An Enhanced Automation Analysis for Structural Algorithm in Agro-Industries Using IoT ^†

Abstract

The Internet of Things (IoT) based structural algorithm for automatic agriculture refers to the system of using powerful real-time data collected from a variety of sensors with software and analytics to autonomously manage agro-ecosystems. This algorithm can be used to monitor environments, analyze data and use this knowledge to take specific actions to help farmers and producers maximize their production and profitability. This algorithm provides an unprecedented level of precision, accuracy and control over the agricultural environment, allowing greater efficiency and optimization in farming practices. It enables monitoring, scheduling, and control of different agro-ecosystem components, such as water, soil, fertilizer, light, humidity, temperature, soil pH and crop growth. The algorithm can also point to general trends and patterns in the environment, as well as offer timely advice to farmers in response to real-time conditions. The algorithm is also capable of automatically diagnosing and responding to unexpected problems, which can help prevent costly mistakes and excessive waste of water, fertilizer, energy, etc.

1. Introduction

Agriculture is a cornerstone of civilization, providing the food and fiber necessary for people to survive and live comfortably [1]. The primary benefit of automatic agriculture is its automation, taking the laborious tasks out of farming, allowing machines and robotics to take care of much of the manual work. Automation reduces the cost of entering into agriculture and opens up opportunities to reach new markets [2]. Automated techniques mean that pesticides, herbicides and fertilizers can be used in much more precise quantities, with machines also being able to identify the potential diseases faster than humans. This ensures that crops are kept healthy and yields are maximized, while the environment is also safeguarded. This trend appears to be set to continue as technological advancements allow for ever more accurate automatic agriculture techniques [3]. Agricultural automation is a rapidly developing field of technology designed to improve agricultural efficiency [4]. Robots can be used to harvest crops such as wheat, corn and soybeans, as well as specialty crops like cherries and apples. They are able to travel through fields at different speeds, cutting and gathering with accuracy and efficiency. Agricultural automation is also helping farmers to manage their resources and increase yields with more precise control [5,6]. IoT farming, or “farming with data”, uses the data from weather sensors to optimize plant growth. Farmers can use the data to monitor water usage and adjust irrigation schedules, or to fine-tune fertilizer application. Agricultural automation technology is revolutionizing the way that farmers are able to manage their farms, increase their yields, and keep up with modern advances in agriculture. As the technology continues to develop, it will provide even more opportunities for farmers to maximize their efficiency and profitability. The main contributions of this research are the following:

• Increased agricultural efficiency: Automation in agriculture can reduce the time and labor required monitoring crops. This increases the efficiency of farming and reduces the amount of errors and omissions due to human labor.
• Improved output quality and accuracy: automation can increase accuracy in the harvesting process, leading to better quality produce.
• Reduced water and pesticide use: automation can help reduce water and pesticide use, leading to a lower environmental impact on the land.
• Improved yields: automation can lead to increased yields, as it is more precise and efficient than manual labor [7,8,9].

2. Materials and Methods

Automatic systems rely on precise information that can easily be altered by external factors, such as weather or soil conditions. If the data are inaccurate, the system could produce outcomes far from what is desired, leading to significant losses. Additionally, automated agriculture systems rely heavily on sensors, which need to be precise and up-to-date in order to ensure accurate data [10]. As the technology is still relatively new, the cost can be quite prohibitive for many agricultural producers. The automated systems rely heavily on digital infrastructure, which may not be well-developed in many areas [11]. Without proper internet connections and reliable digital equipment, the reliability of these systems could be compromised, leading to a reduced yield and potential financial losses. The automated agriculture technology has been an incredible advancement for many aspects of the agricultural industry; there are some significant problems that also accompany its use [12]. The use of automated machinery in farming has resulted in an increase in soil erosion and disruption of the natural environment. Farming technology that uses machinery can damage the environment by disturbing the natural topography of the land, compacting the soil, and introducing contaminants to the environment. This can, in turn, disrupt natural growing cycles and lead to crop failure [13,14,15]. This is because automated machinery can reduce the need for manual labor on farms, leading to job cuts and the risk of unemployment. Moreover, even when automated machinery is used to produce agricultural products, the quality of the products often remains questionable [16]. This leads to the inability for these farmers to compete with large-scale agricultural operations, furthering the gap between large and small-scale agricultural production. The automated agriculture technology has been an incredible advancement for many aspects of the agricultural industry; it has also led to a number of significant problems [17,18]. These include soil erosion and disturbance of the natural environment, a reduction in the availability of jobs for workers in the agricultural sector, a decrease in the quality of agricultural products, and unaffordability for small-scale farmers [19,20].

