Select Page
Your Perfect Assignment is Just a Click Away
We Write Custom Academic Papers

100% Original, Plagiarism Free, Customized to your instructions!

glass
pen
clip
papers
heaphones

ExpertSystemforSelectingandPrioritizingProjectsforHandlingUrbanWaterSupplyCrises.pdf

ExpertSystemforSelectingandPrioritizingProjectsforHandlingUrbanWaterSupplyCrises.pdf

RESEARCH ARTICLE

Expert system for selecting and prioritizing projects for handling urban watersupply crisesWelitom Ttatom Pereira da Silvaa and Marco Antonio Almeida de Souzab

aDepartment of Sanitary and Environmental Engineering, Federal University of Mato Grosso, Cuiabá, Brazil; bDepartment of Civil andEnvironmental Engineering, University of Brasília, Brasília, Brazil

ABSTRACTThe water supply crisis (UWC) has affected various cities around the world. The variability of possiblecauses, the many viable alternatives to UWC management and methodologies for selecting thesealternatives, as well as local government’s economic and technical constraints make the problemcomplex. The aim of this paper is to help select a set of alternative solutions suitable for the UWCproblem. The proposed methodology comprised the following steps: (1) theoretical foundation, (2)planning the expert system (ES) to be built, (3) formal knowledge explicitation, (4) knowledge coding,(5) evaluation and adequacy of ES and (6) application of ES to real-life UWC cases. The main result was acomputational decision support system, called UWC-ES. The conclusion was that UWC-ES behaved as acomputational tool that reasonably reproduces knowledge from various human experts with accepta-ble applicability, and considering the possibility of using it in other cases.

ARTICLE HISTORYReceived 24 January 2018Accepted 24 September 2018

KEYWORDSManagement strategies;rule-based expert system;water crisis

1. Introduction

The urban water supply crisis (UWC) is currently a significantproblem affecting many populations around the world.Numerous UWC cases can be found in the literature, suchas the city of São Paulo (Brazil), the provinces of northernand western China, California (USA), the city of Cape Town(South Africa), and the western prairie provinces of Canada,which have been described in Coutinho, Kraenkel, and Prado(2015); Zheng et al. (2010); Pollak (2010); Ziervogel, Shale,and Du (2010), and Schindler and Donahue (2006), respec-tively. This specific problem has motivated researchers toseek alternative solutions and methodologies to cope withthem adequately.

The alternative solutions are varied and may consider struc-tural strategies (technological options to reduce water con-sumption, such as using water-saving equipment), non-structural (actions that influence demand, such as changes topricing policies) and the combination of structural and non-structural strategies. A more detailed discussion of structuraland non-structural strategies is presented in Savenije and Vander Zaag (2002). The analysis methodologies for handling theUWC include traditional optimization methods, simulation andscenario generation techniques, statistical models, multiobjec-tive and multicriteria methods, among others. For example,Zarghami, Abrishamchi, and Ardakanian (2008) carried outstudies aiming to select alternative water management mea-sures in an environment with significant population growthand frequent water supply failures (in the case of the city ofZahedan, Iran). A multiobjective and multicriteria model forthe problem of water supply contemplating several variables(losses in the water network, consumption measures andothers) was developed. Different criteria (costs, need for

water supply, etc.) were aggregated using the CompromiseProgramming method. The results showed that demand man-agement measures can delay water transfer projects to thecity of Zahedan for more than 10 years. Artificial intelligencetechniques have also been used (León et al. 2000; Tillmanet al. 2005; López-Paredes, Saurí, and Galán 2005).

To analyze this context where there are various alterna-tive solutions and different methodologies, faced with situa-tions of severe limitations of financial and human resourcesthat many Brazilian cities and cities throughout the worldcommonly go through, the following question arises: howto select alternative solutions for a given UWC problem? Asa response, using UWC classification techniques and con-structing an expert system is suggested based on studies bySilva and Souza (2017) and Liao (2005). Thus, this study aimsto help select suitable project alternatives for the UWCproblem. More specifically, it is hoped that a system canbe obtained to support the decision-making process ofselecting priority projects to solve the UWC problem inurban environments with a significant limitation of financialand human resources.

2. Methods

The proposed methodology comprised the following steps: (1)understanding the real problem using a literature review anda study of the theoretical foundations of possible solutions, (2)planning the expert system to be developed, (3) formal knowl-edge explicitation, (4) knowledge coding and development ofthe expert system (ES), (5) evaluation and adequacy of the ESand (6) application of the ES to real-life UWC cases to verifythe acceptability of the developed ES response.

CONTACT Welitom Ttatom Pereira da Silva wttatom@gmail.com

URBAN WATER JOURNAL2018, VOL. 15, NO. 6, 561–567https://doi.org/10.1080/1573062X.2018.1529806

© 2018 Informa UK Limited, trading as Taylor & Francis Group

2.1 Theoretical foundation

In this section, topics such as UWC classification (typification)and the expert system (ES) are presented, which are the basisfor this study.

