检索结果-内蒙古大学图书馆

Retinal disorder diagnosis based on hybrid deep learning models

Multimedia Tools and Applications 2025年 1-25页

作者： Sedik, Ahmed El-Shafai, Walid El-Hag, Noha A. El-Banby, Ghada M. Abd El-Samie, Fathi E. Smart Systems Engineering Laboratory College of Engineering Prince Sultan University Riyadh11586 Saudi Arabia Department of the Robotics and Intelligent Machines Faculty of Artificial Intelligence Kafrelsheikh University Kafr el-Sheikh Egypt Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt The Higher Institute of Commercial Sciences Algarbia Al Mahalla Al Kubra31951 Egypt Department of Industrial Electronics and Control Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Anomaly detection from medical images is badly needed for automated diagnosis. For example, medical images obtained with several modalities, such as magnetic resonance (MR) and confocal microscopy, need to be classified for anomaly detection. The MR images may contain tumors that need to be detected with anomaly detection techniques. In MR imaging, brain tumors are represented as areas composed of abnormal cells that need to be detected. On the other hand, confocal microscopy can be used for retinal imaging. Hence, there is a need to apply classification techniques for diagnosing diseases of the eye, such as Diabetic Retinopathy (DR), which leads to exudates in different regions of the retina. The detection of exudates is necessary for the diagnosis of DR. In this paper, two models are presented for the classification of MR and retinal images. Much research has been done in this area, but it did not achieve high accuracy of classification in an acceptable time. In addition, the previous models did not consider both types of image modalities considered in this paper. The suggested models are Convolutional Neural Network (CNN) and Convolutional Long Short-Term Memory (Conv-LSTM). They are used to classify normal and abnormal cases of both brain tumor and DR diseases. The CNN model is composed of six convolutional layers and six max-pooling layers. A soft-max activation function takes the classification decision. The proposed Conv-LSTM model is composed of three stages: pre-processing, feature extraction, and classification. The deep learning model performance is better than those of traditional networks. The CNN gives an accuracy of 94.26% for DR classification and 95.8% for brain tumor classification, while the Conv-LSTM gives the maximum accuracy of 96.41% for DR classification and 97.4% for brain tumor classification. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Confocal microscopy

来源：评论

学校读者我要写书评

暂无评论

Global-Local Consistency for Cost-Effective Anomaly Localization with Point Annotations

Global-Local Consistency for Cost-Effective Anomaly Localiza...

引用

IIAI International Conference on Advanced Applied Informatics (IIAIAAI)

作者： Keiichi Nakanishi Ryoya Katafuchi Terumasa Tokunaga Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Japan Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Japan

ISBN: (数字)9798350377903

ISBN: (纸本)9798350377910

Creating pixel-level ground-truth (GT) masks is quite costly for deep learning-based image segmentation. Specialists in areas such as anomaly detection and medical diagnostics face difficulties in producing many GT masks due to limited resources. To reduce this burden, we propose a cost-effective image segmentation framework with point annotations (CoSPA) that performs image segmentation with only point annotations. Point annotations refer to the partial and sparse labeled coordinates in an image. The key idea is to ensure consistency between the predictions for the same coordinates from the two different networks of CoSPA. This new consistency enables the CoSPA to improve segmentation performance and extend to semi-supervised learning. For the MVTec AD dataset, we verified the cost-effectiveness of CoSPA through an anomaly detection task. We demonstrated that the point annotating costs were reduced by 80% compared to creating GT masks. Subsequently, the CoSPA realized by 87% of the mean Intersection over Union (mIoU) achieved using the fully supervised method, DeepLabV3+. Moreover, the mIoU of CoSPA using only 30% of all point annotations defeated that of the unsupervised method, PaDiM. This study offers a new direction for economic anomaly localization.

