PFDI: a precise fruit disease identification model based on context data fusion with faster-CNN in edge computing environment
Abstract Fruits significantly impact everyday living, i.e., Citrus fruits. Numerous fruits have a solid nutritious value and are packed with multivitamins and trace components. Citrus fruits are delicate and susceptible to many diseases and infections. Many researchers have suggested deep and machin...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-06-01
|
| Series: | EURASIP Journal on Advances in Signal Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13634-023-01025-y |
| _version_ | 1827916639548473344 |
|---|---|
| author | Poonam Dhiman Poongodi Manoharan Umesh Kumar Lilhore Roobaea Alroobaea Amandeep Kaur Celestine Iwendi Majed Alsafyani Abdullah M. Baqasah Kaamran Raahemifar |
| author_facet | Poonam Dhiman Poongodi Manoharan Umesh Kumar Lilhore Roobaea Alroobaea Amandeep Kaur Celestine Iwendi Majed Alsafyani Abdullah M. Baqasah Kaamran Raahemifar |
| author_sort | Poonam Dhiman |
| collection | DOAJ |
| description | Abstract Fruits significantly impact everyday living, i.e., Citrus fruits. Numerous fruits have a solid nutritious value and are packed with multivitamins and trace components. Citrus fruits are delicate and susceptible to many diseases and infections. Many researchers have suggested deep and machine learning-based fruit disease detection and classification models. This research presents a precise fruit disease identification model based on context data fusion with Faster-CNN in an edge computing environment. The goal is to develop an accurate, efficient, and trustable fruit disease detection model, a critical component of autonomous food production in a robotic edge platform. This research examines and explores four different diseases of Citrus fruits using CNN deep learning models to be adopted as edge computing solutions. Identification of citrus diseases such as cankers black spot, greening, scab, melanosis, and healthy citrus fruits are implemented using the proposed sequential model without pruning, with pruning having different sparsity levels followed by post quantization. Through the transfer learning method, this model is optimized for the assignment of fruit disease detection employing visuals from two patterns: Near-infrared (NIFR) and RGB. Early and late data fusion techniques for integrating multi-model (NIFR and RGB) facts are evaluated. The accuracy obtained from the proposed model for the canker disease is 97%, scab 95%, melanosis 99%, Greening 97%, Black spot 97% and healthy 97%. In this paper, the results of the proposed model are compared and evaluated with the sparsity levels of 50–80%, 60–90%, 70–90%, and 80–90% pruning and also obtained the results of post-quantization on each level. The results show that the model size with 60–90% pruning can be counteracted to the 47.64 of the baseline model without significant loss of accuracy. Moreover, post-quantization can reduce the 60–90% pruning from 28.16 to 8.72. In addition to enhanced precision, the above initiative is much faster to implement for new fruit diseases because it needs bounding box annotation instead of pixel-level annotation. |
| first_indexed | 2024-03-13T03:18:08Z |
| format | Article |
| id | doaj.art-612062a65e934624b6d5736913b22991 |
| institution | Directory Open Access Journal |
| issn | 1687-6180 |
| language | English |
| last_indexed | 2024-03-13T03:18:08Z |
| publishDate | 2023-06-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Advances in Signal Processing |
| spelling | doaj.art-612062a65e934624b6d5736913b229912023-06-25T11:32:10ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61802023-06-012023111810.1186/s13634-023-01025-yPFDI: a precise fruit disease identification model based on context data fusion with faster-CNN in edge computing environmentPoonam Dhiman0Poongodi Manoharan1Umesh Kumar Lilhore2Roobaea Alroobaea3Amandeep Kaur4Celestine Iwendi5Majed Alsafyani6Abdullah M. Baqasah7Kaamran Raahemifar8Department of Higher Education, Government PG CollegeDivision of Information and Communication Technology, College of Science and Engineering, Hamad Bin Khalifa UniversityDepartment of Computer Science and Engineering, Chandigarh UniversityDepartment of Computer Science, College of Computers and Information Technology, Taif UniversityChitkara University Institute of Engineering and Technology, Chitkara UniversitySchool of Creative Technologies, University of BoltonDepartment of Computer Science, College of Computers and Information Technology, Taif UniversityDepartment of Information Technology, College of Computers and Information Technology, Taif UniversityCollege of Information Sciences and Technology, Data Science and Artificial Intelligence Program, Penn StateUniversityAbstract