检索结果-内蒙古大学图书馆

12th China Satellite Navigation Conference, CSNC 2021

作者： He, Xiongwen Xu, Mingwei Yan, Dong Qi, Zheng Yan, Hongcheng Yang, Lijun Jia, Weisong Department of Computer Science and Technology Tsinghua University Beijing China Beijing Institute of Spacecraft System Engineering China Academy of Space Technology Beijing China

ISBN: (纸本)9789811631450

This paper focuses on the requirements of integrated space and onboard high-speed networking, standardization of satellite ground interface, reliable transmission, dynamic routing and dynamic access of the next generation navigation satellite constellation, conducts a comprehensive investigation on the protocols of Consultative Committee for Space Data systems (CCSDS), ECSS, Internet engineering Task Force (IETF) and other international standards organizations, establishes integrated space and onboard network protocol architecture for next generation navigation satellites. The standards involved in the protocol architecture are systematically constructed, and suggestions on standard formulation and application are given, so as to provide technical support for the establishment of next generation navigation network protocol architecture. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Encrypting and Predicting Medical Diagnosis Data 10

Encrypting and Predicting Medical Diagnosis Data

引用

10th International Conference on Internet of Everything, Microwave engineering, Communication and Networks, IEMECON 2021

作者： Faiz, Furqan Mohammed Umar Farooq, Mohd Faiz, Adnan Muhammed Pasha, Mohammed Hijab, Maniza Muffakham Jah College of Engineering Technology Osmania University Department of Computer Science Enginnering Hyderabad India Assistant System Engineering-Trainee Tata Consultancy Services Hyderabad India

ISBN: (纸本)9781665426862

With the rapid development in technology across various branches, data security is the rising concern. Currently, in the healthcare sector, users can contact doctors/hospitals, study or analyze symptoms using wide range of applications and information available on internet, and also occasionally predict diseases. Individuals can easily drop by an appropriate portal and enter their symptoms which then subsequently applies machine learning algorithm to the mentioned data and finally calculate chances of disease incidence. By such a process one may encounter several problems., as these hardly employ any successful data protection services. Therefore, there is a need to maintain the privacy of the individual. Here we focus on designing a CatBoost model with homomorphic encryption for protecting the patient data to make it more secure. Thus finally providing encrypted prediction of diagnosis which is efficient and effective. © 2021 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Algorithm for Room Temperature Detection Using Bioelectric Potential of Plant Data

SSRN

引用

SSRN 2024年

作者： Tahyudin, Imam Rozaq, Hasri Akbar Awal Nambo, Hidetaka Department of Information System Faculty of Computer Science Amikom Purwokerto University Jl. Letjendpol Soemarto Banyumas Purwanegara 53127 Indonesia Graduate School of Informatics Faculty of Computer Science Gazi Üniversitesi Ankara Yenimahalle Turkey Graduate School of NST Division of Electrical Engineering and Computer Science Kanazawa University Kakumamachi Ishikawa Kanazawa920-1192 Japan

Plants are living things that have many secrets in them. One that is very interesting is how plants can communicate with the surrounding environment through the activities of the plants themselves. Then, from this communication activity, plants produce electricity, which we can use to study further the behavior of these plants, commonly known as bioelectric potential. This study has aim to analyze the ability of bioelectric potential of plant to response a room temperature in different condition. This research is analyzed using a deep learning algorithm, namely Long-Short Term Memory (LSTM). The data was recording using a modified amplifier and the output is signal data. The signal obtained is an analog signal which is then converted into a digital signal. The data that has been obtained is then transformed first before being analyzed using the Wavelet Transform method. The algorithm will be evaluated between the baseline and hyperparameter tuning models. The result showed that hyperparameter tuning has the smallest RMSE. Therefore, it is better than baseline model. © 2024, The Authors. All rights reserved.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

MN1 DN121 Vg19: A Multi-stream Ensemble Model for Detecting External Damage on Tomato Surface

MN1 DN121 Vg19: A Multi-stream Ensemble Model for Detecting ...

