pith. sign in

arxiv: 2604.27764 · v1 · submitted 2026-04-30 · 💻 cs.CV

GourNet: A CNN-Based Model for Mango Leaf Disease Detection

Ekram Alam , Jaydip Sanyal , Akhil Kumar Das , Arijit Bhattacharya , Farhana Sultana This is my paper

Pith reviewed 2026-05-07 05:41 UTC · model grok-4.3

classification 💻 cs.CV
keywords GourNetCNNmango leaf diseaseimage classificationdeep learningMangoLeafBDplant disease detectionagriculture
0
0 comments X

The pith

GourNet, a compact CNN, identifies mango leaf diseases across eight classes with 97% accuracy using only 683,656 parameters.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents GourNet, a convolutional neural network built to detect diseases in mango leaves from images. It trains and tests the model on the MangoLeafBD dataset containing seven disease classes plus a healthy class. Images receive resizing, rescaling, and data augmentation before an 80/10/10 split for training, validation, and testing. The resulting network reaches 97% accuracy while remaining small at under 700,000 total parameters. Accurate early detection would allow targeted treatment that limits yield loss and supports sustained mango production.

Core claim

We introduce GourNet, a CNN-based model that identifies infections in mango leaves. We use the MangoLeafBD dataset with eight classes total. Images are preprocessed by resizing, rescaling, and data augmentation. The dataset is split 80% for training and 10% each for validation and testing. The model uses only 683,656 parameters and reaches 97% classification accuracy.

What carries the argument

GourNet is a lightweight convolutional neural network that applies successive convolutional and pooling layers to preprocessed leaf images before a final classification layer outputting one of eight disease or healthy labels.

If this is right

  • Farmers could apply targeted treatments early and reduce overall crop losses in mango orchards.
  • The low parameter count allows the model to run on smartphones or other portable devices for field use.
  • Data augmentation improves robustness so the same pipeline can handle varied real-world image quality.
  • High accuracy on eight distinct classes shows the architecture can separate multiple disease types at once.
  • The workflow supports precision agriculture by replacing broad chemical applications with image-guided decisions.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same lightweight CNN pattern could transfer to leaf-disease tasks on other fruit or vegetable crops once suitable datasets exist.
  • Embedding the model in a mobile app would let farmers scan leaves on-site without sending samples to labs.
  • If accuracy holds on external images, the system could lower dependence on expert pathologists for first-pass diagnosis.
  • This style of efficient network offers a practical route for deploying deep learning in resource-limited agricultural settings.

Load-bearing premise

The MangoLeafBD dataset and its 80/10/10 split capture the full range of lighting, angles, camera types, and field conditions that new mango leaf images will present.

What would settle it

Running GourNet on a fresh collection of mango leaf photos taken from different farms, seasons, or cameras and finding accuracy well below 97%.

Figures

Figures reproduced from arXiv: 2604.27764 by Akhil Kumar Das, Arijit Bhattacharya, Ekram Alam, Farhana Sultana, Jaydip Sanyal.

Figure 1
Figure 1. Figure 1: Structural Overview of a typical CNN Model view at source ↗
Figure 2
Figure 2. Figure 2: Sample images from the eight classes of the MBD dataset view at source ↗
Figure 3
Figure 3. Figure 3: Workflow of the proposed approach This section presents the structured methodology adopted for classifying MLDs. Our ap￾proach includes data collection, preprocessing, model construction, and disease classification, as depicted in view at source ↗
Figure 4
Figure 4. Figure 4: Layer-wise structure of the GourNet model with output shapes and number of pa view at source ↗
Figure 5
Figure 5. Figure 5: Training and validation accuracy and loss trends of the GourNet model view at source ↗
read the original abstract

Mango cultivation is crucial in the agricultural sector, significantly contributing to economic development and food security. However, diseases affecting mango leaves can significantly reduce both the production and overall fruit grade. Detecting leaf diseases at an early stage with precision is key to effective disease prevention and sustaining crop productivity. In this paper, we introduce a "deep learning" model named "GourNet", which leverages "Convolutional Neural Networks" to identify infections in mango leaves. We utilize the "MangoLeafBD" (MBD) dataset to train and assess the effectiveness of the presented model. The MBD dataset contains seven disease classes and a Healthy class, making a total of eight classes. To enhance model performance, the images are preprocessed through steps like resizing, rescaling, and data augmentation prior to training. To properly evaluate the model, the dataset is separated into 80% for training, with the remaining 20% equally split between validation and testing. Our model uses only 683,656 total parameters and achieves a classification accuracy of 97%. This research's source code can be found at: https://github.com/ekramalam/GourNet-Repo.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

