Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.5
2.7
Journals
Applied Sciences
Special Issues
Deep Learning-Based Smart Farm Techniques
share announcement

Deep Learning-Based Smart Farm Techniques

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (15 March 2021) | Viewed by 15376

Special Issue Editors

Prof. Dr. Yongwha Chung

E-Mail Website
Guest Editor
Department of Computer Convergence Software, Korea University, Sejong, Republic of Korea
Interests: image processing; computer vision; deep learning; smart agriculture; livestock monitoring
Special Issues, Collections and Topics in MDPI journals
Dr. Sungju Lee

E-Mail
Guest Editor
Department of Software, Sangmyung University, Cheonan city, Korea
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Food security is a major issue which will become more urgent and critical over the next few decades. It is expected that smart farming techniques could provide solutions to the following challenges:

  • Better monitoring of food development and livestock behavior.
  • Better understanding of the farming conditions such as weather/environment conditions and emergence of pests/diseases.

The advance of deep learning techniques enables the monitoring and the understanding of food- and livestock-based smart farming more effectively.
Deep learning-based smart farming techniques can be divided into sensor techniques, transmission techniques, analysis techniques, and low-cost techniques. In addition to the RFID, there are many sensors such as temperature, humidity, CO2, ammonia, pH values, image/video, and audio. Zigbee, Bluetooth, Wi-Fi, and 3G/4G/5G are possible transmission techniques for smart farm applications. Once the data is received, many analysis techniques can be applied for tracking, tracing, monitoring, and event management tasks. Finally, for large-scale smart farm applications, low-cost solutions such as edge computing- and cloud computing-based solutions should be considered.

This Special Issue of the journal Applied Sciences, titled “Deep Learning-based Smart Farming Techniques,” aims to cover recent advances in the development and application of deep learning techniques for smart farm applications.

Prof. Yongwha Chung
Dr. Sungju Lee
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Sensor techniques for deep learning-based smart farming
  • Transmission techniques for deep learning-based smart farming
  • Analysis techniques for deep learning-based smart farming
  • Low-cost techniques for deep learning-based smart farming
  • Edge computing techniques for deep learning-based smart farming
  • Cloud computing techniques for deep learning-based smart farming  
  • Big data and IoT techniques for deep learning-based smart farming 
  • Deep learning-based applications of food-based farming
  • Deep learning-based applications of livestock (cow, pig, and broiler chicken) farming

Published Papers (5 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

19 pages, 3005 KiB  
Article
EnsemblePigDet: Ensemble Deep Learning for Accurate Pig Detection
by Hanse Ahn, Seungwook Son, Heegon Kim, Sungju Lee, Yongwha Chung and Daihee Park
Appl. Sci. 2021, 11(12), 5577; https://doi.org/10.3390/app11125577 - 16 Jun 2021
Cited by 17 | Viewed by 2294
Abstract
Automated pig monitoring is important for smart pig farms; thus, several deep-learning-based pig monitoring techniques have been proposed recently. In applying automated pig monitoring techniques to real pig farms, however, practical issues such as detecting pigs from overexposed regions, caused by strong sunlight [...] Read more.
Automated pig monitoring is important for smart pig farms; thus, several deep-learning-based pig monitoring techniques have been proposed recently. In applying automated pig monitoring techniques to real pig farms, however, practical issues such as detecting pigs from overexposed regions, caused by strong sunlight through a window, should be considered. Another practical issue in applying deep-learning-based techniques to a specific pig monitoring application is the annotation cost for pig data. In this study, we propose a method for managing these two practical issues. Using annotated data obtained from training images without overexposed regions, we first generated augmented data to reduce the effect of overexposure. Then, we trained YOLOv4 with both the annotated and augmented data and combined the test results from two YOLOv4 models in a bounding box level to further improve the detection accuracy. We propose accuracy metrics for pig detection in a closed pig pen to evaluate the accuracy of the detection without box-level annotation. Our experimental results with 216,000 “unseen” test data from overexposed regions in the same pig pen show that the proposed ensemble method can significantly improve the detection accuracy of the baseline YOLOv4, from 79.93% to 94.33%, with additional execution time. Full article
(This article belongs to the Special Issue Deep Learning-Based Smart Farm Techniques)
►▼ Show Figures

Figure 1

28 pages, 14924 KiB  
Article
Yielding Multi-Fold Training Strategy for Image Classification of Imbalanced Weeds
by Vo Hoang Trong, Yu Gwang Hyun, Kim Jin Young and Pham The Bao
Appl. Sci. 2021, 11(8), 3331; https://doi.org/10.3390/app11083331 - 07 Apr 2021
Cited by 5 | Viewed by 2238
Abstract
An imbalanced dataset is a significant challenge when training a deep neural network (DNN) model for deep learning problems, such as weeds classification. An imbalanced dataset may result in a model that behaves robustly on major classes and is overly sensitive to minor [...] Read more.
An imbalanced dataset is a significant challenge when training a deep neural network (DNN) model for deep learning problems, such as weeds classification. An imbalanced dataset may result in a model that behaves robustly on major classes and is overly sensitive to minor classes. This article proposes a yielding multi-fold training (YMufT) strategy to train a DNN model on an imbalanced dataset. This strategy reduces the bias in training through a min-class-max-bound procedure (MCMB), which divides samples in the training set into multiple folds. The model is consecutively trained on each one of these folds. In practice, we experiment with our proposed strategy on two small (PlantSeedlings, small PlantVillage) and two large (Chonnam National University (CNU), large PlantVillage) weeds datasets. With the same training configurations and approximate training steps used in conventional training methods, YMufT helps the DNN model to converge faster, thus requiring less training time. Despite a slight decrease in accuracy on the large dataset, YMufT increases the F1 score in the NASNet model to 0.9708 on the CNU dataset and 0.9928 when using the Mobilenet model training on the large PlantVillage dataset. YMufT shows outstanding performance in both accuracy and F1 score on small datasets, with values of (0.9981, 0.9970) using the Mobilenet model for training on small PlantVillage dataset and (0.9718, 0.9689) using Resnet to train on the PlantSeedlings dataset. Grad-CAM visualization shows that conventional training methods mainly concentrate on high-level features and may capture insignificant features. In contrast, YMufT guides the model to capture essential features on the leaf surface and properly localize the weeds targets. Full article
(This article belongs to the Special Issue Deep Learning-Based Smart Farm Techniques)
►▼ Show Figures