关键词： Location awareness Image segmentation Costs Annotations Supervised learning Semisupervised learning Medical diagnosis Informatics Anomaly detection Faces

来源：评论

学校读者我要写书评

暂无评论

QoS Based Cloud Security Evaluation Using Neuro Fuzzy Model

引用

computers, Materials & Continua 2022年第1期70卷 1127-1140页

作者： Nadia Tabassum Tahir Alyas Muhammad Hamid Muhammad Saleem Saadia Malik Syeda Binish Zahra Department of Computer Science Virtual University of PakistanLahore54000Pakistan Department of Computer Science Lahore Garrison UniversityLahore54000Pakistan Department of Statistics and Computer science University of veterinary and animal sciencesLahore54000Pakistan Department of Industrial Engineering Faculty of EngineeringRabighKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology-RabighKing Abdulaziz UniversityJeddah21589Saudi Arabia

Cloud systems are tools and software for cloud computing that are deployed on the Internet or a cloud computing network,and users can use them at any *** assessing and choosing cloud providers,however,customers confront the variety and difficulty of quality of service(QoS).To increase customer retention and engagement success rates,it is critical to research and develops an accurate and objective evaluation *** is the emerging environment for distributed services at various *** to the benefits of this environment,globally cloud is being taken as a standard environment for individuals as well as for the corporate sector as it reduces capital expenditure and provides secure,accessible,and manageable services to all stakeholders but Cloud computing has security challenges,including vulnerability for clients and association acknowledgment,that delay the rapid adoption of computing *** of resources in the Cloud is difficult because resources provide numerous measures of quality of *** this paper,the proposed resource allocation approach is based on attribute QoS Scoring that takes into account parameters the reputation of the asset,task completion time,task completion ratio,and resource *** article is focused on the cloud service’s security,cloud reliability,and could *** this paper,the machine learning algorithm neuro-fuzzy has been used to address the cloud security issues to measure the parameter security and privacy,trust *** findings reveal that the ANFIS-dependent parameters are primarily designed to discern anomalies in cloud security and features output normally yields better results and guarantees data consistency and computational power.

关键词： Cloud computing performance quality of service machine learning neuro-fuzzy

来源：评论

学校读者我要写书评

暂无评论

Detection of Diffusion-Generated Images Using Sparse Coding

Detection of Diffusion-Generated Images Using Sparse Coding

引用

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Daishi Tanaka Michiharu Niimi Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Fukuoka Japan Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology Fukuoka Japan

ISBN: (数字)9798350367331

ISBN: (纸本)9798350367348

This paper proposes a method for detecting images generated by diffusion models using sparse coding. In the diffusion model, an image can be generated by removing noise from a noisy image. This different generation process from real images leads us to believe that there may be a statistical difference in pixels between the real and the generated images. Specifically, the image is divided into small patch regions, and all patch images are reconstructed using the basis image. In this process, sparse coefficients that contain many zeros are obtained using sparse coding, and features are calculated from the obtained coefficients. Then, a simple discriminator using the features as input is trained with a small number of data to discriminate the diffusion-generated images. In our experiments, we evaluated the proposed method on six datasets created using three diffusion models and two real image datasets. Experiments were also conducted to evaluate the robustness of the proposed method against JPEG compression. Experimental results show that our proposed method is sufficiently robust against JPEG compression with as few as 1800 training data.

关键词： Image coding Noise Transform coding Training data Information processing Diffusion models Feature extraction Robustness Noise measurement Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Improved Ultimate Link without Markers for Projective Transformation

Improved Ultimate Link without Markers for Projective Transf...

引用

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Keiji Yamadera Michiharu Niimi Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Japan Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Japan

ISBN: (数字)9798350367331

ISBN: (纸本)9798350367348

In our previous work, we have proposed a method that links character string having a certain semantic meaning on papers in real world to the digital content in cyberspace, and call it "Ultimate Link." Ultimate Link adds additional information to characters by drawing colored circles on top of the characters without changing the shape of the characters. A URL can be generated by connecting additional information of semantically organized character strings from an image taken with a digital device. The conventional Ultimate Link drew markers to normalize the drawn circles (markers for projective transformation), similar to the finder pattern in a QR code. In order to achieve a more realistic application, it is desirable it. We report on an improved Ultimate Link that can handle complex multiple character strings. Specifically, improvements were made to enable extraction of information by identifying character strings with embedded additional information from sheets of paper printed with multiple character strings. As a result of experiments, we confirmed that information could be successfully embedded and extracted for both character strings in the target image.

