检索结果-内蒙古大学图书馆

Noise4Denoise:Leveraging noise for unsupervised point cloud denoising

Computational Visual Media 2024年第4期10卷 659-669页

作者： Weijia Wang Xiao Liu Hailing Zhou Lei Wei Zhigang Deng Manzur Murshed Xuequan Lu Deakin University GeelongVIC 3216Australia Department of Mechanical Engineering and Product Design Engineering Swinburne University of TechnologyMelbourneVIC 3122Australia Department of Computer Science University of HoustonHoustonTX 77204-3027USA Department of Computer Science and Information Technology La Trobe UniversityMelbourneVIC 3086Australia

Existing deep learning-based point cloud denoising methods are generally trained in a supervised manner that requires clean data as ground-truth ***,in practice,it is not always feasible to obtain clean point *** this paper,we introduce a novel unsupervised point cloud denoising method that eliminates the need to use clean point clouds as groundtruth labels during *** demonstrate that it is feasible for neural networks to only take noisy point clouds as input,and learn to approximate and restore their clean *** particular,we generate two noise levels for the original point clouds,requiring the second noise level to be twice the amount of the first noise *** this,we can deduce the relationship between the displacement information that recovers the clean surfaces across the two levels of noise,and thus learn the displacement of each noisy point in order to recover the corresponding clean *** experiments demonstrate that our method achieves outstanding denoising results across various datasets with synthetic and real-world noise,obtaining better performance than previous unsupervised methods and competitive performance to current supervised methods.

关键词： point clouds denoising geometry processing deep learning

来源：评论

学校读者我要写书评

暂无评论

AVirtual Cloud Storage Architecture for Enhanced Data Security

引用

computer Systems Science & engineering 2023年第2期44卷 1735-1747页

作者： M.Antony Joans Kumar C.Christopher Columbus E.Ben George T.Ajith Bosco Raj Department of Information Technology St.Xavier’s Catholic College of EngineeringNagercoil629003Tamil NaduIndia Department of Computer Science Engineering PSN College of Engineering and TechnologyTirunelveli627152India Department of Computer Science Engineering University of Technology and Applied SciencesMuscat112Oman Department of Electronics and Communications Engineering PSN College of Engineering and TechnologyTirunelveli627152India

The sensitive data stored in the public cloud by privileged users,such as corporate companies and government agencies are highly vulnerable in the hands of cloud providers and *** proposed Virtual Cloud Storage Archi-tecture is primarily concerned with data integrity and conﬁdentiality,as well as *** provide conﬁdentiality and availability,theﬁle to be stored in cloud storage should be encrypted using an auto-generated key and then encoded into distinct *** the encoded chunks ensured theﬁle integrity,and a newly proposed Circular Shift Chunk Allocation technique was used to determine the order of chunk ***ﬁle could be retrieved by performing the opera-tions in *** the regenerating code,the model could regenerate the missing and corrupted chunks from the *** proposed architecture adds an extra layer of security while maintaining a reasonable response time and sto-rage *** results analysis show that the proposed model has been tested with storage space and response time for storage and *** VCSA model consumes 1.5x(150%)storage *** was found that total storage required for the VCSA model is very low when compared with 2x Replication and completely satisﬁes the CIA *** response time VCSA model was tested with different sizedﬁles starting from 2 to 16 *** response time for storing and retrieving a 2 MBﬁle is 4.96 and 3.77 s respectively,and for a 16 MBﬁle,the response times are 11.06 s for storage and 5.6 s for retrieval.

