检索结果-内蒙古大学图书馆

Informatica (Slovenia) 2025年第5期49卷 37-48页

作者： Remmach, Hassnae Razak, Siti Fatimah Abdul Ullah, Arif Yogarayan, Sumendra Sayeed, Md Shohel Mrhari, Amine Computer Systems Engineering Laboratory Cadi Ayyad University Marrakesh40000 Morocco Faculty of Information Science and Technology Multimedia University Ayer Keroh75450 Malaysia Research in Computer Science Laboratory Faculty of Sciences Ibn Tofail University Kenitra Morocco

In a number of industries, including computer graphics, robotics, and medical imaging, three-dimensional reconstruction is essential. In this research, a CNN-based Multi-output and Multi-Task Regressor with deep learning capabilities is proposed for three-dimensional object reconstruction from 3D point cloud. Our approach is grounded in the original Point Net architecture, which addresses the difficulties associated with convolution when applied to point clouds. Firstly, this paper is modified using a Multi-Output Regressor to accurately recreate Super forms from 3D point clouds. Using this method, we first extract features from the 3D point cloud using Point Net. After that, a Multi-Output Regressor receives these data and uses them to anticipate the Super shape parameters needed to reconstruct the shape. Taking in the data, the Multi-Output Regressor retrieved characteristics from Point Net and simultaneously predicts several outcomes. Second, a Multi-Task Regressor is used to modify the Point Net. The network gains from the capacity to transfer knowledge from one task to another, improving the model's overall performance. The model would forecast the ten parameters needed to create the shape in the case of rebuilding Super shapes. The test findings were better than expected;they are intriguing in terms of prediction accuracy and cost, and they update the result by 80%, which is a good accomplishment for the study. © 2025 Slovene Society Informatika. All rights reserved.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Structural Characteristics of Social Networks and Their Relevance in Community Detection 1st

Comparative Analysis of Structural Characteristics of Social...

引用

1st International Conference on Artificial Intelligence of Things, ICAIoT 2023

作者： Solanki, Shano Kumar, Mukesh Kumar, Rakesh Department of Computer Science and Engineering NITTTR Chandigarh India Department of Computer Science and Engineering UIET Panjab University Chandigarh India Department of Computer Science and Engineering Central University of Haryana Mahendergarh India

ISBN: (纸本)9783031487804

Social Network Analysis based on structural properties is relevant to many application domains including influence maximization, product recommendation, and viral marketing to name a few. The study of structural properties has a vital role in effective community detection and researchers have suggested several algorithms in this direction. The research paper not only gives details of various structural characteristics and their relevance for community detection but it also covers community visualization tools and their useful features. Along with the mapping of structural properties and community detection, efforts have also been made towards understanding the essential community evaluation metrics to know the goodness of communities resulting after applying various algorithms. Network characteristics vary for disjoint and overlapping community detection, so, social network datasets are analyzed to produce different network statistics for a better understanding of their suitability for disjoint and overlapping community detection. The research paper also covers applications of community detection to motivate the researchers for exploring the possibility of using characteristics of social networks for detecting communities for reducing computation time. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Structural properties

来源：评论

学校读者我要写书评

暂无评论

Develop a Framework of a recurring Procedure for Improving Agro Production and Plant Quality by using frameworks 8

Develop a Framework of a recurring Procedure for Improving A...

