At early stage of designing a building, a fast and trustable prediction is superbly needed. The designer needs to propose the design of the building to owner within a very limited amount of time when bidding is held. However, simulation is genuinely needed if the designed building is expected to achieve some points in any green building rating system. Handling simulation which has dozens, hundreds building surrounding require huge additional time for modeling and running the model, but implementing and predicting the output of the simulation is really advantageous for any researcher. Case-based Reasoning (CBR) approach really gives this problem a great solution since in the CBR approach there is no any complicated algorithm that needs very long time to learn if there is any update in the dataset and give the solution almost instantly. Instead of learning the experience, CBR approach retrieve the most similar case then adapt to give the solution which only requires a very short period of time. Based on the fact of these reasons, this research makes a CBR approach to predict the outdoor daylight that influence by outdoor condition. There is some software available to evaluate buildings’ lighting during design stage, but these tools tend to require extended calculation times when it comes to making model or daylight analysis. This research is done using outdoor daylight simulation data which collected from the output of Autodesk Ecotect Analysis. It is used to determine the effect of the outdoor condition of a building which will be represented as building skins. Lastly, the performance of the prediction will be evaluated using MAPE with Leave-one-out validation.

At early stage of designing a building, a fast and trustable prediction is superbly needed. The designer needs to propose the design of the building to owner within a very limited amount of time when bidding is held. However, simulation is genuinely needed if the designed building is expected to achieve some points in any green building rating system. Handling simulation which has dozens, hundreds building surrounding require huge additional time for modeling and running the model, but implementing and predicting the output of the simulation is really advantageous for any researcher. Case-based Reasoning (CBR) approach really gives this problem a great solution since in the CBR approach there is no any complicated algorithm that needs very long time to learn if there is any update in the dataset and give the solution almost instantly. Instead of learning the experience, CBR approach retrieve the most similar case then adapt to give the solution which only requires a very short period of time. Based on the fact of these reasons, this research makes a CBR approach to predict the outdoor daylight that influence by outdoor condition. There is some software available to evaluate buildings’ lighting during design stage, but these tools tend to require extended calculation times when it comes to making model or daylight analysis. This research is done using outdoor daylight simulation data which collected from the output of Autodesk Ecotect Analysis. It is used to determine the effect of the outdoor condition of a building which will be represented as building skins. Lastly, the performance of the prediction will be evaluated using MAPE with Leave-one-out validation.

1. James, G., et al., An introduction to statistical learning. Vol. 112. 2013: Springer.
2. Aha, D.W., Editorial, in Lazy learning. 1997, Springer. p. 7-10.
3. Nasrollahi, N. and E. Shokri, Daylight illuminance in urban environments for visual comfort and energy performance. Renewable and sustainable energy reviews, 2016. 66: p. 861-874.
4. Dogan, T., C. Reinhart, and P. Michalatos, Urban daylight simulation calculating the daylit area of urban designs. Proceedings of SimBuild, 2012. 5(1): p. 613-620.
5. Rutten, A., Sky luminance research imperative for adequate control of temporary supplementary artificial lighting installations. Building and Environment, 1994. 29(1): p. 105-111.
6. Weather Data. [cited 2018 May 4]; Available from: https://energyplus.net/weather.
7. Reinhart, C.F. and O. Walkenhorst, Validation of dynamic RADIANCE-based daylight simulations for a test office with external blinds. Energy and buildings, 2001. 33(7): p. 683-697.
8. Reinhart, C.F. and S. Herkel, The simulation of annual daylight illuminance distributions—a state-of-the-art comparison of six RADIANCE-based methods. Energy and Buildings, 2000. 32(2): p. 167-187.
9. Kota, S., et al., Building Information Modeling (BIM)-based daylighting simulation and analysis. Energy and Buildings, 2014. 81: p. 391-403.
10. Acosta, I., et al., Analysis of the accuracy of the sky component calculation in daylighting simulation programs. Solar Energy, 2015. 119: p. 54-67.
