Smart Agriculture Applications Using Deep Learning Technologies: A Survey
Abstract
:1. Introduction
2. Materials and Methods
- The areas of smart agriculture that were focused on.
- The problems that they tried to solve.
- The deep learning techniques and models used.
- The dataset used.
- The data preprocessing and data augmentation methods that were used.
- The results in terms of accuracy or precision.
3. Deep Learning
3.1. Convolutional Neural Network (CNN)
3.1.1. Convolutional Layer
3.1.2. Pooling Layer
3.1.3. Fully Connected Layer
3.2. Recurrent Neural Network (RNN)
4. Applications of Deep Learning in Agriculture
4.1. Identification/Classification of Plant Disease
4.2. Crop Identification/Classification
4.3. Identification of Weeds
4.4. Identification of Water Stress
4.5. Weather Forecasting
4.6. Fruit Counting
Ref | Agriculture Area | Problem Description | Dataset | DL Model | Framework | Data Preprocessing | Data Augmentation | Results |
---|---|---|---|---|---|---|---|---|
[16] | Identification/classification of plant disease | Detection and classification of banana diseases | (Public dataset). Dataset of 3700 images of banana diseases obtained from the PlantVillage dataset | CNN (LeNet architecture) | Deep learning4j | Resized to 60 × 60 pix., converted to grayscale | N/A | F1-scor 0.968 |
[17] | Identification/classification of plant disease | Classifying and detecting plant diseases from leaf images | (Public dataset). Image of the plants, 87,000 images of healthy and diseased crop leaves from Kaggle | Alex Net | Developed by the authors | N/A | Applied data augmentation techniques | N/A |
[18] | Identification/classification of plant disease | Classify the diseases of sunflower leaf | Data collected by the authors using Google Images | Hybrid model Vgg16 and MoileNet | Keras | Converted the images of size 224 × 224 × 3 into an array | Used ImageDataGenerator class | Accuracy 89.2% |
[19] | Identification/classification of plant disease | Pest and disease detection in rice crops | - Artificial rice leaf images were obtained through Kaggle and comprised a total of 3355 images - Real Data 200 images were collected from rice fields in Gujranwala, Pakistan | Vgg16 Vgg19 ResNet50 ResNet50V2 ResNet101V2 | Keras | Leaf segmentation, background, shadow removal, intensity scaling, and all images were resized to 225 × 225 for uniformity | Data augmentation |
|
[20] | Identification/classification of plant disease | Plant leaf disease diagnosis process | Collected more than labeled 96k images of healthy and infected plant leaves | CNN | Keras TensorFlow | Altered the contrast of image colors, added Gaussian noise, and used image desaturation. | Geometric transformations | Accuracy 94% |
[21] | Identification/classification of plant disease | Prediction of diseases of crops | (Public dataset). Plant Village Dataset contains 54,306 images of leaves and can identify 38 different diseases | DNN | TensorFlow PyTorch, | N/A | N/A | Accuracy 99.24 |
[22] | Identification/classification of plant disease | Classification and identification of plant diseases | A dataset containing 30,880 training images and 2589 validation images was downloaded from the internet | CNN | Developed by the author | All the images are cropped manually, A square is made around the leaves, and Images are resized to 256 × 256 | Affine transformations | Average precision of 96.3%. |
[23] | Identification/classification of plant disease | Classification of plant’s health | 1918 pictures | CNN | Developed by the author | Resized to 224 × 224 and converted to RGB | 1918 pictures were obtained and were augmented to 4588 images | Accuracy of 99.58% |
[24] | Identification/classification of plant disease | Detection and classification of plant diseases | 500 images of 30 different native types of plants of Tamil Nadu | SVM | Developed by the author | Resized to 32 × 32 pixels are converted to HSI format. | N/A | Accuracy 94% |