4 major / 2 minor

Summary. The paper proposes GourNet, a lightweight CNN with 683,656 parameters for multi-class classification of mango leaf diseases on the MangoLeafBD dataset (8 classes: 7 diseases plus healthy). Images undergo resizing, rescaling, and augmentation before training on an 80/10/10 train/validation/test split, yielding a reported test accuracy of 97%. The source code is provided via GitHub.

Significance. If the performance claim holds under rigorous evaluation, the work offers a practical, low-parameter model for early mango leaf disease detection that could support deployment on edge devices in agricultural settings. The explicit parameter count and public code repository are strengths that facilitate reproducibility and potential extension to other crop disease tasks.

major comments (4)
  1. [Experimental Results] Experimental Results section: The central claim of 97% accuracy is presented without any baseline comparisons (e.g., standard CNNs such as ResNet-18, MobileNet, or prior MangoLeafBD results), preventing assessment of whether GourNet advances the state of the art or merely matches simpler models.
  2. [Results and Evaluation] Results and Evaluation: No confusion matrix, per-class precision/recall/F1 scores, or class-wise accuracy is reported. For an 8-class problem, overall accuracy alone is insufficient to rule out poor performance on minority disease classes or to confirm the metric is not inflated by class imbalance.
  3. [Methodology and Discussion] Methodology and Discussion: There is no analysis of overfitting risk (e.g., training vs. validation loss curves, early stopping details, or regularization beyond augmentation) despite the high reported accuracy on a fixed 80/10/10 split; this is load-bearing for trusting the 97% figure generalizes beyond the test set.
  4. [Introduction and Conclusion] Introduction and Conclusion: The paper does not discuss or test generalizability to real-world variations (different lighting, camera types, farm conditions, or seasonal changes), which directly challenges the assumption that MangoLeafBD performance will transfer to new images as stated in the weakest assumption.
minor comments (2)
  1. [Abstract] Abstract: The dataset split is described as '80% for training, with the remaining 20% equally split between validation and testing,' which is consistent but should be repeated with exact counts or percentages in the main text for clarity.
  2. [Model Architecture] The manuscript would benefit from a table summarizing the GourNet architecture layers, filter sizes, and parameter breakdown to substantiate the 683,656 total parameter claim.

Simulated Author's Rebuttal

4 responses · 0 unresolved

We thank the referee for the constructive and detailed feedback. The comments highlight important areas for strengthening the evaluation and discussion of our work. We have addressed each point below and will incorporate the suggested improvements in the revised manuscript.

read point-by-point responses

  1. Referee: Experimental Results section: The central claim of 97% accuracy is presented without any baseline comparisons (e.g., standard CNNs such as ResNet-18, MobileNet, or prior MangoLeafBD results), preventing assessment of whether GourNet advances the state of the art or merely matches simpler models.

    Authors: We agree that baseline comparisons are necessary to contextualize GourNet's performance. In the revised manuscript, we will add results from experiments with ResNet-18, MobileNetV2, and other standard CNNs trained on the same MangoLeafBD dataset and split. We will also reference prior published results on this dataset. These additions will show that GourNet achieves comparable accuracy while using substantially fewer parameters. revision: yes

  2. Referee: Results and Evaluation: No confusion matrix, per-class precision/recall/F1 scores, or class-wise accuracy is reported. For an 8-class problem, overall accuracy alone is insufficient to rule out poor performance on minority disease classes or to confirm the metric is not inflated by class imbalance.

    Authors: We concur that per-class metrics are essential for an 8-class problem. The revised Results and Evaluation section will include a confusion matrix, per-class precision, recall, and F1 scores, as well as class-wise accuracies. This will allow readers to verify performance on each disease class and confirm that the overall accuracy is not driven by any single class. revision: yes

  3. Referee: Methodology and Discussion: There is no analysis of overfitting risk (e.g., training vs. validation loss curves, early stopping details, or regularization beyond augmentation) despite the high reported accuracy on a fixed 80/10/10 split; this is load-bearing for trusting the 97% figure generalizes beyond the test set.

