Aydın Çetin

Resident activity recognition in smart homes by using artificial neural networks

Recognition and detection of human activity is one of the challenges in smart home technologies. In this paper, three algorithms of artificial neural networks, namely Quick Propagation (QP), Levenberg Marquardt (LM) and Batch Back Propagation (BBP), have been used for human activity recognition and compared according to performance on Massachusetts Institute of Technology (MIT) smart home dataset. The achieved results demonstrated that Levenberg Marquardt algorithm has better human activity recognition performance (by 92.81% accuracy) than Quick Propagation and Batch Back Propagation algorithms.

Diagnosis of Chronic Kidney Disease Based on Support Vector Machine by Feature Selection Methods

As Chronic Kidney Disease progresses slowly, early detection and effective treatment are the only cure to reduce the mortality rate. Machine learning techniques are gaining significance in medical diagnosis because of their classification ability with high accuracy rates. The accuracy of classification algorithms depend on the use of correct feature selection algorithms to reduce the dimension of datasets. In this study, Support Vector Machine classification algorithm was used to diagnose Chronic Kidney Disease. To diagnose the Chronic Kidney Disease, two essential types of feature selection methods namely, wrapper and filter approaches were chosen to reduce the dimension of Chronic Kidney Disease dataset. In wrapper approach, classifier subset evaluator with greedy stepwise search engine and wrapper subset evaluator with the Best First search engine were used. In filter approach, correlation feature selection subset evaluator with greedy stepwise search engine and filtered subset evaluator with the Best First search engine were used. The results showed that the Support Vector Machine classifier by using filtered subset evaluator with the Best First search engine feature selection method has higher accuracy rate (98.5%) in the diagnosis of Chronic Kidney Disease compared to other selected methods.

Finding a best parking place using exponential smoothing and cloud system in a metropolitan area

Finding a vacant place to park cars in the rush hour is time-consuming and even may be frustrating for the drivers. In some studies, vehicles are equipped with communicative tools called On Board Units (OBUs), which come along with roadside devices known as Roadside Units (RSUs), which allow the drivers to communicate each other and trace a vacant parking place easily. Previous systems work with connection of sensors all over the road and parking space and may result in spending much time to find a parking place, occupancy of the empty parking place until the car gets to the desired location, requirement for an additional hardware, wired network communication, and security issues. In this paper, we propose an exponential smoothing and multi-objective decision-making by using cloud-based methods to find the best parking place, taking into consideration of the park-cost for the driver. The proposed system uses the cellular base stations to eliminate the cost of the RSUs and the sensors. The results of our simulations via NS-2 network simulator confirm the efficiency of the proposed model.

A 3D game based learning application in engineering education: Powering a recreational boat with renewable energy sources

In this paper, a game based learning application in engineering education is presented. A Learning module with support of a 3D game environment was developed to teach the design of driving system of a recreational boat powered with renewable energy sources. 3D game was designed to enable learners to meet learning objectives of competency based learning module. The 3D game environment enables experiential learning so that learners are able to practice real world problems.

Planning of the GSM network broadcast control channel with data fusion

Global System for Mobile (GSM) technology has a non-linear and complex system structure. Naturally, establishment, operation, management and optimization of such technology require great work. Besides technological point of view, the network optimization is also an economical factor that becomes more critical because of limited sources such as limited number of allocated frequency channels. GSM base station has vast network structure, so the number of frequency channels for each cell and the frequencies to be used in cells should be determined synchronously. In this paper, the frequency planning of the broadcast control channel (BCCH) of the GSM network has been performed with the data fusion by using actual data of the base station (BS) which belongs to a sample region under study. Then, the frequency management and planning have been activated in a sample region by applying the results obtained with data fusion process which is realized with the application of genetic algorithm.

3D Technology Selection for a Virtual Learning Environment by Blending ISO 9126 Standard and AHP.

Web3D presents many opportunities for learners in a virtual world or virtual environment over the web. This is a great opportunity for open-distance education institutions to benefit from web3d technologies to create courses with interactive 3d materials. There are many open source and commercial products offering 3d technologies over the web enabling developers to create interactive 3d contents and course materials. However, characteristics of 3d technology to be used may change according to needs of users or developers. This situation naturally leads to a decision problem. Decision problems are also related to optimization problems, which are concerned with finding the best answer to a particular problem. This article presents and discusses a hierarchic and quality approach for solution of optimization problem which asks the best solution for a web-based 3d technology selection problem.