[25] | Identification/classification of plant disease | Detection of the health and several unhealthy tomato leaf images | 18,161 tomato leaf images frthe om PlantVillage dataset | EfficientNet-B7 EfficientNet-B4 | PyTorch | Resized to 224 × 224 | rotation, scaling, and translation | Accuracy 99.89% |
[26] | Identification/classification of plant disease | Classification of tomato plant diseases | PlantVillage dataset | Random Forest | Developed by the author | Image resizing using cubic interpolation and adjusting colors | N/A | Accuracy 97% |
[27] | Identification/classification of plant disease | Detection of tomato plant diseases | PlantVillage dataset | ResNet-50+SeNet | PyTorch | N/A | Spin, Zoom, Add noise, and Color jitter. | Accuracy 96.81% |
[28] | Identification/classification of plant disease | Detection of tomato plant diseases | PlantVillage dataset | Lightweight CBAM attention module based ResNet20(Lw_renet20_cbam) | Keras with TensorFlow | labeling, resizing, and rescaling | Augmentation of the raw images | Accuracy 99.69 |
[29] | Identification/classification of plant disease | detection of tomato plant diseases | PlantVillage dataset | LeNet VGGNet ResNet50 Xception | Keras with TensorFlow | N/A | Image rotation, patch extraction, and horizontal reflection | Accuracy VGGNet: 99.25% |
[30] | Identification/classification of plant disease | Detection of tomato plant diseases | PlantVillage dataset | Hybrid CNN (Hy CNN) | Keras | Resize to 224 × 224 × 3 | Rotation, flipping and image brightness | Accuracy 98.7% |
[31] | Identification/classification of plant disease | Detection of tomato plant diseases | PlantVillage dataset | Segmentation-based CNN | Developed by the author | resize to 256 × 256 | N/A | Accuracy 98.49 |
[32] | Identification/classification of plant disease | Detection of tomato plant diseases | PlantVillage dataset | CNN model | Developed by the author | resize to 256 × 256 | Rotating, flipping, and cropping | Accuracy 91.2% |
[33] | Identification/classification of plant disease | Detection of tomato plant diseases | PlantVillage dataset | MobileNet Resnet50 Xception Densenet121 Xception ShuffleNet | - | Resize to 224 × 224 × 4 | rotating, flipping, bluer, relight and cropping | Accuracy 97.10% |
[34] | Identification/classification of plant disease | Detection of tomato plant diseases | Tomato leaf diseases dataset in AI CHALLENGER | Restructured residual dense network | Developed by the author | N/A | N/A | Accuracy 95% |
[35] | Identification/classification of plant disease | Detection of tomato plant diseases | PlantVillage dataset | VGG19 AlexNet | - | Downsized to 225 × 225 | N/A | Accuracy 98.9% |
[37] | Crop identification/classification | Classification of crops (wheat, maize, sunflower, soybeans, and sugar beet) | 19 multi-temporal scenes acquired by Landsat-8 and Sentinel-1A RS satellites from a test site in Ukraine | CNN | Developed by the authors | Calibration, multi-looking, speckle filtering (3 × 3 window with Refined Lee algorithm), terrain correction, segmentation, restoration of missing data | N/A | Accuracy 94.60% |
[38] | Crop identification/classification | Classification to differentiate crops, soils, and weeds as well as individual weed species | The dataset used in this study was an independent image set with 16,500 image patches | ResNet-18 DCNN classifier | TensorFlow | N/A | Added, for each image, copies of the image that were rotated by 90,180 and 270 and, additionally, for each rotation angle, copies that were mirrored left to right | Accuracy 94% |
[39] | Crop identification/classification | Classification system of diverse plants in precision agriculture | (Public dataset). Plant Seedlings Dataset contains 4750 images corresponding to 12 species | InceptionV3, VGG16, and Xception | Keras | N/A | N/A | Accuracy 86.21% |