    Authors: We appreciate the emphasis on demonstrating generalization. Our training already employed early stopping on validation loss and data augmentation. In the revision, we will add the training and validation loss curves to the Methodology and Discussion sections, along with explicit details on the early stopping patience and any other regularization steps, to substantiate that overfitting was controlled. revision: yes

  4. Referee: Introduction and Conclusion: The paper does not discuss or test generalizability to real-world variations (different lighting, camera types, farm conditions, or seasonal changes), which directly challenges the assumption that MangoLeafBD performance will transfer to new images as stated in the weakest assumption.

    Authors: We acknowledge this as a genuine limitation of the current evaluation. While the MangoLeafBD dataset includes images under varied conditions, we will expand the Introduction and Conclusion to explicitly discuss real-world transfer challenges and list them as a limitation. We will also outline future work on more diverse field-collected data. Full empirical testing on new conditions is beyond the scope of this revision but will be noted as important next steps. revision: partial

Circularity Check

0 steps flagged

No significant circularity; purely empirical evaluation

full rationale

The paper describes a standard CNN architecture (GourNet) trained and evaluated on the fixed MangoLeafBD dataset using an 80/10/10 split, standard preprocessing, augmentation, and reported test accuracy of 97% with 683,656 parameters. No mathematical derivations, first-principles predictions, fitted parameters renamed as outputs, or self-citation chains appear in the abstract or described methodology. The central claim is a direct empirical result from training and testing on held-out data, with code provided for verification. This matches the default expectation of non-circular empirical ML work.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 0 invented entities

The central claim rests on standard supervised deep-learning assumptions and the representativeness of the MangoLeafBD dataset; no new physical entities are postulated and the only free parameters are the learned weights of the CNN itself.

free parameters (1)
  • GourNet architecture hyperparameters
    Number of layers, filter sizes, and other design choices that define the 683,656-parameter model are chosen by the authors and not derived from first principles.
axioms (1)
  • domain assumption Convolutional neural networks can extract discriminative features from leaf images for disease classification
    Invoked by the decision to use a CNN rather than another classifier; standard in computer vision but not proved in the paper.

pith-pipeline@v0.9.0 · 5518 in / 1339 out tokens · 28876 ms · 2026-05-07T05:41:21.692929+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

38 extracted references · 38 canonical work pages

  1. [1]

    https://nhb.gov.in/report files/mango/mango.htm

    MANGO — nhb.gov.in. https://nhb.gov.in/report files/mango/mango.htm. [Accessed 15- 8 06-2025]

    work page 2025

  2. [2]

    Mangoleafbd: A com- prehensive image dataset to classify diseased and healthy mango leaves.Data in Brief, 47:108941, 2023

    Sarder Iftekhar Ahmed, Muhammad Ibrahim, Md Nadim, Md Mizanur Rahman, Maria Mehjabin Shejunti, Taskeed Jabid, and Md Sawkat Ali. Mangoleafbd: A com- prehensive image dataset to classify diseased and healthy mango leaves.Data in Brief, 47:108941, 2023

    work page 2023

  3. [3]

    Leveraging deep learning for computer vision: A review

    Ekram Alam, Abu Sufian, Akhil Kumar Das, Arijit Bhattacharya, Md Firoj Ali, and MM Hafizur Rahman. Leveraging deep learning for computer vision: A review. In2021 22nd International Arab Conference on Information Technology (ACIT), pages 1–8. IEEE, 2021

    work page 2021

  4. [4]

    Gmdcsa-24: a dataset for human fall detection in videos.Data in Brief, 57:110892, 2024

    Ekram Alam, Abu Sufian, Paramartha Dutta, Marco Leo, and Ibrahim A Hameed. Gmdcsa-24: a dataset for human fall detection in videos.Data in Brief, 57:110892, 2024

    work page 2024

  5. [5]

    Mango disease detection using fused vision transformer with convnext architecture

    Faten S Alamri, Tariq Sadad, Ahmed S Almasoud, Raja Atif Aurangzeb, and Amjad Khan. Mango disease detection using fused vision transformer with convnext architecture. Computers, Materials & Continua, 83(1), 2025

    work page 2025

  6. [6]

    Impact of powdery mildew and sooty mold diseases on mango by natural fungicide.International Journal of Scientific Research Updates, 3(2):127–133, 2022

