Edge Intelligence with Deep Learning in Greenhouse Management

Proietti, Massimiliano; Bianchi, Federico; Marini, Andrea; Menculini, Lorenzo; Termite, Loris Francesco; Garinei, Alberto; Biondi, Lorenzo; Marconi, Marcello

doi:10.5220/0010451701800187

Cited by 6 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After comparing their proposed model to approximately 20 different deep learning methods, the authors concluded that their hybrid CNN-LSTM model surpasses other models. Proietti et al [75] developed an edge intelligence approach to manage a Greenhouse. In this work, the authors presented an LSTM Encoder-Decoder-based system in a greenhouse to detect anomalies in plants and manage their growth and control equipment.…”

Section: Edge Intelligencementioning

confidence: 99%

A Survey of Machine Learning in Edge Computing: Techniques, Frameworks, Applications, Issues, and Research Directions

Jouini,

Sethom,

Namoun

et al. 2024

Technologies

View full text Add to dashboard Cite

Internet of Things (IoT) devices often operate with limited resources while interacting with users and their environment, generating a wealth of data. Machine learning models interpret such sensor data, enabling accurate predictions and informed decisions. However, the sheer volume of data from billions of devices can overwhelm networks, making traditional cloud data processing inefficient for IoT applications. This paper presents a comprehensive survey of recent advances in models, architectures, hardware, and design requirements for deploying machine learning on low-resource devices at the edge and in cloud networks. Prominent IoT devices tailored to integrate edge intelligence include Raspberry Pi, NVIDIA’s Jetson, Arduino Nano 33 BLE Sense, STM32 Microcontrollers, SparkFun Edge, Google Coral Dev Board, and Beaglebone AI. These devices are boosted with custom AI frameworks, such as TensorFlow Lite, OpenEI, Core ML, Caffe2, and MXNet, to empower ML and DL tasks (e.g., object detection and gesture recognition). Both traditional machine learning (e.g., random forest, logistic regression) and deep learning methods (e.g., ResNet-50, YOLOv4, LSTM) are deployed on devices, distributed edge, and distributed cloud computing. Moreover, we analyzed 1000 recent publications on “ML in IoT” from IEEE Xplore using support vector machine, random forest, and decision tree classifiers to identify emerging topics and application domains. Hot topics included big data, cloud, edge, multimedia, security, privacy, QoS, and activity recognition, while critical domains included industry, healthcare, agriculture, transportation, smart homes and cities, and assisted living. The major challenges hindering the implementation of edge machine learning include encrypting sensitive user data for security and privacy on edge devices, efficiently managing resources of edge nodes through distributed learning architectures, and balancing the energy limitations of edge devices and the energy demands of machine learning.

show abstract

Section: Edge Intelligencementioning

confidence: 99%

A Survey of Machine Learning in Edge Computing: Techniques, Frameworks, Applications, Issues, and Research Directions

Jouini,

Sethom,

Namoun

et al. 2024

Technologies

View full text Add to dashboard Cite

show abstract

“…An Arduino-based shield can acquire temperature, relative humidity, pressure, light intensity and UVA. The camera and the sensors are connected to a Raspberry PI that acts as edge computational unit [5].…”

Section: A 2d Measurementsmentioning

confidence: 99%

“…The data extracted from different measurement techniques can be then processed through Machine Learning algorithms, such as classifiers, Deep Learning models or Autoencoders [5], in order to detect anomalies in the plant growth or in the greenhouse equipment or operational parameters.…”

Section: Introductionmentioning

confidence: 99%

Anomaly detection in plant growth in a controlled environment using 3D scanning techniques and deep learning

Xhimitiku

Bianchi

Proietti

et al. 2021

2021 IEEE International Workshop on Metrology for Agriculture and Forestry (MetroAgriFor)

View full text Add to dashboard Cite

This paper presents a comparison of different methodologies for monitoring the plants growth in a greenhouse. A 2D measurement based on Computer Vision algorithms and 3D shape measurements techniques (Structured light, LIDAR and photogrammetry) are compared. From the joined 2D and 3D data, an analysis was performed considering health plant indicators. The methodologies are compared among each other. The acquired data are then fed into Deep Learning algorithms in order to detect anomalies in plant growth. The final aim is to give an assessment on the image acquisition methodologies, selecting the most suitable to be used to create the Deep Learning model inputs saving time and resources.

show abstract

A Decision Support System Based on Rainfall Nowcasting and Artificial Neural Networks to Mitigate Wastewater Treatment Plant Downstream Floods

Termite

Bonamente²,

Garinei³

et al. 2022

Communications in Computer and Information Science

View full text Add to dashboard Cite

Edge Intelligence with Deep Learning in Greenhouse Management

Cited by 6 publications

References 0 publications

A Survey of Machine Learning in Edge Computing: Techniques, Frameworks, Applications, Issues, and Research Directions

A Survey of Machine Learning in Edge Computing: Techniques, Frameworks, Applications, Issues, and Research Directions

Anomaly detection in plant growth in a controlled environment using 3D scanning techniques and deep learning

A Decision Support System Based on Rainfall Nowcasting and Artificial Neural Networks to Mitigate Wastewater Treatment Plant Downstream Floods

Contact Info

Product

Resources

About