检索结果-内蒙古大学图书馆

Impact of CLAHE-based image enhancement for diabetic retinopathy classification through deep learning

Procedia computer Science 2023年 216卷 57-66页

作者： Mira Hayati Kahlil Muchtar Roslidar Novi Maulina Irfan Syamsuddin Gregorius Natanael Elwirehardja Bens Pardamean Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh 23111 Indonesia Telematics Research Center (TRC) Universitas Syiah Kuala Banda Aceh 23111 Indonesia Faculty of Medicine Universitas Syiah Kuala Banda Aceh 23111 Indonesia Department of Computer and Networking Engineering Politeknik Negeri Ujung Pandang Makassar 90245 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program – Master of Computer Science Program Bina Nusantara University Jakarta 11480 Indonesia

Diabetic retinopathy (DR) is a type of diabetes mellitus that attacks the retina of the eye. DR will cause patients to experience blindness slowly. Generally, DR can be detected by using a special instrument called an ophthalmoscope to view the inside of the eyeball. However, in conditions where there is a very small difference between the normal image and the DR image, computer-based assistance is needed for maximizing image reading value. In this research, a method of image quality improvement will be carried out which will then be integrated with a classification algorithm based on deep learning. The results of image improvement using Contrast Limited Adaptive Histogram Equalization (CLAHE) shows that the average accuracy of the method on several models is very competitive, 91% for the VGG16 model, 95% for InceptionV3, and 97% for EfficientNet compared to the results original image which only has an accuracy of 87% for VGG16 model, 90% for InceptionV3 model, and 95% for EfficientNet. However, in ResNet34 better accuracy is obtained in the original image with an accuracy of 95% while in the CLAHE image the accuracy value is only 84%. The results of this comprehensive evaluation and recommendation of famous backbone networks can be useful in the computer-aided diagnosis of diabetic retinopathy.

关键词： Diabetic retinopathy Deep Learning CNN Image Enhancement CLAHE

来源：评论

学校读者我要写书评

暂无评论

Harnessing Inherent Noises for Privacy Preservation in Quantum Machine Learning

arXiv

引用

arXiv 2023年

作者： Ju, Keyi Qin, Xiaoqi Zhong, Hui Zhang, Xinyue Pan, Miao Liu, Baoling State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China Department of Electrical and Computer Engineering University of Houston HoustonTX77204 United States Department of Computer Science Kennesaw State University MariettaGA30060 United States

Quantum computing revolutionizes the way of solving complex problems and handling vast datasets, which shows great potential to accelerate the machine learning process. However, data leakage in quantum machine learning (QML) may present privacy risks. Although differential privacy (DP), which protects privacy through the injection of artificial noise, is a well-established approach, its application in the QML domain remains under-explored. In this paper, we propose to harness inherent quantum noises to protect data privacy in QML. Especially, considering the Noisy Intermediate-Scale Quantum (NISQ) devices, we leverage the unavoidable shot noise and incoherent noise in quantum computing to preserve the privacy of QML models for binary classification. We mathematically analyze that the gradient of quantum circuit parameters in QML satisfies a Gaussian distribution, and derive the upper and lower bounds on its variance, which can potentially provide the DP guarantee. Through simulations, we show that a target privacy protection level can be achieved by running the quantum circuit a different number of times. Copyright © 2023, The Authors. All rights reserved.

关键词： Shot noise

来源：评论

学校读者我要写书评

暂无评论

Integrating Instruction-based Learning with Bidirectional LSTM for Autonomous Vehicle Pedestrian Detection

Integrating Instruction-based Learning with Bidirectional LS...

引用

Multi-Agent Systems for Collaborative Intelligence (ICMSCI), International Conference on

作者： B Shoba T Raghunathan S.Sam Peter Karthick K Akshya. J M. Sundarrajan Mani Deepak Choudhry Department of Electronics and Communication Engineering PSN College of Engineering and Technology Tirunelveli Department of Artificial Intelligence and Data Science Dr.NG.p.Institute of Technology Coimbatore Department of Computer Science and Engineering Sri Krishna College of Technology Coimbatore Department of Information Technology Sona College of Technology Salem Department of Computational Intelligence SRM Institute of Science and Technology Chennai Department of Networking and Communications SRM Institute of Science and Technology Chennai Department of Computing Technologies SRM Institute of Science and Technology Chennai

