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.

Distributed optical fiber sensors are a promising technology for monitoring the structural health of large-scale structures. The fiber sensors are usually coated with nonfragile materials to protect the sensor and are bonded onto the structure using adhesive materials. However, local deformation of the relatively soft coating and adhesive layers hinders strain transfer from the base structure to the optical fiber sensor, which reduces and distorts its strain distribution. In this study, we analytically derive a strain transfer function in terms of strain periods, which enables us to understand how the strain reduces and is distorted in the optical fiber depending on the variation of the strain field. We also propose a method for back-calculating the base structure’s strain field using the reduced and distorted strain distribution in the optical fiber sensor. We numerically demonstrate the back-calculation of the base strain using a composite beam model with an open hole and an attached distributed optical fiber sensor. The new strain transfer function and the proposed back-calculation method can enhance the strain field estimation accuracy in using a distributed optical fiber sensor. This enables us to use a highly durable distributed optical fiber sensor with thick protective layers in precision measurement.

The purpose of this study was to provide baseline data to promote leisure sports activities by examining the exercise stress amateur soccer players undergoes, and defining the how it relates to the participants’ Physical self-efficacy and Exercise Flow. 240 soccer players involved in leisure amateur Soccer clubs were selected as the participants. The participants’ demographic characteristic, exercise stress, physical self-efficacy and exercise immersion was measured through survey. Excluding the inadequate survey results, Statistical analysis was completed through SPSS win 12.0 to analyze the Factor analysis, principal Components, Varimax, Multiple Regression Analysis, Correlation Analysis, Structural Equation Model, and Frequency Analysis. Hypothesis 1, amateur leisure soccer players’ exercise stress has a negative influence on self-efficacy, was accepted by analyzing the data. Hypothesis 2, amateur leisure soccer players’ exercise stress has a negative influence on exercise flow, was accepted by analyzing the data. Hypothesis 3, amateur leisure soccer players’ self-efficacy has a positive influence on exercise flow, was accepted by analyzing the data.

This study is to ascertain how leisure sports participation is related to the senior citizens’ self-realization and their loneliness. Population is elderly people who live in Seoul and Suwon in 2014. Stratified Cluster Random Sampling Method is used in this study. A total of 202 questionnaires are used for processing survey data. The data which has some problems is not included. The results of this study are as in the following. 1. The leisure sports participation of the senior citizens influenced on their self-realization with statistic meaning. 2. The leisure sports participation of the senior citizens influenced on their loneliness with statistic meaning. 3. The leisure sports participation of the senior citizens influenced on their self-realization and their loneliness with statistic meaning.

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. 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.