检索结果-内蒙古大学图书馆

5th IEEE International Conference on Advances in Electronics, computers and Communications, ICAECC 2023

作者： Sheeba, T.M. Antony Raj, S. Albert Anand, M. SRM Institute of Science and Technology Kattankulathur Faculty of Science and Humanities Department of Computer Applications Chennai India SRM Institute of Science and Technology Kattankulathur Faculty of Engineering and Technology Department of Networking and Communications Chennai India

ISBN: (纸本)9798350305449

Optical Coherence Tomography (OCT) is a relatively recent procedure for studying eyes that has proven to be quite beneficial. We propose automatic detection of the RPE (Retinal Pigment Epithelium) layer in Retinal OCT images in this work. The bottom layer of the retina in retinal OCT images is known as the RPE layer, which is extracted in this study and may be studied to diagnose retinal disorders. After effectively increasing the quality of the OCT image using the Wiener filter, we extract the Retinal Pigment Epithelium layer using the Threshold approach. The proposed approach is tested using 40 OCT images of the retina. The results demonstrate 95.50 percent accuracy in RPE layer segmentation. © 2023 IEEE.

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

Optimal Selection of Frequency Band and Wavelet Scattering for Feature Extraction in Multi-class EEG Classification

引用

SN computer science 2025年第2期6卷 1-17页

作者： Shirodkar, Vaishali Edla, Damodar Reddy Kumari, Annu Department of Computer Science and Engineering National Institute of Technology Goa Kottamoll Plateau Goa Cuncolim 403703 India Information Technology Department Goa College of Engineering Farmagudi Goa Ponda 403401 India

Brain–computer interface (BCI) technology has huge potential to transform human–computer interaction across multiple disciplines. Despite efforts, achieving high accuracy in motor imagery (MI) task classification remains difficult. This proposed solution addresses the MI tasks classification challenge utilizing the BCI IV 2a and 2b datasets. Using optimization methods, optimal frequency bands associated with event-related desynchronization were identified to enhance classification accuracy to 90.44% for 2a and 93.78% for 2b datasets. Following band selection, the electroencephalography data were pre-processed, focusing on the identified frequency band, and quadratic interpolation was employed for data augmentation, introducing synthetic data points to improve model generalization and robustness. The proposed method used wavelet scattering transform for feature extraction, which captures both temporal and spectral characteristics. The extracted features set was reduced using common spatial patterns, which utilizes spatial distribution to find discriminative spatial filters. After feature selection simple classifier, recurrent neural network was implemented and compared with many state-of-the-art methods. The system proposed is computationally efficient and lightweight making it applicable to IoT-based applications. The proposed methodology shows that the technique improves BCI classification performance, providing useful insights for applications in healthcare and assistive technologies. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Common spatial patterns Event-related desynchronization Interpolation Motor imagery Optimization Recurrent neural network Wavelet scattering transform

来源：评论

学校读者我要写书评

暂无评论

Automatic Calculation and Detection of Fish Maturity Levels Using Imagery and CNN Methods

Automatic Calculation and Detection of Fish Maturity Levels ...

引用

2024 International Conference on information technology and Computing, ICITCOM 2024

作者： Yustika Manik, Fuzy Harumy, T.H.F. Rilani Manurung, Vindy Anggreani, Dita Universitas Sumatera Utara Faculty of Computer Science and Information Technology Sumatera Utara Medan Indonesia Universitas Sumatera Utara Faculty of Agriculture Sumatera Utara Medan Indonesia

ISBN: (纸本)9798350379839

Fish consumption in Indonesia is still relatively low compared to other countries. This is unfortunate, especially considering how much fish nutrition influences health. To overcome the problem of low consumption of marine fish due to its relatively high price, efforts are needed to develop freshwater fish. However, human population growth, climate change, and unsustainable fishing practices have placed enormous pressure on fisheries resources in the region. Biomass estimation in aquaculture can be done with the basic operation of counting fish. It is important to encourage more efficient breeding and sensible feeding. Fish counting is a reference for determining survival rates, regulating breeding density, and marketing transportation management. This helps farmers in accurately estimating production potential and calculating reproduction rates. Most freshwater aquaculture in the region currently uses labor-intensive or destructive fish counting techniques. This takes a lot of time, is prone to mistakes, and can easily harm the fish's body. So we need a technique that can count fish automatically, precisely, and effectively. technology makes it possible to take digital images of fish quickly and without damaging fish populations. This approach is important because of its high efficacy, affordability, and simplicity of use. To identify and count the number of fish, convolutional neural networks (CNN) will be used in this investigation. Underwater fish image processing technology presents significant challenges due to the complex underwater environment resulting in changing lighting conditions. It is known that the CNN algorithm has an average calculation and detection accuracy rate of 94.27% based on evaluation results. © 2024 IEEE.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

Cardiac Disease Prediction using Supervised Machine Learning Techniques 1

Cardiac Disease Prediction using Supervised Machine Learning...

