Using wavelet transform and hybrid CNN – LSTM models on VOC & ultrasound IoT sensor data for non-visual maize disease detection
Early detection of plant diseases is crucial for safeguarding crop yield, especially in regions vulnerable to food insecurity, such as Sub-Saharan Africa. One of the significant contributors to maize crop yield loss is the Northern Leaf Blight (NLB), which traditionally takes 14–21 days to visually...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-02-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844024026781 |
| _version_ | 1797267605063467008 |
|---|---|
| author | Theofrida Julius Maginga Emmanuel Masabo Pierre Bakunzibake Kwang Soo Kim Jimmy Nsenga |
| author_facet | Theofrida Julius Maginga Emmanuel Masabo Pierre Bakunzibake Kwang Soo Kim Jimmy Nsenga |
| author_sort | Theofrida Julius Maginga |
| collection | DOAJ |
| description | Early detection of plant diseases is crucial for safeguarding crop yield, especially in regions vulnerable to food insecurity, such as Sub-Saharan Africa. One of the significant contributors to maize crop yield loss is the Northern Leaf Blight (NLB), which traditionally takes 14–21 days to visually manifest on maize. This study introduces a novel approach for detecting NLB as early as 4–5 days using Internet of Things (IoT) sensors, which can identify the disease before any visual symptoms appear. Utilizing Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) models, nonvisual measurements of Total Volatile Organic Compounds (VOCs) and ultrasound emissions from maize plants were captured and analyzed. A controlled experiment was conducted on four maize varieties, and the data obtained were used to develop and validate a hybrid CNN-LSTM model for VOC classification and an LSTM model for ultrasound anomaly detection. The hybrid CNN-LSTM model, enhanced with wavelet data preprocessing, achieved an F1 score of 0.96 and an Area under the ROC Curve (AUC) of 1.00. In contrast, the LSTM model exhibited an impressive 99.98% accuracy in identifying anomalies in ultrasound emissions. Our findings underscore the potential of IoT sensors in early disease detection, paving the way for innovative disease prevention strategies in agriculture. Future work will focus on optimizing the models for IoT device deployment, incorporating chatbot technology, and more sensor data will be incorporated for improved accuracy and evaluation of the models in a field environment. |
| first_indexed | 2024-03-07T22:54:17Z |
| format | Article |
| id | doaj.art-65b3219be8af41f59443df84479b6251 |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-04-25T01:19:14Z |
| publishDate | 2024-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-65b3219be8af41f59443df84479b62512024-03-09T09:28:45ZengElsevierHeliyon2405-84402024-02-01104e26647Using wavelet transform and hybrid CNN – LSTM models on VOC & ultrasound IoT sensor data for non-visual maize disease detectionTheofrida Julius Maginga0Emmanuel Masabo1Pierre Bakunzibake2Kwang Soo Kim3Jimmy Nsenga4African Centre of Excellence in Internet of Things (ACEIoT) - University of Rwanda (UR), Rwanda; Corresponding author.African Centre of Excellence in Internet of Things (ACEIoT) - University of Rwanda (UR), RwandaAfrican Centre of Excellence in Internet of Things (ACEIoT) - University of Rwanda (UR), RwandaGlobal Research and Development Business Centre (GRC-SNU) –Seoul National University (SNU), South KoreaAfrican Centre of Excellence in Internet of Things (ACEIoT) - University of Rwanda (UR), RwandaEarly detection of plant diseases is crucial for safeguarding crop yield, especially in regions vulnerable to food insecurity, such as Sub-Saharan Africa. One of the significant contributors to maize crop yield loss is the Northern Leaf Blight (NLB), which traditionally takes 14–21 days to visually manifest on maize. This study introduces a novel approach for detecting NLB as early as 4–5 days using Internet of Things (IoT) sensors, which can identify the disease before any visual symptoms appear. Utilizing Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) models, nonvisual measurements of Total Volatile Organic Compounds (VOCs) and ultrasound emissions from maize plants were captured and analyzed. A controlled experiment was conducted on four maize varieties, and the data obtained were used to develop and validate a hybrid CNN-LSTM model for VOC classification and an LSTM model for ultrasound anomaly detection. The hybrid CNN-LSTM model, enhanced with wavelet data preprocessing, achieved an F1 score of 0.96 and an Area under the ROC Curve (AUC) of 1.00. In contrast, the LSTM model exhibited an impressive 99.98% accuracy in identifying anomalies in ultrasound emissions. Our findings underscore the potential of IoT sensors in early disease detection, paving the way for innovative disease prevention strategies in agriculture. Future work will focus on optimizing the models for IoT device deployment, incorporating chatbot technology, and more sensor data will be incorporated for improved accuracy and evaluation of the models in a field environment.http://www.sciencedirect.com/science/article/pii/S2405844024026781CNNLSTMWaveletVOCUltrasoundMaize |
| spellingShingle | Theofrida Julius Maginga Emmanuel Masabo Pierre Bakunzibake Kwang Soo Kim Jimmy Nsenga Using wavelet transform and hybrid CNN – LSTM models on VOC & ultrasound IoT sensor data for non-visual maize disease detection Heliyon CNN LSTM Wavelet VOC Ultrasound Maize |
| title | Using wavelet transform and hybrid CNN – LSTM models on VOC & ultrasound IoT sensor data for non-visual maize disease detection |
| title_full | Using wavelet transform and hybrid CNN – LSTM models on VOC & ultrasound IoT sensor data for non-visual maize disease detection |
| title_fullStr | Using wavelet transform and hybrid CNN – LSTM models on VOC & ultrasound IoT sensor data for non-visual maize disease detection |
| title_full_unstemmed | Using wavelet transform and hybrid CNN – LSTM models on VOC & ultrasound IoT sensor data for non-visual maize disease detection |
| title_short | Using wavelet transform and hybrid CNN – LSTM models on VOC & ultrasound IoT sensor data for non-visual maize disease detection |
| title_sort | using wavelet transform and hybrid cnn lstm models on voc amp ultrasound iot sensor data for non visual maize disease detection |
| topic | CNN LSTM Wavelet VOC Ultrasound Maize |
| url | http://www.sciencedirect.com/science/article/pii/S2405844024026781 |
| work_keys_str_mv | AT theofridajuliusmaginga usingwavelettransformandhybridcnnlstmmodelsonvocampultrasoundiotsensordatafornonvisualmaizediseasedetection AT emmanuelmasabo usingwavelettransformandhybridcnnlstmmodelsonvocampultrasoundiotsensordatafornonvisualmaizediseasedetection AT pierrebakunzibake usingwavelettransformandhybridcnnlstmmodelsonvocampultrasoundiotsensordatafornonvisualmaizediseasedetection AT kwangsookim usingwavelettransformandhybridcnnlstmmodelsonvocampultrasoundiotsensordatafornonvisualmaizediseasedetection AT jimmynsenga usingwavelettransformandhybridcnnlstmmodelsonvocampultrasoundiotsensordatafornonvisualmaizediseasedetection |