检索结果-内蒙古大学图书馆

12th international conference on learning Representations, ICLR 2024

作者： Yang, June Yong Park, Geondo Kim, Joowon Jang, Hyeongwon Yang, Eunho KAIST Korea Republic of Seoul National University Korea Republic of AITRICS Korea Republic of

Tabular data in the wild are frequently afflicted with class-imbalance, biasing machine learning model predictions towards major classes. A data-centric solution to this problem is oversampling - where the classes are balanced by adding synthetic minority samples via generative methods. However, although tabular generative models are capable of generating synthetic samples under a balanced distribution, their integrity suffers when the number of minority samples is low. To this end, pre-trained generative language models with rich prior knowledge are a fitting candidate for the task at hand. Nevertheless, an oversampling strategy tailored for tabular data that utilizes the extensive capabilities of such language models is yet to emerge. In this paper, we propose a novel oversampling framework for tabular data to channel the abilities of generative language models. By leveraging its conditional sampling capabilities, we synthesize minority samples by progressively masking the important features of the majority class samples and imputing them towards the minority distribution. To reduce the inclusion of imperfectly converted samples, we utilize the power of the language model itself to self-authenticate the labels of the samples generated by itself, sifting out ill-converted samples. Extensive experiments on a variety of datasets and imbalance ratios reveal that the proposed method successfully generates reliable minority samples to boost the performance of machine learning classifiers, even under heavy imbalance ratios. © 2024 12th international conference on learning Representations, ICLR 2024. All rights reserved.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Ratatouille: A tool for Novel Recipe Generation 38

Ratatouille: A tool for Novel Recipe Generation

引用

38th IEEE international conference on data engineering (ICDE)

作者： Goel, Mansi Chakraborty, Pallab Ponnaganti, Vijay Khan, Minnet Tatipamala, Sritanaya Saini, Aakanksha Bagler, Ganesh Indraprastha Inst Informat Technol IIIT Delhi Ctr Computat Biol New Delhi India Indraprastha Inst Informat Technol IIIT Delhi Dept Comp Sci New Delhi India

ISBN: (纸本)9781665481045

Due to availability of a large amount of cooking recipes online, there is a growing interest in using this as data to create novel recipes. Novel Recipe Generation is a problem in the field of Natural Language Processing in which our main interest is to generate realistic, novel cooking recipes. To come up with such novel recipes, we trained various Deep learning models such as LSTMs and GPT-2 with a large amount of recipe data. We present Ratatouille (https://***/ratatouille2/), a web based application to generate novel recipes.

关键词： Novel Recipe Generation Deep learning LSTM machine learning GPT2

来源：评论

学校读者我要写书评

暂无评论

Social Media + machine learning to Offer Clues on Suicide Ideation Concerns 1

引用

The 4th international conference on data Science, machine learning 2022

作者： Prayaga, Lakshmi Prayaga, Chandra Gunuru, Amrutha Department of Information Technology University of West Florida Pensacola United States Physics Department University of West Florida Pensacola United States Information Technology University of West Florida Pensacola United States

ISBN: (数字)9789819920587

ISBN: (纸本)9789819920570

Mental health concerns including suicide ideation are a growing concern especially among younger population. Social media also is providing a platform for people with mental health concerns to vent their frustrations and other psychological mental health concerns including suicide ideation. This research is a study on the application of topic modeling, a machine learning algorithm on big data gathered from social media to discover clues that may play a role resulting in adverse outcomes such as suicide ideation. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

A data-Driven Model For Wildfire Prediction in California

A Data-Driven Model For Wildfire Prediction in California

引用

international conference on Smart Applications, Communications and Networking (SmartNets)

作者： Hahs, Brennon Sood, Kanika Gomez, Desiree Calif State Univ Fullerton Dept Engn & Comp Sci Fullerton CA 92634 USA

ISBN: (纸本)9798350385328;9798350385335

Wildfires in California have consistently been a concern that has been getting more acute in the past years. Rampant wildfires have consistently hit the state of California, creating severe economic and environmental loss. In 2023, wildfires cost nearly 1.2 billion U.S. dollars in financial loss between January and September. Between 2021-2022, wildfires accounted for over 11.2 billion in damage across the United States. Over 1.6 million acres of land have burned and caused large sums of environmental damage. The increasing frequency and severity of wildfires in California have led to a growing need for accurate and reliable wildfire risk assessments. In this research, we propose a machine learning approach based on six different classifiers to determine wildfire risk using environmental data from California. We use a dataset of historical wildfire occurrences and various environmental variables such as temperature, humidity, and wind speed to build a recommendation model using a Random Forest classifier. We use the SMOTE technique to handle class imbalance.

