Zobrazeno 1 - 10
of 666
pro vyhledávání: '"Taghi M. Khoshgoftaar"'
Publikováno v:
Journal of Big Data, Vol 11, Iss 1, Pp 1-20 (2024)
Abstract OCR2SEQ represents an innovative advancement in Optical Character Recognition (OCR) technology, leveraging a multi-modal generative augmentation strategy to overcome traditional limitations in OCR systems. This paper introduces OCR2SEQ’s u
Externí odkaz:
https://doaj.org/article/bcfa728aeb4e41c6a4c2023e9c0de0a9
Publikováno v:
Journal of Big Data, Vol 11, Iss 1, Pp 1-16 (2024)
Abstract In the context of high-dimensional credit card fraud data, researchers and practitioners commonly utilize feature selection techniques to enhance the performance of fraud detection models. This study presents a comparison in model performanc
Externí odkaz:
https://doaj.org/article/4939df3b3a7e4b0a838189d2e8a7897b
Publikováno v:
Journal of Big Data, Vol 11, Iss 1, Pp 1-22 (2024)
Abstract Acquiring labeled datasets often incurs substantial costs primarily due to the requirement of expert human intervention to produce accurate and reliable class labels. In the modern data landscape, an overwhelming proportion of newly generate
Externí odkaz:
https://doaj.org/article/977d85c21b024c07afbcf3f61c5af59b
Autor:
Safak Kayikci, Taghi M. Khoshgoftaar
Publikováno v:
Journal of Big Data, Vol 11, Iss 1, Pp 1-29 (2024)
Abstract Blockchain and machine learning are two rapidly growing technologies that are increasingly being used in various industries. Blockchain technology provides a secure and transparent method for recording transactions, while machine learning en
Externí odkaz:
https://doaj.org/article/7ae353764cfd4ea4b093ca146b9fa553
Publikováno v:
Journal of Big Data, Vol 11, Iss 1, Pp 1-41 (2024)
Abstract In the domain of Medicare insurance fraud detection, handling imbalanced Big Data and high dimensionality remains a significant challenge. This study assesses the combined efficacy of two data reduction techniques: Random Undersampling (RUS)
Externí odkaz:
https://doaj.org/article/9d24166ba09043d38c384d2db436fbe9
Publikováno v:
Journal of Big Data, Vol 11, Iss 1, Pp 1-37 (2024)
Abstract The tasks of few-shot, one-shot, and zero-shot learning—or collectively “low-shot learning” (LSL)—at first glance are quite similar to the long-standing task of class imbalanced learning; specifically, they aim to learn classes for w
Externí odkaz:
https://doaj.org/article/eb6529f298d146ba81e4f6a4cc62f21f
Publikováno v:
Journal of Big Data, Vol 10, Iss 1, Pp 1-31 (2023)
Abstract As a means of building explainable machine learning models for Big Data, we apply a novel ensemble supervised feature selection technique. The technique is applied to publicly available insurance claims data from the United States public hea
Externí odkaz:
https://doaj.org/article/89c068cfa9654be2a0a8a7368f4bcc4f
Publikováno v:
Journal of Big Data, Vol 10, Iss 1, Pp 1-16 (2023)
Abstract Research into machine learning methods for fraud detection is of paramount importance, largely due to the substantial financial implications associated with fraudulent activities. Our investigation is centered around the Credit Card Fraud Da
Externí odkaz:
https://doaj.org/article/5bc138e6b6b14476a2aeb338f4e2b686
Publikováno v:
Journal of Big Data, Vol 10, Iss 1, Pp 1-13 (2023)
Abstract The yearly increase in incidents of credit card fraud can be attributed to the rapid growth of e-commerce. To address this issue, effective fraud detection methods are essential. Our research focuses on the Credit Card Fraud Detection Datase
Externí odkaz:
https://doaj.org/article/04017e2602d24b4ea60a59b568f0a51f
Publikováno v:
Journal of Big Data, Vol 10, Iss 1, Pp 1-20 (2023)
Abstract Fraud datasets often times lack consistent and accurate labels, and are characterized by having high class imbalance where the number of fraudulent examples are far fewer than those of normal ones. Machine learning designed for effectively d
Externí odkaz:
https://doaj.org/article/ea6e81b0491c4fb792cc9016f1ecfc13