Smart City Gnosys
Smart city article details
| Title | Enhancing Proactive Immediate Response With Facial Emotion Detection Using Efficient Deep Learning |
|---|---|
| ID_Doc | 23901 |
| Authors | Valen-Dacanay J.G. |
| Year | 2024 |
| Published | Lecture Notes in Networks and Systems, 1083 LNNS |
| DOI | http://dx.doi.org/10.1007/978-3-031-67431-0_20 |
| Abstract | Emergency and immediate response systems often rely on sensors or trigger warnings, which can delay intervention until the issue becomes more serious. This study investigates the potential of facial emotion recognition using deep learning models to enhance immediate responses. This research proposed a framework that uses Convolutional Neural Networks (CNNs) to analyze facial expressions and predict potential emergencies. The research focuses on two main areas: First, an efficient CNN algorithm suitable for emotion recognition was studied. By utilizing FER2013 dataset for training and testing the model for performance. Methods for data enhancement and bias mitigation in model training have been explored. The second part focuses on sustainability implementation, where customer emotions were considered as possible response to marketing campaigns and to personalize interactions. By combining efficient deep learning and sustainable implementation methods, this research aims to contribute to the development of cost-effective and non-cost-effective next-generation systems one that is not only environmentally friendly, but also promotes social equity through strategies to mitigate bias. This can lead to improved real-time response time that reduced resource cost and impact on businesses. System performance is evaluated using metrics that are important for real-world deployment. This includes accuracy of sensing detection, and processing speed to ensure real-time performance. This research explores the potential of CNN basic deep learning and VGGNet architecture, respectively. Model accuracy and validation accuracy were measured based on the model performance through tuning measures. This work explored various performance evaluation criteria for image emotion recognition models, focusing on recognition speed, accuracy, and validation accuracy. This research aims to contributes to the development of sustainable and efficient deep learning solutions for proactive immediate response, potentially improving outcomes, reducing costs and achieving a safer environment. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. |
| Author Keywords | efficient deep learning; Facial emotion detection; proactive emergency response; smart city systems |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
25997  | 0.886 | Alsharekh M.F. | Facial Emotion Recognition In Verbal Communication Based On Deep Learning | Sensors, 22, 16 (2022) |
| 26100 | 0.865 | Badr O.S.; Ibrahim N.; Elmougy A. | Fake Emotion Detection Using Affective Cues And Speech Emotion Recognition For Improved Human Computer Interaction | 2023 2nd International Conference on Smart Cities 4.0, Smart Cities 4.0 2023 (2023) |
| 25996 | 0.858 | Farman H.; Sedik A.; Nasralla M.M.; Esmail M.A. | Facial Emotion Recognition In Smart Education Systems: A Review | Proceedings of 2023 IEEE International Smart Cities Conference, ISC2 2023 (2023) |
| 5244 | 0.854 | Costa W.; Talavera E.; Oliveira R.; Figueiredo L.; Teixeira J.M.; Lima J.P.; Teichrieb V. | A Survey On Datasets For Emotion Recognition From Vision: Limitations And In-The-Wild Applicability | Applied Sciences (Switzerland), 13, 9 (2023) |
| 21000 | 0.852 | Sharma A.; Kumar A. | Dream: Deep Learning-Based Recognition Of Emotions From Multiple Affective Modalities Using Consumer-Grade Body Sensors And Video Cameras | IEEE Transactions on Consumer Electronics, 70, 1 (2024) |
| 24557 | 0.852 | Elabora A.; Alkhatib M.; Mathew S.S.; El Barachi M. | Evaluating Citizens' Sentiments In Smart Cities: A Deep Learning Approach | 2020 5th International Conference on Smart and Sustainable Technologies, SpliTech 2020 (2020) |