A Deep Learning-Based Approach for Precise Emotion Recognition in Domestic Animals Using EfficientNetB5 Architecture
The perception of animal emotions is key to enhancing veterinary practice, human–animal interactions, and protecting domesticated species’ welfare. This study presents a unique emotion classification deep learning-based approach for pet animals. The actual and emotional status of dogs and cats have...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Eng |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4117/6/1/9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588587010359296 |
|---|---|
| author | Rashadul Islam Sumon Haider Ali Salma Akter Shah Muhammad Imtiyaj Uddin Md Ariful Islam Mozumder Hee-Cheol Kim |
| author_facet | Rashadul Islam Sumon Haider Ali Salma Akter Shah Muhammad Imtiyaj Uddin Md Ariful Islam Mozumder Hee-Cheol Kim |
| author_sort | Rashadul Islam Sumon |
| collection | DOAJ |
| description | The perception of animal emotions is key to enhancing veterinary practice, human–animal interactions, and protecting domesticated species’ welfare. This study presents a unique emotion classification deep learning-based approach for pet animals. The actual and emotional status of dogs and cats have been classified using a modified EfficientNetB5 model. Utilizing a dataset of images classified into four different emotion categories—angry, sad, happy, and neutral—the model incorporates sophisticated feature extraction methods, such as Dense Residual Blocks and Squeeze-and-Excitation (SE) blocks, to improve the focus on important emotional indicators. The basis of the second strategy is EfficientNetB5, which is known for providing an optimal balance in terms of accuracy and processing capabilities. The model exhibited robust generalization abilities for the subtle identification of emotional states, achieving 98.2% accuracy in training and 91.24% during validation on a separate dataset. These encouraging outcomes support the model’s promise for real-time emotion detection applications and demonstrate its adaptability for wider application in ongoing pet monitoring systems. The dataset will be enlarged, model performance will be enhanced for more species, and real-time capabilities will be developed for real-world implementation. |
| format | Article |
| id | doaj-art-e4d8349b5dff4255af4e82a0e1e665e1 |
| institution | Kabale University |
| issn | 2673-4117 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Eng |
| spelling | doaj-art-e4d8349b5dff4255af4e82a0e1e665e12025-01-24T13:31:33ZengMDPI AGEng2673-41172025-01-0161910.3390/eng6010009A Deep Learning-Based Approach for Precise Emotion Recognition in Domestic Animals Using EfficientNetB5 ArchitectureRashadul Islam Sumon0Haider Ali1Salma Akter2Shah Muhammad Imtiyaj Uddin3Md Ariful Islam Mozumder4Hee-Cheol Kim5Institute of Digital Anti-Aging Healthcare, Inje University, Gimhae-si 50834, Republic of KoreaInstitute of Digital Anti-Aging Healthcare, Inje University, Gimhae-si 50834, Republic of KoreaInstitute of Digital Anti-Aging Healthcare, Inje University, Gimhae-si 50834, Republic of KoreaInstitute of Digital Anti-Aging Healthcare, Inje University, Gimhae-si 50834, Republic of KoreaInstitute of Digital Anti-Aging Healthcare, Inje University, Gimhae-si 50834, Republic of KoreaInstitute of Digital Anti-Aging Healthcare, Inje University, Gimhae-si 50834, Republic of KoreaThe perception of animal emotions is key to enhancing veterinary practice, human–animal interactions, and protecting domesticated species’ welfare. This study presents a unique emotion classification deep learning-based approach for pet animals. The actual and emotional status of dogs and cats have been classified using a modified EfficientNetB5 model. Utilizing a dataset of images classified into four different emotion categories—angry, sad, happy, and neutral—the model incorporates sophisticated feature extraction methods, such as Dense Residual Blocks and Squeeze-and-Excitation (SE) blocks, to improve the focus on important emotional indicators. The basis of the second strategy is EfficientNetB5, which is known for providing an optimal balance in terms of accuracy and processing capabilities. The model exhibited robust generalization abilities for the subtle identification of emotional states, achieving 98.2% accuracy in training and 91.24% during validation on a separate dataset. These encouraging outcomes support the model’s promise for real-time emotion detection applications and demonstrate its adaptability for wider application in ongoing pet monitoring systems. The dataset will be enlarged, model performance will be enhanced for more species, and real-time capabilities will be developed for real-world implementation.https://www.mdpi.com/2673-4117/6/1/9emotion detectiondomestic animalangerhappysadEfficientNetB5 |
| spellingShingle | Rashadul Islam Sumon Haider Ali Salma Akter Shah Muhammad Imtiyaj Uddin Md Ariful Islam Mozumder Hee-Cheol Kim A Deep Learning-Based Approach for Precise Emotion Recognition in Domestic Animals Using EfficientNetB5 Architecture Eng emotion detection domestic animal anger happy sad EfficientNetB5 |
| title | A Deep Learning-Based Approach for Precise Emotion Recognition in Domestic Animals Using EfficientNetB5 Architecture |
| title_full | A Deep Learning-Based Approach for Precise Emotion Recognition in Domestic Animals Using EfficientNetB5 Architecture |
| title_fullStr | A Deep Learning-Based Approach for Precise Emotion Recognition in Domestic Animals Using EfficientNetB5 Architecture |
| title_full_unstemmed | A Deep Learning-Based Approach for Precise Emotion Recognition in Domestic Animals Using EfficientNetB5 Architecture |
| title_short | A Deep Learning-Based Approach for Precise Emotion Recognition in Domestic Animals Using EfficientNetB5 Architecture |
| title_sort | deep learning based approach for precise emotion recognition in domestic animals using efficientnetb5 architecture |
| topic | emotion detection domestic animal anger happy sad EfficientNetB5 |
| url | https://www.mdpi.com/2673-4117/6/1/9 |
| work_keys_str_mv | AT rashadulislamsumon adeeplearningbasedapproachforpreciseemotionrecognitionindomesticanimalsusingefficientnetb5architecture AT haiderali adeeplearningbasedapproachforpreciseemotionrecognitionindomesticanimalsusingefficientnetb5architecture AT salmaakter adeeplearningbasedapproachforpreciseemotionrecognitionindomesticanimalsusingefficientnetb5architecture AT shahmuhammadimtiyajuddin adeeplearningbasedapproachforpreciseemotionrecognitionindomesticanimalsusingefficientnetb5architecture AT mdarifulislammozumder adeeplearningbasedapproachforpreciseemotionrecognitionindomesticanimalsusingefficientnetb5architecture AT heecheolkim adeeplearningbasedapproachforpreciseemotionrecognitionindomesticanimalsusingefficientnetb5architecture AT rashadulislamsumon deeplearningbasedapproachforpreciseemotionrecognitionindomesticanimalsusingefficientnetb5architecture AT haiderali deeplearningbasedapproachforpreciseemotionrecognitionindomesticanimalsusingefficientnetb5architecture AT salmaakter deeplearningbasedapproachforpreciseemotionrecognitionindomesticanimalsusingefficientnetb5architecture AT shahmuhammadimtiyajuddin deeplearningbasedapproachforpreciseemotionrecognitionindomesticanimalsusingefficientnetb5architecture AT mdarifulislammozumder deeplearningbasedapproachforpreciseemotionrecognitionindomesticanimalsusingefficientnetb5architecture AT heecheolkim deeplearningbasedapproachforpreciseemotionrecognitionindomesticanimalsusingefficientnetb5architecture |