Using typical cases (case classification) plays an importantrole in decision-making, especially when the decision involvesa large number of indicators and/or influencing factors (López-Paredes, Saurí, and Galán 2005; UNEP/UNESCO 1987). In thisstudy, the decision support model for crisis management inurban water supply (UWC-MODEL), developed by Silva andSouza (2017), was used to simplify the analysis and studydifferent UWC situations (classification of UWC cases).

The UWC-MODEL performs the following activities: (1) itaggregates influential factors in the UWC into five levels(socioeconomic, management, environmental, urban and cul-tural), (2) it evaluates its intensity of contribution to the UWCsituation for each level and (3) based on this evaluation, itclassifies the UWC situation at each level (classes: very strong,strong, moderate, weak and very weak). The UWC-MODEL canclassify and/or typify UWC cases and, consequently, the causeof the UWC is identified, helping to select and prioritize pro-jects handling UWC. For example, in a case that has a verystrong contribution from the cultural level, the measures torestructure the urban water supply system should prioritizeprojects related to the cultural level. Therefore, setting up anenvironmental education program could be an appropriateproject for handling UWC. In Equations (1) and (2), resultsfrom the UWC-MODEL (RUWC-MODEL), the basis and startingpoint of this study, are presented in vector format, whereCj=1, Cj=2, Cj=3, Cj=4 and Cj=5 are the classes of socioeconomic,management, environmental, urban and cultural levels,respectively. More details about the UWC-MODEL can befound in the study by Silva and Souza (2017).

RUWC�MODEL ¼ Cj¼1; Cj¼2; Cj¼3; Cj¼4; Cj¼5� �

(1)

RUWC�MODEL ¼ fo; mfr; fr; mo; mfof g (2)Another basis for this research was using the technique togenerate expert systems (ES). Artero (2009) defined ES as acomputational system designed to represent the knowledgeof one or more human experts on a particular domain and,from the processing of the knowledge base, seek solutions toproblems that, in general, require a great deal of specializedknowledge.

In an ES operation, it is assumed that the user feeds the ESwith factors or information and the system provides the userwith expert knowledge. Internally, ES consists of two maincomponents: the knowledge base and inference engineering.The knowledge base stores knowledge and inference engi-neering uses stored knowledge to construct the conclusions.Some basic concepts refer to the problem domain, the domainknowledge and the inference engineering. A problem domainrefers to a problem specific to an area (medicine, finance,science or engineering) that the expert can solve. The expert’sknowledge of how to solve a specific problem is called domainknowledge. Inference engineering refers to the ability the EShas to infer in the same way a human expert should inferwhen faced with a problem.

The general strategies for ES development are shown byGiarratano and Riley (2004). Briefly, the ES development pro-cess consists of: (1) the ES developer establishes a dialoguewith the experts for the expert knowledge explicitation, (2) thedeveloper encodes the explicit knowledge (ES development),(3) the experts evaluate and criticize the developed ES, thedeveloper makes adjustments and the process is repeateduntil the ES is considered adequate by the experts. In practice,the ES is an executable program that searches for the knowl-edge about its domain in a separate file. This means that theknowledge base can be completely changed and even then,the program will work normally, adopting the knowledge fromthe new base (Artero 2009). Some suggested references onthe subject are: Kim, Wiggins, and Wright (1990); Wright et al.(1993); Nikolopoulos (1997); Resende et al. (2005); Artero(2009); Giarratano and Riley (2004) and Liao (2005).

2.2 Expert system planning

The purpose of the ES planning stage was to produce a formalplan for ES development called the UWC-ES. Thus, the feasi-bility assessment, resource management and preliminary func-tional layout tasks were performed based onrecommendations made by Giarratano and Riley (2004). Forthe feasibility assessment task, the factors and returns sug-gested by Giarratano and Riley (2004) were verified, in order todecide if the ES approach would be adequate. The resourcemanagement task was carried out by researching the compu-ter resources (software and hardware), human resources andfinancial resources to develop the UWC-ES. In order to do this,a literature review of the resources used to develop precursorESs with similar objectives was carried out, and a comparisonwas made with the resources available to develop the UWC-ES. The preliminary functional layout task should define whatthe system will achieve by specifying the system functions.Thus, the objectives of the ES were carefully analyzed in orderto define the functions of the system, following recommenda-tions by Giarratano and Riley (2004).

2.3 Formal knowledge explicitation

Knowledge explicitation refers to the process of acquiring theknowledge needed to solve the problem (domain knowledge).To do this, the activities used by Collier, Leech, and Clark(1999); Tillman et al. (2005) and Patlitzianas, Pappa, andPsarras (2008) were adapted. In this case, these activitiesincluded: (1) defining the population universe of simulatedUWC cases, (2) defining the sample analyzed by the experts,(3) identifying projects for handling UWC and (4) obtainingdomain knowledge. A total of 13 specialists (five with a mas-ter’s degree and seven with a doctorate degree) were consid-ered, of which six were working in the sanitation area, two inthe environment area and five in the water resources area, sixlinked to water regulatory agencies, two to the environmentalprotection agency and five to research institutions anduniversities.