引用

8th IEEE International Conference on Computing, Communication, Control and Automation, ICCUBEA 2024

作者： Wasankar, S.W. Jawandhiya, P.M. Sipna Coet Department of Computer Science & Engineering Amravati India Plit Department of Computer Science & Engineering Buldhana India

ISBN: (纸本)9798350391770

This study seems to propose an innovative approach to addressing the complexities of agricultural sustainability and productivity. By integrating graph-based Q-learning into two crucial aspects of agriculture - nutrient management and crop quality prediction - it offers a promising solution to optimize resource usage and enhance crop yield and quality. The utilization of Q-learning, a reinforcement learning technique, in constructing Nutrient Action and Quality-Action Graphs is particularly intriguing. These graphs seem to serve as dynamic frameworks for decision-making, allowing the algorithm to adapt and learn optimal strategies based on environmental conditions and crop requirements. The emphasis on tailoring nutrient management strategies to special crop and soil textures while taking environmental conditional factors like temperature and humidity underscores the importance of precision agriculture. This approach has the potential to revolutionize traditional fertilization and plant management practices by offering more tailored and adaptive solutions. Overall, combining of these models into agro decision-making processes holds promise for improving both productivity and sustainability in the face of fluctuating environmental conditions and increasing food demand. © 2024 IEEE.

关键词： Agricultural Productivity NAF Plant Quality Improvement Q-Learning QAF Reinforcement Learning

来源：评论

学校读者我要写书评

暂无评论

Knowledge Navigator - Guiding You Through Your Learning Journey Using AI

Knowledge Navigator - Guiding You Through Your Learning Jour...

引用

2024 International Conference on Computational Intelligence and Computing Applications, ICCICA 2024

作者： Yadav, Anup Lal Talwandi, Navjot Singh Kuhar, Sunny Kumar, Munish Chandigarh University Department Of Computer Science & Engineering Mohali India Piet Department Of Computer Science & Engineering Haryana India

ISBN: (纸本)9798350306446

It might be intimidating to navigate the wide array of learning resources in this era of information overload. This article presents Knowledge Navigator, an artificial intelligence (AI) system that adapts the learning process to the needs, preferences, and learning styles of each individual. Knowledge Navigator evaluates past knowledge, determines learning preferences, and comprehends user intent by combining sophisticated Natural Language Processing (NLP) and machine learning algorithms. Users are guaranteed to receive the most interesting and pertinent learning materials, according to their tastes and goals, thanks to this customized approach. The potential advantages of Knowledge Navigator, such as higher learning efficiency, better information retention, and increased student motivation, are discussed in the paper's conclusion. It also looks at potential research avenues in the future, such as gamification and integration with practical uses. © 2024 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

ROUGE-SciQFS: A ROUGE-based Method to Automatically Create Datasets for Scientific Query-Focused Summarization 31

ROUGE-SciQFS: A ROUGE-based Method to Automatically Create D...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Ramirez-Orta, Juan Milios, Evangelos Maguitman, Ana Soto, Axel J. Faculty of Computer Science Dalhousie University Canada Institute for Computer Science and Engineering UNS - CONICET Department of Computer Science and Engineering Universidad Nacional del Sur Argentina

ISBN: (纸本)9798891761964

So far, the task of Scientific Query-Focused Summarization (Sci-QFS) has lagged in development when compared to other areas of Scientific Natural Language Processing because of the lack of data. In this work, we propose a methodology to take advantage of existing collections of academic papers to obtain large-scale datasets for this task automatically. After applying it to the papers from our reading group, we introduce a novel dataset for Sci-QFS composed of 8,695 examples, each one with a query, the sentences of the full text from a paper and the relevance labels for each. After testing several classical and state-of-the-art embedding models on this data, we found that the task of Sci-QFS is far from being solved, although it is relatively straightforward for humans. Surprisingly, we found that classical methods outperformed modern pre-trained Deep Language Models (sometimes by a large margin), showing the need for large datasets to better fine-tune the latter. We share our experiments, data and models at https://***/jarobyte91/rouge_sciqfs. © 2025 Association for Computational Linguistics.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Morlet wavelet transformation based deep similarity structured neural learning for image quality assessment

引用

Multimedia Tools and Applications 2025年第16期84卷 16789-16807页

作者： Balakrishnan, N. Robinson, Y. Harold Department of MCA Sona College of Technology Salem India Department of Computer Science and Engineering Francis Xavier Engineering College Tirunelveli India