    Asmaa M Alkolaly, Rodina A Hassan, and Gehan A Monir. Impact of powdery mildew and sooty mold diseases on mango by natural fungicide.International Journal of Scientific Research Updates, 3(2):127–133, 2022

    work page 2022

  7. [7]

    Review of deep learning: concepts, cnn architectures, challenges, applications, future di- rections.Journal of big Data, 8:1–74, 2021

    Laith Alzubaidi, Jinglan Zhang, Amjad J Humaidi, Ayad Al-Dujaili, Ye Duan, Omran Al- Shamma, Jos´ e Santamar´ ıa, Mohammed A Fadhel, Muthana Al-Amidie, and Laith Farhan. Review of deep learning: concepts, cnn architectures, challenges, applications, future di- rections.Journal of big Data, 8:1–74, 2021

    work page 2021

  8. [8]

    Mango leaf diseases identification using convolutional neural network.International Journal of Pure and Applied Mathematics, 120(6):11067– 11079, 2018

    S Arivazhagan and S Vineth Ligi. Mango leaf diseases identification using convolutional neural network.International Journal of Pure and Applied Mathematics, 120(6):11067– 11079, 2018

    work page 2018

  9. [9]

    MIT press Cambridge, MA, USA, 2017

    Yoshua Bengio, Ian Goodfellow, Aaron Courville, et al.Deep learning, volume 1. MIT press Cambridge, MA, USA, 2017

    work page 2017

  10. [10]

    Cnn variants for computer vision: History, architecture, application, challenges and future scope.Electronics, 10(20):2470, 2021

    Dulari Bhatt, Chirag Patel, Hardik Talsania, Jigar Patel, Rasmika Vaghela, Sharnil Pandya, Kirit Modi, and Hemant Ghayvat. Cnn variants for computer vision: History, architecture, application, challenges and future scope.Electronics, 10(20):2470, 2021

    work page 2021

  11. [11]

    Mdcn: Mod- ified dense convolution network based disease classification in mango leaves

    Chirag Chandrashekar, KP Vijayakumar, K Pradeep, and A Balasundaram. Mdcn: Mod- ified dense convolution network based disease classification in mango leaves

    work page

  12. [12]

    A review on production and marketing of mango fruit.World Journal of Agriculture and Soil Science, 2(2):1–7, 2019

    Kayier Guien Chay, Amsale Workeneh, and Beshadu Shifera. A review on production and marketing of mango fruit.World Journal of Agriculture and Soil Science, 2(2):1–7, 2019

    work page 2019

  13. [13]

    Deep learning-based software engineering: progress, challenges, and opportunities.Science China Information Sciences, 68(1):1–88, 2025

    Xiangping Chen, Xing Hu, Yuan Huang, He Jiang, Weixing Ji, Yanjie Jiang, Yanyan Jiang, Bo Liu, Hui Liu, Xiaochen Li, et al. Deep learning-based software engineering: progress, challenges, and opportunities.Science China Information Sciences, 68(1):1–88, 2025

    work page 2025

  14. [14]

    The cnn paradigm.IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications, 40(3):147–156, 1993

    Leon O Chua and Tamas Roska. The cnn paradigm.IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications, 40(3):147–156, 1993

    work page 1993

  15. [15]

    A systematic analysis of various techniques for mango leaf disease detection

    Rinku Garg, Amanpreet Kaur Sandhu, and Bobbinpreet Kaur. A systematic analysis of various techniques for mango leaf disease detection. In2023 International Conference on Disruptive Technologies (ICDT), pages 349–354. IEEE, 2023. 9

    work page 2023

  16. [16]

    Enhancing disease management in mango cultivation: A machine learning approach to classifying leaf diseases.Indonesian Journal of Data and Science, 4(3):160–168, 2023

    Gst Ayu Vida Mastrika Giri, Izmy Alwiah Musdar, Husni Angriani, and Medi Taruk. Enhancing disease management in mango cultivation: A machine learning approach to classifying leaf diseases.Indonesian Journal of Data and Science, 4(3):160–168, 2023

    work page 2023

  17. [17]

    S Gowrishankar. Convnext-based mango leaf disease detection: Differentiating pathogens and pests for improved accuracy.International Journal of Advanced Computer Science and Applications, 14(6), 2023

    work page 2023

  18. [18]

