检索结果-内蒙古大学图书馆

Differentiable Deformation Graph-Based Neural Non-rigid Registration

Communications in Mathematics and Statistics 2023年第1期11卷 151-167页

作者： Wanquan Feng Hongrui Cai Junhui Hou Bailin Deng Juyong Zhang School of Mathematical Sciences University of Science and Technology of ChinaHefei 230026People’s Republic of China School of Data Science University of Science and Technology of ChinaHefei 230026People’s Republic of China Department of Computer Science City University of Hong KongHong KongPeople’s Republic of China School of Computer Science and Informatics Cardiff UniversityCardiffUK

The traditional pipeline for non-rigid registration is to iteratively update the correspondence and alignment such that the transformed source surface aligns well with the target *** the pipeline,the correspondence construction and iterative manner are key to the results,while existing strategies might result in local *** this paper,we adopt the widely used deformation graph-based representation,while replacing some key modules with neural learning-based ***,we design a neural network to predict the correspondence and its reliability confidence rather than the strategies like nearest neighbor search and pair ***,we adopt the GRU-based recurrent network for iterative refinement,which is more robust than the traditional *** model is trained in a self-supervised manner and thus can be used for arbitrary datasets without *** experiments demonstrate that our proposed method outperforms the state-of-the-art methods by a large margin.

关键词： Differentiable deformation graph Non-rigid registration

来源：评论

学校读者我要写书评

暂无评论

Enhancing wireless sensing via a target-mounted intelligent reflecting surface

引用

National science Review 2023年第8期10卷 13-14页

作者： Xiaodan Shao Rui Zhang School of Science and Engineering Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Department of Electrical and Computer Engineering National University of Singapore

An intelligent reflecting surface(IRS),or its various equivalents such as an reconfigurable intelligent surface(RIS), is an emerging technology to control radio signal propagation in wireless systems. An IRS is a digitally controlled metasurface consisting of a large number of passive reflecting elements, which are connected to a smart controller to enable dynamic adjustments of the amplitude and/or phase of the incident signal on each element independently [1].

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cloud Computing Network in Remote Sensing-Based Climate Detection Using Machine Learning Algorithms

引用

Remote Sensing in Earth Systems sciences 2025年第2期8卷 400-408页

作者： Srinivas, Jhade Raju, Ch VV Narasimha Sasikala, C. Bhaskar, Parumanchala Panyala, Amarendra Reddy Priya, Divya Department of Computer Science and Engineering - Data Science K G Reddy College of Engineering and Technology Moinabad Telangana Hyderabad India Information Technology Marri Laxman Reddy Institute of Technology and Management Dundigal Telangana Hyderabad 500043 India Dept of CSE Srinivasa Ramanujan Institute of Technology (Autonomous) Andhra Pradesh Ananthapuramu India Department of Computer Science and Engineering Santhiram Engineering College Nandyal India Department of Computer Science and Engineering (Data Science) Malla Reddy University Telangana Hyderabad India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

Effective monitoring of the environment over a large area will require mobilization of a considerable amount of information. Otherwise, the use of traditional methods will prove to be costly and would take up so much time. Also, assessing the land cover changes between two times is one of the other methods which can be adopted to measure the environmental sustainability. Using ML techniques for predictive modeling in remote sensing has emerged as a useful approach in solving some of the environmental and climatic challenges. This research proposes a novel method in remote sensing image-based climate detection utilizing cloud computing and machine learning algorithms. Here, the cloud computing module is used in the collection of remote sensing images for the detection of climate changes. Then, the collected image is processed for noise removal as well as normalization. The processed image is segmented, and features are extracted utilizing a fuzzy K-clustering-based contour Gaussian model with graph cut Boltzmann CNN. Experimental analysis is carried out for various remote sensing-based climate change datasets in terms of training accuracy, random precision, AUC, recall, and F-measure. The proposed technique obtained 97% of training accuracy, 95% of random precision, 96% of recall, 93% of AUC, and 94% of F-measure. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Climate detection Cloud computing Contour Gaussian model Machine learning algorithms Remote sensing images

来源：评论

学校读者我要写书评

暂无评论

AI Based Criminal Detection and Recognition System for Public Safety and Security using novel CriminalNet-228 4th

AI Based Criminal Detection and Recognition System for Publi...

引用

4th International Conference on Frontiers in Computing and Systems, COMSYS 2023

作者： Murthy, Jamuna S. Siddesh, G.M. Department of Computer Science and Engineering Ramiah Institute of Technology Bengaluru India Department of Artificial Intelligence and Data Science Ramiah Institute of Technology Bengaluru India