引用

International Conference on Electrical and computer engineering (ICECE)

作者： Most. Jebun Nahar Juthy Tauhid Md. Faruk Hosen Md. Abul Basara Mst. Nargis Aktar Muhammad Shahin Uddin Monir Morshed Department of Information and Communication Technology Mawlana Bhashani Science and Technology University Tangail Bangladesh Department of Computing and Information System Daffodil International University (DIU) Ashulia Dhaka Bangladesh Department of Computer Science and Engineering Uttara University (UU) Holding 77 Beribadh Road Dhaka Bangladesh

ISBN: (数字)9798331531782

ISBN: (纸本)9798331507923

The use of advanced computer vision and powerful deep-learning capabilities is increasingly important in the agricultural industry, particularly for monitoring crops and detecting diseases. However, detecting external damage to fruit crops remains a significant challenge. In our study, we introduced a multi-stream ensemble model called MN1_DN121_Vg19, which is designed to identify external damage on tomato surfaces. We separately used different pre-trained approaches, including InceptionV3, ResNet50, ResNet101, VGG16, VGG19M obileNetV1, and DenseNet121, and we examined how well they performed. After evaluating their performance, We merged the three wellknown pre-trained methods: MobileNetV1, DenseNet121, and VGG19, and extracted the learned features from these models. After that, we fine-tuned some of the top layers to effectively learn the features from our used dataset. The top 10 layers of DenseNet121 and MobileNet, as well as the top 4 layers of VGG19, were fine-tuned to create the merged model. The accuracy of the suggested multi-stream ensemble model was $98.51 \%$ using a dataset of 6500 images across 4 classes. When compared to existing pre-trained models, our merged model demonstrated superior performance across all metrics.

关键词： Measurement computer vision Accuracy Computational modeling Crops Feature extraction Monitoring Residual neural networks Diseases Defect detection

来源：评论

学校读者我要写书评

暂无评论

Enhancing IT Risk Management in XYZ Vocational School: Leveraging COBIT 5 Framework with the APO12 Domain

Enhancing IT Risk Management in XYZ Vocational School: Lever...

引用

Emerging Technologies for Sustainability and Intelligent systems (ICETSIS), ASU International Conference in

作者： Winanti Erick Fernando Jullend Gate Department of Information Systems Universitas Insan Pembangunan Indonesia Information System Faculty of Engineering and Informatics Universitas Multimedia Nusantara Tangerang Indonesia Computer Science Department BINUS Online Learning Bina Nusantara University Jakarta Indonesia

This article explores the importance of IT risk management, especially at XYZ Vocational School. The agency is equipped to manage business risks, emphasizing the need to improve decision-making and risk mitigation by identifying potential hazards and evaluating internal and external threats, including hacking risks. The research investigates IT risk management at XYZ Vocational School using a qualitative and quantitative method with a focus on the APO12 COBIT 5 domain: Align, plan, and organize. It assesses subdomains such as data collection, risk analysis, profile maintenance, risk articulation, portfolio management, and response strategies. Conclusively, the research reveals institutional IT capabilities at level 1 (Performed Process) in the APO12 subdomain. Recommendations include developing COBIT-compliant SOPs for processes at this level, highlighting the need for further improvements in IT governance. This study provides valuable insights into IT risk management practices, offering recommendations for improving IT governance in educational settings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multiperspective Quality Model for Process Design 2

Multiperspective Quality Model for Process Design

引用

2nd International Conference on Information systems and Software Technologies, ICI2ST 2021

作者： Mosquera, Estefania Patricia Galvez Gaibor, Marco Oswaldo Santorum Escuela Politécnica Nacional Faculty of System Engineering Quito Ecuador Escuela Politécnica Nacional Department of Informatics and Computer Science Quito Ecuador

