检索结果-内蒙古大学图书馆

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Govindaram, Anitha Prasath, J.S. Suganya, A. Jayasakthi, K. rajkumar, N. Jose Anand, A. Thandalam Chennai602105 India Department of Computer Science and Engineering Sapthagiri NPS University Chikkasandra Karnataka Bengaluru560057 India Department of Artificial Intelligence and Data Science Anand Institute of Higher Technology Kazhipattur Tamil Nadu Chengalpattu603103 India Department of ECE KCG College of Technology Karapakkam Tamil Nadu Chennai600097 India Department of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Thiruvalluvar Tamil Nadu Avadi600062 India

ISBN: (纸本)9798331522667

Artificial Intelligence (AI) part of Federated Learning (FL) builds on distributed data and modelling to deliver learning to the edge of the device. Even though FL has been celebrated as the beginning of AI, it has not yet gained mainstream adoption, mostly because of concerns about privacy and security. Security and privacy issues with the FL technique need to be found, examined, and recorded before at this point, we can expect to see significant progress in this field of study or widespread adoption of the FL approach. This article aims to afford a complete review of the methods discussed with FL for huge data by introducing studies from six angles: blockchain, privacy, hybrid approach, VFL, FL, and foundation design and device heterogeneity. This survey can address the challenges of FL, offer their predictions for the future of research on the subject, outline how FL is now being put to use in the real world, and with most salient features. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Generative Artificial Intelligence Opportunities and Threats: Bibliometric Analysis

Generative Artificial Intelligence Opportunities and Threats...

引用

International Conference on Computer Science and Engineering (UBMK)

作者： Betül Ersöz Şeref Sağıroğlu Halil İbrahim Bülbül Artificial Intelligence and Big Data Analytics Security R&D Center Gazi University Ankara Türkiye Computer Education and Instructional Technology Gazi University Ankara Türkiye

ISBN: (数字)9798350365887

ISBN: (纸本)9798350365894

This study conducts a bibliometric analysis on 4,262 works published under the title “Generative Artificial Intelligence-GAI” between 2020 and 2024, sourced from Web of Science (WoS). The analysis covers keyword clouds, the most frequently used terms in article titles, types of publications, fields with the highest volume of publications. The research on GAI, a rapidly growing subfield of artificial intelligence (AI), is examined, the current state is critically analyzed, and recommendations are provided concerning the opportunities and threats in the responsible development of AI.

关键词： Computer science Generative AI Computational modeling Bibliometrics robots research and development Education data analysis Chatbots Python

来源：评论

学校读者我要写书评

暂无评论

Predictive Maintenance in IoT Networks Using a Temporal Attention Mechanism Based Federated Convolutional Neural Network 4

Predictive Maintenance in IoT Networks Using a Temporal Atte...

引用

4th IEEE Asian Conference on Innovation in technology, ASIANCON 2024

作者： Guduri, Naga Venkata ramakrishna Charaan, r.M. dilip Kalaiyarasi, r. Samuthira Pandi, V. reddy, d.Laxma Selvaprabhu, T. University of Technology and Applied Sciences Faculty of Engineering Al Musannah Oman Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Rajalakshmi Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India Chennai Institute of Technology Centre for Advanced Wireless Integrated Technology Tamil Nadu Chennai India Mlr Institute of Technology Department of Ece Hyderabad India Dhanalakshmi College of Engineering Department of Cse Tamil Nadu Chennai India

ISBN: (纸本)9798350354218

In the era of Industry 4.0, edge devices in industrial settings generate vast amounts of data crucial for process optimization and Predictive Maintenance (PM). Traditional cloud-based approaches for handling this data are becoming untenable due to cost, latency, and privacy issues. Federated learning emerges as a viable solution, offering localized and efficient data processing while mitigating these challenges. This paper presents a Federated Convolutional Neural Network with Temporal Attention Mechanism (FedCNN-TAM) for PM tasks in Internet of Things (IoT) networks. This model leverages temporal features in sensor data to enhance predictive accuracy. Evaluated on the CMAPSS dataset, FedCNN-TAM outperforms representative models with a significant performance gain. This model exhibits the potential for broader applications in industrial IoT, setting the stage for future research on its scalability and adaptability to multi-modal data types. © 2024 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Advancements in Artificial Intelligence for Better Image Analysis, recognition, and Interpretation in the Field of Image Processing 2

Advancements in Artificial Intelligence for Better Image Ana...

