检索结果-内蒙古大学图书馆

Design of an Image Segmentation System Based on Hierarchical Density-Based Spatial Clustering of Applications with Noise for Off-Road Unmanned Ground Vehicles

Design of an Image Segmentation System Based on Hierarchical...

引用

international conference on Autonomous Unmanned Systems (ICAUS)

作者： Wang, Jingguo Wang, Yiquan Wang, Jiandong Shen, Yongkang Zhao, Xijun Jiuquan Satellite Launch Ctr Jiuquan Gansu Peoples R China China North Artificial Intelligence & Innovat Res Beijing Peoples R China

ISBN: (纸本)9789819904815;9789819904792;9789819904785

This paper presents an improved, unsupervised machine learning image segmentation system with density-based noisy spatial hierarchical clustering (IS-HDBSCAN). Compared with the conventional image segmentation clustering algorithm K-means, IS-HDBSCAN has better segmentation results, higher adaptivity and lower data pre-processing requirements in complex unstructured environments;compared with convolutional neural network FCN, IS-HDBSCAN does not rely on dataset and model training and has better noise robustness. The article firstly introduces the key issues in the field of image segmentation, then proposes the IS-HDBSCAN image segmentation system and introduces its principles and advantages. Finally, the comparison of image segmentation results in the field environment demonstrates that the IS-HDBSCAN-based image segmentation system has better segmentation results.

关键词： Unsupervised machine learning Complex environment Clustering Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Research on Rolling Bearing Fault Diagnosis Based on Distributed Fuzzy Broad learning System Under Imbalanced data 5

Research on Rolling Bearing Fault Diagnosis Based on Distrib...

引用

5th international conference on Sensing, Measurement and data Analytics in the Era of Artificial Intelligence, ICSMD 2024

作者： Pan, Haiyang Liu, Haoran Zheng, Jinde Tong, Jinyu Cheng, Jian School of Mechanical Engineering Anhui University of Technology Ma'anshan243032 China

ISBN: (纸本)9798331529192

As a novel fast and effective intelligent algorithm, Broad learning System (BLS) is popularly used in data classification task. However, the real data are often imbalanced, which makes BLS have limited performance in dealing with imbalanced data and cannot achieve good classification results. In view of this, a method based on Distributed Fuzzy Broad learning System (DFBLS) under imbalanced data is proposed in this paper. The model assigns a fuzzy affiliation value to each training point, reducing the effect of imbalanced samples on the model, and DFBLS executes fuzzy function in parallel, thus improving computational efficiency and processing speed. Moreover, DFBLS learns the features in the input data by mapping features and enhancement features, which solves the deficiency of fuzzification that leads to the loss or confusion of data samples. Finally, it is validated by two rolling bearing experimental datasets, and the research results show that this technology has demonstrated excellent performance in various evaluation indexes and provides an efficient solution to the fault diagnosis problem in imbalanced data sets. © 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

Integrating ARIMA with machine learning for temperature prediction in major cities in China 3

Integrating ARIMA with machine learning for temperature pred...

引用

3rd international conference on Intelligent Computing and Human-Computer Interaction, ICHCI 2022

作者： Boyan, Li Loskot, Pavel Zhejiang University-University of Illinois Urbana-Champaign Institute Zhejing University China

ISBN: (纸本)9781510661301

The changes in temperature may arise risks in many industries. To solve this problem, the National Meteorological Center and Dalian Commodity Exchange jointly compiled a temperature index which includes 5 cities. Therefore, forecasting time series temperature data in those cities is an important subject. Traditionally, we use statistic method ARIMA to predict the next lags of time series. With the advancement in computational power of computers and the introduction of more advanced machine learning algorithms, this paper develops a method by integrating ARIMA with machine learning to analyze and forecast time series data. The empirical studies conducted show that integrating ARIMA with Long Short-Term Memory outperforms that with Support Vector Regression, or Random Forest in their prediction accuracy. © 2023 SPIE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

The Price Prediction of Sneakers Based on machine learning

The Price Prediction of Sneakers Based on Machine Learning

引用

2022 international conference on machine learning and Knowledge engineering, MLKE 2022

作者： Yan, WeiJia Shanghai University of Electric Power Computer Science Department Shanghai200120 China

ISBN: (纸本)9781665495677

Sneaker culture is a self-organizing culture spontaneously formed by teenagers. In the Internet and digital age, sports shoes are endowed with appreciation and financial attributes through manual speculation, which has triggered a wave of sports shoes speculation with the participation of the whole people. As a human group behavior, the detonating mechanism behind speculative sneakers is worth thinking about. There is a set of logical behavior chains and practical logic in the behavior of frying shoes. It is necessary to use threshold theory to reveal the dynamic process of convergence from micro behavior to macro behavior. Therefore, machine learning can be used to predict the movement of sneaker prices in the sneaker market. The data set of this study is from stockx. In the research, the machine learning method is used to study the price of sports shoes and analyze the data. Four linear regression models were used for prediction. It is found that the OLS regression model's accuracy is high. So OLS model is the best model for this dataset. © 2022 IEEE.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Fuzhou Destination Image Perception Study - Based on machine learning LDA model and SVM model

Fuzhou Destination Image Perception Study - Based on machine...

