pith. sign in

arxiv: 1907.07772 · v1 · pith:YNJLVVCWnew · submitted 2019-07-15 · 💻 cs.CY · cs.LG· stat.ML

Modern CNNs for IoT Based Farms

Patrick Kinyua Gikunda This is my paper

Pith reviewed 2026-05-24 21:04 UTC · model grok-4.3

classification 💻 cs.CY cs.LGstat.ML
keywords convolutional neural networksinternet of thingsagriculturedeep learningtaxonomyreviewprecision agriculturefarm automation
0
0 comments X

The pith

A review of modern CNN architectures proposes a taxonomy to guide their selection and optimization for IoT-based farm applications.

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

The paper reviews the basics of convolutional neural networks along with recent state-of-the-art architectures and the factors that affect their computational demands. It introduces a classification system organized around agricultural needs and then surveys how these networks have been applied to tasks in crop production, livestock, and related systems. The work positions the taxonomy and analysis as practical aids that let farm users pick suitable models and let tool builders identify where performance gains remain possible.

Core claim

The paper presents an initial understanding of CNNs, surveys recent architectures and their complexities, proposes a classification taxonomy tailored for agricultural application of CNN, and delivers a comprehensive review of research on state-of-the-art CNNs in agricultural production systems, thereby supplying benchmarking findings for end users and complexity analysis for developers seeking further optimizations.

What carries the argument

A classification taxonomy tailored for agricultural application of CNN that organizes architectures by their use in farm tasks and highlights performance trade-offs.

If this is right

  • End users of agricultural deep learning tools receive a guide for selecting appropriate CNN architectures based on the benchmarking findings.
  • Agricultural software developers gain an explanation of state-of-the-art CNN complexities that can inform design choices.
  • The analysis identifies possible future directions for optimizing the running performance of deep learning tools on farms.
  • The taxonomy supplies a structured way to map new CNN developments to specific agricultural production systems.

Where Pith is reading between the lines

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

  • Users could extend the taxonomy by adding performance metrics measured directly on IoT hardware typical of field deployments.
  • The review's focus on existing literature leaves open whether architectures optimized for general image tasks transfer equally well to the noisy, variable conditions of real farms.
  • Developers might combine the taxonomy with hardware-specific profiling to rank models by both accuracy and energy use on edge devices.

Load-bearing premise

The authors' selection of literature and the proposed taxonomy supply reliable guidance for choosing architectures without the paper itself running experiments or quantitative comparisons across the reviewed models.

What would settle it

A side-by-side test of several reviewed CNN architectures on the same set of farm images or sensor data that produces selection rankings different from those implied by the taxonomy.

Figures

Figures reproduced from arXiv: 1907.07772 by Patrick Kinyua Gikunda.

Figure 1
Figure 1. Figure 1: Top-1 Accuracy vs the computational cost. The size of the circles is propor￾taional to number of parameters. Legend;the grey cirles at the botton right represents number of parameters in millions. [32] LeNet-5 is a 7-layer pioneer convolutional network by LeCun et al. [34] to classify digits, used to recognise hand-written numbers digitized in 32x32 pixel greyscale input images. High resolution images requ… view at source ↗
Figure 2
Figure 2. Figure 2: Proposed classification taxonomy for CNN use in smart farm recognition, land cover classification, fruit counting and identification of weeds. It consist of 5 columns to show: the problem description, size of data used, accu￾racy according to the metrics used, the state-of-the-art CNN used and reference literature. In their paper, Amara et al. [54] use the LeNet architecture to classify the banana leaves d… view at source ↗
read the original abstract

Recent introduction of ICT in agriculture has brought a number of changes in the way farming is done. This means use of Internet of Things(IoT), Cloud Computing(CC), Big Data (BD) and automation to gain better control over the process of farming. As the use of these technologies in farms has grown exponentially with massive data production, there is need to develop and use state-of-the-art tools in order to gain more insight from the data within reasonable time. In this paper, we present an initial understanding of Convolutional Neural Network (CNN), the recent architectures of state-of-the-art CNN and their underlying complexities. Then we propose a classification taxonomy tailored for agricultural application of CNN. Finally, we present a comprehensive review of research dedicated to applications of state-of-the-art CNNs in agricultural production systems. Our contribution is in two-fold. First, for end users of agricultural deep learning tools, our benchmarking finding can serve as a guide to selecting appropriate architecture to use. Second, for agricultural software developers of deep learning tools, our in-depth analysis explains the state-of-the-art CNN complexities and points out possible future directions to further optimize the running performance.