引用

2nd IEEE Global Conference on Communications and Information Technologies, GCCIT 2024

作者： Saravanan, V. Adaikkammai, A. Sasikala, G. Iyswariya, A. Babisha, A. Latha, M. Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Nano Electronics Materials and Sensors Tamilnadu Chennai India R.M.D. Engineering College Department of Computer Science and Business Systems India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Ece Avadi Chennai India R.M.K. Engineering College Department of Ece Chennai India Panimalar Engineering College Department of Artificial Intelligence and Data Science India Srm Institute of Science and Technology Department of It India

ISBN: (纸本)9798350388916

The rapid advancement of artificial intelligence (AI) has brought about a significant revolution in image processing. This revolutionary technology has enabled the analysis, recognition, and interpretation of images in ways that were previously inconceivable. An investigation into the most recent developments in artificial intelligence techniques that have improved the efficiency and precision of image processing tasks is presented in this study. We survey the emergence of transformer architectures and the integration of deep learning models, namely Convolutional Neural Networks (CNNs), to explore how these technologies have transformed the understanding and application of images in several industries. An overview of existing image processing methods and the limits of those approaches is presented at the beginning of our research. This highlights the necessity of more advanced AI-driven solutions. After that, we examine the advancements that have been made in artificial intelligence, such as the incorporation of attention processes, the development of more effective CNN architectures, and the utilisation of generative adversarial networks (GANs) for the purpose of picture synthesis and augmentation. The purpose of this research is to investigate the impact that artificial intelligence has on particular applications of image processing, such as autonomous car navigation systems, facial recognition, medical imaging, and satellite images analysis. Specifically, we focus on the enhancements in diagnostic accuracy, environmental monitoring, security, and safety that arose as a result of the adoption of artificial intelligence in these sectors through the use of case studies. Furthermore, we discuss the issues that are associated with artificial intelligence in image processing. These challenges include the necessity for explainable AI models, the requirement for computational resources, and the protection of data privacy. A number of potential solutions to these problems

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimizing dry eye disease diagnosis: Integrating deep learning insights from OSdI questionnaires and ocular blinking videos

Optimizing dry eye disease diagnosis: Integrating deep learn...

引用

2023 International Conference on Computer Application and Information Security, ICCAIS 2023

作者： Wang, Mini Han Lin, Zhiyuan Zeng, Peijin Fang, Xiaoxiao Yu, Yang Hu, Wenhan Liu, Yunxiao Liu, Haoyang Li, Xinyue Jiang, Xudong Chen, Guangshun Zhou, ruoyu Hou, Guanghui Chong, Kelvin K.L. Fang, Junbin The Faculty of Medicine Chinese University of Hong Kong 999077 Hong Kong City University of Macao The Faculty of Data Sciences 999078 China Guangdong Zhuhai519000 China AI and big Data R&D Department Zhuhai Institute of Advanced Technology Chinese Academy of Sciences Guangdong Zhuhai519000 China AI and Ophthalmology R&D Laboratory Perspective Technology Group Guangdong Zhuhai519000 China Beijing Institute of Technology Guangdong Zhuhai519000 China The Department of Dry Eye Disease Zhuhai Aier Eye Hospital Zhuhai519000 China School of Biomedical Engineering Guangdong Medical University Guangdong Dongguan523000 China Faculty of Science and Technology Beijing Normal University-Hong Kong Baptist University United International College Guangdong Zhuhai519000 China School of Optometry and Ophthalmology Tianjin Medical University Tianjin300000 China Department of Optoelectronic Engineering Jinan University Guangdong Guangzhou510000 China

ISBN: (纸本)9781510675032

This study introduces a novel and comprehensive diagnostic approach for dry Eye disease (dEd) by combining a dedicated Ocular Surface disease Index (OSdI) questionnaire and a measurement system tailored for Chinese citizens with the implementation of the YOLOv8 deep learning model. The research involves the analysis of 52 real-world ophthalmic videos to detect eye blinking conditions, with the model trained to identify abnormal blinking patterns through feature extraction such as blink frequency, duration, and irregularities. Performance metrics, including mean Average Precision (mAP), specificity, recall, f1-score, and Frame Per Second (FPS), are measured on a PC (CPU, Core i5-10500H) with an input size of 640*640. The integration of these deep learning methods, utilizing both subjective OSdI questionnaires and objective ocular blinking videos, signifies a groundbreaking approach that enhances diagnostic accuracy for dEd. The study anticipates transformative effects on dEd diagnosis and improved patient outcomes as technology advances. Additionally, the research team introduces a user-friendly system for dry eye detection, named the "AI dry Eye Analytic System," accessible at the UrL "***," demonstrating the practical implementation of the developed methodologies. © 2024 SPIE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Leveraging Machine Learning for Predictive Maintenance in Supply Chain Management Systems

Leveraging Machine Learning for Predictive Maintenance in Su...

