Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Ismail Alarab"'
Autor:
Ismail Alarab, Simant Prakoonwit
Publikováno v:
Data Science and Management, Vol 5, Iss 2, Pp 66-76 (2022)
Cryptocurrency blockchain data encounter a class-imbalance problem due to only a few known labels of illicit or fraudulent activities in the blockchain network. For this purpose, we seek to compare various resampling methods applied to two highly imb
Externí odkaz:
https://doaj.org/article/ad1eadf7269b47cda9c721f8ec435e80
Autor:
Ismail Alarab, Simant Prakoonwit
Publikováno v:
Soft Computing. 27:7925-7937
Uncertainty estimation has received momentous consideration in applied machine learning to capture model uncertainty. For instance, the Monte-Carlo dropout method (MC-dropout), an approximated Bayesian approach, has gained intensive attention in prod
Autor:
Ismail Alarab, Simant Prakoonwit
Publikováno v:
Neural Processing Letters. 55:689-707
Elliptic data—one of the largest Bitcoin transaction graphs—has admitted promising results in many studies using classical supervised learning and graph convolutional network models for anti-money laundering. Despite the promising results provide
Autor:
Weilai Xu, Ismail Alarab, Charlie Lloyd-Buckingham, Steve Bowden, Benjamin Noer, Fred Charles, Simant Prakoonwit, Andrew Callaway, Shelly Ellis, Chris Jones
Publikováno v:
2022 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR).
Autor:
Ismail Alarab, Simant Prakoonwit
We propose a novel method to capture data points near decision boundary in neural network that are often referred to a specific type of uncertainty. In our approach, we sought to perform uncertainty estimation based on the idea of adversarial attack
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::156d2e805f634cff33e69580731748d2
https://eprints.bournemouth.ac.uk/36455/7/Alarab-Prakoonwit2022_Article_AdversarialAttackForUncertaint.pdf
https://eprints.bournemouth.ac.uk/36455/7/Alarab-Prakoonwit2022_Article_AdversarialAttackForUncertaint.pdf
Publikováno v:
Neural Processing Letters. 53:1001-1011
The past few years have witnessed the resurgence of uncertainty estimation generally in neural networks. Providing uncertainty quantification besides the predictive probability is desirable to reflect the degree of belief in the model’s decision ab
Publikováno v:
International Series in Operations Research & Management Science ISBN: 9783030704773
Blockchain is a new technology resulting from a continuous research on consensus mechanisms to ensure the integrity of a distributed shared replica. It represents a data structure built on a hash function and distributed among the various participant
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0487e1ffd356b75fa697730a9a3294a8
https://doi.org/10.1007/978-3-030-70478-0_1
https://doi.org/10.1007/978-3-030-70478-0_1
Publikováno v:
International Series in Operations Research & Management Science ISBN: 9783030704773
The use of the Internet of Things (IoT) in the healthcare sector has shown to be a promising solution to reduce the workload of doctors and provide better service to patients. However, shared data may be subject to theft or misuse due to the security
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6581e6342cb91a28165a6000580c819a
https://doi.org/10.1007/978-3-030-70478-0_3
https://doi.org/10.1007/978-3-030-70478-0_3
Publikováno v:
IECC 2020: 2nd International Electronic Communication Conference
The Smart Distributed Ledger (aka blockchain) has attracted much attention in recent years. According to the European Parliament, this technology has the potential to change the lives of many people. The blockchain is a data structure built upon a ha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d92004e62b55032843063ca4c7425eec
https://eprints.bournemouth.ac.uk/34651/1/BRIANTheChainAFastSecureAndParallelTreatmentOfTransactions.pdf
https://eprints.bournemouth.ac.uk/34651/1/BRIANTheChainAFastSecureAndParallelTreatmentOfTransactions.pdf
Graph networks are extensively used as an essential framework to analyse the interconnections between transactions and capture illicit behaviour in Bitcoin blockchain. Due to the complexity of Bitcoin transaction graph, the prediction of illicit tran
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::37817cc046f9052ba3d73e1446342e8d
https://eprints.bournemouth.ac.uk/34650/1/BRIANCompetenceOfGraphConvolutionalNetworksForAntiMoneyLaunderingInBitcoinBlockchain.pdf
https://eprints.bournemouth.ac.uk/34650/1/BRIANCompetenceOfGraphConvolutionalNetworksForAntiMoneyLaunderingInBitcoinBlockchain.pdf