The population universe of simulated UWC cases is thetotal possible number of combinations of the UWC-MODELclassifications. Thus, 3125 (five levels and five classifications,

562 W. T. P. D. SILVA AND M. A. A. D. SOUZA

N = 55) individuals or typologies of simulated UWC cases wereobserved that form the population universe. To define thesample to be analyzed by the experts, the simple randomsample method was used. As justification, this method ofsampling leads to the sample in which each typology of thesample population has the same probability of being selected,not privileging specific situations or cases. The number ofsample units (n) was defined in 10% of the population,which made a total of 313 typologies analyzed by the experts.To identify the projects for handling UWC, a literature reviewwas carried out. Identifying priority projects (PP) for handlingUWC by experts for the ‘n’ sample units yielded the trainingdatabase, an initial part of the task of obtaining the domainknowledge. For this purpose, the UWC (UWC-MODEL) classifi-cation and/or typology information, the identification of pro-jects for handling UWC, the sampling technique used and thesamples to be analyzed were made available to the experts.The experts were then asked to identify PP for handling UWC(selection of five major projects for handling UWC) for each ofthe typologies of the real-world/simulated cases analyzed bythem. For exemplification, from the process of obtaining thetraining database, a graphical representation is illustrated inFigure 1.

Having defined the training database, the final part of obtain-ing the knowledge domain (obtaining the rules) was started.Moreover, a machine learning technique was used for this pur-pose, which automatically extracts information from the trainingdatabase. More specifically, a decision tree was used as theclassification model, which is one of the most widely usedmachine supervised learning methods in practice (Artero 2009).The method is based on the decision tree construction, from thetraining database to obtaining the production rules (domainknowledge). For the construction of the decision tree, algorithmJ48, which is one of the most known and used algorithms forconstructing decision trees, was used (Artero 2009). To evaluatethe classification model (decision tree), the Confusion Matrix andKappa Statistics (κ) were used, as recommended by Resendeet al. (2005). Furthermore, it was considered that the classifica-tion model would be adequate if it presented Kappa Statistics (κ)values equal or above κ = 0.41 (moderate agreement), accordingto Landis and Koch (1977). Otherwise, adjustments in the classi-fication model would be necessary.

2.4 Knowledge coding

For knowledge coding, a Pentium 2.13GHz microcomputerwas used, with 4GB of RAM in the Windows operating system

using CLIPS (C Language Integrated Production System) shell,version 6.3. In this case, it was adopted as a robust andefficient shell for ES development, one that: (1) presentedthe ability to resolve conflicts between rules, (2) operatedsatisfactorily with the forward chain, (3) was a free accessshell and (4) presented good answers (accuracy). This robustshell definition considered the existence of conflicting opi-nions among the experts consulted, the proposition of theModus Ponens type ‘if (condition) – then (action)’ as an appro-priate form of inference, and the economic limitation forcommercial shell acquisition. Thus, the CLIPS shell can beevaluated as robust to the problem in focus agreeing withthe works of Riley et al. (1987); Mettrey (1991), and Kuestenand McLellan (1994).

2.5 Evaluation and adequacy

According to Giarratano and Riley (2004), at this stage, theexpert should evaluate and criticize the UWC-ES, passing onthis information to the ES developer, who in turn performs theadjustments and again returns the ES to the expert for re-evaluation. This process is iterative until the expert judges thatUWC-ES is adequate. Considering the characteristics of theproblem and the studies carried out by Spring (1997) andCollier, Leech, and Clark (1999), the Turing test (a classic testthat aims to verify if a machine has the intelligence matchingthat of a human). To implement the test, the methodologiesused by Spring (1997); Collier, Leech, and Clark (1999), andArtero (2009) were adjusted.

The Turing test is based on forming three groups of differ-ent experts, indicated here by G-1, G-2 and G-3. The testbasically consists of collecting a set of ‘m’ test cases, previouslysolved by experts from the G-1 group, solving these cases bydeveloped ES (G-2), carrying out the specific evaluation ofboth solutions, S (G-1) and S (G-2) by other experts (G-3). Inthe specific evaluation, two outputs were requested from theG-3 group; the first output refers to the quality evaluation ofthe G-1 and G-2 solutions, according to a scale ranging from 1to 7 (1 = very bad, 4 = reasonable, 7 = very good). In thesecond output, the identification of the solutions from the ESwas requested. If G-3 assigns a value greater than or equal to 4to the quality of solutions presented by G-2 and cannot deter-mine (with a minimum of 50% accuracy) which one of the two(G-1 or G-2) is the group of experts, it is said that the machinehas passed the Turing test and therefore can simulate humanintelligence. In this case, the end of the UWC-ES developmentis observed, and the ES is considered suitable to select the

Figure 1. Obtaining the knowledge domain.

