检索结果-内蒙古大学图书馆

Video and image quality improvement using an enhanced optimized dehazing technique

Multimedia Tools and Applications 2024年 1-19页

作者： Ayoub, Abeer El-Shafai, Walid El-Samie, Fathi E. Abd Hamad, Ehab K. I. EL-Rabaie, El-Sayed M. Electrical Engineering Department Faculty of Engineering Aswan University Aswan81542 Egypt Department of Electronics and Electrical Communication Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

The detrimental effects of atmospheric haze frequently plague outdoor imagery. This phenomenon arises from the scattering of light by minute particles within the ambient environment surrounding the scene to be imaged. Haze engenders an overall whitening of the image, leading to diminished contrast. To address these issues and enhance the quality of hazy images and videos, an enhanced dehazing technique is proposed. The proposed technique includes image enhancement before the optimal dehazing process. The enhancement stage entails the implementation of both homomorphic processing and Contrast Limited Adaptive Histogram Equalization (CLAHE), serving to control the image dynamic range, while concurrently heightening the image contrast. The culminating stage encompasses an optimized dehazing technique, adept at expunging haze-induced artifacts from images. The homomorphic processing and CLAHE, applied in the pre-processing step, establish a foundation for the subsequent dehazing procedure. This proposed methodology is systematically applied to a gamut of visual outputs, including visible videos, Near-Infrared (NIR) frames, and authentic hazy images. Comparative evaluations of the proposed technique, homomorphic-processing-based enhanced dehazing, and standalone dehazing techniques is undertaken on different video types encompassing five frames. It is evident that the proposed technique, synergizing the homomorphic processing, CLAHE, and dehazing, outperforms alternative strategies. Furthermore, the proposed technique is subjected to a comparative study with various existing dehazing techniques over real hazy images. The assessment depends on Peak Signal-to-Noise Ratio (PSNR), correlation, and entropy metrics. The results underscore the efficacy of the proposed technique, particularly in terms of spectral entropy enhancement of dehazed frames. For both visible and NIR frames, the percentages of enhancement by the proposed technique are 17.66% and 118.48%, respectively. ©

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Proposed 3D chaos-based medical image cryptosystem for secure cloud-IoMT eHealth communication services

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 1-28页

作者： El-Shafai, Walid Khallaf, Fatma El-Rabaie, El-Sayed M. El-Samie, Fathi E. Abd Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Electrical Engineering Faculty of Engineering Ahram Canadian University Giza 6th October City Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Riyadh84428 Saudi Arabia

Medical image encryption is a mandatory process in various healthcare, Internet of Medical Things (IoMT) and cloud services. This paper provides a robust cryptosystem based on a 3D chaotic map for the medical image encryption in secure IoMT and cloud services. The proposed encryption method depends on a 3D chaotic map. With this map, a nonlinear ciphering process is implemented for pixel value diffusion and position permutation. Five operations are conducted in the suggested cryptosystem on the medical images to be transmitted in order to attain a high security level. These operations are 3D chaos generation, chaos histogram equalization, row rotation, column rotation, and XOR operation. To validate the suggested cryptosystem, different medical images with different characteristics are tested. Moreover, the suggested cryptosystem and more recent state-of-the-art security systems are discussed and analyzed in a comparative study. Different assessment parameters are adopted to assess the suggested cryptosystem, which reveals high security performance. The simulation outcomes show that the suggested cryptosystem is trustworthy. Furthermore, it offers high robustness levels and recommended security levels for utilization in healthcare, IoMT and cloud service applications. It is observed that the amount of average entropy obtained by the proposed 3D chaos cryptosystem is 7.95 which is very close to its best value of 8, and the average NPCR value is 99.62% which is also much close to its supreme value of 99.60%. In addition, all other results scored for the test evaluation parameters on the suggested cryptosystem are superior to those of the traditional security systems. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Latent Dirichlet Allocation for Topic Modeling and Intelligent Document Classification 2nd

Latent Dirichlet Allocation for Topic Modeling and Intelli...

