检索结果-内蒙古大学图书馆

Strategy for Rapid Diabetic Retinopathy Exposure Based on Enhanced Feature Extraction Processing

computers, Materials & Continua 2023年第6期75卷 5597-5613页

作者： V.Banupriya S.Anusuya Department of Computer Science and Business Systems M.Kumarasamy College of EngineeringKarur639113TamilnaduIndia Department of Information Technology Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesSIMATSChennai602117Tamil NaduIndia

In the modern world,one of the most severe eye infections brought on by diabetes is known as diabetic retinopathy(DR),which will result in retinal damage,and,thus,lead to *** retinopathy(DR)can be well treated with early *** fundus images of humans are used to screen for lesions in the ***,detecting DR in the early stages is challenging due to the minimal ***,the occurrence of diseases linked to vascular anomalies brought on by DR aids in diagnosing the ***,the resources required for manually identifying the lesions are ***,training for Convolutional Neural Networks(CNN)is more *** proposed research aims to improve diabetic retinopathy diagnosis by developing an enhanced deep learning model(EDLM)for timely DR identification that is potentially more accurate than existing CNN-based *** proposed model will detect various lesions from retinal images in the early ***,characteristics are retrieved from the retinal fundus picture and put into the EDLM for *** dimensionality reduction,EDLM is ***,the classification and feature extraction processes are optimized using the stochastic gradient descent(SGD)*** EDLM’s effectiveness is assessed on the KAG-GLE dataset with 3459 retinal images,and results are compared over VGG16,VGG19,RESNET18,RESNET34,and *** results show that the EDLM achieves higher average sensitivity by 8.28%for VGG16,by 7.03%for VGG19,by 5.58%for ResNet18,by 4.26%for ResNet 34,and by 2.04%for ResNet 50,respectively.

关键词： Diabetic retinopathy deep learning classification retinal fundus

来源：评论

学校读者我要写书评

暂无评论

Designing Quantum-Resilient Blockchain Frameworks: Enhancing Transactional Security with Quantum Algorithms in Decentralized Ledgers

引用

International Journal of Advanced computer science and Applications 2025年第4期16卷 618-628页

作者： Kale, Meenal R. Baker El-Ebiary, Yousef A. Sathiya, L. Burugari, Vijay Kumar Yulduz, Erkiniy Muniyandy, Elangovan Alanazi, Rakan Department of Humanities Yeshwantrao Chavan College of Engineering Hingna Nagpur India Faculty of Informatics and Computing UniSZA University Malaysia Department of CSE Panimalar Engineering College Chennai India Dept of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh Guntur India Automatic Control and Computer Engineering Department Turin Polytechnic University in Tashkent Tashkent Uzbekistan Department of Biosciences-Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Applied Science Research Center Applied Science Private University Amman Jordan Department of Information Technology Faculty of Computing and Information Technology Northern Border University Rafha Saudi Arabia

Quantum computing is progressing at a fast rate and there is a real threat that classical cryptographic methods can be compromised and therefore impact the security of blockchain networks. All of the ways used to secure blockchain like Rivest–Shamir–Adleman (RSA), Elliptic Curve Cryptography (ECC) and Secure Hash Algorithm 256-bit (SHA256) are the characteristic of the traditional cryptographic techniques vulnerable to attack by quantum algorithms: Shor’s and Grover’s algorithms: can efficiently break asymmetric encryption and speed up brute force attacks. Because of this vulnerability, there exists a need to develop an advance quantum resilient blockchain framework to protect the decentralized ledgers from the future threats of the quantum. This research proposes Post-Quantum Cryptography (PQC), Quantum Key Distribution (QKD) and Quantum Random Number Generation (QRNG) as a formidable architectural integration, to fortify security of blockchain. Classical encryption is replaced with PQC, QKD with secure key exchange by detecting eavesdropping, and QRNG with improving cryptographic randomness to remove the predictable key vulnerability. Only with a small loss of transaction efficiency, we increase transaction encryption accuracy, key exchange security, and resistance to quantum attacks. In this quantum enhanced blockchain design, the idea is to preserve the decentralization, transparency and security and at the same time overcome the future quantum threat. By going through rigorous analysis and comparative evaluation, we demonstrate that the approach saves blockchain networks from the emerging quantum risks to make sure that the decentralized finance, smart contracts and cross chain transactions. © (2025), (science and information Organization). All rights reserved.

