检索结果-内蒙古大学图书馆

Deep Transfer Learning Models for Mobile-Based Ocular Disorder Identification on Retinal Images

computers, Materials & Continua 2024年第7期80卷 139-161页

作者： Roseline Oluwaseun Ogundokun Joseph Bamidele Awotunde Hakeem Babalola Akande Cheng-Chi Lee Agbotiname Lucky Imoize Department of Multimedia Engineering Kaunas University of TechnologyKaunas44249Lithuania Department of Computer Science Landmark UniversityOmu Aran251103Nigeria Department of Computer Science Faculty of Information and Communication SciencesUniversity of IlorinIlorin240003Nigeria Department of Telecommunication Science University of IlorinIlorin230003Nigeria Department of Library and Information Science Fu Jen Catholic UniversityNew Taipei City24205TaiwanChina Department of Computer Science and Information Engineering Fintech and Blockchain Research CenterAsia UniversityTaichung City41354TaiwanChina Department of Electrical and Electronics Engineering Faculty of EngineeringUniversity of LagosAkokaLagos100213Nigeria Department of Electrical Engineering and Information Technology Institute of Digital CommunicationRuhr UniversityBochum44801Germany

Mobile technology is developing *** phone technologies have been integrated into the healthcare industry to help medical ***,computer vision models focus on image detection and classification ***2 is a computer vision model that performs well on mobile devices,but it requires cloud services to process biometric image information and provide predictions to *** leads to increased *** biometrics image datasets on mobile devices will make the prediction faster,but mobiles are resource-restricted devices in terms of storage,power,and computational ***,a model that is small in size,efficient,and has good prediction quality for biometrics image classification problems is *** pre-trained CNN(PCNN)MobileNetV2 architecture combined with a Support Vector Machine(SVM)compacts the model representation and reduces the computational cost and memory *** proposed novel approach combines quantized pre-trained CNN(PCNN)MobileNetV2 architecture with a Support Vector Machine(SVM)to represent models efficiently with low computational cost and *** contributions include evaluating three CNN models for ocular disease identification in transfer learning and deep feature plus SVM approaches,showing the superiority of deep features from MobileNetV2 and SVM classification models,comparing traditional methods,exploring six ocular diseases and normal classification with 20,111 images postdata augmentation,and reducing the number of trainable *** model is trained on ocular disorder retinal fundus image datasets according to the severity of six age-related macular degeneration(AMD),one of the most common eye illnesses,Cataract,Diabetes,Glaucoma,Hypertension,andMyopia with one class *** the experiment outcomes,it is observed that the suggested MobileNetV2-SVM model size is *** testing accuracy for MobileNetV2-SVM,InceptionV3,and MobileNetV2 is 90.11%,86.88%,a

关键词： Retinal images ocular disorder deep transfer learning disease identification mobile device

来源：评论

学校读者我要写书评

暂无评论

A comprehensive tool for rapid and accurate prediction of disease using DNA sequence classifier

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第10期14卷 13869-13885页

作者： Mathur, Garima Pandey, Anjana Goyal, Sachin Department of Computer Science and Engineering UIT RGPV Bhopal India Department of Information Technology UIT RGPV Bhopal India

In the current pandemic situation where the coronavirus is spreading very fast that can jump from one human to another. Along with this, there are millions of viruses for example Ebola, SARS, etc. that can spread as fast as the coronavirus due to the mobilization and globalization of the population and are equally deadly. Earlier identification of these viruses can prevent the outbreaks that we are facing currently as well as can help in the earlier designing of drugs. Identification of disease at a prior stage can be achieved through DNA sequence classification as DNA carries most of the genetic information about organisms. This is the reason why the classification of DNA sequences plays an important role in computational biology. This paper has presented a solution in which samples collected from NCBI are used for the classification of DNA sequences. DNA sequence classification will in turn gives the pattern of various diseases;these patterns are then compared with the samples of a newly infected person and can help in the earlier identification of disease. However, feature extraction always remains a big issue. In this paper, a machine learning-based classifier and a new technique for extracting features from DNA sequences based on a hot vector matrix have been proposed. In the hot vector representation of the DNA sequence, each pair of the word is represented using a binary matrix which represents the position of each nucleotide in the DNA sequence. The resultant matrix is then given as an input to the traditional CNN for feature extraction. The results of the proposed method have been compared with 5 well-known classifiers namely Convolution neural network (CNN), Support Vector Machines (SVM), K-Nearest Neighbor (KNN) algorithm, Decision Trees, Recurrent Neural Networks (RNN) on several parameters including precision rate and accuracy and the result shows that the proposed method gives an accuracy of 93.9%, which is highest compared to other classifiers. © 2022

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Genetic Algorithm Based Deterministic Workflow Scheduling with Load Balancing 2

Genetic Algorithm Based Deterministic Workflow Scheduling wi...

