Artificial neural networks are amongst the artificial intelligence techniques with their ability to provide machines with some functionalities such as decision making, comparison, and forecasting. They are known for having the capability of forecasting issues in real-world problems. Their acquired knowledge is stored in the interconnection strengths or weights of neurons through an optimization system known as learning. Several limitations have been identified with commonly used gradient-based optimization algorithms, including the risk of premature convergence, the sensitivity of initial parameters and positions, and the potential for getting trapped in local optima. Various meta-heuristics are proposed in the literature as alternative training algorithms to mitigate these limitations. Therefore, the primary aim of this study is to combine a feed-forward artificial neural network (ANN) with a cultural algorithm (CA) as a meta-heuristic, aiming to establish an efficient and dependable training system in comparison to existing methods. The proposed artificial neural network system (ANN-CA) evaluated its performance on classification tasks over nine benchmark datasets: Iris, Pima Indians Diabetes, Thyroid Disease, Breast Cancer Wisconsin, Credit Approval, Glass Identification, SPECT Heart, Wine and Balloon. The overall experimental results indicate that the proposed method outperforms other methods included in the comparative analysis by approximately 12% in terms of classification error and approximately 7% in terms of accuracy.

With the growing popularity of delay-sensitive applications (e.g., real-time conversational video, online gaming, and augmented reality) and future trends toward ultra-reliable low-latency communications such as the tactile Internet, performance analysis of wireless systems under the finite code blocklength constraint becomes extremely important. In this paper, we investigate the maximum achievable throughput of incremental redundancy-hybrid automatic repeat request (IR-HARQ) over the (correlated) Rayleigh fading channel under finite blocklength and delay-violation probability constraints as a function of the modulation scheme. The maximum number of HARQ rounds together with the transport block size specifies the underlying coding latency of the IR-HARQ scheme. A framework, namely the HARQ Markov model (HARQ-MM), is introduced to track the throughput and the probability of error of IR-HARQ over the Rayleigh fading channel as a function of the modulation scheme. The dispersion of parallel additive white Gaussian noise channels with finite input alphabets (e.g., pulse amplitude modulation) is analytically characterized. It is used to identify the state transition probabilities of the underlying HARQ-MM. An algorithm is developed to efficiently compute the steady-state distribution of the HARQ-MM. Extensive performance evaluation is conducted, which shows a good match between the throughput performance characterized by the theoretical framework and that achieved by the practical channel codes.

Reservoir computing (RC) is a class of neuromorphic computing approaches that deals particularly well with time-series prediction tasks. It significantly reduces the training complexity of recurrent neural networks and is also suitable for hardware implementation whereby device physics are utilized in performing data processing. In this paper, the RC concept is applied to detecting a transmitted symbol in multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems. Due to wireless propagation, the transmitted signal may undergo severe distortion before reaching the receiver. The nonlinear distortion introduced by the power amplifier at the transmitter may further complicate this process. Therefore, an efficient symbol detection strategy becomes critical. The conventional approach for symbol detection at the receiver requires accurate channel estimation of the underlying MIMO-OFDM system. However, in this paper, we introduce a novel symbol detection scheme where the estimation of the MIMO-OFDM channel becomes unnecessary. The introduced scheme utilizes an echo state network (ESN), which is a special class of RC. The ESN acts as a black box for system modeling purposes and can predict nonlinear dynamic systems in an efficient way. Simulation results for the uncoded bit error rate of nonlinear MIMO-OFDM systems show that the introduced scheme outperforms conventional symbol detection methods.

Reservoir computing (RC) is attracting widespread attention in several signal processing domains owing to its nonlinear stateful computation. It deals particularly well with time-series prediction tasks and reduces training complexity over recurrent neural networks. It is also suitable for hardware implementation whereby device physics are utilized in performing data processing. In this paper, the RC concept is applied to modeling a Multiple-Input Multiple-Output Orthogonal Frequency Division Multiplexing (MIMO-OFDM) system. Due to the harsh propagation environment, the transmitted signal undergoes severe distortion that must be compensated for at the receiver. The nonlinear distortion introduced by the power amplifier at the transmitter further complicates this process. An effective channel estimation scheme is therefore required. In this paper, we introduce a MIMO-OFDM channel estimation scheme utilizing Echo State Network (ESN). Echo State Networks are powerful recurrent neural networks that can predict time-series very well. They acts as a black-box for system modeling purposes and models nonlinear dynamic systems efficiently. Simulation results for the bit error rate of the nonlinear MIMO-OFDM system show that the introduced channel estimator outperforms commonly used channel estimation schemes.

