**5. Current status progress of plant EOs and active compounds for sustainability in agriculture 4.0**

Using the status of applied plant EOs has not seen any concrete results in the continued practical use of farmers. Farmer occupation is mainly for life subsistence as well as lack of business processes in response to the policy of Agriculture 4.0. Therefore, the use of plant EO will be part of the chain of production processes until the plantation level to prepare the quality of raw materials. Additionally, active network information should be published to build the acceptance and confidence with the integration of agricultural knowledge, science, and technology together with the modern innovation. Network creation of a collaboration between researchers, entrepreneurs, and farmers in response to the development of intensive and comprehensive support mechanisms for agricultural innovation. The smart operating cycle based on agricultural database systems and network management organization will be helpful in efficient and comprehensive management that are shown in **Figures 5** and **6** [57–59]. Natural-productbased plant EOs can be applied for crop protection and management in the preliminary processes under farm operation. The operational results for pathogen detection rely on a more complex concept of visions as follows: data collection, processing, analysis, and publishing by smart platforms.

Sørensen et al. [60] indicated the conceptual model of a future farm management information system. Smart electronic tools with easy use and affordable prices are important factors in the real-time business decision-making for farmers under the highly competitive markets known as Farm Management Information Systems (FMIS). FMIS was integrated by various technologies and standard software packages such as information technology (IT), information systems (IS), and enterprise resource planning (ERP) in the form of information for data collection, processing, storing, and disseminating [61]. All of FMIS operations, information and multiple business functions with registration, interoperation, and communication in connection with

*Perspective Chapter: Perspectives on Pathogenic Plant Virus Control with Essential Oils… DOI: http://dx.doi.org/10.5772/intechopen.104639*

#### **Figure 5.**

*The smart operating cycle based on agricultural database systems and network management organization (figure was created from figure and table of reference number [57]).*

#### **Figure 6.**

*The pyramid of smart agricultural operating hierarchy. (figure was modified from figures and data of reference numbers [58, 59]).*

external systems were incorporated for a single integrated system creating [62]. Silvie et al. [63] showed that the developable knowledge base and a software prototype called Knomana knowledge-based system (KBS) for botanical species used as pesticide plant species for crop protection and pest management. The developable software prototype can be categorized the botanical species and their used parts for the protection of targeted organisms. It also shows the ranking of active plant species used in plant health for users and alternative information for selecting suitable methods and applications. Therefore, this software prototype also enables the novel knowledge production related to insect pest management (IPM) push-pull strategy and policy.

Pantazi et al. [64] applied the machine learning (ML) techniques connected to the internet of things (IoT) and wireless sensor network (WSN) for recognition of the environmental parameters. The results showed that this operation successfully distinguished between healthy and diseased plants. Interesting techniques, advanced technologies of automated and robotic systems are developed for precision agriculture and plant management in open fields. Plant health monitoring by remote sensing technique of unmanned aerial vehicle (UAV) or drone and ground robot (unmanned ground vehicle, UGV) can be applied for various agricultural management including crop monitoring [65], field mapping [66], plant population counting [67], weed management [68], biomass estimation [69], crop nutrient diagnosis [70], plant disease diagnosis and detection [71], and spraying [72]. Tillett and Hague [73] reported that a machine vision system could detect and remove weeds up to 80% as well as weeds could serve as susceptible hosts and reservoir alternative hosts of pathogens and their vectors. The imaging techniques have potential for various crop diseases detection including ground imagery, UAV imagery, and satellite imagery. Similarly, Mongkolchart and Ketcham [74] reported that the rice leaf color values of rice plant diseases were caused by infestations of the brown planthopper (BPH) and rice leaffolder (RLF) and were correctly detected with 73% accuracy. Xie et al. [75] found that the application of ground imagery with deep learning (DL) methods and extreme learning machine (ELM) classifier model could detect different tobacco diseases with accuracy ranging from 97.1 to 100%. In a similar way, Zhu et al. [76] reported that the ELM classifier could be applied to the hyperspectral image (HSI) for TMV detection on tobacco leaves with 98% accuracy. In the same context, Jin et al. [77] successfully classified between infected and healthy wheat head crops by HSI with 84.6% accuracy. Therefore, the roles of image analysis in robotic management, as well as robotic systems and human-robot collaboration (co-robot) systems, have the potential for greater efficiency and flexibility in open agricultural fields and environments. These knowledge systems have a high potential for crop disease prediction and detection in earlier stages by meteorological systems integrated with algorithms. In addition, robot systems can cooperate for one-stop service development with various detection methods such as next-generation sequencing (NGS) techniques [78], loop-mediated isothermal amplification (LAMP) [79], and lab-on-chip based on electrical impedance spectroscopy (EIS) [80].
