检索结果-内蒙古大学图书馆

12th international conference on Frontier Computing, FC 2022

作者： Lv, Lujun Chen, Qingyi Jilin Agricultural Science and Technology University Jilin Jilin China

ISBN: (纸本)9789819914272

Intelligent home care service platform is an intelligent platform formed by pension + Internet + machine learning to provide pension services for the elderly. Aging is an important problem in society. This problem needs a new intelligent system to help solve. At present, scholars have proposed a set of machine learning algorithm and big data technology to establish a set of intelligent service system for the elderly. This paper introduces the research on the architecture of the pension service platform on account of machine learning and big data analysis, and explains the relevant research and theories on the architecture of the pension service platform. The test shows that the architecture research of pension service platform on account of machine learning and big data analysis has high performance in the architecture research of pension service platform. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

machine Propositional Model Research Based on Natural Language Processing

Machine Propositional Model Research Based on Natural Langua...

引用

IEEE international conference on Electrical engineering, Big data and Algorithms (EEBDA)

作者： Zhou, Jie Sun, Yuqi Wang, Baoping Wang, Zheng Li, Kun Li, Xujia City Univ Macau Sch Educ Macau Peoples R China Minist Educ Engn Res Ctr Appl Technol Machine Translat & Arti Macao Polytech Inst Macau Peoples R China City Univ Macau Fac Data Sci Macau Peoples R China Shandong Youth Univ Polit Sci Sch Informat Engn Jinan Shandong Peoples R China Beijing 171 High Sch Beijing Peoples R China New China Asset Management Co Dept Informat Management Beijing Peoples R China

ISBN: (纸本)9781665416061

machine propositions are the research frontier of natural language processing technology, and the core of the technology path is the result of the development of reading comprehension and question answering systems. machine propositions can help save a lot of manpower and time, especially in the case of the continuous development of the Covid-19, and help the teaching acceptance and learning evaluation of online learning. At present, the simultaneous pursuit of autonomous propositions and precision requirements in the academic field of machine propositions is the research focus and difficulty.

关键词： machine proposition machine reading comprehension text summarization automatic scoring

来源：评论

学校读者我要写书评

暂无评论

The Review of Natural Language Processing Applications with Emphasis on machine learning Implementations

The Review of Natural Language Processing Applications with ...

引用

2022 international conference on Electronics and Renewable Systems, ICEARS 2022

作者： Nagarhalli, Tatwadarshi P. Mhatre, Sneha Patil, Sanket Patil, Prafulla Vidyavardhini's College of Engineering and Technology Department of Computer Engineering Mumbai India Vidyavardhini's College of Engineering and Technology Department of Computer Engineering and Tpo Mumbai India Industry Institute Interaction Cell Vidyavardhini's College of Engineering and Technology Mumbai India

ISBN: (纸本)9781665484251

There is a renewed interest in the recent times for research and development in the field and subfield of Artificial Intelligence, and this is especially true for machine learning and Natural Language Processing. With its ability to make predictions by relying on the data rather than any explicit instructions machine learning and Deep learning Techniques have been employed and adapted in many fields of study and businesses with great success of the different areas which have been revolutionised by the implementation of machine learning and Deep learning Techniques, Natural Language Processing is one such field of study which has benefited the most by this adaptation of learning techniques. Not only in processing of natural language, the learning techniques have played a very positive role in the different applications of Natural Language Processing as well. The paper proposes to highlight the important role played by the learning technique in improving the accuracy of the different applications of Natural Language Processing. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

AutoML Framework for Physical Activities Recognition 3

AutoML Framework for Physical Activities Recognition

引用

3rd international conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Kovalevsky, Vladislav Delhibabu, Radhakrishnan Zhukova, Nataly St. Petersburg Federal Research Center The Russian Academy of Sciences St. Petersburg Russia Vellore Institute of Technology School of Computer Science and Engineering Vellore India

ISBN: (纸本)9798350372120

The rise of measuring, computing, and storage capabilities in modern information systems has led to vast amounts of data in various fields of human activities. Various algorithms for machine learning have been developed to get valuable insights from this raw data. Tuning the hyperparameters of each algorithm is necessary. Finding the right algorithm and manually tuning its hyperparameters for a given task can be very time-consuming. The methods for automating this search are within the scope of AutoML (automated machine learning). The wide use of wearable devices such as smartwatches and fitness trackers enables the gathering of various information about the physical activities of the wearer. This information, in turn, can be used to produce useful insights, such as recognizing activities being performed. AutoML can automate the process of building models for this task, but the performance of the resulting models can be very different depending on the AutoML library that performed the task. In this work, we develop an AutoML framework that unites several commonly used AutoML libraries and enables the use of common constraints and metrics. The developed framework is then used to build models for the task of human activity recognition by processing a dataset containing information collected from smart devices worn by users. © 2024 IEEE.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Multiclass Support Vector data Description in Extreme learning machine Feature Space 3

Multiclass Support Vector Data Description in Extreme Learni...