关键词： Uniform resource locators Shape Semantics Lighting Web pages Personal digital devices QR codes Information processing Information retrieval Data mining

来源：评论

学校读者我要写书评

暂无评论

Control Displaying of Web Push Notifications Inducing Users to Phishing Websites

Control Displaying of Web Push Notifications Inducing Users ...

引用

IEEE Conference on Dependable and Secure Computing

作者： Masaya Sato Ryuki Mandai Faculty of Computer Science and Systems Engineering Okayama Prefectural University Soja Japan Graduate School of Computer Science and Systems Engineering Okayama Prefectural University Soja Japan

ISBN: (数字)9798331540289

ISBN: (纸本)9798331540296

The number of phishing websites is increasing, and the methods used to direct users to these sites are becoming more diverse. As web push notifications become more widespread, adversaries have begun using them as a method to direct users to phishing websites, known as phishing web push notifications. While protection against other phishing methods has been widely studied, countermeasures against phishing web push notifications remain an ongoing research topic. In this paper, we explore a method to control the display of web push notifications to protect users from phishing attempts. To minimize the cost of implementing and introducing the control mechanism, we utilized a browser extension to manage the display of web push notifications. We employed a keyword-based approach to detect and prevent the display of suspicious web push notifications. Our experimental results demonstrated that the proposed method effectively blocks phishing notifications.

关键词： Costs Phishing Buildings Prototypes Browsers Protection

来源：评论

学校读者我要写书评

暂无评论

A nano-scale design of a multiply-accumulate unit for digital signal processing based on quantum computing

引用

Optical and Quantum Electronics 2024年第1期56卷 1-25页

作者： Ahmadpour, Seyed-Sajad Navimipour, Nima Jafari Yalcin, Senay Bakhshayeshi Avval, Danial Ain, Noor Ul Department of Computer Engineering Faculty of Engineering and Natural Sciences Kadir Has University Istanbul Turkey Future Technology Research Center National Yunlin University of Science and Technology Douliou 64002 Taiwan Department of Computer Engineering Nisantasi University Istanbul Turkey Department of Information Systems Engineering Sakarya University Sakarya Turkey Department of Business Administration Kadir Has University Istanbul Turkey

Digital signal processing (DSP) is used in computer processing to conduct different signal-processing tasks. The DSPs are used in the series numbers representing a continuous variable in a domain such as time, area, or frequency. The multiply-accumulate (MAC) unit is crucial in various DSP applications, including convolution, discrete cosine transform (DCT), Fourier Transform, etc. Thus, all DSPs contain a critical MAC unit in signal processing. The MAC unit conducts multiplication and accumulation operations for continuous and complicated DSP application processes. On the other hand, in the MAC structure, the stability of the circuit and the occupied area pose some significant challenges. However, high-performance quantum technology can easily overcome all the previous shortcomings. Hence, this paper suggests an efficient MAC for DSP applications using a Vedic multiplier, half adder, and accumulator based on quantum technology. All the proposed structures have used a single-layer layout without rotated cells. The suggested architecture is designed and validated based on the QCADesigner 2.0.3 tool. The findings revealed that all the developed circuits have a simple architecture with fewer quantum cells, optimal area, and low latency. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Multiply-accumulate (MAC) Nano-design Quantum dot cellular automata (QCA) Signal processing

来源：评论

学校读者我要写书评

暂无评论

Sustainable Smart Road: A Unified Cost Estimation Model for Renewable-Powered Smart Roads 4

Sustainable Smart Road: A Unified Cost Estimation Model for ...

引用

4th IEEE International Conference on Electrical, computer, and Energy Technologies, ICECET 2024

作者： Colombo, Cristian Giovanni Longo, Michela Nocera, Leonardo Ota, Ryosuke Zaninelli, Dario Politecnico di Milano Department of Energy Milan Italy Politecnico di Milano Milan Italy Tokyo Metropolitan University Faculty of Systems Design Department of Electrical Engineering and Computer Science Tokyo Japan

