Brain-Inspired Wireless Communications: Where Reservoir Computing Meets MIMO-OFDM.

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.

Can neural network able to estimate the prognosis of epilepsy patients according to risk factors?

The aim of this study is to evaluate the underlying etiologic factors of epilepsy patients and to predict the prognosis of these patients by using a Multi-Layer Perceptron Neural Network (MLPNN) according to risk factors. 758 patients with epilepsy diagnosis are included in this study. The MLPNNs were trained by the parameters of demographic properties of the patients and risk factors of the disease. The results show that the most crucial risk factor of the epilepsy patients was constituted by the febrile convulsion (21.9%), the kinship of parents (22.3%), the history of epileptic relatives (21.6%) and the history of head injury (18.6%). We had 91.1 % correct prediction rate for detection of the prognosis by using the MLPNN algorithm. The results indicate that the correct prediction rate of prognosis of the MLPNN model for epilepsy diseases is found satisfactory.

Neural network-based computer-aided diagnosis in classification of primary generalized epilepsy by EEG signals.

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 classify subgroups of primary generalized epilepsy by using Multilayer Perceptron Neural Networks (MLPNNs). This is the first study classifying primary generalized epilepsy using MLPNNs. MLPNN classified primary generalized epilepsy with the accuracy of 84.4%. This model also classified generalized tonik-klonik, absans, myoclonic and more than one type seizures epilepsy groups correctly with the accuracy of 78.5%, 80%, 50% and 91.6%, respectively. Moreover, new MLPNNs were constructed for determining significant variables affecting the classification accuracy of neural networks. The loss of consciousness in the course of seizure time variable caused the largest decrease in the classification accuracy when it was left out. These outcomes indicate that this model classified the subgroups of primary generalized epilepsy successfully.

A radial basis function neural network model for classification of epilepsy using EEG signals.

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 epilepsy groups such as partial and primary generalized epilepsy by using Radial Basis Function Neural Network (RBFNN) and Multilayer Perceptron Neural Network (MLPNNs). Four hundred eighteen patients with epilepsy diagnoses according to International League against Epilepsy (ILAE 1981) were included in this study. The correct classification of this data was performed by two expert neurologists before they were executed by neural networks. The neural networks were trained by the parameters obtained from the EEG signals and clinic properties of the patients. Experimental results show that the predictions of both neural network models are very satisfying for learning data sets. According to test results, RBFNN (total classification accuracy = 95.2%) has classified more successfully when compared with MLPNN (total classification accuracy = 89.2%). These results indicate that RBFNN model may be used in clinical studies as a decision support tool to confirm the classification of epilepsy groups after the model is developed.

A radial basis function neural network (RBFNN) approach for structural classification of thyroid diseases.

The thyroid is a gland that controls key functions of body. Diseases of the thyroid gland can adversely affect nearly every organ in human body. The correct diagnosis of a patient's thyroid disease clarifies the choice of drug treatment and also allows an accurate assessment of prognosis in many cases. This study investigates Multilayer Perceptron Neural Network (MLPNN) and Radial Basis Function Neural Network (RBFNN) for structural classification of thyroid diseases. A data set for 487 patients having thyroid disease is used to build, train and test the corresponding neural networks. The structural classification of this data set was performed by two expert physicians before the input variables and results were fed into the neural networks. Experimental results show that the predictions of both neural network models are very satisfying for learning data sets. Regarding the evaluation data, the trained RBFNN model outperforms the corresponding MLPNN model. This study demonstrates the strong utility of an artificial neural network model for structural classification of thyroid diseases.