[40] | Crop identification/classification | Flower classification | (Public dataset). Kaggle flower dataset that contains 4323 images of flowers, with 224 × 224 input | CNN | TensorFlow Keras | N/A | N/A | Accuracy 91% |
[41] | Crop identification/classification | Predicting accurate paddy crop yield | (Public dataset). - Two sets of data collected combined into a single dataset - Annual yield of rice in India FY 1991–2020 | ANN | Developed by the authors | Cleaning, normalization and feature selection | N/A | RMSE 0.051 |
[42] | Crop identification/classification | Plant seedlings classification | (Public dataset). Plant Seedlings Dataset contains 4275 images of 12 species | CNN | Keras | Images were resized to 224 × 224 pixels Data | Flip, rotate, scale, flip scale, and histogram |
|
[43] | Crop identification/classification | Classification of summer crops | 19 images from ETM+ and 18 images from OLI | LSTM + Conv1D | Developed by the author | N/A | N/A | F1 score of 0.73 and accuracy of 85.54% |
[44] | Crop identification/classification | Prediction the necessary supplements and minerals that should be provided to the dirt | 140 pictures of wilting/wilted grass and normal grass captured by an Edge-smart camera ICAM700 | CNN | DeepRes Netetc, AlexNet, DenseNet, GoogleLeNet, CaffeNet, VGGNet | N/A | N/A | Accuracy 90% |
[45] | Crop identification/classification | Multi-temporal crop-type classification | Collected by authors | CNN-RF | Developed by the author | N/A | N/A | Accuracy 94.27% |
[46] | Crop identification/classification | Fruit quality classification | Collected by authors | R-CNN | - | N/A | N/A | Accuracy 97.86%. |
[47] | Crop identification/classification | Plant detection and density variation | Collected by authors | FRCNN | - | N/A | N/A | - |
[48] | Identification of weeds | Detecting sugar beet plants and weeds in the field based on image data | 1969 RGB+NIR images captured using a JAI camera in nadir view placed on a UAV | CNN | TensorFlow | Separated vegetation/background based on NDVI, binary mask to describe vegetation, blob segmentation, resized to 64 × 64 pix., normalized and centered | 64 even rotations |
|
[49] | Identification of weeds | Weed Classification from Natural Corn Field | Collected by authors | CNN | Tensorflow | Resized to 128 × 128 × 3 | N/A | Accuracy 97% |
[55] | Identification of weeds | Recognize weeds and identify their growth stages | (Public dataset). The dataset consists of 9649 images for various types of weeds, divided into nine classes | ResNet, MobileNet, Wide ResNet, DenseNet | Pytorch | Image resized to 128 × 128 | Augmented data by horizontal and vertical flipping, translation, and rotation | Accuracy 93.45% |
[6] | Identification of water | Identification of the water-stressed areas in the crop (maize) field | Collected dataset with 1340 RGB images using DJI Inspire-1 Pro UAV | CNN | Developed by the authors | Segmented images were resized to 1792 × 1792 and divided into an 8 × 8 grid to obtain 224 × 224 image patches of the canopy (leaves) | Added Gaussian noise, contrast, saturation, brightness, and random flips |
|
[50] | Identification of water | Monitoring of stress induced by water deficiency in plants | The authors created a new dataset of two chickpea varieties, JG-62 and Pusa-372, containing 7680 images | CNN-LSTM | TensorFlow and Keras | Gaussian noise | Horizontal flipping, rotation, shear, and translation |
|
[51] | Identification of water | Water spray detection | Created by authors and data acquired using UAV | R-CNN | TensorFlow | N/A | N/A | N/A |
[52] | Weather forecasting | Frost prediction in crops by estimating low temperatures | Data time series IoT infrastructure generates 144 rows per day | LSTM | Keras TensorFlow | NA | NA | RMSE 0.8068 |