URBAN WATER JOURNAL 563

best solutions for the UWC problem. Otherwise, adjustmentsmust be made in the UWC-ES.

2.6 Application of the expert system

The purpose of the application cases was to help evaluatethe results of the developed ES model. Considering theprospect of possible water supply problems in the FederalDistrict, as mentioned by Conejo et al. (2009), some of theAdministrative Regions (AR) of the Federal District wereadopted as case studies. These AR included Brasília, LagoNorte, Cruzeiro, Guará, Varjão, Estrutural and Park Way.These AR were chosen according to the importance ofstudying urban environments with different economic levels.For ES application, secondary information was used, basedon data from Silva (2012). In addition, the Federal DistrictGovernment was considered as the decision-maker in thecase, with its respective competent institutions (BrazilianFederal District’s Regulatory Agency for Water, Energy andSanitation – ADASA, Brazilian Federal District’s WaterSupplier and Sanitation Company – CAESB, BrazilianInstitute of Environment and Water Resources – IBRAM andSecretary of State for the Environment – SEMA).

3. Results

Based on following the formal plan and setting the predefinedtasks for UWC-ES development (expert system planning stage),responses about its viability were obtained. The result of thefeasibility assessment task, the verification of the factors andreturns suggested by Giarratano and Riley (2004), led to thereturn of the viability response of the ES approach. The rea-sons that led to this response refer to the fact that most of thereturns (factors 1, 3, 4, 5 and 6) showed a favorable return toES development, as shown in Table 1.

For the resource management task, the result indicatedthat the available resources are comparable to the resourcesused to develop other ES with equivalent functions, accordingto the literature review (Cheng, Yang, and Chan 2003; Chau,Chuntian, and Li 2002; León et al. 2000). Based on the pre-liminary functional layout task, it was found that the proposedES must ensure compliance of the purpose of pointing outpriority projects for handling UWC. From the knowledge expli-citness stage, the population universe (possible combinations,which make a total of N = 3125) and the identification (Id.) ofthe sample units (typologies, totalizing n = 313) were identi-fied to be studied.

As a result of the task of identifying projects for handling UWC,Table 2 shows a summary list obtained from a literature review.

As the problem was modeled to obtain five priority projects(PP) for handling UWC from the experts, five classificationmodels (decision trees) were found, one for each priorityestimate (PP1, PP2, …, PP5). Part of the classification model(decision tree) and respective production rules (domain knowl-edge) obtained for PP1 are presented in Figure 3(a,b).

In total, 409 production rules were obtained that make upthe domain knowledge. Additional information on these clas-sification models (decision tree) and production rules waspresented in Silva (2012).

As a result of the evaluation of the classification model(decision tree), the Confusion Matrix and the Kappa Statistics(κ) were obtained. The Confusion Matrix is shown in Figure 2(c).The Confusion Matrix provides an effective measure of fit forthe classification model by showing the number of correctclassifications versus the number of classifications predictedfor each class, concerning a training database. Thus, the correctclassification of the model (coincidence of the response pre-sented by the expert, shown in the lines, and the responsepresented by the classification model, presented in the col-umns) is given by the diagonal elements of the ConfusionMatrix. The total number of training data correctly classifiedby the classification model for PP1 is given by the sum of theelements in the diagonal of the Confusion Matrix, and all otherswere incorrectly classified. Therefore, a reasonable fit of theclassification model (decision tree) of PP1 was observed inFigure 2(c). Moreover, it should be mentioned that the otherclassification models presented slightly better results.

For the average Kappa Statistics (κ), whose individualvalues for each classification model (decision tree) areκPP1 = 0.41, κPP2 = 0.49, κPP3 = 0.54, κPP4 = 0.49 andκPP5 = 0.45, an average value of κ = 0.48 was found, consid-ered adequate according to the adopted methodology. Thisvalue indicates that the classification showed a moderateagreement. The classification model presented a moderateadjustment and, according to Landis and Koch (1977), canrepresent, with moderate precision, the training data.

Table 1. Factors and returns considered in the ES viability assessment.

Item Factora Returnb Evaluationc

1 Can the problem be solved efficiently byconventional programming?

No No

2 Is the problem’s domain well defined? Yes No3 Is there a need and interest for an ES? Yes Yes4 Are there human experts willing to cooperate? Yes Yes5 Can the experts pass on their knowledge? Yes Yes6 Does the solution of the problem mainly involve

heuristics and uncertainty?Yes Yes

Notes: a) Factors suggested by Giarratano and Riley (2004), b) expected returnfor the ES approach to be viable, c) return found after feasibility assessment.