关键词： Quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

A comprehensive evaluation of large language models in mining gene relations and pathway knowledge

引用

Quantitative Biology 2024年第4期12卷 360-374页

作者： Muhammad Azam Yibo Chen Micheal Olaolu Arowolo Haowang Liu Mihail Popescu Dong Xu Department of Electrical Engineering and Computer Science University of MissouriColumbiaMissouriUSA Bond Life Sciences Center University of MissouriColumbiaMissouriUSA Institute for Data Science and Informatics University of MissouriColumbiaMissouriUSA Department of Biomedical Informatics Biostatistics and Medical EpidemiologyUniversity of MissouriColumbiaMissouriUSA

Understanding complex biological pathways,including gene–gene interactions and gene regulatory networks,is critical for exploring disease mechanisms and drug *** literature curation of biological pathways cannot keep up with the exponential growth of new discoveries in the ***-scale language models(LLMs)trained on extensive text corpora contain rich biological information,and they can be mined as a biological knowledge *** study assesses 21 LLMs,including both application programming interface(API)-based models and open-source models in their capacities of retrieving biological *** evaluation focuses on predicting gene regulatory relations(activation,inhibition,and phosphorylation)and the Kyoto Encyclopedia of Genes and Genomes(KEGG)pathway *** indicated a significant disparity in model ***-based models GPT-4 and Claude-Pro showed superior performance,with an F1 score of 0.4448 and 0.4386 for the gene regulatory relation prediction,and a Jaccard similarity index of 0.2778 and 0.2657 for the KEGG pathway prediction,***-source models lagged behind their API-based counterparts,whereas Falcon-180b and llama2-7b had the highest F1 scores of 0.2787 and 0.1923 in gene regulatory relations,*** KEGG pathway recognition had a Jaccard similarity index of 0.2237 for Falcon-180b and 0.2207 for *** study suggests that LLMs are informative in gene network analysis and pathway mapping,but their effectiveness varies,necessitating careful model *** work also provides a case study and insight into using LLMs das knowledge *** code is publicly available at the website of GitHub(Muh-aza).

关键词： biomedical text mining gene-gene interaction KEGG pathway large language model

来源：评论

学校读者我要写书评

暂无评论

Heart Failure: Machine Learning Prediction Within a 5-Year Framework 24

Heart Failure: Machine Learning Prediction Within a 5-Year F...

引用

24th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2024

作者： Tsarapatsani, Konstantina-Helen Tsakanikas, Vasilios D. Sakellarios, Antonis Trampisch, Hans J. Karapintzou, Efterpi Rudolf, Henrik Matsopoulos, George K. Fotiadis, Dimitrios I. Biomedical Research Institute Foundation for Research and Technology-Hellas Ioannina Greece Ruhr University Bochum Department of Medical Informatics Biometry and Epidemiology Bochum Germany University of Ioannina Unit of Medical Technology and Intelligent Information Systems Dept. of Materials Science and Engineering Greece Institute for Biostatistics and Informatics in Medicine and Ageing Research University Medical Center Rostock Germany School of Electrical and Computer Engineering National Technical University of Athens Athens Greece University of Ioannina and Biomedical Research Institute-FORTH Unit of Medical Technology and Intelligent Information Systems Dept. of Materials Science and Engineering Ioannina Greece