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

Pedestrian detection is a crucial aspect of autonomous vehicle (A V) safety, as it enables accurate identification and tracking of individuals in an A V environment. Effective pedestrian detection supports essential A V functions like braking, steering, and speed control to prevent accidents in urban settings. Traditional computer vision methods, such as Support Vector Machines and Random Forests, rely on pre-designed features like the Histogram of Oriented Gradients. While the existing techniques offer some performance, it face significant challenges in dynamic environments, especially under varying lighting conditions, occlusions, and diverse pedestrian poses. Traditional models also require extensive manual feature engineering and tuning, which limits scalability and adaptability. Recent advances in deep learning, particularly with Convolutional Neural Networks (CNNs), have allowed for automatic feature learning, yielding practical improvements over classical methods. However, CNNs can struggle in low light and when facing adversarial attacks, as they mainly capture spatial features. To address these limitations, this research proposes a new methodology combining CNNs for spatial feature extraction with Bidirectional Long Short-Term Memory (BiLSTM) networks to capture temporal dependencies. This hybrid approach enhances detection capabilities by learning both static and dynamic patterns. Our proposed CNN-BiLSTM model achieves a 92 % detection accuracy and an F1 score of 88.5% across diverse conditions, outperforming existing models by up to 15%. By integrating temporal features, the model reduces missed detections and false positives by up to 20%, providing a more reliable and adaptable solution for pedestrian detection in autonomous vehicles.

关键词： Adaptation models Pedestrians Heuristic algorithms Feature extraction Real-time systems Vehicle dynamics Collision avoidance Autonomous vehicles Optimization Logistics

来源：评论

学校读者我要写书评

暂无评论

FAD-SAR: A Novel Fishing Activity Detection System via Synthetic Aperture Radar Images Based on Deep Learning Method

FAD-SAR: A Novel Fishing Activity Detection System via Synth...

引用

IEEE International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)

作者： Yanbing Bai Siao Li Rui-Yang Ju Zihao Yang Jinze Yu Jen-Shiun Chiang Center for Applied Statistics School of Statistics Renmin University of China Beijing China Graduate Institute of Networking and Multimedia National Taiwan University Taipei City Taiwan Department of Mechanical Systems Engineering Tokyo University of Agriculture and Technology Tokyo Japan Department of Electrical and Computer Engineering Tamkang University New Taipei City Taiwan

ISBN: (数字)9798350389210

ISBN: (纸本)9798350389227

Illegal, unreported, and unregulated (IUU) fishing activities seriously affect various aspects of human life. However, traditional methods for detecting and monitoring IUU fishing activities at sea have limitations. Although synthetic aperture radar (SAR) can complement existing vessel detection systems, extracting useful information from SAR images using traditional methods remains a challenge, especially in IUU fishing. This paper proposes a deep learning based fishing activity detection system, which is implemented on the xView3 dataset using six classical object detection models: SSD, RetinaNet, FSAF, FCOS, Faster R-CNN, and Cascade R-CNN. In addition, this work employs different enhancement techniques to improve the performance of the Faster R-CNN model. The experimental results demonstrate that training the Faster R-CNN model using the Online Hard Example Mining (OHEM) strategy increases the Avg-F1 value from 0.212 to 0.216.

关键词： Deep learning Training Radar cross-sections Object detection Signal processing Radar polarimetry Data mining Synthetic aperture radar Remote sensing Monitoring

来源：评论

学校读者我要写书评

暂无评论

A Novel Evaluation of Cryptocurrency Future Price Prediction to Manage Fluctuations in Market by using Hybrid Learning Methodology

A Novel Evaluation of Cryptocurrency Future Price Prediction...

引用

Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： D. Pradeep G. Divya R Rajeshwari R. Deepa T. V. V. Satyanarayana Department of CSE M.Kumarasamy College of Engineering Karur Department of Networking and Communications Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai India Dept of MCA S.A. Engineering College Chennai Department of Computer Science Engineering R.M.K. Engineering College Chennai Department of ECE Mohan Babu University(Erstwhile SreeVidyanikethan Engineering College) Tirupati AP

