检索结果-内蒙古大学图书馆

14th International Conference on the Properties and Applications of Dielectric Materials, ICPADM 2024

作者： Cheypoca, Thepjit Promphanich, Wiboon Thway, Aung Ye Hankae, Angelina Phimpissada Jeenmuang, Siwakorn Pattanadech, Norasage School of Engineering King Mongkut's Institute of Technology Ladkrabang Instrumentation and Control Engineering Dept. Bangkok Thailand School of Engineering King Mongkut's Institute of Technology Ladkrabang Computer Engineering Dept. Bangkok Thailand School of Engineering King Mongkut's Institute of Technology Ladkrabang Electrical Engineering Dept. Bangkok Thailand School of Engineering King Mongkut's Institute of Technology Ladkrabang Mechatronics Engineering Dept. Bangkok Thailand

ISBN: (纸本)9798350374605

This paper introduces a novel approach for classifying with the 1D Convolutional Neural Network model for partial discharge patterns, that consists of corona discharge, surface discharge and internal discharge. The PD measuring circuit suggested in IEC 60270:2000 is used to record Partial discharge signals. Independent parameters such as phase and charge of PD patterns were recorded. The Artificial Neural Network for the classification model was constructed. Moreover, 2×1D CNN feature extraction was utilized to reduce the curse of dimensionality in the dense layer of the proposed PD classification model. 80% of the recorded data will be used as a training data and 20% recorded data was used for testing of the classification models. Impacts of neuron numbers and network architecture on the PD classification performance will be observed. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Machine Learning in Predictive Maintenance for Industrial Equipment 1

Machine Learning in Predictive Maintenance for Industrial Eq...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Rathore, Saurabh Pratap Singh Gupta, Anjali Parashar, Akshat Upadhyay, Dheeresh Deb, R.K. Gupta, Abhinav ICAPSR Dept. of Management New Delhi India Madhav University Dept. of Pharmacy Pindwara India Mangalayatan University Dept. of EEE Aligarh India Lingayas Vidyapeeth Dept. of Mechanical Engineering Faridabad India J.S. University Dept. of Computer Science Shikohabad India

ISBN: (纸本)9798350356816

The integration of machine learning into predictive maintenance strategies has revolutionized how industries manage equipment reliability & performance. This abstract examines the role of machine learning algorithms in predicting equipment failures & optimizing maintenance activities. By analyzing historical data, sensor information, & operational conditions, machine learning models can forecast potential failures, enabling preemptive maintenance actions that reduce unplanned down-times & extend equipment life. Techniques such as decision trees, neural networks, & clustering algorithms are explored for their effectiveness in detecting anomalies, predicting failures, & recommending maintenance schedules. This approach not only improves the efficiency of maintenance processes but also offers significant cost savings & safety enhancements. The research addresses practical challenges in deploying machine learning solutions, including data acquisition, model accuracy, & integration into existing maintenance systems. The abstract highlights the potential of these technologies to transform maintenance practices & drive future advancements in industrial equipment management. © 2024 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

3D modelling and virtual reality for museum heritage presentation: Contextualisation of sculpture from the tang era 10

3D modelling and virtual reality for museum heritage present...

引用

10th International Workshop 3D-ARCH "3D Virtual Reconstruction and Visualization of Complex Architectures"

作者： Spallone, R. Lamberti, F. Vigo, L. Ronco, F. Calandra, D. Ferraro, M. Dept. of Architecture and Design Politecnico di Torino Italy Dept. of Control and Computer Engineering Politecnico di Torino Italy Curator of Asian Arts Montreal Museum of Fine Arts MontrealQC Canada

The present research concerns the contextualisation and presentation of eleven small statues from the Tang era dated from the XI and XII centuries CE today housed at the Asian Art Museum in Turin (MAO). A multidisciplinary group with expertise in Asian art, digital representation, and information processing systems, with the support of VR@POLITO and MOD Lab Arch of the Politecnico di Torino is involved in the work. The goal is to present together several Tang-era pottery models not belonging to the same funerary outfit within the spaces of a coeval, philologically compatible hypogeal tomb. With a pronounced storytelling intent, the reconstructive 3D model represents a virtual exhibition project summarizing Tang art's architectural, pictorial, and sculptural features. The pipeline was developed through photogrammetric acquisition with Structure from Motion (SfM) technology and 3D modeling of the artworks, reconstructive modeling and texturing of a Tang tomb as the ideal space of the statues, and communication through a virtual reality (VR) experience augmented with a set of information. © Author(s) 2024.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Finding Optimal Routes in MaaS Framework using ParetoBFS 6

Finding Optimal Routes in MaaS Framework using ParetoBFS

引用

6th International Conference on Intelligent Computing and control Systems, ICICCS 2022

作者： Mitra, Poojarini Rehena, Zeenat Mukherjee, Nandini University of Engineering & Management Dept. of Computer Applications Kolkata India Aliah University Dept. of Computer Science & Engineering Kolkata India Jadavpur University Dept. of Computer Science & Engineering Kolkata India