[53] | Weather forecasting | The prediction of low temperatures | Real data obtained from an IoT system | LSTM | TensorFlow and Keras | Smoothing mechanism | N/A | R2 0.95 |
[54] | Fruit counting | Predict the number of tomatoes in the images | 24,000 synthetic images produced by the authors | Modified Inception-ResNet CNN | TensorFlow | Blurred synthetic images by a Gaussian filter | Generated synthetic 128 × 128 pix. images to train the network, colored circles to simulate background, and tomato plant/crops | Accuracy 91% |
5. Deep Learning Techniques in Agriculture
5.1. Area of Agriculture
5.2. Datasets Used in Papers
5.3. Deep Learning Model Used
5.4. Framework Used
5.5. Data Preprocessing
5.6. Data Augmentation
5.7. Performance Metrics Used in Results
6. Discussion
6.1. Advantages and Disadvantages of Deep Learning
6.2. Future of Deep Learning in Agriculture
7. Proposed System Architecture
7.1. The CNN Model
7.2. The SVM Classifier
7.3. The Residual Attention Network
8. Conclusions
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Liu, Q.; Yan, Q.; Tian, J.; Yuan, K. Key technologies and applications in intelligent agriculture. J. Phys. Conf. Ser. 2021, 1757, 012059. [Google Scholar] [CrossRef]
- Kitzes, J.; Wackernagel, M.; Loh, J.; Peller, A.; Goldfinger, S.; Cheng, D.; Tea, K. Shrink and share humanity’s present and future ecological footprint. Philos. Trans. the Roy. Soc. Lond. B Biol. Sci. 2008, 363, 467–475. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- FAO. How to Feed the World in 2050; Food and Agriculture Organization of the United Nations: Rome, Italy, 2009. [Google Scholar]
- Kamilaris, A.; Prenafeta-Boldú, F.X. Deep learning in agriculture: A survey. Comput. Electron. Agric. 2018, 147, 70–90. [Google Scholar] [CrossRef] [Green Version]
- Ren, C.; Dae-Kyoo, K.; Jeong, D. A survey of deep learning in agriculture: Techniques and their applications. J. Inf. Processing Syst. 2020, 16, 1015–1033. [Google Scholar]
- Kumar, A.; Shreeshan, S.; Tejasri, N.; Rajalakshmi, P.; Guo, W.; Naik, B.; Marathi, B.; Desai, U. Identification of water-stressed area in maize crop using UAV based remote sensing. In Proceedings of the 2020 IEEE India Geoscience and Remote Sensing Symposium (InGARSS), Ahmedabad, India, 1–4 December 2020. [Google Scholar]
- Dargan, S.; Kumar, M.; Ayyagari, M.R.; Kumar, G. A survey of deep learning and its applications: A new paradigm to machine learning. Arch. Comput. Methods Eng. 2020, 27, 1071–1092. [Google Scholar] [CrossRef]
- LeCun, Y.; Bengio, Y.; Hinton, G. Deep learning. Nature 2015, 521, 436–444. [Google Scholar] [CrossRef]
- Zhu, N.; Liu, X.; Liu, Z.; Hu, K.; Wang, Y.; Tan, J.; Guo, Y. Deep learning for smart agriculture: Concepts, tools, applications, and opportunities. Int. J. Agric. Biol. Eng. 2018, 11, 32–44. [Google Scholar] [CrossRef]
- Pouyanfar, S.; Sadiq, S.; Yan, Y.; Tian, H.; Tao, Y.; Reyes, M.P.; Shyu, M.-L.; Chen, S.C.; Iyengar, S.S. A survey on deep learning: Algorithms, techniques, and applications. ACM Comput. Surv. (CSUR) 2018, 51, 1–36. [Google Scholar] [CrossRef]
- Ajit, A.; Acharya, K.; Samanta, A. A review of convolutional neural networks. In Proceedings of the 2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE), Vellore, India, 24–25 February 2020. [Google Scholar]
- Zaremba, W.; Sutskever, I.; Vinyals, O. Recurrent neural network regularization. arXiv 2014, arXiv:1409.2329. [Google Scholar]
- Sak, H.; Senior, A.; Beaufays, F. Long short-term memory recurrent neural network architectures for large scale acoustic modeling. arXiv 2014, arXiv:1402.1128. [Google Scholar]
- Sharma, A.; Jain, A.; Gupta, P.; Chowdary, V. Machine learning applications for precision agriculture: A comprehensive review. IEEE Access 2020, 9, 4843–4873. [Google Scholar] [CrossRef]