ISBN: (纸本)9789819726103

The recent surge in public space criminal activities underscores the need for an efficient system to promptly detect, recognize, and track criminals. Existing AI-based criminal detection literature, while insightful, has limitations such as the complexity to analyze video data, time, and speed of accuracy when it comes to training the algorithms that call for further advancements. Hence proposed AI-driven system addresses this demand, aiming to automate criminal identification, equipping law enforcement with a potent tool for proactive crime prevention and resolution. The system utilizes the innovative "CriminalNet-228" Convolutional Neural Network (CNN) architecture, meticulously trained on a vast criminal image dataset for enhanced detection accuracy. To bolster face detection, additional computational resources like parallel processing and distributed computing are employed, enabling real-time analysis of extensive CCTV footage. Notably, the system tracks identified criminals, providing law enforcement with real-time situational awareness. CriminalNet-228 achieves an impressive overall Mean Average Precision (mAP) of 0.65 and excels in detecting facial features as small as 4 × 4 pixels, demonstrating its detail-oriented recognition capabilities. When evaluating Proposed CriminalNet-228 in comparison to established state-of-the-art techniques like Fast-RCNN, Yolov7, and AlexNet, it surpassed them in terms of precision, recall, f-measure, and accuracy, achieving an impressive accuracy rate of 99.2%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Real-Time computer Vision-Based Green Intensity Estimation Method for the Arecanut Tree Pesticide Spraying System

A Real-Time Computer Vision-Based Green Intensity Estimation...

引用

International Conference on VLSI, Signal Processing, Power Electronics, IoT, Communication and Embedded Systems, VSPICE 2023

作者： Nagaraja Hebbar, N. Sandeep, Bhat Artificial Intelligence and Data Science Department Srinivas Institute of Technology Mangaluru India Computer Science and Engineering Department Srinivas Institute of Technology Mangaluru India

ISBN: (纸本)9789819746569

In India, one of the commercial crops is arecanut. The majority of arecanut growers depend on the arecanut production. However, they are also having a great deal of difficulty finding skilled workers to do pesticide spraying jobs. This effort uses computer vision technologies to address the aforementioned problem. This work compares the HSV estimation with the green pixel estimate approach. This makes it easier to position the robot at the right height, where the pesticide spray will work best. In this case, the HSV estimation identified a better way to manage the robot’s motion. Using a wireless camera, the experimental setup achieves an incredibly innovative performance to capture an image of the arecanut crop. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Framework for Automatic Sarcasm Detection Using Proposed Tensor-DNN-50 Algorithm 4th

A Real-Time Framework for Automatic Sarcasm Detection Using ...

引用

4th International Conference on Frontiers in Computing and Systems, COMSYS 2023

作者： Murthy, Jamuna S. Siddesh, G.M. Department of Computer Science and Engineering Ramaiah Institute of Technology Bengaluru India Department of Artificial Intelligence and Data Science Ramaiah Institute of Technology Bengaluru India

ISBN: (纸本)9789819726103

Social media platforms such as Twitter, Facebook, and Instagram are vast repositories of trending global news. They generate an enormous amount of data, offering a valuable resource for both academic researchers and IT marketing teams. These data can be harnessed for various insights and applications. A prominent and pressing research area within this data is the detection of sarcasm and fake news. The internet is rife with misleading and false information, often causing widespread confusion. Current research primarily categorizes news as either real or fake, using machine learning algorithms. However, this binary approach struggles with news that is partially true yet contains elements that could be deemed fake. To address this issue, our work introduces a real-time framework for sarcasm detection, utilizing an innovative deep learning technique called Tensor-DNN-50 for multiclass classification. The TDNN-50 model not only classifies news articles based on authenticity but also quantifies the level of sarcasm within them. Comparative analysis against leading techniques like SVM, att-RNN, and EANN demonstrates the superiority of our proposed algorithm. It achieves an impressive accuracy of 96.4% for two-class classification, 94.32% for four-class classification, and an astonishing 99.1% for seven-class classification. These results underscore the potential of our Tensor-DNN-50 Model in effectively addressing the intricate challenges of sarcasm detection and news classification with unparalleled accuracy across multiple classes. © 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

An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Language Model Inference

An Empirical Study on Cross-lingual Vocabulary Adaptation fo...

引用

2024 Findings of the Association for Computational Linguistics, EMNLP 2024

作者： Yamaguchi, Atsuki Villavicencio, Aline Aletras, Nikolaos School of Computer Science University of Sheffield United Kingdom Department of Computer Science Institute of Data Science and Artificial Intelligence University of Exeter United Kingdom The Alan Turing Institute United Kingdom

ISBN: (纸本)9798891761681

The development of state-of-the-art generative large language models (LLMs) disproportionately relies on English-centric tokenizers, vocabulary and pre-training data. Despite the fact that some LLMs have multilingual capabilities, recent studies have shown that their inference efficiency deteriorates when generating text in languages other than English. This results in increased inference time and costs. Cross-lingual vocabulary adaptation (CVA) methods have been proposed for adapting models to a target language aiming to improve downstream performance. However, the effectiveness of these methods on increasing inference efficiency of generative LLMs has yet to be explored. In this paper, we perform an empirical study of five CVA methods on four generative LLMs (including monolingual and multilingual models) across four typologically-diverse languages and four natural language understanding tasks. We find that CVA substantially contributes to LLM inference speedups of up to 271.5%. We also show that adapting LLMs that have been pre-trained on more balanced multilingual data results in downstream performance comparable to the original models. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Support Vector Machine (SVM) on Challenging datasets for Forest Fire Detection

arXiv

引用

arXiv 2024年

作者： Kar, Ankan Nath, Nirjhar Kemprai, Utpalraj Aman Department of Computer Science Chennai Mathematical Institute India Department of Mathematics and Computer Science Chennai Mathematical Institute India Department of Data Science Chennai Mathematical Institute India