关键词： Wildfires machine learning random forest natual disasters decision trees naive bayes logistic regression

来源：评论

学校读者我要写书评

暂无评论

Noise-resistant state of charge estimation of Li-ion battery using the outlier robust extreme learning machine

引用

ENERGY REPORTS 2023年 9卷 1-8页

作者： Zhang, Yuao Dai, Yunwei Yang, Ranchen Li, Zhenyu Zhao, Jun Wu, Qingbiao Zhejiang Univ Sch Math Sci Hangzhou 310027 Peoples R China Zhejiang Univ Coll Elect Engn Hangzhou 310027 Peoples R China

The State of Charge (SOC) indicates the amount of charge remaining in the battery, which is a critical parameter in the battery management system (BMS). A precise SOC estimation can effectively protect the battery and extend its service life. Recently, a leading-edge machine learning model, namely the extreme learning machine (ELM), has been applied for SOC estimation due to its powerful fitting and fast training capabilities. However, as BMS is required to operate in more and more complex environments, it is inevitable to encounter the effects of non-Gaussian noises caused by system errors, human causes, and other factors. These noises are random, sparse, and far from the targets, mainly referring to the outliers. The classical extreme learning machine (ELM) is susceptible to noise, leading to poor performance in outlier-contaminated datasets. To overcome this problem, we developed a new robust SOC estimation method through the outlier robust ELM (OR-ELM) in this paper. Additionally, a powerful iterative algorithm, namely the alternating direction method of multipliers (ADMM), was utilized for training OR-ELM. Experiments were carried out on a dataset of Panasonic 18650 cells, and the results show the applicability and robustness of OR-ELM in the SOC estimation. (c) 2022 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Alternating direction method of multipliers Battery management system Extreme learning machine Robustness State of charge

来源：评论

学校读者我要写书评

暂无评论

Analysis of IPL Auction dataset Using Explainable machine learning with Lime and H2O AutoML 4

Analysis of IPL Auction Dataset Using Explainable Machine Le...

引用

4th international conference on Intelligent engineering and Management, ICIEM 2023

作者： Garg, Aradya Chaudhary, Alka Amity Institute of Information Technology Amity University Uttar Pradesh Noida India

ISBN: (纸本)9798350341126

The global sports market, one of the biggest markets in the world, grew from 354.96 billion in 2021 to 496.52 billion in 2022, according to research from a business research organization. Sports teams are becoming increasingly devoted to investing in sports data analytics to gain a competitive edge as spending on the global sports market rises;as a result, it is predicted that the sports analytics industry will exceed 4.5 billion by 2025. It is the study of athletic performance and business health to maximize a sports organization's processes and results. Explainable machine learning (XML) is a key part of machine learning and AI because it explains how machine learning models create predictions. To establish trust and ensure accountability in AI systems, it is crucial to be able to comprehend and evaluate a model's predictions. © 2023 IEEE.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

Comparing Different machine learning Techniques for Diabetes Risk Prediction

Comparing Different Machine Learning Techniques for Diabetes...

引用

2022 international conference on Computer Vision, Application, and Algorithm, CVAA 2022

作者： Cai, Wenzhe Chen, Yifei Wang, Helin Jinan University - University of Birmingham Joint Institute at Jinan University Jinan University Guangdong Guangzhou510000 China School of Software Engineering South China University of Technology Guangdong Guangzhou510000 China Ira A. Fulton Schools of Engineering Arizona State University Tempe85281 United States

ISBN: (纸本)9781510664036

Diabetes is a very common disease, and many people in the world are poisoned by it. Diabetes will also cause some complication, such as diabetic foot, diabetic retinopathy, and even permanent loss of vision. At present, the most effective way to fight diabetes is early detection and early intervention. Restricting sugar intake as early as possible is the most economical approach. However, early diabetes often has no obvious symptoms, so it is very time-consuming and laborious for doctors to check one by one. Therefore, it is particularly important for an automated algorithm to assess the risk of diabetes change. This paper uses two machine learning methods and an artificial neuron network, popular frameworks to handle big data and built by python toolkits, to automatically make predictions of diabetes, and compares their performances of them in order to provide some insights into future diabetes prevention and treatments. The machine learning models in the paper are support vector machine (SVM) and GaussianNB, both of which possess relatively good interpretability and classification ability. The deep learning model is a classical artificial neural network (ANN). The result shown by confusion matrices presents that the artificial neuron network has the best accuracy in prediction among the three models with a limited dataset, which is 0.736, and the SVM and GaussianNB are 0.72 and 0.735 respectively. © 2023 SPIE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Prediction of Liver Abnormality using machine learning

Prediction of Liver Abnormality using Machine Learning

引用

2022 OPJU international Technology conference on Emerging Technologies for Sustainable Development, OTCON 2022

作者： Gottemukkala, Lavanya Jeevan Nagendra Kumar, Y. Sai Manikanta Phani Teja, U. Tanishq Dhanraj, N. Nitish, Y. Gokaraju Rangaraju Institute of Engineering and Technology Jntuh Department of Information Technology Hyderabad India