关键词： Erasure code regenerating code cryptography virtual cloud storage architecture circular shift chunk allocation algorithm

来源：评论

学校读者我要写书评

暂无评论

EPDTNet + -EM: Advanced Transfer Learning and SubNet Architecture for Medical Image Diagnosis

引用

Cognitive Computation 2025年第2期17卷 1-22页

作者： K, Dhivya K, Sangamithrai S, Indra Priyadharshini M, Vedaraj Department of Electronics and Communication Engineering SRM Institute of Science and Technology Tamilnadu Kattankulathur India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R & d Institute of Science and Technology Tamilnadu Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai India Department of Computer Science and Engineering R.M.D. Engineering College RSM Nagar Tamilnadu Kavaraipettai Thiruvallur601206 India

This paper presents a novel medical imaging framework, Efficient Parallel Deep Transfer SubNet+-based Explainable Model (EPDTNet + -EM), designed to improve the detection and classification of abnormalities in medical images. The model integrates Enhanced Exponential Transfer Learning (En-ETL) and the Parallel SubNet (PSNet +) architecture, addressing challenges like overfitting, high computational cost, and limited generalization across complex datasets. En-ETL accelerates learning and enhances precision, while PSNet + balances computational efficiency and performance through parallel convolutional layers and an axis attention mechanism. The proposed framework preprocesses medical images using resizing, noise removal, and contrast enhancement, ensuring high-quality inputs for analysis. For classification, the PSNet + model categorizes medical images into normal and abnormal cases. Explainable AI (XAI) is applied to highlight key features in classified images, improving interpretability and clinical decision-making. Experimental results validate the framework on various datasets, including MRI, CT, X-ray, and mammography images. The proposed model achieves a classification accuracy of 98.83%, a false positive rate of 2%, and an execution time of 5.3 ms. Comparative Analysis show superior performance over existing approaches in classification accuracy and efficiency. Ablation studies confirmed the significant contributions of the proposed model using each component in enhancing performance. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent surveillance support system

引用

Discover Internet of Things 2023年第1期3卷 9页

作者： Saketh, Meduri Nandal, Neha Tanwar, Rohit Reddy, B. Pradyun Department of Computer Science Engineering Gokaraju Rangaraju Institute of Engineering and Technology Hyderabad India Geethanjali College of Engineering and Technology Hyderabad India School of Computer Science University of Petroleum and Energy Studies Dehradun India Department of Computer Science Engineering Sreenidhi Institute of Engineering and Technology Hyderabad India

The Intelligent Surveillance Support System(ISSS) is an innovative software solution that enables real-time monitoring and analysis of security footage to detect and identify potential threats. This system incorporates advanced features such as face recognition, alarm on theft detection, visitors in/out detection and motion detection, to provide a comprehensive and reliable security solution. The implementation of this software aims to improve the efficiency of surveillance systems, thereby enhancing the safety and security of public and private spaces. The focus of this study is on performing the aforementioned tasks in real time while utilizing enhanced algorithms from the OpenCV Library, such as LBPH and Haar Cascading, which enhance the use of machine perception and help us produce outcomes with an accuracy of about 95% after multiple runs. With the rapid advancements in technology and the increasing need for surveillance in today’s world, the Intelligent Surveillance Support System holds immense potential in the field of security and surveillance. © The Author(s) 2023.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Advances, Application and Challenges of Lithography Techniques 5

Advances, Application and Challenges of Lithography Techniqu...

引用

5th International Conference on Advancements in Computational Sciences, ICACS 2024

作者： Raza, Ali Saeed, Zubair Aslam, Adnan Nizami, Syeda Mehwish Habib, Kanwal Malik, Ahmad Nazir National University of Technology Department of Computer Engineering Islamabad Pakistan University of Engineering and Technology Department of Computer Engineering Taxila Pakistan University of Engineering and Technology Department of Electronic Engineering Taxila Pakistan University of Engineering and Technology Department of Electrical Engineering Taxila Pakistan Hitec University Department of Computer Engineering Taxila Pakistan

ISBN: (纸本)9798350394764

Miniaturization of the transistor has resulted in novel patterning techniques to come into account. To alleviate the resolution limits of photolithography, various promising techniques have been developed with high resolution, throughput, overlay accuracy, low line edge roughness, and low defectivity. This paper reviews major nanolithography techniques including conventional photolithography, Extreme ultraviolet lithography, Nanoimprint lithography, and additional techniques. All these lithographic methods are key technologies to manufacture ICs, microchips, and MEMS (micro-electromechanical system) devices. This paper also presents various challenges, status, and applications of NGL (next-generation lithography). In the end, a comparative analysis of these techniques is also discussed. © 2024 IEEE.

