Pub Date : 2023-02-23DOI: 10.1142/s021821302350032x
M. M. Farag, R.A. Alhamad, A. Nassif
{"title":"Metaheuristic Algorithms in Optimal Power Flow Analysis: A Qualitative Systematic Review","authors":"M. M. Farag, R.A. Alhamad, A. Nassif","doi":"10.1142/s021821302350032x","DOIUrl":"https://doi.org/10.1142/s021821302350032x","url":null,"abstract":"","PeriodicalId":50280,"journal":{"name":"International Journal on Artificial Intelligence Tools","volume":" ","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44468997","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}
Pub Date : 2023-02-23DOI: 10.1142/s0218213023500318
E. Dazea, P. Stefaneas
{"title":"An Explainable AI Model for ICU Admission Prediction of COVID-19 Patients","authors":"E. Dazea, P. Stefaneas","doi":"10.1142/s0218213023500318","DOIUrl":"https://doi.org/10.1142/s0218213023500318","url":null,"abstract":"","PeriodicalId":50280,"journal":{"name":"International Journal on Artificial Intelligence Tools","volume":" ","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46621316","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}
Pub Date : 2023-02-23DOI: 10.1142/s0218213023500331
A. Chouhan, D. Chutia, S. Aggarwal
{"title":"Deep Learning Approach for Multi-class Semantic Segmentation of UAV Images","authors":"A. Chouhan, D. Chutia, S. Aggarwal","doi":"10.1142/s0218213023500331","DOIUrl":"https://doi.org/10.1142/s0218213023500331","url":null,"abstract":"","PeriodicalId":50280,"journal":{"name":"International Journal on Artificial Intelligence Tools","volume":" ","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49491108","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}
Pub Date : 2023-02-14DOI: 10.1142/s0218213023500276
Yuichiro Nomura, Takio Kurita
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.
{"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}
Pub Date : 2023-02-04DOI: 10.1142/s0218213023400171
V. Rajasekar, M. Saracevic, M. Hassaballah, D. Karabašević, D. Stanujkić, M. Zajmovic, Umair Ullah Tariq, P. Jayapaul
{"title":"Efficient Multimodal Biometric Recognition for Secure Authentication Based on Deep Learning Approach","authors":"V. Rajasekar, M. Saracevic, M. Hassaballah, D. Karabašević, D. Stanujkić, M. Zajmovic, Umair Ullah Tariq, P. Jayapaul","doi":"10.1142/s0218213023400171","DOIUrl":"https://doi.org/10.1142/s0218213023400171","url":null,"abstract":"","PeriodicalId":50280,"journal":{"name":"International Journal on Artificial Intelligence Tools","volume":"63 1","pages":"2340017:1-2340017:16"},"PeriodicalIF":1.1,"publicationDate":"2023-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74126021","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}
Pub Date : 2023-01-18DOI: 10.1142/s0218213023500288
M. Beniwal, Anuradha Singh, N. Kumar
{"title":"Alternative to Buy-and-Hold: Predicting Indices Direction and Improving Returns Using a Novel Hybrid LSTM Model","authors":"M. Beniwal, Anuradha Singh, N. Kumar","doi":"10.1142/s0218213023500288","DOIUrl":"https://doi.org/10.1142/s0218213023500288","url":null,"abstract":"","PeriodicalId":50280,"journal":{"name":"International Journal on Artificial Intelligence Tools","volume":" ","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45927406","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}
Pub Date : 2023-01-18DOI: 10.1142/s0218213023500306
M. Mattheakis, H. Joy, P. Protopapas
{"title":"Reservoir Computing for Solving Ordinary Differential Equations","authors":"M. Mattheakis, H. Joy, P. Protopapas","doi":"10.1142/s0218213023500306","DOIUrl":"https://doi.org/10.1142/s0218213023500306","url":null,"abstract":"","PeriodicalId":50280,"journal":{"name":"International Journal on Artificial Intelligence Tools","volume":"2004 1","pages":"2350030:1-2350030:17"},"PeriodicalIF":1.1,"publicationDate":"2023-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88332386","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}
Pub Date : 2023-01-18DOI: 10.1142/s021821302350029x
M. Benllarch, S. E. Hadaj, M. Benhaddi
{"title":"Improving McDiarmid Tree Performance for Predicting Heart Disease from Data Streams with Missing and Meaningless Values","authors":"M. Benllarch, S. E. Hadaj, M. Benhaddi","doi":"10.1142/s021821302350029x","DOIUrl":"https://doi.org/10.1142/s021821302350029x","url":null,"abstract":"","PeriodicalId":50280,"journal":{"name":"International Journal on Artificial Intelligence Tools","volume":" ","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44915070","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}
Pub Date : 2023-01-17DOI: 10.1142/s0218213023500264
K. Jyothi, M. Okade
{"title":"Text2Color Networks: Deep Learning Models for Color Generation from Compositional Color Descriptions","authors":"K. Jyothi, M. Okade","doi":"10.1142/s0218213023500264","DOIUrl":"https://doi.org/10.1142/s0218213023500264","url":null,"abstract":"","PeriodicalId":50280,"journal":{"name":"International Journal on Artificial Intelligence Tools","volume":" ","pages":""},"PeriodicalIF":1.1,"publicationDate":"2023-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42102820","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}
Pub Date : 2023-01-17DOI: 10.1142/s0218213023600035
J. M. Johnson, Robert K. L. Kennedy, T. Khoshgoftaar
{"title":"Learning from Highly Imbalanced Big Data with Label Noise","authors":"J. M. Johnson, Robert K. L. Kennedy, T. Khoshgoftaar","doi":"10.1142/s0218213023600035","DOIUrl":"https://doi.org/10.1142/s0218213023600035","url":null,"abstract":"","PeriodicalId":50280,"journal":{"name":"International Journal on Artificial Intelligence Tools","volume":"47 1","pages":"2360003:1-2360003:20"},"PeriodicalIF":1.1,"publicationDate":"2023-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75246189","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：