Abstract: In this paper, we propose and evaluate OFDM(Orthogonal Frequency Division Multiplexing)-SSB(Singe Side Band) for improving spectral efficiency. The proposed system is based on OFDM system using DCT(Discrete Cosine Transform) and DHT(Discrete Hilbert Transform). This proposed system transmits a BPSK (binary phase shit keying) modulation signal through a single sideband. Therefore, spectrum efficiency can be improved into 2 times than the conventional DSB(double sided band) communication system. Conclusively, the proposed system can transmits two different BPSK signal with each different single sideband in DSB band.

• Publication Date: 19-Aug-2016
• DOI: 10.15224/978-1-63248-099-6-28
• Views: 0
• Downloads: 0

Abstract: Deep learning algorithms have become popular methods for pattern recognition due to their advantages over traditional methods such as providing deep representations of data, high-level semantic features. Deep convolutional neural network is one of the deep learning technique used in computer vision. Deep convolutional neural network consists of alternating convolution and pooling layers, and feedforward layers after them. It has not a fixed structure hence determining the optimal structure such as number of convolution and pooling layers, kernel size of these layers is crucial for faster and high performance implementations. Hence, in this work different convolutional neural network structures were established and tested on recognition of 28x28 MINST handwritten digits. According to the test results, kernels should cover at least 2 neighbor pixels of the current pixel from each side. Moreover, increasing the number of layers provide better results at the same time leads to decreases in

• Publication Date: 19-Aug-2016
• DOI: 10.15224/978-1-63248-099-6-29
• Views: 0
• Downloads: 0