Positive and Negative Emotion Classification Based on Multi-channel

Optimizing 1D-CNN-Based Emotion Recognition Process through Channel and Feature Selection from EEG Signals

EEG-based emotion recognition has numerous real-world applications in fields such as affective computing, human-computer interaction, and mental health monitoring. This offers the potential for developing IOT-based, emotion-aware systems and personalized interventions using real-time EEG data. This study focused on unique EEG channel selection and feature selection methods to remove unnecessary data from high-quality features. This helped improve the overall efficiency of a deep learning model in terms of memory, time, and accuracy. Moreover, this work utilized a lightweight deep learning method, specifically one-dimensional convolutional neural networks (1D-CNN), to analyze EEG signals and classify emotional states. By capturing intricate patterns and relationships within the data, the 1D-CNN model accurately distinguished between emotional states (HV/LV and HA/LA). Moreover, an efficient method for data augmentation was used to increase the sample size and observe the performance deep learning model using additional data. The study conducted EEG-based emotion recognition tests on SEED, DEAP, and MAHNOB-HCI datasets. Consequently, this approach achieved mean accuracies of 97.6, 95.3, and 89.0 on MAHNOB-HCI, SEED, and DEAP datasets, respectively. The results have demonstrated significant potential for the implementation of a cost-effective IoT device to collect EEG signals, thereby enhancing the feasibility and applicability of the data.

The Impact of Emotional States on Construction Workers’ Recognition Ability of Safety Hazards Based on Social Cognitive Neuroscience

The construction industry is one of the most dangerous industries with grave situation owing to high accident rate and mortality rate, which accompanied with a series of security management issues that need to be tackled urgently. The unsafe behavior of construction workers is a critical reason for the high incidence of safety accidents. Affective Events Theory suggests that individual emotional states interfere with individual decisions and behaviors, which means the individual emotional states can significantly influence construction workers’ unsafe behaviors. As the complexity of the construction site environment and the lack of attention to construction workers’ emotions by managers, serious potential emotional problems were planted, resulting in the inability of construction workers to effectively recognize safety hazards, thus leading to safety accidents. Consequently, the study designs a behavioral experiment with E-prime software based on social cognitive neuroscience theories. Forty construction workers’ galvanic skin response signals were collected by a wearable device (HKR-11C+), and the galvanic skin response data were classified into different emotional states with support vector machine (SVM) algorithm. Variance analysis, correlation analysis and regression analysis were used to analyze the influence of emotional states on construction workers’ recognition ability of safety hazards. The research findings indicate that the SVM algorithm could effectively classify galvanic skin response data. The construct ion workers’ the reaction time to safety hazards and emotional valence were negatively correlated, while the accuracy of safety hazards recognition and the perception level of safety hazard separately had an inverted “U” type relationship with emotional valence. For construction workers with more than 20 years of working experience, work experience could effectively reduce the influence of emotional fluctuations on the accuracy of safety hazards identification. This study contributes to the application of physiological measurement techniques in construction safety management and shed a light on improving the theoretical system of safety management.