检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2023年第1期4卷 148-160页

作者： Pan, Zhaoqing Yuan, Feng Wang, Xu Xu, Long Shao, Xiao Kwong, Sam the School of Electrical and Information Engineering Tianjin University Tianjin300072 China the College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China the Key Laboratory of Solar Activity National Astronomical Observatories Chinese Academy of Sciences Beijing100012 China the School of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China the Department of Computer Science City University of Hong Kong Hong Kong

No-reference image quality assessment (NR-IQA) aims to evaluate image quality without using the original reference images. Since the early NR-IQA methods based on distortion types were only applicable to specific distortion scenarios, and lack of practicality, it is challenging to designing a universal NR-IQA method. In this article, a multibranch convolutional neural network (MB-CNN) based NR-IQA method is proposed, which includes a spatial-domain feature extractor, a gradient-domain feature extractor, and a weight mechanism. The spatial-domain feature extractor aims to extract the distortion features from the spatial domain. The gradient-domain feature extractor is used to guide the spatial-domain feature extractor to pay more attention to the distortions of the structure information. Particularly, the spatial-domain feature extractor uses the hierarchical feature merge module to realize multiscale feature representation, and the gradient-domain feature extractor uses pyramidal convolution to extract the multiscale structure information of the distorted image. In addition, a position vector is proposed to build the weight mechanism by considering the position relationships between patches and its entire image for improving the final prediction performance. We conduct the experiments on five representative databases: LIVE, TID2013, CSIQ, LIVE MD and Waterloo Exploration Database, and the experimental results show that the proposed NR-IQA method achieves the state-of-the-art performance, which demonstrate the effectiveness of our proposed NR-IQA method. The code ofthe proposed MB-CNN will be released at https://***/NUIST-Videocoding/MB-CNN. © 2020 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

A Brief Overview of Deep Learning Approaches for IoT Security 4

A Brief Overview of Deep Learning Approaches for IoT Securit...

引用

4th International Conference on Computing, Mathematics and engineering Technologies, iCoMET 2023

作者： Hassaan Khalid, Muhammad Sharif, Hanan Rehman, Faisal Naeem Ullah, Muhammad Shaukat, Shahbaz Maqsood, Hadia Nouman Ali, Chaudhry Hussain, Ayaz Iftikhar, Irfana Lahore Leads University Department of Computer Science & Information Technology Lahore Pakistan Mehran University of Engineering and Technology Szab Department of Software Engineering Khairpur Mir's Pakistan

ISBN: (纸本)9798350335316

The continuous increasing usage of internet devices in many areas of human life is continuously growing and demanding a proper method to protect these IoT devices from cyber-attacks and vulnerabilities. In this aspect, deep learning neural networks are a very helpful and beneficial method to provide protection to internet devices in many aspects. This study's objective is to systematically research and examine the background of research about neural networks tactics functional to different internet-based devices' safety use-cases. We put the influences we looked at into many different groups to show where this research is lacking. This particular research or findings mainly captures the articles related to 'Deep neural networks', 'Cyber risks' and 'IOT' in four databanks, namely Science Direct, ACM Digital Library, IEEEXplore and Springer Link. These studies concern 3 main studies, which involve safety aspects, their own Deep Learning network designs, and the occupied datasets. The final round is to find out the loopholes to be examined in the future and vulnerabilities and drawbacks in the IoT security scenario. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Innovating Project Management: AI Applications for Success Prediction and Resource Optimization 2nd

Innovating Project Management: AI Applications for Success P...

引用

2nd International Conference on Advances in Computing Research, ACR 2024

作者： Tarawneh, Monther AbdAlwahed, Huda AlZyoud, Faisal Computer Science Department Isra University Amman Jordan Software Engineering Department Isra University Amman Jordan Information Technology Department Tafilah Technical University Tafila Jordan

ISBN: (纸本)9783031569494

The revolution of Artificial Intelligence (AI) has made transformative changes in all industries. The field of software engineering has great benefit from AI by Automat all process. Applying Artificial intelligence (AI) technologies, particularly Deep Neural Network (DNN) models, to project management will transform traditional methodologies to new ways. This work investigates how AI can be used within project management to better allocate resources, estimate time, and predict costs. Data from many recourses used to improve accuracy in project planning, refine how risks are managed, and develop new methods. Data includes real projects portfolio, open-source data, and simulated data. The integration of AI in project management examines project success and client satisfaction. This work shows 99% accuracy for learning and 78% for testing of predicting project success and highlights the need to constantly update methods to effectively use the big potential changes AI can bring to project management. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Secret Sharing Based Key Agreement Protocol for Body Area Networks 18th

Secret Sharing Based Key Agreement Protocol for Body Area N...

