International Journal of Neural Systems

Considering the 2030 United Nations intent of world connection, Cyber Intelligence becomes the main area of the human dimension able of inflicting changes in geopolitical dynamics. In cyberspace, the new battlefield is the mind of people including new weapons like abuse of social media with information manipulation, deception by activists and misinformation. In this paper, a Sentiment Analysis system with Anomaly Detection (SAAD) capability is proposed. The system, scalable and modular, uses an OSINT-Deep Learning approach to investigate on social media sentiment in order to predict suspicious anomaly trend in Twitter posts. Anomaly detection is investigated with a new semi-supervised process that is able to detect potentially dangerous situations in critical areas. The main contributions of the paper are the system suitability for working in different areas and domains, the anomaly detection procedure in sentiment context and a time-dependent confusion matrix to address model evaluation with unbalanced dataset. Real experiments and tests were performed on Sahel Region. The detected anomalies in negative sentiment have been checked by experts of Sahel area, proving true links between the models results and real situations observable from the tweets.

Error-correcting output coding (ECOC) is a method for constructing a multi-valued classifier using a combination of given binary classifiers. ECOC can estimate the correct category by other binary classifiers even if the output of some binary classifiers is incorrect based on the framework of the coding theory. The code word table representing the combination of these binary classifiers is important in ECOC. ECOC is known to perform well experimentally on real data. However, the complexity of the classification problem makes it difficult to analyze the classification performance in detail. For this reason, theoretical analysis of ECOC has not been conducted. In this study, if a binary classifier outputs the estimated posterior probability with errors, then this binary classifier is said to be noisy. In contrast, if a binary classifier outputs the true posterior probability, then this binary classifier is said to be noiseless. For a theoretical analysis of ECOC, we discuss the optimality for the code word table with noiseless binary classifiers and the error rate for one with noisy binary classifiers. This evaluation result shows that the Hamming distance of the code word table is an important indicator.

Somatosensory evoked potential (SEP) has been commonly used as intraoperative monitoring to detect the presence of neurological deficits during scoliosis surgery. However, SEP usually presents an enormous variation in response to patient-specific factors such as physiological parameters leading to the false warning. This study proposes a prediction model to quantify SEP amplitude variation due to noninjury-related physiological changes of the patient undergoing scoliosis surgery. Based on a hybrid network of attention-based long-short-term memory (LSTM) and convolutional neural networks (CNNs), we develop a deep learning-based framework for predicting the SEP value in response to variation of physiological variables. The training and selection of model parameters were based on a 5-fold cross-validation scheme using mean square error (MSE) as evaluation metrics. The proposed model obtained MSE of 0.027$\mu {\mathrm{\text{V}}}^2$ on left cortical SEP, MSE of 0.024$\mu {\mathrm{\text{V}}}^2$ on left subcortical SEP, MSE of 0.031$\mu {\mathrm{\text{V}}}^2$ on right cortical SEP, and MSE of 0.025$\mu {\mathrm{\text{V}}}^2$ on right subcortical SEP based on the test set. The proposed model could quantify the affection from physiological parameters to the SEP amplitude in response to normal variation of physiology during scoliosis surgery. The prediction of SEP amplitude provides a potential varying reference for intraoperative SEP monitoring.

Impulsivity is a multidimensional construct often associated with unfavorable outcomes. Previous studies have implicated several electroencephalography (EEG) indices to impulsiveness, but results are heterogeneous and inconsistent. Using a data-driven approach, we identified EEG power features for the prediction of self-reported impulsiveness. To this end, EEG signals of 56 individuals (18 low impulsive, 20 intermediate impulsive, 18 high impulsive) were recorded during a risk-taking task. Extracted EEG power features from 62 electrodes were fed into various machine learning classifiers to identify the most relevant band. Robustness of the classifier was varied by stratified $k$-fold cross validation. Alpha and beta band power showed best performance in the classification of impulsiveness (accuracy = 95.18% and 95.11%, respectively) using a random forest classifier. Subsequently, a sequential bidirectional feature selection algorithm was used to estimate the most relevant electrode sites. Results show that as little as 10 electrodes are sufficient to reliably classify impulsiveness using alpha band power ($f$-measure = 94.50%). Finally, the Shapley Additive exPlanations (SHAP) analysis approach was employed to reveal the individual EEG features that contributed most to the model’s output. Results indicate that frontal as well as posterior midline alpha power seems to be of most importance for the classification of impulsiveness.

Repetitive Transcranial Magnetic Stimulation (rTMS) is proposed as an effective treatment for major depressive disorder (MDD). However, because of the suboptimal treatment outcome of rTMS, the prediction of response to this technique is a crucial task. We developed a deep learning (DL) model to classify responders (R) and non-responders (NR). With this aim, we assessed the pre-treatment EEG signal of 34 MDD patients and extracted effective connectivity (EC) among all electrodes in four frequency bands of EEG signal. Two-dimensional EC maps are put together to create a rich connectivity image and a sequence of these images is fed to the DL model. Then, the DL framework was constructed based on transfer learning (TL) models which are pre-trained convolutional neural networks (CNN) named VGG16, Xception, and EfficientNetB0. Then, long short-term memory (LSTM) cells are equipped with an attention mechanism added on top of TL models to fully exploit the spatiotemporal information of EEG signal. Using leave-one subject out cross validation (LOSO CV), Xception-BLSTM-Attention acquired the highest performance with 98.86% of accuracy and 97.73% of specificity. Fusion of these models as an ensemble model based on optimized majority voting gained 99.32% accuracy and 98.34% of specificity. Therefore, the ensemble of TL-LSTM-Attention models can predict accurately the treatment outcome.

To enable an accurate recognition of neuronal excitability in an epileptic brain for modeling or localization of epileptic zone, here the brain response to single-pulse electrical stimulation (SPES) has been decomposed into its constituent components using adaptive singular spectrum analysis (SSA). Given the response at neuronal level, these components are expected to be the inhibitory and excitatory components. The prime objective is to thoroughly investigate the nature of delayed responses (elicited between 100ms–1 s after SPES) for localization of the epileptic zone. SSA is a powerful subspace signal analysis method for separation of single channel signals into their constituent uncorrelated components. The consistency in the results for both early and delayed brain responses verifies the usability of the approach.