检索结果-内蒙古大学图书馆

28th International Conference on database Systems for Advanced Applications, DASFAA 2023

作者： Hu, Richa Li, Dan Ng, See-Kiong Zheng, Zibin School of Software Engineering Sun Yat-Sen University Zhuhai528478 China Institute of Data Science National University of Singapore Singapore117602 Singapore School of Computing National University of Singapore Singapore117417 Singapore

ISBN: (纸本)9783031306778

In the era of big data, numerous data measurements collected from all walks of life are playing important roles in various data mining applications. Not all data owners (or keepers) could develop feasible learning models for knowledge discovery’s sake. Oftentimes, the original data need to be passed to or shared with researchers or data scientists for better mining insights, especially in the medical, financial, and industrial fields. However, concerns about sensitivity and privacy limit the availability and completeness of shared (or passed) data and the quality of mining results. In this paper, we propose a novel Convolutional Bidirectional Generative Adversarial Networks (CB-GAN) framework to generate sensitive synthetic data. The Convolutional Neural Networks are utilized to capture the feature correlations of the original data, and the Generative Adversarial Networks with Autoencoders are combined to synthesize realistically distributed data. To demonstrate the feasibility of the model, we evaluated it from three aspects: how similar are the distributions of the synthetic data to the original data, how well can the synthetic data accomplish future data mining tasks, and how much sensitive information has been hidden. Various experimental results showed the superiority of the proposed method compared with the state-of-the-art methods. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Mathematical Reasoning in GPT-J Through Topic-Aware Prompt Engineering 25

Enhancing Mathematical Reasoning in GPT-J Through Topic-Awar...

引用

Adjunct Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization

作者： Lev Sukherman Yetunde Folajimi Wentworth Institute of Technology Boston MA USA School of Computing and Data Science Wentworth Institute of Technology Boston MA USA

来源：评论

学校读者我要写书评

暂无评论

Meta Heuristic Image Optimisation in LiDAR Sensor Based on Cloud IoT Network and Deep Learning Algorithms

引用

Remote Sensing in Earth Systems sciences 2025年第2期8卷 566-575页

作者： Meenakshi, K. Manoj, Gunna Diwakar, Meenakshi Prabakaran, Manjula Sravan, Padala Babu, Gaddam Ravindra Department of Networking and Communications School of Computing SRM Institute of Science and Technology Kattankulathur Chennai India Cyber Security Marri Laxman Reddy Institute of Technology and Management Telangana Hyderabad India Department of IT Panimalar Engineering College Chennai India Dept of CSE (Data Science) Madanapalle Institute of Technology & Science Andhra Pradesh Angallu India Computer Science and Engineering NIIT with learning partner Hainan Normal University Haikou China Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Telangana Hyderabad India

LiDAR technology has become a vital tool for researching these atmospheric components because of its capacity to measure backscattered signals and investigate the atmosphere at extremely high spatial and temporal resolution. However, machine learning has become a potent technique for sophisticated data processing and analysis because of the complexity and diversity of lidar technology. The aim of this research is to propose a novel technique in cloud IoT network-based LiDAR sensor imaging with image optimization using a metaheuristic deep learning model. Input has been collected LiDAR image using a cloud IoT module and processed for noise removal and normalization. Then this processed image is classified and optimized utilizing a quantile transfer graph convolutional model with binary firefly whale colony optimization. The experimental analysis is carried out in terms of detection accuracy, random precision, recall, RMSE, and AUC for various LiDAR sensor-based datasets. Comparing the results of the various approaches reveals that the suggested approach outperforms them all with a recall of 94%, a random precision of 95%, and a detection accuracy of 98%. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Cloud IoT network Convolutional model Image optimization LiDAR sensor Metaheuristic deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing PAN Card Security with OCR Based Information Extraction and Face Recognition for Reliable Identity Verification

Enhancing PAN Card Security with OCR Based Information Extra...

引用

data science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： D N Harshavardhan Reddy Malapati Sai Sravanth Reddy Panyam Sudha Dandapani Computer Science and Engineering With Data Science Sathyabama Institute of Science and Technology Chennai India Computer Science and Engineering School of Computing Sathyabama Institute of Science and Technology Chennai India

ISBN: (数字)9798331537555

ISBN: (纸本)9798331537562

Due to the potential for impersonation, the Indian PAN card is of great importance and thus, it should be encrypted with certain methods. The paper proposes a system that deals for achieving greater security of PAN card by applying a combination of OCR based information extraction and face recognition system as a means of securing identity verification. A set of OCR algorithms is first entrusted with the task to accurately read and translate the text found on the PAN card which includes the, date of birth, name and the PAN number, along with other features. The digitized and translated data is easier to store and retrieve, which makes the verification process quicker. Furthermore, a deep learning face recognition module is added in a bid to match the face of the PAN card holder with the face on the card. The proposed system is based on the architecture of the convolutional neural network (CNN) which has been shown to perform well in systems that need to compare in different amounts of light and at different angles making it reduce both the false acceptance and the false rejection rates. This article emphasizes the need for cutting-edge technologies to be implemented in identity verification systems, as identity fraud can be avoided through the use of Computerized Optical character recognition technology (OCR) combined with face recognition technology that provides advanced scanning capabilities advanced scanning capabilities that assist in safeguarding the PAN card.