引用

2024 International Conference on Science, technology, Engineering and Management, ICSTEM 2024

作者： Sharan, Bediga Vijai, C. Srivastava, Kingshuk Singla, Atul Bhati, Indira Kumar, T.Ch. Anil School of CS & AI SR University Telangana Warangal India Department of Commerce and Business Administration Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai62 India Department of Data Science UPES Uttarakhand Dehradun India Lovely Professional University Phagwara India India Department of Mechanical Engineering Vignan's Foundation for Science Technology and Research Vadlamudi Andhra Pradesh Guntur522213 India

ISBN: (纸本)9798350376913

The purpose of this exploratory research is to investigate the incorporation of machine literacy (ML) techniques for prediction conservation in supply chain management (SCM) systems. The successful operation of force chains is essential to the success of an organization in the modern business environment, which is always shifting and transitioning. When it comes to preemptively managing outfit failures, performing in expensive time-outs, and functional dislocations, conventional conservation techniques frequently fall short unexpectedly. To analyze literal data, detector inputs, and external variables, the utilization of machine learning algorithms makes it possible to anticipate conservation requirements. Through the utilization of prophetic analytics, supply chain management systems can identify hidden faults in the outfit, which enables visionary conservation actions. This study assesses various machine learning models and algorithms that have been adapted to forecast conservation circumstances in supply chain management (SCM) systems. Specific variables such as monitoring the status of the outfit and recognizing failure patterns are taken into consideration. In the end, the purpose of the investigation is to provide insight into the actual implementation of machine learning-driven prophetic conservation methods. This will enable organizations to improve their overall performance and optimize their force chain operations. © 2024 IEEE.

关键词： Maintenance

来源：评论

学校读者我要写书评

暂无评论

A Novel Architecture for Efficient Mobile Communication based on Scattered and diverse Combination using Prioritize and Postoperative Soft Modulation 7

A Novel Architecture for Efficient Mobile Communication base...

引用

7th International Conference on Intelligent Computing and Control Systems, ICICCS 2023

作者： Sumithra, J. Mercy Theresa, M. Geetha Priya, S. Jackson, Beulah Samuthira Pandi, V. Balamurugan, A. R. M. D Engineering College Department of Electronics and Communication Engineering Tamil Nadu India SRM Institute of Science and Technology Department of Data Science and Business Systems Tamil Nadu India R. M. D Engineering College Department of Computer Science and Engineering Tamil Nadu India Vel Tech Rangarajam Dr. Sagunthala R&D Institute of Science and Technology Department of Electronics and Communication Engineering Tamil Nadu India SRM Institute of Science and Technology Department of Electronics and Communication Engineering Tamil Nadu India Chennai Institute of Technology Department of Electrical and Electronics Engineering Tamil Nadu India

ISBN: (纸本)9798350397253

The proposed work suggests a novel approach for the cooperation of geographically scattered individuals and the blending of different points of view. This work ensures that the center on heterogeneous networks in which nodes support both long-range low-rate radio Frequency (rF) interfaces (like cellular) and short-range high-rate rF interfaces (such as IEEE802.11) that communicate over urban rayleigh fading channels. These interfaces are used to connect the devices. The interfaces are what are used to link the various gadgets. This research work proposes and evaluates a wide variety of hierarchically distributed cooperation strategies that can function despite resource restrictions such as limited short-range rF bandwidth. These strategies are contained within the confines of this paradigm, which serves as the framework for proposed work. Post Soft-demodulation Combining, often referred to as PSdC, and Priority Maximum ratio Combining are the two approaches that come highly recommended by our team (PMrC). This work provides evidence that using the offered methods increases throughput, reliability, and signal-to-noise ratio. Moreover, this study found that PMrC and PSdC have the ability to improve throughput performance by more than an order of magnitude across a wide range of communication circumstances. © 2023 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Parasitized Malarial Infected Cell detection through Variance Scaling Kernel Initializer Conv2d

Parasitized Malarial Infected Cell Detection through Varianc...

引用

Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT), International Conference on

作者： M. Shyamala devi d. Umanandhini Aparna Joshi Gowtham dontamsetti Shreyas S Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu India Computer Science & Engineering Pimpri Chinchwad College of Engineering Pune India Artificial Intelligence and Data Science Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu India