引用

2nd International Conference on Computational Intelligence, Communication technology and Networking, CICTN 2025

作者： Mittal, Punit Kumar, Satender Sharma, Swati Department of Computer Science and Engineering Quantum University Roorkee India Department of Information Technology Meerut Institute of Engineering and Technology Meerut India

ISBN: (纸本)9798331530389

A crucial problem in cloud computing is load balancing, which makes it challenging to guarantee that services operate as intended in accordance with quality of service (QoS), performance reviews, and service contracts that cloud service providers (CSPs) demand of businesses. The main goal is to distribute workloads among computer resources in order to improve performance. Load balancing is categorized as an "NP-hard" problem due to the ample solution space and the time needed to identify the optimal solution. While only a few approaches may provide an exact answer in polynomial time, prior research shows that metaheuristic-based tactics can find correct solutions in a fair amount of time. We use a framework that integrates Neural Network Task Classification (N2TC) and Genetic Algorithm Task Assignment (GATA) for load balancing. By taking load balancing and task completion time into account, this approach seeks to maximize load distribution and reduce process execution time. Extensive simulations of application operations were carried out to evaluate the effectiveness of the suggested load-balancing strategy. Results have shown that the proposed framework outperforms tournament selection genetic algorithm (TSGA), Heterogeneous Earliest Finish Time (HEFT), and Performance Effective Task Scheduling (PETS) heuristics in terms of load balancing up to 4.52% and makespan by 6.47%. © 2025 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

FeAdaBoost: EnhancingFederated Learning Accuracy by Ensemble Techniques 29

FeAdaBoost: EnhancingFederated Learning Accuracy by Ensemble...

引用

29th International computer Conference, computer Society of Iran, CSICC 2025

作者： Fotoohabadi, Vida Afzali, Afsaneh Shamsinejadbabaki, Pirooz Department of Computer Engineering and Information Technology Shiraz University of Technology Shiraz Iran

ISBN: (纸本)9798331523114

Federated Learning (FL), an advanced technique in machine learning (ML), allows for model training without transferring data to a central server. This method is particularly valuable in sensitive applications, such as healthcare and finance, as it preserves data privacy and reduces security risks. However, FL faces the challenge of reduced accuracy compared to centralized approaches due to limited access to the full dataset. To address this issue, we propose a solution that integrates the ensemble learning method AdaBoost with FL, which we call FeAdaBoost. We validate the effectiveness of our approach using the task of classifying a chest X-ray image dataset. The experimental results confirm that the proposed approach significantly improves both accuracy and efficiency compared to traditional FL. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Speech cryptography algorithms: utilizing frequency and time domain techniques merging

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第10期15卷 3617-3649页

作者： Faragallah, Osama S. Farouk, M. El-sayed, Hala S. El-bendary, Mohsen A. M. Department of Information Technology College of Computers and Information Technology Taif University Al- Hawiya21974 Saudi Arabia Department of Computer Science and Engineering Menoufia University Menouf32952 Egypt Department of Electrical Engineering Menoufia University Shebin El-kom32511 Egypt Department of Electronics Technology Faculty of Technology and Education Helwan University Cairo Egypt

Due to the importance security of sensitive speech and audio signals such as the countries president’s call phone, this research work presents an efficient audio cryptosystem. Audio speech communications play main and essential role in the human daily life, covering many important fields ranging from simple personal private information up to top secret, sensitive and critical information. It is difficult to prevent the eavesdropping by unauthorized person especially 1-D audio scrambling methods, it is built by simple algorithms and has low security level. So, there is a dire need for enhancing audio cryptosystem to be more secure against different types of attacks. In this work, the enhanced audio cryptosystem is proposed, the first approach enhances multiple key audio cryptosystem utilizing the chaotic baker map through enhancing the confusion level for both encryption/decryption algorithms employing time and transform domains. Simulation experiments revealed that the proposed boosted audio cryptosystem on time and transform domains is secure and robust against different types of attacks. The boosted multiple key based audio crypto-system is performed by increasing confusion and enlarging the secret-key space. Results of the simulation experiments revealed that the proposed multiple secret key-enhanced confusion audio cryptosystem is secure and robust with respect to different types of attacks. Moreover, results for transform domains show better results than results for time domain for the three proposed boosted audio cryptosystem. Also, the third proposed audio cryptosystem DWT-based shows the best results among all other proposed audio cryptosystem. Due to the results, robustness and reliability of proposed technique are higher the existing audio cryptographic system. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

