Labour costs in the apparel manufacturing industry in Bangladesh have increased dramatically. Hence, there is no alternative way to optimize the apparel supply chain to survive in the competitive market. In this study, we implemented artificial neural networks (ANN) in apparel manufacturing organizations to optimize the supply chain by convergent on the right supplier selection by analyzing their performance criteria. Moreover, data was collected from three different factories to analyze the efficiency and profit-loss status of their units. Furthermore, analyze the supplier selection criteria of three suppliers in order to select the right supplier at the right time in the apparel manufacturing industry. This study shows that it can save 18% of the total cost. Additionally, the mathematical analysis has been performed to validate the data analysis for the right supplier selection based on the performance criteria.
Shibbir Ahmad and Mohammad Kamruzzaman (2022) Optimization in Apparel Supply Chain Using Artificial Neural Network, European Journal of Logistics, Purchasing and Supply Chain Management, Vol.10 No.1, pp.1-14
Biometric Authentication of Remote Fingerprint Live Scan Using Artificial Neural Network with Back Propagation Algorithm and Possibility for Wider Security Applications (Published)
This study is aim to experiments the development of an automated foolproof university library system that integrates fingerprint technique with fingerprint-based Personally Identified Number (PIN)/password architecture for enhanced registration and login security. The development environment for creating the electronic library application for universities as RESTful Web Service is Jersey Framework. This framework implements JAS-RX 2.0 API, which is a de facto specification for developing a RESTful Web Service-based software system. Other necessary programming technologies employed in the research work are JDK, Apache Tomcat and Eclipse, which were set up prior to setting up the Jersey Framework as the development environment. The study is therefore summarized by generating hash digital values of perfectly matched reference shape signatures formed from the extraction of global minutiae features, comparing and further matching each hash value with its corresponding highly encrypted password equivalence for unique establishment of a person’s identity, minimal mean-square errors and unnecessary ambiguity introduced through false positives, as an extended security enhancement measure in biometric systems. , the study investigates the algorithm for generating templates for matching minutiae  together with the algorithm for generating reference axis , which infers that for a pair of minutiae (pn , q0) to match, there exists a reference point that corresponds between the two fingerprint images. The experimental result shows that the Sample fingerprint images were captured using a biometric scanner, which was integrated with the help of JAVA libraries, and stored in a database as raw image files..
Prediction and Modeling of Seasonal Concentrations of Air Pollutants in Semi-Urban Region Employing Artificial Neural Network Ensembles (Published)
This study utilizes Artificial Neural Network (ANN) ensembles to predict seasonal variation of air pollutants in semi-urban region of Eleme, Rivers state, Nigeria. A ten year monthly concentrations of SO2, NO2, CO and CH4 in the region was obtained for dry and rainy seasons. Air pollutant concentrations in semi urban area of Eleme can be attributed mainly to industrial activities, vehicular emissions and some local background concentrations influenced by meteorological and geographical conditions of the area. Training of the network models was achieved using Neural NetTime Series feature of MATLAB software. Observed concentrations of pollutants and meteorological parameters were used as input variables for the prognostic models. The developed ANN prognostic models accurately captured the dynamic relationships between pollutant concentrations and meteorological predictor variables. The relationships between predicted and observed values were highly significant at 95% of confidence level for all models as dry and rainy seasons models gave R2 greater than 0.99 (indicating close relationships between observed and predicted values). CH4 showed R2 of 0.9946 and 0.9974 for dry and rainy seasons respectively; CO showed R2 of 0.9918 and 0.9972 for dry and rainy seasons respectively; NO2 showed R2 of 0.9998 and 0.9982 for dry and rainy seasons respectively; SO2 showed R2 of 0.9921 and 0.9991 for dry and rainy seasons respectively. The trend in predicted pollutants indicated that the study area is a major receptor of air pollutants emanating mainly from industrial activities and vehicular exhaust emissions. Further research study is needed to compare ANN model with other modeling approaches such as with multiple linear regression models for the prediction of air pollutants.
Friction stir welding (FSW) is a relatively new welding process that may have significant advantages compared to the fusion processes as follows: joining of conventionally non-fusion weldable alloys, reduced distortion and improved mechanical properties of weldable alloys joints due to the pure solid-state joining of metals. This work presents a systematic approach to develop the mathematical model by three methods such as artificial neural networks using software, Response surface methodology (RSM) and regression Analysis for predicting the ultimate tensile strength, percentage of elongation and hardness of 6061 aluminum alloy which is widely used in automotive, aircraft and defense Industries by incorporating (FSW) friction stir welding process parameter such as tool rotational speed, welding speed and material thickness. The results obtained through regression analysis and response surface methodology were compared with those through artificial neural networks
System and environmental parameters affecting the output of the wind farm system at different stations in Jordan have been computationally investigated, using artificial neural network (ANN). For the several variables identified, statistical analysis was employed to indicate their relative significance to the targeted output, with the aid of the Pearson’s correlation coefficients. ANN shows proficiency in the prediction of the original experimental data for all the stations and turbines. In the simulation, the energy gain increases with the increase in the system and environmental parameters. However, there appears to be a phenomenon of threshold value in the output parameter, which limits the impacts of change in the input parameters on the eventual response of the output. It can be deduced that there is a minimum energy gain value below which increase in any of the system/environmental parameters will not have positive impact on the energy output. Findings show that the turbine characteristics, like rotor diameter and hub height, have more significant impact on the energy gain than the environmental factor like wind speed. The uniqueness of this work is that it predicts the important output of the wind farm system based on the logical arrangement of detailed parameters that are found in all operational units of the system in order to elicit desired effects.