检索结果-内蒙古大学图书馆

Temporally consistent video colorization with deep feature propagation and self-regularization learning

Computational Visual Media 2024年第2期10卷 375-395页

作者： Yihao Liu Hengyuan Zhao Kelvin CKChan Xintao Wang Chen Change Loy Yu Qiao Chao Dong Shenzhen Institute of Advanced Technology Chinese Academy of SciencesShenzhen 518055China University of Chinese Academy of Sciences Beijing 100049China Department of Electrical&Computer Engineering Nanyang Technological University50 Nanyang AvenueSingapore 639798 Applied Research Center Tencent PCGShenzhenChina

Video colorization is a challenging and highly ill-posed *** recent years have witnessed remarkable progress in single image colorization,there is relatively less research effort on video colorization,and existing methods always suffer from severe flickering artifacts(temporal inconsistency)or unsatisfactory *** address this problem from a new perspective,by jointly considering colorization and temporal consistency in a unified ***,we propose a novel temporally consistent video colorization(TCVC)*** effectively propagates frame-level deep features in a bidirectional way to enhance the temporal consistency of ***,TCVC introduces a self-regularization learning(SRL)scheme to minimize the differences in predictions obtained using different time *** does not require any ground-truth color videos for training and can further improve temporal *** demonstrate that our method can not only provide visually pleasing colorized video,but also with clearly better temporal consistency than state-of-the-art methods.A video demo is provided at https://***/watch?v=c7dczMs-olE,while code is available at https://***/lyh-18/TCVC-Tem porally-Consistent-Video-Colorization.

关键词： video colorization temporal consistency feature propagation self-regularization

来源：评论

学校读者我要写书评

暂无评论

Guardians of Truth: Exploring Techniques for Veracity Identification in social media during an Infodemic 3

Guardians of Truth: Exploring Techniques for Veracity Identi...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Suthanthiradevi, P. Revathy, G. Sathish Kumar, P. Karthikeyan, B. Muthu, Lakshmi.V SRM institute of Science and Technology Data Science and Business Systems School of Computing India Vels Institute of science Technology and Advanced studies Department of Computer science and engineering India Rajalakshmi institute of technology Computer and Communication Engineering India SASTRA Deemed University School of Computing India St. Joseph's Institute of Technology Department of Computer Science and Engineering India

ISBN: (纸本)9798350372120

With the recent advent of technology, social networks are accessible 24/7 using mobile devices. During covid-19 pandemic the propagation of misinformation are mostly related to the disease, its cures and prevention. With Twitter as the medium this information was spreaded to millions of people who lack domain specific knowledge. This can lead to bloster fear and direct damage to the people. This research focuses on identifying the veracity of the Twitter posts behind pandemic situation. The authors have proposed a Transformer Model using Bat Algorithm for identifying the fake news. This model is trained and evaluated using infodemic metadata. Our experimental results shows by which proposed model accurately detected the fake news and achieved 96.5% of f1-score. © 2024 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

A Music Recommender System to Identify the Emotional State of a Person Using Machine Learning Algorithms 4

A Music Recommender System to Identify the Emotional State o...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Muruganantham, A. Malarvizhi, C. Divya Vahini, S. Saranya, D. Uthiramoorthy, A. Karnataka Bengaluru India Psg Institute of Advanced Studies Department of Computer Science Coimbatore India Dr.Mahalingam College of Engineering and Technology Department of Computer Applications Tamil Nadu Pollachi India Sri Eshwar College of Engineering Department of Information Technology Coimbatore India Rathinam College of Arts and Science Department of Computer Science India