- Saleem, M.H.; Potgieter, J.; Arif, K.M. Plant disease detection and classification by deep learning. Plants 2019, 8, 468. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Jihen, A.; Bouaziz, B.; Algergawy, A. A Deep Learning-Based Approach for Banana Leaf Diseases Classification. In Datenbanksysteme für Business, Technologie und Web (BTW 2017)-Workshopband; Gesellschaft für Informatik e.V.: Bonn, Germany, 2017. [Google Scholar]
- Dipali, M.; Deepa, D. Automation and integration of growth monitoring in plants (with disease prediction) and crop prediction. Mater. Today Proc. 2021, 43, 3922–3927. [Google Scholar]
- Akash, S.; Malik, A. A c for the classification of sunflower diseases using deep learning. In Proceedings of the 2021 2nd International Conference on Intelligent Engineering and Management (ICIEM), London, UK, 28–30 April 2021. [Google Scholar]
- Burhan, S.A.; Minhas, S.; Tariq, A.; Hassan, M.N. Comparative study of deep learning algorithms for disease and pest detection in rice crops. In Proceedings of the 2020 12th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Bucharest, Romania, 25–27 June 2020. [Google Scholar]
- Ahmed, A.A.; Reddy, G.H. A mobile-based system for detecting plant leaf diseases using deep learning. AgriEngineering 2021, 3, 478–493. [Google Scholar] [CrossRef]
- Pallagani, V.; Khandelwal, V.; Chandra, B.; Udutalapally, V.; Das, D.; Mohanty, S.P. DCrop: A deep-learning-based framework for accurate prediction of diseases of crops in smart agriculture. In Proceedings of the 2019 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS), Rourkela, India, 16–18 December 2019. [Google Scholar]
- Sladojevic, S.; Arsenovic, M.; Anderla, A.; Culibrk, D.; Stefanovic, D. Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification. Comput. Intell. Neurosci. 2016, 2016, 3289801. [Google Scholar] [CrossRef] [Green Version]
- Abdullahi, H.S.; Sheriff, R.; Mahieddine, F. Convolution neural network in precision agriculture for plant image recognition and classification. In Proceedings of the 2017 Seventh International Conference on Innovative Computing Technology (INTECH), Luton, UK, 16–18 August 2017; pp. 1–3. [Google Scholar] [CrossRef]
- Arivazhagan, S.; Shebiah, R.N.; Ananthi, S.; Varthini, S.V. Detection of unhealthy region of plant leaves and classification of plant leaf diseases using texture features. Agric. Eng. Int. CIGR J. 2013, 15, 211–217. [Google Scholar]
- Chowdhury, M.E.; Rahman, T.; Khandakar, A.; Ayari, M.A.; Khan, A.U.; Khan, M.S.; Al-Emadi, N.; Reaz, M.B.I.; Islam, M.T.; Ali, S.H.M. Automatic and reliable leaf disease detection using deep learning techniques. AgriEngineering 2021, 3, 294–312. [Google Scholar] [CrossRef]
- Khan, S.; Narvekar, M. Novel fusion of color balancing and superpixel based approach for detection of tomato plant diseases in natural complex environment. J. King Saud Univ. Comput. Inf. Sci. 2020. [Google Scholar] [CrossRef]
- Zhao, S.; Peng, Y.; Liu, J.; Wu, S. Tomato leaf disease diagnosis based on improved convolution neural network by attention module. Agriculture 2021, 11, 651. [Google Scholar] [CrossRef]
- Bhujel, A.; Kim, N.E.; Arulmozhi, E.; Basak, J.K.; Kim, H.T. A lightweight Attention-based convolutional neural networks for tomato leaf disease classification. Agriculture 2022, 12, 228. [Google Scholar] [CrossRef]
- Kumar, A.; Vani, M. Image based tomato leaf disease detection. In Proceedings of the 2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT), Kanpur, India, 30 December 2019; pp. 1–6. [Google Scholar]
- Kaur, P.; Harnal, S.; Tiwari, R.; Upadhyay, S.; Bhatia, S.; Mashat, A.; Alabdali, A.M. Recognition of Leaf Disease Using Hybrid Convolutional Neural Network by Applying Feature Reduction. Sensors 2022, 22, 575. [Google Scholar] [CrossRef] [PubMed]
- Trivedi, N.K.; Gautam, V.; Anand, A.; Aljahdali, H.M.; Villar, S.G.; Anand, D.; Goyal, N.; Kadry, S. Early Detection and Classification of Tomato Leaf Disease Using High-Performance Deep Neural Network. Sensors 2021, 21, 7987. [Google Scholar] [CrossRef] [PubMed]
