SCANet: Implementation of Selective Context Adaptation Network in Smart Farming Applications
In the last decade, deep learning has enjoyed its spotlight as the game-changing addition to smart farming and precision agriculture. Such development has been predominantly observed in developed countries, while on the other hand, in developing countries most farmers especially ones with smallholde...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/3/1358 |
| _version_ | 1797623261745381376 |
|---|---|
| author | Xanno Sigalingging Setya Widyawan Prakosa Jenq-Shiou Leu He-Yen Hsieh Cries Avian Muhamad Faisal |
| author_facet | Xanno Sigalingging Setya Widyawan Prakosa Jenq-Shiou Leu He-Yen Hsieh Cries Avian Muhamad Faisal |
| author_sort | Xanno Sigalingging |
| collection | DOAJ |
| description | In the last decade, deep learning has enjoyed its spotlight as the game-changing addition to smart farming and precision agriculture. Such development has been predominantly observed in developed countries, while on the other hand, in developing countries most farmers especially ones with smallholder farms have not enjoyed such wide and deep adoption of this new technologies. In this paper we attempt to improve the image classification part of smart farming and precision agriculture. Agricultural commodities tend to possess certain textural details on their surfaces which we attempt to exploit. In this work, we propose a deep learning based approach called Selective Context Adaptation Network (SCANet). SCANet performs feature enhancement strategy by leveraging level-wise information and employing context selection mechanism. In exploiting contextual correlation feature of the crop images our proposed approach demonstrates the effectiveness of the context selection mechanism. Our proposed scheme achieves <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>88.72</mn><mo>%</mo></mrow></semantics></math></inline-formula> accuracy and outperforms the existing approaches. Our model is evaluated on the cocoa bean dataset constructed from the real cocoa bean industry scene in Indonesia. |
| first_indexed | 2024-03-11T09:26:10Z |
| format | Article |
| id | doaj.art-7dd89dfc4a304edb96e098df8b2625bb |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T09:26:10Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-7dd89dfc4a304edb96e098df8b2625bb2023-11-16T17:59:55ZengMDPI AGSensors1424-82202023-01-01233135810.3390/s23031358SCANet: Implementation of Selective Context Adaptation Network in Smart Farming ApplicationsXanno Sigalingging0Setya Widyawan Prakosa1Jenq-Shiou Leu2He-Yen Hsieh3Cries Avian4Muhamad Faisal5Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei City 10607, TaiwanDepartment of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei City 10607, TaiwanDepartment of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei City 10607, TaiwanDepartment of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei City 10607, TaiwanDepartment of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei City 10607, TaiwanDepartment of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei City 10607, TaiwanIn the last decade, deep learning has enjoyed its spotlight as the game-changing addition to smart farming and precision agriculture. Such development has been predominantly observed in developed countries, while on the other hand, in developing countries most farmers especially ones with smallholder farms have not enjoyed such wide and deep adoption of this new technologies. In this paper we attempt to improve the image classification part of smart farming and precision agriculture. Agricultural commodities tend to possess certain textural details on their surfaces which we attempt to exploit. In this work, we propose a deep learning based approach called Selective Context Adaptation Network (SCANet). SCANet performs feature enhancement strategy by leveraging level-wise information and employing context selection mechanism. In exploiting contextual correlation feature of the crop images our proposed approach demonstrates the effectiveness of the context selection mechanism. Our proposed scheme achieves <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>88.72</mn><mo>%</mo></mrow></semantics></math></inline-formula> accuracy and outperforms the existing approaches. Our model is evaluated on the cocoa bean dataset constructed from the real cocoa bean industry scene in Indonesia.https://www.mdpi.com/1424-8220/23/3/1358deep learningSelective Context Adaptationsmart farmingprecision agriculturelevel-wise information |
| spellingShingle | Xanno Sigalingging Setya Widyawan Prakosa Jenq-Shiou Leu He-Yen Hsieh Cries Avian Muhamad Faisal SCANet: Implementation of Selective Context Adaptation Network in Smart Farming Applications Sensors deep learning Selective Context Adaptation smart farming precision agriculture level-wise information |
| title | SCANet: Implementation of Selective Context Adaptation Network in Smart Farming Applications |
| title_full | SCANet: Implementation of Selective Context Adaptation Network in Smart Farming Applications |
| title_fullStr | SCANet: Implementation of Selective Context Adaptation Network in Smart Farming Applications |
| title_full_unstemmed | SCANet: Implementation of Selective Context Adaptation Network in Smart Farming Applications |
| title_short | SCANet: Implementation of Selective Context Adaptation Network in Smart Farming Applications |
| title_sort | scanet implementation of selective context adaptation network in smart farming applications |
| topic | deep learning Selective Context Adaptation smart farming precision agriculture level-wise information |
| url | https://www.mdpi.com/1424-8220/23/3/1358 |
| work_keys_str_mv | AT xannosigalingging scanetimplementationofselectivecontextadaptationnetworkinsmartfarmingapplications AT setyawidyawanprakosa scanetimplementationofselectivecontextadaptationnetworkinsmartfarmingapplications AT jenqshiouleu scanetimplementationofselectivecontextadaptationnetworkinsmartfarmingapplications AT heyenhsieh scanetimplementationofselectivecontextadaptationnetworkinsmartfarmingapplications AT criesavian scanetimplementationofselectivecontextadaptationnetworkinsmartfarmingapplications AT muhamadfaisal scanetimplementationofselectivecontextadaptationnetworkinsmartfarmingapplications |