1976 İstanbul doğumluyum. Evliyim. Bir kız çocuğum var.
Scuba dalış yapmak
1976 İstanbul doğumluyum. Evliyim. Bir kız çocuğum var.
Scuba dalış yapmak
Objective: To evaluate diagnosis accuracy of immunos algorithms for classification of migraine, tension-type and cluster-type of headaches by using our website based diagnosis survey expert system.
Methods: The headache diagnoses of eight-hundred and fifty patients from three different cities in Turkey were evaluated by using immunos algorithms. Data were collected through our website based diagnosis survey expert system under the guidance of neurologists.
Results: Immunos algorithms for diagnosis have the maximum accuracy of 95.65% which can be used for classification. Conclusion: It is possible to classify primary headaches with immunos algorithm and using our website based diagnosis expert system will be helpful for neurologist in order to obtain precise results as well as easy information sharing.
Direct marketing in telephone banking has been an important topic recently. The success of such campaigns is directly proportional to the effective customer participation. The success rate of such campaigns that especially conducted by banks may be enhanced by data mining methods. The main purpose of this study is to implement the classification process via ant colony optimization which is a heuristic algorithm in data mining for telephone banking dataset. The real world data from a bank in Portuguese for analysis. The possibilities of the customer credit subscription were estimated by using ant colony optimization algorithm and the results were compared to other commonly used methods in data mining. The rate of the success were calculated by classifcation accuracy, sensitivity and spesificity.
The present study evaluated the diagnostic accuracy of immune system algorithms with the aim of classifying the primary types of headache that are not related to any organic etiology. They are divided into four types: migraine, tension, cluster, and other primary headaches. After we took this main objective into consideration, three different neurologists were required to fill in the medical records of 850 patients into our web-based expert system hosted on our project web site. In the evaluation process, Artificial Immune Systems (AIS) were used as the classification algorithms. The AIS are classification algorithms that are inspired by the biological immune system mechanism that involves significant and distinct capabilities. These algorithms simulate the specialties of the immune system such as discrimination, learning, and the memorizing process in order to be used for classification, optimization, or pattern recognition. According to the results, the accuracy level of the classifier used in this study reached a success continuum ranging from 95% to 99%, except for the inconvenient one that yielded 71% accuracy.
The objective of this study is to determine the most convenient decision tree method in terms of accuracy and classification built time by comparing the performance of decision tree algorithms with the purpose of identifying the spam e-mails.
The data were gathered from one of the datasets of University of California machine learning datasets including 4601 e-mails for the classification of spam. The spam e-mails were classified utilizing 10 fold cross validation by using WEKA machine learning software involving 12 different decision trees. The performance of this classification was found by implementing the principle component analysis.
It was found that the performance of decision trees on determining spam e-mails showed accuracy rate ranging between 91% and 94.68%.
Random Forest algorithm was found to be the best classifier with the accuracy rate of 94.68%. It was understood that this algorithm can classify spam e-mails quickly in a hectic e-mail exchange system because the classification built time of the algorithm is 2.11 seconds for the 4601 e-mails.
Computer supported studies in wide range of medical fields have been greatly expanded in recent years. Also, many medical organizations continue to build databases for different diseases. This medical database for artificial intelligence techniques for the determination of the disease is invaluable. As a subset, artificial neural networks and decision tree techniques are used for disease diagnosis. In this study Gini algorithm from decision trees and distributed delay network, probabilistic neural network, feed-forward network and learning vector quantization from artificial neural network have been used in order to diagnose migraine and probable migraine. Performance of these techniques has been compared and distributed delay network technique is observed as the best diagnosis with 95.45% accuracy.
According to World Bank Logistics Performance Index Turkey ranks 27. Turkey, logistics performance index of which compared to previous years has been improving, should rank on the top according to 2023 economic objectives. Therefore, it should improve its economic infrastructure. In addition, it should model the logistics facility differences well among the successful countries in terms of logistics and maritime sector. It is also necessary to analyze the differences in logistical infrastructures between Turkey and leader countries in maritime and logistics in order to make the right investment decision. therefore it is necessary to collect, prepare, model and analyze data globally in logistics field. One of the best ways of modelling is data mining. Data mining can provide valuable data to include future related predictions and its showing clearly the present situation in the knowledge cluster in a specific topic. In this study, the applications of data mining in logistic sector in various fields were shown and it evaluates the importance of it in the case of Turkey.
İstenmeyen SMS mesajları her ne kadar ülkemizde devlet kontrolü altına alınmaya çalışılsa da tam olarak önlenememiştir. Akıllı telefon kullanımının artışıyla beraber kötü amaçlı yazılımlarından telefonlara bulaşma olasılığı artmıştır. Bu sebeple geliştirilen istenmeyen SMS tespiti ve filtrelemesi uygulaması için bu çalışmada kullanılan karınca koloni algoritması performansı diğer çalışmalarda ki bilinen diğer algoritmalarla kıyaslanmıştır. Elde edilen sonuçlara göre karınca koloni algoritması %94 doğru sınıflandırma oranı ile en iyi performansı göstermiştir.
Veri madenciliğinde, birliktelik analizi büyük verilerde yer alan ilişkilerin ortaya çıkarılarak keşfedilmesinde çok popüler ve iyi bir araştırma metodudur. Birliktelik kurallarının çıkarılması için birçok algoritma mevcuttur. Bunların içinde en popüler olanı büyük verilerde birliktelik analizi yaparak ilişkisel boyutları ortaya koyan ve büyük verilerden bilgi keşfini sağlayan apriori algoritmasıdır. Bu çalışmada bu algoritma metin madenciliği ve metin analizleri için kullanılacaktır. Metin madenciliği metnin doğal dilinde verilerin analizidir. Metin analizleri, bilgi çıkarımı ve sözcüksel analiz ile ilişkilidir. Bu analizler kelime sıklık dağılımlarını gözlemlemek için örüntü tanıma, etiketleme/açıklama, bilgi çıkarımı, bağlantı, ilişki analizi, görselleştirme ve öngörü analitiğini yapan veri madenciliği teknikleridir. Bu çalışmanın amacı; Yönetim Bilişim Sistemleri (YBS) alanında ele alınan konuların önem sırasının belirlenmesi ve yüksek kalite bilgilerin YBS alanında yazılmış bilimsel makalelerdeki anahtar kelimelerden çıkarılmasıdır.
Wastewater treatment systems speed up natural cleansing process to achieve the desired treatment objectives. Prediction of the obtained wastewater treatment characteristics provides to set up existing process steps and it is important to achieve maximum process efficiency. In this study, a computer aided decision tree based on gini algorithm is developed for estimating important output parameters of wastewater such as pH, DBO, DQO, and SS. Used dataset in this study was obtained from the University of California Irvine (UCI) Machine Learning library.