检索结果-内蒙古大学图书馆

Adaptive isomap feature extractive gradient deep belief network classifier for diabetic retinopathy identification

Multimedia Tools and Applications 2025年第9期84卷 6349-6370页

作者： Singh, Alka Kumar, Rakesh Gandomi, Amir H. Department of Computer Science and Engineering Madan Mohan Malaviya University of Technology Gorakhpur India Faculty of Engineering & Information Technology University of Technology Sydney SydneyNSW Australia Óbuda University Budapest1034 Hungary

Diabetic retinopathy (DR) is an infection that bases eternal visualization loss in patients with diabetes mellitus. With DR, the glucose level in the blood increases, as well as its viscosity, this results in fluid leakage into surrounding tissues in the retina. In other words, DR represents the pathology of capillaries and venules in the retina with leakage effects, being the main acute retinal disorder caused by diabetes. Many DR detection methods have been previously discussed by different researchers;however, accurate DR detection with a reduced execution time has not been achieved by existing methods. The proposed method, the Shape Adaptive box linear filtering-based Gradient Deep Belief network classifier (SAGDEB) Model, is performed to enhance the accuracy of DR detection. The objective of the SAGDEB Model is to perform an efficient DR identification with a higher accuracy and lower execution time. This model comprises three phases: pre-processing, feature extraction, and classification. The shape adaptive box linear filtering image pre-processing is carried out to reduce the image noise without removing significant parts of image content. Then, an isomap geometric feature extraction is performed to compute features of different natures, like shape, texture, and color, from the pre-processed images. After that, the Adaptive gradient Tversky Deep belief network classifier is to perform classification. The deep belief network is probabilistic and generative graphical model that consists of multiple layers such as one input unit, three hidden units, and one output unit. The extracted image featuresare considered in the input layer and these images are sent to hidden layers. Tversky similarity index is applied in hidden layer 1 to analyze the extracted features with testing features. Regarding the similarity value, the sigmoid activation function is determined in hidden layer 2 so different levels of DR can be identified. Finally, the adaptive gradient method is

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Modeling Long- and Short-Term Service Recommendations with a Deep Multi-Interest Network for Edge Computing

引用

Tsinghua science and technology 2024年第1期29卷 86-98页

作者： Rui Yuan Shunmei Meng Ruihan Dou Xinna Wang Department of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210056China Faculty of Mathematics University of WaterlooWaterloo N2L 3G1Canada

Edge computing platforms enable application developers and content providers to provide context-aware services(such as service recommendations)using real-time wireless access network *** to recommend the most suitable candidate from these numerous available services is an urgent ***-through rate(CTR)prediction is a core task of traditional service ***,many existing service recommender systems do not exploit user mobility for prediction,particularly in an edge computing *** this paper,we propose a model named long and short-term user preferences modeling with a multi-interest network based on user *** uses a logarithmic network to capture multiple interests in different fields,enriching the representations of user short-term *** terms of long-term preferences,users'comprehensive preferences are extracted in different periods and are fused using a nonlocal *** experiments on three datasets demonstrate that our model relying on user mobility can substantially improve the accuracy of service recommendation in edge computing compared with the state-of-the-art models.

关键词： recommender system logarithmic network nonlocal network

来源：评论

学校读者我要写书评

暂无评论

An Efficient Machine Learning Classification Model for Rainfall Prediction in Bangladesh 2nd

An Efficient Machine Learning Classification Model for Rainf...

引用

2nd International Conference on Big Data, IoT and Machine Learning, BIM 2023

作者： Biplob, Md. Badiuzzaman Haque, Md. Mokammel Computer Science and Engineering Department Chittagong University of Engineering and Technology Chattogram Bangladesh Computer Science and Engineering Department Faculty of Engineering Chittagong University of Engineering and Technology Chattogram Bangladesh

ISBN: (纸本)9789819989362

One of the most significant and difficult tasks in the modern world is rainfall forecast. Rainfall is a complicated and nonlinear phenomenon that requires sophisticated computer modeling and simulation to anticipate with any degree of accuracy. In many regions of the world, daily rainfall totals are dispersed based on various frequency distribution functions. Rainfall has become a significant factor in agricultural countries. We provide a machine learning-based framework for forecasting the total monthly precipitation. In this study, three Bangladeshi weather stations’ daily rainfall was forecasted with a 365-day lead time using backpropagation long short-term memory (LSTM), random forest, and neural network algorithms. The predicted results from the selected algorithms were compared with the observed data to determine prediction precision by mean absolute error (MAE) test results. We found that selected algorithms predicted daily rainfall with reasonable accuracy. Therefore, year-long, month-long, and day-long rainfall can be predicted using these models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cyber-Physical Systems Security: A Review of Deep Learning and Blockchain Integration 5

Enhancing Cyber-Physical Systems Security: A Review of Deep ...

