Smart Farming Applications Research Articles

A Developed IoT Platform-Based Data Repository for Smart Farming Applications

Generally, it is possible to increase agricultural output while decreasing the time required for human oversight by automating routine tasks. In this work, the Internet of things (IoT) played a vital role in designing a platform to monitor a farm wirelessly, reducing human involvement, allowing remote observing, and remote control of the design using a public IP address based cross-platform, Apache, MySQL, PHP and Perl (XAMPP) Apache package. A cloud is appealing when a wireless sensor network generates a lot of data. Cloud-based wireless communication systems are being tested to monitor and manage a set of sensors and actuators to estimate paddy (rice) water requirements in a particular location. The proposed design shows robust interaction between two microcontrollers to deal with different sensors and simultaneously act as a WiFi unit. The row data obtained from the sensors is uploaded to the cloud through specific Hypertext Preprocessor (PHP) files to store and fetch the data from the database. Through the programming method, the system focuses on tracking the paddy growing value and the amount of water available in the soil, which should be around (10 Kpa) for an optimum paddy environment. The results emphasized that 80% of water is retained when a maximal 10 Kpa of soil moisture is achieved.

Internet of Things and Wireless Sensor Networks for Smart Agriculture Applications: A Survey

Internet of Things and Wireless Sensor Networks for Smart Agriculture Applications: A Survey

IoT-Smart Agriculture: Comparative Study on Farming Applications and Disease Prediction of Apple Crop using Machine Learning

Recently, the Internet of Things has emerged as an encouraging technology that is scaling up new heights towards the modernization of real word physical objects into smarter devices in several domains. Internet of Things (IoT) based solutions in agriculture drives farming into a smart way through the proliferation of smart devices to enhanced production with minimal human involvement. This paper presents a comprehensive study of the role of IoT in prominent applications of farming, wireless communication protocols, and the role of sensors in precision farming. In this research article, the existing frameworks in IoT-based agriculture systems with relevant technologies are presented. Furthermore, the comparative analysis of the apple disease prediction system concerning different types of disease found in the apple crop are discussed. In addition, this paper presents the contributions made by numerous researchers over the past few years in the apple disease prediction system. The aim of this research is to support the development of smart agriculture applications that would be helpful in precision farming for the optimization of resources with the help of IoT in agriculture and early disease prediction in apple crops.

Plant Growth Monitoring: Design, Fabrication, and Feasibility Assessment of Wearable Sensors Based on Fiber Bragg Gratings

Global climate change and exponential population growth pose a challenge to agricultural outputs. In this scenario, novel techniques have been proposed to improve plant growth and increase crop yields. Wearable sensors are emerging as promising tools for the non-invasive monitoring of plant physiological and microclimate parameters. Features of plant wearables, such as easy anchorage to different organs, compliance with natural surfaces, high flexibility, and biocompatibility, allow for the detection of growth without impacting the plant functions. This work proposed two wearable sensors based on fiber Bragg gratings (FBGs) within silicone matrices. The use of FBGs is motivated by their high sensitivity, multiplexing capacities, and chemical inertia. Firstly, we focused on the design and the fabrication of two plant wearables with different matrix shapes tailored to specific plant organs (i.e., tobacco stem and melon fruit). Then, we described the sensors' metrological properties to investigate the sensitivity to strain and the influence of environmental factors, such as temperature and humidity, on the sensors' performance. Finally, we performed experimental tests to preliminary assess the capability of the proposed sensors to monitor dimensional changes of plants in both laboratory and open field settings. The promising results will foster key actions to improve the use of this innovative technology in smart agriculture applications for increasing crop products quality, agricultural efficiency, and profits.

