M. Fatih Adak

Forecasting natural gas consumption with hybrid neural networks — Artificial bee colony

Natural gas distribution companies have different consumer types including manufacturing industry, organized industrial zones, food and beverage industry, household and other low consuming enterprises, etc. Leading two categories of these consumers are household and low consuming enterprises as they have high consumption in winter whereas low in summer. The paper studies consumption demand forecasting for certain consumption group using artificial neural network (ANN). Prepared consumption data is divided into two groups. First three years daily consumption data is kept for training while forth year data is kept for testing. For consumption forecasting its own historical data is used. The research is completed by applying two different model types having eleven different sub-models each. Sub-models have different numbers of neurons and three hidden layers at most. Estimations are done with twenty-two different scenarios in total. In two distinct models, ANN weights are trained with backpropagation (BP) and artificial bee colony (ABC) algorithms. After training stage, network structures are tested by test datasets. As a result, it is concluded that ABC model with two hidden layered scenarios gives better results in demand forecasting than the others.

An elective course suggestion system developed in computer engineering department using fuzzy logic

Besides required courses which are compulsory for each student to be taken, universities also offer elective courses chosen by the students themselves. In their undergraduate study, since students are not guided about the elective courses, they lack information about the description and content of the course and generally fail to take the appropriate ones for their course of study. As a solution, using the knowledge of the previous required courses taken by the student it is possible to guide the student about elective courses appropriate for him/her. In this study, information from the transcripts of students are analyzed, and using this information a relationship is conducted between the required courses and the elective courses taken previously by the student. Rules are extracted by the help of data mining and an elective course suggestion system is developed using fuzzy logic. Successful results are obtained from the tests; it is observed that the students successful from the required courses are also successful in the related elective ones.

Time series forecasting using artificial bee colony based neural networks

Artificial neural networks (ANN) are among the nonlinear prediction techniques popular in the last two decades. Recent studies show that ANN can be modeled with different training techniques. ANN is usually trained by the backpropagation method (BP). In this study, ANN structures were trained by using artificial bee colony algorithm (ABC) and, weight and bias values were tried to be determined. ABC training (ANN-ABC) was tested over three different datasets and compared with the BP training (ANN-BP) results. In addition to use ABC in modeling, different error types such as mean square error (MSE), mean absolute percent error (MAPE) and adjusted coefficient of determination (R) have been used in the training. The results on popular time series datasets have shown that ABC based ANN training yields successful results in forecasting.

Development of smart gas sensor system to classify binary gas mixtures

Solvents are used in a large number of industries especially in cleaning and cosmetic. Solvents are known to be harmful to human health. Classification of solvent in a product is important to determine the level of hazard that can people faced. In this study, three different solvents, methanol, acetone, and chloroform, are used to obtain binary gas mixtures in a laboratory environment. A gas sensor system that has 9 QCM sensors is used to obtain binary gas mixtures data. The developed system uses artificial neural network trained by artificial bee colony algorithm. This hybrid algorithm is used to classify binary gas mixtures. Too many scenarios are tested and it is observed that classifying binary gas mixtures by ANN-ABC hybrid method gives successful results and increased the classification performance of test data by 71.43%.

Finding cuts point of textile products using blob analysis method

This study includes a cuts point finding algorithm on textile products. Most of the textile product especially laces and curtains have spare part on bottom of the product. This spare part is used for setting product up to machines. Until product finalizing, this part is used, but before packing operation, it must be cut. This operation mostly done with human force but machines can do this too. This study explains how blob analysis method can be used to find cuts point. According to this algorithm steps we will get cuts point coordinates that can be input of a cutting machine.