引用

18th International Conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2024

作者： Sheng, Weihong Cai, Bin Hu, Chunqiang Li, Ruinian School of Big Data and Software Engineering Chongqing University Chongqing China Computer Science Department Bowling Green State University Bowling Green United States

ISBN: (纸本)9783031714634

In order to provide more comprehensive medical services and personalized health monitoring according to individual needs, Body Area Networks (BANs) have been extensively studied by many researchers. As BANs involve the transmission of personal private data, the security of the communication is of utmost importance. Unfortunately, existing encryption techniques cannot be directly applied with the limited power or computation ability of the sensors in BANs. An alternative direction is to use physiological signals for key agreement. However, many of the current physiological signal-based key agreement schemes either have high overheads or are vulnerable to certain security issues. In this paper, we proposed a novel secret sharing and Bloom filter based key agreement scheme that balances overhead and security for BANs. Also, we use an approximate hash table to free ourselves from the problem of dependence on the ordering of features, which has been neglected by previous researchers. We validate the security of our scheme with based on real datasets and compare overheads with other solutions. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Internal department Budget Forecasting of a Company: Benchmark of Artificial Neural Networks

Internal Department Budget Forecasting of a Company: Benchma...

引用

2022 Advances in Science and engineering Technology International Conferences, ASET 2022

作者： Akpinar, Mustafa Akpinar, Kevser Ovaz Sakarya University Software Engineering Department Sakarya Turkey Sakarya University Computer Engineering Department Sakarya Turkey

ISBN: (纸本)9781665418010

Budget forecasting plays an essential role in management activities. Governments, corporations, and companies want to know what they are spending in the future periods. It helps plan the investments, produces, human resources and affects companies' future. The purpose of this paper is to estimate the budget for a company. Independent variables of the study are the last month and the last 12 months of the budget. Different training errors, hidden layers, dividing data are examined to determine the proper model. The neural network is used for forecasting, and results are shown with mean absolute percent error. The results showed that the number of hidden layers and dividing the data as a training-validation-test decreased the error in the budget forecasting. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Diagnosis and Identification of Citrus Canker Growth Rate Using Machine Learning 4

Diagnosis and Identification of Citrus Canker Growth Rate Us...

引用

4th IEEE International Conference on Pattern Recognition and Machine Learning, PRML 2023

作者： Zainab, Naureen Afzal, Hammad Arif, Fahim Ghafoor, Abdul Iltaf, Naima Zakria, Muhammad Hyder, Muhammad Javed Ahsan, Rafia National University of Sciences and Technology Department of Computer Software Engineering Islamabad44000 Pakistan Park Road Islamabad44000 Pakistan Department of Mechanical Engineering Islamabad44000 Pakistan

ISBN: (纸本)9798350324303

Citrus canker is a bacterial disease caused by Xanthomonas citri pv citri. Mainly the research in the field of Citrus canker has been done on fruits;early detection of disease on leaves can help in adopting preventive measures at early stage. The present study focuses on the detection of Citrus canker in leaves and classification of six different growth stages/levels of disease: water soaking, yellow initiation, chlorosis, and blister formation, canker infection (50%), canker infection (100%). The primary dataset was developed by taking images of citrus leaves infected by X. citri for the specified time. The proposed strategy is based on the detection of the lesion spot on citrus leaves and the classification of citrus disease stages/level was done to evaluate the growth rate of citrus canker through six distinct growth levels and evaluate affected area of leaf with each passing day. The entire processing includes Pre-processing, Segmentation, Features extraction and perform Classification using four different classifiers which include SVM, KNN, Naive Bayes, and Neural Network. The efficiency of different classifiers was 96.77% by SVM, followed by KNN 90%, NB 84% and NN 82% respectively. The lowest execution time was achieved by NB 0.011s, followed by KNN 0.015s, SVM 0.021s, and N.N. 0.216s. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Impact of Digital Twin Technology Utilization in Manufacturing on Sustainability: An Industrial Case Study

Impact of Digital Twin Technology Utilization in Manufacturi...

引用

2023 Portland International Conference on Management of engineering and Technology, PICMET 2023

作者： Firat Unal, A. Albayrak, Ozlem Unal, Perin University of California Electrical and Computer Engineering Los Angeles United States Teknopar Research and Development Ankara Turkey Tedu Software Engineering Department Ankara Turkey

ISBN: (纸本)9781890843434

Parallel to the advancements in technologies that form the core of Industry 4.0, there is an accelerated use of digital twins in many industries. Digital twin utilization aims at various objectives including but not limited to increasing overall equipment efficiency, minimizing energy consumption, enabling predictive maintenance, process optimization, condition monitoring, and waste minimization. Being one of the essential components in contemporary technology management, digital twins positively impact economic and environmental sustainability. This study briefs the management and development phases of a cognitive digital twin implemented as an H2020 Research and Development project for a steel pipe manufacturing factory. The study also presents literature review results related to the impact of digital twins on sustainability, with a special emphasis on energy consumption. The study explains the experiences and the lessons learned, during the digital twin project. Based on the observed experiences, the authors state that in the use of the digital twin technology, the evidenced benefit of technology is a major reason for the technology utilization. The developed digital twin enabled a 10% decrease in energy consumption of the production line and resulted in a reduction in carbon footprint. © 2023 PICMET (Portland International Center for Management of engineering and Technology(.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Generation of Substitution Box Structures Based on Blum Blum Shub Random Number Outputs 16

Generation of Substitution Box Structures Based on Blum Blum...

