Proposed Fuzzy-Stranded-Neural Network Model That Utilizes IoT Plant-Level Sensory Monitoring and Distributed Services for the Early Detection of Downy Mildew in Viticulture
Novel monitoring architecture approaches are required to detect viticulture diseases early. Existing micro-climate decision support systems can only cope with late detection from empirical and semi-empirical models that provide less accurate results. Such models cannot alleviate precision viticultur...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/13/3/63 |
| _version_ | 1797241569207648256 |
|---|---|
| author | Sotirios Kontogiannis Stefanos Koundouras Christos Pikridas |
| author_facet | Sotirios Kontogiannis Stefanos Koundouras Christos Pikridas |
| author_sort | Sotirios Kontogiannis |
| collection | DOAJ |
| description | Novel monitoring architecture approaches are required to detect viticulture diseases early. Existing micro-climate decision support systems can only cope with late detection from empirical and semi-empirical models that provide less accurate results. Such models cannot alleviate precision viticulture planning and pesticide control actions, providing early reconnaissances that may trigger interventions. This paper presents a new plant-level monitoring architecture called thingsAI. The proposed system utilizes low-cost, autonomous, easy-to-install IoT sensors for vine-level monitoring, utilizing the low-power LoRaWAN protocol for sensory measurement acquisition. Facilitated by a distributed cloud architecture and open-source user interfaces, it provides state-of-the-art deep learning inference services and decision support interfaces. This paper also presents a new deep learning detection algorithm based on supervised fuzzy annotation processes, targeting downy mildew disease detection and, therefore, planning early interventions. The authors tested their proposed system and deep learning model on the grape variety of protected designation of origin called debina, cultivated in Zitsa, Greece. From their experimental results, the authors show that their proposed model can detect vine locations and timely breakpoints of mildew occurrences, which farmers can use as input for targeted intervention efforts. |
| first_indexed | 2024-04-24T18:25:24Z |
| format | Article |
| id | doaj.art-3468e2f449964cbebbb741afef539d06 |
| institution | Directory Open Access Journal |
| issn | 2073-431X |
| language | English |
| last_indexed | 2024-04-24T18:25:24Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj.art-3468e2f449964cbebbb741afef539d062024-03-27T13:31:59ZengMDPI AGComputers2073-431X2024-02-011336310.3390/computers13030063Proposed Fuzzy-Stranded-Neural Network Model That Utilizes IoT Plant-Level Sensory Monitoring and Distributed Services for the Early Detection of Downy Mildew in ViticultureSotirios Kontogiannis0Stefanos Koundouras1Christos Pikridas2Laboratory Team of Distributed Microcomputer Systems, Department of Mathematics, University of Ioannina, University Campus, 45110 Ioannina, GreeceDepartment of Agriculture, Aristotle University of Thessaloniki, 54124 Thessaloniki, GreeceSchool of Rural and Surveying Engineering, Aristotle University of Thessaloniki, 54124 Thessaloniki, GreeceNovel monitoring architecture approaches are required to detect viticulture diseases early. Existing micro-climate decision support systems can only cope with late detection from empirical and semi-empirical models that provide less accurate results. Such models cannot alleviate precision viticulture planning and pesticide control actions, providing early reconnaissances that may trigger interventions. This paper presents a new plant-level monitoring architecture called thingsAI. The proposed system utilizes low-cost, autonomous, easy-to-install IoT sensors for vine-level monitoring, utilizing the low-power LoRaWAN protocol for sensory measurement acquisition. Facilitated by a distributed cloud architecture and open-source user interfaces, it provides state-of-the-art deep learning inference services and decision support interfaces. This paper also presents a new deep learning detection algorithm based on supervised fuzzy annotation processes, targeting downy mildew disease detection and, therefore, planning early interventions. The authors tested their proposed system and deep learning model on the grape variety of protected designation of origin called debina, cultivated in Zitsa, Greece. From their experimental results, the authors show that their proposed model can detect vine locations and timely breakpoints of mildew occurrences, which farmers can use as input for targeted intervention efforts.https://www.mdpi.com/2073-431X/13/3/63viticulture decision makingagriculture 4.0precision agriculturedeep learning modelsdecision support systems for the agriculture industrydistributed IoT systems and services |
| spellingShingle | Sotirios Kontogiannis Stefanos Koundouras Christos Pikridas Proposed Fuzzy-Stranded-Neural Network Model That Utilizes IoT Plant-Level Sensory Monitoring and Distributed Services for the Early Detection of Downy Mildew in Viticulture Computers viticulture decision making agriculture 4.0 precision agriculture deep learning models decision support systems for the agriculture industry distributed IoT systems and services |
| title | Proposed Fuzzy-Stranded-Neural Network Model That Utilizes IoT Plant-Level Sensory Monitoring and Distributed Services for the Early Detection of Downy Mildew in Viticulture |
| title_full | Proposed Fuzzy-Stranded-Neural Network Model That Utilizes IoT Plant-Level Sensory Monitoring and Distributed Services for the Early Detection of Downy Mildew in Viticulture |
| title_fullStr | Proposed Fuzzy-Stranded-Neural Network Model That Utilizes IoT Plant-Level Sensory Monitoring and Distributed Services for the Early Detection of Downy Mildew in Viticulture |
| title_full_unstemmed | Proposed Fuzzy-Stranded-Neural Network Model That Utilizes IoT Plant-Level Sensory Monitoring and Distributed Services for the Early Detection of Downy Mildew in Viticulture |
| title_short | Proposed Fuzzy-Stranded-Neural Network Model That Utilizes IoT Plant-Level Sensory Monitoring and Distributed Services for the Early Detection of Downy Mildew in Viticulture |
| title_sort | proposed fuzzy stranded neural network model that utilizes iot plant level sensory monitoring and distributed services for the early detection of downy mildew in viticulture |
| topic | viticulture decision making agriculture 4.0 precision agriculture deep learning models decision support systems for the agriculture industry distributed IoT systems and services |
| url | https://www.mdpi.com/2073-431X/13/3/63 |
| work_keys_str_mv | AT sotirioskontogiannis proposedfuzzystrandedneuralnetworkmodelthatutilizesiotplantlevelsensorymonitoringanddistributedservicesfortheearlydetectionofdownymildewinviticulture AT stefanoskoundouras proposedfuzzystrandedneuralnetworkmodelthatutilizesiotplantlevelsensorymonitoringanddistributedservicesfortheearlydetectionofdownymildewinviticulture AT christospikridas proposedfuzzystrandedneuralnetworkmodelthatutilizesiotplantlevelsensorymonitoringanddistributedservicesfortheearlydetectionofdownymildewinviticulture |