If you would like to write for this, or any other Emerald publication, then please use our Emerald for Authors service information about how to choose which publication to write for and submission guidelines are available for all. Please visit www.emeraldinsight.com/authors for more information. About Emerald www.emeraldinsight.comEmerald is a global publisher linking research and practice to the benefit of society. The company manages a portfolio of more than 290 journals and over 2,350 books and book series volumes, as well as providing an extensive range of online products and additional customer resources and services.Emerald is both COUNTER 4 and TRANSFER compliant. The organization is a partner of the Committee on Publication Ethics (COPE) and also works with Portico and the LOCKSS initiative for digital archive preservation.Abstract Traditionally, statistical time series methods like moving average (MA), autoregression (AR), or combinations of them are used for forecasting sales. Since these models predict future sales only on the basis of previous sales, they fail in an environment where the sales are more influenced by exogenous variables such as size, price, color, climatic data, effect of media, price changes or campaigns. Although, a linear regression model can take these variables into account its approximation function is restricted to be linear. Soft computing methods such as fuzzy logic, artificial neural networks (ANNs), and genetic algorithms offer an alternative taking into account both endogenous and exogenous variables and allowing arbitrary non-linear approximation functions derived (learned) directly from the data. In this paper, two approaches have been investigated for forecasting women's apparel sales, statistical time series modeling, and modeling using ANNs. Four years' sales data (1997)(1998)(1999)(2000) were used as backcast data in the model and a forecast was made for 2 months of the year 2000. The performance of the models was tested by comparing one of the goodness-of-fit statistics, R 2 , and also by comparing actual sales with the forecasted sales of different types of garments. On an average, an R 2 of 0.75 and 0.90 was found for single seasonal exponential smoothing and Winters' three parameter model, respectively. The model based on ANN gave a higher R 2 averaging 0.92. Although, R 2 for ANN model was higher than that of statistical models, correlations between actual and forecasted were lower than those found with Winters' three parameter model.

Engineered fabrics are desired for military protective clothing applications. Such fabrics, exhibiting high tactile comfort, can be computationally designed. Through the use of an extensive database that contains handfeel, mechanical, construction, and tactile comfort data for fabrics, desired comfort can be predicted by measuring a limited number of properties. Output systems can be optimized to exhibit the highest level of comfort by engineering a fabric with specific properties. Using an extensive fabric database, we identify the most significant handfeel, mechanical, and construction properties influencing tactile fabric comfort. This is done through the use of regression analysis of handfeel, mechanical, construction fabric properties, and perceived tactile comfort, using B un-standardized coefficients and Beta standardized coefficients.

Polymeric materials are finding increasing application in commercial optical communication systems. Taking advantage of techniques from the field of artificial intelligence, the goal of our research is to construct systems that can computationally design polymer formulations, including polymer optical fibers, with specified desirable consumer characteristics. Through the use of an extensive structure-property correlation database, properties of polymers can be predicted by an artificial network and the structure of novel polymers with desired properties can be optimized by a genetic algorithm. In this paper, we are focusing on one of the parameters, glass transition temperature (T g ) that influences a desired outcome in polymer optical fibers. Performance of such fibers can be optimized by engineering a polymer to exhibit a lower refractive index and T g . This paper compares and discusses a neural network model and a linear model that have been developed to correlate T g and repeating units of polymers. A neural network and multiple linear regression analysis were used in the study. A set of descriptors, chosen based on previous studies on the relations between T g and polymer structure, were used to describe the structure of repeating units, individual bond energies, and intermolecular forces, especially hydrogen bonding, which is the strongest intermolecular force and exerts the greatest influence on T g compared with other intermolecular interactions. A comprehensive neural network model with 28 descriptors was developed to predict T g values of 6 randomly selected polymers from a database containing 71 polymers. The network was trained with the remaining 65 polymers and had a typical training root mean square error of 17 K (R 2 = 0.95) and prediction average error of 17 K (R 2 = 0.85). A linear regression model developed for comparison had an average error of 30 K (R 2 = 0.88).

If you would like to write for this, or any other Emerald publication, then please use our Emerald for Authors service information about how to choose which publication to write for and submission guidelines are available for all. Please visit www.emeraldinsight.com/authors for more information. About Emerald www.emeraldinsight.comEmerald is a global publisher linking research and practice to the benefit of society. The company manages a portfolio of more than 290 journals and over 2,350 books and book series volumes, as well as providing an extensive range of online products and additional customer resources and services.Emerald is both COUNTER 4 and TRANSFER compliant. The organization is a partner of the Committee on Publication Ethics (COPE) and also works with Portico and the LOCKSS initiative for digital archive preservation. AbstractPurpose -The second of a two-part series, this paper aims to explain the design and development of a hybrid system for reverse engineering. Design/methodology/approach -A prediction engine to map the perception of tactile sensations using a neural network engine was developed. Since seventeen mechanical properties form the inputand tactile compfort score is used as the output -a direct reversal of the data set becomes impossible, hence, a hybrid approach was employed. The neural net is coupled with a genetic algorithm engine for the reversal process. The trained neural network acts as the objective function to evaluate the property set while the solution set is generated by Genetic Algorithm (GA) engine. Limitation of the GA and a means to overcome it is discussed. Application software based on the current research is also presented. Findings -Human perception of tactile sensations is non-linear in terms of the mechanical properties of textile materials. Originality/value -The paper deals with reverse engineering and discusses application software based on the current research. IntroductionEngineered product manufacturing is becoming an indispensable strategy for any manufacturer particularly with products involving direct human interaction. Textile materials contribute significantly to human well-being and require engineered product development. Two principal aspects of textile materials are functionality and comfort. Functionality can be achieved by incorporating specialized materials for the required set of properties. The importance of mechanical properties on the functional behavior of textile materials has been studied extensively. A comprehensive review of surface modification techniques employed for improved functional behavior of textiles can be found in Wei (2009). Unlike functionality, tactile comfort sensation forms a complex platform as it involves psycho-physiological phenomena. In his pioneering work, Stylios (1998) systematically defined principles for aesthetic measurements of textile materials. Stylios et al. (2002) further advanced the work by mapping the relationship between the drape attributes and fabric bending, shear and weight using neural networks. It ...

Quantitative structure-activity relationships (QSARs) are developed that correlate the observed mutagenic activity of 181 aromatic amine derivatives with a variety of molecular descriptors calculated using quantum-chemical semiempirical methodology. Conventional multiple linear regression techniques using five descriptors give a relationship that accounts for approximately 66% of the observed variation in the relative mutagenic behavior of these compounds; increasing the number of descriptors does not significantly improve the correlation equations. Approaches using artificial neural networks, in conjunction with fuzzy logic, can account for more than 90% of this variation using 10 descriptors.