This article delves into the analysis of performance and utilization of Support Vector Machines (SVMs) for the critical task of forest fire detection using image datasets. With the increasing threat of forest fires to ecosystems and human settlements, the need for rapid and accurate detection systems is of utmost importance. SVMs, renowned for their strong classification capabilities, exhibit proficiency in recognizing patterns associated with fire within images. By training on labeled data, SVMs acquire the ability to identify distinctive attributes associated with fire, such as flames, smoke, or alterations in the visual characteristics of the forest area. The document thoroughly examines the use of SVMs, covering crucial elements like data preprocessing, feature extraction, and model training. It rigorously evaluates parameters such as accuracy, efficiency, and practical applicability. The knowledge gained from this study aids in the development of efficient forest fire detection systems, enabling prompt responses and improving disaster management. Moreover, the correlation between SVM accuracy and the difficulties presented by high-dimensional datasets is carefully investigated, demonstrated through a revealing case study. The relationship between accuracy scores and the different resolutions used for resizing the training datasets has also been discussed in this article. These comprehensive studies result in a definitive overview of the difficulties faced and the potential sectors requiring further improvement and focus. © 2024, CC BY.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A comparative analysis for deep-learning-based approaches for image forgery detection

International Journal of Systematic Innovation

引用

International Journal of Systematic Innovation 2024年第1期8卷 1-10页

作者： Ch, Ravikumar Radha, Marepalli Mahendar, Maragoni Manasa, Pinnapureddy Department of Artificial Intelligence &Data Science Chaitanya Bharathi Institute of Technology Hyderabad 500075 India Department of Computer Science and Engineering CVR College of Engineering Hyderabad 501510 India Department of Computer Science and Engineering Neil Gogte Institute of Technology Hyderabad 500039 India

The detection of counterfeit photographs is critical in the digital age because of the widespread development of digital media and its significant impact on social networks. The legitimacy of digital content is being threatened by the growing sophistication of picture counterfeiting. With the help of pre-trained VGG-16 models and deep learning techniques that integrate Error Level Analysis (ELA) and Convolutional Neural Networks (CNNs), this study presents a fresh solution to this problem. The study thoroughly assesses and contrasts these models with a dataset that has been carefully chosen to bring the presented findings into perspective. To ensure a reliable evaluation of each model's performance 5000 experiments were carried out in total. With an accuracy rate of 99.87% and an accurate identification rate of 99% of hidden forgeries, the results demonstrate the exceptional effectiveness of the ELA-CNN model. However, despite its robustness, the VGG-16 model only achieves a significantly lower accuracy rate of 97.93% and a validation rate of 75.87%. This study clarifies the relevance of deep learning in the identification of image forgeries and highlights the practical ramifications of various models. Moreover, the research recognizes its constraints, especially for highly advanced counterfeits, and proposes possible paths for enhancing the accuracy and scope of detection algorithms. In the ever-changing world of digital media, the thorough comparative analysis provided in this study offers insightful information that can direct the creation of accurate forgery detection tools, protecting digital content integrity and reducing the effects of image manipulation. © (2023), (Society of Sytematic Innovation). All Rights Reserved.

关键词： Counterfeit images deep learning ELA-CNN Image forgery detection VGG-16 model

来源：评论

学校读者我要写书评

暂无评论

QuMIN: quantum multi-modal data fusion for humor detection

引用

Multimedia Tools and Applications 2025年第18期84卷 18855-18872页

作者： Phukan, Arpan Haq Khan, Anas Anwarul Ekbal, Asif Department of Computer Science and Engineering Indian Institute of Technology Patna Bihta Bihar Patna801106 India Kalinga Institute of Industrial Technology Odisha Bhubaneswar751024 India School of AI and Data Science Indian Institute of Technology Jodhpur Rajasthan Jodhpur342030 India

Humour detection has attracted considerable attention due to its significance in interpreting dialogues across text, visual, and acoustic modalities. However, effective methods to map correlations among different modalities remain an active area of research. In this study, we go beyond traditional machine learning techniques by introducing a Variational Quantum Circuit (VQC) that capitalizes on the inherent quantum properties of superposition, entanglement, and interference. Our proposed model, Quantum Multi-Modal data Fusion (QuMIN), is designed to better capture and reproduce the interaction across modalities, as well as the internal correlations within each modality. Our introduction of the novel VQC, which augments the DialogueRNN baseline with only an additional 4,809 parameters, signifies a substantial advancement in multi-modal humor detection with improvements of 12.34% in precision, 8.84% in recall and 10.57% in F1 score compared to the state-of-the-art methods. © 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

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：