Electromechanical Properties of a Hybrid Broadband Wind Energy Harvester for Smart Agriculture Monitoring in the Loess Plateau

Wind, as a ubiquitous energy, is an important power source for intelligent monitoring systems in smart agriculture applications, and its efficient collection can greatly improve the long-term performance of monitoring systems. However, it is difficult to achieve the broadband and efficient harvesting of wind energy using the existing energy collection technology. Herein, a broadband energy conversion device (ECD), consisting of a triboelectric nanogenerator (TENG) and an electromagnetic generator (EMG), is proposed for wind energy collection under different wind speeds. The introduction of an optimized Scotch yoke mechanism greatly improves the utilization of wind energy by the TENG, thus reducing energy dissipation. Moreover, the addition of a deflector into the fan greatly reduces the start-up wind speed and improves the ability of the device to capture breeze energy. By doping multi-walled carbon nanotubes, the output voltage and current of the TENG can be improved by 108.89% and 116.61%, respectively. Furthermore, the adopted all-directional conductive foam can greatly prolong the service life of the ECD. The peak power of the ECD is 68.49 mW at 9.6 m/s, with the EMG and TENG producing approximately 64.80 mW and 3.69 mW, respectively. The proposed ECD provides a new technical strategy for the practical application of wind energy harvesters.

Smart Agriculture Solutions for Vietnamese Farmers

Agriculture is the back bone of Vietnam and more than 70% of people in Vietnam depend on agriculture. Nowadays, agriculture crops are affected due to many environmental changes. To overcome this problem, I design and prototype a wireless sensor and actuator network for smart agriculture application. The aim of this work is to be able to capture useful data to start predicting measurements and events that could help farmers and specialists to save time and money. I propose two solutions for smart agriculture. In the first solution, wireless sensor and actuator nodes monitor multiple environmental parameters and transmit the sensor data to a server via the internet. Users can monitor these environmental parameters from anywhere via the internet. In the second solution, wireless sensor and actuator nodes send data to a local computer. This computer is deployed in a technical room. The experiments show that both solutions operate well in real conditions.

Implementing a Compression Technique on the Progressive Contextual Excitation Network for Smart Farming Applications

The utilization of computer vision in smart farming is becoming a trend in constructing an agricultural automation scheme. Deep learning (DL) is famous for the accurate approach to addressing the tasks in computer vision, such as object detection and image classification. The superiority of the deep learning model on the smart farming application, called Progressive Contextual Excitation Network (PCENet), has also been studied in our recent study to classify cocoa bean images. However, the assessment of the computational time on the PCENet model shows that the original model is only 0.101s or 9.9 FPS on the Jetson Nano as the edge platform. Therefore, this research demonstrates the compression technique to accelerate the PCENet model using pruning filters. From our experiment, we can accelerate the current model and achieve 16.7 FPS assessed in the Jetson Nano. Moreover, the accuracy of the compressed model can be maintained at 86.1%, while the original model is 86.8%. In addition, our approach is more accurate than ResNet18 as the state-of-the-art only reaches 82.7%. The assessment using the corn leaf disease dataset indicates that the compressed model can achieve an accuracy of 97.5%, while the accuracy of the original PCENet is 97.7%.

The smart agriculture applications (current and future)

Smart agriculture applications (monitoring, sensing, automation and control) of micro-climate and environmental conditions for different agriculture production sectors and scales, decision-makers and researchers need to take it into consideration to strengthen the efforts of mitigation and adaption of climate change impacts as well as maximize the natural resources use efficiencies and food production. Motivate the farmers to implement smart agriculture applications, especially in developed and poor countries, strong cooperation for technology transfer and build up the technology infrastructure of information and communication (ICT) plus the internet of things (IoT).

Internet of Things Implementation for Development of Smart Agriculture Applications

The era of the industrial revolution 4.0 is an era that puts forward the concept that puts forward the Internet of Things (IoT). This concept changes from object-oriented to smart objects and makes connections not limited by time and space. The agricultural sector is one sector that adapts to the direction of automation and data processing with the development of a smart agriculture system. The purpose of this research is to change the pattern of agricultural land management from conventional concepts to become much more productive and efficient. The utilization of internet of things technology is carried out through a control and monitoring system. Manager agricultural land can regulate and predict crop yields so that agricultural productivity is more optimal. Some of the supporting devices for the agriculture system are the ESP microcontroller 8266, soil moisture sensor, temperature sensor, humidity sensor DHT-11, and jet pump mini. Sketch Arduino IDE (Integrated Development Environment) as a programming application and interface for the ESP 8266 device. The development of this smart agriculture application uses the method Design Science Research Method (DSRM). The testing phase is carried out with function and performance tests by using the ThingView mobile device.