ISBN: (纸本)9798331518622

Heart failure (HF) is a complex syndrome that is affected by many factors and causes. It is crucial to early recognize the disease subtypes and the unidentified clinical pathways that give rise to it. Machine learning (ML) is the tool that assist to deal with these challenges and improve the prediction of HF. In this work, the HF risk prediction was implemented by employed ML classifiers, such as Random Forest (RF), Extreme Grading Boosting (XGBoost) and Light Gradient-Boosting Machine (LGBM). We utilized the data from the German epidemiological trial on ankle brachial index - getABI cohort, which includes 6,454 patients. The performance of classifiers was estimated by Accuracy (ACC), Sensitivity, Specificity and the area under the receiver operating characteristic curve (AUC) in mean values for each ML classifier. The results were also interpreted using the Explainable artificial intelligence (XAI) approach, the Shapley Additive exPlanations (SHAP) values. Our work reveals that LGBM classifier predict the HF risk within 5 years follow-up in general population with 68 % accuracy. Moreover, the N-terminal pro-B-type natriuretic peptide (NT-proBNP) was identified as the most important feature for HF risk prediction. © 2024 IEEE.

关键词： Risk perception

来源：评论

学校读者我要写书评

暂无评论

Adaptive Indoor People-Counting System Based on Edge AI Computing

引用

IEEE Transactions on Emerging Topics in Computational Intelligence 2024年第1期8卷 255-263页

作者： Yen, Mao-Hsu Lin, Bor-Shyh Kuo, Yu-Lun Lee, I-Jung Lin, Bor-Shing National Taiwan Ocean University Department of Computer Science and Engineering Keelung City202301 Taiwan National Yang Ming Chiao Tung University Institute of Imaging and Biomedical Photonics Tainan71150 Taiwan Chi Mei Medical Center Department of Medical Research Tainan71004 Taiwan National Taipei University Department of Computer Science and Information Engineering New Taipei City237303 Taiwan National Taipei University College of Electrical Engineering and Computer Science New Taipei City237303 Taiwan

Since the outbreak of COVID-19 in 2019, people counting in confined spaces has become essential for controlling the flow of people and reducing viral spread. Many people-counting systems use a fisheye lens to achieve a wide viewing range. However, the images captured with a fisheye lens can have different sizes and deformations due to different camera heights, which consequently affects the accuracy of people counting. In this study, a Raspberry Pi 4 development board attached to a fisheye lens was used to construct an edge computing platform for people counting by using artificial intelligence. A modified You Only Look Once (YOLO) model, which has three output layers and a spatial pyramid pooling module, is proposed to recognize people in images captured at various heights. For efficiently running this deep learning model on the proposed edge computing platform, a TensorFlow Lite framework was used to reduce the model size. The final experimental results indicated that the mean average error and mean squared error of the modified tiny version of the YOLO v4 model were 0.249 and 0.292, respectively, and the detection speed of the platform was 2 frames per second. The results indicate that the proposed edge computing platform can efficiently and accurately count the number of people. Because the proposed system uses edge computing, it can effectively solve personal privacy and transmission bandwidth problems. © 2017 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Delving into the Realm of information-Theoretic Security Emerging Trends and Future Directions

Delving into the Realm of Information-Theoretic Security Eme...

引用

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Srilekha, Gopu Santosh Kumar, B. Singh, Navdeep Singh, Jay Bhavana, Munugapati Jabbar, Ahmed Sabah Abed AL-Zahra Institute Of Aeronautical Engineering Department Of Computer Science And Engineering Telangana Hyderabad India New Horizon College Of Engineering Department Of Computer Science Engineering Bangalore India Lovely Professional University Phagwara India Gl Bajaj Institute Of Technology & Management U.P. Greater Noida India Mlr Institute Of Technology Department Of Computer Science And Information Technology Telangana Hyderabad India College Of Medical Technology The Islamic University Medical Laboratory Technology Department Najaf Iraq

ISBN: (纸本)9798350366846

QKD, ECC, PQC, SMPC, and biometric-based authentication are examined in this work as essential information-theoretic security approaches. Each solution improves information-theoretic security by improving communication, error reduction, quantum-resistant cryptography, project collaboration, and identity verification. Quantum Key Distribution employs quantum entanglement and regular transmission to secure key exchange in a 12-step flowchart. Error-Correcting Code Implementation employs Reed-Solomon codes to discover and rectify errors in delivered messages in 10 steps, protecting data. Post-Quantum Cryptography uses a 10-step graphic to demonstrate lattice-based solutions for post-quantum security and secure communication. A 10-step 'safe multi-party computing' procedure enables individuals to collaborate on a computer project while safeguarding their privacy. It uses homomorphic encryption to secure protected data computations. Biometric authentication employs biometric data to verify a person's name in 10 steps with complicated arithmetic. Tables and graphs indicate that the information-theoretic approach outperforms other security techniques in key size, quantum attack resistance, authentication strength, and total security. These results demonstrate that the suggested strategy may considerably increase information-theoretic security in many scenarios. The response to the developing field of information security is robust. © 2024 IEEE.