引用

1st International Conference on Artificial Intelligence, Computational Electronics and Communication System, AICECS 2021

作者： Gupta, Chiradeep Saha, Athina Reddy, N.V. Subba Acharya, U. Dinesh Computer Science and Information Security Department of Computer Science Manipal Institute of Technology MAHE Manipal India

Diagnosis of cardiac disease requires being more accurate, precise, and reliable. The number of death cases due to cardiac attacks is increasing exponentially day by day. Thus, practical approaches for earlier diagnosis of cardiac or heart disease are done to achieve prompt management of the disease. Various supervised machine-learning techniques like K-Nearest Neighbour, Decision Tree, Logistic Regression, Naïve Bayes, and Support Vector Machine (SVM) model are used for predicting cardiac disease using a dataset that was collected from the repository of the University of California, Irvine (UCI). The results depict that Logistic Regression was better than all other supervised classifiers in terms of the performance metrics. The model is also less risky since the number of false negatives is low as compared to other models as per the confusion matrix of all the models. In addition, ensemble techniques can be approached for the accuracy improvement of the classifier. Jupyter notebook is the best tool, for the implementation of Python Programming having many types of libraries, header files, for accurate and precise work. © 2022 Institute of Physics Publishing. All rights reserved.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Improving cloud data security through hybrid verification technique based on biometrics and encryption system

引用

International Journal of computers and Applications 2022年第5期44卷 455-464页

作者： Hossain, Md. Alamgir Al Hasan, Md. Abdullah Department of Computer Science and Engineering Prime University Dhaka Bangladesh Bangladesh-Japan Information Technology Dhaka Bangladesh

Cloud computing is a unique network or environment where access, maintenance and process can be done from any part of the world. It is a customized internet-based computer server. It is a current trend of modern technology. For the massive computational power, it is the best option for storing data. There is no uncertainty that Cloud Data Server offers quick and solid types of assistance to its customers. When data is storing in the cloud storage the most important thing comes is the security of data. So, in recent years, cloud security is so much important issue because of the increasing of data. For the security of cloud computing, in this research, a hybrid verification technique is made which is based on biometric and encryption systems. In order to achieve strong and secure technique, this work use fingerprint as biometric technique and advanced encryption standard as a trustworthy encryption system. The primary goal of this paper is to avert information access from cloud information stockpiling focuses by unapproved clients. This new data security system can provide efficient authentication of cloud computing. © 2020 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Cyber Security Management through User Testing of E-Commerece Website - A Case Study 5

Cyber Security Management through User Testing of E-Commerec...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Kaswan, Suresh Yugal, Lisha Khirasaria, Vivek Amita Goyal, Parul Chandigarh University Department of Computer Science & Engineering Punjab Mohali India Sharda University Department of Computer Science & Engineering Greater Noida India Sharda University Faculty of Engineering and Technology Uzbekistan M. M. Engineering College Maharishi Markandeshwar Deemed to Be University Computer Science & Engineering Department Haryana Mullana India

ISBN: (纸本)9798350379945

Software testing is crucial for ensuring software quality, including security. This research presents a case study examining manual and open-source tool-based security testing of an e-commerce website. By applying various testing techniques, the study aims to identify potential vulnerabilities and assess security measures at different development stages. The findings will contribute to developing effective security testing strategies for web applications. © 2024 IEEE.

关键词： E-Commerce testing Security Testing Software Testing System testing

来源：评论

学校读者我要写书评

暂无评论

Secure Image Communication Using Galois Field,Hyper 3D Logistic Map,and B92 Quantum Protocol

引用

computers, Materials & Continua 2024年第12期81卷 4435-4463页

作者： De Rosal Ignatius Moses Setiadi Nova Rijati Ahmad Rofiqul Muslikh Bonifacius Vicky Indriyono Aceng Sambas Faculty of Computer Science Universitas Dian NuswantoroSemarang50131Central JavaIndonesia Research Center for Quantum Computing and Materials Informatics Faculty of Computer ScienceUniversitas Dian NuswantoroSemarang50131Central JavaIndonesia Faculty of Information Technology Universitas MerdekaMalang65146East JavaIndonesia Faculty of Economics and Business Universitas STRADA IndonesiaKediri64133East JavaIndonesia Faculty of Informatics and Computing Universiti Sultan Zainal AbidinCampus BesutBesut22200TerengganuMalaysia Department of Mechanical Engineering Universitas Muhammadiyah TasikmalayaTamansari GobrasTasikmalaya46196Indonesia

In this paper,we propose a novel secure image communication system that integrates quantum key distribution and hyperchaotic encryption techniques to ensure enhanced security for both key distribution and plaintext ***,we leverage the B92 Quantum Key Distribution(QKD)protocol to secure the distribution of encryption keys,which are further processed through Galois Field(GF(28))operations for increased *** encrypted plaintext is secured using a newly developed Hyper 3D Logistic Map(H3LM),a chaotic system that generates complex and unpredictable sequences,thereby ensuring strong confusion and diffusion in the encryption *** hybrid approach offers a robust defense against quantum and classical cryptographic attacks,combining the advantages of quantum-level key distribution with the unpredictability of hyperchaos-based *** proposed method demonstrates high sensitivity to key changes and resilience to noise,compression,and cropping attacks,ensuring both secure key transmission and robust image encryption.