关键词： Privacy Translation Face recognition Optical character recognition Information retrieval Fraud Convolutional neural networks Reliability Protection Next generation networking

来源：评论

学校读者我要写书评

暂无评论

PulseSync BP: A Neural Network Framework for Non-Contact Blood Pressure Estimation

PulseSync BP: A Neural Network Framework for Non-Contact Blo...

引用

Advances in data Engineering and Intelligent computing Systems (ADICS), International Conference on

作者： Tanumay Ghosh Omisha Singal Namit Lodh S Suchitra Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur Tamil Nadu India

ISBN: (数字)9798350364828

ISBN: (纸本)9798350364835

Using a cutting-edge neural network framework, “PulseSync BP” estimates blood pressure without contact. Using photoplethysmogram (PPG) signals and other physiological data, this novel model uses advanced signal processing. The suggested framework changes blood pressure monitoring by eliminating cuff-based measures. PulseSync BP's RNN architecture is carefully designed for optimal prediction accuracy. The algorithm effectively estimates blood pressure through extensive experimentation, demonstrating its potential for continuous healthcare applications. This framework's capacity to use various physiological cues shows its adaptability and versatility. PulseSync BP allows real-time, non-intrusive blood pressure monitoring, advancing individualized health tracking solutions. Cuffless blood pressure estimate is advanced here, demonstrating how artificial intelligence could improve healthcare accessibility and patient-centric monitoring. PulseSync BP and other revolutionary technologies can transform blood pressure monitoring in healthcare.

关键词： Neural networks Signal processing algorithms Estimation Signal processing Blood pressure Real-time systems Biomedical monitoring

来源：评论

学校读者我要写书评

暂无评论

Design of Airborne Intelligent computing System Oriented to Intelligent Task Processing 26

Design of Airborne Intelligent Computing System Oriented to ...

引用

26th ACIS International Winter Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed computing, SNPD-Winter 2023

作者： Bai, Linting Wen, Pengcheng Xie, Jianchun Li, Yunxi Lin, Rongchao School of Computer Science Northwestern Polytechnical University Xi'an Aeronautics Computing Technique Research Institute Avic Xi'an China Xi'an Aeronautics Computing Technique Research Institute Avic Aviation Key Laboratory of Science and Technology on Airborne and Missile-borne Computer Xi'an China Xi'an Aeronautics Computing Technique Research Institute Avic Aeronautics Data and Sensor Business Unit Avic Xi'an China

ISBN: (纸本)9798350345865

The rapid development of artificial intelligence technology promotes the gradual evolution of the 'three integration' of mechanization, informatization and intelligence. The mass data characteristics of airborne mission informatization put forward higher demands on the storage, transmission and management capabilities of airborne data. The characteristics of high complexity, strong confrontation, strong real-time, and uncertainty of airborne intelligent tasks pose more challenges to the intelligent processing of airborne data. This paper analyzes the data characteristics and mission characteristics in the process of airborne intelligence missions, and proposes an airborne intelligent computing architecture for airborne data processing of intelligent missions. The composition and function of each technical layer are expounded, and several problems of airborne intelligent computing technology are analyzed. Finally, the development trend of airborne intelligent technology development is prospected. © 2023 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Multi-layer network embedding on scc-based network with motif

引用

Digital Communications and Networks 2024年第3期10卷 546-556页

作者： Lu Sun Xiaona Li Mingyue Zhang Liangtian Wan Yun Lin Xianpeng Wang Gang Xu Department of Communication Engineering Institute of Information Science TechnologyDalian Maritime UniversityDalian116026China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and TelecommunicationsChongqing400065China Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province DUT School of Software Technology&DUT-RU International School of Information Science and EngineeringDalian University of TechnologyDalian 116620China College of Information and Communication Engineering Harbin Engineering UniversityHarbin 150001China School of Information and Communication Engineering Hainan UniversityHaikou 570228China State Key Laboratory of Millimeter Waves School of Information Science and EngineeringSoutheast UniversityNanjing 210096China

Interconnection of all things challenges the traditional communication methods,and Semantic Communication and computing(SCC)will become new *** is a challenging task to accurately detect,extract,and represent semantic information in the research of SCC-based *** previous research,researchers usually use convolution to extract the feature information of a graph and perform the corresponding task of node ***,the content of semantic information is quite *** graph convolutional neural networks provide an effective solution for node classification tasks,due to their limitations in representing multiple relational patterns and not recognizing and analyzing higher-order local structures,the extracted feature information is subject to varying degrees of ***,this paper extends from a single-layer topology network to a multi-layer heterogeneous topology *** Bidirectional Encoder Representations from Transformers(BERT)training word vector is introduced to extract the semantic features in the network,and the existing graph neural network is improved by combining the higher-order local feature module of the network model representation network.A multi-layer network embedding algorithm on SCC-based networks with motifs is proposed to complete the task of end-to-end node *** verify the effectiveness of the algorithm on a real multi-layer heterogeneous network.

