Abstract:Humans experience a variety of emotions throughout the course of their daily lives, including happiness, sadness, and rage. As a result, an effective emotion identification system is essential for electroencephalography (EEG) data to accurately reflect emotion in real-time. Although recent studies on this problem can provide acceptable performance measures, it is still not adequate for the implementation of a complete emotion recognition system. In this research work, we propose a new approach for an emotion r… Show more
“…In this study [6], the authors proposed a novel method for emotion recognition that combines multichannel EEG analysis with a newly developed entropy called multivariate multiscale modified-distribution entropy (MM-mDistEn) with a model based on an artificial neural network (ANN) to outperform existing approaches. The suggested system outperformed previous approaches in tests using two distinct datasets.…”
Section: Related Workmentioning
confidence: 99%
“…However, people are capable of easily masking facial and speech information with the right training [5]. On the other hand, since it is impossible for people to conceal or influence their brainwaves, EEG signals [6] have been used in recent years to evaluate a person's emotional state in order to stop possible industrial insider attacks. Moreover, several EEG signal-based human evaluation systems have employed Machine Learning [7] classifiers in various configurations to analyze human emotions in the context of AI applications.…”
The major aim of this paper is to explain the data poisoning attacks using label-flipping during the training stage of the electroencephalogram (EEG) signal-based human emotion evaluation systems deploying Machine Learning models from the attackers' perspective. Human emotion evaluation using EEG signals has consistently attracted a lot of research attention. The identification of human emotional states based on EEG signals is effective to detect potential internal threats caused by insider individuals. Nevertheless, EEG signal-based human emotion evaluation systems have shown several vulnerabilities to data poison attacks. Besides, due to the instability and complexity of the EEG signals, it is challenging to explain and analyze how data poison attacks influence the decision process of EEG signal-based human emotion evaluation systems. In this paper, from the attackers' side, data poison attacks occurring in the training phases of six different Machine Learning models including Random Forest, Adaptive Boosting (AdaBoost), Extra Trees, XGBoost, Multilayer Perceptron (MLP), and K-Nearest Neighbors (KNN) intrude on the EEG signal-based human emotion evaluation systems using these Machine Learning models. This seeks to reduce the performance of the aforementioned Machine Learning models with regard to the classification task of 4 different human emotions using EEG signals. The findings of the experiments demonstrate that the suggested data poison assaults are model-independently successful, although various models exhibit varying levels of resilience to the attacks. In addition, the data poison attacks on the EEG signal-based human emotion evaluation systems are explained with several Explainable Artificial Intelligence (XAI) methods including Shapley Additive Explanation (SHAP) values, Local Interpretable Model-agnostic Explanations (LIME), and Generated Decision Trees. And the codes of this paper are publicly available on GitHub.
