, the real-time deployment has demonstrated the model’s ability to dynamically traffic patterns, which induced false positives to be reduced remarkably. The results help in the improvement of intrusion detection systems by providing a scalable, adaptive, and efficient way to handle constantly altering cyber threats. © 2025 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Sustainable Development Goal-17 and Nigeria Data Protection Regulation Adoption among Organizations in Nigeria

Sustainable Development Goal-17 and Nigeria Data Protection ...

引用

2024 International Conference on Science, engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Babangida-Sabo, Sumayya Avemaria Utulu, Samuel C. Ajibesin, Abel American University of Nigeria Department of Informaton Systems School of Informtaon Technology and Computing Yola Nigeria Amerucan University of Nigeria Department of Software Engineering School of Information Technology and Computing Yola Nigeria

ISBN: (纸本)9798350358155

Adoption of computerized systems by organizations in Nigeria poses some data security challenges to citizens and people from other nations. The challenges require organizations to deploy personal data security that are in line with global standards, hence, Nigeria Data Protection Regulation (NDPR) was introduced. NDPR is to promote ethical personal data security and Nigeria's attainment of the sustainable development goal-17. However, only small number of organizations in Nigeria are able to adopt the NDPR because its adoption is complex and necessitate the implementation of organizational change management (OCM) project. Experience shows that OCM projects usually fails because many OCM frameworks used for OCM projects do not align with both scientifically proven ideas and organizational realities. Our study addresses the benefits of collaborative practice research studies to the production of OCM frameworks that incorporates both theoretical ideas and organizational realities. Our study provides viable solutions to the problem of lack of practice oriented OCM frameworks that organizations in Nigeria can use to drive the adoption the NDPR. © 2024 IEEE.

关键词： Sustainable development goals

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cybersecurity Policy Awareness Programs in the Financial Sector: A Comprehensive Framework and Assessment of Effectiveness 1

引用

International Conference on Business and technology, ICBT 2024

作者： Thamae, Reneuoe Abdullah, Hanifa Mujinga, Mathias School of Computing College of Science Engineering and Technology University of South Africa Pretoria South Africa

ISBN: (数字)9783031674440

ISBN: (纸本)9783031674433

In today's tech-driven landscape and amid rising cyber threats, prioritizing cybersecurity is crucial for financial organizations. While traditional measures like firewalls are insufficient, human vulnerability persists due to inadequate employee training. To solve this, institutions must enact comprehensive awareness programs on cybersecurity policies. Despite their recognized importance, research gaps exist regarding their effectiveness. This study proposes a framework to enhance such programs, drawing from literature reviews and expert insights. Using a quantitative approach, it examines employee perspectives, revealing gender disparities in cybersecurity knowledge. The framework integrates gender mainstreaming to address these gaps and recommends proactive measures such as inclusive training and reporting procedures. By emphasizing inclusivity and diversity, it aims to foster a robust cybersecurity culture and ensure policy adherence across financial organizations. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Loan Repayment Predictive Model Using Ensemble Algorithm

Loan Repayment Predictive Model Using Ensemble Algorithm

引用

2024 IEEE SmartBlock4Africa, SmartBlock4Africa 2024

作者： Godwin Akinbayo, O. Akintola Kolawole, G. Adewole David, B. School of Computing Federal University of Technology Department of Software Engineering Ondo State Akure Nigeria

ISBN: (纸本)9798350376838

The accurate prediction of loan repayment ability is paramount in any financial industry to minimize risks and enhance decision making. This project centers on the development of a loan repayment predictive model using ensemble algorithm. The performance of the algorithm is evaluated through the following metrics: f1 score, accuracy, and precision. Five classifiers including Random Forest, AdaBoost, Gradient Boosting, Logistic Regression, and SVC were used as base classifiers for the ensemble. Ensemble-based optimization (using RSCV) is employed to get the best combination of hyperparameters. This technique performs a randomized search over specified hyperparameter values, using cross-validated performance to find the best combination to create models that make up the ensemble model. Preliminary results indicate promising performance improvements when compared to single model. Future research in this domain could further refine the model and expand its applications in the ever-evolving financial sector. © 2024 IEEE.

关键词： Decentralized finance

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：