- Agarwal, M.; Singh, A.; Arjaria, S.; Sinha, A.; Gupta, S. ToLeD: Tomato leaf disease detection using convolution neural network. Procedia Comput. Sci. 2020, 167, 293–301. [Google Scholar] [CrossRef]
- Hong, H.; Lin, J.; Huang, F. Tomato disease detection and classification by deep learning. In Proceedings of the 2020 International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), Fuzhou, China, 12–14 June 2020; pp. 25–29. [Google Scholar]
- Zhou, C.; Zhou, S.; Xing, J.; Song, J. Tomato leaf disease identification by restructured deep residual dense network. IEEE Access 2021, 9, 28822–28831. [Google Scholar] [CrossRef]
- Kibriya, H.; Abdullah, I.; Nasrullah, A. Plant Disease Identification and Classification Using Convolutional Neural Network and SVM. In Proceedings of the 2021 International Conference on Frontiers of Information Technology (FIT), Islamabad, Pakistan, 13–14 December 2021; pp. 264–268. [Google Scholar]
- Bhanumathi, S.; Vineeth, M.; Rohit, N. Crop yield prediction and efficient use of fertilizers. In Proceedings of the 2019 International Conference on Communication and Signal Processing (ICCSP), Chennai, India, 4–6 April 2019. [Google Scholar]
- Kussul, N.; Lavreniuk, M.; Skakun, S.; Shelestov, A. Deep learning classification of land cover and crop types using remote sensing data. IEEE Geosci. Remote Sens. Lett. 2017, 14, 778–782. [Google Scholar] [CrossRef]
- de Camargo, T.; Schirrmann, M.; Landwehr, N.; Dammer, K.H.; Pflanz, M. Optimized deep learning model as a basis for fast UAV mapping of weed species in winter wheat crops. Remote Sens. 2021, 13, 1704. [Google Scholar] [CrossRef]
- Diaz, C.A.M.; Castaneda, E.E.M.; Vassallo, C.A.M. Deep learning for plant classification in precision agriculture. In Proceedings of the 2019 International Conference on Computer, Control, Informatics and its Applications (IC3INA), Tangerang, Indonesia, 23–24 October 2019. [Google Scholar]
- Narvekar, C.; Rao, M. Flower classification using CNN and transfer learning in CNN-agriculture perspective. In Proceedings of the 2020 3rd International Conference on Intelligent Sustainable Systems (ICISS), Thoothukudi, India, 3–5 December 2020. [Google Scholar]
- Gopal, P.M.; Bhargavi, R. A novel approach for efficient crop yield prediction. Comput. Electron. Agric. 2019, 165, 104968. [Google Scholar] [CrossRef]
- Hassan, E.; Shams, M.; Hikal, N.A.; Elmougy, S. Plant seedlings classification using transfer learning. In Proceedings of the 2021 International Conference on Electronic Engineering (ICEEM), Menouf, Egypt, 3–4 July 2021. [Google Scholar]
- Zhong, L.; Hu, L.; Zhou, H. Deep learning based multi-temporal crop classification. Remote Sens. Environ. 2019, 221, 430–443. [Google Scholar] [CrossRef]
- Kanmani, R.; Muthulakshmi, S.; Subitcha, K.S.; Sriranjani, M.; Radhapoorani, R.; Suagnya, N. Modern Irrigation System using Convolutional Neural Network. In Proceedings of the 2021 7th International Conference on Advanced Computing and Communication Systems, ICACCS 2021, Coimbatore, India, 19–20 March 2021; pp. 592–597. [Google Scholar] [CrossRef]
- Yang, S.; Gu, L.; Li, X.; Jiang, T.; Ren, R. Crop classification method based on optimal feature selection and hybrid CNN-RF networks for multi-temporal remote sensing imagery. Remote Sens. 2020, 12, 3119. [Google Scholar] [CrossRef]
- Mohapatra, D.; Choudhury, B.; Sabat, B. An Automated System for Fruit Gradation and Aberration Localisation using Deep Learning. In Proceedings of the 2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS), Coimbatore, India, 19–20 March 2021. [Google Scholar]
- Mhango, J.K.; Harris, E.W.; Green, R.; Monaghan, J.M. Mapping potato plant density variation using aerial imagery and deep learning techniques for precision agriculture. Remote Sens. 2021, 13, 2705. [Google Scholar] [CrossRef]
