International Journal on Artificial Intelligence Tools最新文献_第6页

Metaheuristic Algorithms in Optimal Power Flow Analysis: A Qualitative Systematic Review 最优潮流分析中的元启发式算法:定性系统综述

IF 1.1 4区计算机科学

International Journal on Artificial Intelligence Tools Pub Date : 2023-02-23 DOI: 10.1142/s021821302350032x

M. M. Farag, R.A. Alhamad, A. Nassif

引用次数: 0

An Explainable AI Model for ICU Admission Prediction of COVID-19 Patients 新冠肺炎患者ICU入院预测的可解释人工智能模型

IF 1.1 4区计算机科学

International Journal on Artificial Intelligence Tools Pub Date : 2023-02-23 DOI: 10.1142/s0218213023500318

E. Dazea, P. Stefaneas

引用次数: 0

Deep Learning Approach for Multi-class Semantic Segmentation of UAV Images 无人机图像多类语义分割的深度学习方法

IF 1.1 4区计算机科学

International Journal on Artificial Intelligence Tools Pub Date : 2023-02-23 DOI: 10.1142/s0218213023500331

A. Chouhan, D. Chutia, S. Aggarwal

引用次数: 0

Data Expansion Approach with Attention Mechanism for Learning with Noisy Labels 基于注意机制的带噪声标签学习数据扩展方法

IF 1.1 4区计算机科学

International Journal on Artificial Intelligence Tools Pub Date : 2023-02-14 DOI: 10.1142/s0218213023500276

Yuichiro Nomura, Takio Kurita

{"title":"Data Expansion Approach with Attention Mechanism for Learning with Noisy Labels","authors":"Yuichiro Nomura, Takio Kurita","doi":"10.1142/s0218213023500276","DOIUrl":"https://doi.org/10.1142/s0218213023500276","url":null,"abstract":"In recent years, the development of deep learning has contributed to various areas of machine learning. However, deep learning requires a huge amount of data to train the model, and data collection techniques such as web crawling can easily generate incorrect labels. If a training dataset has noisy labels, the generalization performance of deep learning significantly decreases. Some recent works have successfully divided the dataset into samples with clean labels and ones with noisy labels. In light of these studies, we propose a novel data expansion framework to robustly train the models on noisy labels with the attention mechanisms. First, our method trains a deep learning model with the sample selection approach and saves the samples selected as clean at the end of training. The original noisy dataset is then extended with the selected samples and the model is trained on the dataset again. To prevent over-fitting and allow the model to learn different patterns of the selected samples, we leverage the attention mechanism of deep learning to modify the representation of the selected samples. We evaluated our method with synthetic noisy labels on CIFAR-10 and CUB-200-2011 and real-world dataset Clothing1M. Our method obtained comparable results to baseline CNNs and state-of-the-art methods.","PeriodicalId":50280,"journal":{"name":"International Journal on Artificial Intelligence Tools","volume":"90 1","pages":"2350027:1-2350027:19"},"PeriodicalIF":1.1,"publicationDate":"2023-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83906081","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Efficient Multimodal Biometric Recognition for Secure Authentication Based on Deep Learning Approach 基于深度学习方法的高效多模态生物特征安全认证

IF 1.1 4区计算机科学

International Journal on Artificial Intelligence Tools Pub Date : 2023-02-04 DOI: 10.1142/s0218213023400171

V. Rajasekar, M. Saracevic, M. Hassaballah, D. Karabašević, D. Stanujkić, M. Zajmovic, Umair Ullah Tariq, P. Jayapaul

引用次数: 3

Alternative to Buy-and-Hold: Predicting Indices Direction and Improving Returns Using a Novel Hybrid LSTM Model 买入和持有的替代方案：使用一种新的混合LSTM模型预测指数方向和提高收益

IF 1.1 4区计算机科学

International Journal on Artificial Intelligence Tools Pub Date : 2023-01-18 DOI: 10.1142/s0218213023500288

M. Beniwal, Anuradha Singh, N. Kumar

引用次数: 0

Reservoir Computing for Solving Ordinary Differential Equations 求解常微分方程的油藏计算

IF 1.1 4区计算机科学

International Journal on Artificial Intelligence Tools Pub Date : 2023-01-18 DOI: 10.1142/s0218213023500306

M. Mattheakis, H. Joy, P. Protopapas

引用次数: 0

Improving McDiarmid Tree Performance for Predicting Heart Disease from Data Streams with Missing and Meaningless Values 从具有缺失和无意义值的数据流中改进McDiarmid树预测心脏病的性能

IF 1.1 4区计算机科学

International Journal on Artificial Intelligence Tools Pub Date : 2023-01-18 DOI: 10.1142/s021821302350029x

M. Benllarch, S. E. Hadaj, M. Benhaddi

引用次数: 0

Text2Color Networks: Deep Learning Models for Color Generation from Compositional Color Descriptions Text2Color网络:从成分颜色描述中生成颜色的深度学习模型

IF 1.1 4区计算机科学

International Journal on Artificial Intelligence Tools Pub Date : 2023-01-17 DOI: 10.1142/s0218213023500264

K. Jyothi, M. Okade

引用次数: 0

Learning from Highly Imbalanced Big Data with Label Noise 从带有标签噪声的高度不平衡大数据中学习

IF 1.1 4区计算机科学

International Journal on Artificial Intelligence Tools Pub Date : 2023-01-17 DOI: 10.1142/s0218213023600035

J. M. Johnson, Robert K. L. Kennedy, T. Khoshgoftaar

引用次数: 0