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

2 major / 1 minor

Summary. The paper presents an overview of CNNs and recent state-of-the-art architectures with their complexities, proposes a classification taxonomy tailored to agricultural applications, and reviews existing research on CNN use in agricultural production systems. It claims a two-fold contribution: benchmarking findings to guide end users in selecting architectures for agricultural deep learning tools, and an in-depth analysis of complexities with future optimization directions for developers.

Significance. If the literature synthesis is comprehensive and the taxonomy well-motivated, the review could help practitioners navigate CNN choices in IoT-based farming contexts. However, the central claim of delivering actionable 'benchmarking findings' as a selection guide lacks support from any original quantitative comparisons or unified metrics across architectures on relevant datasets, limiting the significance to that of a standard survey rather than a validated benchmarking resource.

major comments (2)
  1. [Abstract] Abstract: The claim that 'our benchmarking finding can serve as a guide to selecting appropriate architecture' is load-bearing for the first contribution but is unsupported; the described paper structure is a literature review with no mention of author-conducted experiments, head-to-head performance tables, or quantitative synthesis of metrics (e.g., accuracy, latency, parameter count) on agricultural/IoT datasets.
  2. [Abstract] Abstract (contribution paragraph): The second contribution asserts that the 'in-depth analysis explains the state-of-the-art CNN complexities and points out possible future directions'; without a dedicated section providing new comparative analysis or falsifiable optimization predictions beyond citing prior work, this reduces to restating existing literature.
minor comments (1)
  1. [Abstract] Abstract: 'two-fold' should be written as 'twofold' for standard academic style.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our survey manuscript. The comments highlight opportunities to better align the abstract wording with the paper's scope as a literature review and taxonomy proposal. We respond to each major comment below.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The claim that 'our benchmarking finding can serve as a guide to selecting appropriate architecture' is load-bearing for the first contribution but is unsupported; the described paper structure is a literature review with no mention of author-conducted experiments, head-to-head performance tables, or quantitative synthesis of metrics (e.g., accuracy, latency, parameter count) on agricultural/IoT datasets.

    Authors: We agree that the phrasing 'benchmarking finding' is imprecise and could be read as implying original experiments or unified head-to-head evaluations, which the manuscript does not contain. The guidance offered is instead a synthesis of performance metrics (accuracy, model size, inference time) as reported in the reviewed agricultural studies. We will revise the abstract and contribution statement to replace 'benchmarking finding' with 'synthesis of reported performance metrics across the literature' and will add an explicit description of this synthesis approach in the introduction. revision: yes

  2. Referee: [Abstract] Abstract (contribution paragraph): The second contribution asserts that the 'in-depth analysis explains the state-of-the-art CNN complexities and points out possible future directions'; without a dedicated section providing new comparative analysis or falsifiable optimization predictions beyond citing prior work, this reduces to restating existing literature.

    Authors: The in-depth analysis and future directions are presented through the proposed agricultural-specific taxonomy and the structured review of complexities drawn from the cited works. While we do not introduce new experimental predictions, the taxonomy itself constitutes an original organizing framework that highlights domain-specific trade-offs not previously synthesized for this application area. We will revise the abstract to emphasize that the analysis and directions are synthesized via the taxonomy and literature review rather than new comparative experiments. revision: yes

Circularity Check

0 steps flagged

No circularity: review synthesis rests on external citations

full rationale

The paper is a literature review that introduces CNN concepts, proposes a taxonomy for agricultural use, and surveys existing applications. Its two-fold contribution frames 'benchmarking findings' explicitly as guidance drawn from reviewed external works rather than any internal derivation, fitted parameter, or self-referential reduction. No equations, predictions, or uniqueness claims appear that reduce to the paper's own inputs by construction. Self-citations, if present, are not load-bearing for the central claims, satisfying the criteria for a self-contained review against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The paper's claims rest on the authors' curation and interpretation of prior CNN and agriculture literature. No free parameters, axioms, or invented entities are introduced in the abstract.