    Deep learning for image based mango leaf disease detection.International Journal of Recent Technology and Engineering, 8(3S3):54–56, 2019

    Sampada Gulavnai and Rajashri Patil. Deep learning for image based mango leaf disease detection.International Journal of Recent Technology and Engineering, 8(3S3):54–56, 2019

    work page 2019

  19. [19]

    A survey on vision transformer.IEEE transactions on pattern analysis and machine intelligence, 45(1):87–110, 2022

    Kai Han, Yunhe Wang, Hanting Chen, Xinghao Chen, Jianyuan Guo, Zhenhua Liu, Yehui Tang, An Xiao, Chunjing Xu, Yixing Xu, et al. A survey on vision transformer.IEEE transactions on pattern analysis and machine intelligence, 45(1):87–110, 2022

    work page 2022

  20. [20]

    Speeding up efficientnet: Selecting update blocks of convolutional neural networks using genetic algorithm in transfer learning.arXiv preprint arXiv:2303.00261, 2023

    Md Mehedi Hasana, Muhammad Ibrahim, and Md Sawkat Ali. Speeding up efficientnet: Selecting update blocks of convolutional neural networks using genetic algorithm in transfer learning.arXiv preprint arXiv:2303.00261, 2023

    work page arXiv 2023

  21. [21]

    Deep learning for mango leaf disease identification: A vision transformer perspective.He- liyon, 10(17), 2024

    Md Arban Hossain, Saadman Sakib, Hasan Muhammad Abdullah, and Shifat E Arman. Deep learning for mango leaf disease identification: A vision transformer perspective.He- liyon, 10(17), 2024

    work page 2024

  22. [22]

    A dilated cnn model for image classi- fication.IEEE Access, 7:124087–124095, 2019

    Xinyu Lei, Hongguang Pan, and Xiangdong Huang. A dilated cnn model for image classi- fication.IEEE Access, 7:124087–124095, 2019

    work page 2019

  23. [23]

    Detect bangladeshi mango leaf diseases using lightweight convolutional neural network

    Nosin Ibna Mahbub, Feroza Naznin, Md Imran Hasan, Syed Mahfuzur Rahman Shifat, Md Alamgir Hossain, and Md Zahidul Islam. Detect bangladeshi mango leaf diseases using lightweight convolutional neural network. In2023 International Conference on Electrical, Computer and Communication Engineering (ECCE), pages 1–6. IEEE, 2023

    work page 2023

  24. [24]

    Light-weight deep learning model for accelerating the classification of mango- leaf disease.Emerging Science Journal, 8(1):28–42, 2024

    Bahar Uddin Mahmud, Abdullah Al Mamun, Md Jakir Hossen, Guan Yue Hong, and Busrat Jahan. Light-weight deep learning model for accelerating the classification of mango- leaf disease.Emerging Science Journal, 8(1):28–42, 2024

    work page 2024

  25. [25]

    Mango leaf disease detection and classification using spatial attention enabled ensemble classification

    V Pandiyaraju, Shravan Venkatraman, A Abeshek, SA Aravintakshan, et al. Mango leaf disease detection and classification using spatial attention enabled ensemble classification. In2024 International Conference on Advances in Data Engineering and Intelligent Com- puting Systems (ADICS), pages 1–8. IEEE, 2024

    work page 2024

  26. [26]

    A deep learning based approach for detecting mango leaf diseases

    Astik Kumar Pradhan, Jitendra Kumar Rout, Debanjan Ghosh, and Shailendra Kumar Sinha. A deep learning based approach for detecting mango leaf diseases. In2024 6th International Conference on Computational Intelligence and Networks (CINE), pages 1–6. IEEE, 2024

    work page 2024

  27. [27]

    Mobilenetv3 for mango leaf disease detection: An efficient deep learning approach for precision agriculture

    Sukruth S Puranik, Siddharth R Hanamakkanavar, Anupama P Bidargaddi, Vighnesh V Ballur, Pratham T Joshi, Meena SM, and Uday Kulkarni. Mobilenetv3 for mango leaf disease detection: An efficient deep learning approach for precision agriculture. In2024 5th International Conference for Emerging Technology (INCET), pages 1–7. IEEE, 2024

    work page 2024

  28. [28]

    A novel neural network-based federated learning system for imbalanced and non-iid data.arXiv e-prints, pages arXiv– 2311, 2023

