In this letter, we describe an adaptive hybrid SR ARQ scheme using punctured TCM and code combining. Numerical results show that the proposed scheme yields better throughput efficiency than the scheme using TCM at the values of Es/No smaller than 9 dB.

In this letter we purpose adaptive neuro-fuzzy inference system (ANFIS) for channel estimation in orthogonal frequency division multiplexing (OFDM) systems. To evaluate the performance of this estimator, we compare the ANFIS with least square (LS) algorithm, minimum mean square error (MMSE) algorithm by using bit error rate (BER) and mean square error (MSE) criterias. According to computer simulations the performance of ANFIS has better performance than LS algorithm and close to MMSE algorithm. Besides there is unnecessity to send pilot when used the ANFIS.

In this letter, parallel interference cancellation (PIC) in code division multiple access (CDMA) was performed with two different structures by using a neural network (NN). In the first structure (receiver-1) the NN was used as a front-end stage of a one stage PIC circuit. In the second structure (receiver-2), the NN was used instead of the one stage PIC circuit and it was trained as a multiple access interference (MAI) detector to perform the PIC process by subtracting the MAI from the outputs of the matched filter. The PIC is a classical technique in multi user detection process and its bit error rate (BER) performance is not good in one stage for most of the applications. For improving its BER performance, generally a multi stage PIC which has the high computational complexity is used. In this study, we have gotten a better BER performance than a three stages PIC receiver with both proposed receivers that have the lower computational complexity.

In this letter, multi user detection process in Code Division Multiple Access (CDMA) is performed by fuzzy inference system (FIS) and the bit error rate (BER) performance was compared with the single user bound, the matched filter receiver and neural network receiver. The BER performance of the matched filter receiver degrades as the number of the active users and the power level differences among the users increase. The neural network receiver needs the training process. Optimal receiver that has the best BER performance is too complex for practical application. The BER performance near the optimal case was obtained with the proposed receiver. The proposed receiver uses the FIS without training process and it has lower time complexity than the optimal receiver.