引用

16th IEEE International Conference on Advanced Trends in Radioelectronics, Telecommunications and computer engineering, TCSET 2022

作者： Ari, Ali Ozkaynak, Fatih Inönü University Department of Computer Engineering Malatya Turkey Firat University Department of Software Engineering Elazig Turkey

ISBN: (纸本)9781665468619

One of the most important milestones in our transformation into a digital society is the effective adoption of Internet technologies by all stakeholders of the society. The critical factor in this adoption has been the trust model provided through cryptographic protocols. However, the secure environment that tries to be created with cryptographic algorithms is constantly under attack threat with technological developments. Therefore, it is necessary to develop new algorithms resistant to new attacks. In this study, a new approach is proposed for substitution box structures, which is a cryptographic component that can be used as a precaution against side channel attacks. The success of the obtained component has been analyzed for five basic substitution box design metrics. Successful experimental results indicate that the proposed approach have various potentials for new practical applications that can be designed in the future. © 2022 IEEE.

关键词： Side channel attack

来源：评论

学校读者我要写书评

暂无评论

Optimizing MEMS Optical Arrays with Silicon Micro Mirrors using Machine Learning Techniques 3

Optimizing MEMS Optical Arrays with Silicon Micro Mirrors us...

引用

3rd International Conference on Computational Modelling, Simulation and Optimization, ICCMSO 2024

作者： Joshi, Vilas Ramrao Sharma, Surender Kumar Galande, Vijay Agatrao Sachin Patil, Pallavi Patil, Ushadevi Suttarwala, Hussain Sharma, Deepak K. Savitribai Phule Pune University Department of Computer Engineering Pune India Poornima University Department of Electrical Engineering Jaipur India KJEI's Trinity Academy of Engineering Department of Engineering Science Pune India Genba Sopanrao Moze College of Engineering Department of Civil Engineering Pune India American Express Senior Software Engineer PhoenixAZ85054 United States University of Technology Jaipur India

ISBN: (纸本)9798350361391

In the rapidly evolving landscape of optical microsystems, the infusion of Machine Learning (ML) techniques stands out as a catalyst for unprecedented progress. This research paper delves into the intricate interplay between Micro-Electro-Mechanical Systems (MEMS), optical arrays, and silicon micro mirrors, shedding light on the transformative prowess unleashed by Machine Learning in optimizing these intricate components. Focusing on the limitations posed by conventional designs, the paper not only illuminates the challenges encountered but also presents a compelling narrative of how ML algorithms emerge as formidable allies, poised to surmount these hurdles with ingenuity and precision. The exploration extends beyond a mere technical discourse;it unfolds as a narrative of innovation, where the convergence of MEMS, optical arrays, and silicon micro mirrors, guided by the intelligence of Machine Learning, transcends traditional boundaries, propelling optical microsystems into an era of unparalleled efficiency and adaptability. This research beckons a new epoch, where the intricate dance of silicon micro mirrors and the intricate mechanics of MEMS find harmony through the symphony of Machine Learning, reshaping the landscape of optical microsystems and inspiring future possibilities that were once deemed beyond reach. © 2024 IEEE.

关键词： Microchannels

来源：评论

学校读者我要写书评

暂无评论

ML-Based Service Type Priority Decision Method Using Ambient Information for 5GB

ML-Based Service Type Priority Decision Method Using Ambient...

引用

2023 International Conference on Smart Applications, Communications and Networking, SmartNets 2023

作者： Altunan, Umut Sazak, Halenur Yazar, Ahmet Eskisehir Osmangazi University Department of Electrical and Electronics Engineering Eskisehir Turkey Eskisehir Osmangazi University Department of Computer Engineering Eskisehir Turkey Sakarya University Department of Information Systems Engineering Sakarya Turkey Eskisehir Osmangazi University Department of Software Engineering Eskisehir Turkey

ISBN: (纸本)9798350302523

5G communications systems offer several types of service groups include enhanced mobile broadband (eMBB), ultra-reliable low-latency communications (URLLC), and massive machine-type communications (mMTC). The ability to meet various mobile communications requirements of different users is ensured by these service groups. In this paper, a novel service type priority decision method is proposed for 5G and beyond (5GB) systems to determine the most needed service group under a specific region. This approach is useful for the resource allocation planning and optimization through a coverage region. The proposed method is based on the machine learning (ML) usage with several ambient information. Instance-based and model-based techniques are compared for ML. Also, the ensemble methods are tested on the generated synthetic dataset. © 2023 IEEE.

关键词： Machine learning

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：