Investigation into the relationship between chlorine decay and water distribution parameters using data driven methods

Gibbs, Matthew S.; Morgan, Nicolas; Maier, Holger R.; Dandy, Graeme C.; Nixon, John B.; Holmes, Mike

doi:10.1016/j.mcm.2006.01.007

Cited by 74 publications

(46 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The process based models have extensive range of application but developing the process based models assumes very good understanding of the process and also accurate and extensive data in order to produce the model (Gibs et al, 2006). In this paper Bromilow's time cost model is used as process based model.…”

Section: Implementation Of the Process Based Modelmentioning

confidence: 99%

Trust in a viable real estate economy with disruption and blockchain

Veuger

2018

121

View full text Add to dashboard Cite

Centre for Real Estate -in daily speaking 'CEJ' -is the new centralized real estate centre in the Danish public authority, Capital Region of Denmark. Since 1 January 2017, more than 700 employees have been part of the centre, which has the task of creating, operating and optimizing the buildings owned by the regional authority. The trusted FM partnerThe Capital Region is responsible of hospitals, mental health services, research, disability services, social services and solving environmental tasks. The building stock is approx. 2 million m 2 with a portfolio consisting of more than 750 single buildings at more than 70 locations. The strategic ambition in CEJ is to become the trusted partner for the regions core businesses and not as de facto the default FM organization. In this article we share our first experiences as inspiration to others who are considering a change process from decentral to central facilities management. The preparationsThe corporate management decided in 2015 that the preparations of a centre for real estate should take place in 2016 and 1 of January 2017 was set as the formal opening day. Mogens Kornbo started as CEO of CEJ the 1. March 2016 and during the spring, summer and fall the contours of CEJ started to settle. The centre should be a real estate and facilities management centre, the hospitals etc. should hand over responsibilities together with employees and budgets and a process was started to prepare and motivate the 720 employees who was about to change their organizational association and become the vast majority of the CEJ employees. An important part of the preparations was the constellation of the organizational structure. It consists of a CEO and deputy with representation in the corporate management, supported by administrative staff and 5 units of  System and processes  Planning and building projects  Operation and technique  Energy and environment  Logistics and supply chain The REFM scopeCEJ´s is set out to be a Real Estate FM (REFM) centre that unites ownership, investment and operational optimization in one and the same organization. The responsibilities are in general the physical environment and the technical services related to operation of buildings including: indoor and outdoor building maintenance, technical service, outdoor areas, fire and safety, indoor environment, waste handling parking and environment. In the future we might grow with other FM services, but currently cleaning, catering, receptions, guard etc. is not included in our responsibilities. These FM tasks remain for the time being in the core business organizations. Corporate economy, IKT and HR on are also not the responsibility of CEJ, as the region has other centres with this as their resort. 9The financial basisThe economic negotiations were challenging and they still are. Top management at the hospitals accepted or even supported the idea of a central real estate organization, but like in all other situations where resources are limited; there were at times hard negotiations about transfer...

show abstract

Section: Implementation Of the Process Based Modelmentioning

confidence: 99%

Trust in a viable real estate economy with disruption and blockchain

Veuger

2018

121

View full text Add to dashboard Cite

show abstract

“…Another technique is to use and generate a scree plot of the percentage contribution of each k t h PC and to visually identify an optimal value of k (Fodor, 2002). PCA has been used as the basis for IVS for the development of ANN models (see, for example, Olsson et al (2004), Gibbs et al (2006), and Bowden (2003)). However, the mixing of input variables is assumed to be linear, as is the relationship between principal components and the output.…”

Section: Principal Component Analysismentioning

confidence: 99%

Review of Input Variable Selection Methods for Artificial Neural Networks

May¹,

Dandy²,

Maier³

2011

Artificial Neural Networks - Methodological Advances and Biomedical Applications

247

163

View full text Add to dashboard Cite

“…Regression techniques have been used for decades with some success in water distribution problems (Gibbs et al 2006). Artificial Neural Networks (ANNs) have been applied to a variety of water distribution problems including in the water quality domain (Wu et al 2014).…”

Section: Data Driven Classification Modelsmentioning

confidence: 99%

Ensemble Decision Tree Models Using RUSBoost for Estimating Risk of Iron Failure in Drinking Water Distribution Systems

Mounce

Ellis

Edwards

et al. 2017

Water Resour Manage

View full text Add to dashboard Cite

Safe, trusted drinking water is fundamental to society. Discolouration is a key aesthetic indicator visible to customers. Investigations to understand discolouration and iron failures in water supply systems require assessment of large quantities of disparate, inconsistent, multidimensional data from multiple corporate systems. A comprehensive data matrix was assembled for a seven year period across the whole of a UK water company (serving three million people). From this a novel data driven tool for assessment of iron risk was developed based on a yearly update and ranking procedure, for a subset of the best quality data. To avoid a 'black box' output, and provide an element of explanatory (human readable) interpretation, classification decision trees were utilised. Due to the very limited number of iron failures, results from many weak learners were melded into one high-quality ensemble predictor using the RUSBoost algorithm which is designed for class imbalance. Results, exploring simplicity vs predictive power, indicate enough discrimination between variable relationships in the matrix to produce ensemble decision tree classification models with good accuracy for iron failure estimation at District Management Area (DMA) scale. Two model variants were explored: 'Nowcast' (situation at end of calendar year) and 'Futurecast' (predict end of next year situation from this year's data). The Nowcast 2014 model achieved 100% True Positive Rate (TPR) and 95.3% True Negative Rate (TNR), with 3.3% of DMAs classified High Risk for un-sampled instances. The Futurecast 2014 achieved 60.5% TPR and 75.9% TNR, with 25.7% of DMAs classified High Risk for un-sampled instances. The output can be used to focus preventive measures to improve iron compliance.

show abstract

Investigation into the relationship between chlorine decay and water distribution parameters using data driven methods

Cited by 74 publications

References 15 publications

Trust in a viable real estate economy with disruption and blockchain

Trust in a viable real estate economy with disruption and blockchain

Review of Input Variable Selection Methods for Artificial Neural Networks

Ensemble Decision Tree Models Using RUSBoost for Estimating Risk of Iron Failure in Drinking Water Distribution Systems

Contact Info

Product

Resources

About