- Milioto, A.; Lottes, P.; Stachniss, C. Real-time blob-wise sugar beets vs weeds classification for monitoring fields using convolutional neural networks. In Proceedings of the International Conference on Unmanned Aerial Vehicles in Geomatics, Bonn, Germany, 6–7 April 2017. [Google Scholar]
- Garibaldi-Márquez, F.; Flores, G.; Mercado-Ravell, D.A.; Ramírez-Pedraza, A.; Valentín-Coronado, L.M. Weed Classification from Natural Corn Field-Multi-Plant Images Based on Shallow and Deep Learning. Sensors 2022, 22, 3021. [Google Scholar] [CrossRef] [PubMed]
- Azimi, S.; Wadhawan, R.; Gandhi, T.K. Intelligent monitoring of stress induced by water deficiency in plants using deep learning. IEEE Trans. Instrum. Meas. 2021, 70, 5017113. [Google Scholar] [CrossRef]
- Albuquerque, C.K.; Polimante, S.; Torre-Neto, A.; Prati, R.C. Water spray detection for smart irrigation systems with Mask R-CNN and UAV footage. In Proceedings of the 2020 IEEE International Workshop on Metrology for Agriculture and Forestry (MetroAgriFor), Trento, Italy, 4–6 November 2020. [Google Scholar]
- Guillén, M.A.; Llanes, A.; Imbernón, B.; Martínez-España, R.; Bueno-Crespo, A.; Cano, J.C.; Cecilia, J.M. Performance evaluation of edge-computing platforms for the prediction of low temperatures in agriculture using deep learning. J. Supercomput. 2021, 77, 818–840. [Google Scholar] [CrossRef]
- Guillén-Navarro, M.A.; Martínez-España, R.; Llanes, A.; Bueno-Crespo, A.; Cecilia, J.M. A deep learning model to predict lower temperatures in agriculture. J. Ambient. Intell. Smart Environ. 2020, 12, 21–34. [Google Scholar] [CrossRef]
- Rahnemoonfar, M.; Sheppard, C. Deep count: Fruit counting based on deep simulated learning. Sensors 2017, 17, 905. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Vypirailenko, D.; Kiseleva, E.; Shadrin, D.; Pukalchik, M. Deep learning techniques for enhancement of weeds growth classification. In Proceedings of the 2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), Glasgow, UK, 17–20 May 2021. [Google Scholar]
- Hughes, D.P.; Salathé, M. An open access repository of images on plant health to enable the development of mobile disease diagnostics. arXiv 2015, arXiv:1511.08060. [Google Scholar]
- Zheng, X.; Wang, M.; Ordieres-Meré, J. Comparison of data preprocessing approaches for applying deep learning to human activity recognition in the context of industry 4.0. Sensors 2018, 18, 2146. [Google Scholar] [CrossRef] [Green Version]
No | Performance Metric | Description |
---|---|---|
1 | Accuracy | This is the % of correct classifications. |
2 | Precision | Precision is defined as the fraction of relevant examples (true positives) among all of the examples that were predicted to belong to a certain class. |
3 | F1 score | F-measure provides a single score that balances both the concerns of precision and recall in one number. |
4 | R^2 | The determination coefficient is a statistical measure representing the proportion of the variance for a dependent variable explained by an independent variable. |
5 | Root Mean Square Error (RMSE) | It is a standard deviation of the errors that occur when a prediction is made on a dataset. |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Altalak, M.; Ammad uddin, M.; Alajmi, A.; Rizg, A. Smart Agriculture Applications Using Deep Learning Technologies: A Survey. Appl. Sci. 2022, 12, 5919. https://doi.org/10.3390/app12125919
Altalak M, Ammad uddin M, Alajmi A, Rizg A. Smart Agriculture Applications Using Deep Learning Technologies: A Survey. Applied Sciences. 2022; 12(12):5919. https://doi.org/10.3390/app12125919
Chicago/Turabian StyleAltalak, Maha, Mohammad Ammad uddin, Amal Alajmi, and Alwaseemah Rizg. 2022. "Smart Agriculture Applications Using Deep Learning Technologies: A Survey" Applied Sciences 12, no. 12: 5919. https://doi.org/10.3390/app12125919