No abstract

In sports competitions, depending on the conditions such as excitement, stress, fatigue, etc. during the match, negative situations such as disability or loss of life may occur for players and spectators. Therefore, it is extremely important to constantly check their health. In addition, some strategic analyzes are made during the match. According to the results of these analyzes, the technical team affects the course of the match. Effects can have positive and sometimes negative results. In this article, fog computing and an Internet of Things (IoT) based architecture are proposed to produce new technical strategies and to avoid disabilities. Players and spectators are monitored with sensors such as blood pressure, body temperature, heart rate, location etc. The data obtained from the sensors are processed in the fog layer and the resulting information is sent to the devices of the technical team and club doctors. In the architecture based on fog computing and IoT, priority processes are computed with low latency. For this, a task management algorithm based on priority queue and list of fog nodes is modified in the fog layer. Authentication and data confidentiality are provided with the Federated Lightweight Authentication of Things (FLAT) method used in the proposed model. In addition, using the Software Defined Network controller based on blockchain technology ensures data integrity.

No abstract

Özetçe-Bu çalışmada, metin madenciliği yöntemlerinde sıklıkla kullanılan terim frekansı-ters doküman frekansı (TF-IDF) metoduna dayanan iki yeni metin ağırlıklandırma yöntemi TF.TESDF ve TF.SADF önerilmiştir. Ayrıca önişlem aşamasında yeni bir yöntem olarak "metin sınıflandırmada fiillerin önemsizliği" yaklaşımları ortaya konulmuş ve test edilmiştir. Önerilen yöntemlerin diğer TF-IDF yöntemlerinden daha iyi sonuçlar verdiği görülmüştür. Ön işlem için kullanılan metinlerden fiillerin atılması yöntemi ile elde edilen başarının neredeyse hiç değişmediği, işlenecek verinin ortalama 1/6 oranında azaldığı gözlemlenmiştir. AnahtarKelimeler -metin sınıflandırma, terim ağırlıklandırma, ters doküman frekansı. Abstract -In this study, two new document weighting methods are proposed based on term frequency-inverse document frequency (TF-IDF) generally used in text mining methods. Also, insignificance of the verb in text classification which will be a new method in pre-processing have been put forward and tested. The better results were observed through using these methods when these methods compare with other method, It was observed that the performance rate hardly change and the data size which was processed decreased by omitting verbs of texts.

No abstract