Quality assessment is a key problem to be resolved in image processing. Few research works have been designed to analyze the quality of images using different techniques. However, the accuracy involved during the process of image quality assessment was not sufficient. A novel method Morlet Wavelet Transformation Based Deep Similarity Structured Neural Learning (MWT-DSSNL) is proposed to enhance the performance of image quality assessment with minimal peak signal-to-noise ratio. The MWT-DSSNL Method is based on artificial neural networks with representation learning. The MWT-DSSNL Method initially gets the number of images from a given dataset as input. The MWT-DSSNL Method uses multiple layers to extract higher-level features from the input images. The MWT-DSSNL Method is a Feed-Forward network where each layer employs the output from the previous layer as input. The MWT-DSSNL Method is designed based on a biological neural network of the human brain. Contrary to the existing method, the MWT-DSSNL Method uses multiple hidden layers and Morlet wavelet transformation to deeply analyze input images and thereby extract features such as luminance, contrast, and structure with a minimal amount of time consumption. By considering the discovered features, finally MWT-DSSNL Method determines structural similarity and thereby exactly identifies the quality of input images with a lower time. From that, the MWT-DSSNL Method achieves enhanced image quality assessment performance when compared to existing works. The simulation of the MWT-DSSNL Method is conducted on factors such as PSNR, average processing time, quality detection accuracy, and false positive rate with different numbers of input images. The simulation result depicts that the MWT-DSSNL method increases the accuracy and also minimizes the time of image quality assessment when compared to conventional works. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

Home Automation-Based Health Assessment Along Gesture Recognition via Inertial Sensors

引用

computers, Materials & Continua 2023年第4期75卷 2331-2346页

作者： Hammad Rustam Muhammad Muneeb Suliman A.Alsuhibany Yazeed Yasin Ghadi Tamara Al Shloul Ahmad Jalal Jeongmin Park Department of Computer Science Air UniversityIslamabad44000Pakistan Department of Computer Science College of ComputerQassim UniversityBuraydah51452Saudi Arabia Department of Computer Science and Software Engineering Al Ain UniversityAl Ain15551UAE Department of Humanities and Social Science Al Ain UniversityAl Ain15551UAE Department of Computer Engineering Korea Polytechnic University237 Sangidaehak-ro Siheung-siGyeonggi-do15073Korea

Hand gesture recognition (HGR) is used in a numerous applications,including medical health-care, industrial purpose and sports *** have developed a real-time hand gesture recognition system using inertialsensors for the smart home application. Developing such a model facilitatesthe medical health field (elders or disabled ones). Home automation has alsobeen proven to be a tremendous benefit for the elderly and disabled. Residentsare admitted to smart homes for comfort, luxury, improved quality of life,and protection against intrusion and burglars. This paper proposes a novelsystem that uses principal component analysis, linear discrimination analysisfeature extraction, and random forest as a classifier to *** have achieved an accuracy of 94% over the publicly benchmarked HGRdataset. The proposed system can be used to detect hand gestures in thehealthcare industry as well as in the industrial and educational sectors.

关键词： Genetic algorithm human locomotion activity recognition human–computer interaction human gestures recognition principal hand gestures recognition inertial sensors principal component analysis linear discriminant analysis stochastic neighbor embedding

来源：评论

学校读者我要写书评

暂无评论

Optimised brain tumour detection with the Pteropus Unicinctus optimisation reliant deep model

引用

International Journal of Intelligent Information and Database Systems 2025年第2期17卷 186-216页

作者： Chhabra, Sumit Bansal, Khushboo Desh Bhagat University Punjab Mandi Gobindgarh India Department of Computer Science Khalsa College for Women Amritsar India Department of Computer Science and Engineering Desh Bhagat University Punjab Mandi Gobindgarh India