引用

2022 international conference on Computer Graphics, Artificial Intelligence, and data Processing, ICCAID 2022

作者： Liu, Ronghui Lin, Jinhuang Wei, Qianqian Jiang, Qingquan School of Economics and Management Xiamen University of Technology Xiamen China

ISBN: (纸本)9781510663350

The image shaping of tourist attractions is one of the important factors to attract tourists. This paper explores the perceived impression of Fuzhou in tourists' mind and the perceived dimensions of tourists' attention by studying the review texts of tourists when they visit Fuzhou. By collecting reviews about Fuzhou on ***, ***, and Donkey Mama, the destination image of Fuzhou is obtained through LDA (Latent Dirichlet Allocation) theme modeling model and SVM (Support Vector machine) sentiment analysis model text data mining, so as to objectively extract the perceptual dimensions of tourists when visiting Fuzhou. The study found that the perceptual dimensions that tourists focus on during their visit to Fuzhou are mainly, namely, "tourism services", "entrance fee", "human landscape", "natural landscape";"natural scenery", "history and culture", and "activity experience". The results of the study have some reference significance for Fuzhou in construction and promotion. © 2023 SPIE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

machine learning-assisted probabilistic creep life assessment for high-temperature superheater outlet header considering material uncertainty

引用

international JOURNAL OF PRESSURE VESSELS AND PIPING 2024年 209卷

作者： Zhang, Zhen Wang, Xiaowei Li, Zheng Xia, Xianxi Chen, Yefeng Zhang, Tianyu Zhang, Hao Yang, Zheyi Zhang, Xiancheng Gong, Jianming Nanjing Tech Univ Sch Mech & Power Engn Nanjing 211816 Peoples R China Jiangsu Key Lab Design & Manufacture Extreme Press Nanjing 211816 Peoples R China East China Univ Sci & Technol Key Lab Pressure Syst & Safety Minist Educ Shanghai 200237 Peoples R China Suzhou Nucl Power Res Inst Suzhou Xihuan Rd 1688 Suzhou 215004 Peoples R China Xian Thermal Power Res Inst Co Ltd Xian Peoples R China

The high-temperature superheater outlet header (Outlet Header) in ultra-supercritical (USC) thermal power plants is subjected to high temperatures and pressures, which increases the risk of creep failure. To assess the structural reliability of the Outlet Header, it is necessary to consider the impact of uncertainty factors. Furthermore, the diverse operating conditions make reliability assessment inconvenient. This study evaluates the creep life reliability of the Outlet Header based on material uncertainty and simplifies the assessment process using machine learning methods. Considering the scatter of creep rupture data, the uncertainty of material constants in the Larson-Miller (LM) model is quantified by randomly sampling a specific number of creep rupture life data. Based on the results of uncertainty quantification and finite element analysis, the distribution of the Outlet Header's creep life is obtained to calculate its reliability under design life. machine learning is employed to assist in the reliability assessment of creep life under different operating conditions of Outlet Header. The results indicate that Artificial Neural Network (ANN) demonstrates good performance in this study, and an assessment diagram based on the ANN has been constructed. This approach provides a practical solution for assessing the reliability of high-temperature components in engineering.

关键词： Creep life Reliability assessment machine learning High -temperature superheater outlet header

来源：评论

学校读者我要写书评

暂无评论

GitSchemas: A dataset for Automating Relational data Preparation Tasks 38

GitSchemas: A Dataset for Automating Relational Data Prepara...

引用

38th IEEE international conference on data engineering (ICDE)

作者： Doehmen, Till Hulsebos, Madelon Beecks, Christian Schelter, Sebastian Fraunhofer FIT St Augustin Germany Univ Amsterdam Amsterdam Netherlands Univ Hagen Hagen Germany

ISBN: (纸本)9781665481045

The preparation of relational data for machine learning (ML) has largely remained a manual, labor-intensive process, while automated machine learning has made great strides in recent years. Long-standing challenges, such as reliable foreign key detection still pose a major hurdle towards more automation of data integration and preparation tasks. We created a new dataset aimed at increasing the level of automation of data preparation tasks for relational data. The dataset, called GITSCHEMAS, consists of schema metadata for almost 50k real-world databases, collected from public GitHub repositories. To our knowledge, this is the largest dataset of such kind, containing approximately 300k table names, 2M column names including data types, and 100k real (not semantically inferred) foreign key relationships. In this paper, we describe how GITSCHEMAS was created, and provide key insights into the dataset. Furthermore, we show how GITSCHEMAS can be used to find relevant tables for data augmentation in an AutoML setting.

