30 research outputs found
NHS Big Data Intelligence on Blockchain Applications
No full textWith the exponentially increasing number of AI (Artificial intelligence) applications on Big Data being developed, AI cyber security defense becomes ever required. Blockchain technology invented in 2008 with BitCoin could be benefited alongside the customer of Big Data and so on. Following a rapid progress in its advance, this subject has recently become a hot discussion topic in the ICT (Information and communications technology) world. In this chapter, Big Data security is discussed from the beginning to the impact which could benefit IT engineers, ICT students and CS academic researchers. As a case study, because medical record is personally identifiable privacy information, it needs strictly access control security. Blockchain technology has the features of trustworthy cyber security, anti-fake, anti-alteration, integrity, immutability and transaction accounting transparency reputation, these made it a good candidate for being applied to NHS medical records. Currently Blockchain technology, as one of the most important smart technologies, had been very widely used in smart applications that could influence the world. An analysis on such topic is provided in this chapter
Spatial and temporal variation in elemental signatures of statoliths from the Patagonian longfin squid (Loligo gahi)
No full textAuthor Posting. © National Research Council Canada, 2004. This article is posted here by permission of National Research Council Canada for personal use, not for redistribution. The definitive version was published in Canadian Journal of Fisheries and Aquatic Sciences 61 (2004): 1212-1224, doi:10.1139/F04-075.We quantified elemental signatures in statoliths of 718 Patagonian longfin squid (Loligo gahi) collected in the vicinity of the Falkland Islands (southwest Atlantic) and at sites on the Patagonian Shelf and coastal Peru. All squid were assigned to a spawning cohort by size, spawning condition, and back-calculated spawning date based on daily increments in statoliths. The remaining statolith was then analyzed for six elemental ratios (Mg/Ca, Mn/Ca, Sr/Ca, Cd/Ca, Ba/Ca, and Pb/Ca) using high-resolution inductively coupled plasma mass spectrometry (ICP-MS). Elemental concentrations in the statoliths were broadly similar to other biogenic aragonites. Differences in Sr/Ca ratios in statoliths among geographic locations were generally consistent with a negative correlation between Sr/Ca and temperature. Variations in statolith Cd/Ca and Ba/Ca values confirmed that during winter months, the squid were foraging deeper in the water column. Both Mg/Ca and Mn/Ca ratios in statoliths decreased with squid size, probably corresponding to a decrease in the contribution of the organic component of the statolith. Elemental signatures in the statoliths of L. gahi varied significantly geographically and between spring- and autumn-spawned cohorts, which must therefore have spent significant portions of their life histories in different environments.The research was funded by the Falkland Islands Government
and was also supported in part by National Science
Foundation grants OCE-9871047 and OCE-0134998 to
S.R.T
An Automated Big Data Quality Anomaly Correction Framework Using Predictive Analysis
No full textBig data has emerged as a fundamental component in various domains, enabling organizations to extract valuable insights and make informed decisions. However, ensuring data quality is crucial for effectively using big data. Thus, big data quality has been gaining more attention in recent years by researchers and practitioners due to its significant impact on decision-making processes. However, existing studies addressing data quality anomalies often have a limited scope, concentrating on specific aspects such as outliers or inconsistencies. Moreover, many approaches are context-specific, lacking a generic solution applicable across different domains. To the best of our knowledge, no existing framework currently automatically addresses quality anomalies comprehensively and generically, considering all aspects of data quality. To fill the gaps in the field, we propose a sophisticated framework that automatically corrects big data quality anomalies using an intelligent predictive model. The proposed framework comprehensively addresses the main aspects of data quality by considering six key quality dimensions: Accuracy, Completeness, Conformity, Uniqueness, Consistency, and Readability. Moreover, the framework is not correlated to a specific field and is designed to be applicable across various areas, offering a generic approach to address data quality anomalies. The proposed framework was implemented on two datasets and has achieved an accuracy of 98.22%. Moreover, the results have shown that the framework has allowed the data quality to be boosted to a great score, reaching 99%, with an improvement rate of up to 14.76% of the quality score
Adaptive, Privacy-Enhanced Real-Time Fraud Detection in Banking Networks Through Federated Learning and VAE-QLSTM Fusion
No full textIncreased digital banking operations have brought about a surge in suspicious activities, necessitating heightened real-time fraud detection systems. Conversely, traditional static approaches encounter challenges in maintaining privacy while adapting to new fraudulent trends. In this paper, we provide a unique approach to tackling those challenges by integrating VAE-QLSTM with Federated Learning (FL) in a semi-decentralized architecture, maintaining privacy alongside adapting to emerging malicious behaviors. The suggested architecture builds on the adeptness of VAE-QLSTM to capture meaningful representations of transactions, serving in abnormality detection. On the other hand, QLSTM combines quantum computational capability with temporal sequence modeling, seeking to give a rapid and scalable method for real-time malignancy detection. The designed approach was set up through TensorFlow Federated on two real-world datasets—notably IEEE-CIS and European cardholders—outperforming current strategies in terms of accuracy and sensitivity, achieving 94.5% and 91.3%, respectively. This proves the potential of merging VAE-QLSTM with FL to address fraud detection difficulties, ensuring privacy and scalability in advanced banking networks
Real-Time Online Banking Fraud Detection Model by Unsupervised Learning Fusion
No full textDigital trades and payments are becoming increasingly popular, as they typically entail monetary transactions. This not only makes electronic transactions more convenient for the end customer, but it also raises the likelihood of fraud. An adequate fraud detection system with a cutting-edge model is critical to minimizing fraud costs. Identifying fraud at the ideal time entails establishing and setting up ubiquitous systems to consume and analyze massive amounts of streaming data. Recent advances in data analytics methods and introducing open-source technology for big data storage and processing opened new options for detecting fraud. This study aims to tackle this critical issue by providing a newly real-time e-transaction fraud detection schema that consolidates the advantages of both unsupervised learners, including autoencoder and extended isolation forests, with cutting-edge big data gadgets such as Spark streaming and sparkling water. It addresses the shortage of non-fraudulent instances and handles the excessive dimension of the set of features. On two real-world transactional datasets, we assess our suggested technique. Compared with other current fraud identification systems, our methodology delivers an elevated accuracy yield of 99%. Furthermore, it outperforms state-of-the-art approaches in reliably identifying fraudulent samples. Doi: 10.28991/HIJ-2024-05-01-014 Full Text: PD
Securing EHRs With a Novel Token-Based and PPoS Blockchain Methodology
No full textBlockchain technology is vital in strengthening the security of private information, particularly in the healthcare sector. Its features, such as confidentiality, decentralization, security and privacy, address challenges traditional healthcare systems face, such as phishing, denial of service and identity theft attacks. In this regard, our research paper presents a security solution specifically tailored for healthcare applications. This solution integrates decentralized identity management (DIDs) for identity verification, employs the advanced ChaCha20-Poly1305 encryption algorithm to ensure data confidentiality, and utilizes a token-based mechanism for immutable record keeping. Furthermore, it incorporates a pure proof of stake (PPoS) consensus mechanism to enhance system security while optimizing efficiency. This comprehensive and scalable system showcases improvements in cost effectiveness, time efficiency of an average of 6,5 seconds and overall data protection compared to traditional approaches used in healthcare data security
