IoT-Based Smart Farming Architecture Using Federated Learning: a Nitrous Oxide Emission Prediction Use Case DOI
Patrick Killeen, Ci Lin,

Futong Li

и другие.

ACM Journal on Computing and Sustainable Societies, Год журнала: 2025, Номер unknown

Опубликована: Март 13, 2025

Precision agriculture and smart farming can enable real-time decision-making to optimize resources lower costs via data-driven model predictions. Adoption rates of systems are unfortunately low due farmers’ privacy concerns the high initial monetary deploying such systems. High be lowered by replacing expensive sensing equipment with machine learning models. Cloud computing used train models, but this suffers from poor privacy. Instead, fog edge local important geographical trends may lost data segmentation. Federated address these challenges. A privacy-aware Internet Things (IoT)-based architecture that uses federated was proposed. prototype deployed gather sensor a Canadian farm in Ottawa, Ontario. For various we perform nitrous oxide prediction experiments using centralized, local, federated, distributed ensemble learning. We found compete similarly well centralized Our results demonstrate our methodology potentially replace emission inexpensive sensors combined predictive analytics

Язык: Английский

Applications of IoT for optimized greenhouse environment and resources management DOI
Chrysanthos Maraveas, Dimitrios Piromalis, Konstantinos G. Arvanitis

и другие.

Computers and Electronics in Agriculture, Год журнала: 2022, Номер 198, С. 106993 - 106993

Опубликована: Апрель 30, 2022

Язык: Английский

Процитировано

145
A Systematic Survey on the Role of Cloud, Fog, and Edge Computing Combination in Smart Agriculture DOI Creative Commons
Yogeswaranathan Kalyani, Rem Collier

Sensors, Год журнала: 2021, Номер 21(17), С. 5922 - 5922

Опубликована: Сен. 3, 2021

Cloud Computing is a well-established paradigm for building service-centric systems. However, ultra-low latency, high bandwidth, security, and real-time analytics are limitations in when analysing providing results large amount of data. Fog Edge offer solutions to the Computing. The number agricultural domain applications that use combination Cloud, Fog, increasing last few decades. This article aims provide systematic literature review current works have been done smart agriculture between 2015 up-to-date. key objective this identify all relevant research on new computing paradigms with propose architecture model combinations Cloud–Fog–Edge. Furthermore, it also analyses examines application domains, approaches, used combinations. Moreover, survey discusses components models briefly explores communication protocols interact from one layer another. Finally, challenges future directions pointed out article.

Язык: Английский

Процитировано

118
Harnessing quantum computing for smart agriculture: Empowering sustainable crop management and yield optimization DOI
Chrysanthos Maraveas, Debanjan Konar,

Dimosthenis K. Michopoulos

и другие.

Computers and Electronics in Agriculture, Год журнала: 2024, Номер 218, С. 108680 - 108680

Опубликована: Фев. 10, 2024

Язык: Английский

Процитировано

23
Machine-Learning-Based UAV-Assisted Agricultural Information Security Architecture and Intrusion Detection DOI
Rui Fu, Xiaojun Ren, Ye Li

и другие.

IEEE Internet of Things Journal, Год журнала: 2023, Номер 10(21), С. 18589 - 18598

Опубликована: Янв. 30, 2023

In recent years, unmanned aerial vehicle (UAV) remote sensing has developed rapidly in the field of farmland information monitoring. Real-time and accurate access to crop growth dynamics is a prerequisite for implementation precision agriculture. Machine learning identifies existing knowledge acquire new knowledge, promotes development Artificial Intelligence, brings large number data training sets machine learning. This article aims ensure safe operation agricultural systems guarantee security intelligent The method explores wireless network deployment UAV system. geographical location can effectively carry out rapid detection security. First, UAV-assisted acquisition system was studied. Besides, double deep $Q$ -network (DDQN) algorithm based on geography position (GPI) proposed quickly optimize UAVs. GPI avoid complicated calculation process channel state information. DDQN introduced obtain functional relationship between optimal position, forming GPI-Learning strategy. addition, convolutional neural (CNN) long short-term memory (LSTM) are integrated as CNN–LSTM build intrusion Agricultural Internet Things (AIoT) structure system, LSTM responsible transmission, CNN capable model building. Combined with influence various parameters performance algorithm, simulation experiment set population size 36, discovery probability 0.25, step scaling factor 0.8, Levy flight index 1.25. throughput combined cuckoo search better than other algorithms under different numbers On KDD-CUP99 set, accuracy rate AIoT CNN+LSTM reached 93.5% 94.4%, respectively. general, reported here crucial practical reference value systems.

Язык: Английский

Процитировано

40
Current Status and Prospects of Research on Sensor Fault Diagnosis of Agricultural Internet of Things DOI Creative Commons
Xiuguo Zou, Wenchao Liu, Zhiqiang Huo

и другие.

