Crop diseases cannot be accurately predicted by merely analyzing individual disease causes. Only through construction of a comprehensive analysis system can users be provided with predictions of highly probable diseases. In this study, cloud-based technology capable of handling the collection, analysis, and prediction of agricultural environment information in one common platform was developed. The proposed Farm as a Service (FaaS) integrated system supports high-level application services by operating and monitoring farms as well as managing associated devices, data, and models. This system registers, connects, and manages Internet of Things (IoT) devices and analyzes environmental and growth information. In addition, the IoT-Hub network model was constructed in this study. This model supports efficient data transfer for each IoT device as well as communication for non-standard products, and exhibits high communication reliability even in poor communication environments. Thus, IoT-Hub ensures the stability of technology specialized for agricultural environments. The integrated agriculture-specialized FaaS system implements specific systems at different levels. The proposed system was verified through design and analysis of a strawberry infection prediction system, which was compared with other infection models.

There has been much research and various attempts to apply new IoT technology to agricultural areas. However, IoT for the agriculture should be considered differently against the same areas such as industrial, logistics. This paper presents the IoT-based agricultural production system for stabilizing supply and demand of agricultural products while developing the environment sensors and prediction system for the growth and production amount of crops by gathering its environmental information. Currently, the demand by consumption of agricultural products could be predicted quantitatively, however, the variation of harvest and production by the change of farm's cultivated area, weather change, disease and insect damage etc. could not be predicted, so that the supply and demand of agricultural products has not been controlled properly. To overcome it, this paper designed the IoT-based monitoring system to analyze crop environment, and the method to improve the efficiency of decision making by analyzing harvest statistics. Therefore, this paper developed the decision support system to forecast agricultural production using IoT sensors. This system was also a unified system that supports the processes sowing seeds through selling agricultural products to consumers. 3 Corresponding author The IoT-based agricultural production system through correlation analysis between the crop statistical information and agricultural environment information has enhanced the ability of farmers, researchers, and government officials to analyze current conditions and predict future harvest. Additionally, agricultural products quality can be improved because farmers observe whole cycle from seeding to selling using this IoT-based decision support system.

Application of computer vision and robotics in agriculture requires sufficient knowledge and understanding of the physical properties of the object of interest. Yield monitoring is an example where these properties affect the quantified estimation of yield mass. In this study, we propose an image-processing and artificial intelligence-based system using multi-class detection with instance-wise segmentation of fruits in an image that can further estimate dimensions and mass. We analyze a tomato image dataset with mass and dimension values collected using a calibrated vision system and accurate measuring devices. After successful detection and instance-wise segmentation, we extract the real-world dimensions of the fruit. Our characterization results exhibited a significantly high correlation between dimensions and mass, indicating that artificial intelligence algorithms can effectively capture this complex physical relation to estimate the final mass. We also compare different artificial intelligence algorithms to show that the computed mass agrees well with the actual mass. Detection and segmentation results show an average mask intersection over union of 96.05%, mean average precision of 92.28%, detection accuracy of 99.02%, and precision of 99.7%. The mean absolute percentage error for mass estimation was 7.09 for 77 test samples using a bagged ensemble tree regressor. This approach could be applied to other computer vision and robotic applications such as sizing and packaging systems and automated harvesting or to other measuring instruments.

The swarm intelligence (SI)-based bio-inspired algorithm demonstrates features of heterogeneous individual agents, such as stability, scalability, and adaptability, in distributed and autonomous environments. The said algorithm will be applied to the communication network environment to overcome the limitations of wireless sensor networks (WSNs). Herein, the swarm-intelligence-centric routing algorithm (SICROA) is presented for use in WSNs that aim to leverage the advantages of the ant colony optimization (ACO) algorithm. The proposed routing protocol addresses the problems of the ad hoc on-demand distance vector (AODV) and improves routing performance via collision avoidance, link-quality prediction, and maintenance methods. The proposed method was found to improve network performance by replacing the periodic “Hello” message with an interrupt that facilitates the prediction and detection of link disconnections. Consequently, the overall network performance can be further improved by prescribing appropriate procedures for processing each control message. Therefore, it is inferred that the proposed SI-based approach provides an optimal solution to problems encountered in a complex environment, while operating in a distributed manner and adhering to simple rules of behavior.

Despite the recent increase in smart farming practices, system uncertainty and difficulties associated with maintaining farming sites hinder their widespread adoption. Agricultural production systems are extremely sensitive to operational downtime caused by malfunctions because it can damage crops. To resolve this problem, the types of abnormal data, the present error determination techniques for each data type, and the accuracy of anomaly data determination based on spatial understanding of the sensed values are classified in this paper. We design and implement a system to detect and predict abnormal data using a recurrent neural network algorithm and diagnose malfunctions using an ontological technique. The proposed system comprises the cloud in charge of the IoT equipment installed in the farm testbed, communication and control, system management, and a common framework based on machine learning and deep learning for fault diagnosis. It exhibits excellent prediction performance, with a root mean square error of 0.073 for the long short-term memory model. Considering the increasing number of agricultural production facilities in recent years, the results of this study are expected to prevent damage to farms due to downtime caused by mistakes, faults, and aging.

With the expansion of smart agriculture, wireless sensor networks are being increasingly applied. These networks collect environmental information, such as temperature, humidity, and CO₂ rates. However, if a faulty sensor node operates continuously in the network, unnecessary data transmission adversely impacts the network. Accordingly, a data-based fault-detection algorithm was implemented in this study to analyze data of sensor nodes and determine faults, to prevent the corresponding nodes from transmitting data; thus, minimizing damage to the network. A cloud-based “farm as a service” optimized for smart farms was implemented as an example, and resource management of sensors and actuators was provided using the oneM2M common platform. The effectiveness of the proposed fault-detection model was verified on an integrated management platform based on the Internet of Things by collecting and analyzing data. The results confirm that when a faulty sensor node is not separated from the network, unnecessary data transmission of other sensor nodes occurs due to continuous abnormal data transmission; thus, increasing energy consumption and reducing the network lifetime.