关键词： Quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

Study on the Compression Property of Formation Space for Theoretical Support

Study on the Compression Property of Formation Space for The...

引用

2023 Intelligent Computing and Control for engineering and Business Systems, ICCEBS 2023

作者： Rajesh Kanna, R. Sharmila, L. Senthil, K. Umadevi, G. Raja, R. Vinston Srm Institute of Science and Technology Department of Computer Science and Engineering Ramapuram India Agni College of Technology Department of Computer Science and Engineering Tamil Nadu India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering India Panimalar Engineering College Department of Information Technology Chennai India

ISBN: (纸本)9798350394580

At present, the open stopping with subsequent filling mining of the 'two step' mode has received significant attention. The recovery method entails dividing the ore block into the first step ore room and the second step ore room, mining the first step ore room initially and filling the formation space using cemented materials and then mining the second step ore room and filling the formation space using tailings. There are two questions to resolve in the tailings-filling work of a goaf. The first is making an accurate filling plan to assure the accomplishment of the work on time, which will not affect the recovery progress. The other is accurately calculating the lateral pressure that tailings exert on the cemented fill body to provide theoretical support for designing the required strength of cement filling body to assure its stability and the safety of the recovery process of second step ore room. These questions are associated with the density of the tailings. However, the open stoping with subsequent filling mining method is characterized by a high stage and long span. When the recovery of ore room is finished, the volume of the resulting goaf is large. The density of the tailings is affected by its weight and this exhibits non-linear growth as the height of the tailings increases. Therefore, to solve these questions, research is needed on the compressibility of the tailings under its weight. © 2023 IEEE.

关键词： Compacting rule, Model Self-compacting behavior Tailings

来源：评论

学校读者我要写书评

暂无评论

RAFA-Net: Region Attention Network for Food Items and Agricultural Stress Recognition

IEEE Transactions on AgriFood Electronics

引用

IEEE Transactions on AgriFood Electronics 2025年第1期3卷 121-133页

作者： Bera, Asish Krejcar, Ondrej Bhattacharjee, Debotosh Birla Institute of Technology and Science Department of Computer Science and Information Systems Pilani333031 India University of Hradec Kralove Center for Basic and Applied Science Faculty of Informatics and Management Hradec Kralove50003 Czech Republic Skoda Auto University Mlada Boleslav29301 Czech Republic Universiti Teknologi Malaysia Malaysia Japan International Institute of Technology Kuala Lumpur81310 Malaysia Jadavpur University Department of Computer Science and Engineering Kolkata700032 India

Deep convolutional neural networks (CNNs) have facilitated remarkable success in recognizing various food items and agricultural stress. A decent performance boost has been witnessed in solving the agro-food challenges by mining and analyzing region-based partial feature descriptors. Also, computationally expensive ensemble learning schemes fusing multiple CNNs have been studied in earlier works. This work proposes a region attention scheme for modeling long-range dependencies by building a correlation among different regions within an input image. The attention method enhances feature representation by learning the usefulness of context information from complementary regions. Spatial pyramidal pooling and average pooling pairs aggregate partial descriptors into a holistic representation. Both pooling methods establish spatial and channelwise relationships without incurring extra parameters. A context gating scheme is applied to refine the descriptiveness of weighted attentional features, which is relevant for classification. The proposed region attention network for food items and agricultural stress recognition method, dubbed RAFA-Net, has been experimented on three public food datasets, and has achieved state-of-the-art performances with distinct margins. The highest top-1 accuracy of RAFA-Net is 91.69%, 91.56%, and 96.97% on the UECFood-100, UECFood-256, and MAFood-121 datasets, respectively. In addition, better accuracies have been achieved on two benchmark agricultural stress datasets. The best top-1 accuracies on the Insect Pest (IP-102) and PlantDoc-27 plant disease datasets are 92.36%, and 85.54%, respectively;implying RAFA-Net's generalization capability. © 2023 IEEE.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Unlocking Complex Patterns Through the Power of Deep Learning for Advanced Data Analysis and Prediction

Unlocking Complex Patterns Through the Power of Deep Learnin...

