BITS Faculty Publications
Permanent URI for this communityhttp://localhost:4000/handle/123456789/1867
Browse
41 results
Search Results
Item Automation in Site Management: A Qualitative Approach(IAARC, 2007) Barai, Sudhir KumarThis paper will address a new approach to construction management: Qualitative Construction Site Assessment System (QCSAS). QCSAS is essentially a site management software package. The objective of this system is three fold. Firstly, it aims to provide a holistic view of construction site to the project manager. It tries to achieve this by tracking essential factors like construction progress, construction quality, safety on site and resource requirement. Secondly, it assesses the condition of all factors on site in qualitative terms by using fuzzy logic. Thirdly, the system intends to achieve smooth information flow between various participants of site, i.e., the site supervisors, procurement officer, quality inspector, safety engineer, planning engineer and project manager with minimal effort and time wastage.Item Abonyi, Janos 43 Alchanatis, Victor 159 Avineri, Erel 221 Ballerini, Lucia 149(Springer, 2009) Barai, Sudhir KumarContains a collection of papers that were presented at the 12th On-line World Conference on Soft Computing in Industrial Applications, held in October 2007Item Neural Networks for Damage Detection in Steel Railway Bridges(IABSE, 1995) Barai, Sudhir KumarThe paper presents Artificial Neural Networks developed for typical steel railway bridges for the purpose of damage detection. Multilayer perceptrons have been used for generating the architecture for the bridges of different configurations. The back propagation algorithm has been adopted for training the network with simulated damage states. The training pairs have been generated using a standard finite element program. The weights of the trained networks have been stored and can be used as a knowledge source independently. It is demonstrated that the trained networks have practical relevance.Item Air Quality Prediction: An Opportunistic Neuro-Ensemble Approach(Sage, 2003) Barai, Sudhir KumarThe present article discusses the development of neural-network-based air quality prediction models which can work with a limited number of data sets and are robust enough to handle data with noise. Five different variations of neural network models (partial recurrent network (PRNM), sequential network construction (SNCM), self-organizing feature maps (SOFM), moving window (MWM), and integrated normalized autoregressive moving average-self-organized feature maps models (NARMA-SOFM)), were implemented in a WINDOWS environment using MATLAB software. Developed models were run to simulate and forecast the daily average data for three parameters: RPM (respirable particulate matter), SO2 (sulphur dioxide), and NO2 (nitrogen dioxide) for the Ashram Chowk location in New Delhi, India. The implemented models were found to predict air quality patterns with modest accuracy. To improve the models’ performance, an innovative approach using an opportunistic ensemble of the first four developed neural network models (OEM) was proposed for predicting the same short-term data. The ensemble approach indeed demonstrated an improvement on earlier models. However, the NARMA-SOFM model performed the best.Item Neural Networks Applications to Structural Identification: An Overview(University Presss, 2005) Barai, Sudhir KumarRecent developments in artificial neural networks (ANN) have opened up new possibilities in the domain of structural engineering. For inverse problems like structural identification of large civil engineering structures where the in situ measured data are considered to be imprecise and often incomplete, the ANN holds greater promise. The detection of structural damage and identification of damaged elements in a large complex structure is a challenging task indeed. In this paper, a general introduction to neural networks, its relevance to structural engineering and a review of lit-erature are presented in the context of neural networks application in structural identification. Finally, the unresolved issues warranting further investigation in the Indian context are identified.Item Material behaviour modelling using machine learning model(Springer, 2006-11) Barai, Sudhir KumarMaterial behaviour modelling involves the development &mathematical models based on experimental data, experts' observations and reasoning. Against the rigorous iterative exercise of developing mathematical models, machine learning (ML) model neural networks (NN) offer a fundamentally different and appealing approach to the derivation and representation of material behaviour relationships. Such networks would contain sufficient information about the material behaviour complexities, non-linear characteristics, stress strain behaviour, material properties etc. Further, these networks could be used effectively as material model to reproduce the trained experimental data and untrained experimental data. This paper addresses identification of comprehensive data set end developing a systematic approach for material model using NN Demonstration examples of this study are taken up using the experimentalItem Ensemble modeling or selecting the best model: Many could be better than one(1999) Barai, Sudhir KumarIn the course of data modeling, many models could be created. Much work has been done on formulating guidelines for model selection. However, by and large, these guidelines are conservative or too speci c. Instead of using general guidelines, models could be selected for a particular task based on statistical tests. When selecting one model, others are discarded. Instead of losing potential sources of information, models could be combined to yield better performance. We review the basics of model selection and combination and discuss their di erences. Two examples of opportunistic and principled combinations are presented. The rst demonstrates that mediocre quality models could be combined to yield signi cantly better performance. The latter is the main contribution of the paper; it describes and illustrates a novel heuristic approach called the SG (k-NN) ensemble for the generation of good quality and diverse models that can even improve excellent quality models.Item Air Quality Forecaster: Moving Window Based Neuro Models(Springer, 2009) Barai, Sudhir KumarThe present paper aims to demonstrate neural network based air quality forecaster, which can work with limited number of data sets and are robust enough to handle air pollutant concentrations data and meteorological data. Performance of neural network models is reported using novel approach of moving window concept for data modelling. The performance of model is checked with reference to other research work and found to be encouraging.Item Neuro-ensemble for air quality prediction(Loughborough University, 2002) Barai, Sudhir KumarThe present study investig; ttes the advantage of ensemble of neural networks (Haykin, 2000) for forecasting the air pollution. The aim is to find accurate air quality predictors, which can work with low number of data sets and should be robust enough to handle data with noise and errorsItem Fuzzy logic based bridge management system for handheld devices(IEEE, 2007) Barai, Sudhir Kumarhe paper aims at presenting initial development of prototype system for bridge inspection, condition evaluation and record maintenance. The system is supposed to be accessible from handheld devices such as common mobile phones and personal digital assistants, for the system to be easily usable at a remote location too. It will also be free from the network availability constraints in case of mobile phones. In short, it will be an entirely standalone application. In the proposed system the procedure of inspection is standardized and the analysis is done qualitatively. The linguistic data is converted to mathematical format for its assessment by the use of popular fuzzy logic approach.