A deep learning generative model approach for image synthesis of plant leaves.

A well-known drawback to the implementation of Convolutional Neural Networks (CNNs) for image-recognition is the intensive annotation effort for large enough training dataset, that can become prohibitive in several applications. In this study we focus on applications in the agricultural domain and we implement Deep Learning (DL) techniques for the automatic generation of meaningful synthetic images of plant leaves, which can be used as a virtually unlimited dataset to train or validate specialized CNN models or other image-recognition algorithms. Following an approach based on DL generative models, we introduce a Leaf-to-Leaf Translation (L2L) algorithm, able to produce collections of novel synthetic images in two steps: first, a residual variational autoencoder architecture is used to generate novel synthetic leaf skeletons geometry, starting from binarized skeletons obtained from real leaf images. Second, a translation via Pix2pix framework based on conditional generator adversarial networks (cGANs) reproduces the color distribution of the leaf surface, by preserving the underneath venation pattern and leaf shape. The L2L algorithm generates synthetic images of leaves with meaningful and realistic appearance, indicating that it can significantly contribute to expand a small dataset of real images. The performance was assessed qualitatively and quantitatively, by employing a DL anomaly detection strategy which quantifies the anomaly degree of synthetic leaves with respect to real samples. Finally, as an illustrative example, the proposed L2L algorithm was used for generating a set of synthetic images of healthy end diseased cucumber leaves aimed at training a CNN model for automatic detection of disease symptoms. Generative DL approaches have the potential to be a new paradigm to provide low-cost meaningful synthetic samples. Our focus was to dispose of synthetic leaves images for smart agriculture applications but, more in general, they can serve for all computer-aided applications which require the representation of vegetation. The present L2L approach represents a step towards this goal, being able to generate synthetic samples with a relevant qualitative and quantitative resemblance to real leaves.

Bluetooth low energy indoor localization for large industrial areas and limited infrastructure

Systems using Bluetooth Low Energy (BLE) communication are widely used in various industrial applications, which benefit from the efficient low-power operation and pervasive availability of BLE transceivers in a large number of devices and sensors. It is no different in Smart Factory and Smart Farming settings, where BLE systems are already used for asset monitoring, management, tracking, and localization. The existing BLE-based localization systems aim at high accuracy and precision using radio propagation models and multilateration, or radio fingerprinting. Both methods use the received signal strength indicator (RSSI) measurements and the dependency of RSSI on the distance between the transmitter and the receiver. Because RSSI measurements are highly inaccurate and susceptible to radio propagation phenomena, high localization accuracy is only possible if the anchor devices are densely deployed, and the propagation conditions are stable. Unfortunately, these requirements do not hold in industrial systems where radio propagation is complex, the number of anchors is limited, and propagation conditions change because the environment is dynamic. Therefore, localization methods for industrial applications have to balance system complexity (e.g., anchor density, energy cost) and localization accuracy so that practical benefits can be attained. This paper presents a set of localization algorithms that require limited infrastructure, have low complexity, and can provide valuable location information at low costs. The proposed algorithms were verified in a real-life Smart Farming application where BLE is used to monitor well-being of farm animals. The animal localization was integrated with the already existing system and proved to operate reliably despite system-level constraints and varying propagation conditions — interference, signal attenuation, and unavailability of raw radio signal measurements. The proposed approaches allow localizing animals in the cowshed of 1600m2, using only 10 anchors with an average positioning error below 8m. The algorithms are based on signal strength measurement, so they can be applied to other radio technologies.