Table 2. Summary list of projects for handling UWC.

P Projects for handling UWC

P1 Loss reduction (S)P2 Macro and micro-mediation implementation (S)P3 Implementation of individualized measurement (S)P4 Implementation of efficient bathrooms (S)P5 Reduction in pressure in the hydraulic system in bathrooms (S)P6 Reduction in pressure in the water distribution network (S)P7 Rainwater collection and use (S)P8 Greywater collection, treatment and use (S)P9 Setting up environmental education programs (NS)P10 Application of fiscal stimuli for consumption reduction (NS)P11 Tax on inefficiency in water use (NS)P12 Adjustment of tariff policy (NS)P13 Regulation of the water consumption of household appliances/savers (NS)P14 Increase in production capacity (S)P15 Intermittence/rationing in the supply system (S)P16 Regulation of consumption (NS)P17 Creating green roofs (S)P18 Strengthening water supply operator (NS)P19 Using good practices for water conservation (NS)P20 Privatization/concession of the water supply services operator (NS)

Note: (S) is structural measures and (NS) is non-structural measures.

564 W. T. P. D. SILVA AND M. A. A. D. SOUZA

The knowledge coding step occurred satisfactorily. The toolused was considered adequate as the production rules andconflict resolution strategies were easy to implement. Figure 3shows the CLIPS development environment and part of theelaborated coding.

The results of the UWC-ES evaluation and adequacy stageindicated that the first group, the G-1 group, was formed bythe 13 experts who effectively contributed to forming thetraining database (domain knowledge). The second group(G-2) was formed by the answers given by the ES, i.e. it refersto the UWC-ES. Furthermore, the third group was the G-3,formed by three experts who did not participate in obtainingdomain knowledge. The first output, given by the G-3, indi-cated an average value of 4 for the quality of the solutionspresented by UWC-ES, on a scale ranging from 1 to 7 (1 = verybad, 4 = reasonable, 7 = very good). When analyzing thequality of the solutions presented by the G-1 human experts,which was also 4, a similarity can be observed between G-1and G-2. This also shows a reasonable divergence between theopinions of the human experts of the G-1 group and the G-3group. These divergences are also conveyed in the responsesgiven by the ES. It was observed that cases with similarcharacteristics receive different solutions, depending predomi-nantly on the training, experience and professional experienceof the expert who analysed the case. This fact requires carefuluse of the results of the developed ES (UWC-ES) and provesthe complexity of the studied problem. Similar problems were

reported by Giarratano and Riley (2004) because even amongthe experts there is no consensus.

The second result indicated that the G-3 was unable todetermine, with 67% accuracy, which of the two (G-1 or G-2),is the group of human specialists, therefore UWC-ES wasapproved by the Turing test. In other words, it can be con-cluded that the UWC-ES is able to select the best solutions tothe problem of handling UWC.

The main results found for the case studies chosen, afterusing the UWC-MODEL, are presented in Table 3. These werethe results used to feed the UWC-ES.

According to the UWC-MODEL, the environmental level(j = 4) was the one that presented the greatest contributionto the intensification of the studied UWC. For the second andthird level of greatest contribution, the urban dimension (j = 3)and managerial dimension (j = 2) were found, respectively.This suggests that the PPs selected by the UWC-ES for solvingthe UWC case studies are targeted at reducing the contribu-tion or collaboration, of the environmental, urban and man-agerial levels. The results obtained for the case studies, afterusing the ES (input of the results of the UWC-MODEL in theUWC-ES) are presented in Table 3.

In summary, eight PPs were suggested for the solution of thestudied case of UWC, which are the following: loss reduction (P1),implementation of individualized measurement (P3), rainwatercollection and use (P7), greywater collection, treatment and use(P8), application of fiscal stimulus for consumption reduction

Figure 2. (a) Part of the classification model (decision trees); (b) production rules; (c) confusion matrix of PP1.

URBAN WATER JOURNAL 565

(P10), consumption regulation (P16), strengthening water supplyoperator (P18) and use of good practices for water conservation(P19). When analyzing the results presented by the UWC-ES, someproblems can be observed, such as the recommendation of theguideline ‘implementation of individualized measurement’ (P3) forthe Estrutural and Varjão AR, whose predominant housing typol-ogy is isolated single-family residences that already have indivi-dualized measurement; the non-recommendation of theindividualized measurement (P3) for regions (in the case of theBrasília and Cruzeiro AR) in which there is predominance of apart-ment housing without individualized measurement, and therecommendation to strengthen the water supply operator (P18)to a well-structured company (CAESB). These problems suggestthe need for making adaptations to the UWC-ES since the modelresponded reasonably to these cases. In contrast, the indication ofthe PP for rainwater collection and use (P7), greywater collection,treatment and use (P8), regulation of consumption (P16) andusing good practices for water conservation (P19) can be consid-ered appropriate for the case studies, as they try to solve the UWCproblem by addressing its cause (j = 4, greater influence of theenvironmental level). Thus, it can be considered that the devel-oped ES presented acceptable results, in agreement with pre-viously presented adjustment indicators.

