{"title":"Construction Unit Rate Factor Modelling Using Neural Networks","authors":"Balimu Mwiya, Mundia Muya, Chabota Kaliba, Peter Mukalula","volume":97,"journal":"International Journal of Civil and Environmental Engineering","pagesStart":29,"pagesEnd":35,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/10000298","abstract":"
Factors affecting construction unit cost vary
\r\ndepending on a country’s political, economic, social and
\r\ntechnological inclinations. Factors affecting construction costs have
\r\nbeen studied from various perspectives. Analysis of cost factors
\r\nrequires an appreciation of a country’s practices. Identified cost
\r\nfactors provide an indication of a country’s construction economic
\r\nstrata. The purpose of this paper is to identify the essential factors
\r\nthat affect unit cost estimation and their breakdown using artificial
\r\nneural networks. Twenty five (25) identified cost factors in road
\r\nconstruction were subjected to a questionnaire survey and employing
\r\nSPSS factor analysis the factors were reduced to eight. The 8 factors
\r\nwere analysed using neural network (NN) to determine the
\r\nproportionate breakdown of the cost factors in a given construction
\r\nunit rate. NN predicted that political environment accounted 44% of
\r\nthe unit rate followed by contractor capacity at 22% and financial
\r\ndelays, project feasibility and overhead & profit each at 11%. Project
\r\nlocation, material availability and corruption perception index had
\r\nminimal impact on the unit cost from the training data provided.
\r\nQuantified cost factors can be incorporated in unit cost estimation
\r\nmodels (UCEM) to produce more accurate estimates. This can create
\r\nimprovements in the cost estimation of infrastructure projects and
\r\nestablish a benchmark standard to assist the process of alignment of
\r\nwork practises and training of new staff, permitting the on-going
\r\ndevelopment of best practises in cost estimation to become more
\r\neffective.<\/p>\r\n","references":"[1] G. Raballand and A. Whitworth \u201cThe Crisis in the Zambian Road\r\nSector\u201d, Working Paper No. 5, Zambia Institute for Policy Analysis and\r\nResearch (ZIPAR), 2012, Lusaka.\r\n[2] C. Hendrickson, Project Management for Construction, Fundamental\r\nConcepts for Owners, Engineers, Architects and Builders, 2008,\r\n(available online: http:\/\/pmbook.ce.cmu.edu\/ (accessed 05\/11\/20139))\r\n[3] Zambia Public Procurement Authority, Consulting services to undertake\r\nan assessment of the prevailing market rates in the construction industry,\r\nRequest for proposals, ZPPA, Zambia, 2014.\r\n[4] J. De la Garza and K. Rouhana, Neural Network versus parameter-based\r\napplication. Cost Engineering, 37(2) 1995, pp.14-18.\r\n[5] A. K. Mason and A. E. Smith, Cost Estimation Predictive Modeling:\r\nRegression versus Neural Network. Engineering Economist 42, (2)\r\n1997, pp. 137-161. [6] AACE International, Cost Engineering Terminology, Recommended\r\nPractice No. 10S-90, TCM Framework: General Reference, Association\r\nfor the Advancement of Cost Engineering (AACE),2013\r\n[7] Langdon, D., Spon's Civil Engineering and Highway Works Price Book\r\n2009, Spon Press, 2009\r\n[8] J. Mashilipa, An investigation on the effects and their implications of\r\nusing British outputs in Estimating in the Zambian Construction\r\nIndustry, BSc (Building) Unpublished thesis, Copperbelt University,\r\nZambia, 2004.\r\n[9] Ibid\r\n[10] E. J Blocher, E. David, G. C. Stout and K. H. Chen, Cost management;\r\nA strategic emphasis 4th ed., McGraw Hill, 2008.\r\n[11] A. Enshassi, S. Mohamed, and I. Madi, Contractors\u2019 Perspectives\r\ntowards Factors Affecting Cost Estimation in Palestine. Jordan Journal\r\nof Civil Engineering, 1 (2) 2007, pp. 186-193.\r\n[12] A. Trombka and S. Downey, A Study of County Road Project Cost and\r\nSchedule Estimates, Office of Legislative Oversight, Montgomery\r\nCounty, Maryland Report Number 2008-04, 2008, (available online\r\nhttps:\/\/www.montgomerycountymd.gov\/olo\/resources\/files\/2008-4.pdf\r\n(accessed 05\/07\/2014))\r\n[13] A.H. Memon, I.A. Rahman, M.R. Abdullah, and A.A.A. Azis, Factors\r\nAffecting Construction Cost Performance in Project Management\r\nProjects: Case of Mara Large Projects. Proceedings of Post Graduate\r\nseminar on Engineering, Technology and Social Science. 29-30\r\nNovember 2010, Universiti Tun Hussein Onn Malaysia, 2010\r\n[14] A.U. Elinwa and S.A. Buba, Construction cost factors in Nigeria,\r\nJournal of Construction Engineering and Management. 119 (4), 1993,\r\npp. 698-713.\r\n[15] J. Bode, Neural Networks for Cost Estimation, Cost Engineering Journal\r\n40 (1) 1998, pp.25-30\r\n[16] I. Pe\u0161ko, M. Trivuni\u0107, G. Cirovi\u0107 and V. Mu\u010denski, A preliminary\r\nestimate of time and cost in urban road construction using neural\r\nnetworks Technical Gazette 20 (3), 2013, pp. 563-570 (accessed\r\n16\/01\/2014)\r\n[17] A. J. Hasan, Parametric Cost Estimation of Road Projects Using\r\nArtificial Neural Networks, M.Sc. Unpublished thesis, The Islamic\r\nUniversity, Gaza, 2013\r\n[18] S. Muqeem, A. Idrus, F. M. Khamidi, J.B. Ahmad, and S.B. Zakaria,\r\nConstruction labor production rates modeling using artificial neural\r\nnetwork, Journal of Information Technology in Construction (ITcon),\r\nVol. 16, 2011, pp. 713-726, (available online\r\nhttp:\/\/www.itcon.org\/2011\/42 (accessed on 09\/04\/2014))\r\n[19] A. Hashem, P.A. Alex, and M. Tantash, Preliminary Cost Estimation of\r\nHighway Construction Using Neural Networks, Cost Engineering 41, (3)\r\n1999, pp. 19-24\r\n[20] D. R. Cooper and P.S. Schindler, Business research methods 11th ed.,\r\nMcGraw Hill, 2011, pp.390-397\r\n[21] Creative Research Systems, Sample Size Formula, (available online:\r\nhttp:\/\/www.surveysystem.com\/sample-size-formula.htm (accessed on\r\n09\/04\/2014))\r\n[22] J. C. F. de Winter, D. Dodou, and P. A. Wieringa, Exploratory Factor\r\nAnalysis with Small Sample Sizes, Multivariate Behavioral Research,\r\n44, 2009, pp147\u2013181","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 97, 2015"}