Artificial Neural Networks (ANNs) which are one of the main tools used in machine learning have often been utilised in developing models for path loss modelling in recent times. However, the ANN algorithm that provides the best results has not been well established neither has the models been characterized to limit their performances and applications in the various frequency bands. In this paper, we characterize the propagation loss in the Very High Frequency Band (VHF, 30-300MHz) by using different ANN learning algorithms and activation functions based on the measurement data collected at 203.25 MHz in an urban environment (Ilorin, Nigeria). Prediction results of Hata, ECC-33, Egli and COST 231 propagation models at varying distances were fed into a feed-forward neural network and mapped to each corresponding measured path loss value. Statistical analysis shows that the ANN model that was trained with hyperbolic tangent activation function (HTAF), Levenberg-Marquardt (LM) algorithm, and 80 neurons in the hidden layer produced the most satisfactory results with Mean Error (ME), Root Mean Square Error (RMSE), Standard Deviation (SD), and coefficient of determination (R^2) values of 3.75 dB, 5.10 dB, 3.46 dB, and 0.95. However, the HTAF with Scale Conjugate Gradient (SCG) is more stable even though its prediction errors were slightly higher than that of LM.

Information secrecy is achievable in a broadcast wireless communication system when the adversary channel witness a greater disruption as against the main channel. The secrecy level need to be enhanced as the adversary terminal can use advance method to eaves drop the hidden message being exchanged between the two legitimate communicating partners. The use of relay- assisted node in information-theoretic approach at the physical layer security has been widely researched into but they are mostly operate in a half-duplex mode (HD). With the advancement in electronic technology, the use of a single antenna in full duplex mode (FD) is possible. We explore this property in enhancing the security of a broadcast wireless system at the physical layer. In this work, the transmitter generates artificial noise (AN) while the legitimate receiver(LR) also transmits another jamming noise (JN) from its antenna to unintended receiver (UR) node. The effect of these multiple noises are examined on the secrecy capacity and probability outage capacity on the UR channel. Mathematical analysis and the numerical simulation results show improvement in channel secrecy capacity over the conventional approaches.

This paper proposes an iterative decoding algorithm for network coding HARQ (NC-HARQ) retransmission scheme in LDPC system. Including two erroneous codewords and one retransmitted network coded word, a larger Tanner graph is applied in the decoding algorithm. We modify the process of iterative decoding and separate the external information into two parts which come from channel coding and network coding respectively. Different iteration numbers are set in these two parts and a weighting factor is multiplied to the latter one. Simulation results show that, compared with traditional HARQ in which the repeat codewords are the erroneous codewords themselves, the proposed scheme can not only reduce the retransmission number but also improve the throughput significantly.