关键词： Semantic communication and computing Multi-layer network Graph neural network Motif

来源：评论

学校读者我要写书评

暂无评论

Hybrid System with Modified Cuckoo Search to Design Airfoil

Hybrid System with Modified Cuckoo Search to Design Airfoil

引用

2023 International Conference on data science, Agents and Artificial Intelligence, ICDSAAI 2023

作者： Thinakaran, K. Anand, M. Kumar, T.Rajesh Atham, Saira Banu Subramanian, K.M. Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science India Srm Institute of Science and Technology School of Computing Department of Data Science and Business Systems Chennai Kattankulathur India Saveetha Institute of Medical and Technical Science Saveetha School of Engineering India Presidency University School of Cse & Is Department of Computer Science and Engineering Bangaluru India Shadan College of Engineering and Technology Department of Computer Science Engineering Hyderabad India

ISBN: (纸本)9798350348910

The proposed models can design the airfoil by Cuckoo search with Levenberg-Marquardt. The Neural Network framework has impediments due to over-fitting. This paper proposed a modified cuckoo search. here the aerodynamic coefficient as an input to produce output the airfoil coordinates. The generated airfoil is compared to know its performance metrics. The Cuckoo search with the Feedforward Neural Network model yields the lowest prediction error. © 2023 IEEE.

关键词： Airfoils

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Feature Augmentation for Domain Generalization

arXiv

引用

arXiv 2024年

作者： Liu, Yingnan Zou, Yingtian Qiao, Rui Liu, Fusheng Lee, Mong Li Hsu, Wynne School of Computing National University of Singapore Singapore Institute of Data Science National University of Singapore Singapore

Domain generalization aims to develop models that are robust to distribution shifts. Existing methods focus on learning invariance across domains to enhance model robustness, and data augmentation has been widely used to learn invariant predictors, with most methods performing augmentation in the input space. However, augmentation in the input space has limited diversity whereas in the feature space is more versatile and has shown promising results. Nonetheless, feature semantics is seldom considered and existing feature augmentation methods suffer from a limited variety of augmented features. We decompose features into class-generic, class-specific, domain-generic, and domain-specific components. We propose a cross-domain feature augmentation method named XDomainMix that enables us to increase sample diversity while emphasizing the learning of invariant representations to achieve domain generalization. Experiments on widely used benchmark datasets demonstrate that our proposed method is able to achieve state-of-the-art performance. Quantitative analysis indicates that our feature augmentation approach facilitates the learning of effective models that are invariant across different domains. Our code is available at https://***/NancyQuris/XDomainMix. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Development and Testing of Mobile Assisted Language Learning Application to Improve Oral Clinical Case Presentation of Student Nurses

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2023年第15期17卷 171-188页

作者： Milton, Cynthia Subramaniam, Aruna Sridevi, S. Kumar, S. Ganesh Faculty of Allied Health Sciences Sri Ramachandra Institute of Higher Education Tamil Nadu Chennai India Faculty of Nursing Sri Ramachandra Institute of Higher Education Tamil Nadu Chennai India Sri Ramachandra Engineering and Technology Sri Ramachandra Institute of Higher Education Tamil Nadu Chennai India Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai India

Background: Nurses’ oral case presentation is a core clinical communication skill with distinctive linguistic qualities that require specific language training. The present paper is a user feedback analysis of a start-up Mobile Assisted Language Learning application (MALL app) developed and implemented to provide English language training to improve Oral Case Presentation (OCP) of student nurses pursuing baccalaureate degrees from a nursing college in South India. Objective: The aim was to develop and test an Android based OCP-MALL application for user acceptability and effectiveness in improving OCP performance and decreasing the perceived language difficulty. Methodology: Sixty-two student nurses from a reputed nursing college in Chennai, South India, using Android mobile phones participated in the study. All the participants were given access and instructions on the use of OCP-MALL app. A comparison of pre and post-test of perceived level of language difficulty and OCP pre and post score along with users’ acceptance were collected. Results: The users’ acceptability showed that all participants rated the clarity in reading the text with highest mean score of 8.29 and std of 1.276, simplicity in navigation – moving to next page with next highest mean score of 8.19 and std of 1.526, clarity in text application layout with a mean score of 8.14 and std of 1.497 and user friendliness of the application with a mean score of 8.13 and std of 1.393. Conclusion: This startup OCP-MALL app user satisfaction feedback proves that Indian ELT trainers can create cost-effective and need-based m-learning applications. © 2023 by the authors of this article. Published under CC-BY.

关键词： Students

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：