ISBN: (纸本)9798331523923

In today's digital world, customized recommendation algorithms can improve user experiences in many different areas. Within the sphere of intelligent human-technology interaction, this paper specifically examines a music recommender system driven by machine learning algorithms. It figures out what mood users are in and can provide an appropriate response in real time. The system being propounded in this essay uses advanced technology in facial expression recognition. With the help of a webcam, it aims to accurately detect user emotions, including joy, sadness, and anger. Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN) and Support Vector Machines (SVM) have been employed to effectively classify people's mood and recommend an appropriate song. Our extensive tests and examinations show that CNN, RNN, and SVM models are all very good at guessing users' moods - with high precision, recall, F1-score, and accuracy percentages. Furthermore, in-depth analyses like confusion matrixes illuminate how well each model serves as an emotion recognizer. This study's findings are representative of future prospects in affective computing around the globe with major implications for intelligent recommendation systems to which it's important that the models are sensitive. In conclusion, the suggested Music Recommender System is something new for taking a more personal view: We can be as deeply entertained as the web allows us to be - make tailored entertainment paths in the digital era. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Rock / Mine Classification Using Supervised Machine Learning Algorithms

Rock / Mine Classification Using Supervised Machine Learning...

引用

2023 IEEE International Conference on Intelligent and Innovative Technologies in Computing, electrical and Electronics, ICIITCEE 2023

作者： Sivachandra, K. Kumudham, R. Kumar, P Sathish Rajendran, V. Lakshmi, G.R.Jothi Vels Institute of Science Technology and Advanced Studies Department of ECE Chennai India Rajalakshmi Institute of Technology Department of Computer and Communication Engineering Chennai India

ISBN: (纸本)9781665462631

Nowadays, Artificial Intelligence appears in the domain of goetechnics, underwater acoustics, tunneling, geomorphology engineering and also in several fields too. This paper focused on the prospectivefor machine learning approaches which are sub field of artificial intelligence especially in underwater acoustics domain. In this proposal, machine learning approaches such as light gradient boosting, logistic regression, and random forest classifier algorithms are used for categorizing rocks or mines from collected sonar dataset. Based on performance metrics such as precision, F-score, recall, execution time, accuracy and confusion matrix, evaluate overall performance of machine learning models. Here, the experimental results shows that among all classifier algorithms, light gradient boosting achieves greater validation accuracy as 95% also training accuracy as 100∗ moreover, random forest classifier achieves 100% accuracy during training phase. © 2023 IEEE.

关键词： Underwater acoustics

来源：评论

学校读者我要写书评

暂无评论

Accurate and efficient remaining useful life prediction of batteries enabled by physics-informed machine learning

引用

Journal of Energy Chemistry 2024年第4期91卷 512-521页

作者： Liang Ma Jinpeng Tian Tieling Zhang Qinghua Guo Chunsheng Hu School of Mechanical MaterialsMechatronic and Biomedical EngineeringUniversity of WollongongWollongongNSW 2522Australia Department of Electrical and Electronic Engineering and Research Centre for Grid Modernization The Hong Kong Polytechnic UniversityKowloonHong Kong 999077China School of Electrical Computer and Telecommunications EngineeringUniversity of WollongongWollongongNSW 2522Australia School of Advanced Interdisciplinary Studies Ningxia UniversityYinchuan 750000NingxiaChina

The safe and reliable operation of lithium-ion batteries necessitates the accurate prediction of remaining useful life(RUL).However,this task is challenging due to the diverse ageing mechanisms,various operating conditions,and limited measured *** data-driven methods are perceived as a promising solution,they ignore intrinsic battery physics,leading to compromised accuracy,low efficiency,and low *** response,this study integrates domain knowledge into deep learning to enhance the RUL prediction *** demonstrate accurate RUL prediction using only a single charging ***,a generalisable physics-based model is developed to extract ageing-correlated parameters that can describe and explain battery degradation from battery charging *** parameters inform a deep neural network(DNN)to predict RUL with high accuracy and *** trained model is validated under 3 types of batteries working under 7 conditions,considering fully charged and partially charged *** data from one cycle only,the proposed method achieves a root mean squared error(RMSE)of 11.42 cycles and a mean absolute relative error(MARE)of 3.19%on average,which are over45%and 44%lower compared to the two state-of-the-art data-driven methods,*** its accuracy,the proposed method also outperforms existing methods in terms of efficiency,input burden,and *** inherent relationship between the model parameters and the battery degradation mechanism is further revealed,substantiating the intrinsic superiority of the proposed method.

