Early Detection of Avian Diseases Based on Thermography and Artificial Intelligence
Non-invasive measures have a critical role in precision livestock and poultry farming as they can reduce animal stress and provide continuous monitoring. Animal activity can reflect physical and mental states as well as health conditions. If any problems are detected, an early warning will be provid...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Animals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-2615/13/14/2348 |
| _version_ | 1797590591336349696 |
|---|---|
| author | Mohammad Sadeghi Ahmad Banakar Saeid Minaei Mahdi Orooji Abdolhamid Shoushtari Guoming Li |
| author_facet | Mohammad Sadeghi Ahmad Banakar Saeid Minaei Mahdi Orooji Abdolhamid Shoushtari Guoming Li |
| author_sort | Mohammad Sadeghi |
| collection | DOAJ |
| description | Non-invasive measures have a critical role in precision livestock and poultry farming as they can reduce animal stress and provide continuous monitoring. Animal activity can reflect physical and mental states as well as health conditions. If any problems are detected, an early warning will be provided for necessary actions. The objective of this study was to identify avian diseases by using thermal-image processing and machine learning. Four groups of 14-day-old Ross 308 Broilers (20 birds per group) were used. Two groups were infected with one of the following diseases: Newcastle Disease (ND) and Avian Influenza (AI), and the other two were considered control groups. Thermal images were captured every 8 h and processed with MATLAB. After de-noising and removing the background, 23 statistical features were extracted, and the best features were selected using the improved distance evaluation method. Support vector machine (SVM) and artificial neural networks (ANN) were developed as classifiers. Results indicated that the former classifier outperformed the latter for disease classification. The Dempster–Shafer evidence theory was used as the data fusion stage if neither ANN nor SVM detected the diseases with acceptable accuracy. The final SVM-based framework achieved 97.2% and 100% accuracy for classifying AI and ND, respectively, within 24 h after virus infection. The proposed method is an innovative procedure for the timely identification of avian diseases to support early intervention. |
| first_indexed | 2024-03-11T01:22:44Z |
| format | Article |
| id | doaj.art-9f8c83569bbf4d61bd8f1e994bc6a63c |
| institution | Directory Open Access Journal |
| issn | 2076-2615 |
| language | English |
| last_indexed | 2024-03-11T01:22:44Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Animals |
| spelling | doaj.art-9f8c83569bbf4d61bd8f1e994bc6a63c2023-11-18T18:01:08ZengMDPI AGAnimals2076-26152023-07-011314234810.3390/ani13142348Early Detection of Avian Diseases Based on Thermography and Artificial IntelligenceMohammad Sadeghi0Ahmad Banakar1Saeid Minaei2Mahdi Orooji3Abdolhamid Shoushtari4Guoming Li5Biosystems Engineering Department, Tarbiat Modares University, Tehran 14117-13116, IranBiosystems Engineering Department, Tarbiat Modares University, Tehran 14117-13116, IranBiosystems Engineering Department, Tarbiat Modares University, Tehran 14117-13116, IranDepartment of Medical Engineering, Tarbiat Modares University, Tehran 14117-13116, IranDepartment of Poultry Disease, Razi Vaccine and Serum Research Institute, Karaj 31976-19751, IranDepartment of Poultry Science, Institute for Artificial Intelligence, University of Georgia, Athens, GA 30602, USANon-invasive measures have a critical role in precision livestock and poultry farming as they can reduce animal stress and provide continuous monitoring. Animal activity can reflect physical and mental states as well as health conditions. If any problems are detected, an early warning will be provided for necessary actions. The objective of this study was to identify avian diseases by using thermal-image processing and machine learning. Four groups of 14-day-old Ross 308 Broilers (20 birds per group) were used. Two groups were infected with one of the following diseases: Newcastle Disease (ND) and Avian Influenza (AI), and the other two were considered control groups. Thermal images were captured every 8 h and processed with MATLAB. After de-noising and removing the background, 23 statistical features were extracted, and the best features were selected using the improved distance evaluation method. Support vector machine (SVM) and artificial neural networks (ANN) were developed as classifiers. Results indicated that the former classifier outperformed the latter for disease classification. The Dempster–Shafer evidence theory was used as the data fusion stage if neither ANN nor SVM detected the diseases with acceptable accuracy. The final SVM-based framework achieved 97.2% and 100% accuracy for classifying AI and ND, respectively, within 24 h after virus infection. The proposed method is an innovative procedure for the timely identification of avian diseases to support early intervention.https://www.mdpi.com/2076-2615/13/14/2348avian diseasepoultryprecision livestock farmingmachine learningthermography |
| spellingShingle | Mohammad Sadeghi Ahmad Banakar Saeid Minaei Mahdi Orooji Abdolhamid Shoushtari Guoming Li Early Detection of Avian Diseases Based on Thermography and Artificial Intelligence Animals avian disease poultry precision livestock farming machine learning thermography |
| title | Early Detection of Avian Diseases Based on Thermography and Artificial Intelligence |
| title_full | Early Detection of Avian Diseases Based on Thermography and Artificial Intelligence |
| title_fullStr | Early Detection of Avian Diseases Based on Thermography and Artificial Intelligence |
| title_full_unstemmed | Early Detection of Avian Diseases Based on Thermography and Artificial Intelligence |
| title_short | Early Detection of Avian Diseases Based on Thermography and Artificial Intelligence |
| title_sort | early detection of avian diseases based on thermography and artificial intelligence |
| topic | avian disease poultry precision livestock farming machine learning thermography |
| url | https://www.mdpi.com/2076-2615/13/14/2348 |
| work_keys_str_mv | AT mohammadsadeghi earlydetectionofaviandiseasesbasedonthermographyandartificialintelligence AT ahmadbanakar earlydetectionofaviandiseasesbasedonthermographyandartificialintelligence AT saeidminaei earlydetectionofaviandiseasesbasedonthermographyandartificialintelligence AT mahdiorooji earlydetectionofaviandiseasesbasedonthermographyandartificialintelligence AT abdolhamidshoushtari earlydetectionofaviandiseasesbasedonthermographyandartificialintelligence AT guomingli earlydetectionofaviandiseasesbasedonthermographyandartificialintelligence |