pith-pipeline@v0.9.0 · 5728 in / 1085 out tokens · 25138 ms · 2026-05-24T21:04:28.309294+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

61 extracted references · 61 canonical work pages · 7 internal anchors

  1. [1]

    Empirical Evaluation of Rectified Activations in Convolutional Network

    Xu, B., Wang, N., Chen, T., Li, M. Empirical Evaluation of Rectified Activations in Convolutional Network. CoRR, abs/1505.00853 (2015)

    work page internal anchor Pith review Pith/arXiv arXiv 2015

  2. [2]

    Research on Quantum Neural Network and its Applications Based on Tanh Activation Function

    Luo, P., Li, H. Research on Quantum Neural Network and its Applications Based on Tanh Activation Function. Comput. Digit. Eng, 16, 3339 (2016)

    work page 2016

  3. [3]

    Sladojevic, S., Arsenovic, M., Anderla, A., Culibrk, D., Stefanovic, D. (2016). Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification. Comp. Int. and Neuroscience (2016)

    work page 2016

  4. [4]

    Food security: the challenge of feeding 9 billion people

    Godfray, H.C., Beddington, J.R., Crute, I.R., Haddad, L., Lawrence, D., Muir, J.F., Pretty, J.N., Robinson, S., Thomas, S.M., Toulmin, C. Food security: the challenge of feeding 9 billion people. Science, 327 5967, 812-8 (2010)

    work page 2010

  5. [5]

    The coming acceleration of global pop- ulation ageing

    Lutz, W.L., Sanderson, W.C., Scherbov, S. The coming acceleration of global pop- ulation ageing. Nature, 451, 716-719 (2008). 10 Gikunda and Jouandeau

    work page 2008

  6. [6]

    Bruinsma, J. (Ed.). World Agriculture: Towards 2015/2030. An FAO Perspective. Earthscan, London (2003)

    work page 2015

  7. [7]

    Using Deep Learning for Image-Based Plant Disease Detection

    Mohanty, S.P., Hughes, D.P., Salath, M. Using Deep Learning for Image-Based Plant Disease Detection. Front. Plant Science (2016)

    work page 2016

  8. [8]

    Precision agriculture and food security

    Gebbers, R., Adamchuk, V.I. Precision agriculture and food security. Science, 327 5967, 828-31 (2010)

    work page 2010

  9. [9]

    SmartFarm : Improving Agriculture Sustainability Using Modern Information Technology (2016)

    Krintz, C., Wolski, R., Golubovic, N., Lampel, B., Kulkarni, V., Sethura- masamyraja, B.B., Roberts, B. SmartFarm : Improving Agriculture Sustainability Using Modern Information Technology (2016)

    work page 2016

  10. [10]

    A review of the use of convolu- tional neural networks in agriculture

    Kamilaris, Andreas Prenafeta Bold, Francesc. A review of the use of convolu- tional neural networks in agriculture. The Journal of Agricultural Science. 1-11. 10.1017/S0021859618000436 (2018)

    work page doi:10.1017/s0021859618000436 2018

  11. [11]

    Weber R. H. Weber R. Internet of Things: Legal perspectives. Berlin: Springer- Verlag Berlin Heidelberg. 10.1007/978-3-642-11710-7 (2010)

    work page doi:10.1007/978-3-642-11710-7 2010

  12. [12]

    Anindya Sunday, Remote Sensing in Agriculture, International Journal of Envi- ronment, Agriculture and Biotechnology (IJEAB), Vol-1, Issue-3 (2016)

    work page 2016

  13. [13]

    Jinbo, C., Xiangliang, C., Han-Chi, F. et al. Cluster Computing.https://doi.org/ 10.1007/s10586-018-2022-5

    work page doi:10.1007/s10586-018-2022-5 2022

  14. [14]

    Big data for re- mote sensing: challenges and opportunities

    Chi M, Plaza A, Benediktsson JA, Sun Z, Shen J and Zhu Y. Big data for re- mote sensing: challenges and opportunities. Proceedings of the IEEE 104, 22072219 (2016)

    work page 2016

  15. [15]