4. Conclusions

A computational tool was developed to help select a set ofpriority projects (PP) to solve the UWC problem. This tool was

called UWC-ES. The tool (UWC-ES) can replace human andfinancial resources for decision making in UWC. Therefore, itis especially suitable for urban environments where limitationsof human and financial resources are important.

The results of the UWC-ES indicated acceptable applicabil-ity and the possibility of using it in other cases. The use ofUWC-ES is based on analyzing various pieces of informationabout the urban environment by an (artificial) UWC expert,which reasonably reproduces the knowledge of several humanexperts. Thus, the resources required to use the UWC-ES con-sist of efforts to obtain these various pieces of informationand, of course, without the experts’ full participation.

Although the characteristics of the problem are appropriateto the approach of the expert system, some obstacles wereencountered during the development of the UWC-ES sub-model, including the following: (1) the difficulty of findingspecialists willing to collaborate, (2) the existence of diver-gence between the opinions of specialists and (3) the exis-tence of problems in inference, mainly due to the existence ofdivergence between the opinions of the specialists. Thus, newstudies are suggested focusing on changes in methodology inorder to minimize the divergence of expert opinions. Onepossible modification, for example, could be the aggregationof responses from experts with similar academic backgroundsand the assignment of weights to each specialty class.

Acknowledgements

The authors would like to express their gratitude for the financial sup-port from the Brazilian agencies CNPq (Project Nº 556084/2009-8) andCAPES. The authors would like to express their gratitude to the followinginstitutions: Brazilian Federal District’s Regulatory Agency for Water,Energy and Sanitation (ADASA), Water National Agency of the Brazil(ANA), Brazilian Federal District’s Water Supplier and SanitationCompany (CAESB) and Brazilian Federal District’s Planning Company(CODEPLAN).

Disclosure statement

No potential conflict of interest was reported by the authors.

Figure 3. CLIPS development environment and part of the developed ES coding.

Table 3. UWC-MODEL and UWC-ES results for the case studies.

Classification of cases accordingto the UWC-MODEL

UWC-ES results for thecase studies

Case Study j = 1 j = 2 j = 3 j = 4 j = 5 PP1 PP2 PP3 PP4 PP5

Brasilia AR fr fr mo fo mfr P18 P19 P16 P8 P7Cruzeiro AR fr fr mo fo mfr P18 P19 P16 P8 P7Estrutural AR mo mo mo fo fr P19 P7 P1 P3 P10Guará AR mo mo mo fo mfr P19 P3 P1 P8 P7Lago Norte AR mo mo fo fo fr P1 P7 P8 P6 P10Park Way AR mo mo fo fo fr P1 P7 P8 P6 P10Varjão AR fr mo mo fo fr P1 P2 P3 P6 P7

566 W. T. P. D. SILVA AND M. A. A. D. SOUZA

Funding

This work was supported by the Conselho Nacional de DesenvolvimentoCientífico e Tecnológico, CNPq [556084/2009-8].

References

Artero, A. O. 2009. Inteligência artificial: Teórica e prática. eds L. Da Físicaand S. Paulo. Brazil: Ed. Livraria da Física. 230.

Chau, K. W., C. Chuntian, and C. W. Li. 2002. “Knowledge ManagementSystem on Flow and Water Quality Modeling.” Expert System withApplications 22: 321–330. doi:10.1016/S0957-4174(02)00020-9.

Cheng, H., Z. Yang, and C. W. Chan. 2003. “An Expert System forDecision Support of Municipal Water Pollution Control.”Engineering Applications of Artificial Intelligence 16: 159–166.doi:10.1016/S0952-1976(03)00055-1.

Collier, P. A., S. A. Leech, and N. Clark. 1999. “A Validated ExpertSystem for Decision Making in Corporate Recovery.” InternationalJournal of Intelligence System in Accounting, Finance & Management8: 75–88. doi:10.1002/(SICI)1099-1174(199906)8:2<75::AID-ISAF164>3.0.CO;2-T.

Conejo, J. G. L., S. R. A. Soares, E. S. Juliatto, C. A. A. O. Pereira, D. D.Oliveira, L. E. G. Grisotto, and J. M. Moraes Junior. 2009. “Panorama daoferta de água nos grandes centros urbanos do país a partir dosresultados do atlas regiões metropolitanas.” In XVIII Simpósio Brasileirode Recursos Hídricos by Associação Brasileira de Recursos Hídricos (ABRH),November. Campo Grande, Brazil. Available online at: https://abrh.s3.sa-east-1.amazonaws.com/Sumarios/110/ae9682a9106cb5ce55070d2514e4eac6_92410090c83add2d5ab32fb41fdba13c.pdf Accessed 06October 2018

Coutinho, R. M., R. A. Kraenkel, and P. I. Prado. 2015. “Catastrophic RegimeShift in Water Reservoirs and São Paulo Water Supply Crisis.” Plos One:1–14. doi: 10.1371/journal.pone.0138278.

