968 Hits in 5.6 sec

Detection of Plastic Greenhouses Using High Resolution Rgb Remote Sensing Data and Convolutional Neural Network

Balázs Jakab, Boudewijn van Leeuwen, Zalán Tobak
2021 Journal of Environmental Geography  
This research presents the results of the use of a convolutional neural network for automatic object detection of plastic greenhouses in high resolution remotely sensed data within a GIS environment with  ...  The model based on the VGG_11 backbone model (with dropout) resulted in an average accuracy of 79.2% with a relatively short training time of 90 minutes, the much more complex DenseNet121 model was trained  ...  Training performance can be increased considerably by applying transfer training based on a model with many parameters that was pre-trained for a different task (Howard and Gugger, 2020) .  ... 
doi:10.2478/jengeo-2021-0004 fatcat:zov5ef5bgfhzrpdztgpg4j7q6m

Applications of Artificial Neural Networks in Greenhouse Technology and Overview for Smart Agriculture Development

Axel Escamilla-García, Genaro M. Soto-Zarazúa, Manuel Toledano-Ayala, Edgar Rivas-Araiza, Abraham Gastélum-Barrios
2020 Applied Sciences  
This article reviews the applications of artificial neural networks (ANNs) in greenhouse technology, and also presents how this type of model can be developed in the coming years by adapting to new technologies  ...  The advantages and disadvantages of neural networks (NNs) are observed in the different applications in greenhouses, from microclimate prediction, energy expenditure, to more specific tasks such as the  ...  short term in the next step based on the data of the interior environment due to recursive online training.  ... 
doi:10.3390/app10113835 fatcat:lts6ftjttbd3vf5k5buawddb6i

Monthly Electric Load Forecasting Using Transfer Learning for Smart Cities

Seung-Min Jung, Sungwoo Park, Seung-Won Jung, Eenjun Hwang
2020 Sustainability  
In this paper, we propose a novel monthly electric load forecasting scheme for a city or district based on transfer learning using similar data from other cities or districts.  ...  Although diverse forecasting models based on artificial intelligence techniques have been proposed with good performance, they require sufficient datasets for training.  ...  To the best of our knowledge, this is the first study that used transfer learning based on similarity between data for MTLF.  ... 
doi:10.3390/su12166364 fatcat:v5ih63jo2jckrbfucmbv5nmgi4

Robust Model-based Reinforcement Learning for Autonomous Greenhouse Control [article]

Wanpeng Zhang, Xiaoyan Cao, Yao Yao, Zhicheng An, Xi Xiao, Dijun Luo
2021 arXiv   pre-print
As for the safety concern, we propose a sample dropout module to focus more on worst-case samples, which can help improve the adaptability of the greenhouse planting policy in extreme cases.  ...  In this paper, we present a model-based robust RL framework for autonomous greenhouse control to meet the sample efficiency and safety challenges.  ...  This work was also supported in part by the National Natural Science Foundation of China ( 61972219  ... 
arXiv:2108.11645v2 fatcat:rtnxbasfbbglreb4pev5bvjs5a

Recognition of Image-Based Plant Leaf Diseases Using Deep Learning Classification Models

Sakshi Takkar, Anuj Kakran, Veerpal Kaur, Manik Rakhra, Manish Sharma, Pargin Bangotra, Neha Verma
2021 Nature Environment and Pollution Technology  
Accurate and rapid illness prediction for early illness treatment to crops minimizes economical loss to the individual and further proves to be productive for healthy crops.  ...  Super-Resolution Convolutional Neural Network (SRCNN) and Bicubic models are employed in the system to identify healthy and diseased leaves with an accuracy of 99.175 % and 99.156 % respectively.  ...  SRCNN is a deep convolutional neural network that is used for end-to-end mapping of low-resolution to high-resolution images (Fig. 2 ).  ... 
doi:10.46488/nept.2021.v20i05.031 fatcat:vhlqmambabhtjfplogohaudcae

Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things [article]

Jing Zhang, Dacheng Tao
2020 arXiv   pre-print
In the Internet of Things (IoT) era, billions of sensors and devices collect and process data from the environment, transmit them to cloud centers, and receive feedback via the internet for connectivity  ...  However, transmitting massive amounts of heterogeneous data, perceiving complex environments from these data, and then making smart decisions in a timely manner are difficult.  ...  However, humans learn new concepts based not only on data but on prior knowledge. Likewise, prior knowledge can be very useful for training deep learning models in a data-efficient way.  ... 
arXiv:2011.08612v1 fatcat:dflut2wdrjb4xojll34c7daol4

Intelligent Control Strategy for Transient Response of a Variable Geometry Turbocharger System Based on Deep Reinforcement Learning

Hu, Yang, Li, Li, Bai
2019 Processes  
In this context, one of the latest model-free DRL algorithms, the deep deterministic policy gradient (DDPG) algorithm, was built in this paper to develop and finally form a strategy to track the target  ...  In addition, the proposed strategy is able to adapt to the changing environment and hardware aging over time by adaptively tuning the algorithm in a self-learning manner on-line, making it attractive to  ...  Data Availability: The data used to support the findings of this study are available from the corresponding author upon request. Nomenclature  ... 
doi:10.3390/pr7090601 fatcat:55x4mcpuuvchff7odly3x72zyi

Deep Learning for Change Detection in Remote Sensing Images: Comprehensive Review and Meta-Analysis [article]