    Environmental conditions big data management and cloud computing analytics for sustainable agriculture

    Waga D and Rabah K. Environmental conditions big data management and cloud computing analytics for sustainable agriculture. World Journal of Computer Ap- plication and Technology 2,7381 (2017)

    work page 2017

  16. [16]

    Big Data: A Survey

    Chen, M., Mao, S., Liu, Y. Big Data: A Survey. MONET, 19, 171-209 (2014)

    work page 2014

  17. [17]

    ImageNet Large Scale Visual Recognition Challenge

    Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M.S., Berg, A.C., Fei-Fei, L. ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision, 115, 211-252 (2015)

    work page 2015

  18. [18]

    Liang, M., Hu, X. (2015). Recurrent convolutional neural network for object recog- nition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3367-3375 (2015)

    work page 2015

  19. [19]

    Aspect extraction for opinion mining with a deep convolutional neural network

    Poria, S., Cambria, E., Gelbukh, A.F. Aspect extraction for opinion mining with a deep convolutional neural network. Knowledge-Based System., 108, 42-49 (2016)

    work page 2016

  20. [20]

    Deep Learning

    Goodfellow, I.J., Bengio, Y., Courville, A.C. Deep Learning. Nature, 521, 436-444, (2015)

    work page 2015

  21. [21]

    Applications of Convolu- tional Neural Networks, (2016)

    Bhandare, A., Bhide, M., Gokhale, P., Chandavarkar, R. Applications of Convolu- tional Neural Networks, (2016)

    work page 2016

  22. [22]

    Deep learning in neural networks: an overview

    Schmidhuber J. Deep learning in neural networks: an overview. Neural Networks 61,85117 (2015)

    work page 2015

  23. [23]

    http://image-net.org/challenges/LSVRC/2017, last accessed 2018/09/02

    work page 2017

  24. [24]

    http://image-net.org/challenges/LSVRC/2012/, last accessed 2018/09/02

    work page 2012

  25. [25]

    http://image-net.org/challenges/LSVRC/2013/, last accessed 2018/09/02

    work page 2013

  26. [26]

    ImageNet, http://image-net.org, last accessed 2018/10/21

    work page 2018

  27. [27]

    The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches

    Zahangir M.A, Tarek M. Taha1, Chris Yakopcic, Stefan Westberg, Paheding Sidike, Mst Shamima Nasrin, Brian C Van Essen, Abdul A S. Awwal, and Vijayan K. Asari. The History Began from AlexNet: A Comprehensive Survey on Deep Learn- ing Approaches.https://arxiv.org/pdf/1803.01164

    work page internal anchor Pith review Pith/arXiv arXiv

  28. [28]

    Prenafeta-Boldu

    Kamilaris, Andreas and Francesc X. Prenafeta-Boldu. Deep learning in agriculture: A survey. Computers and Electronics in Agriculture 147: 70-90 (2018). Modern CNNs for IoT Based Farms 11

    work page 2018

  29. [29]

    Automatic Identification of Center Pivot Irrigation Systems from Landsat Images Using Convolutional Neural Net- works

    Zhang, C., Yue, P., Liping, D., Zhaoyan, W,. Automatic Identification of Center Pivot Irrigation Systems from Landsat Images Using Convolutional Neural Net- works. Agriculture (2018)

    work page 2018

  30. [30]

    Computers and Electronics in Agriculture

    Chebet, E., Yujian, l., Njuki, S., Yingchun, L., A comparative study of fine-tuning deep learning models for plant disease identification. Computers and Electronics in Agriculture. https://doi.org/10.1016/j.compag.2018.03.032

    work page doi:10.1016/j.compag.2018.03.032 2018

  31. [31]

    Hyperdrive: A Systolically Scalable Binary-Weight CNN Inference Engine for mW IoT End-Nodes

    Andri, R., Cavigelli, L., Rossi, D., Benini, L. Hyperdrive: A Systolically Scalable Binary-Weight CNN Inference Engine for mW IoT End-Nodes. 2018 IEEE Com- puter Society Annual Symposium on VLSI (ISVLSI), 509-515 (2018)

    work page 2018

  32. [32]