关键词： Lithium-ion batteries Remaining useful life Physics-informed machine learning

来源：评论

学校读者我要写书评

暂无评论

Leveraging Deep Learning Models for Machine-Generated Text Detection Using Transformer-Based Models

Leveraging Deep Learning Models for Machine-Generated Text D...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart electrical Systems, ICSES 2024

作者： Suthanthiradevi, P. Revathy, G. Rejini, K. Muthu Lakshmi, V. School of Computing Srm institute of Science and Technology Department of Data Science and Business Systems Kattankulathur Chennai India Vels Institute of science Technology and Advanced studies Department of Computer science and engineering Chennai117 India Amrita college of Engineering and Technology Department of Computer Science Engineering Nagercoil India St. Joseph's College of Engineering Department of Computer Science and Engineering OMR Chennai India

ISBN: (纸本)9798331543617

GPT is a large language model (LLM) derived from natural language processing that can generate a human-like text using machine learning. However, these models raise questions about authenticity and reliability of material, particularly in fields such as journalism, social media, and academia, despite their usefulness for automating text-based tasks. Detecting machine-generated text is thus an important difficulty in ensuring content integrity. This study investigates the use of huge language models as a technique for recognizing machine-generated material. The author proposes a comprehensive detection model by evaluating the language patterns, syntactic structures, and stylistic traits that separate AI-generated literature from human writing. In addition, this research investigate the possibilities of fine-tuning models designed expressly for text identification tasks and evaluate their performance using LLM - Detect AI Generated Text datasets. In digital ecosystems, LLMs are effective at detecting AI-generated text, providing a novel approach for content moderation, academic integrity checks, and synthetic media detection. An increasingly AI-powered future will require a model that can discriminate between human and machine-generated writing in real-time. According to experimental findings, the CNN architecture's design combined with the use of DistilBERT embeddings allows for the effective and efficient classification of AI generated text data, achieving an exceptional 98% accuracy rate. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

High-Performance Intelligent System for Real-Time Medical Image Using Deep Learning and Augmented Reality 4th

High-Performance Intelligent System for Real-Time Medical Im...

引用

4th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2023

作者： Senthil, G.A. Prabha, R. Rajesh Kanna, R. Umadevi Venkat, G. Deepa, R. Department of Information Technology Agni College of Technology Chennai India Department of Electronics and Communication Engineering Sri Sai Ram Institute of Technology Chennai India Department of Computer Science and Engineering Agni College of Technology Chennai India Department of Computer Science and Engineering Vels Institute of Science and Technology and Advanced Studies Chennai India

ISBN: (纸本)9789819965854

Evolving new diseases demand the need for technology to identify the disease in an effective way. Medical imaging in the field of disease identification helps to identify the disease by scanning the human parts, thereby preventing the increased rate of deaths. Deep learning algorithms make it easier to identify and analyze disease efficiently through medical imaging. The high performance of these models is needed for the disease to be predicted with accurate results. The prediction rate of the disease can be increased by the efficient use of deep learning modules and algorithms. This research involves the use of deep learning models in identifying brain hemorrhage and retinopathy diseases through deep learning algorithms. The deep learning algorithms AlexNet and convolutional neural network (CNN) with the accuracy of 90% and 96%, respectively, are employed for the detection of brain hemorrhage, and ResNet-50 and CNN with accuracy of 70% and 92%, respectively, are used for the identification of retinopathy. The output of the model is displayed using augmented reality (AR), which makes it interactive for the user to analyze the results. The AR display is achieved using the unity engine along with the Vuforia package and using the barracuda package for importing the deep learning model into unity. Thus, by increasing the accuracy rate of the system, this research demonstrates the high performance of the intelligent system. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

A First Approach on the Impact of Distributed Generation and Fault Impedance on studies on domain of frequency of Voltage Sags

Renewable Energy and Power Quality Journal

引用

Renewable Energy and Power Quality Journal 2023年 21卷 314-322页

作者： Ramos, A.C.L. Batista, A.J. Leborgne, R.C. Domingues, E.G. Calixto, W.P. EDP Transmission Goias S.A Brazil School of Electrical and Computer Engineering Federal University of Goias Brazil Department of Electrical Engineering Federal University of Rio Grande do Sul Brazil Nucleus of Studies Experimental and Technological Electrotechnical Department-Federal Institute of Goias Brazil