Fruits significantly impact everyday living, i.e., Citrus fruits. Numerous fruits have a solid nutritious value and are packed with multivitamins and trace components. Citrus fruits are delicate and susceptible to many diseases and infections. Many researchers have suggested deep and machine learning-based fruit disease detection and classification models. This research presents a precise fruit disease identification model based on context data fusion with Faster-CNN in an edge computing environment. The goal is to develop an accurate, efficient, and trustable fruit disease detection model, a critical component of autonomous food production in a robotic edge platform. This research examines and explores four different diseases of Citrus fruits using CNN deep learning models to be adopted as edge computing solutions. Identification of citrus diseases such as cankers black spot, greening, scab, melanosis, and healthy citrus fruits are implemented using the proposed sequential model without pruning, with pruning having different sparsity levels followed by post quantization. Through the transfer learning method, this model is optimized for the assignment of fruit disease detection employing visuals from two patterns: Near-infrared (NIFR) and RGB. Early and late data fusion techniques for integrating multi-model (NIFR and RGB) facts are evaluated. The accuracy obtained from the proposed model for the canker disease is 97%, scab 95%, melanosis 99%, Greening 97%, Black spot 97% and healthy 97%. In this paper, the results of the proposed model are compared and evaluated with the sparsity levels of 50–80%, 60–90%, 70–90%, and 80–90% pruning and also obtained the results of post-quantization on each level. The results show that the model size with 60–90% pruning can be counteracted to the 47.64 of the baseline model without significant loss of accuracy. Moreover, post-quantization can reduce the 60–90% pruning from 28.16 to 8.72. In addition to enhanced precision, the above initiative is much faster to implement for new fruit diseases because it needs bounding box annotation instead of pixel-level annotation.https://doi.org/10.1186/s13634-023-01025-yData fusionDeep learningPruningDiseaseSparsityQuantization |
| spellingShingle | Poonam Dhiman Poongodi Manoharan Umesh Kumar Lilhore Roobaea Alroobaea Amandeep Kaur Celestine Iwendi Majed Alsafyani Abdullah M. Baqasah Kaamran Raahemifar PFDI: a precise fruit disease identification model based on context data fusion with faster-CNN in edge computing environment EURASIP Journal on Advances in Signal Processing Data fusion Deep learning Pruning Disease Sparsity Quantization |
| title | PFDI: a precise fruit disease identification model based on context data fusion with faster-CNN in edge computing environment |
| title_full | PFDI: a precise fruit disease identification model based on context data fusion with faster-CNN in edge computing environment |
| title_fullStr | PFDI: a precise fruit disease identification model based on context data fusion with faster-CNN in edge computing environment |
| title_full_unstemmed | PFDI: a precise fruit disease identification model based on context data fusion with faster-CNN in edge computing environment |
| title_short | PFDI: a precise fruit disease identification model based on context data fusion with faster-CNN in edge computing environment |
| title_sort | pfdi a precise fruit disease identification model based on context data fusion with faster cnn in edge computing environment |
| topic | Data fusion Deep learning Pruning Disease Sparsity Quantization |
| url | https://doi.org/10.1186/s13634-023-01025-y |
| work_keys_str_mv | AT poonamdhiman pfdiaprecisefruitdiseaseidentificationmodelbasedoncontextdatafusionwithfastercnninedgecomputingenvironment AT poongodimanoharan pfdiaprecisefruitdiseaseidentificationmodelbasedoncontextdatafusionwithfastercnninedgecomputingenvironment AT umeshkumarlilhore pfdiaprecisefruitdiseaseidentificationmodelbasedoncontextdatafusionwithfastercnninedgecomputingenvironment AT roobaeaalroobaea pfdiaprecisefruitdiseaseidentificationmodelbasedoncontextdatafusionwithfastercnninedgecomputingenvironment AT amandeepkaur pfdiaprecisefruitdiseaseidentificationmodelbasedoncontextdatafusionwithfastercnninedgecomputingenvironment AT celestineiwendi pfdiaprecisefruitdiseaseidentificationmodelbasedoncontextdatafusionwithfastercnninedgecomputingenvironment AT majedalsafyani pfdiaprecisefruitdiseaseidentificationmodelbasedoncontextdatafusionwithfastercnninedgecomputingenvironment AT abdullahmbaqasah pfdiaprecisefruitdiseaseidentificationmodelbasedoncontextdatafusionwithfastercnninedgecomputingenvironment AT kaamranraahemifar pfdiaprecisefruitdiseaseidentificationmodelbasedoncontextdatafusionwithfastercnninedgecomputingenvironment |