ISBN: (纸本)9780738143613

Organizational processes are constantly evolving due to different factors. To take care of this continuous transformation, these processes must be flexible enough, which implies their formalization and optimal design. To operate efficiently, the organizations must identify and manage all their processes, therefore it is important to ensure their quality. There are companies in Ecuador devoted to providing consulting services for management of processes;to that end they use methodologies, techniques, and good practices, in order to provide optimal services to meet the expectations of their customers. However, this not always *** objective of this work is to present a proposal of a model to guide the quality in the design of processes, which allows expert companies to perform a design following good practices and to evaluate the quality from syntactic, semantic, and pragmatic perspectives. © 2021 IEEE.

关键词： Design

来源：评论

学校读者我要写书评

暂无评论

START: Automatic Sleep Staging with Attention-based Cross-modal Learning Transformer

START: Automatic Sleep Staging with Attention-based Cross-mo...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jingpeng Sun Rongxiao Wang Gangming Zhao Chen Chen Yixiao Qu Jinpeng Li Xiyuan Hu Yizhou Yu School of Computer Science and Engineering Nanjing University of Science and Technology Institute of Automation Chinese Academy of Sciences College of Mathematics and System Science Xinjiang University Department of Computer Science The University of Hong Kong Ningbo Institute of Life and Health Industry University of Chinese Academy of Sciences

Automatic sleep staging is vital to scale up sleep assessment and diagnosis to serve millions experiencing sleep deprivation and disorders and enable longitudinal sleep monitoring in home environments. However, how to learn from multi-channel raw physiological signal inputs (e.g., EEG and EOG) to capture the sleep stage and physiological signal relations remains a big challenge. In this paper, we propose a sleep staging model, named Sleep Staging Cross-modal Transformer (START), which is a transformer-only method for sleep stage classification. Our model is capable of learning a joint representation from both EEG and EOG signals by using a cross-modal fusion strategy. Experimental results show that our model outperforms the state-of-the-art methods on two public datasets. Furthermore, our model provides considerable reductions in parameters and training time compared to previous methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Challenges in internet of things towards the security using deep learning techniques

引用

Measurement: Sensors 2022年 24卷

作者： Ravikumar, K.C. Chiranjeevi, Pandi Manikanda Devarajan, N. Kaur, Chamandeep Taloba, Ahmed I. Department of Computer Science Engineering Sridevi Women's Engineering College India Ace Engineering College Ghatkesar Hyderabad India Department of Electronics and Communication Engineering Malla Reddy Engineering College Medchal - Malkajgiri District Telangana 500100 India Computer Science Department Jazan University Jizan Saudi Arabia Department of Computer Science College of Science and Arts in Qurayyat Jouf University Saudi Arabia Information System Department Faculty of Computers and Information Assiut University Assiut Egypt

Securing IoT devices and delivering end-to-end security in an IoT ecosystem presents a variety of issues. Regardless of the way that security concerns are not new with regards to data innovation, the qualities of numerous IoT arrangements give new and special security issues. It's anything but a main concern to resolve these issues and guarantee the security of IoT items and administrations. Clients should have certainty that IoT gadgets and related information administrations are secure, especially as this innovation develops more unavoidable and coordinated into our day by day lives. The goal of this article is to provide an overview of the Internet of Things and to go through all of the known security concerns that the Internet of Things faces today. All of the findings are based on publicly available documentation for essential Internet of Things components. Threats to IoT security, both inherent and newly developed, are discussed, as well as numerous potentials. The attack surfaces of the IoT system are examined, as well as the potential hazards associated with each surface. We then, at that point go over the benefits, weaknesses, and qualities of every Deep Learning approach for IoT security. We talk about the advantages and disadvantages of applying Deep Learning to IoT security. Future exploration headings could be founded on these chances and difficulties. © 2022

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Honeypot Comparison of Attack Detection and Mitigation of SSH Attack

Honeypot Comparison of Attack Detection and Mitigation of SS...