An analysis of the distributed generation (DG) and fault impedance on studies of voltage sags caused by system faults is presented on domain of frequency. The simulation of 62 case studies of phase-to-ground faults on 13.8, 69, 138 and 230 kV transmission lines were performed and the voltage of a 380 V sensitive industrial busbar client was monitored. These lines are part of the electrical system of the city of Goiania, Brazil. For each case study, different fault positions and impedance fault were simulated by considering different DG levels connected to the consumer busbar. Long-term simulation scenarios were obtained by the Monte Carlo method and analyzed based on their cumulative distribution functions and probability density curves of voltage sags. This is one major contribution of this work. © 2023, European Association for the Development of Renewable Energy, Environment and Power Quality (EA4EPQ). All rights reserved.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

One-Step Plasma Jet Deposition and Self-Sintering of Gold Nanoparticle Inks on Low-Temperature Substrates

IEEE Journal on Flexible Electronics

引用

IEEE Journal on Flexible Electronics 2024年第5期3卷 197-204页

作者： Manzi, Jacob Varghese, Tony Eixenberger, Josh Prakasan, Lakshmi Estrada, David Subbaraman, Harish Oregon State University School of Electrical Engineering and Computer Science CorvallisOR97331 United States Boise State University Department of Electrical and Computer Engineering Micron School of Material Science and Engineering BoiseID83725 United States Boise State University Micron School of Material Science and Engineering Center for Advanced Energy Studies BoiseID83725 United States Idaho National Laboratory Idaho FallsID83415 United States INFlex Labs LLC BoiseID83706 United States

Flexible electronics on low-temperature substrates like paper are very appealing for their use in disposable and biocompatible electronic applications and areas like healthcare, wearables, and consumer electronics. Plasma-jet printing (PJP) uses a dielectric barrier discharge plasma to focus aerosolized nanoparticles onto a target substrate. The same plasma can be used to change the properties of the printed material and even sinter in situ. In this work, we demonstrate the one-step deposition of gold structures onto flexible and low-temperature substrates without the need for thermal or photonic postprocessing. We also explore the plasma effect on the deposition of the gold nanoparticle ink. The plasma voltage is optimized for the sintering of the gold nanoparticles, and a simple procedure for manufacturing traces with increased adhesion and conductivity is presented, with a peak conductivity of 6.2\times 10{5} S/m. PJP-printed gold LED interconnects and microheaters on flexible substrates are developed to demonstrate the potential of this single-step sintered deposition of conductive traces on low-temperature substrates. © 2022 IEEE.

关键词： Sintering

来源：评论

学校读者我要写书评

暂无评论

What Drives I4.0 Adoption? Establishing the Importance of Strategy

引用

IEEE engineering Management Review 2024年第5期52卷 8-16页

作者： Arcidiacono, Francesco Ancarani, Alessandro Di Mauro, Carmela Schupp, Florian University of Catania Department of Electrical Electronic and Computer Engineering Catania95124 Italy Schaeffler Automotive Bühl Bühl77815 Germany University of Catania Department of Civil Engineering and Architecture Catania95124 Italy Corvinus University of Budapest Corvinus Institute for Advanced Studies Budapest1093 Hungary Constructor University School of Business Social and Decision Sciences Bremen28759 Germany

This article investigates the adoption patterns of Industry 4.0 (I4.0) technologies in the automotive component sector and links I4.0 adoption to competitive strategies. Analysis of survey data concerning 288 automotive suppliers reveals that most firms currently focus on implementing real-time collection and analysis of production data (i.e., the Internet of Things, Big Data, and Artificial Intelligence), while other technologies, such as additive manufacturing and blockchain, are infrequently adopted. I4.0 adoption is associated with a simultaneous strategic emphasis on cost, quality, and delivery, thus suggesting automotive suppliers look at I4.0 as a mean to overcome performance tradeoffs. Findings also confirm that small- and medium-sized firms are less likely to adopt I4.0. Based on these results, implications for academics, managers, and policymakers are suggested. © 2023 IEEE.

关键词： Smart manufacturing

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：