ISBN: (纸本)9781665410359

To offer Mobility as a Service (MaaS) to the consumers while handling time-dependent multi-modal transportation and maintaining multiple criteria is a complex task. The system needs to be intelligent enough to provide optimal routes within the least possible computation time. This paper proposes a simple method that seeks to provide a solution by using the ParetoBFS algorithm, a modified version of the traditional BFS algorithm, which uses Pareto constraints to prune the graph and find all Pareto-optimal paths in a network considering multiple criteria. Evaluations with different scenarios were performed using the proposed mechanism and its performance was compared with Weighted-Sum Dijkstra's Algorithm. It can be observed that the proposed mechanism is achieving better results than Weighted-Sum Dijkstra's Algorithm. © 2022 IEEE.

关键词： Pareto principle

来源：评论

学校读者我要写书评

暂无评论

A Probabilistic Topology Inference Method for Networked Dynamical System via Single Excitation 63

A Probabilistic Topology Inference Method for Networked Dyna...

引用

63rd IEEE Conference on Decision and control, CDC 2024

作者： Jiao, Qing Li, Yushan He, Jianping Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Dept. of Automation Shanghai China

ISBN: (纸本)9798350316339

A growing number of works have investigated inferring the topology of networked dynamical systems from observations, such as to better understand the system behaviour. Despite the tremendous advances, most of them require the observations to be abundant. This paper focuses on inferring the topology by injecting single excitation on a node and collecting several steps of noisy observations. The problem is challenging because the noises cannot be depressed in several observations and are mixed with the injected excitation, making it hard to directly reveal the topology. To practice, we develop a probabilistic method based on the hypothesis test framework. First, we infer the neighbors that are within h-hop of the excited node and derive the accuracy guarantees. Then, we extend the method to infer the exact h-hop neighbors. A computable lower bound for the accuracy probability is established to provide confidence support in the inference procedures. Furthermore, we give the conditions of excitation input to ensure a desired inference probability, which provides guidance for the input design. Numerical simulations are conducted to verify the effectiveness of the proposed method. © 2024 IEEE.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Designing of Creator's Information Hub using Machine Learning 2

Designing of Creator's Information Hub using Machine Learnin...

引用

2nd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry, IDICAIEI 2024

作者： Gabhane, Diksha Gawande, Ujwalla Gaikwad, Sanjana Gajarlewar, Swati Bhawalkar, Rita Yeshwantrao Chavan College of Engineering Dept. of Computer Science & Design Nagpur India Yeshwantrao Chavan College of Engineering Dept. of Information Technology Nagpur India NCPharmacy Wanadongri Nagpur India G H Raisoni College of Engineering and Management Dept. of Cyber Security and Data Science Pune India

ISBN: (纸本)9798331528713

The proliferation of educational content on platforms like YouTube has transformed digital learning, yet it presents challenges in effective creation, dissemination, and impact assessment. This paper proposes a strategic initiative to collaborate with 6,000 active educational YouTubers to enhance global educational outreach. Central to this initiative is the compilation and analysis of a comprehensive dataset containing vital information about content creators and their audiences. Leveraging advanced machine learning algorithms, the analysis aims to identify collaboration opportunities, optimize engagement strategies, enhance content relevance and impact, facilitate knowledge sharing, and measure outcomes. The problem statement highlights fragmentation in educational content, lack of data-driven insights, and suboptimal collaboration opportunities. Addressing these challenges requires a structured approach to connect creators, leverage data analytics, and establish a collaborative ecosystem for enriching educational experiences worldwide. © 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

From Product Sheet to Text and Video: A NLG Pipeline to Transform Structured Data into Comprehensive Descriptions 32

From Product Sheet to Text and Video: A NLG Pipeline to Tran...

引用

32nd Italian Symposium on Advanced Database Systems, SEBD 2024

作者： Avignone, Andrea Fiori, Alessandro Chiusano, Silvia Rizzo, Giuseppe Dept. of Control and Computer Engineering Politecnico di Torino Corso Duca degli Abruzzi 24 Torino10129 Italy LINKS Foundation Torino Italy

The recent improvement of powerful Large Language Models is the key to automatically produce satisfactory written and spoken language, in contrast to the constraints of conventional template-based solutions. However, the most advanced models can be costly and complex to integrate into practical applications, especially in business contexts where the output quality significantly matters. This study presents a tailored pipeline for data-to-text and text-to-speech generation, primarily harnessing the availability of open source pre-trained language models and leveraging established Natural Language Processing tasks. As a use case, we worked on the automatic generation of both textual and video product descriptions from the structured information about the product features. The pipeline involves all the required steps, providing the final trained and customized model. The obtained descriptions showed the capability of replicating the overall semantic, lexical and linguistic style of the corresponding human counterpart, despite being based on a cost-effective model. © 2024 Copyright for this paper by its authors.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Fast and More Accurate Seed-and-Extension Density-Based Clustering Algorithm