引用

2024 International Conference on Cybernation and Computation, CYBERCOM 2024

作者： Sasikumar, S. Kumar, M. Guru Vimal Paramesh, J. Sriram, K.P. Anbalagan, E. Saveetha Engineering College Department of Computer Science and Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R and D Institute of Science and Technology Department of Computer Science and Engineering Avadi Chennai600062 India St. Joseph's Institute of Technology Information Technology OMR Chennai600119 India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331542344

Supervised deep learning has brought changes to data analysis and prediction function by leveraging its capacity to make many number of relationships with heterogeneous forms of data. This paper compares deep learning techniques like Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Long Short-Term Memory (LSTM) networks in three tasks: There are three types of tasks, including image classification, time-series prediction, and text classification. In the picture simulation of the CIFAR-10 set for training, the accuracy of the ResNet model was 95% while the accuracy of VGG16 w 93%. When applied to the M4 competition dataset in time-series prediction, the LSTM model was superior to other benchmarks with MAE of 0.40 and RMSE of 0.60, with the RNN model giving MAE of 0.50 and RMSE of 0.65. It is 0.92 of accuracy, 0.91 of F1 score, and 0.921 for precision using the IMDB reviews dataset in text classification of movies using the CNN-LSTM hybrid model while the Bi-LSTM only had an accuracy of 0.89 and an F1 score of 0.889. Even though models, such as ResNet and Bi-LSTM, took slightly more time to train-Approximately 5.0 hours-it was because the epoch models were significantly superior to the baseline model. The present work focuses on the benefits of deep learning architectures in providing interpretable patterns in numerous applications. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Telecom Customer Loyalty Through Churn Prediction Models 8

Enhancing Telecom Customer Loyalty Through Churn Prediction ...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Thanam, A. Malchijah Raj, M.S. Joel, M. Robinson Shanthakumar, P. Jacson, J. Joel Department of Computer Science and Engineering Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Mathematics Tamil Nadu Chennai602105 India Kcg College of Technology Department of Computer Science and Engineering Chennai India Nehru Institute of Technology Department of Computer Science and Engineering Coimbatore India Kings Engineering College Department of Information Technology Chennai India

ISBN: (纸本)9798350367904

In the rapidly evolving telecommunications sector, maintaining profitability and growth depends on customer retention. With the goal of identifying the critical elements influencing customer attrition and creating a useful predictive model, this study offers a thorough investigation of customer churn prediction using a telecom dataset. This study uses a dataset that contains a variety of client features, such as account details, demographic data, and service consumption trends. Here, the data preparation techniques are used to manage anomalies, missing values, and data normalisation. The study uses a range of machine learning methods to forecast churn, such as support vector machines, random forests, decision trees, logistic regression, and gradient boosting. Metrics including accuracy, then precision, also the recall, then F1 score, and also the area under the curve of receiver operating characteristic are used to assess each model's performance (AUC-ROC). By use of cross-validation and hyperparameter adjustment, we guarantee the models' resilience and generalizability. Significant churn predictors, including contract type, duration, monthly costs, and customer support interactions, are identified by our investigation. According to the research, month-to-month contract holders who have higher monthly fees and frequent contact with customer service are more likely to experience customer attrition. The model with the highest degree of prediction accuracy is the random forest, which has an AUC-ROC of 0.85, making it the best-performing model. This paper offers a useful foundation for putting churn prediction models into practice in addition to highlighting the important variables causing customer churn in the telecom industry. Telecom firms may lower churn rates by creating focused retention tactics, such personalised offers and better customer care, by proactively identifying at-risk clients. The findings highlight how crucial it is to use machine learning and data a

关键词： Sales

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：