引用

5th International Conference on Image Processing and Capsule Networks, ICIPCN 2024

作者： Selvi, K. Dilip, Golda SRM Institute of Science and Technology Faculty of Engineering and Technology Department of Computer Science and Engineering Vadapalani Campus Chennai India

ISBN: (纸本)9798350367171

Cyber-Physical Systems (CPS) combine physical and computational elements to produce intelligent systems communicating with their surroundings. By integrating digital and physical processes, CPS provides increased functionality in various industries, including industry, transportation, and healthcare. However, there are security, data integrity, and privacy issues brought on by the extensive integration of CPS across several domains. Therefore, addressing these issues is significant for an effective and reliable CPS model. This study presents a comprehensive review exploring the synergistic relationship between two cutting-edge technologies, Deep Learning (DL) and Blockchain, deployed to resolve these issues in CPS. This study explores the efficiency of leveraging DL and blockchain to enhance the reliability and effectiveness of the CPS models. Also, this study examines the challenges and limitations faced by those DL and blockchain approaches during their implementation across different CPS domains. This comprehensive review provides promising directions for future research in this dynamic and interdisciplinary field for mitigating the challenges in CPS models. It also aids researchers, practitioners, and policymakers by providing a deeper understanding of the possible effects, difficulties, and opportunities related to utilizing DL and Blockchain technologies to improve the security and functionality of CPS. © 2024 IEEE.

关键词： Blockchain technologies Cyber-Physical Systems Deep Learning Internet of Things

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Learning Management Systems:Modern Developments, Challenges and Future Trends during theAge of ChatGPT

引用

computers, Materials & Continua 2024年第8期80卷 3289-3314页

作者： Sameer Qazi Muhammad Bilal Kadri Muhammad Naveed Bilal AKhawaja Sohaib Zia Khan Muhammad Mansoor Alam Mazliham Mohd Su’ud Department of Computer Science Faculty of EngineeringScience and TechnologyIQRA UniversityKarachi75500Pakistan College of Computer and Information Sciences Prince Sultan UniversityRiyadh11586Saudi Arabia Faculty of Engineering Department of Electrical EngineeringIslamic University of MadinahP.O.BOX 170Madinah41411Saudi Arabia Faculty of Engineering Department of Mechanical EngineeringIslamic University of MadinahP.O.BOX 170Madinah41411Saudi Arabia Faculty of Computing Riphah International UniversityIslamabad46000Pakistan Faculty of Computing and Informatics(FCI)Multimedia University Cyberjaya63100Malaysia Faculty of Engineering and Information Technology School of Computer ScienceUniversity of Technology SydneySydneyNSW 2007Australia

COVID-19 pandemic restrictions limited all social activities to curtail the spread of the *** foremost and most prime sector among those affected were schools,colleges,and *** education system of entire nations had shifted to online education during this *** shortcomings of Learning Management Systems(LMSs)were detected to support education in an online mode that spawned the research in Artificial Intelligence(AI)based tools that are being developed by the research community to improve the effectiveness of *** paper presents a detailed survey of the different enhancements to LMSs,which are led by key advances in the area of AI to enhance the real-time and non-real-time user *** AI-based enhancements proposed to the LMSs start from the Application layer and Presentation layer in the form of flipped classroom models for the efficient learning environment and appropriately designed UI/UX for efficient utilization of LMS utilities and resources,including AI-based *** layer enhancements are also required,such as AI-based online proctoring and user authentication using *** extend to the Transport layer to support real-time and rate adaptive encrypted video transmission for user security/privacy and satisfactory working of *** also needs the support of the Networking layer for IP-based geolocation features,the Virtual Private Network(VPN)feature,and the support of Software-Defined Networks(SDN)for optimum Quality of Service(QoS).Finally,in addition to these,non-real-time user experience is enhanced by other AI-based enhancements such as Plagiarism detection algorithms and Data Analytics.