    An Analysis of Deep Neural Network Models for Practical Applications

    Canziani, A., Paszke, A., Culurciello, E. An Analysis of Deep Neural Network Models for Practical Applications. CoRR, abs/1605.07678 (2016)

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  33. [33]

    Towards Principled Design of Deep Convolutional Networks: Introducing SimpNet

    HasanPour, S.H., Rouhani, M., Fayyaz, M., Sabokrou, M., Adeli, E. Towards Principled Design of Deep Convolutional Networks: Introducing SimpNet. CoRR, abs/1802.06205 (2018)

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  34. [34]

    Gradient-Based Learning Applied to Document Recognition

    LeCun, Y., Bottou, L., Bengio, Y. Gradient-Based Learning Applied to Document Recognition. Proceedings of the IEEE, 86(11):22782324 (1998)

    work page 1998

  35. [35]

    ImageNet Classification with Deep Con- volutional Neural Networks

    Krizhevsky, A., Sutskever, I., Hinton, G.E. ImageNet Classification with Deep Con- volutional Neural Networks. Commun. ACM, 60, 84-90. (2012)

    work page 2012

  36. [36]

    Network In Network

    Lin, M., Chen, Q., Yan, S. Network In Network. CoRR, abs/1312.4400 (2013)

    work page internal anchor Pith review Pith/arXiv arXiv 2013

  37. [37]

    ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation

    Paszke, A., Chaurasia, A., Kim, S., Culurciello, E. ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation. CoRR, abs/1606.02147 (2016)

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  38. [38]

    Visualizing and understanding convolutional networks

    Zeiler, M.D., Fergus, R. Visualizing and understanding convolutional networks. In European conference on computer vision, pages 818833. Springer (2014)

    work page 2014

  39. [39]

    Going deeper with convolutions

    Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S.E., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A. Going deeper with convolutions. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1-9 (2015)

    work page 2015

  40. [40]

    Very Deep Convolutional Networks for Large-Scale Image Recognition

    Simonyan, K., Zisserman, A. Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR, abs/1409.1556 (2014)

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  41. [41]

    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z. (2016). Rethinking the Inception Architecture for Computer Vision. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2818-2826 (2016)

    work page 2016

  42. [42]

    Deep Residual Learning for Image Recognition

    He, K., Zhang, X., Ren, S., Sun, J. Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770-778 (2015)

    work page 2016

  43. [43]

    Densely Connected Convolu- tional Networks

    Huang, G., Liu, Z., Maaten, L.V., Weinberger, K.Q. Densely Connected Convolu- tional Networks. 2017 IEEE Conference on Computer Vision and Pattern Recog- nition (CVPR), 2261-2269 (2017)

    work page 2017

  44. [44]

    Inception-v4, Inception-ResNet and the Im- pact of Residual Connections on Learning

    Szegedy, C., Ioffe, S., Vanhoucke, V. Inception-v4, Inception-ResNet and the Im- pact of Residual Connections on Learning. AAAI (2017)

    work page 2017

  45. [45]

    Identity Mappings in Deep Residual Networks

    He, K., Zhang, X., Ren, S., Sun, J. Identity Mappings in Deep Residual Networks. ECCV (2016)

    work page 2016

  46. [46]

    Deep fruit detection in orchards

    Bargoti, S., Underwood, J.P. Deep fruit detection in orchards. 2017 IEEE Interna- tional Conference on Robotics and Automation (ICRA), 3626-3633 (2017)

    work page 2017

  47. [47]

    DeepFruits: A Fruit Detection System Using Deep Neural Networks

    Sa, I., Ge, Z., Dayoub, F., Upcroft, B., Perez, T., McCool, C. DeepFruits: A Fruit Detection System Using Deep Neural Networks. Sensors (2016)

    work page 2016

  48. [48]

    Deep-plant: Plant identification with convolutional neural networks

    Lee, S.H., Chan, C.S., Wilkin, P., Remagnino, P. Deep-plant: Plant identification with convolutional neural networks. 2015 IEEE International Conference on Image Processing (ICIP), 452-456 (2015)

    work page 2015

  49. [49]