Lazhar Khelifi, Max Mignotte
2020 arXiv   pre-print
Then, we focus on deep learning-based change detection methodologies for remote sensing images by giving a general overview of the existing methods.  ...  This study will contribute in several ways to our understanding of deep learning for change detection and will provide a basis for further research.  ...  [101] have transferred a CNNs already pre-trained on large-scale natural image data set (e.g., ImageNet [102] ), to a RS domain.  ... 
arXiv:2006.05612v1 fatcat:35b2rn6xsbhhlabzkxa7kmsj6e

Forecasting renewable energy for environmental resilience through computational intelligence

Mansoor Khan, Essam A. Al-Ammar, Muhammad Rashid Naeem, Wonsuk Ko, Hyeong-Jin Choi, Hyun-Koo Kang, Zaher Mundher Yaseen
2021 PLoS ONE  
Finally, the CNN-LSTM deep learning hybrid model is fine-tuned with various parameters for reliable forecasting of wind energy on three different offshore Windfarms.  ...  Second, a mixture of the CNN and LSTM models is used to train prominent wind features and further improve forecasting accuracy.  ...  The trained model is then transferred to the deep learning model based on Convolutional Neural Network (CNN) combined with LSTM to predict wind power on all three offshore Windfarms.  ... 
doi:10.1371/journal.pone.0256381 pmid:34415924 pmcid:PMC8378711 fatcat:paeq4ik5nve6bdqsbuxo7iizxu

Monitoring Spatial Sustainable Development: semi-automated analysis of Satellite and Aerial Images for Energy Transition and Sustainability Indicators [article]

Tim De Jong
2020 arXiv   pre-print
For the evaluation of the deep learning models we used a cross-site evaluation approach: the deep learning models where trained in one geographical area and then evaluated on a different geographical area  ...  The aim of the project was to evaluate whether deep learning models could be developed, that worked across different member states in the European Union.  ...  a convolutional neural network on the NRW data and evaluating it on the Heerlen datatraining an auto-encoder architecture on the NRW data Training Setup for the Heerlen data A pre-trained VGG16 model  ... 
arXiv:2009.05738v1 fatcat:nlgfrhrrwje55jj32hgpm5573u

Deep Learning for Change Detection in Remote Sensing Images: Comprehensive Review and Meta-Analysis

Lazhar Khelifi, Max Mignotte
2020 IEEE Access  
[101] have transferred a CNNs already pre-trained on large-scale natural image data set (e.g., ImageNet [102] ), to a RS domain.  ...  a deep hierarchical modeling of the training data [42] .  ... 
doi:10.1109/access.2020.3008036 fatcat:xtl27xx3lnhhpf4ubxuuheya6e


2019 Applied Ecology and Environmental Research  
It acquires data based on sensor groups and conducts decision analysis to change the behavior control and feedback of objects, such as the greenhouse monitoring system studied in this paper.  ...  Based on the IoT and Zig Bee wireless sensor network technology, this paper designs a general scheme of an intelligent greenhouse control system based on IoT technology.  ...  Finally, based on the characteristics of the greenhouse environment, the mathematical model of the greenhouse was established and the final model optimization was carried out.  ... 
doi:10.15666/aeer/1704_84498464 fatcat:anle4gesebdopg3ps5ofym24ay

Image-based Automatic Diagnostic System for Tomato Plants using Deep Learning

Shaheen Khatoon, Md Maruf Hasan, Amna Asif, Majed Alshmari, Yun-Kiam Yap
2021 Computers Materials & Continua  
Various Convolutional Neural Networks (CNNs) are trained on a large dataset of leaves and fruits images of tomato plants.  ...  We compared the performance of ShallowNet (a shallow network trained from scratch) and the state-of-theart deep learning network (models are ne-tuned via transfer learning).  ...  Acknowledgement: We extend our appreciation to the College of Agriculture, King Faisal University, for providing access to its agriculture farms and providing expertise for data labeling.  ... 
doi:10.32604/cmc.2021.014580 fatcat:ozmla5vusrhhrgv7incuhrqsie

Precision Irrigation Management Using Machine Learning and Digital Farming Solutions

Emmanuel Abiodun Abioye, Oliver Hensel, Travis J. Esau, Olakunle Elijah, Mohamad Shukri Zainal Abidin, Ajibade Sylvester Ayobami, Omosun Yerima, Abozar Nasirahmadi
2022 AgriEngineering  
The focus of this paper is to investigate research regarding the integration of different machine learning models that can provide optimal irrigation decision management.  ...  Freshwater is essential for irrigation and the supply of nutrients for plant growth, in order to compensate for the inadequacies of rainfall.  ...  Data Availability Statement: Not applicable. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/agriengineering4010006 fatcat:ld6yznzpkvcppn6zfxwpsfoyuq

Machine Learning Based Indoor Localization Using Wi-Fi RSSI Fingerprints: An Overview

Navneet Singh, Sangho Choe, Rajiv Punmiya
2021 IEEE Access  
This survey attempts to provide a summarized investigation of MLbased Wi-Fi RSSI fingerprinting schemes, including data preprocessing, data augmentation, ML prediction models for indoor localization, and  ...  Any ML-based study is heavily reliant on datasets. Therefore, we dedicate a significant portion of this survey to the discussion of dataset collection and open-source datasets.  ...  Deep autoencoders are trained to denoise data in the offline phase and construct RSS fingerprints based on learned weights.  ... 
doi:10.1109/access.2021.3111083 fatcat:7o6zb7kycrgftfpsukuwnsl24m
« Previous Showing results 1 — 15 out of 968 results