Digital agriculture killjoy: Happy objects and cruel quests for the good life

AbstractThis article brings together phenomena not often connected in the rural studies cannon to show an underlying relationality connecting digital agriculture, conceptions of the good life and pursuits of happiness. Drawing from the scholarship of Sara Ahmed and Lauren Berlant, Agriculture 4.0 technologies are described as ‘cruel’ happiness pointers. These platforms are shown to direct actors towards happiness while potentially accelerating the very conditions that produced the problems they are promising to solve. Highlighting conceptions of the good life that are fluid, contested and multiple, which have connections to sayings and doings associated with these platforms, the analysis makes visible norms and values animating the so‐called digital revolution. At the same time, the article interrogates what these changing affective politics means for the future of farming and farm‐based identities, at least in Western countries. The data analysed, from individuals who had adopted smart farming applications in the US, were collected from focus groups and personal interviews, the latter conducted pre (2019) and post coronavirus (COVID‐19) outbreak (2020 and 2021).

Wireless communication protocols in smart agriculture: A review on applications, challenges and future trends

IoT based smart agriculture systems are important for efficient usage of lands, water, and energy resources. Wireless communication protocols constitute a critical part of smart agriculture systems because the fields, in general, cover a large area requiring system components to be placed at distant locations. There are various communication protocols with different features that can be utilized in smart agriculture applications. When designing a smart agriculture system, it is required to carefully consider the features of possible protocols to make a suitable and optimal selection. Therefore, this review paper aims to underline the specifications of the wireless communication protocols that are widely used in smart agriculture applications. Furthermore, application-specific requirements, which may be useful during the design stage of the smart agriculture systems, are highlighted. To accomplish these aims, this paper compares the technical properties and investigates the practical applications of five different wireless communication protocols that are commonly used in IoT applications: ZigBee, Wi-Fi, Sigfox, NB-IoT, and LoRaWAN. In particular, the inconsistencies in the technical properties of these protocols reported in different resources have been highlighted and the reason for this situation has been discussed. Considering the features offered by the protocols and the requirements of smart agriculture applications, the appropriateness of a particular protocol to a particular smart agriculture application is examined. In addition, issues about cost, communication quality, and hardware of the five protocols have been mentioned. The trending technologies with high potential for the future applications of smart agriculture have been introduced. In this context, the relation of the technologies like aerial systems, cellular communication, and big data analytics with wireless have been specified. Finally, the leading protocol and the smart agriculture application area have been highlighted through observing the year-based distribution of the recent publications. It has been shown that usage of LoRaWAN protocol has become more widespread in recent years.

Downscaling CLDAS Soil Moisture Product by Integrating Sentinel-1 and Sentinel-2 Data over Agricultural Area

Soil Moisture (SM) plays a key role in the energy exchange between the atmosphere and the land surface. Most of the SM products retrieved from satellite remote sensing data are not suitable for drought monitoring and irrigation management in smart agriculture applications due to their coarse spatial resolution. We propose an SM downscaling method named Water Cloud Change Detection (WCCD) that effectively combines the Water-Cloud Model (WCM) and the Change Detection Method (CDM) to downscale the China Land Data Assimilation System soil moisture (CLDAS_SM, 6000-m resolution) product. The WCM is used to retrieve the soil backscattering at a fine spatial resolution by deducting the canopy backscattering from the surface total backscattering, and the linear regression relationship between soil backscattering and CLDAS_SM is established for each pixel at the coarse scale under the assumption that the surface roughness does not change for dozens of days. The performance of the algorithm is tested in an agricultural crop region in Hebei province of China with Sentinel-1 and Sentinel-2 images. The validation results show that the downscaled SM at different spatial resolutions are in good agreement with the in-situ measurements with the correlation coefficient (R) higher than 0.71 and the Root Mean Squared Error (RMSE) lower than 0.042 cm3×cm−3.