E3C: a tool for evaluating communication and computation costs in authentication and key exchange protocol

引用

Iran Journal of computer Science 2024年第2期7卷 325-335页

作者： Salami, Yashar Khajehvand, Vahid Zeinali, Esmaeil Department of Computer and Information Technology Engineering Qazvin Branch Islamic Azad University Qazvin Iran

Today, with the advancement of blockchain and Internet of Things (IoT) technologies, there is a growing need for authentication protocols and key exchanges to facilitate communication between these diverse technologies. Authentication and key exchange protocols are designed using symmetric and asymmetric encryption methods, each with varying computational costs. In IoT systems, where memory and computation power are often limited, researchers are actively seeking lightweight protocol designs to minimize computational burdens. Traditionally, the calculation of computational and communication costs for protocols has been a manual process, which is prone to human error. In this paper, we propose the E3C tool, which automates the calculation of computation and communication costs for authentication and key exchange protocols. E3C enables the comparison of multiple protocols in terms of their communication and processing costs, presenting the results in separate charts. By comparing the processing and communication costs of both classical and modern protocols, both manually and using E3C, we demonstrate that E3C achieves 99.99% accuracy in calculating the costs of authentication and key exchange protocols. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Avispa E3C Formal Network Security

来源：评论

学校读者我要写书评

暂无评论

Software design and FPGA implementation of optimized medical image fusion techniques

引用

Multimedia Tools and Applications 2025年 1-31页

作者： Elshazly, E.A. El-Shafai, Walid El-Hoseny, Heba El-Rabaie, El-Sayed M Zahran, O. Abdelwahab, Safey A. S. El-Halawany, M.M. Fikry, R.M. Elaraby, S.M. Faragallah, Osama S. Mohamed, Wael A. Mahmoud, Korany R. Abd El-Samie, Fathi E. Cairo 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 Faculty of Computer Studies Arab Open University 11681 Riyadh Saudi Arabia Department of Information Technology College of Computers and Information Technology Taif University 11099 Taif21944 Saudi Arabia Department of Electrical Engineering Faculty of Engineering Benha University Benha Egypt Electronics and Communications Engineering Department Faculty of Engineering Helwan University Helwan Egypt Giza Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Nowadays, medical image fusion plays a crucial role in enhancing the diagnosis accuracy and the clinical decision-making process in various healthcare applications. This research work presents a comprehensive study of the design and implementation of optimized medical image fusion techniques using a combination of software and Field-Programmable Gate Array (FPGA) technologies. The proposed medical image fusion strategy is based on the utilization of Discrete Wavelet Transform (DWT) and Modified Central Force Optimization (MCFO). The implementation of the proposed technique as well as the traditional medical image fusion techniques is considered using an appropriate software design and FPGA. The presented techniques aim to overcome the limitations of traditional fusion techniques by integrating advanced image processing algorithms, optimization algorithms, and parallel computing capabilities offered by FPGA platforms. The first step in the proposed framework is to match the histogram of one of the images with that of the other, so that both images will have the same dynamic range. After that, the DWT is used to decompose the images that should be fused together. Based on some constraints, the MCFO optimization algorithm is used to evaluate the optimum level of decomposition and the optimum parameters for the best fusion quality. Finally, to improve the obtained visual quality and reinforce the information in the fusion result, an additional contrast enhancement step using adaptive histogram equalization is applied to the fusion result. Comparative study between the proposed optimized DWT-based fusion framework, the traditional Principal Component Analysis (PCA), Additive Wavelet Transform (AWT), and DWT-based fusion techniques is presented. Various metrics of fusion quality are considered, including average gradient, standard deviation, local contrast, entropy, edge strength, Peak Signal-to-Noise Ratio (PSNR), Qab/f, and processing time. The proposed optimized DWT-ba

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

The Claim-based Priority-Discriminated Channel Access (CPDCA) Method using the Registered Backoff Time Mechanism for IEEE 802.11ah

引用

Mobile Networks and Applications 2023年第3期28卷 1096-1115页

作者： Huang, Chung-Ming Cheng, Rung-Shiang Pan, Yan-Jia Department of Computer Science and Information Engineering National Cheng Kung University Tainan Taiwan Department of Information Technology Overseas Chinese University Taichung Taiwan