Giarratano, J. C., and G. D. Riley. 2004. Expert System: Principles andProgramming, 842. 4rd ed. Boston, USA: PWS Publishing Company.

Kim, T. R., L. L. Wiggins, and J. R. Wright. 1990. Expert Systems: Applicationsto Urban Planning, 268. New York, USA: Springer-Verlag.

Kuesten, C. L., and M. R. McLellan. 1994. “Expert System Shells – Selectingthe Most Appropriate Development Environment.” Food ResearchInternational 27: 101–110. doi:10.1016/0963-9969(94)90150-3.

Landis, J. R., and G. G. Koch. 1977. “The Measurement of ObserverAgreement for Categorical Data.” Biometrics 33: 159–174.

León, C., S. Martín, J. M. Elena, and J. Luque. 2000. “EXPLORE – HybridExpert System for Water Networks Management.” Journal of WaterResources Planning and Management, ASCE 126 (2): 65–74.doi:10.1061/(ASCE)0733-9496(2000)126:2(65).

Liao, S. H. 2005. “Expert System Methodology and Applications ADecade Review from 1995 to 2004.” Expert Systems withApplications 28: 93–103. doi:10.1016/j.eswa.2004.08.003.

López-Paredes, A., D. Saurí, and J. M. Galán. 2005. “Urban WaterManagement with Artificial Societies of Agents: The FIRMABARSimulator.” Simulation 81 (3): 189–199. doi:10.1177/0037549705053167.

Mettrey, W. 1991. “A Comparative Evaluation of Expert System Tools.”IEEE Computer Society Press 24 (1): 19–31. doi:10.1109/2.67208.

Nikolopoulos, C. 1997. Expert Systems: Introduction to First and SecondGeneration and Hybrid Knowledge Based Systems, 331. Marcel Dekker,New York, USA: Marcel Dekker, Inc.

Patlitzianas, K. D., A. Pappa, and J. Psarras. 2008. “An Information DecisionSupport System Towards the Formulation of a Modern EnergyCompanies’ Environment.” Renewable and Sustainable Energy Reviews12: 790–806. doi:10.1016/j.rser.2006.10.014.

Pollak, J. 2010. “California Water and the Rhetoric of Crisis.” BerkeleyPlanning Journal 23: 1–8.

Resende, S. O., A. G. Evsukoff, A. C. B. Garcia, A. C. P. L. F. Carvalho, A. P. Braga,M. C. Monard, N. F. F. Ebecken, P. E. M. Almeida, and T. B. Ludermir. 2005.Sistemas inteligentes: Fundamentos e aplicações, 525. Barueri, Brazil: EditoraManole Ltda.

Riley, G., C. Culbert, R. T. Savely, and F. Lopez, 1987. “CLIPS: An expertsystem tool for delivery and training.” accessed 10 October 2017.https://ntrs.nasa.gov/search.jsp?R=19880006986

Savenije, H., and P. Van der Zaag. 2002. “Water as an Economic Good andDemand Management – Paradigms with Pitfalls.” Water International 27(1): 97–104. doi:10.1080/02508060208686982.

Schindler, D. W., and W. F. Donahue. 2006. “An Impending Water Crisis inCanada’s Western Prairie Provinces.” Proceedings of the NationalAcademy of Sciences (PNAS) 103 (19): 7210–7216. doi:10.1073/pnas.0601568103.

Silva, W. T. P., 2012 “Modelo para priorização de diretrizes de combate acrises de abastecimento urbano de água.” PhD thesis, Department ofCivil and Environmental Engineering. The University of Brasília.

Silva, W. T. P., and M. A. S. Souza. 2017. “A Decision Support Model toAid the Management of Crises in Urban Water Supply Systems (TheUWC-MODEL).” Urban Water Journal 14 (6): 612–620. doi:10.1080/1573062X.2016.1223861.

Spring, G. S., 1997 “Critical Review of Expert System Validation inTransportation.” Proceedings Congress Annual Meeting of theTransportation Research Board No 76, Washington DC/USA. doi:10.3141/1588-13.

Tillman, D. E., T. A. Larsen, C. Pahl-Wostl, and W. Gujer. 2005. “SimulatingDevelopment Strategies for Water Supply.” Journal Hidroinformatics 7(1): 41–51. doi:10.2166/hydro.2005.0005.

UNEP/UNESCO, 1987. Methodological guidelines for the integrated envir-onmental evaluation of water resources development [on line].Available online at: http://unesdoc.unesco.org/images/0008/000897/089740eb.pdf Accessed 17 January 2011

Wright, J. R., L. L. Wiggins, R. K. Jain, and T. J. Kim. 1993. Expert Systems inEnvironmental Planning, 311. Berlin, Germany: Springer-Verlag.

