Big Data-Enhanced Risk Management

Bischof, Christian; Wilfinger, Daniela

doi:10.21278/tof.43206

Cited by 4 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this article, we demonstrate how PAI in combination with data science and AI can contribute to the reduction of nuclear risks worldwide: analysts will have access to a finer level of details on descriptive analytics for increased situational awareness, leading to a higher level of confidence in insights and analyses at the scale used for real-time informed decisionmaking. This aligns with previous work highlighting the value of data analytics and open-source information for nuclear security, safeguards, and risk reduction [6], [9], [38]- [41]. We presented our NLP and DL approaches to automatically learn dynamically evolving proliferation expertise representations from open data sources that have extreme volume, velocity, and complexity-terabytes of unstructured scientific publications over the last five years-focusing on six countries of interest-Russia, North Korea, Pakistan, India, Iran, and the United States.…”

Section: Discussionsupporting

confidence: 89%

Learning Global Proliferation Expertise Evolution Using AI-Driven Analytics and Public Information

Glenski

Ayton

Soni

et al. 2022

IEEE Trans. Nucl. Sci.

View full text Add to dashboard Cite

Detecting and anticipating global proliferation expertise and capability evolution from unstructured, noisy, and incomplete public data streams is a highly desired, but extremely challenging task. In this article, we present our pioneering data-driven approach to support the non-proliferation mission to detect and explain the evolution of proliferation expertise and capability development globally from terabytes of publicly available information (PAI), focusing on our knowledge extraction pipeline and descriptive analytics. We first discuss how we fuse nine open-source data streams, including multilingual data, to convert 4 TB of unstructured data to structured knowledge and encode dynamically evolving proliferation expertise representations-content and context graphs. For this, we rely on natural language processing (NLP) and deep learning (DL) models to perform information extraction, topic modeling, and distributed text representation (aka embedding) learning. We then present interactive, usable, and explainable descriptive analytics to refine domain knowledge and present it in a humanunderstandable form. Finally, we introduce future work avenues that will leverage our dynamic knowledge representations and descriptive analytics to enable predictive and prescriptive inferences to achieve real-time domain understanding and contextual reasoning about global proliferation expertise and capability evolution.

show abstract

Section: Discussionsupporting

confidence: 89%

Learning Global Proliferation Expertise Evolution Using AI-Driven Analytics and Public Information

Glenski

Ayton

Soni

et al. 2022

IEEE Trans. Nucl. Sci.

View full text Add to dashboard Cite

show abstract

“…The risk of data manipulation, security and hidden costs were also identified in the study of Guha and Kumar (2017) that explored the emergence of big data research in the field of operations management. In the aspect of big data, Bischof and Wilfinger (2019) opined that material, financial and information risks are some of the crucial risk factors associated with this digital technology. In the study of Digmayer and Jakobs (2018), some critical risks associated with the 4IR technologies include issues relating to interconnection of systems, increase data generation, changing demands placed on employees, data security and safety, job loss, etc.…”

Section: Risk Of Digitalisation In Constructionmentioning

confidence: 99%

Unravelling the risks of construction digitalisation in developing countries

Aghimien

Aigbavboa

Meno

et al. 2021

View full text Add to dashboard Cite

Purpose This study aims to present the result of an assessment of the risk of construction digitalisation with a view to sensitising and preparing construction organisations for unforeseen issues that might arise in the course of their digital transformation. Design/methodology/approach The study took a post-positivist stance through a quantitative research approach. A survey of construction professionals actively involved in construction projects in South Africa was conducted using a structured questionnaire. The analysis of the data gathered was done using mean item scores, Kruskal–Wallis H test, exploratory factor analysis (EFA) and structural equation modelling (SEM). Findings EFA revealed five principal risk factors (human and financial, technological, legal and security, operations and socioeconomic risk factors) associated with the digitalisation of construction organisations. However, SEM revealed that four out of these risk components have significant direct relationships with some selected digitalisation outcomes. These significant risk factors are technology, legal and security issues, operations and socioeconomic issues. Originality/value This study provides practical insight into the risk inherent in construction digitalisation, and its result can help organisations seeking to be digitally transformed make informed decisions. Theoretically, the study reveals the risks associated with construction digitalisation – an aspect that has not gained significant attention in the current fourth industrial revolution discourse. Therefore, its findings can form a basis for future studies on the risk of digitalising construction organisations.

show abstract

“…Все эти данные необходимо извлекать и обрабатывать, чтобы сохранить трафик ввода-вывода из-за медленной вычислительной мощности. [5].…”

Section: глава 1 введениеunclassified