This research Pteropus Unicinctus optimisation (PUO) is proposed which is mathematically derived from the echolocation character of Pteropusand and the eye power searching ability of Unicinctus. The integration of convolutional neural networks (CNNs) and long short-term memory (LSTM) in the PUO-reliant deep model presents an optimal solution to enhance the precision and dependability of brain tumour detection. This strategy leverages the unique capabilities of both architectures and fine-tunes their performance through hyperparameter optimisation, which leads to better diagnostic results and improved quality of patient care in brain tumour detection. The proposed approach attained the accuracy of 99.51%, 99.58%, and 99.50%, and considering sensitivity 99.48%, 99.60%, 99.37% attained, and the model attained 99.48%, 99.58%, and 99.26% of specificity for BraTS 2019 dataset, SimBRATS 2019 dataset, and brain tumour dataset respectively. Copyright © 2025 Inderscience Enterprises Ltd.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Detection of Quality Deep Fake Images and Videos Using Customised Convolutional Neural Networks 1

Detection of Quality Deep Fake Images and Videos Using Custo...

引用

1st International Conference on Advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Mahar, Alap Verma, Pushpneel Singh, Ajit Bhagwant University Department of Computer Science and Engineering Rajasthan Ajmer305004 India VMSB University Department of Computer Science and Engineering India

ISBN: (纸本)9798331518578

Due to advancements in artificial intelligence there are numerous deep fake images and video collections are available on the Internet and social media. The primary aim of the study is to analyse the deep fake images and videos since the quality is constantly improving a novel method was developed for accurate detection of quality deep fakes. The suggested approach uses a customised convolutional neural network (CNN) technique that uses facial landmark detection to extract structured data from photos and video frames before feeding it into the methods of CNN. The customised CNN model is augment-based CNN for generation of fake images and fake data. Involves about 260 films from the data set in which 202 images are made up while others were real images. About 300 videos are used in which 250 videos are fake and 50 were real the proposed model achieved the accuracy of 95.58% and 0.97 AUC score that outperforms the existing models like MLP-CNN and CNN. Additionally, the method succeeds with greater accuracy then the conventional models like DST -Net, VGG 16 Efficient Net. This research study's primary goal is to create a new CNN learning method for identifying high-quality deep fake photos and videos. © 2025 IEEE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Adaptation of Federated Explainable Artificial Intelligence for Efficient and Secure E-Healthcare Systems

引用

computers, Materials & Continua 2024年第3期78卷 3413-3429页

作者： Rabia Abid Muhammad Rizwan Abdulatif Alabdulatif Abdullah Alnajim Meznah Alamro Mourade Azrour Department of Computer Science Kinnaird College for WomenLahorePakistan College of Science and Engineering University of DerbyDerbyDE221GBUK Department of Computer Science College of ComputerQassim UniversityBuraydah51452Saudi Arabia Department of Information Technology College of ComputerQassim UniversityBuraydah51452Saudi Arabia Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh84428Saudi Arabia STI Laboratory IDMS TeamFaculty of Sciences and TechniquesMoulay Ismail University of MeknèsMeknesMorocco

Explainable Artificial Intelligence(XAI)has an advanced feature to enhance the decision-making feature and improve the rule-based technique by using more advanced Machine Learning(ML)and Deep Learning(DL)based *** this paper,we chose e-healthcare systems for efficient decision-making and data classification,especially in data security,data handling,diagnostics,laboratories,and *** Machine Learning(FML)is a new and advanced technology that helps to maintain privacy for Personal Health Records(PHR)and handle a large amount of medical data *** this context,XAI,along with FML,increases efficiency and improves the security of e-healthcare *** experiments show efficient system performance by implementing a federated averaging algorithm on an open-source Federated Learning(FL)*** experimental evaluation demonstrates the accuracy rate by taking epochs size 5,batch size 16,and the number of clients 5,which shows a higher accuracy rate(19,104).We conclude the paper by discussing the existing gaps and future work in an e-healthcare system.

关键词： Artificial intelligence data privacy federated machine learning healthcare system security

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：