Diagnostic biomarker discovery from brain EEG data using LSTM, reservoir-SNN, and NeuCube methods in a pilot study comparing epilepsy and migraine.

The study introduces a new online spike encoding algorithm for spiking neural networks (SNN) and suggests new methods for learning and identifying diagnostic biomarkers using three prominent deep learning neural network models: deep BiLSTM, reservoir SNN, and NeuCube. EEG data from datasets related to epilepsy, migraine, and healthy subjects are employed. Results reveal that BiLSTM hidden neurons capture biological significance, while reservoir SNN activities and NeuCube spiking dynamics identify EEG channels as diagnostic biomarkers. BiLSTM and reservoir SNN achieve 90 and 85% classification accuracy, while NeuCube achieves 97%, all methods pinpointing potential biomarkers like T6, F7, C4, and F8. The research bears implications for refining online EEG classification, analysis, and early brain state diagnosis, enhancing AI models with interpretability and discovery. The proposed techniques hold promise for streamlined brain-computer interfaces and clinical applications, representing a significant advancement in pattern discovery across the three most popular neural network methods for addressing a crucial problem. Further research is planned to study how early can these diagnostic biomarkers predict an onset of brain states.

Hybrid fuzzy deep neural network toward temporal-spatial-frequency features learning of motor imagery signals.

Achieving an efficient and reliable method is essential to interpret a user's brain wave and deliver an accurate response in biomedical signal processing. However, EEG patterns exhibit high variability across time and uncertainty due to noise and it is a significant problem to be addressed in mental task as motor imagery. Therefore, fuzzy components may help to enable a higher tolerance to noisy conditions. With the advent of Deep Learning and its considerable contributions to Artificial intelligence and data analysis, numerous efforts have been made to evaluate and analyze brain signals. In this study, to make use of neural activity phenomena, the feature extraction preprocessing is applied based on Multi-scale filter bank CSP. In the following, the hybrid series architecture named EEG-CLFCNet is proposed which extract the frequency and spatial features by Compact-CNN and the temporal features by the LSTM network. However, the classification results are evaluated by merging the fully connected network and fuzzy neural block. Here, the proposed method is further validated by the BCI competition IV-2a dataset and compare with two hyperparameter tuning methods, Coordinate-descent and Bayesian optimization algorithm. The proposed architecture that used fuzzy neural block and Bayesian optimization as tuning approach, results in better classification accuracy compared with the state-of-the-art literatures. As results shown, the remarkable performance of the proposed model, EEG-CLFCNet, and the general integration of fuzzy units to other classifiers would pave the way for enhanced MI-based BCI systems.

Causal associations of genetic factors with clinical progression in amyotrophic lateral sclerosis.

BACKGROUND AND OBJECTIVE: Recent advances in the genetic causes of ALS reveals that about 10% of ALS patients have a genetic origin and that more than 30 genes are likely to contribute to this disease. However, four genes are more frequently associated with ALS: C9ORF72, TARDBP, SOD1, and FUS. The relationship between genetic factors and ALS progression rate is not clear. In this study, we carried out a causal analysis of ALS disease with a genetics perspective in order to assess the contribution of the four mentioned genes to the progression rate of ALS. METHODS: In this work, we applied a novel causal learning model to the CRESLA dataset which is a longitudinal clinical dataset of ALS patients including genetic information of such patients. This study aims to discover the relationship between four mentioned genes and ALS progression rate from a causation perspective using machine learning and probabilistic methods. RESULTS: The results indicate a meaningful association between genetic factors and ALS progression rate with causality viewpoint. Our findings revealed that causal relationships between ALSFRS-R items associated with bulbar regions have the strongest association with genetic factors, especially C9ORF72; and other three genes have the greatest contribution to the respiratory ALSFRS-R items with a causation point of view. CONCLUSIONS: The findings revealed that genetic factors have a significant causal effect on the rate of ALS progression. Since C9ORF72 patients have higher proportion compared to those carrying other three gene mutations in the CRESLA cohort, we need a large multi-centric study to better analyze SOD1, TARDBP and FUS contribution to the ALS clinical progression. We conclude that causal associations between ALSFRS-R clinical factors is a suitable predictor for designing a prognostic model of ALS.