关键词： Learning management systems chatbots ChatGPT online education Internet of Things(IoT) artificial intelligence(AI) convolutional neural networks natural language processing

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Network and GAN-Based Reversible Data Hiding in Encrypted Images: A Privacy-Preserving Approach

引用

SN computer science 2024年第1期5卷 45页

作者： Nalavade, Jagannath E. Patil, Akshta Buchade, Amar Jadhav, Nagesh Department of Computer Science and Engineering MIT Art Design and Technology University School of Computing Pune India Department of Computer Engineering Rajarambapu Institute of Technology Sakharale Sangli India

In light of recent incidents involving the leakage of private photographs of Hollywood celebrities from iCloud, the need for robust methods to safeguard image content has gained paramount importance. This paper addresses this concern by introducing a novel framework for reversible image editing (RIT) supported by reversible data hiding with encrypted images (RDH-EI) techniques. Unlike traditional approaches vulnerable to hacking, this framework ensures both efficient and secure data embedding while maintaining the original image’s privacy. The framework leverages two established methods: secret writing and knowledge activity. While secret writing is susceptible to hacking due to the complex nature of cipher languages, RDH-EI-supported RIT adopts a more secure approach. It replaces the linguistic content of the original image with the semantics of a different image, rendering the encrypted image visually indistinguishable from a plaintext image. This novel substitution prevents cloud servers from detecting encrypted data, enabling the adoption of reversible data hiding (RDH) methods designed for plaintext images. The proposed framework offers several distinct advantages. Firstly, it ensures the confidentiality of sensitive information by concealing the linguistic content of the original image. Secondly, it supports reversible image editing, enabling the restoration of the original image from the encrypted version without any loss of data. Lastly, the integration of RDH techniques designed for plaintext images empowers the cloud server to embed supplementary data while preserving image quality. Incorporating convolutional neural network (CNN) and generative adversarial network (GAN) models, the framework ensures accurate data extraction and high-quality image restoration. The applications of this concealed knowledge are vast, spanning law enforcement, medical data privacy, and military communication. By addressing limitations of previous methods, it opens new avenues

关键词： Deep hiding Deep neural network GAN model Reversible data hiding (RDH)

来源：评论

学校读者我要写书评

暂无评论

Enhanced Neutrosophic Set and Machine Learning Approach for Kidney Disease Prediction

引用

Neutrosophic Sets and Systems 2025年 80卷 465-477页

作者： Al-Doori, Humam M. Alkellezli, Tareef S. Abdelhafeez, Ahmed Eassaa, Mohamed Sawah, Mohamed S. El-Douh, Ahmed A. Cybersecurity Sciences Department College of Science Ashur University Baghdad Iraq Cybersecurity Engineering Department College of Engineering Ashur University Baghdad Iraq Computer Science Department Faculty of Information System and Computer Science October 6 University Giza12585 Egypt Applied Science Research Center Applied Science Private University Amman Jordan Department of Computer Science Faculty of Information Technology Ajloun National University P.O.43 Ajloun26810 Jordan Cybersecurity Technology Engineering Department College of Engineering Technology Ashur University Baghdad Iraq

Kidney disease (KD) is a gradually increasing global health concern. It is a chronic illness linked to higher rates of morbidity and mortality, a higher risk of cardiovascular disease and numerous other illnesses, and expensive medical expenses. The machine learning (ML) models are applied for KD prediction with higher accuracy and precision. The KD dataset has uncertainty and vague information, so, we used the neutrosophic set (NS) to deal with vague and uncertainty information in the KD dataset. The KD dataset is converted into the N-KD dataset with three membership functions: truth, indeterminacy, and falsity. Three ML models are used in this study such as logistic regression (LR), support vector machine (SVM), and k-nearest neighbor (KNN). These ML models are applied to the N-KD dataset. The results show the LR has higher accuracy and precision on the N-KD dataset than the original KD dataset. © 2025, University of New Mexico. All rights reserved.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Indoor Uncertain Semantic Trajectory Similarity Join

引用

Journal of computer science & technology 2024年第6期39卷 1441-1465页

作者： Hong-Bo Yin Dong-Hua Yang Kai-Qi Zhang Hong Gao Jian-Zhong Li Faculty of Computing Harbin Institute of TechnologyHarbin 150001China Center of Analysis Measurement and ComputingHarbin Institute of TechnologyHarbin 150001China Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China