11. Tagliabue, L.C., M. Buzzetti, and B. Arosio, Energy saving through the sun: Analysis of visual comfort and energy consumption in office space. Energy Procedia, 2012. 30: p. 693-703.
12. Jones, P., et al., Evaluation of methods for modelling daylight and sunlight in high rise Hong Kong residential buildings. Indoor and Built Environment, 2004. 13(4): p. 249-258.
13. Yoon, Y., J.W. Moon, and S. Kim, Development of annual daylight simulation algorithms for prediction of indoor daylight illuminance. Energy and Buildings, 2016. 118: p. 1-17.
14. Joarder, M.A.R., et al., Daylight simulation for sustainable urban office building design in Dhaka, Bangladesh: decision-making for internal blind configurations. 2009.
15. Wu, X., et al., Top 10 algorithms in data mining. Knowledge and information systems, 2008. 14(1): p. 1-37.
16. Jain, A.K., Data clustering: 50 years beyond K-means. Pattern Recognition Letters, 2010. 31(8): p. 651-666.
17. Wong, T.-T., Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation. Pattern Recognition, 2015. 48(9): p. 2839-2846.
18. Shao, Z. and M.J. Er, Efficient Leave-One-Out Cross-Validation-based Regularized Extreme Learning Machine. Neurocomputing, 2016. 194: p. 260-270.
19. Chlis, N.-K., Machine Learning Methods for Genomic Signature Extraction. 2015, TECHNICAL UNIVERSITY OF CRETE.
20. Chou, J.-S., Web-based CBR system applied to early cost budgeting for pavement maintenance project. Expert Systems with Applications, 2009. 36(2): p. 2947-2960.
21. Kolodner, J., Case-based reasoning. 2014: Morgan Kaufmann.
22. Bergmann, R., et al. Retrieving Adaptable Cases in Process-Oriented Case-Based Reasoning. in FLAIRS Conference. 2016.
23. Patterson, D., N. Rooney, and M. Galushka. A regression based adaptation strategy for case-based reasoning. in AAAI/IAAI. 2002.
24. Watson, I. and H. Watson, CAIRN: a case-based document retrieval system. Proc. of the 3rd United Kingdom Case-Based Reasoning Wrokshop, University of Manchester, Filer, N & Watson, I (Eds), 1997.
25. Doğan, S.Z., D. Arditi, and H. Murat Günaydin, Using decision trees for determining attribute weights in a case-based model of early cost prediction. Journal of Construction Engineering and Management, 2008. 134(2): p. 146-152.
26. Baruque, B., et al., A forecasting solution to the oil spill problem based on a hybrid intelligent system. Information Sciences, 2010. 180(10): p. 2029-2043.
27. Chang, P.-C., J.-C. Hsieh, and T.W. Liao. A case-based reasoning approach for due-date assignment in a wafer fabrication factory. in International Conference on Case-Based Reasoning. 2001. Springer.
28. Li, H. and J. Sun, Gaussian case-based reasoning for business failure prediction with empirical data in China. Information Sciences, 2009. 179(1-2): p. 89-108.
29. Aha, D.W., The omnipresence of case-based reasoning in science and application. Knowledge-based systems, 1998. 11(5-6): p. 261-273.
30. Yamin, Z., et al., Research on Matching Method for Case Retrieval Process in CBR Based on FCM. Procedia Engineering, 2017. 174: p. 267-274.
31. Yan, A., et al., An attribute difference revision method in case-based reasoning and its application. Engineering Applications of Artificial Intelligence, 2017. 65: p. 212-219.
32. Petrovic, S., G. Khussainova, and R. Jagannathan, Knowledge-light adaptation approaches in case-based reasoning for radiotherapy treatment planning. Artif Intell Med, 2016. 68: p. 17-28.
33. Henriet, J., et al., Case-Based Reasoning adaptation of numerical representations of human organs by interpolation. Expert Systems with Applications, 2014. 41(2): p. 260-266.