关键词： database schemas relational data data preparation machine learning

来源：评论

学校读者我要写书评

暂无评论

Artistic Essence of Generative Adversarial Networks: Analyzing Training data's Impact on Performance 2

Artistic Essence of Generative Adversarial Networks: Analyzi...

引用

2nd international conference on machine learning and data engineering, icmlde 2023

作者： Pal, Kuldeep Chaudhuri, Rapti Deb, Suman Saha, Ashim National Institute of Technology Agartala 799046 India

Generative adversarial networks (GANs) are powerful deep learning models for synthesizing realistic data. However, their performance critically depends on curating optimal training data. This research conducts a comprehensive study analyzing the impact of sample size, class balance, and heterogeneity in training datasets on GAN image and text generation quality. Through extensive experiments on CIFAR-10, it has been demonstrated that insufficient samples, imbalanced classes, and lack of diversity cause degraded sample quality, coherence, and mode collapse. The analysis conducted in this research work provides unique insights into data-GAN interplay. Models trained on balanced subsets with adequate samples per class produce superior Inception Scores and BLEU, avoiding limited variety in outputs. The techniques presented enable developing more generalizable and creative GANs. This work proves to be the first of its kind to rigorously evaluate the role of data characteristics like size, balance and heterogeneity in stabilizing GAN training and improving output fdelity across modalities. The data-centric findings would be valuable for researchers to curate optimal datasets that can unlock GANs' full potential for diverse, realistic generation with wide applications in graphics, vision, language and beyond. © 2024 Elsevier B.V.. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Designing of VehiNet Using Convolutional Neural Networks and Deep learning Techniques 2

Designing of VehiNet Using Convolutional Neural Networks and...

引用

2nd international conference on machine learning and data engineering, icmlde 2023

作者： Kandala, Mahita Kaushik, M. Nambiar, Vaishakh Vignesh, S.G. Jyotsna, C. Singh, Tripty Duraisamy, Prakash Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetam Bengaluru India University of Wisconsin Green BayWI United States

Traffic congestion has become a critical issue in metropolitan areas, inflicting significant hardships on individuals on a daily basis. This adverse situation poses multifaceted challenges, including increased air pollution, heightened fuel consumption, and compromised road safety. Deep learning algorithms, encompassing both Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN) have showcased remarkable performance in areas such as computer vision, natural language processing, healthcare, finance, and autonomous systems. This research paper proposes a novel methodology to develop a vehicle detection model - VehiNet, which can subsequently be refined to create an automated traffic signal system. The study explores the effectiveness of various CNN, RNN, and deep learning algorithms and techniques in accomplishing this objective. The dataset picked for the study in addition to being compiled from internet resources, was also painstakingly assembled manually using a variety of methods to collect over 2000 photographs from various angles, lighting conditions, and locations within Bengaluru city. The main motive is to apply CNN, RNN, and other Deep learning classification techniques for object detection and classification of Indian vehicles and see how well these deep learning algorithms and techniques affect prediction efficiency. This research stands out from others and makes its novelty clear thanks to the carefully collected dataset and the detailed analysis of the methodologies. © 2024 Elsevier B.V.. All rights reserved.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Time Series Anomaly Detection Toolkit for data Scientist 38

Time Series Anomaly Detection Toolkit for Data Scientist

引用

38th IEEE international conference on data engineering (ICDE)

作者： Patel, Dhaval Phan, Dzung Mueller, Markus IBM Corp Thomas J Watson Res Ctr Yorktown Hts NY 10598 USA

ISBN: (数字)9781665408837

ISBN: (纸本)9781665408837

This tutorial presents a design and implementation of a scikit-compatible system for detecting anomalies from time series data for the purpose of offering a broad range of algorithms to the end user, with special focus on unsupervised/semi-supervised learning. Given an input time series, we discuss how data scientist can construct four categories of anomaly pipelines followed by an enrichment module that helps to label anomaly. The tutorial provides an hand-on-experience using a deployed system on IBM API Hub for developer communities that aim to support a wide range of execution engines to meet the diverse need of anomaly workloads such as Serveless for CPU intensive work, GPU for deep-learning model training, etc.

关键词： anomaly detection machine learning pipelines

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：