Sensors, Год журнала: 2023, Номер 23(5), С. 2528 - 2528

Опубликована: Фев. 24, 2023

Sensors have been used in various agricultural production scenarios due to significant advances the Agricultural Internet of Things (Ag-IoT), leading smart agriculture. Intelligent control or monitoring systems rely heavily on trustworthy sensor systems. Nonetheless, failures are likely factors, including key equipment malfunction human error. A faulty can produce corrupted measurements, resulting incorrect decisions. Early detection potential faults is crucial, and fault diagnosis techniques proposed. The purpose detect data recover isolate sensors so that finally provide correct user. Current technologies based mainly statistical models, artificial intelligence, deep learning, etc. further development technology also conducive reducing loss caused by failures.

Язык: Английский

Процитировано

24
Challenges in Achieving Artificial Intelligence in Agriculture DOI
Anjana J. Atapattu, L. Perera, Tharindu D. Nuwarapaksha

и другие.

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

9
Harnessing the potential of nanostructured materials for sustainable development DOI

Jacob Tizhe Liberty,

Aiswarya Anil,

Stephen James Ijimdiya

и другие.

Nano-Structures & Nano-Objects, Год журнала: 2024, Номер 38, С. 101216 - 101216

Опубликована: Май 1, 2024

Язык: Английский

Процитировано

8
From soil health to agricultural productivity: The critical role of soil constraint management DOI Creative Commons
Tong Li, Lizhen Cui, Vilim Filipović

и другие.

CATENA, Год журнала: 2025, Номер 250, С. 108776 - 108776

Опубликована: Янв. 30, 2025

Язык: Английский

Процитировано

1
A Novel Model for Soil Organic Matter and Total Nitrogen Detection Based on Visible/Shortwave Near-Infrared Spectroscopy DOI Creative Commons
Jiangtao Qi, Peng Cheng,

Junbo Zhou

и другие.

Land, Год журнала: 2025, Номер 14(2), С. 329 - 329

Опубликована: Фев. 6, 2025

Soil organic matter (SOM) and total nitrogen (TN) are critical indicators for assessing soil fertility. Although laboratory chemical analysis methods can accurately measure their contents, these techniques time-consuming labor-intensive. Spectral technology, characterized by its high sensitivity convenience, has been increasingly integrated with machine learning algorithms nutrient monitoring. However, the process of spectral data remains complex requires further optimization simplicity efficiency to improve prediction accuracy. This study proposes a novel model enhance accuracy SOM TN predictions in northeast China’s black soil. Visible/Shortwave Near-Infrared Spectroscopy (Vis/SW-NIRS) within 350–1070 nm range were collected, preprocessed, dimensionality-reduced. The scores first nine principal components after partial least squares (PLS) dimensionality reduction selected as inputs, measured contents used outputs build back-propagation neural network (BPNN) model. results show that processed combination standard normal variate (SNV) multiple scattering correction (MSC) have best modeling performance. To stability this model, three named random search (RS), grid (GS), Bayesian (BO) introduced. demonstrate Vis/SW-NIRS provides reliable PLS-RS-BPNN achieving performance (R2 = 0.980 0.972, RMSE 1.004 0.006 TN, respectively). Compared traditional models such forests (RF), one-dimensional convolutional networks (1D-CNNs), extreme gradient boosting (XGBoost), proposed improves R2 0.164–0.344 predicting 0.257–0.314 respectively. These findings confirm potential technology effective tools prediction, offering valuable insights application sensing information.

Язык: Английский

Процитировано

1
Application of Internet of Things (IoT) for Optimized Greenhouse Environments DOI Creative Commons
Chrysanthos Maraveas, Thomas Bartzanas

AgriEngineering, Год журнала: 2021, Номер 3(4), С. 954 - 970

Опубликована: Ноя. 29, 2021

This review presents the state-of-the-art research on IoT systems for optimized greenhouse environments. The data were analyzed using descriptive and statistical methods to infer relationships between Internet of Things (IoT), emerging technologies, precision agriculture, agriculture 4.0, improvements in commercial farming. discussion is situated broader context mitigating adverse effects climate change global warming through optimization critical parameters such as temperature humidity, intelligent acquisition, rule-based control, resolving barriers adoption agriculture. recent unexpected severe weather events have contributed low agricultural yields losses; this a challenge that can be resolved technology-mediated Advances technology over time development sensors frost prevention, remote crop monitoring, fire hazard precise control nutrients soilless cultivation, power autonomy use solar energy, feeding, shading, lighting improve reduce operational costs. However, particular challenges abound, including limited uptake smart technologies price, accuracy sensors. should help guide future Research & Development projects applications.

Язык: Английский

Процитировано

55