引用

Delhi Section Conference (DELCON), IEEE

作者： Wasif Ali Ahthasham Sajid Tanvi Ajit Ghodke Rida Malik Neeru Malik Keshav Kaushik Department of Cyber Security Riphah Institute of System Engineering Riphah International University Islamabad Pakistan Department of Computer Science and Engineering Pimpri Chinchwad University Maharashtra India School of Engineering & Technology Pimpri Chinchwad University Pune Maharashtra India Amity School of Engineering and Technology Amity University Mohali India

ISBN: (数字)9798331518592

ISBN: (纸本)9798331518608

This research study addresses the importance of honeypots at multiple levels, which includes but not limited to placement in network or group of networks working alongside in an organization. This paper talks about the usage of multiple honeypots working alongside to log useful data for the mitigation of ongoing bot or actual attack this approach helps the organization better understand the threat they are dealing and the techniques which they can use to overcome the gap of the unseen security risks. The comparison will shed better light to the working and attack patterns of the ongoing attacks, gaining more confidence on using the honeypot for better protection. This allows strategic, optimized and critical insight to the evolving attack patterns.

关键词： Production systems computer hacking Prevention and mitigation Interactive systems Intrusion detection Organizations Real-time systems Security Reliability Protection

来源：评论

学校读者我要写书评

暂无评论

Integrative Multi-Source Mapping of Coastal Environments Using Hy-perspectral Data Fusion Platforms

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年

作者： Han, Huimin Por, Lip Yee Talpur, Bandeh Ali Hashim, Muhammad Yang, Jing Saidani, Taoufik Djumaniyazova, Mukhayya Xusinovna Madrakhimovich, Khudoynazarov Egambergan Talpur, Kazim Raza Hainan Vocational University of Science and Technology Mechanical and Electrical Engineering Col-lege Haikou571126 China Uni-versiti Malaya Department of Computer System and Technology Kuala Lumpur50603 Malaysia Trinity Col-lege Dublin School of Computer Science and Statistics Ireland National Textile Uni-versity Faisalabad Faisalabad Business School Pakistan Universiti Malaya Department of Computer System and Technology Faculty of Computer Science and Information Technology Kuala Lumpur50603 Malaysia Northern Border University Center for Scientific Research and Entrepreneurship Arar73213 Saudi Arabia Urganch State University Pedagogy and Psychology Department Uzbekistan Mamun University Uzbekistan Jamshoro Institute of Health Management and Re-search Sciences Sindh Pakistan

Hyperspectral images (HSIs) not only have a large number of spectral features, but also show a comprehensive spa-tial distribution of land cover and offer substantial advantages in the fine classification of ground materials. However, due to the high dimensionality and redundancy of HSIs and class imbalance in hyperspectral datasets, improving classification performance is still a huge challenge. Recently, graph-based learning algorithms are proven to be better classifiers for high dimensional data. Learning graph data and modeling spatial topological links be-tween features are significantly more accessible and more effective with graph-based deep learning, which has been demonstrated to be a promising approach. In the past few years, convolutional neu-ral networks (CNNs) and graph convolutional networks (GCNs) have achieved good results in HSI classification, but CNNs strug-gle to achieve good accuracy in low samples, while GCNs have a substantial computational cost. To resolve these issues, this paper proposes a feature fusion model using a 3D-CNN and hybrid-GAT named FFCHG. The algorithm consists of two elements: the 3D-CNN, which produces good classification for 3D HSI cube data, and GAT-based encoder and decoder modules that help in im-proving the classification accuracy of the 3D-CNN. Finally, the multiple features are merged with the help of two neural network models. Experiments on three public HSI datasets show that the proposed methods perform better than other state-of-the-art methods using the limited training samples and in low classifica-tion time with accuracy of more than 90% in all datasets and kappa with more than 91% for each dataset. © 2025 IEEE.

关键词： Convolutional neural networks

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：