关键词： MEMS

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Combination of Machine Learning Approaches for Groundwater Fluctuations Prediction

引用

Iranian Journal of Science and technology - Transactions of Civil engineering 2025年 1-15页

作者： Rezapour, Abbasali Sabzekar, Mostafa Department of Civil Engineering Birjand University of Technology Birjand Iran Department of Computer Engineering Birjand University of Technology Birjand Iran

Accurate prediction of groundwater levels (GWL) is crucial for effective resource management and addressing challenges such as water scarcity and aquifer sustainability. This study aims to develop and evaluate a novel ensemble framework that integrates multiple machine learning (ML) models, including support vector regression (SVR), adaptive neuro-fuzzy inference systems (ANFIS), and long short-term memory (LSTM) networks, for robust GWL fluctuation prediction. The primary objectives are to (1) leverage the complementary strengths of these diverse ML techniques, (2) optimize their contributions through particle swarm optimization (PSO), and (3) validate the framework's performance across multiple regions in the Birjand watershed, Iran. The proposed method combines the time-series analysis capabilities of LSTM, the generalization power of SVR, and the non-linear mapping ability of ANFIS, achieving superior prediction accuracy. By employing PSO for dynamic weighting, the ensemble dynamically emphasizes the most effective models, resulting in statistically significant improvements over individual methods for metrics such as RMSE, MAE, and the inequality coefficient. Applied to four zones, the framework demonstrates consistent outperformance, with the best results achieved when considering GWL data from two prior months. The ensemble approach not only enhances prediction reliability but also addresses limitations in isolated modeling approaches, offering a scalable and adaptive solution for sustainable groundwater management. © The Author(s), under exclusive licence to Shiraz University 2025.

关键词： ANFIS model Groundwater fluctuations LSTM networks Machine learning Particle swarm optimization Support vector regression

来源：评论

学校读者我要写书评

暂无评论

Forecasting Maternal Women's Health Risks using Random Forest Classifier 7

Forecasting Maternal Women's Health Risks using Random Fores...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Thakkar, Dhruvi Gandhi, Vaibhav C. Trivedi, Dhriti Faculty of Engineering & Technology Computer Science & Engineering Department Vadodara India Computer Engineering Department Anand India Computer Engineering Department Vadodara India

ISBN: (纸本)9798350359299

Nowadays, maternal health during pregnancy is a major concern, especially in rural areas where risks are increased by a lack of medical experts and poor infrastructure. The lack of effective methods for predicting maternal health risks poses a significant challenge in maternal healthcare. Traditional approaches often fall short of accurately identifying and managing complications during pregnancy, leading to adverse outcomes. To overcome, this new technique can accurately assess medical data in order to forecast threats to maternal health. This research investigates machine learning algorithms' potential in predicting such risks using medical data. The study utilizes a carefully curated dataset called the Maternal Health Risk Dataset, encompassing parameters like age, blood pressure, glucose levels, body temperature, heart rate, and risk level. Through ensemble learning-based feature engineering, algorithms like Random Forest, XG Boost, Support Vector Classifier (SVC), Decision Tree, and Logistic Multiclass are assessed. Results show Random Forest achieving an impressive accuracy of 94.26%, indicating its potential in maternal health risk prediction, crucial for minimizing adverse outcomes and enabling timely interventions during pregnancy. © 2024 IEEE.