34. Qi, J., J. Hu, and Y. Peng, Hybrid weighted mean for CBR adaptation in mechanical design by exploring effective, correlative and adaptative values. Computers in Industry, 2016. 75: p. 58-66.
35. Craw, S., N. Wiratunga, and R.C. Rowe, Learning adaptation knowledge to improve case-based reasoning. Artificial Intelligence, 2006. 170(16-17): p. 1175-1192.
36. Qi, J., J. Hu, and Y. Peng, A modularized case adaptation method of case-based reasoning in parametric machinery design. Engineering Applications of Artificial Intelligence, 2017. 64: p. 352-366.
37. Castro, J.L., et al., Loss and gain functions for CBR retrieval. Information Sciences, 2009. 179(11): p. 1738-1750.
38. Ezghari, S., A. Zahi, and K. Zenkouar, A new nearest neighbor classification method based on fuzzy set theory and aggregation operators. Expert Systems with Applications, 2017. 80: p. 58-74.
39. Bora, M., et al., Effect of different distance measures on the performance of K-means algorithm: an experimental study in Matlab. arXiv preprint arXiv:1405.7471, 2014.
40. Fuchs, B., et al. An algorithm for adaptation in case-based reasoning. in 14th European Conference on Artificial Intelligence-ECAI'2000. 2000. IOS Press.
41. Grech, A. and J. Main. Case-base injection schemes to case adaptation using genetic algorithms. in European Conference on Case-Based Reasoning. 2004. Springer.
42. Cordier, A., B. Fuchs, and A. Mille. Engineering and learning of adaptation knowledge in case-based reasoning. in International Conference on Knowledge Engineering and Knowledge Management. 2006. Springer.
43. Liu, C.-H. and H.-C. Chen, A novel CBR system for numeric prediction. Information Sciences, 2012. 185(1): p. 178-190.
44. Li, Y.F., M. Xie, and T.N. Goh, A study of project selection and feature weighting for analogy based software cost estimation. Journal of Systems and Software, 2009. 82(2): p. 241-252.
45. Lu, G.Y. and D.W. Wong, An adaptive inverse-distance weighting spatial interpolation technique. Computers & Geosciences, 2008. 34(9): p. 1044-1055.
46. de Mesnard, L., Pollution models and inverse distance weighting: Some critical remarks. Computers & Geosciences, 2013. 52: p. 459-469.
47. Basu, A. and S. Sarkar, On disparity based goodness-of-fit tests for multinomial models. Statistics & Probability Letters, 1994. 19(4): p. 307-312.
48. Lee, K.M. and J. Wason, Design of experiments for a confirmatory trial of precision medicine. Journal of Statistical Planning and Inference, 2018.
49. Rosa, J.L., et al., Electrodeposition of copper on titanium wires: Taguchi experimental design approach. Journal of Materials Processing Technology, 2009. 209(3): p. 1181-1188.
50. Yang, L., B.-J. He, and M. Ye, Application research of ECOTECT in residential estate planning. Energy and Buildings, 2014. 72: p. 195-202.
51. Ibarra, D.I. and C.F. Reinhart, DAYLIGHT FACTOR SIMULATIONS – HOW CLOSE DO SIMULATION
BEGINNERS ‘REALLY’ GET? Eleventh International IBPSA Conference, 2009.
52. Laouadi, A., C. Reinhart, and D. Bourgeois, Efficient calculation of daylight coefficients for rooms with dissimilar complex fenestration systems. Journal of Building Performance Simulation, 2008. 1(1): p. 3-15.
53. Soulayman, S., Comments on solar azimuth angle. Renewable Energy, 2018. 123: p. 294-300.
54. Rajaram, C. and R.P. Kumar, Calculation of Separation Distance between Adjacent Buildings: A Review on Codal Provisions. Journal of Seismology and Earthquake Engineering, 2016. 17(1): p. 31-42.
55. Baker, N.V., A. Fanchiotti, and K. Steemers, Daylighting in architecture: a European reference book. 2013: Routledge.