ISBN: (纸本)9798350395914

With new stringent policies affecting the transport and generation sectors, new technologies have emerged to drive the electric and technological transition. One of these is the smart road, a highly sensorised system to enable the integration of new vehicles and safety technologies. In this paper, the implementation of a smart road is simulated, first from an energy point of view and then from an economic point of view, by identifying the power demand of components and their cost. Next, the energetic core of the smart road is implemented. The energy core consists of a PV plant capable of powering the infrastructure. In this paper a simulation to test the proposed methodology is implemented. In the case study, a 280.05 kW smart road is powered by an optimally dimensioned PV plant. The production guaranteed by the 283.8 kWp plant will be 389.49 MW h/year and requires 57232. Furthermore, the 234.57 x20AC investment for the plant will represent less than 10% of the total investment, highlighting how renewable integration can be an economic sustainable purpose. Finally, another method to return the investment as quickly as possible will be proposed. © 2024 IEEE.

关键词： PV' Renewable Integration Road Infrastructure Smart Road

来源：评论

学校读者我要写书评

暂无评论

Multithreaded Haplotype Block Partitioning of Rheumatoid Arthritis Genomic Data

Multithreaded Haplotype Block Partitioning of Rheumatoid Art...

引用

2023 IEEE EMBS Special Topic Conference on Data science and engineering in Healthcare, Medicine and Biology, IEEECONF 2023

作者： Al-Khalifa, Azza M. Saad, Mohamed N. Rushdi, Muhammad A. Eldeib, Ayman M. Minia University Faculty of Engineering Biomedical Engineering Department Egypt Cairo University Faculty of Engineering Department of Biomedical Engineering and Systems Giza12613 Egypt Southern New Hampshire University School of Engineering Technology and Aeronautics Computer Science Department ManchesterNH United States

ISBN: (纸本)9798350383386

Haplotype block partitioning methods have been widely employed in the analysis of genetic patterns of common and complex diseases. The existing methods suffer from high time and memory complexities due to the key bottleneck of computing the linkage disequilibrium (LD) for all or most pairs of single-nucleotide polymorphisms (SNPs). In this work, we propose a multithreaded variant of the confidence internal test (CIT) method for haplotype block partitioning implementations. The usefulness of the proposed method in reducing the time and memory costs is demonstrated through experiments on the North American Rheumatoid Arthritis Consortium (NARAC) dataset. Our simulation results show 11-35% savings in time and 8-36% savings in memory requirements with only 3-6% increase in CPU *** Relevance: This work seeks time and memory savings in genetic analysis for the prediction of diseases with complex factors (e.g., rheumatoid arthritis in our case). These savings can streamline and accelerate relevant clinical workflows and reduce demand for computational resources. © 2023 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

ShieldSMS Sentinel: Guardian of Your Digital Communication Bastion 2

ShieldSMS Sentinel: Guardian of Your Digital Communication B...

引用

2nd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry, IDICAIEI 2024

作者： Gourshettiwar, Palash Thakare, Rajesh D. Duddalwar, Prapti Shete, Rushikesh Gundewar, Swapnil Verma, Prateek Faculty of Engineering and Technology Department of Computer Science and Medical Engineering Maharashtra Wardha442001 India Yashavantrao Chavan College of Engineering Department of Electronics Engineering Maharashtra Nagpur440002 India Vishwakarma Institute of Technology Department of Electronics Engineering Maharashtra Pune411037 India St. Vincent Pallotti College of Engineering and Technology Department of Computer Science and Business Systems Maharashtra Nagpur440002 India Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha442001 India

ISBN: (纸本)9798331528713

The SMS spam detection Project provides a comprehensive framework for reliably identifying and classifying spam messages sent over SMS communication channels by fusing ML algorithms with NLP techniques. Using EDA, a dataset of labelled SMS messages identified as spam or ham is thoroughly studied to reveal patterns in the word count, sentence count, and message length distributions. Then, unstructured text is transformed into structured data that may be utilized with ML models through tokenization, punctuation and stop word removal, stemming, and other text preprocessing techniques. Feature engineering, which numerically represents text data using vectorization techniques like BoW and TF-IDF, plays a significant role. Various ML algorithms, including Gaussian Naive Bayes, Multinomial Naive Bayes, SVM, and ensemble approaches, are trained and evaluated. Performance metrics, including accuracy and precision, serve as standards for model selection. © 2024 IEEE.

关键词： Text messaging

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：