Volume 10 - 2018

Planning a radio network

Abstract

Planning a radio network is a very complex process involving planning capacity, coverage and frequency. Each of these planning processes requires first of all to look at the needs of the users. Such as the speed of voice transmission and data in wireless and mobile communications, the coverage of the scope of operation. All these processes and methods that are necessary for the planning of radio networks are described in detail in this work. All these processes and methods that are necessary for the planning of radio networks are described in detail in this work. In addition, the possibilities for using the WinProp program are described.

Keywords: Планирање радио мрежа, планирање капацитета, планирање покривености, планирање расподеле фреквенције, WинПроп.
Published on website: 16.7.2018

CLASSIFICATION ALGORITHMS FOR THE DETECTION OF THE PRIMARY TUMOR BASED ON MICROSCOPIC IMAGES OF BONE METASTASES

Abstract

This paper presents the analysis of techniques for microscopic images in order to find a primary tumor based on the of bone metastases. Was done alg orithmic classification into three groups, kidney, lung and breast. In order to speed up the treatment of the patient and easier for doctors and therefore reduce room for human error. Digital microscope images of bone metastases were analyzed, for which it is known that the primary tumor is in one of the three human organs: kidney, lung or breast. We tested several solutions for classification, were tested two methods of image analysis. Multifractal analysis and convolutional neural network. Both methods were tested with and without preprocessing image. Results of multifractal analysis were then classified using different algorithms. Images were processed using CLAHE and k-means algorithm. At the end, the results obtained using a variety of techniques are presented.

Keywords: Класификација канцера, микроскопске слике, препроцесирање слика, мултифрактална анализа, алгоритми класификације
Published on website: 22.4.2018

TRAFFIC SIGN RECOGNITION AND CLASSIFICATION USING CONVOLUTIONAL NEURAL NETWORK

Abstract

Artificial Neural Networks enables solving many problems in which classical computing is not up to task. Neural Networks and Deep Learning currently provide the best solutions to problems in image recognition, speech recognition and natural language processing. In this paper a Neural Network, more specific - Convolutional Neural Network solution for the purpose of recognizing and classifying road traffic signs is proposed. Such solution could be used in autonomous vehicle production, and also similar solutions could easily be implemented in any other application that requires image object recognition.

Keywords: Неуралне мреже, конволуционе неуралне мреже, класификација, саобраћајни знакови.
Published on website: 16.7.2018