引用

2nd International Conference on Innovations in Data Analytics, ICIDA 2023

作者： Chatterjee, Rajdeep Mukherjee, Chandan Chatterjee, Siddhartha Nath, Biswaroop School of Computer Engineering KIIT Deemed to be University Bhubaneswar751024 India School of Engineering and Technology The Assam Kaziranga University Jorhat785006 India Department of Computer Science and Engineering College of Engineering and Management Kolaghat West Bengal Purba Medinipu721171 India

ISBN: (纸本)9789819749270

Document classification plays a pivotal role in facilitating faster and more intelligent information retrieval. This paper specifically focuses on document image classification, utilizing optical character recognition (OCR) to transform it into a natural language processing (NLP) problem. Our research aims to enhance the accuracy of popular models by incorporating Latent Dirichlet Allocation (LDA), a text mining and topic modeling technique based on probabilistic distributions. By integrating LDA, we aim to leverage its capabilities for filtering the OCR-generated textual data. This filtering process enables us to extract important features and improve the performance of our models. In our study, we employed several models, in which the Long Short-Term Memory (LSTM) model, a widely used deep learning architecture, to tackle the document image classification task achieved the most promising results, with the LSTM achieving a notable accuracy rate of 92%. To establish the robustness of our findings, we conduct extensive testing on a separate, larger test dataset, which further validates the accuracy and reliability of our proposed approach. Real-life test scenarios are also considered, wherein our LSTM model successfully identifies different types of documents. The successful application of our model in real-world scenarios highlights its potential for practical implementation. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Forecasting and managing urban futures: machine learning models and optimization of urban expansion

引用

Asian Journal of Civil engineering 2024年第6期25卷 4673-4682页

作者： Abid, Mohammed Talib Aljarrah, Njood Shraa, Tamer Alghananim, Haneen Marouf Department of Architecture College of Engineering Al-Nahrain University Baghdah Iraq Computer Sciences Faculty of Information Technology and Computer Sciences Ajloun National University Ajloun Jordan Faculty of Science and Information Technology Cyber Security Irbid National University Irbid Jordan Faculty of Engineering Architecture Department Ain Shams University Cairo Egypt

This paper presents a novel method for predicting and controlling urban growth by combining convolutional neural networks (CNN) with Spider Monkey Optimization (SMO) to efficiently use their combined capabilities. This strategy utilizes sophisticated machine learning algorithms to forecast urban development patterns, while optimization technologies enhance these forecasts by including sustainable urban design ideas. Integration plays a crucial role in tackling the difficulties presented by fast urbanization, including issues related to land use, resource administration, and environmental sustainability in the fields of civil and architectural engineering. The study employs large datasets to assess the efficacy of CNN models in detecting urban expansion patterns and enhances these models with optimization scenarios encompassing land use, traffic flow, electricity efficiency, water resources, and waste management, all with the goal of enhancing urban sustainability. The findings demonstrate a significant improvement in the precision of predictions and the ability to maintain positive results, highlighting the crucial role of integrating machine learning and optimization in urban planning methodologies. This method not only provides urban planners and politicians with strong and effective tools for making decisions but also creates opportunities for implementing creative and sustainable solutions for urban growth. The results provide a substantial contribution to the existing urban planning literature by demonstrating the actual use of these technologies in regulating urban expansion. This will stimulate more study in this rapidly evolving subject. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Convolutional neural networks Machine learning Optimization techniques Spider monkey optimization Sustainable urban planning Urban expansion

来源：评论

学校读者我要写书评

暂无评论

Harmfully Manipulated Images Matter in Multimodal Misinformation Detection 24

Harmfully Manipulated Images Matter in Multimodal Misinforma...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Wang, Bing Wang, Shengsheng Li, Changchun Guan, Renchu Li, ximing College of Computer Science and Technology Jilin University Jilin Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education Jilin University China

ISBN: (纸本)9798400706868

Nowadays, misinformation is widely spreading over various social media platforms and causes extremely negative impacts on society. To combat this issue, automatically identifying misinformation, especially those containing multimodal content, has attracted growing attention from the academic and industrial communities, and induced an active research topic named Multimodal Misinformation Detection (MMD). Typically, existing MMD methods capture the semantic correlation and inconsistency between multiple modalities, but neglect some potential clues in multimodal content. Recent studies suggest that manipulated traces of the images in articles are non-trivial clues for detecting misinformation. Meanwhile, we find that the underlying intentions behind the manipulation, e.g., harmful and harmless, also matter in MMD. Accordingly, in this work, we propose to detect misinformation by learning manipulation features that indicate whether the image has been manipulated, as well as intention features regarding the harmful and harmless intentions of the manipulation. Unfortunately, the manipulation and intention labels that make these features discriminative are unknown. To overcome the problem, we propose two weakly supervised signals as alternatives by introducing additional datasets on image manipulation detection and formulating two classification tasks as positive and unlabeled learning problems. Based on these ideas, we propose a novel MMD method, namely Harmfully Manipulated Images Matter in MMD (Hami-m3d). Extensive experiments across three benchmark datasets can demonstrate that Hami-m3d can consistently improve the performance of any MMD baselines. © 2024 ACM.