With the widespread deployment of indoor positioning systems, an unprecedented scale of indoor trajectories is being produced. By considering the inherent uncertainties and the text information contained in such an indoor trajectory, a new definition named Indoor Uncertain Semantic Trajectory is defined in this paper. In this paper, we focus on a new primitive, yet quite essential query named Indoor Uncertain Semantic Trajectory Similarity Join (IUST-Join for short), which is to match all similar pairs of indoor uncertain semantic trajectories from two sets. IUST-Join targets a number of essential indoor applications. With these applications in mind, we provide a purposeful definition of an indoor uncertain semantic trajectory similarity metric named IUS. To process IUST-Join more efficiently, both an inverted index on indoor uncertain semantic trajectories named 3IST and the first acceleration strategy are proposed to form a filtering-and-verification framework, where most invalid pairs of indoor uncertain semantic trajectories are pruned at quite low computation cost. And based on this filtering-and-verification framework, we present a highly-efficient algorithm named Indoor Uncertain Semantic Trajectory Similarity Join Processing (USP for short). In addition, lots of novel and effective acceleration strategies are proposed and embedded in the USP algorithm. Thanks to these techniques, both the time complexity and the time overhead of the USP algorithm are further reduced. The results of extensive experiments demonstrate the superior performance of the proposed work.

关键词： filtering-and-verification framework indoor uncertain semantic trajectory inverted index trajectory similarity join

来源：评论

学校读者我要写书评

暂无评论

design an optimization based ensemble machine learning framework for detecting rice leaf diseases

引用

Multimedia Tools and Applications 2024年第36期83卷 84401-84424页

作者： Rajasekhar, Veeramreddy Arulselvi, Gnanasekaran Babu, K. Suresh Department of Computer Science Engineering Annamalai University Tamilnadu Chidambaram India Department of Computer Science and Engineering Faculty of Engineering and Technology Annamalai University Tamil Nadu Chidambaram India International School of Technology and Sciences for Women East Gonagudem Rajanagaram A.P Rajamahendravaram India

The agriculture industry is currently dealing with serious issues with rice plants as a result of illnesses that decrease the quantity and output of the harvest. Numerous fungi and bacteria diseases harm plants that affect the growth of yield. So identification of the detection of crop diseases is essential for enhancing the productivity of crops. Many techniques have been developed to improve disease detection in crops but there are still some issues such as noise, time consumption, delay, poor segmentation, and less accuracy. To overcome these issues, this paper, designed a Spider Monkey-based Random Forest (SMbRF) model for accurate detection and classification of rice leaf diseases and the designed model was implemented in the Python system. The main aim is to develop an optimization-based random forest technique for accurate prediction of rice leaf disease by exact segmentation. Initially, preprocessing is performed to enhance the data quality and remove errors. Furthermore, separate the lesions using mean shift image segmentation and extract the shape and color features to improve the detection results of the developed model. As well, spider monkey fitness is updated in the RF classification layer for accurate classification of diseases and improves accuracy with less execution time. The experiment results show the reliability and efficiency of the designed model, it attains better performance in accuracy, sensitivity, specificity, and precision. The designed model attained 99.29% accuracy, 99.52% sensitivity, 98.76% precision, and 99% specificity proving the scalability of the designed model. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Sentimental Analysis for Trump Tweets Using R 8th

Sentimental Analysis for Trump Tweets Using R

引用

8th International Conference on Information System design and Intelligent Applications, ISDIA 2024

作者： Nishok, V.G. Bharathi, N. Department of Computer Science and Engineering Faculty of Engineering and Technology SRM Institute of Science and Technology Vadapalani Campus Chennai India

ISBN: (纸本)9789819786657

Twitter is the best source for sentiment analysis, product reviews, current issues, etc. Sentiment analysis extracts positive and negative opinions from the Twitter data set, and R studio provides the best environment for this Twitter sentiment analysis. Find if Trump’s phone Android is fake or not by comparing his iPhone and Android tweets using R with datasets. Detailed analysis is not there. The Twitter data collected might not be representative of the entire population. By using filtering of tweets as we need Android and iPhone tweets here and usage of tweets per day, no of tweets with and without quotes and pictures and links, taking common words from Android and iPhone and trying with log ratio that is Android /iPhone and with log ratio and common word find sentiment. We got good results by the usage of Twitter of each device, no of tweets quoted and non-quoted, no picture/link and picture/link, most common words, words compare with Android and iPhone and log ratio, finding sentiment of it which type of word it is. My work helps his account is a trump or not for Android as it contains negative tweets by common words, Android and iPhone words and log odd ratio with that it detects sentiment as it is a positive, negative or neutral by showing anger, sad, happy, etc. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Tweets

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：