Figure 1

16 pages, 3160 KiB  
Article
A Study of Adversarial Attacks and Detection on Deep Learning-Based Plant Disease Identification
by Zhirui Luo, Qingqing Li and Jun Zheng
Appl. Sci. 2021, 11(4), 1878; https://doi.org/10.3390/app11041878 - 20 Feb 2021
Cited by 2 | Viewed by 2377
Abstract
Transfer learning using pre-trained deep neural networks (DNNs) has been widely used for plant disease identification recently. However, pre-trained DNNs are susceptible to adversarial attacks which generate adversarial samples causing DNN models to make wrong predictions. Successful adversarial attacks on deep learning (DL)-based [...] Read more.
Transfer learning using pre-trained deep neural networks (DNNs) has been widely used for plant disease identification recently. However, pre-trained DNNs are susceptible to adversarial attacks which generate adversarial samples causing DNN models to make wrong predictions. Successful adversarial attacks on deep learning (DL)-based plant disease identification systems could result in a significant delay of treatments and huge economic losses. This paper is the first attempt to study adversarial attacks and detection on DL-based plant disease identification. Our results show that adversarial attacks with a small number of perturbations can dramatically degrade the performance of DNN models for plant disease identification. We also find that adversarial attacks can be effectively defended by using adversarial sample detection with an appropriate choice of features. Our work will serve as a basis for developing more robust DNN models for plant disease identification and guiding the defense against adversarial attacks. Full article
(This article belongs to the Special Issue Deep Learning-Based Smart Farm Techniques)
►▼ Show Figures

Figure 1

17 pages, 3662 KiB  
Article
Field-Applicable Pig Anomaly Detection System Using Vocalization for Embedded Board Implementations
by Minki Hong, Hanse Ahn, Othmane Atif, Jonguk Lee, Daihee Park and Yongwha Chung
Appl. Sci. 2020, 10(19), 6991; https://doi.org/10.3390/app10196991 - 07 Oct 2020
Cited by 15 | Viewed by 3315
Abstract
Failure to quickly and accurately detect abnormal situations, such as the occurrence of infectious diseases, in pig farms can cause significant damage to the pig farms and the pig farming industry of the country. In this study, we propose an economical and lightweight [...] Read more.
Failure to quickly and accurately detect abnormal situations, such as the occurrence of infectious diseases, in pig farms can cause significant damage to the pig farms and the pig farming industry of the country. In this study, we propose an economical and lightweight sound-based pig anomaly detection system that can be applicable even in small-scale farms. The system consists of a pipeline structure, starting from sound acquisition to abnormal situation detection, and can be installed and operated in an actual pig farm. It has the following structure that makes it executable on the embedded board TX-2: (1) A module that collects sound signals; (2) A noise-robust preprocessing module that detects sound regions from signals and converts them into spectrograms; and (3) A pig anomaly detection module based on MnasNet, a lightweight deep learning method, to which the 8-bit filter clustering method proposed in this study is applied, reducing its size by 76.3% while maintaining its identification performance. The proposed system recorded an F1-score of 0.947 as a stable pig’s abnormality identification performance, even in various noisy pigpen environments, and the system’s execution time allowed it to perform in real time. Full article
(This article belongs to the Special Issue Deep Learning-Based Smart Farm Techniques)
►▼ Show Figures

Figure 1

22 pages, 3849 KiB  
Article
EmbeddedPigDet—Fast and Accurate Pig Detection for Embedded Board Implementations
by Jihyun Seo, Hanse Ahn, Daewon Kim, Sungju Lee, Yongwha Chung and Daihee Park
Appl. Sci. 2020, 10(8), 2878; https://doi.org/10.3390/app10082878 - 22 Apr 2020
Cited by 29 | Viewed by 4093
Abstract
Automated pig monitoring is an important issue in the surveillance environment of a pig farm. For a large-scale pig farm in particular, practical issues such as monitoring cost should be considered but such consideration based on low-cost embedded boards has not yet been [...] Read more.
Automated pig monitoring is an important issue in the surveillance environment of a pig farm. For a large-scale pig farm in particular, practical issues such as monitoring cost should be considered but such consideration based on low-cost embedded boards has not yet been reported. Since low-cost embedded boards have more limited computing power than typical PCs and have tradeoffs between execution speed and accuracy, achieving fast and accurate detection of individual pigs for “on-device” pig monitoring applications is very challenging. Therefore, in this paper, we propose a method for the fast detection of individual pigs by reducing the computational workload of 3 × 3 convolution in widely-used, deep learning-based object detectors. Then, in order to recover the accuracy of the “light-weight” deep learning-based object detector, we generate a three-channel composite image as its input image, through “simple” image preprocessing techniques. Our experimental results on an NVIDIA Jetson Nano embedded board show that the proposed method can improve the integrated performance of both execution speed and accuracy of widely-used, deep learning-based object detectors, by a factor of up to 8.7. Full article
(This article belongs to the Special Issue Deep Learning-Based Smart Farm Techniques)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-5
Back to TopTop