Genetic Algorithm Based Timetabling Program

Course Timetabling Problem is concerned with assigning a number of courses and instructors to classrooms by taking the constraints into consideration. Generally, this problem is typically resolved manually; and due to the large variety of constraints, resource limitations and complicated human factors involved, it takes a lot of time and manpower. It is considered as one of the most time-consuming problems faced by universities and colleges today. In this study, we aimed to develop a genetic algorithm-based timetabling software to bring a solution to course timetabling problem, which is a real world problem. This software allows constraints to be entered easily and allows that optimal solutions are found. To find the most suitable solution for optimization, two different solution methods, a full-genetic algorithm and a partial-genetic algorithm, were tested. Test results showed that when we start the full genetic algorithms from randomly generated initial population, it takes quite some time to obtain the appropriate solution. With the partial-genetic algorithm, an optimal solution was achieved much more quickly than the full genetic algorithm.

Intelligent Traffic Signaling Control Using Petri Nets

Transportation vehicles refer to the vehicles used to transport people's needs and goods from one area to another. Intelligent traffic signalling systems are needed due to the increase in the number of vehicles in traffic, the roads used, the insufficiency of the surrounding areas and the inability to widen these roads or construct upper / lower roads. Nowadays, there are situations where traffic control is insufficient in current density due to the traffic system mechanisms being dependent on fixed time. Therefore, some smart methods have been developed to prevent waste of time and economic problems. In this study, application of Petri Nets (PA) based on real data collected at certain times of the day for intelligent control of traffic lights at a four-way intersection. PA's performances have been compared with their classical (fixed time) performances. When the results obtained were evaluated in terms of both the number of passing vehicles and time, it was seen that the PA passed 849 vehicles in 755 seconds, 341 vehicles in 920 seconds in the classical method and a better result was obtained with PA.

Shuttle Run Analysis with Image Processing

Increasing auto control systems in the light of today's technological developments, designing unmanned control mechanisms that can meet requirements such as the need for accurate measurement and analysis is the main goal. With the developed software, it was aimed to make time analysis of the athletes with shuttle running in indoor sports halls with the help of a camera and to store these analyses in the computer environment. No solution is available on the current problem. Similarly, there are prospective projects of traffic in the traffic bases and these are based on the work on them. In this thesis study, firstly moving objects in the image are captured, followed by images that match the color filter specified later. As a result of follow-up, the data such as lap times are stored. The end result is that the athlete's data have been successfully measured and stored.

A Method on The Translation of The Words Written by Ottoman Alphabet to Turkish Alphabet

The Ottoman alphabet was used as a writing language in Turkish with Arabic letters. The Turkish alphabet is used as a writing language in Turkish with Latin letters. There are numerous documents written in the Ottoman alphabet in the archives. In this study, the image of the words written in the Ottoman alphabet was converted into editable text by optical character recognition method. In this way the words are translated into text. Later, the characters in these words were made understandable by using their equivalents in the Turkish alphabet. It was tried to increase the accuracy rate by comparing the words translated into Turkish alphabet and the table where Turkish words were found. An algorithm that gives a similarity value is used for the comparison process.

Expert Systems Approach to Route Selection

Directing technical teams in which companies in the service industry required to call on a daily basis to customers; is carried out with the help of the route that is generated manually by an employee according to acquired experiences, appointment intervals dedicated to different customers and customers ' requests and priority. The manually route generating may cause some losses (time, financial, manpower, etc) by the virtue of the situations and work load may be missed, the difficulty in determining the costs and priority.In this article, an expert system approach that can revise itself according to operators’cost and customer-oriented approach and can balance the level of customer satisfaction and financial profit has been developed. In this respect, it is aimed to determine the most appropriate route for technical teams based on the priorities determined by the operator, to increase work efficiency during the day, to reduce the costs of accessing and planning work and to keep customer satisfaction at the top level.

Business Intelligence Application For Campaign Magagement In The Retail Sector

Access to and retain information has become easier with the emergence of information technology. All of the processes of analyzing the data of the enterprises by using information technologies and making them more meaningful and useful are called business intelligence. It will be very useful for enterprises to benefit from business intelligence solutions in marketing, campaigning and decision-making processes. In this study, business intelligence concept and the required infrastructure for benefiting from business intelligence applications were examined. According to the investigation, a sample application for retail sector was developed as well as how the businesses will benefit from business intelligence applications and its contributions to the applied sectors were emphasized.

Detecting Fake Twitter Accounts with using Artificial Neural Networks

Online Social Networks (OSNs) are great environments for sharing ideas, following news, advertising products etc., and they have been widely using by people. Although these advantages of OSNs, it is difficult to understand whether an account in OSNs really belongs to a person or organization. Through created fake accounts, unwanted content can spread over the social network. Therefore, the identification of fake accounts is an important problem. In this study, we applied Artificial Neural Network (ANN) classifier to this problem and we evaluated performances of different activation functions. According to the experimental results, use of artificial neural networks in detecting fake accounts yielded successful results. The use of various activation functions in different layers on the ANN significantly affects the results. In the literature, other classification methods have been widely used for detecting fake accounts and spammers on OSNs. To the best of our knowledge, there is no detailed study that classifies fake accounts using ANNs with different activation functions.