IEEE 802.11ah is a protocol that adopts the CSMA/CA-based channel access way for Internet of Thing (IOT). This work proposed a newly devised Restricted Access Window (RAW) called the Claiming RAW to let those spontaneous stations having high priority’s uplinked data frames do claims of intending to uplink high priority’s data to reduce collisions. In addition, instead of generating the random backoff time after the collision happens, which the regular CSMA/CA-based 802.11* protocols adopt, this work adopted the registered backoff time mechanism, for which a station registers its next backoff time to IEEE 802.11ah AP when its current channel access is finished, i.e., a station generates the backoff time before the collision happens. Thus, IEEE 802.11ah AP is able to schedule stations’ channel accesses based on stations’ registered backoff time to avoid collisions more effectively. Through the use of the Claiming RAW and the registered backoff time mechanisms, IEEE 802.11ah AP can know which stations have high priority’s uplinked data frames and then schedule these stations to have the higher privilege to access the channel. The simulation results shown that. Comparing with the traditional IEEE 802.11ah, the simulation results shown that the proposed Claim-based Priority-Discriminated Channel Access (CPDCA)method has a lower collision rate and higher throughput in the network environment having the higher number of stations in each time slot;the transmission time of those stations with high priority’s uplinked data frames using the CPDCA mechanism is much lower than that of using the traditional IEEE 802.11ah. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Semantic Tree Based PPDP Technique for Multiple Sensitive Attributes in Inter Cloud

引用

SN computer Science 2024年第6期5卷 722页

作者： Gadad, Veena Sowmyarani, C.N. Dayananda, P. Department of Computer Science and Engineering R V College of Engineering Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education

Digital devices and information systems have made data privacy essential. The collected data contains sensitive attributes such as salary, marital status and health history that need to be protected. Such data is exchanged or published to a third party using cloud infrastructure to perform various analyses, conduct research, and make critical decisions. Unauthorized users of the published data may violate privacy, notwithstanding the benefits. Data anonymization is one of the technique for achieving data privacy. Existing techniques consider single sensitive attribute and data is anonymized using generalization or suppression approaches. On observation, it is found that these techniques are less efficient since the collected data contains multiple sensitive attributes when anonymized using the same approaches leads to higher information loss and residue records. In this paper, multiple sensitive attributes are considered and the dataset is anonymized by constructing a semantic hierarchical tree it is further partitioned using the anatomy approach. Later, the partitions are stored in interclouds to achieve better privacy protection. Experiments are conducted to observe and analyze the computational performance, residue records and diversity percentage. The results obtained prove that the proposed technique is efficient when compared to the existing ones. © The Author(s) 2024.

关键词： Anonymization Data privacy information loss Multiple sensitive attributes Privacy threats

来源：评论

学校读者我要写书评

暂无评论

Unified Approach Integrating Machine Learning Algorithms for Detection of e-Mail Phishing Attacks 1

Unified Approach Integrating Machine Learning Algorithms for...

引用

1st International Conference on Computing, Sciences and Communications, ICCSC 2024

作者： Mathur, Abeer Dubey, Abhinav Sudhakar Mahara, Pranav Singh Gandhi, Usha Devi School of Computer Science & Engineering Vellore Institute of Technology Department of Software Systems Vellore India School of Computer Science Engineering & Information Systems Vellore Institute of Technology Department of Information Technology Vellore India

ISBN: (纸本)9798350353648

With the ever-rising risk of phishing attacks, which capitalize on vulnerable human behavior in the contemporary digital space, requires new cybersecurity methods. This literary work contributes to the solution by novel incorporation of three techniques: Support Vector Machine (SVM), Natural Language Processing (NLP) and Random Forest (RF). Utilizing NLP for deep analysis of text in phishing e-mails, SVM for strong categorization and Random Forest's decision making by group helps in improving detection. This combination of language and pattern analysis along with group learning builds a fortified system. This approach differs from prior work on a variety of factors such as reliability, security, integrity, scalability, interpretability, transparency, and robustness. Thorough evaluation on a reliable dataset aimed to demonstrate the method's effectiveness, which resulted in 98.7 % of accuracy in detection. This majorly aims at showcasing the potential of ensemble techniques to combat against cyber-attacks like phishing for laying a strong foundation for a secure digital environment. © 2024 IEEE.

关键词： Phishing

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：