Chandrabhushan Roy

Modelling thermal comfort of visitors at urban squares in hot and arid climate using NN-ARX soft computing method

Visitors utilize the urban space based on their thermal perception and thermal environment. The thermal adaptation engages the user’s behavioural, physiological and psychological aspects. These aspects play critical roles in user’s ability to assess the thermal environments. Previous studies have rarely addressed the effects of identified factors such as gender, age and locality on outdoor thermal comfort, particularly in hot, dry climate. This study investigated the thermal comfort of visitors at two city squares in Iran based on their demographics as well as the role of thermal environment. Assessing the thermal comfort required taking physical measurement and questionnaire survey. In this study, a non-linear model known as the neural network autoregressive with exogenous input (NN-ARX) was employed. Five indices of physiological equivalent temperature (PET), predicted mean vote (PMV), standard effective temperature (SET), thermal sensation votes (TSVs) and mean radiant temperature (Tmrt) were trained and tested using the NN-ARX. Then, the results were compared to the artificial neural network (ANN) and the adaptive neuro-fuzzy inference system (ANFIS). The findings showed the superiority of the NN-ARX over the ANN and the ANFIS. For the NN-ARX model, the statistical indicators of the root mean square error (RMSE) and the mean absolute error (MAE) were 0.53 and 0.36 for the PET, 1.28 and 0.71 for the PMV, 2.59 and 1.99 for the SET, 0.29 and 0.08 for the TSV and finally 0.19 and 0.04 for the Tmrt.

Prediction of ultrasonic pulse velocity for enhanced peat bricks using adaptive neuro-fuzzy methodology

Ultrasonic pulse velocity is affected by defects in material structure. This study applied soft computing techniques to predict the ultrasonic pulse velocity for various peats and cement content mixtures for several curing periods. First, this investigation constructed a process to simulate the ultrasonic pulse velocity with adaptive neuro-fuzzy inference system. Then, an ANFIS network with neurons was developed. The input and output layers consisted of four and one neurons, respectively. The four inputs were cement, peat, sand content (%) and curing period (days). The simulation results showed efficient performance of the proposed system. The ANFIS and experimental results were compared through the coefficient of determination and root-mean-square error. In conclusion, use of ANFIS network enhances prediction and generation of strength. The simulation results confirmed the effectiveness of the suggested strategies.

A comparative study for estimation of wave height using traditional and hybrid soft-computing methods

The present study developed a wave height prediction model by the recorded climatic data. We used 1-year buoy data for training and testing the developed soft-computing model. Models were developed using a novel method based on the Support Vector Machine (SVM) coupled with the Firefly Algorithm (FFA). This research work used the FFA for estimating the optimum parameters. In addition, this work compared the predicted results of SVM-FFA model to the artificial neural networks (ANNs) and genetic programming (GP). The results indicate that the SVM-FFA approach attains an improvement in capability of generalization and predictive accuracy in comparison to the GP and ANN. A thorough statistical analysis was conducted to compare the predictions of three models i.e., among the SVM-FFA, ANN, and GP. A high R2 value of 0.979 was obtained for the SVM-FFA predictions. Further, the ANN and GP results showed R2 values of 0.524 and 0.525, respectively. Moreover, achieved results indicate that the developed SVM-FFA model can be used with confidence for future research works on formulating novel models for predictive strategy on wave height. The results also show that the new algorithm can learn thousands of times faster than the former popular learning algorithms. This study finds that the application of SVM-FFA is the likely alternative method for estimating the wave height.

Evaluating the legibility of decorative arabic scripts for Sultan Alauddin mosque using an enhanced soft-computing hybrid algorithm

Ornamental calligraphy features sacred inscriptions in mosques as an integral part of its interior design. This study analyzes the legibility of these Arabic scripts for Malaysian users of mosques, implementing for the first time a quantitative tool for this effort, the ANFIS method. Our purpose is to identify the most influential parameters affecting the readability and understanding of various decorative Arabic scripts. Mosques have important roles in social life and in teaching the Islamic faith to Muslims. We conducted a questionnaire survey handed to the public attending the Sultan Alauddin mosque in Selangor, Malaysia. We subjected the data resulting from this survey to the ANFIS method (the adaptive neuro fuzzy inference system), to identify measurable parameters that play a role in the ability to read decorative Arabic scripts. The ANFIS process for variable selection was implemented in order to detect the predominant variables among the parameters identified. We analyzed how demographic aspects and cognitive skills relate to the ability to correctly interpret these scripts. The results indicated that of the parameters examined, the ability to read Arabic is the one that influences the most, the correct interpretation of ornamental inscriptions of mosques, and the best predictor of accuracy. The social role of mosques.The decoration of mosques features inscriptions.Calligraphy as a form of art.The readability of calligraphy.The most influential parameters related to the readability of Arabic calligraphy.