引用

IEEE Transactions on Knowledge and Data engineering 2023年第6期35卷 5458-5471页

作者： Tung, Ming-Hao Chen, Yi-Ping Phoebe Liu, Chen-Yu Liao, Chung-Shou Research and Development Micron Technology Inc Hsinchu Taiwan Department of Computer Science and Information Technology La Trobe University Melbourne Australia Dept. Industrial Engineering and Engineering Management National Tsing Hua University Hsinchu Taiwan Industrial Engineering and Engineering Management National Tsing Hua University Hsinchu Taiwan

Clustering algorithms have been widely studied in many scientific areas, such as data mining, knowledge discovery, bioinformatics and machine learning. A density-based clustering algorithm, called density peaks (DP), which was proposed by Rodriguez and Laio, outperforms almost all other approaches. Although the DP algorithm performs well in many cases, there is still room for improvement in the precision of its output clusters as well as the quality of the selected centers. In this study, we propose a more accurate clustering algorithm, seed-and-extension-based density peaks (SDP). SDP selects the centers that hold the features of their clusters while building a spanning forest, and meanwhile, constructs the output clusters in a seed-and-extension manner. Experiment results demonstrate the effectiveness of SDP, especially when dealing with clusters with relatively high densities. Precisely, we show that SDP is more accurate than the DP algorithm as well as other state-of-the-art clustering approaches concerning the quality of both output clusters and cluster centers while maintaining similar running time of the DP algorithm, particularly for a variety of time-series data. Moreover, SDP outperforms DP in the dynamic model in which data point insertion and deletion are allowed. From a practical perspective, the proposed SDP algorithm is obviously helpful to many application problems. © 1989-2012 IEEE.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Technique for Real-Time Forest Fire Detection from Video Streams 11

Deep Learning Technique for Real-Time Forest Fire Detection ...

引用

11th International Conference on Intelligent Systems and Embedded Design, ISED 2023

作者： Gupta, Nidhi Chakravarty, Sujata Dash, Satyabrata Centurion University of Technology & Management Dept. of Computer Science & Engineering Odisha India Gandhi Institute of Technology & Management Gitam Deemed to Be University Dep. of Computer Science and Engineering Andhra Pradesh India

ISBN: (纸本)9798350318159

Forest fires are currently the most common issue that we are dealing with. The resources that have been lost are irreplaceable. Forest fires are uncontrollable fires that occur in nature as a result of human involvement or any other natural event. Forest fires can be so large that putting them out takes a long time. Contrasting with previous years, there has been a striking surge in the frequency of forest fires. Changes in climatic conditions are the key factor affecting the scope of forest fires. Long dry spells in the spring and summer make the woodlands particularly vulnerable. The extent of forest fires is mostly determined by weather conditions such as precipitation and wind, as well as the terrain's architecture. Long dry spells in the spring and summer make the woodlands particularly vulnerable. The extent of forest fires is mostly determined by weather conditions such as precipitation and wind, as well as the terrain's architecture. The incorporation of a Video Fire Detection model significantly enhances the efficiency of fire detection systems, particularly in large spaces. Establishing a video fire detection system involves focusing on spatial, spectral, and temporal indicators, as well as flame picture segmentation, recognition, tracking, and prediction. Analytical techniques, specifically utilizing ResNet50 and VGG16 models, can be applied to identify pool fire images through these segmentation processes, contributing to more robust fire detection capabilities. © 2023 IEEE.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

Exploring User Experience and Challenges with Mobile Wallet Adoption in Emerging Markets 2

Exploring User Experience and Challenges with Mobile Wallet ...

引用

2nd International Conference on Technology Innovation and Its Applications, ICTIIA 2024

作者： Priandito Lutfiani, Ninda Yusuf, Natasya Aprila Goh, Thomas Sumarsan Madani, Muchlisina University of Raharja Dept. of Informatics Engineering Tangerang Indonesia University of Raharja Dept. of Digital Business Tangerang Indonesia University of Raharja Dept. of Information Systems Tangerang Indonesia Universitas Methodist Indonesia Dept. of Management Medan Indonesia University of Raharja Dept. of Computer System Tangerang Indonesia

ISBN: (纸本)9798350351613

This study explores user experiences and challenges in mobile wallet adoption in emerging markets using the UTAUT model. These markets face rapid technological growth alongside infrastructural and economic challenges. The research examines how factors like performance expectancy, effort expectancy, social influence, and facilitating conditions influence adoption. Data from 80 mobile wallet users was collected through an online survey and analyzed using SmartPLS 4.1.0.6. The results show that performance and effort expectancy predict behavioral intention, while facilitating conditions affect actual usage. The study highlights the role of infrastructure in supporting adoption and validates the UTAUT model's relevance in less developed regions. These findings provide insights into enhancing financial inclusion in emerging markets. © 2024 IEEE.

关键词： Emerging Markets Mobile Wallet Technology Adoption User Experience UTAUT

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：