关键词： image manipulation

来源：评论

学校读者我要写书评

暂无评论

Periodic Prompt on Dynamic Heterogeneous Graph for Next Basket Recommendation 24

Periodic Prompt on Dynamic Heterogeneous Graph for Next Bask...

引用

24th IEEE International Conference on Data Mining, ICDM 2024

作者： Li, Ru-Bin Chen, Man-Sheng Ding, xin-Yu Wang, Chang-Dong xie, Sihong Liu, Shuangyin Chen, Min Guizani, Mohsen School of Electronics and Information Technology Sun Yat-sen University Guangzhou China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China College of Information Science and Technology Zhongkai University of Agriculture and Engineering Guangzhou China Guangzhou China School of Computer Science and Engineering South China University of Technology Guangzhou China Machine Learning Department Abu Dhabi United Arab Emirates

ISBN: (纸本)9798331506681

In next basket recommendation, baskets are usually formed through a large number of user interactions with items in the early stage. In general, the existing methods for next basket recommendation primarily focus on historical purchase behavior of users, assuming that user purchase interests are static, and overlook the dynamic and diverse changes in user purchase interests. In order to fully capture dynamic user interests and provide users with more diverse recommendations, we propose our method, Dynamic Heterogeneous Graph Prompt (DHGP), for next basket recommendation. By constructing a dynamic heterogeneous graph, we can adequately consider the influence of various interactive behaviors on the user's baskets at different times. Furthermore, we introduce a periodic dynamic heterogeneous prompt strategy to capture the interest directions between baskets from different users and provide users with more diverse interest directions. Extensive experimental validation on six real world datasets demonstrates that our method shows strong applicability across datasets under various conditions and outperforms several state-of-the-art recommendation methods. To the best of our knowledge, DHGP is the first next basket recommendation method that effectively combines dynamic and heterogeneous information. The implementation code is accessible at https://***/AllminerLab. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Bayesian Multidimensional Scaling for Location Awareness in Hybrid-Internet of Underwater Things

引用

IEEE/CAA Journal of Automatica Sinica 2022年第3期9卷 496-509页

作者： Ruhul Amin Khalil Nasir Saeed Mohammad Inayatullah Babar Tariqullah Jan Sadia Din IEEE Department of Electrical Engineering Faculty of Electrical and Computer EngineeringUniversity of Engineering and TechnologyPeshawar 25120Pakistan the Department of Electrical Engineering Northern Border UniversityArar 73222Saudi Arabia College of Science and Engineering Hamad Bin Khalifa UniversityDoha 34110Qatar

Localization of sensor nodes in the internet of underwater things(IoUT)is of considerable significance due to its various applications,such as navigation,data tagging,and detection of underwater ***,in this paper,we propose a hybrid Bayesian multidimensional scaling(BMDS)based localization technique that can work on a fully hybrid IoUT network where the nodes can communicate using either optical,magnetic induction,and acoustic *** communication technologies are already used for communication in the underwater environment;however,lacking localization *** and magnetic induction communication achieves higher data rates for short *** the contrary,acoustic waves provide a low data rate for long-range underwater *** proposed method collectively uses optical,magnetic induction,and acoustic communication-based ranging to estimate the underwater sensor nodes’final ***,we also analyze the proposed scheme by deriving the hybrid Cramer-Rao lower bound(H-CRLB).Simulation results provide a complete comparative analysis of the proposed method with the literature.

关键词： Bayesian multidimensional scaling(BMDS) hybrid Cramer-Rao lower bound(H-CRLB) internet of underwater things(IoUT) signals of opportunity(SOA)approach

来源：评论

学校读者我要写书评

暂无评论

Sustainable Practices in Enhanced Diagnosis and Monitoring of Polycystic Ovary Syndrome (PCOS) using Machine Learning 3

Sustainable Practices in Enhanced Diagnosis and Monitoring o...

引用

3rd Odisha International Conference on Electrical Power engineering, Communication and Computing technology, ODICON 2024

作者： Channabasamma Siri, Dharmapuri Harshitha, MacHa Babu, Kammagani Shobhan Mohammad, Aleem Alkhayyat, Ahmad Computer Science & Engineering Gokaraju Rangaraju Institute of Engineering and Technology Telangana India Gokaraju Rangaraju Institute of Engineering and Technology Telangana India Electronics & Communication Engineering K.G Reddy College of Engineering and Technology Telangana Hyderabad India Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq

ISBN: (纸本)9798350354379

Polycystic Ovary Syndrome (PCOS) is a complex endocrine disorder affecting a significant percentage of women of reproductive age, leading to various metabolic, reproductive, and psychological issues. Despite its prevalence, the diagnosis and monitoring of PCOS remain challenging due to its heterogeneous nature and the multifactorial aspects of its manifestation. This study presents the development and implementation of advanced machine learning techniques aimed at enhancing the diagnosis and monitoring of PCOS, leveraging predictive analytics to improve medical outcomes. Introduced a comprehensive framework that integrates diverse data sources, including clinical, hormonal, and ultrasound data, along with patient lifestyle and genetic information. Advanced machine learning models including Random Forest, Decision Trees, and Logistic Regression were employed and compared to identify the most effective approach for PCOS diagnosis and prognosis. The models were trained, validated, and tested on a large dataset obtained from various healthcare facilities, ensuring a robust and generalizable system. The results demonstrate the potential of machine learning in revolutionizing the management of PCOS. The models achieved high accuracy, sensitivity, and specificity in diagnosing PCOS and predicting associated complications, such as infertility, metabolic syndrome, and cardiovascular risks. Furthermore, the system provides personalized treatment and lifestyle recommendations, contributing to a holistic approach to managing PCOS. © 2024 IEEE.

关键词： Decision Trees Logistic Regression Polycystic Ovary Syndrome Random Forest

来源：评论

学校读者我要写书评

暂无评论

The Impactful Analysis of ML Based technology in Forecasting the Specific Disorders in a Community 4

The Impactful Analysis of ML Based Technology in Forecasting...

引用

4th IEEE International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2024

作者： Khanna, M.Rajesh Sarkar, Rashel Saxena, Arpna Loganayagi, S. Dheidan, Ali Hasan Muhsin, Omar Vel Tech Multi Tech Dr.Rangarajan Dr.Sakunthala Engineering College Department of Information Technology India The Assam Royal Global University Department of Computer Science and Engineering Assam India Ajay Kumar Garg Engineering College Department of Mca Ghaziabad India Department of Computer Science and Engineering Chennai Tamil Nadu Thandalam602105 India National University of Science and Technology College of Technical Engineering Dhi Qar64001 Iraq Al-Farahidi University Baghdad Iraq

ISBN: (纸本)9798350360165

In the healthcare industry, systems increasingly rely on data mining techniques to diagnose and make decisions about diseases. Cardiovascular disease (CVD) prognosis and complication assessment based on risk levels is an area where these approaches have the greatest impact. To this end, fuzzy logic is used to develop an association rule that provides a framework for disease prediction. In addition, the Adaptive Neuro Fuzzy Inference System (ANFIS) is used to quantify the robustness in CVD prediction. In this study, the model was thoroughly tested to investigate the effect of different parameter values on its prediction performance. By adjusting these variables, the scientists sought to maximize the predictive power of the model, assuring its accuracy and reliability in describing heart conditions and the associated complications were examined. The cardiovascular prediction accuracy obtained in this study was remarkably high, reaching 97.39%. This high accuracy indicates the efficiency of the data mining methods used, as well as the robustness of the prediction model developed Such accurate predictions can greatly help healthcare providers to identify individuals who are at risk for heart disease and implement timely interventions to reduce these risks. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

On Consistent and Weak Transitive Neutrosophic Fuzzy Matrices

引用

Neutrosophic Sets and Systems 2025年 79卷 572-598页

作者： Radhika, K. Kavitha, M. Thirumalai, K. Geethanjaliyadav, R. Buvaneswari, N. Kamalakannan, V. Tamilnadu Thanjavur613005 India Department of Mathematics Panimalar Engineering College Tamilnadu Chennai India Department of Mathematics Saveetha Engineering College Tamilnadu Chennai602105 India Department of Mathematics Rajalakshmi institute of Technology Poonamalle Tamilnadu Chennai India Department of Mathematics Siga College of Management and Computer Science Villupuram Affiliated to Annamalai University Tamilnadu Chidambaram India

This paper delves into the properties of two specific types of Neutrosophic Fuzzy Matrices (NFM) namely consistent and weakly transitive NFM. A significant focus is placed on nilpotent and transitive NFM, highlighting their critical role in the analysis. It is demonstrated that these two types of matrices are controllable, and a formula is derived for determining the canonical form of a weakly transitive NFM. To support and clarify the findings, counterexamples are provided throughout the discussion. We introduce an operation on NFM, referred to as the Gödel implication operator. Utilizing this operator, we establish several significant results for NFM, with a particular emphasis on properties related to pre-orders. Our analysis focuses primarily on reflexive and transitive NFM, enabling us to derive meaningful insights. Additionally, we demonstrate a method for constructing an idempotent NFM from any given matrices. © 2025, university of New Mexico. All rights reserved.

关键词： Matrix algebra

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：