Zarghami, M., A. Abrishamchi, and R. Ardakanian. 2008. “Multi-CriteriaDecision Making for Integrated Urban Water Management.” WaterResource Management 22: 1017–1029. doi:10.1007/s11269-007-9207-7.

Zheng, C., J. Liu, G. Cao, E. Kendy, H. Wang, and Y. Jia. 2010. “Can ChinaCope with Its Water Crisis? – Perspectives from the North China Plain.”Ground Water 48 (3): 350–354. doi:10.1111/j.1745-6584.2010.00695_3.x.

Ziervogel, G., M. Shale, and M. Du. 2010. “Climate Change Adaptation ina Developing Country Context: The Case of Urban Water Supply inCape Town.” Climate and Development Journal 2: 94–110.doi:10.3763/cdev.2010.0036.

URBAN WATER JOURNAL 567

Copyright of Urban Water Journal is the property of Taylor & Francis Ltd and its content maynot be copied or emailed to multiple sites or posted to a listserv without the copyright holder’sexpress written permission. However, users may print, download, or email articles forindividual use.

  • Abstract
  • 1. Introduction
  • 2. Methods
    • 2.1 Theoretical foundation
    • 2.2 Expert system planning
    • 2.3 Formal knowledge explicitation
    • 2.4 Knowledge coding
    • 2.5 Evaluation and adequacy
    • 2.6 Application of the expert system
  • 3. Results
  • 4. Conclusions
  • Acknowledgements
  • Disclosure statement
  • Funding
  • References

How it Works

  1. Clіck оn the “Place оrder tab at the tоp menu оr “Order Nоw” іcоn at the bоttоm, and a new page wіll appear wіth an оrder fоrm tо be fіlled.
  2. Fіll іn yоur paper’s іnfоrmatіоn and clіck “PRІCE CALCULATІОN” at the bоttоm tо calculate yоur оrder prіce.
  3. Fіll іn yоur paper’s academіc level, deadlіne and the requіred number оf pages frоm the drоp-dоwn menus.
  4. Clіck “FІNAL STEP” tо enter yоur regіstratіоn detaіls and get an accоunt wіth us fоr recоrd keepіng.
  5. Clіck оn “PRОCEED TО CHECKОUT” at the bоttоm оf the page.
  6. Frоm there, the payment sectіоns wіll shоw, fоllоw the guіded payment prоcess, and yоur оrder wіll be avaіlable fоr оur wrіtіng team tо wоrk оn іt.

Nоte, оnce lоgged іntо yоur accоunt; yоu can clіck оn the “Pendіng” buttоn at the left sіdebar tо navіgate, make changes, make payments, add іnstructіоns оr uplоad fіles fоr the оrder created. e.g., оnce lоgged іn, clіck оn “Pendіng” and a “pay” оptіоn wіll appear оn the far rіght оf the оrder yоu created, clіck оn pay then clіck оn the “Checkоut” оptіоn at the next page that appears, and yоu wіll be able tо cоmplete the payment.

Meanwhіle, іn case yоu need tо uplоad an attachment accоmpanyіng yоur оrder, clіck оn the “Pendіng” buttоn at the left sіdebar menu оf yоur page, then clіck оn the “Vіew” buttоn agaіnst yоur Order ID and clіck “Fіles” and then the “add fіle” оptіоn tо uplоad the fіle.

Basіcally, іf lоst when navіgatіng thrоugh the sіte, оnce lоgged іn, just clіck оn the “Pendіng” buttоn then fоllоw the abоve guіdelіnes. оtherwіse, cоntact suppоrt thrоugh оur chat at the bоttоm rіght cоrner

NB

Payment Prоcess

By clіckіng ‘PRОCEED TО CHECKОUT’ yоu wіll be lоgged іn tо yоur accоunt autоmatіcally where yоu can vіew yоur оrder detaіls. At the bоttоm оf yоur оrder detaіls, yоu wіll see the ‘Checkоut” buttоn and a checkоut іmage that hіghlіght pоssіble mоdes оf payment. Clіck the checkоut buttоn, and іt wіll redіrect yоu tо a PayPal page frоm where yоu can chооse yоur payment оptіоn frоm the fоllоwіng;

  1. Pay wіth my PayPal accоunt‘– select thіs оptіоn іf yоu have a PayPal accоunt.
  2. Pay wіth a debіt оr credіt card’ or ‘Guest Checkout’ – select thіs оptіоn tо pay usіng yоur debіt оr credіt card іf yоu dоn’t have a PayPal accоunt.
  3. Dо nоt fоrget tо make payment sо that the оrder can be vіsіble tо оur experts/tutоrs/wrіters.

Regards,

Custоmer Suppоrt

Order Solution Now