ISBN: (纸本)9781665492942

Cancer according to the American Society of Clinical Oncology journal was first described back in 1600 B.C. and has been prevalent ever since. The technological advancement in the field of medical sciences aided with advancement in the field of machine learning and deep learning has brought us to a situation today, where a subject can be informed of the dangers or the possibility of possessing an infected liver. In the prediction model, different enzymes were studied, and appropriate ratios were to determine the stability of the hepatocytes in the liver. The data was employed by different machine learning algorithms and based on their accuracy levels the final prediction has been made using the most appropriate algorithm. In an attempt to take the model to the next level, a few more algorithms were employed and explored the dataset even more. The results of each algorithm are compared using ROC graphs and ROC AUC SCORE to achieve a better model for this prediction model. Each algorithm is given by certain hyper-parameters which would increase the fitting nature more towards the best. The most important features calculated by each algorithm are mentioned and used accordingly to calculate the results. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Enhancing Dynamic Hand Gesture Recognition through Optimized Feature Selection using Double machine learning 24

Enhancing Dynamic Hand Gesture Recognition through Optimized...

引用

8th international conference on Big data and Internet of Things

作者： Yan, Keyue Lam, Chi Fai Fong, Simon Marques, Joao Alexandre Lobo Song, Qun Qin, Huafeng Univ Macau Dept Comp & Informat Sci Taipa Macau Peoples R China Univ St Joseph Lab Appl Neurosci Macau Peoples R China Chongqing Technol & Business Univ Dept Artificial Intelligence Chongqing Key Lab Intelligent Percept & Blockchai Chongqing Peoples R China

ISBN: (纸本)9798400717529

Causal machine learning combines causal inference and machine learning to understand and utilize causal relationships in data. While traditional machine learning focuses on missions of prediction and pattern recognition, causal machine learning goes a step further by revealing causal relationships between variables. In this research, we employ the double machine learning method to identify variables in the gesture recognition problem where independent variables have causal relationships with the final gesture. These variables are then selected for further classification and analysis. By comparing this approach with traditional feature selection methods, we find that the variables selected using double machine learning are more useful for classification and yield excellent results across different machine learning classification models. This new double machine learning based approach provides a valuable reference for researchers during the feature selection stage.

关键词： Leap Motion Controller Hand Gesture Recognition Feature Selection Causal Effect Double machine learning

来源：评论

学校读者我要写书评

暂无评论

machine learning Models for Predicting "Left Without Being Seen" in Distributed Emergency Departments: A Comparative Study in Naples, Italy 8

Machine Learning Models for Predicting "Left Without Being S...

引用

8th international conference on Biomedical engineering and Applications (ICBEA)

作者： Fidecicchi, Andrea Santalucia, Ida Raiola, Eliana Majolo, Massimo Chiacchio, Michelangelo Romano, Maria Rosaria Triassi, Maria Marino, Marta Rosaria Scala, Arianna Univ Naples Federico II Dept Publ Hlth Naples Italy Univ Pavia Dept Publ Hlth Expt & Forens Med Pavia Italy Local Hlth Author Napoli 3 Sud Torre Del Greco Italy Univ Naples Federico II Interdept Ctr Res Healthcare Management & Innovat Dept Publ Hlth Naples Italy

ISBN: (纸本)9798350375305;9798350375299

Emergency departments (EDs) are challenged by overcrowding, which affects the quality of care and increases the rate of patients leaving without being seen (LWBS). The study aims to predict LWBS cases in Local Health Authority No. 3 in Naples, Italy, a distributed ED system, using machine learning (ML) models and compare its performance with single-center EDs. data from 53,761 patients at LHA No. 3, 83,739 at Hospital H1, and 77,607 at Hospital H2 from the year 2022 were analyzed. The dataset included gender, age, triage score, mode of arrival, and time of admission. machine learning algorithms such as Random Forest (RF), Support Vector machine (SVM), Naive Bayes (NB), and Logistic Regression (LR) were implemented using the KNIME Analytics platform. The primary outcome was LWBS. All ML models showed high accuracy rates above 90%. The RF model showed the highest accuracy (91.2%) and F-measure (95.3%). The study also revealed patterns in patient flow, most notably a peak in arrivals between 6:00 and 12:00. A balanced age distribution was observed, in contrast to the older patient demographics in previous studies. The ML models, particularly RF, were highly effective in predicting LWBS cases in a distributed ED system. This high predictive accuracy can contribute to the efficient allocation of ED resources and improve patient satisfaction, thereby addressing the problem of overcrowding.

关键词： Emergency Departments Overcrowding machine learning Random Forest Support Vector machine Naive Bayes Logistic Regression Left Without Being Seen Predictive Analytics Resource Allocation Patient Satisfaction Healthcare Quality Workflow Optimization

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：