    Fine-tuning Deep Convolutional Net- works for Plant Recognition CLEF (2015)

    Reyes, A.K., Caicedo, J.C., Camargo, J.E. Fine-tuning Deep Convolutional Net- works for Plant Recognition CLEF (2015). 12 Gikunda and Jouandeau

    work page 2015

  50. [50]

    Using Deep Learning to Challenge Safety Standard for Highly Autonomous Machines in Agriculture

    Steen, K.A., Christiansen, P., Karstoft, H., Jrgensen, R.N. Using Deep Learning to Challenge Safety Standard for Highly Autonomous Machines in Agriculture. J. Imaging, 2, 6 (2016)

    work page 2016

  51. [51]

    Deep- Anomaly: Combining Background Subtraction and Deep Learning for Detecting Obstacles and Anomalies in an Agricultural Field

    Christiansen, P., Nielsen, L.N., Steen, K.A., Jrgensen, R.N., Karstoft, H. Deep- Anomaly: Combining Background Subtraction and Deep Learning for Detecting Obstacles and Anomalies in an Agricultural Field. Sensors (2016)

    work page 2016

  52. [52]

    A., Rasmussen, J., Nielsen, J., Jrgensen, R

    Srensen, R. A., Rasmussen, J., Nielsen, J., Jrgensen, R. N. Thistle Detection using Convolutional Neural Networks. In EFITA WCCA 2017 Conference, Montpellier Supagro, Montpellier, France, July 26 (2017)

    work page 2017

  53. [53]

    Deep Count: Fruit Counting Based on Deep Simulated Learning

    Rahnemoonfar, M., Sheppard, C. Deep Count: Fruit Counting Based on Deep Simulated Learning. Sensors (2017)

    work page 2017

  54. [54]

    A Deep Learning-based Approach for Ba- nana Leaf Diseases Classification

    Amara, J., Bouaziz, B., Algergawy, A. A Deep Learning-based Approach for Ba- nana Leaf Diseases Classification. BTW (2017)

    work page 2017

  55. [55]

    Towards on-farm pig face recognition using convolutional neural net- works

    Hansen, M.F., Smith, M.L., Smith, L.N., Salter, M.G., Baxter, E.M., Farish, M., Grieve, B. Towards on-farm pig face recognition using convolutional neural net- works. Computers in Industry, 98, 145-152 (2018)

    work page 2018

  56. [56]

    Plant species classification using deep convolutional neural network

    Dyrmann, M., Karstoft, H., Midtiby., H. Plant species classification using deep convolutional neural network. Biosystems Engineering 151,7280 (2016)

    work page 2016

  57. [57]

    H., Irfan, M., Minh, L., Suhyeon, I

    Hyun, J., Ibrahim. H., Irfan, M., Minh, L., Suhyeon, I. UAV based wilt detection system via convolutional neural networks. Sustainable Computing: Informatics and Systems. https://doi.org/10.1016/j.suscom.2018.05.010

    work page doi:10.1016/j.suscom.2018.05.010 2018

  58. [58]

    Deep convolutional neural networks for mobile capture device-based crop disease classi- fication in the wild

    Picona, A., Alvarez, A., Seitz, M., Ortiz, O., Echazarra, J., Johannes, A. Deep convolutional neural networks for mobile capture device-based crop disease classi- fication in the wild. Computers and Electronics in Agriculture.https://doi.org/10. 1016/j.compag.2018.04.002

    work page 2018

  59. [59]

    Caffe: Convolutional Architecture for Fast Feature Embed- ding

    Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R.B., Guadar- rama, S., Darrell, T. Caffe: Convolutional Architecture for Fast Feature Embed- ding. ACM Multimedia (2014)

    work page 2014

  60. [60]

    Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

    Ioffe, S., Szegedy, C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. ICML (2015)

    work page 2015

  61. [61]

    Delving Deep into Rectifiers: Surpassing Human- Level Performance on ImageNet Classification

    He, K., Zhang, X., Ren, S., Sun, J. Delving Deep into Rectifiers: Surpassing Human- Level Performance on ImageNet Classification. 2015 IEEE International Confer- ence on Computer Vision (ICCV), 1026-1034 (2015)

    work page 2015