关键词： Galois field hyper 3D logistic map hyperchaotic map image security improved logistic map secure communication quantum security

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cloud Security: A Comprehensive Review of Machine Learning Approaches 2

Enhancing Cloud Security: A Comprehensive Review of Machine ...

引用

2nd International Conference on Cyber Resilience, ICCR 2024

作者： Safi, Wassim Ghwanmeh, Sameh Mahfuri, Mahmoud Al-Sit, Waleed T. Higher Institute For Applied Sciences And Technology-HIAST Damascus Syria American University In The Emirates Department Of Computer Science United Arab Emirates International University For Science And Technology Computer And Information Technology Department Damascus Syria College Of Engineering Mu'tah University Department Of Computer Engineering Al-karak Jordan Higher Colleges Of Technology Dubai United Arab Emirates

ISBN: (纸本)9798350394962

Cloud Computing (CC) has ushered in a paradigm shift in the provisioning of IT resources, offering users enhanced cost-efficiency and streamlined infrastructure management. However, this growth in CC adoption has also brought forth a myriad of security challenges, encompassing threats to availability, integrity, and confidentiality. To combat these challenges, Cloud Service Providers (CSPs) are increasingly turning to Machine Learning (ML) to diminish the necessity for human intervention in the identification and resolution of security issues. ML's capacity to process extensive datasets and make highly accurate predictions holds the potential to revolutionize CSPs' approach to security. This paper delves into recent advancements in the realm of ML-based security within Cloud Computing. It assesses the attributes and efficacy of various ML algorithms, underscoring their distinctive strengths and possible limitations. Our objective is to present a comprehensive overview of the current landscape of ML in cloud security, illuminating the promising prospects this emerging field holds. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Deep Radiomics: A Picture's Worth a Thousand Words - A Review 1

Deep Radiomics: A Picture's Worth a Thousand Words - A Revie...

引用

1st IEEE Karachi Section Humanitarian technology Conference, Khi-HTC 2024

作者： Meraj, Syeda Shah, Asadullah Ismail, Ahsiah Sembokb, Tengku Mt Shadab, Syed Aftab, Syed Nageena, Syeda Khan, Nusratullah Nusratullah, Kajal Kulliyyah of Information and Communications Technology Department of Information Systems Selangor Malaysia Kulliyyah of Information and Communications Technology Department of Computer Science Selangor Malaysia Al Musanna College of Technology City Department of Information Technology Oman Higher Colleges of Technology Department of Aeronautical Engineering Technology Al-Ain United Arab Emirates Department of Health and Family Welfare Karnataka Koppal India Yanbu Industrial College Royal Commission Computer Science and Engineering Department Yanbu Saudi Arabia

ISBN: (纸本)9798350373042

In recent decades, the prevalence of diseases has witnessed a notable surge. The increasing health challenges have led to a greater use of advanced diagnostic machines for detecting and understanding these disease conditions. The diagnostic modalities, such as X-rays, CT scans, MRI scans, and nuclear medicine imaging, generate a wealth of interpretative data through medical images. Deep Radiomics aims to improve the efficiency and accuracy of image interpretation by automating the process of feature extraction, allowing for more comprehensive insights for advancing personalized medicine and improving outcomes in medical imaging. Enhance disease detection, diagnosis, and subsequent treatment strategies. © 2024 IEEE.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

CIMulator: Evaluating Neuromorphic Accelerators with HZO FefinFET-Based Synaptic Device 7

CIMulator: Evaluating Neuromorphic Accelerators with HZO Fef...

引用

7th International Conference on Green technology and Sustainable Development, GTSD 2024

作者： Le, Hoang-Hiep Lu, Hao-Yu Baig, Md. Aftab De, Sourav Lin, Ing-Chao Lu, Darsen D. Minghsin University of Science and Technology Department of Computer Science and Information Engineering Hsinchu Taiwan National ChengKung University Intelligent Computing Industrial Doctorate Program Tainan Taiwan Institute of Microelectronics National ChengKung University Tainan Taiwan National ChengKung University Department of Computer Science and Information Engineering Tainan Taiwan

ISBN: (纸本)9798350386073

In this study, we use the CIMulator platform to evaluate the performance of neuromorphic accelerators with novel Hf0.5Zr0.5O2 (HZO) ferroelectric fin field-effect transistor (FefinFET) as synaptic device. The MNIST handwritten digit dataset is used for training and inference processes in multilayer perceptron (MLP) neural networks. With the highly optimized synaptic device, the results demonstrate high training and inference accuracy, achieving up to 97% for the MLP, approaching the accuracy of software implementations. © 2024 IEEE.

关键词： Multilayer 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：