Design of MRI structured spiking neural networks and learning algorithms for personalized modelling, analysis, and prediction of EEG signals.

This paper proposes a novel method and algorithms for the design of MRI structured personalized 3D spiking neural network models (MRI-SNN) for a better analysis, modeling, and prediction of EEG signals. It proposes a novel gradient-descent learning algorithm integrated with a spike-time-dependent-plasticity algorithm. The models capture informative personal patterns of interaction between EEG channels, contrary to single EEG signal modeling methods or to spike-based approaches which do not use personal MRI data to pre-structure a model. The proposed models can not only learn and model accurately measured EEG data, but they can also predict signals at 3D model locations that correspond to non-monitored brain areas, e.g. other EEG channels, from where data has not been collected. This is the first study in this respect. As an illustration of the method, personalized MRI-SNN models are created and tested on EEG data from two subjects. The models result in better prediction accuracy and a better understanding of the personalized EEG signals than traditional methods due to the MRI and EEG information integration. The models are interpretable and facilitate a better understanding of related brain processes. This approach can be applied for personalized modeling, analysis, and prediction of EEG signals across brain studies such as the study and prediction of epilepsy, peri-perceptual brain activities, brain-computer interfaces, and others.

Neuro-adaptive backstepping control of SISO non-affine systems with unknown gain sign.

This paper presents two neuro-adaptive controllers for a class of uncertain single-input, single-output (SISO) nonlinear non-affine systems with unknown gain sign. The first approach is state feedback controller, so that a neuro-adaptive state-feedback controller is constructed based on the backstepping technique. The second approach is an observer-based controller and K-filters are designed to estimate the system states. The proposed method relaxes a priori knowledge of control gain sign and therefore by utilizing the Nussbaum-type functions this problem is addressed. In these methods, neural networks are employed to approximate the unknown nonlinear functions. The proposed adaptive control schemes guarantee that all the closed-loop signals are semi-globally uniformly ultimately bounded (SGUUB). Finally, the theoretical results are numerically verified through simulation examples. Simulation results show the effectiveness of the proposed methods.

Stochastic stability and stabilization of Markov jump linear systems with instantly time-varying transition rates: A unified framework.

This paper investigates the stochastic stability and stabilization problems of non-homogeneous Markov jump linear systems (NHMJLSs) characterized by instantly unconditionally time-varying transition rates (TRs). The novelty of the study lies in proposing a systematic method for achieving finite dimensional conditions with an acceptable degree of conservativeness for the stability and the stabilization problems of the system. In this framework, by first processing the time-varying TRs, a finite number of uncertain but time-constant TR matrices are obtained. Then, a high-level switching signal is constructed for the system, which models the contribution of each possible time-constant TR matrix. Based on the results, the NHMJLS is reformed into an uncertain switching structure referred to as the associated switched Markov jump linear system (AS-MJLS). Finally, by taking advantage of the new representation, sufficient conditions are obtained to ensure the stability and stabilizability of the system, also the controller gains are designed. The proposed framework provides a realistic representation as well as practically solvable analysis and synthesis conditions for the NHMJLS. It also leads to less conservative results compared with the existing well-known techniques. Comparative simulation studies for a single-machine infinite-bus (SMIB) power system subject to stochastically varying load demonstrate the efficiency and superiority of the method.

Adaptive Neural Stabilizing Controller for a Class of Mismatched Uncertain Nonlinear Systems by State and Output Feedback.

In this paper, first, an adaptive neural network (NN) state-feedback controller for a class of nonlinear systems with mismatched uncertainties is proposed. By using a radial basis function NN (RBFNN), a bound of unknown nonlinear functions is approximated so that no information about the upper bound of mismatched uncertainties is required. Then, an observer-based adaptive controller based on RBFNN is designed to stabilize uncertain nonlinear systems with immeasurable states. The state-feedback and observer-based controllers are based on Lyapunov and strictly positive real-Lyapunov stability theory, respectively, and it is shown that the asymptotic convergence of the closed-loop system to zero is achieved while maintaining bounded states at the same time. The presented methods are more general than the previous approaches, handling systems with no restriction on the dimension of the system and the number of inputs. Simulation results confirm the effectiveness of the proposed methods in the stabilization of mismatched nonlinear systems.