引用

3rd international conference on Computer, Big data and Artificial Intelligence, ICCBDAI 2022

作者： Lei, Yaolin Ding, Wenrui Wang, Yufeng Zhang, Wenbo Chai, Xinghua Electronic Information Engineering College Beihang University Beijing100000 China 54th Research Institute of China Electronics Technology Group Corporation Shijiazhuang050081 China School of Electronic Engineering Xidian University Xi'an710071 China

Support vector data description (SVDD) method aims to address the one-class classification (OCC) problem to find a hypersphere-shaped description of target data set. For extending SVDD to multiclass classification while remaining the ability of detecting outliers, we propose a novel multiclass SVDD scheme which can be used in effective feature mapping and meta-class separation based on the extreme learning machine algorithm (ELM-MSVDD). Accordingly, the imprecise data difficult to distinguish in specific classes is classified to a meta-class,the meta-class is defined by the disjunction of these specific classes, this operation can reduce the error rate effectively. Experimental results of our ELM-MSVDD method show well performance on the datasets from the UCI machine learning library and radar signal source recognition. Meanwhile, our proposed method provide a theoretical and practical support for other relevant pattern recognition field. © Published under licence by IOP Publishing Ltd.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Determining Whether a Turkish Text is Produced by Artificial Intelligence or Human 3

Determining Whether a Turkish Text is Produced by Artificial...

引用

3rd international conference on Computing and machine Intelligence (ICMI)

作者： Er, Rezzan Nisa Cogalmis, Kevser Nur Istanbul Sabahattin Zaim Univ Comp Engn Istanbul Turkiye

ISBN: (纸本)9798350372977;9798350372984

Nowadays, with the acceleration of the flow of information over the internet, text content such as articles, blog posts and news are now produced in digital environments. Some of this content is produced by artificial intelligence rather than traditional authorship. This situation raises important questions about the reliability of text contents as well as the ease of access to information. The aim of this study is to determine whether an academic text was written by the ChatGPT artificial intelligence content creation tool or by a human. We received our data from the Dergipark platform, which contains Turkish academic articles. The data consists of summaries of Turkish articles. The dates of the articles taken from Dergipark are before the launch of Chatgpt (November 2022). In order to make a real distinction, we had to make sure that the data was actually written by a human. Distinguishing information such as the name and keywords of each article was given to Chatgpt 3.5 and the article summary was requested (tagged as ai). Abstracts of articles with the same distinctive information are also labeled human. The accuracy rate obtained in the study using LSTM is 0.8869 for the test set. In this way, it is aimed to make it easier to determine whether a written text was written by a human or an artificial intelligence text creator.

关键词： NLP LSTM Deep learning machine learning ChatGPT

来源：评论

学校读者我要写书评

暂无评论

Predicting Sepsis Onset in ICU Patients Using machine learning and Feature Section: A Case Study of MIMIC-IV data 2

Predicting Sepsis Onset in ICU Patients Using Machine Learni...

引用

2024 international conference on Medical Artificial Intelligence

作者： Shan, Wenhong Sun, Duanchen Liu, Zhi-Ping Shandong Univ Sch Control Sci & Engn Jinan 250061 Shandong Peoples R China Shandong Univ Sch Math Jinan 250100 Shandong Peoples R China

ISBN: (纸本)9798350377620;9798350377613

This study aims to predict the onset of sepsis in ICU patients using multiple machine-learning models with data from the MIMIC-IV database. We employed seven prediction models Logistic Regression, Gaussian Naive Bayes, Random Forest, Artificial Neural Network, SVM, XGBoost, and Gradient Boosting Decision Tree using 81 features extracted from routine checks conducted within 12 hours before and 4 hours after ICU admission from 46,530 patients. The features were represented by key values such as maximum, minimum, and mean, referencing the official MIMIC derived daily data tables. XGBoost achieved the best performance with an AUC of 0.81 and an accuracy of 0.729. We then applied Recursive Feature Elimination (RFE) to identify the optimal feature subset for each model, finding 13 features commonly selected across all models. This overlap highlights their importance in predicting sepsis and suggests potential for model simplification without losing predictive power. Notably, 6 of these common features overlap with the top 20 SHAP features from the XGBoost model, validating their critical role. Training models with these 18 common features demonstrated that this feature selection process can lead to a simplified, yet effective, predictive model. Thus, we developed a simple, rapid, and practical tool for early detection and clinical intervention of sepsis.