Hybridized energy harvesting device based on high-performance triboelectric nanogenerator for smart agriculture applications

Smart agriculture can be deemed as the deep cross-boundary integration of modern information technologies such as Internet of things (IoTs), intelligent equipment, and big data with agriculture, among which the numerous distributed sensors play a vital role in providing precise planting management. However, the lack of efficiency and low-cost energy harvesting approaches to power distributed sensor nodes has become a severe challenge. This challenge will seriously inhibit the development of smart agriculture. Herein, a hybridized energy harvesting device (HEHD) for capturing wind and solar energy was designed by combining two electromagnetic generators (EMGs), two triboelectric nanogenerators (TENGs), and two solar cells (SCs) to enable environmental energy collection. The rotation motion can be transformed into translational motion by introducing a transverse connector to link TENG and EMG, which favors the durability of the TENG. The output performance of TENGs and EMGs increases with increasing wind speed, and the open-circuit voltage (VOC) and short-circuit current (ISC) of the individual TENG and EMG can reach up to nearly 570 V, 40 μA, and 0.8 V, 1.85 mA at the 7 ms−1 wind speed, respectively. The self-powered temperature and humidity (Temp&Humid) monitoring system was established by combining the HEHD, a self-developed mobile phone application and a commercial Temp&Humid sensor, which can realize remote monitoring and multi-points connection of farmland environmental Temp&Humid data through the Internet. Moreover, a farm peripheral security alarm system based on the HEHD was constructed to achieve passive remote infrared monitoring. This work makes a beneficial attempt to realize self-powered sensor nodes, indicating broad potential for the use of TENGs in smart agriculture applications.

An Electromagnetic Wind Energy Harvester Based on Rotational Magnet Pole-Pairs for Autonomous IoT Applications

In this paper, we report a wind energy harvesting system for Internet of Things (IoT)-based environment monitoring (e.g., temperature and humidity, etc.) for potential agricultural applications. A wind-driven electromagnetic energy harvester using rotational magnet pole-pairs (rotor) with a back-iron shield was designed, analyzed, fabricated, and characterized. Our analysis (via finite element method magnetic simulations) shows that a back-iron shield enhances the magnetic flux density on the front side of a rotor where the series connected coils interact and convert the captured mechanical energy (wind energy) into electrical energy by means of electromagnetic induction. A prototype energy harvester was fabricated and tested under various wind speeds. A custom power management circuit was also designed, manufactured, and successfully implemented in real-time environmental monitoring. The experimental results show that the harvester can generate a maximum average power of 1.02 mW and maximum power efficiency of 73% (with power management circuit) while operated at 4.5 m/s wind speed. The system-level demonstration shows that this wind-driven energy harvesting system is capable of powering a commercial wireless sensor that transmits temperature and humidity data to a smartphone for more than 200 min after charging its battery for only 10 min. The experimental results indicate that the proposed wind-driven energy harvesting system can potentially be implemented in energetically autonomous IoT for smart agriculture applications.

Application of Internet of Things and Sensors in Healthcare.

The Internet of Things (IoT) is an innovative technology with billions of sensors in various IoT applications. Important elements used in the IoT are sensors that collect data for desired analyses. The IoT and sensors are very important in smart cities, smart agriculture, smart education, healthcare systems, and other applications. The healthcare system uses the IoT to meet global health challenges, and the newest example is COVID-19. Demand has increased during COVID-19 for healthcare to reach patients remotely and digitally at their homes. The IoT properly monitors patients using an interconnected network to overcome the issues of healthcare services. The aim of this paper is to discuss different applications, technologies, and challenges related to the healthcare system. Different databases were searched using keywords in Google Scholar, Elsevier, PubMed, ACM, ResearchGate, Scopus, Springer, etc. This paper discusses, highlights, and identifies the applications of IoT healthcare systems to provide research directions to healthcare, academia, and researchers to overcome healthcare system challenges. Hence, the IoT can be beneficial by providing better treatments using the healthcare system efficiently. In this paper, the integration of the IoT with smart technologies not only improves computation, but will also allow the IoT to be pervasive, profitable, and available anytime and anywhere. Finally, some future directions and challenges are discussed, along with useful suggestions that can assist the IoT healthcare system during COVID-19 and in a severe pandemic.