    Mahfuzur Rahman Chowdhury and Muhammad Ibrahim. A novel neural network-based federated learning system for imbalanced and non-iid data.arXiv e-prints, pages arXiv– 2311, 2023. 10

    work page 2023

  29. [29]

    Enhancing mango leaf disease classification: Vit, bit, and cnn-based models evaluated on cyclegan-augmented data

    Syed Taha Yeasin Ramadan, Tanjim Sakib, Md Ahsan Rahat, Shakil Mosharrof, Fatin Ishrak Rakin, and Raiyan Jahangir. Enhancing mango leaf disease classification: Vit, bit, and cnn-based models evaluated on cyclegan-augmented data. In2023 26th Inter- national Conference on Computer and Information Technology (ICCIT), pages 1–6. IEEE, 2023

    work page 2023

  30. [30]

    Fractional ordering of ac- tivation functions for neural networks: A case study on texas wind turbine.Engineering Applications of Artificial Intelligence, 127:107308, 2024

    Bhukya Ramadevi, Venkata Ramana Kasi, and Kishore Bingi. Fractional ordering of ac- tivation functions for neural networks: A case study on texas wind turbine.Engineering Applications of Artificial Intelligence, 127:107308, 2024

    work page 2024

  31. [31]

    A vision transformer-based approach for recognizing seven prevalent mango leaf diseases

    Md Eshmam Rayed, Nazia Alfaz, Sadia Islam Niha, SM Sajibul Islam, et al. A vision transformer-based approach for recognizing seven prevalent mango leaf diseases. In2023 26th International Conference on Computer and Information Technology (ICCIT), pages 1–6. IEEE, 2023

    work page 2023

  32. [32]

    Leafnet: A proficient convolutional neural network for detecting seven prominent mango leaf diseases.Journal of Agriculture and Food Research, 14:100787, 2023

    Redwan Ahmed Rizvee, Tasnim Hossain Orpa, Adil Ahnaf, Md Ahsan Kabir, Mohammad Rifat Ahmmad Rashid, Mohammad Manzurul Islam, Maheen Islam, Taskeed Jabid, and Md Sawkat Ali. Leafnet: A proficient convolutional neural network for detecting seven prominent mango leaf diseases.Journal of Agriculture and Food Research, 14:100787, 2023

    work page 2023

  33. [33]

    Enhancing mango disease diagnosis through eco-informatics: A deep learning approach.Ecological Informatics, 77:102216, 2023

    Abdullah Ali Salamai. Enhancing mango disease diagnosis through eco-informatics: A deep learning approach.Ecological Informatics, 77:102216, 2023

    work page 2023

  34. [34]

    Plant leaf disease detection and classifi- cation based on cnn with lvq algorithm

    Melike Sardogan, Adem Tuncer, and Yunus Ozen. Plant leaf disease detection and classifi- cation based on cnn with lvq algorithm. In2018 3rd international conference on computer science and engineering (UBMK), pages 382–385. IEEE, 2018

    work page 2018

  35. [35]

    Mango disease classification-shallow cnn or residual cnn?-which is better?

    Dhruv Soni and Janyl Jumadinoda. Mango disease classification-shallow cnn or residual cnn?-which is better?

    work page

  36. [36]

    Deep learning in computer vision through mobile edge computing for iot.Mobile Edge Computing, pages 443–471, 2021

    Abu Sufian, Ekram Alam, Anirudha Ghosh, Farhana Sultana, Debashis De, and Mianxiong Dong. Deep learning in computer vision through mobile edge computing for iot.Mobile Edge Computing, pages 443–471, 2021

    work page 2021

  37. [37]

    Abhishek Upadhyay, Narendra Singh Chandel, Krishna Pratap Singh, Subir Kumar Chakraborty, Balaji M Nandede, Mohit Kumar, A Subeesh, Konga Upendar, Ali Salem, and Ahmed Elbeltagi. Deep learning and computer vision in plant disease detection: a comprehensive review of techniques, models, and trends in precision agriculture.Artificial Intelligence Review, 58...

    work page 2025

  38. [38]

    Artificial intelligence in surgery.Nature medicine, 30(5):1257–1268, 2024

    Chris Varghese, Ewen M Harrison, Greg O’Grady, and Eric J Topol. Artificial intelligence in surgery.Nature medicine, 30(5):1257–1268, 2024. 11

    work page 2024