关键词： Sepsis Prediction Intensive Care Unit MIMIC-IV database machine learning Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Classification of failure modes, bearing capacity, and effective stiffness prediction for corroded RC columns using machine learning algorithm

引用

JOURNAL OF BUILDING engineering 2025年 102卷

作者： Zeng, Zhuo Ying, Guogang Zhang, Yi Gong, Yiwei Mei, Yong Li, Xiaopeng Sun, Hua Li, Bing Ma, Jiaxing Li, Shaohua Zhejiang Univ Coll Civil Engn & Architecture Hangzhou 310058 Peoples R China NingboTech Univ Sch Civil Engn & Architecture Ningbo 315199 Peoples R China Southeast Univ Sch Civil Engn Nanjing Peoples R China VRcollab Pte Ltd 75 Ayer Rajah Crescent Singapore 139953 Singapore Acad Mil Sci Inst Def Engn Beijing 100036 Peoples R China PopSmart Technol Co Ltd Ningbo 315100 Peoples R China Nanyang Technol Univ Sch Civil & Environm Engn 50 Nanyang Ave Singapore 639798 Singapore NingboTech Univ Sch Civil Engn & Architecture Ningbo Peoples R China

Corrosion of reinforcement is a crucial factor that significantly impairs the seismic performance of reinforced concrete (RC) columns in building structures. This paper examines three key parameters related to the seismic performance of RC columns: seismic failure modes, maximum bearing capacity, and effective stiffness. The design methodologies for RC columns vary significantly depending on the failure modes, as different failure modes involve distinct mechanical characteristics, thereby influencing the corresponding bearing capacity and effective stiffness. In this study, an intelligent approach is proposed, which first performs the classification of failure modes and subsequently predicts the associated bearing capacity and effective stiffness through regression analysis. Seven supervised learning algorithms and one deep learning algorithm were utilized in this study, with particular emphasis on the k-nearest neighbor (KNN) algorithm due to its simplicity and effectiveness. A comprehensive dataset comprising 221 corroded column specimens under cyclic loading tests was collected, and the findings indicate that the KNN-based model exhibits a high degree of accuracy in failure modes classification (accuracy = 0.91), bearing capacity prediction (R2 = 0.99), and effective stiffness prediction (R2 = 0.95). Comparisons with other algorithms were conducted, and the results indicate that the KNN algorithm outperforms the others. Furthermore, the bearing capacity and effective stiffness predictions generated by the KNN algorithm were compared with empirical formulas from design codes, revealing the clear superiority of the proposed method. Thus, it can be concluded that machine learning techniques offer a promising alternative to traditional mechanics-driven models, particularly in the context of big data and the unique challenges posed by the complex mechanical behavior of RC columns in buildings.

关键词： machine learning K -nearest neighbor Reinforced concrete column Effective stiffness Predictions

来源：评论

学校读者我要写书评

暂无评论

Regret Bounds for Risk-sensitive Reinforcement learning with Lipschitz Dynamic Risk Measures 27

Regret Bounds for Risk-sensitive Reinforcement Learning with...

引用

27th international conference on Artificial Intelligence and Statistics (AISTATS)

作者： Liang, Hao Luo, Zhi-Quan Chinese Univ Hong Kong Shenzhen Hong Kong Peoples R China

We study finite episodic Markov decision processes incorporating dynamic risk measures to capture risk sensitivity. To this end, we present two model-based algorithms applied to Lipschitz dynamic risk measures, a wide range of risk measures that subsumes spectral risk measure, optimized certainty equivalent, and distortion risk measures, among others. We establish both regret upper bounds and lower bounds. Notably, our upper bounds demonstrate optimal dependencies on the number of actions and episodes while reflecting the inherent trade-off between risk sensitivity and sample complexity. Our approach offers a unified framework that not only encompasses multiple existing formulations in the literature but also broadens the application spectrum.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Active Contrastive learning With Noisy Labels in Fine-Grained Classification

Active Contrastive Learning With Noisy Labels in Fine-Graine...

引用

2024 international conference on Electronics, Information, and Communication, ICEIC 2024

作者： Kim, Byeong-Il Ko, Byung Chul Keimyung University Dept. of Computer Engineering Korea Republic of

ISBN: (纸本)9798350371888

In real-world scenarios mirroring fine-grained datasets, labeling may result in noisy labels due to ambiguous data characteristics. This study introduces a new classification approach that integrates active and contrastive learning to address the issue of highly noisy labels in fine-grained datasets. We strategically employ active learning to select boundary points near class-dependent decision boundaries, effectively expanding the distances between classes in the data space. By combining contrastive learning and active learning, we successfully extract robust features from the data. Our experiments consistently achieve high average performance across various levels of label noise, highlighting the potential of our approach in fine-grained datasets. This underscores the method's capability to maintain reliable performance even in the presence of label noise, contributing to the field of fine-grained classification and noisy label mitigation. This innovative approach provides promising insights for enhancing the performance of machine learning models in fine-grained classification tasks. © 2024 IEEE.

关键词： Classification (of information)

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：