Enes Celik

Earthquake prediction using seismic bumps with Artificial Neural Networks and Support Vector Machines

Earthquakes are what happens when immediate vibrations which shake earth surface, spread as waves as a result of earth crust cracks. Earthquakes depend on variables such as the way of spreading of these waves, calculation of these waves and calculating methods, evaluations of these recorded data sets. Predicting probable earthquakes and minimizing the damages are the important factors. Decision systems can be developed only through using seismic bump data. At this point, seismic data will be classified first and then comparative results will be analyzed at the test stage. We use end seismic data obtained from mine pit which are classified through classification algorithms. Artificial Neural Networks and Support Vector Machine are used in the classification. Early detection rate is calculated as 83% with the classification through Artificial Neural Network. Early detection rate is calculated as 91% with the classification through Support Vector Machine.

Detection and estimation of down syndrome genes by machine learning techniques

Down syndrome is accepted as the common birth defect in population and diagnosed as more physical development with less cognitive activity than an average human. Early diagnosis of disease play important role for the patient future life. Computer aided systems, in terms of artificial intelligence, results more accurate and consistent diagnosis in the detection and estimation of down syndrome genes compare to doctor decisions. In this study, detection and estimation of down syndrome disease is maintained by analyzing the protein levels in genes. In this sense, a Decision Support System based on machine learning techniques are proposed to estimate the down syndrome automatically. Additionally, another technique named as Principal Component Analyses are performed to eliminate multi proteins in genes into fewer number to achieve the same success with less information.

The mesothelioma disease diagnosis with artificial intelligence methods

Asbestos is a carcinogenic substance, and threatens human health. Malignant Mesothelioma disease is one of the most dangerous kind of cancer caused by asbestos mineral. The most common symptom of the disease, progressive shortness of breath and constant pain. Early treatment and diagnosis are necessary. Otherwise, the disease can lead people to die in a short period of time. In this paper, different types of artificial intelligence methods are compared for effective Malignant Mesotheliomas diseases classification. Support Vector Machine, Neural Network and Decision Tree methods are selected in terms of regular machine learning concept. Additionally, Bagging and Adaboost re-sampling within ensemble learning terminology is also adapted. Totally 324 Malignant Mesothelioma data which consists of 34 features is used in this study. K-fold cross-validation technique is performed to compute the performance of the algorithms with different K values. 100% classification accuracies are obtained from three tested methods; Support Vector Machine, Decision Tree and Bagging. Additionally, the process time of methods are measured in case of using method in lots of data. In this sense, methods are evaluated based on accuracy and time complexity. The results of this paper are also compared with previous studies using same Malignant Mesotheliomas dataset.

Detection of fake banknotes with Artificial Neural Networks and Support Vector Machines

The document and banknote counterfeiting remove us as a usurpation of the rights of individuals and institutions. By the advancement of technology special paper, the ink usage in the original banknote, placing watermarks, micro text are challenged to fraud that also does not prevent the counterfeiting of widespread. The counterfeit banknotes detection and minimizing damage is one of the important elements. In this, decided and expert systems can be improved to estimate the counterfeit banknotes to using dates of the moneys. The data of banknotes are sorted before to this point, after comparative results are discussed of the testing. In this study, it is classified by the classification algorithms to using digitized available data of real and counterfeit banknotes images. Artificial Neural Networks and Support Vector Machines are used in the classification. Correctly identified is detected to rate of 74.6% in the test results which is tested by Artificial Neural Networks, correctly identified is detected to rate of 93.8% in the results of tests which is tested by Support Vector Machines.

Early detection of hazardous weather conditions in Turkey with satellite images using Support Vector Machines and Artificial Neural Networks

The prediction of meteorological phenomena resulting from rainfall, is one of the most important elements of the minimization of the damages. Local meteorological radars works at regional base hence they cannot represent the parameters of precipitation. Because of insufficiency of the radar systems early detection, satellite images can be used to create decision systems. At this point firstly infrared satellite images will be classified and then comparative results will be discussed on experimental stage. In this work, we used Wavelet Transform applied to infrared satellite images to extract approximation coefficients. Size of these coefficients are reduced using Principal Component Analysis and classified through classification algorithms. Artificial Neural Network and Support Vector Machines are used for classification. As a result of the classification made with Artificial Neural Networks, we accomplished 84% prediction rate. With the classification of Support Vector Machines, we reached 93% prediction rate.

Assamese character recognition with Artificial Neural Networks

Nowadays characters that written on tablets with electronic pens are recognized and classified by computers so these are most used applications. In this study (x,y) coordinate values of hand-written Assamese characters are saved by this program. Features can be found by getting maximum, minimum, average, variant, Standard deviation and range values after size of these values are decreased by Principle Component Analysis. These features classified as Feed Forward Backpropagation Artificial Neural Network and Radial Basis Artificial Neural Network.Test results are compared after classification. In this study, online Assamese hand written tool and database of University of California Computer and Information Science department is used. Test results show that Feed Forward Backpropagation Artificial Neural Network %96 successful although Radial Basis Artificial Neural Network %82 successful.