关键词： Health risks

来源：评论

学校读者我要写书评

暂无评论

Optimized Visual Recognition Through a Deep Convolutional Neural Network With Hierarchical Modular Organization

引用

IEEE Access 2024年 12卷 95517-95528页

作者： Clinton Sitepu, Ade Liu, Chuan-Ming National Taipei University of Technology College of Electrical Engineering and Computer Science Taipei10608 Taiwan National Taipei University of Technology Department of Computer Science and Information Engineering Taipei10608 Taiwan

Artificial Intelligence, including machine learning and deep convolutional neural networks (DCNNs), relies on complex algorithms and neural networks to process and analyze data. DCNNs for visual recognition often require access to high-performance hardware, such as GPUs and cloud-based computing resources, to perform tasks efficiently. Visual recognition requires DCNNs with numerous layers. Fully connected layers in DCNNs are often the most computationally intensive. These layers connect every neuron in one layer to every neuron in the next layer, resulting in a large number of parameters to compute. To mitigate redundancy and make DCNNs more efficient, this article implements and demonstrates the concept to identifying and removing redundant or low-impact connections from fully connected layers using convolution neural network with hierarchical modular organization. The modularity of the DCNNs is built based on the cluster hierarchy of the similar image. These clusters are created based on a novel similarity metric, which measures how closely related images are to each other. The architecture uses multiple smaller DCNNs, referred to as modules, designed to progressively classify images into super clusters according to their similarity. Experimental results using popular image datasets show that the proposed DCNNs model to optimized number of operations by 49% to 99% and keeps its performance comparable. © 2024 The Authors.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Towards robust and efficient intrusion detection in IoMT: a deep learning approach addressing data leakage and enhancing model generalizability

引用

Multimedia Tools and Applications 2024年 1-20页

作者： Bouke, Mohamed Aly El Atigh, Hayate Abdullah, Azizol Department of Communication Technology and Network Faculty of Computer Science and Information Technology Universiti Putra Malaysia Serdang43400 Malaysia Departement of Computer Engineering Faculty of Computer Engineering Bandirma Onyedi Eylul University Balikesir10200 Turkey

The Internet of Medical Things (IoMT) brings advanced patient monitoring and predictive analytics to healthcare but also raises cybersecurity and data privacy issues. This paper introduces a deep-learning model for IoMT intrusion detection, utilizing the WUSTL EHMS 2020 dataset, which focuses on cyber threats like man-in-the-middle attacks and data injection. Our sequential model, trained with TensorFlow, surpasses traditional predictive accuracy and efficiency methods. It achieves 99% accuracy with reduced loss and excels in precision, recall, F1 Score, and ROC AUC. The model uses 25 key features from 45, preventing overfitting and addressing data leakage in preprocessing. These steps ensure the model's reliability for IoMT cybersecurity, demonstrating its effectiveness in real-world scenarios. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Mining user's navigation structure by filtering impurity nodes for generating relevant predictions

引用

International Journal of Cognitive Computing in engineering 2023年第1期4卷 248-258页

作者： Jindal, Honey Sardana, Neetu Vidyarthi, Ankit Gupta, Deepak Mahmud, Mufti Department of Computer Science & Engineering and Information Technology Jaypee Institute of Information Technology Noida India Department of Computer Science and Engineering Maharaja Agrasen Institute of Technology Delhi India United Kingdom

Web Navigation Prediction (WNP) has been popularly used for finding future probable web pages. Obtaining relevant information from a large web is challenging, as its size is growing with every second. Web data may contain irrelevant noise, and thus cleaning such data is essential. In this paper, we emphasize the identification and elimination of noisy information from user-navigated web pages. The pruning of user browsed sessions by removing noisy webpages and their relations can help in the development of high-performing prediction models with fewer prediction errors. To minimize the prediction errors, we have proposed four pruning models namely PM3ER, PM3EN, PM3GI, and PM3EP which remove noisy web pages and their relations from the model consisting of varied simple and complex navigations. The study reveals that PM3ER is effective in prediction for websites with complicated structures resulting in complex navigations, and PM3EN is effective in predicting websites with a simple tree-like structure resulting in simple navigations. PM3ER has shown an improvement in predictions by up to 3% whereas PM3EN has attained improvement up to 5.45%. © 2023

关键词： Forecasting

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：