Aslay, Semi Emrah

This study aims to quantify architectural design features and predict and explain their relationship with contract prices. This work focuses on the random forest algorithm, one of the machine learning algorithms. This algorithm is enhanced through parameter optimizations and compared with Shapley Additive Explanations (SHAP) to measure each architectural feature's contribution to the model's prediction. The combined evaluation of feature importance and SHAP significantly enhanced the model's interpretability. The results showed that the roof area and the number of doors had a significant impact on project costs among the building's architectural features. The performance evaluation metric outputs obtained, with R2 at 0.8725, NSE at 0.8709, MAE at 0.6510, and RMSE at 0.9615, align with the developed prediction model. The study reveals the relationship between contract costs and their sub-variables using predictive models and explainable machine learning methods to build architectural features.

Bulut, H. Alperen; Kandil, Ufuk

The purpose of this study is to evaluate the waste tires that harm the environment as aggregate in concrete and to examine the effect on the mechanical properties of concrete. Three different classes (powder, crumb and chips) of waste rubber with seven different ratios (0%, 4%, 8%, 12%, 16%, 20% and 24%) and two different water to cement ratio (0.4 and 0.5) were used in concrete production. In this regard, this study conducted various experiments consisting of 28 and 90 days of the curing process to determine the properties of unit weight, compressive, flexural, and splitting tensile strength, along with ultrasonic pulse velocity (UPV) and dynamic modulus of elasticity. The waste rubber concrete with the highest compressive strength at the end of 90 days is the concrete that includes 4% waste rubber (0.4WR4) with 58.81 MPa. Concrete containing 8% waste rubber has the highest UPV of 5660 m/s after 90 days. The increase in the water/cement ratio from 0.4 to 0.5 and the waste rubber ratio cause deterioration in the mechanical properties of concrete. Although the use of waste rubbers does not bring an increase in strength, it is feasible to produce high strength concretes with 4% and 8% waste rubber substitution ratios. The water/cement ratio and curing time were highly effective on the mechanical properties of rubberized concrete.