Desktop version

Home arrow Computer Science

  • Increase font
  • Decrease font


<<   CONTENTS   >>

Application of Neural Networks in Construction Management

S. VARADHARAJAN1’, KIRTHANASHRI S. VASANTHAN2, SHWETAMBARA VERMA3, and PRIYANKA SINGH4

  • 1A Department of Civil Engineering, Amity School of Engineering and Technology, Amity University, Noida, Uttar Pradesh 201301, India
  • 2Amity Institute of Molecular Medicine and Stem Cell Research,

Amity University, Noida, Uttar Pradesh 201301, India

department of Civil Engineering, School of Engineering and Technology, Kaziranga University, Jorhat, Assam.

'Corresponding author. E-mail: This email address is being protected from spam bots, you need Javascript enabled to view it

ABSTRACT

The review of past research works pertaining to construction management shows that artificial intelligence is being widely used in this field. The use of artificial intelligence has given numerous advantages to the practicing engineers, which has immensely improved scheduling and management of construction activities resulting in huge economic benefits. This chapter explores use of artificial intelligence in different aspects of construction management and elucidates the problems encountered and presents possible solutions to the problems.

INTRODUCTION

Artificial intelligence is a system specifically designed to exhibit human-like behavior in decision making for solving complex problems. The decisions made by artificial intelligence are quick, efficient, and straightforward. Artificial intelligence is an interdisciplinary subject, which has inherent advantages over traditional modeling and statistical methods. The developed artificial neural networks (ANNs) are useful in the collection, analysis, and processing the data on a large scale. After that, the difference between actual and target values is computed to propose an activation function.

Artificial intelligence combines different fields such as computer science, neuropsychology, psychology, and information technology. The ANN is often used in the field of civil engineering due to its efficiency and lesser tune consumption in different aspects such as modeling, design, analysis, and optimization, which are veiy complex, time-consuming, and prone to error. The techniques of data collection and analysis are widely applied in the field of structural engineering, especially for predicting the strength of concrete. The ANN can be trained based on the experimental dataset for prediction of desired output parameters.

This chapter mainly focuses on different types of neural networks in cost pricing, scheduling, and estimation of various rent projects related to civil engineering. In the first pari, a brief introduction to the concept of activation function has been presented, hi the second part, a detailed literature review involving research works of the past two decades has been summarized concerning the utilization of ANN models in cost pricing, construction scheduling, and estimation. The third part deals with the identification of problems involved with currently employed ANN and proposed solutions. The final part deals with suggestions for improvement in the existing solution with scope for future work.

12.1.1 ELEMENTS OF NEURON

The biological networks are quite complex and very difficult to explain. A human brain is comprised of hundreds of biological neurons, and it is impossible to represent these neurons using a mathematical model. However, engineering problems can be simplistically represented by simple neural network models resembling the functioning of the actual brain, which can yield accurate results. The input signals are received by the artificial neuron from the brain. After that, output data and eveiy information or peripheral data of this neuron are generated, which can be used as the input data for further iterations. The input layer receives data from the surroundings and is processed in the hidden layers by the activation function. The output layer receives these processed data, which forms a solution of the problem. The input layer may comprise of n number of neurons, but eveiy neuron receives one input data only.

12.1.2 COEFFICIENT DESCRIBING WEIGHTS

The biological networks are quite complex and very difficult to explain. A human brain is comprised of hundreds of biological neurons, and it is impossible to represent these neurons using a mathematical model. However, engineering problems can be simplistically represented by simple neural network models resembling the functioning of the actual brain, which can yield accurate results. The artificial neuron receives the input signals from the brain. After that, output data and eveiy information or peripheral data of this neuron are generated, which can be used as the input data for further iterations. The data from surroundings received by the input layer are processed in the hidden layers by the activation function. The output layer receives these processed data, which forms a solution of the problem. The input layer may comprise of n number of neurons, but eveiy neuron receives one input data only.

 
<<   CONTENTS   >>

Related topics