Enhancing Animal Welfare with Interaction Recognition: A Deep Dive into Pig Interaction Using Xception Architecture and SSPD-PIR Method
The advent of artificial intelligence (AI) in animal husbandry, particularly in pig interaction recognition (PIR), offers a transformative approach to enhancing animal welfare, promoting sustainability, and bolstering climate resilience. This innovative methodology not only mitigates labor costs but...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/13/8/1522 |
| _version_ | 1797585878340599808 |
|---|---|
| author | Jung Hwan Kim Alwin Poulose Savina Jassica Colaco Suresh Neethirajan Dong Seog Han |
| author_facet | Jung Hwan Kim Alwin Poulose Savina Jassica Colaco Suresh Neethirajan Dong Seog Han |
| author_sort | Jung Hwan Kim |
| collection | DOAJ |
| description | The advent of artificial intelligence (AI) in animal husbandry, particularly in pig interaction recognition (PIR), offers a transformative approach to enhancing animal welfare, promoting sustainability, and bolstering climate resilience. This innovative methodology not only mitigates labor costs but also significantly reduces stress levels among domestic pigs, thereby diminishing the necessity for constant human intervention. However, the raw PIR datasets often encompass irrelevant porcine features, which pose a challenge for the accurate interpretation and application of these datasets in real-world scenarios. The majority of these datasets are derived from sequential pig imagery captured from video recordings, and an unregulated shuffling of data often leads to an overlap of data samples between training and testing groups, resulting in skewed experimental evaluations. To circumvent these obstacles, we introduced a groundbreaking solution—the Semi-Shuffle-Pig Detector (SSPD) for PIR datasets. This novel approach ensures a less biased experimental output by maintaining the distinctiveness of testing data samples from the training datasets and systematically discarding superfluous information from raw images. Our optimized method significantly enhances the true performance of classification, providing unbiased experimental evaluations. Remarkably, our approach has led to a substantial improvement in the isolation after feeding (IAF) metric by 20.2% and achieved higher accuracy in segregating IAF and paired after feeding (PAF) classifications exceeding 92%. This methodology, therefore, ensures the preservation of pertinent data within the PIR system and eliminates potential biases in experimental evaluations. As a result, it enhances the accuracy and reliability of real-world PIR applications, contributing to improved animal welfare management, elevated food safety standards, and a more sustainable and climate-resilient livestock industry. |
| first_indexed | 2024-03-11T00:12:24Z |
| format | Article |
| id | doaj.art-566eba1caf214dc59652497b78b91ebc |
| institution | Directory Open Access Journal |
| issn | 2077-0472 |
| language | English |
| last_indexed | 2024-03-11T00:12:24Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj.art-566eba1caf214dc59652497b78b91ebc2023-11-18T23:51:17ZengMDPI AGAgriculture2077-04722023-07-01138152210.3390/agriculture13081522Enhancing Animal Welfare with Interaction Recognition: A Deep Dive into Pig Interaction Using Xception Architecture and SSPD-PIR MethodJung Hwan Kim0Alwin Poulose1Savina Jassica Colaco2Suresh Neethirajan3Dong Seog Han4School of Electronic and Electrical Engineering, Kyungpook National University, 80 Daehak-ro Buk-gu, Daegu 41566, Republic of KoreaSchool of Data Science, Indian Institute of Science Education and Research, Thiruvananthapuram 695551, IndiaSchool of Electronic and Electrical Engineering, Kyungpook National University, 80 Daehak-ro Buk-gu, Daegu 41566, Republic of KoreaDepartment of Animal Science and Aquaculture, Faculty of Computer Science, Dalhousie University, 6050 University Ave, Halifax, NS B3H 1W5, CanadaSchool of Electronic and Electrical Engineering, Kyungpook National University, 80 Daehak-ro Buk-gu, Daegu 41566, Republic of KoreaThe advent of artificial intelligence (AI) in animal husbandry, particularly in pig interaction recognition (PIR), offers a transformative approach to enhancing animal welfare, promoting sustainability, and bolstering climate resilience. This innovative methodology not only mitigates labor costs but also significantly reduces stress levels among domestic pigs, thereby diminishing the necessity for constant human intervention. However, the raw PIR datasets often encompass irrelevant porcine features, which pose a challenge for the accurate interpretation and application of these datasets in real-world scenarios. The majority of these datasets are derived from sequential pig imagery captured from video recordings, and an unregulated shuffling of data often leads to an overlap of data samples between training and testing groups, resulting in skewed experimental evaluations. To circumvent these obstacles, we introduced a groundbreaking solution—the Semi-Shuffle-Pig Detector (SSPD) for PIR datasets. This novel approach ensures a less biased experimental output by maintaining the distinctiveness of testing data samples from the training datasets and systematically discarding superfluous information from raw images. Our optimized method significantly enhances the true performance of classification, providing unbiased experimental evaluations. Remarkably, our approach has led to a substantial improvement in the isolation after feeding (IAF) metric by 20.2% and achieved higher accuracy in segregating IAF and paired after feeding (PAF) classifications exceeding 92%. This methodology, therefore, ensures the preservation of pertinent data within the PIR system and eliminates potential biases in experimental evaluations. As a result, it enhances the accuracy and reliability of real-world PIR applications, contributing to improved animal welfare management, elevated food safety standards, and a more sustainable and climate-resilient livestock industry.https://www.mdpi.com/2077-0472/13/8/1522pig interaction recognition (PIR)convolution neural network (CNN)XceptionResNetdeep neural networkdomestic livestock |
| spellingShingle | Jung Hwan Kim Alwin Poulose Savina Jassica Colaco Suresh Neethirajan Dong Seog Han Enhancing Animal Welfare with Interaction Recognition: A Deep Dive into Pig Interaction Using Xception Architecture and SSPD-PIR Method Agriculture pig interaction recognition (PIR) convolution neural network (CNN) Xception ResNet deep neural network domestic livestock |
| title | Enhancing Animal Welfare with Interaction Recognition: A Deep Dive into Pig Interaction Using Xception Architecture and SSPD-PIR Method |
| title_full | Enhancing Animal Welfare with Interaction Recognition: A Deep Dive into Pig Interaction Using Xception Architecture and SSPD-PIR Method |
| title_fullStr | Enhancing Animal Welfare with Interaction Recognition: A Deep Dive into Pig Interaction Using Xception Architecture and SSPD-PIR Method |
| title_full_unstemmed | Enhancing Animal Welfare with Interaction Recognition: A Deep Dive into Pig Interaction Using Xception Architecture and SSPD-PIR Method |
| title_short | Enhancing Animal Welfare with Interaction Recognition: A Deep Dive into Pig Interaction Using Xception Architecture and SSPD-PIR Method |
| title_sort | enhancing animal welfare with interaction recognition a deep dive into pig interaction using xception architecture and sspd pir method |
| topic | pig interaction recognition (PIR) convolution neural network (CNN) Xception ResNet deep neural network domestic livestock |
| url | https://www.mdpi.com/2077-0472/13/8/1522 |
| work_keys_str_mv | AT junghwankim enhancinganimalwelfarewithinteractionrecognitionadeepdiveintopiginteractionusingxceptionarchitectureandsspdpirmethod AT alwinpoulose enhancinganimalwelfarewithinteractionrecognitionadeepdiveintopiginteractionusingxceptionarchitectureandsspdpirmethod AT savinajassicacolaco enhancinganimalwelfarewithinteractionrecognitionadeepdiveintopiginteractionusingxceptionarchitectureandsspdpirmethod AT sureshneethirajan enhancinganimalwelfarewithinteractionrecognitionadeepdiveintopiginteractionusingxceptionarchitectureandsspdpirmethod AT dongseoghan enhancinganimalwelfarewithinteractionrecognitionadeepdiveintopiginteractionusingxceptionarchitectureandsspdpirmethod |