Tuib et al. (2024) used a convolutional neural network (CNN) and binary moth flame optimization (BMFO) algorithm to detect emotions from electroencephalogram (EEG) signals. The main goal was to develop a robust and accurate system. CNN is used to process EEG signals due to its ability to learn patterns and spatial features, while BMFO is used to optimize CNN hyperparameters. This research utilizes publicly available EEG datasets, and the performance of the system is assessed using metrics such as accuracy, precision, recall, and F1-score.
The results show that the proposed system achieves high accuracy in detecting emotions from EEG signals and is more effective compared to other existing methods. Thus, this study concludes that the use of CNN and BMFO combination is effective in detecting emotions from EEG signals. Now artificial intelligence (AI) can read human emotions, so it is necessary to improve some aspects of them:
- Difficulty in reading emotions: emotions are challenging to read as they depend on context. Although AI has learned to recognize faces, identifying the emotional state of a person’s face can fail to capture important information.
- Technical challenges: there are significant technical challenges in reading emotions, especially in considering context to infer emotions. Since AI can give wrong results, using an inaccurate system in making decisions can make the user much worse off.
- False trust: humans tend to trust AI systems more than other authority figures. This can lead to inaccurate use of the system in decision-making, which needs to be watched out for.
- Ethical and social considerations: we need to consider the fairness, accountability, transparency, and ethics of AI systems in the design and implementation process. We must also always put humans as the final decision-makers.
Therefore, vigilance is needed to ensure the use of AI in reading human emotions is done correctly and ethically, avoiding the use of inaccurate systems and maintaining the role of humans in decision-making.
Citations:
Heckman, C. (2020, January 20). Kini kecerdasan buatan AI dapat membaca emosi manusia, mengapa kita perlu waspada? The Conversation. https://theconversation.com/kini-kecerdasan-buatan-ai-dapat-membaca-emosi-manusia-mengapa-kita-perlu-waspada-129986
Tuib, T. A., Saoudi, B. H., Hussein, Y. M., Mandeel, T. H., & Al-Dhief, F. T. (2024). Convolutional neural network with binary moth flame optimization for emotion detection in electroencephalogram. IAES International Journal of Artificial Intelligence (IJ-AI), 13(1), 1172–1178. https://ijai.iaescore.com/index.php/IJAI/article/view/22725/13920
By: I. Busthomi