Medical pathologists physically examine Plasmodium falciparum parasites infected blood cells that have been infected through a magnifying glass as part of the traditional diagnostic process, which is time-consuming and liable to mistakes. CNN and advanced technology have recently been used to conduct research on optimizing this procedure to identify orientation and geometrical information from blood sample particle images. With this view, this research recommends Variance Scaling Kernel Initializer Conv2d (VSKIC) Sequential model for predicting the infected malaria cell. The Malaria Cell Images dataset from KAGGLE, which contains 27,558 visuals of plasmodium parasites has been used for execution in the suggested VSKIC model. For the purpose of predicting a malarial cell infection, images are preprocessed and fitted using the VSKIC model. Three convolutional layers merged with max pooling layer, and three dense layers that are weight initialized with variance scaling kernel initializer are used as preprocessing steps on the malaria cell images for the purpose of identifying the presence of affected malarial tissue. The picture files were separated into training and evaluation images, and the training Malaria Cell images were used to evaluate the effectiveness of the VSKIC model along with the standard conV2d paradigms. While comparing the suggested model with the available CNN methods, the execution observations made with Python on a V100 Nvidia GPU workstation using 64 and 250 training intervals demonstrates that the proposed VSKIC model predicts with the higher accuracy of 98.96% and Area under curve of 97.8%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

depositional process of hyperpycnal flow deposits:A case study on Lower Cretaceous Sangyuan outcrop in the Luanping Basin,Northeast China

引用

China Geology 2024年第3期7卷 505-516页

作者： de-zhi Yan ru-kai Zhu Hao Shou Zhao-hui Xu Wei-hong Liu Si-cheng Zhu Zhi-cheng Lei Jing-ya Zhang Chang Liu Yi Cai Huai-min Xu Research Institute of Petroleum Exploration and Development PetroChinaBeijing 100083China National Energy Tight Oil and Gas R&D Center Beijing 100083China PetroChina Key Laboratory of Oil and Gas Reservoir Beijing 100083China State Key Laboratory of Petroleum Resources and Prospecting China University of Petroleum(Beijing)Beijing 102249China College of Geosciences China University of Petroleum(Beijing)Beijing 102249China Jiangxi Engineering Laboratory on Radioactive Geoscience and Big Data Technology Department of Information and EngineeringEast China University of TechnologyNanchang 330013China

Sedimentary process research is of great significance for understanding the distribution and characteristics of *** the detailed observation and measurement of the Sangyuan outcrop in Luanping Basin,this paper studies the depositional process of the hyperpycnal flow deposits,and divides their depositional process into three phases,namely,acceleration,erosion and *** the acceleration phase,hyperpycnal flow begins to enter the basin nearby,and then speeds up *** developed in the acceleration phase are *** addition,the original deposits become unstable and are taken away by hyperpycnal flows under the eroding *** a result,there are a lot of mixture of red mud pebbles outside the basin and gray mud pebbles within the *** the erosion phase,the reverse deposits are eroded and become thinner or even ***,no reverse grading characteristic is found in the proximal major channel that is closer to the source,but it is still preserved in the middle branch channel that is far from the *** entering the deceleration phase,normally grading deposits appear and cover previous *** final deposits in the basin are *** are reverse,and others are *** are superimposed with each other under the action of hyperpycnal *** analysis of the Sangyuan outcrop demonstrates the sedimentary process and distribution of hyperpycnites,and reasonably explain the sedimentary characteristics of *** is helpful to the prediction of oil and gas exploration targets in gravity flow deposits.

关键词： Hyperpycnal flow Sedimentary characteristics depositional process Gravity flow deposit Hyperpycnite red mud pebble Gray mud pebble Oil and gas exploration engineering Luanping Basin

来源：评论

学校读者我要写书评

暂无评论

Blockchain and Machine Learning Integration for Safe data Sharing in Finance and Hr

Blockchain and Machine Learning Integration for Safe Data Sh...

引用

2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems, IACIS 2024

作者： Sivakumar, T.B. Prathiba, E. Sharma, Shweta Prasad, rashmi Saket ramaratnam, M.S. Krishnamoorthy, V. School of Computing Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Cse Chennai India Mailam Engineering College Department of Artificial Intelligence and Data Science Mailam India Shambhunath Institute of Engineering & Technology Department of Business Administration Prayagraj India D Y Patil Pgdm Institute Akurdi Pune India Sri Chandrasekharendra Saraswathi Viswa Mahavidyalaya Department of Management Studies Kanchipuram India Kongu Engineering College Department of Management Studies Perundurai Erode India

ISBN: (纸本)9798350360660

Modern finance and Hr businesses have challenges in exchanging data due to centralized systems that are subject to hacking and lack transparency. The study proposes employing blockchain technology and machine intelligence (ML) to address these issues holistically. The proposed system enhances integrity and resilience to assaults by utilizing a decentralized ledger for secure data exchange. ML algorithms enable predictive analytics, risk management, and personalized insights. The proposed system outperforms the existing system in terms of accuracy, security, and efficiency. The accuracy of fraud detection increases from 0.75 to 0.90, as does the estimate of staff turnover from 0.80 to 0.95. The proposed system achieves an overall accuracy of 95%, surpassing the existing system's 85%. Blockchain and ML integration can alter data management methods in finance and Hr industries, with improved security measures resulting in a risk score of 2 compared to 7 in the existing system. © 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：