Modeling of Reinforcement in Concrete Beams Using Machine Learning Tools

The paper discusses the results obtained to predict reinforcement in singly reinforced beam using Neural Net (NN), Support Vector Machines (SVM-s) and Tree Based Models. Major advantage of SVM-s over NN is of minimizing a bound on the generalization error of model rather than minimizing a bound on mean square error over the data set as done in NN. Tree Based approach divides the problem into a small number of sub problems to reach at a conclusion. Number of data was created for different parameters of beam to calculate the reinforcement using limit state method for creation of models and validation. The results from this study suggest a remarkably good performance of tree based and SVM-s models. Further, this study found that these two techniques work well and even better than Neural Network methods. A comparison of predicted values with actual values suggests a very good correlation coefficient with all four techniques.

Structural Characteristics of Three-Dimensional Random Packing of Aggregates with Wide Size Distribution

The mechanical properties of granular solids are dependent on the flow of stresses from one particle to another through inter-particle contact. Although some experimental methods have been used to study the inter-particle contacts in the past, preliminary work with these techniques indicated that they do not have the necessary resolution to distinguish between those contacts that transmit the load and those that do not, especially for systems with a wide distribution of particle sizes. In this research, computer simulations are used to study the nature and distribution of contacts in a compact with wide particle size distribution, representative of aggregate size distribution used in asphalt pavement construction. The packing fraction, the mean number of contacts and the distribution of contacts were studied for different scenarios. A methodology to distinguish and compute the fraction of load-bearing particles and the fraction of space-filling particles (particles that do not transmit any force) is needed for further investigation.

Potential of GIS to Find Solutions to Space Related Problems in Construction Industry

Geographic Information System (GIS) is a computerbased tool used extensively to solve various engineering problems related to spatial data. In spite of growing popularity of GIS, its complete potential to construction industry has not been realized. In this paper, the summary of up-to-date work on spatial applications of GIS technologies in construction industry is presented. GIS technologies have the potential to solve space related problems of construction industry involving complex visualization, integration of information, route planning, E-commerce, cost estimation, etc. GISbased methodology to handle time and space issues of construction projects scheduling is developed and discussed in this paper.