In recognition of its optimistic vision on the probable future of cryptocurrencies, the value of cryptocurrency has risen dramatically during the previous eight decades. Cryptocurrency offers significant benefits over the established financial system, and investors have taken notice. Cryptocurrency is unique in that it facilitates decentralized financial services, making it immune to control by large financial institutions. With the rise of electronic currencies like Ethereum (ETH) and BTT, business may be conducted entirely online. One illustration of the distributed structure of physical currencies is the reality that all consumers who use virtual money have utilization of operations without the need for a third-party they can depend on. Like the market fluctuations of traditional stocks, cryptocurrencies fluctuations in price are extremely volatile and non stationary. Traders and academics alike have given increased focus to predictions of bitcoin prices due to the asset class' rising popularity. The use of deep learning in projecting the price of cryptocurrencies has become increasingly important. This research presented a new algorithm for predicting cryptocurrency prices called Hybrid Learning for Crypto Prediction (HLCP), and results from these models demonstrated that the proposed HLCP algorithm outperformed all other methods in this area. The HLCP model offered encouraging and precise predictions for all cryptocurrencies; hence it can be considered the most successful algorithm. The model was used to forecast the 6 month ending prices of cryptocurrency. To measure how well predictions match targets during training and testing, we used the HLCP correlation metric. The proposed method efficiency is evaluated with respect to the following metrics such as training and testing accuracy levels, training and testing loss ratio as well as different cryptocurrencies (ETH, BitCoin and BTT) prediction and actual price comparisons. These metrics clearly shows the effic

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tuning Quantum Computing Privacy through Quantum Error Correction

arXiv

引用

arXiv 2023年

作者： Zhong, Hui Ju, Keyi Sistla, Manojna Zhang, Xinyue Qin, Xiaoqi Fu, Xin Pan, Miao Department of Electrical and Computer Engineering University of Houston HoustonTX77204 United States State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China Department of Computer Science Kennesaw State University MariettaGA30060 United States

Quantum computing is a promising paradigm for efficiently solving large and high-complexity problems. To protect quantum computing privacy, pioneering research efforts proposed to redefine differential privacy (DP) in quantum computing, i.e., quantum differential privacy (QDP), and harvest inherent noises generated by quantum computing to implement QDP. However, such an implementation approach is limited by the amount of inherent noises, which makes the privacy budget of the QDP mechanism fixed and uncontrollable. To address this issue, in this paper, we propose to leverage quantum error correction (QEC) techniques to reduce quantum computing errors, while tuning the privacy protection levels in QDP. In short, we gradually decrease the quantum noise error rate by deciding whether to apply QEC operations on the gate in a multiple single qubit gates circuit. We have derived a new calculation formula for the general error rate and corresponding privacy budgets after QEC operation. Then, we expand to achieve further noise reduction using multi-level concatenated QEC operation. Through extensive numerical simulations, we demonstrate that QEC is a feasible way to regulate the degree of privacy protection in quantum computing. © 2023, CC BY.

关键词： Quantum noise

来源：评论

学校读者我要写书评

暂无评论

Generative AI for Data Augmentation in Wireless Networks: Analysis, Applications, and Case Study

arXiv

引用

arXiv 2024年

作者： Wen, Jinbo Kang, Jiawen Niyato, Dusit Zhang, Yang Wang, Jiacheng Sikdar, Biplab Zhang, Ping College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China School of Automation Guangdong University of Technology China College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical and Computer Engineering College of Design and Engineering National University of Singapore Singapore State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications China

Data augmentation is a powerful technique to mitigate data scarcity. However, owing to fundamental differences in wireless data structures, traditional data augmentation techniques may not be suitable for wireless data. Fortunately, Generative Artificial Intelligence (GenAI) can be an effective alternative to wireless data augmentation due to its excellent data generation capability. This article systemically explores the potential and effectiveness of GenAI-driven data augmentation in wireless networks. We first briefly review data augmentation techniques, discuss their limitations in wireless networks, and introduce generative data augmentation, including reviewing GenAI models and their applications in data augmentation. We then explore the application prospects of GenAI-driven data augmentation in wireless networks from the physical, network, and application layers, which provides a GenAI-driven data augmentation architecture for each application. Subsequently, we propose a general generative diffusion model-based data augmentation framework for Wi-Fi gesture recognition, which uses transformer-based diffusion models to generate high-quality channel state information data. Furthermore, we develop residual neural network models for Wi-Fi gesture recognition to evaluate the role of augmented data and conduct a case study based on a real dataset. Simulation results demonstrate the effectiveness of the proposed framework. Finally, we discuss research directions for generative data augmentation. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Reliable and Stable V2V Routing Scheme for Warning Message Dissemination in VANETs using Bi-Directional Clustering 22

A Reliable and Stable V2V Routing Scheme for Warning Message...