A Multiwall Path-Loss Prediction Model Using 433 MHz LoRa-WAN Frequency to Characterize Foliage’s Influence in a Malaysian Palm Oil Plantation Environment

Palm oil is the main cash crop of tropical Asia, and the implementation of LPWAN (low-power wide-area network) technologies for smart agriculture applications in palm oil plantations will benefit the palm oil industry in terms of making more revenue. This research attempts to characterize the LoRa 433 MHz frequency channels for the available spreading factors (SF7-SF12) and bandwidths (125 kHz, 250 kHz, and 500 kHz) for wireless sensor networks. The LoRa channel modeling in terms of path-loss calculation uses empirical measurements of RSS (received signal strength) in a palm oil plantation located in Selangor, Malaysia. In this research, about 1500 LoS (line-of-sight) and 300 NLoS (non-line-of-sight) propagation measurement data are collected for path-loss prediction modeling. Using the empirical data, a prediction model is constructed. The path-loss exponent for LoS propagation of the proposed prediction model is found to be 2.34 and 2.9 for 125–250 kHz bandwidth and 500 kHz bandwidth, respectively. Again, for the NLoS propagation links, the attenuation per trunk is found to be 7.58 dB, 7.04 dB, 5.35 dB, 5.02 dB, 5.01 dB, and 5 dB for SF7-SF12, and the attenuation per canopy is found to be 9.32 dB, 7.96 dB, 6.2 dB, 5.89 dB, 5.79 dB, and 5.45 dB for SF7-SF12. Moreover, the prediction model is found to be the better choice (mean RMSE 2.74 dB) in comparison to the empirical foliage loss models (Weissberger’s and ITU-R) to predict the path loss in palm oil plantations.

Cotton-assisted dual rotor-stator triboelectric nanogenerator for real-time monitoring of crop growth environment

Employing clean and sustainable wind energy to build a sensor system is of critical importance for the currently thriving smart agriculture and the goals of carbon peaking and carbon neutrality, as an essential driving force for rural revitalization. Triboelectric nanogenerators (TENGs) exhibit broad applications in sensor networks as power sources owing to the advantages of irregular and distributed energy harvesting. However, TENGs suffer from the problems of limited average power density and durability, which motivate us to design the soft-contact flower-bud array cotton-based TENG (SFC-TENG) with the rotation of a double rotor-stator structure for harvesting wind energy. The adopted cellulose-rich cotton-assisted soft-contact and double rotor-stator structure with multiple contact areas endow SFC-TENG with excellent performance in triboelectrification, which is beneficial for reducing frictional resistance and prolonging the lifetime. The assembled TENG device reveals excellent output performances with high open-circuit voltage of 2500 V, short circuit current of 85 μA, and maximum output power of 80 mW. Especially, high durability is achieved with no significant degradation of output performance after 320,000 cycles. The prominent properties confirm that the SFC-TENG is feasible for powering smart farming in night lighting, pH detection, and temperature/humidity monitoring. This work provides an effective strategy combining design of the double rotor-stator structure with the flexible contact of cotton, which is of great inspiration for the exploitation of high-performance TENGs for smart agriculture application.

Smart Farming Application for Protecting Animal Intrusion Using AI

Abstract: Agriculture automation has been on the rise using, among others, Deep Neural Networks (DNN) and IoT for the development and deployment of numerous controlling, monitoring and shadowing operation at a fine-granulated position. In this fleetly evolving scenario, managing the relationship with the rudiments external to the farming ecosystem, similar as wildlife, is a applicable open issue. One of the main concerns of present cultivators is guarding crops from wild creatures’ attacks. There are different traditional approaches to address this problem which can be murderous (e.g., shooting, trapping) and non-lethal (e.g., scarecrow, chemical repellents, organic substances, mesh, or electric walls). Nonetheless, some of the traditional styles have environmental pollution effects on both humans and ungulates, while others are veritably precious with high conservation costs, with limited trustability and limited effectiveness. In this project, we develop a system, that combines AI Computer Vision using DCNN for detecting and recognizing animal species, and specific ultrasound emigration (i.e., different for each species) for repelling them. The edge computing device activates the camera, and executes its DCNN software to determine the target, and once the animal is detected, it sends back a communication to the Animal Repelling Module including the type of ultrasound to be generated for the specific division of the animal.