“…In this study [6], the authors proposed a novel method for emotion recognition that combines multichannel EEG analysis with a newly developed entropy called multivariate multiscale modified-distribution entropy (MM-mDistEn) with a model based on an artificial neural network (ANN) to outperform existing approaches. The suggested system outperformed previous approaches in tests using two distinct datasets.…”
Section: Related Workmentioning
confidence: 99%
“…However, people are capable of easily masking facial and speech information with the right training [5]. On the other hand, since it is impossible for people to conceal or influence their brainwaves, EEG signals [6] have been used in recent years to evaluate a person's emotional state in order to stop possible industrial insider attacks. Moreover, several EEG signal-based human evaluation systems have employed Machine Learning [7] classifiers in various configurations to analyze human emotions in the context of AI applications.…”
The major aim of this paper is to explain the data poisoning attacks using label-flipping during the training stage of the electroencephalogram (EEG) signal-based human emotion evaluation systems deploying Machine Learning models from the attackers' perspective. Human emotion evaluation using EEG signals has consistently attracted a lot of research attention. The identification of human emotional states based on EEG signals is effective to detect potential internal threats caused by insider individuals. Nevertheless, EEG signal-based human emotion evaluation systems have shown several vulnerabilities to data poison attacks. Besides, due to the instability and complexity of the EEG signals, it is challenging to explain and analyze how data poison attacks influence the decision process of EEG signal-based human emotion evaluation systems. In this paper, from the attackers' side, data poison attacks occurring in the training phases of six different Machine Learning models including Random Forest, Adaptive Boosting (AdaBoost), Extra Trees, XGBoost, Multilayer Perceptron (MLP), and K-Nearest Neighbors (KNN) intrude on the EEG signal-based human emotion evaluation systems using these Machine Learning models. This seeks to reduce the performance of the aforementioned Machine Learning models with regard to the classification task of 4 different human emotions using EEG signals. The findings of the experiments demonstrate that the suggested data poison assaults are model-independently successful, although various models exhibit varying levels of resilience to the attacks. In addition, the data poison attacks on the EEG signal-based human emotion evaluation systems are explained with several Explainable Artificial Intelligence (XAI) methods including Shapley Additive Explanation (SHAP) values, Local Interpretable Model-agnostic Explanations (LIME), and Generated Decision Trees. And the codes of this paper are publicly available on GitHub.
“…Similarly, in existing achievements, the neural regulatory mechanisms of electrical and magnetic stimulation signals on the target area are not yet explicit. In future research, we will also focus on combining electrophysiological signals such as patients' electroencephalogram(EEG) [100] and electrocardiogram(ECG) [101] to study the neural regulatory mechanisms.…”
The sleep loss (SL) are one of the important diseases that endanger the health of aging individuals. This study evaluated SL in aging individuals, and explored the relationship between age and the organic changes that affect brain and sleep. The causes of SL in aging individuals and its harmful effects on them have been outlined. To enable individuals in choosing a suitable way to sleep better, we also reviewed advantages and disadvantages of the existing sleep modulation based on lifestyle habits and drug and physical stimulation. We found the former as more suitable for patients with mild SL, while the latter may fail to achieve the desired effects and may even lead to the onset of new diseases. Therefore, it is proposed to use non-invasive electrical and magnetic stimulations to improve the sleep quality in aging patients.In this review, mechanisms of the two stimulation methods have been summarized. Through analysis, it was found that magnetic stimulation can induce neuronal action potential, which makes patients twitch, and equipment noise causes discomfort in the elderly during treatment. Comparative analysis of stimulation methods revealed that transcranial electrical stimulation (tES) is a considerably safe, convenient, non-invasive, and easy to operate method with few adverse reactions, and it can be considered a potential therapeutic method for SL in aging patients.
“…Recently, deep learning has made massive strides in many research areas obtaining state of art performance in computer vision [8], natural language processing [9], and many other domains [10][11][12]. In order to learn sophisticated feature interactions, deep neural networks were recently proposed to predict CTR [13][14][15][16][17].…”
Human click behavior prediction is crucial for recommendation scenarios such as online commodity or advertisement recommendation, as it is helpful to improve the quality and user satisfaction of services. In recommender systems, the concept of click-through rate (CTR) is used to estimate the probability that a user will click on a recommended candidate. Many methods have been proposed to predict CTR and achieved good results. However, they usually optimize the parameters through a global objective function such as minimizing logloss or root mean square error (RMSE) for all training samples. Obviously, they intend to capture global knowledge of user click behavior but ignore local information. In this work, we propose a novel approach of retrieval-based factorization machines (RFM) for CTR prediction, which can effectively predict CTR by combining global knowledge which is learned from the FM method with the neighbor-based local information. We also leverage the clustering technique to partition the large training set into multiple small regions for efficient retrieval of neighbors. We evaluate our RFM model on three public datasets. The experimental results show that RFM performs better than other models in metrics of RMSE, area under ROC (AUC), and accuracy. Moreover, it is efficient because of the small number of model parameters.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.