Future wireless communications will face the dual challenge of supporting large traffic volume while providing reliable service for various kinds of delay-sensitive traffic. In the light of this challenge, this paper investigates the throughput performance of hybrid automatic repeat request (HARQ) systems under finite blocklength constraint. We present a framework to compute the maximum achievable rate with HARQ over the Rayleigh fading channel for a given probability of error. In the proposed framework, the operation of HARQ over the Rayleigh fading channel is modeled as a finite-state Markov chain. The state transition probabilities of the proposed Markov model are estimated from the fading characteristics of the wireless channel as well as the dispersion associated with different channel state sequence realizations. With this framework we are able to link the HARQ throughput performance to the characteristics of the underlying physical channel as well as the system design parameters such as modulation and transmit power. Furthermore, we discuss the relationship between the system throughput, and the number of HARQ rounds. The results show that the required number of HARQ rounds to take full advantage of HARQ depends on the choice of modulation, and varies as a function of the signal-to-noise ratio (SNR).

Future wireless communications will face the dual challenge of supporting large traffic volume while providing reliable service for various kinds of delay-sensitive traffic. In the light of this challenge, this paper investigates the throughput performance of wireless systems under channel coding over finite transport blocks (TBs) with the channel state sequence available only at the receiver. We analyze the performance of a communication scheme with feedback, namely early decoding, where for each codeblock the receiver makes a single decoding attempt at a time determined based on the available channel state information. A finite-state Markov channel (FSMC) is introduced to model the TB-based wireless system where the parameters of the model are linked to the characteristics of the underlying physical channel. The FSMC model is then used to assess the maximum achievable throughput of the early decoding strategy. Numerical results suggest that despite its low computational complexity the proposed scheme significantly reduces the coding latency to achieve rates near the channel capacity.

Future wireless communications will face the dual challenge of supporting large traffic volume while providing reliable service for various kinds of delay-sensitive traffic. In light of this challenge, this paper investigates the throughput performance of wireless communication systems under channel coding over finite transport blocks (TBs) with the channel state sequence available only at the receiver. When we apply coding across multiple TBs, the underlying wireless channel can be effectively modeled as a finite-state Markov chain. By linking the characteristics of the underlying physical channel to the parameters of the Markov chain, we characterize the channel dispersion of the corresponding system. The channel dispersion is then used to assess the coding performance of various communication strategies. We also propose a communication scheme where the receiver determines the decoding time based on the available channel state sequence. Numerical results show that the proposed scheme significantly reduces the coding delay to achieve rates near the channel capacity.

In modern wireless systems such as 3GPP LTE/LTE-Advanced, packets are partitioned into multiple transport blocks where each transport block is a group of resource elements with a common modulation and coding scheme. Accordingly, a transport block is the data unit in the physical layer of modern wireless systems. In this paper, we investigate the throughput performance of modern wireless systems under channel coding over finite transport blocks. When we apply coding over multiple transport blocks, the underlying wireless channel can be effectively modeled as a finite-state discrete-time Markov chain. We link the characteristics of the underlying physical channel to the parameters of the Markov chain, and derive the corresponding “channel dispersion.” The “channel dispersion” is then used to assess the throughput performance of various communication strategies. The results show that for a fixed packet size the system throughput increases with transport block size.

Future wireless communications will face the dual challenge of supporting large traffic volume while providing reliable service for various kinds of delay-sensitive traffic. In light of this challenge, this paper investigates the throughput performance of a wireless communication system under channel coding over finite “packets.” When we apply coding over multiple “packets,” the underlying wireless channel can be effectively modeled as a finite-state Markov process. By linking the characteristics of the underlying physical channel to the parameters of the Markov process, we are able to derive the channel dispersion of the corresponding system. The channel dispersion is then used to assess the coding performance of various communication strategies. It is interesting to find that when there is a constraint on the total blocklength, coding over large “packets” will give better performance than that of coding over small “packets”.

Epilepsy is a disorder of cortical excitability and still an important medical problem. The correct diagnosis of a patient's epilepsy syndrome clarifies the choice of drug treatment and also allows an accurate assessment of prognosis in many cases. The aim of this study is to evaluate epileptic patients and classify subgroups of partial epilepsy by Multilayer Perceptron Neural Networks (MLPNNs). This is the first study to classify the partial epilepsy groups using the neural network according to EEG signals. 418 patients with epilepsy diagnoses according to International League against Epilepsy (ILAE, 1981) were included in this study. The epilepsy outpatients at the Neurology Department Clinic of Cukurova University Medical School between the years of 2002–2005 were examined and included in the study. The MLPNNs were trained by the parameters obtained from the EEG signals and clinical findings of the patients. Test results show that the MLPNN model is able to classify partial epilepsy with an accuracy of 91.5%. Moreover, new MLPNNs were constructed for determining significant variables on classification. The loss of consciousness in the course of seizure time variable caused the largest decrease in the classification accuracy when it was left out. In conclusion, we think that the classification performance of MLPNN model for partial epilepsy is satisfactory and this model may be used in clinical studies as a decision support tool to determine the partial epilepsy classification of the patients.