引用

Proceedings of the 2022 12th International Conference on Communication and Network Security

作者： Mansoor Khan Shanshan Tu Ghulam Abbas Ziaul Haq Abbas Hisham Alasmary Muhammad Waqas Faculty of Computer Science and Engineering GIK Institute of Engineering and Technology Pakistan Information Technology Beijing University of Technology Beijing 100124 China China Telecommunications and Networking Research Center GIK Institute of Engineering and Technology Pakistan College of Computer Science King Khalid University Kingdom of Saudi Arabia and Information Security and Cybersecurity Unit King Khalid University Kingdom of Saudi Arabia Computer Engineering Department University of Bahrain Computer Engineering 32038 Bahrain. Bahrain and School of Engineering Edith Cowan University Australia

ISBN: (纸本)9781450397520

Road traffic injuries cause considerable life and economic losses to individuals, their families, and nations as a whole. To avoid road accidents, Vehicular Ad-hoc Networks (VANETs) play a vital role by enhancing transportation systems to make them intelligent. To enhance road safety, emergency message dissemination schemes are indispensable in VANET-based applications. This paper proposes a routing protocol for emergency message dissemination, which uses stable clustering for the bi-directional highway scenario. To assure the long-term sustainability of a cluster, a median technique for selecting a CH is devised. Further, an extended form of the K-medoids algorithm for a new node joining a cluster is employed, which ensures that both node and cluster have the same direction for bi-directional road traffic. Simulation results reveal that the proposed protocol proffers enhanced throughput and lowers the packet loss rates and end-to-end delay compared with state-of-the-art routing schemes.

关键词： bi-directional traffic warning message dissemination vehicular ad hoc network clustering

来源：评论

学校读者我要写书评

暂无评论

Joint Precoding and Reflection Optimization for IRS-Assisted MU-MIMO-OTFS Downlink Systems

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Zou, Tingting Wang, Fengyu Xu, Wenjun Zhang, Yimeng Pan, Miao Han, Zhu Beijing University of Posts and Telecommunications State Key Laboratory of Network and Switching Technology Beijing100876 China Beijing University of Posts and Telecommunications School of Artificial Intelligence Beijing100876 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology China Mobile Research Institute Beijing100876 China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

Orthogonal time frequency space (OTFS) modulation has been proposed as a promising technique to achieve high-reliability communications in high-mobility scenarios. In this paper, we consider a multi-user (MU) multiple-input multiple-output (MIMO)-OTFS downlink communication scenario, where an intelligent reflecting surface (IRS) is deployed to enhance the performance. Specifically, the delay- Doppler (DD) domain input-output relationship of such a system is first derived, based on which, the joint optimization of the precoding matrices and IRS reflection phase is studied to maximize the weighted sum rate (WSR) considering user fairness. Note that the corresponding optimization problem is non-convex. To tackle this challenge, we first reformulate the problem into a more traceable equivalent form by the weighted mean minimum square error (WMMSE) approach. Utilizing the characteristics of the DD domain signal relationship, we then decouple the reformulated problem and further transform it into two subproblems, which are solved by the Lagrangian function method and the project-descent-retracting (PDR) algorithm, respectively. The precoding matrices and reflection phase are jointly optimized by alternative optimization to maximize WSR. Simulation results demonstrate that, compared with benchmark schemes, the proposed WMMSE-ALT can improve the rate more than 85% in IRS-assisted MU-MIMO-OTFS systems. © 1967-2012 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Physical Layer Security for V2I Communications: Reflecting Surfaces Vs. Relaying

Physical Layer Security for V2I Communications: Reflecting S...

引用

2021 IEEE Global Communications Conference, GLOBECOM 2021

作者： Mensi, Neji Rawat, Danda B. Balti, Elyes Howard University Department of Electrical Engineering and Computer Science WashingtonDC20059 United States University of Texas at Austin Wireless Networking and Communications Group AustinTX78712 United States

Wireless vehicular network (WVN) is exponentially gaining attention from industries and researchers since it is the keystone of intelligent transportation systems (ITS). Despite the sophisticated features and services that it can offer, it is susceptible to networking attacks such as eavesdropping threats where the confidential transmitted signal could be overheard by a malicious entity. In this paper, we intend to study the physical layer security (PLS) where we consider the eavesdropping attack for vehicle-to-infrastructure (V2I) communications. We analyze the average secrecy capacity, under different scenarios by comparing the performances of employing the decode-and-forward (DF) relay, the amplify-and-forward fixed gain (AFFG) relay, and the intelligent reflecting surface (IRS). Actually, this comparison investigates the efficiency of IRS comparing to the traditional relaying systems, since it was introduced as a novel paradigm in wireless technology with highly promising potential, especially in 5G and 6G. © 2021 IEEE.

关键词： Intelligent vehicle highway systems

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：