Evaluation of the benefits of using a backward chaining decision support expert system for local flood forecasting and warning

Zhang, Xiaoyin; Moynihan, Gary P.; Ernest, Andrew; Gutenson, Joseph L.

doi:10.1111/exsy.12261

Cited by 9 publications

(15 citation statements)

References 33 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…How to quantify the performance of tunnels using the deterioration of these factors is open for discussion. A vast amount of research (Bui, Nguyen, Chou, Xuan, & Ngo, 2018; X. Y. Zhang, Moynihan, Ernest, & Gutenson, 2018) shows the effectiveness of expert systems in such complexity situation. We believe that expert systems have broad application prospects in evaluating the health condition of metro tunnels under the influence of multiple factors, before a more effective multifactor analysis method is developed, and thus, the expert‐based TSR system is adopted in this study.…”

Section: Related Workmentioning

confidence: 99%

Tunnel condition assessment via cloud model‐based random forests and self‐training approach

Zhu

Guo

et al. 2020

Computer aided Civil Eng

View full text Add to dashboard Cite

To proactively assess the losses caused by the deterioration of metro tunnels during the operational period, a new method, the cloud model‐based random forests (CRFs), is proposed to discuss the inconsistencies induced by mapping the monitoring data into the health rate of the metro tunnels. On top of the CRF, a self‐training framework is introduced to improve the predictive accuracy and the stability of the CRF by adding more unlabeled data. The main contribution of this paper is proposing a novel CRF model along with a semisupervised approach to overcome the inapplicability of the random forests algorithm in an inconsistent small database, and to reduce the substantial time and cost for expert annotation. The results indicate that (1) the proposed CRF achieves higher accuracy and stability than random forests in predictions; (2) the CRF outperforms the other state‐of‐the‐art methods even in a small database; (3) the self‐training improved CRF keeps highly precise when the ratio of labeled to unlabeled data is no less than 1:11.4. In this study, the suggested ratio of labeled and unlabeled data is no lower than 1:5.7 to reduce the risk of wrongly forecasting a seriously damaged tunnel section as a slightly damaged tunnel section.

show abstract

Section: Related Workmentioning

confidence: 99%

Tunnel condition assessment via cloud model‐based random forests and self‐training approach

Zhu

Guo

et al. 2020

Computer aided Civil Eng

View full text Add to dashboard Cite

show abstract

“…[ 29,37,38,48,[51][52][53][54][55] River or flood water, level observed [36,38,56] River or flood water, level forecasted [32,[57][58][59][60][61] Flood inundation extent Establish a spatial representation of floods to understand the impacted area.…”

Section: Intelligence On Flood Hazardsmentioning

confidence: 99%

“…[35,38,50,66,69,70,[76][77][78] Historical flood events and water level Understand inundation levels and impact caused by past flood events and extrapolate this knowledge to an emerging flood situation. [53,56,79] Flood propagation time/lead time Calculate lead time (travel time) of floods to plan early warnings, evacuation, and response, e.g., upstream to downstream or flood arrival time based on predicted or actual rainfall.…”

Section: Intelligence On Flood Hazardsmentioning

confidence: 99%

Advanced Technologies for Offering Situational Intelligence in Flood Warning and Response Systems: A Literature Review

Samansiri

Fernando

Ingirige

2022

Water

View full text Add to dashboard Cite

Deaths and property damage from floods have increased drastically in the past two decades due to various reasons such as increased populations, unplanned developments, and climate change. Such losses from floods can be reduced by issuing timely early warnings and through effective response mechanisms based on situational intelligence during emerging flood situations. This paper presents the outcome of a literature review that was conducted to identify the types and sources of the intelligence required for flood warning and response processes as well as the technology solutions that can be used for offering such intelligence. Twenty-seven different types of intelligence are presented together with the technologies that can be used to extract such intelligence. Furthermore, a conceptual architecture that illustrates how relevant technology solutions can be used to extract intelligence at various stages of a flood cycle for decision-making in issuing early warnings and planning responses is presented.

show abstract

“…"Knowledge Base and Presentation Layer" and the "Knowledge Processing Layer". For the sake of a proof of concept and exemplification, the architecture python knowledge engine (PyKE) has been used for the artificial intelligence in the system [46,47]. PyKE uses fact-bases and rule-bases as part of the knowledge base in the system with the expert system engine processes for bringing in the intelligence in the system.…”

Section: Smart Aaa Agent Architecturementioning

confidence: 99%

Smart and Adaptive Architecture for a Dedicated Internet of Things Network Comprised of Diverse Entities: A Proposal and Evaluation

Singh¹,

Ali²,

Lundberg³

2022

Sensors

View full text Add to dashboard Cite

Advances in 5G and the Internet of Things (IoT) have to cater to the diverse and varying needs of different stakeholders, devices, sensors, applications, networks, and access technologies that come together for a dedicated IoT network for a synergistic purpose. Therefore, there is a need for a solution that can assimilate the various requirements and policies to dynamically and intelligently orchestrate them in the dedicated IoT network. Thus we identify and describe a representative industry-relevant use case for such a smart and adaptive environment through interviews with experts from a leading telecommunication vendor. We further propose and evaluate candidate architectures to achieve dynamic and intelligent orchestration in such a smart environment using a systematic approach for architecture design and by engaging six senior domain and IoT experts. The candidate architecture with an adaptive and intelligent element (“Smart AAA agent”) was found superior for modifiability, scalability, and performance in the assessments. This architecture also explores the enhanced role of authentication, authorization, and accounting (AAA) and makes the base for complete orchestration. The results indicate that the proposed architecture can meet the requirements for a dedicated IoT network, which may be used in further research or as a reference for industry solutions.

show abstract

Evaluation of the benefits of using a backward chaining decision support expert system for local flood forecasting and warning

Cited by 9 publications

References 33 publications

Tunnel condition assessment via cloud model‐based random forests and self‐training approach

Tunnel condition assessment via cloud model‐based random forests and self‐training approach

Advanced Technologies for Offering Situational Intelligence in Flood Warning and Response Systems: A Literature Review

Smart and Adaptive Architecture for a Dedicated Internet of Things Network Comprised of Diverse Entities: A Proposal and Evaluation

Contact Info

Product

Resources

About