Proposed Model

The IoT-based structural algorithm for automatic agriculture is a new technology that facilitates the monitoring and management of large agricultural areas using sophisticated algorithms and sensor networks.

$$v″(u)=u^v\underset{v\to 0}{\lim }\frac{u^v-1}{v}$$

(1)

$$v″(u)=\underset{u\to 0}{\lim }\frac{u(v+u)-u(v)}{v}$$

(2)

$$v″(u)=\underset{v\to 0}{\lim }\frac{u^{v+u}-u^v}{v}=\underset{v\to 0}{\lim }\frac{u^v{u}^u-u^v}{v}$$

(3)

$$v″(u)=\underset{u\to 0}{\lim }\frac{u^v(u^v-1)}{v}=u^v\underset{v\to 0}{\lim }\frac{v^u-1}{u}$$

(4)

Stage. 1: The first stage towards constructing an effective IoT-based structural algorithm for automated agriculture is to identify the necessities and requirements of the system. To do this, a thorough understanding of the factors involved in the process must be acquired. The data gathered should include information such as crop types, soil type, soil-moisture levels, climate information, local weather conditions, and existing agricultural practices. Once the data are acquired, they should be analyzed in order to identify the best methods and practices for the particular environment.

Stage. 2: The second stage is to develop the algorithms. This phase involves constructing a set of algorithms that accurately simulate the conditions required for a successful agricultural process. The most important components of the algorithms include planting patterns, harvesting patterns, irrigation, fertilization, pest management, weed control and other such factors. Additionally, simulations should also be used to ensure that the agricultural conditions remain within a certain range of values for optimum growth.

Stage. 3: The third stage is to construct sensors and devices that can measure and monitor the conditions necessary for automatic agriculture. This includes temperature, humidity, soil moisture levels, soil nutrient levels and so on. Additionally, a communication network should be established which will enable the transfer of data between the sensors and the computer interface.

Stage. 4: The fourth stage is to establish a system of control that will enable the control and monitoring of the various factors which are necessary for agriculture. This should include a system of automation, which will enable automated processes such as watering, planting, harvesting, fertilizing and pest management. Additionally, the control system should also be able to alert the users of any potential anomalies in the environment.

$$\frac{du}{dv}=u\ast \ln (v)$$

(5)

$$\frac{du}{dv}=v^u\ast \ln (u)$$

(6)

The collected data are used to inform the algorithm which then makes decisions about the optimal planting and harvesting of crops according to the season, soil conditions, weather, etc. The functional block diagram is shown in the following Figure 1.

This automated process allows for a more efficient use of resources, reduced water and fertilizer usage, increased crop yields, and easier management of the entire agricultural operation. As more data are collected on the performance of the algorithm,

$$\frac{\partial u}{\partial v}=\frac{\partial }{\partial v}(v^u\ast \sin Vu)$$

(7)

$$\frac{du}{dv}=\cos Vu\ast \frac{d}{dv}(v^u)+V^u\frac{d}{dv}(\cos Vu)$$

(8)

It uses sensors to collect data related to soil, humidity, light, temperature, and other environmental variables.

$$\frac{du}{dv}=\cos Vu\ast v^u+v^u\ast \sin Vu\ast \frac{d}{dv}(Vu)$$

(9)

$$\frac{du}{dv}=v^u\cos Vu+v^u\sin Vu\ast v$$

(10)

Other benefits to the use of SAFA include improved crop monitoring and precise data collection. In a traditional farming system, a lot of manual labor is required in the form of data collection and analysis.

3. Results

The proposed IoT-based Structural Algorithm (ISA) has compared with the existing Agricultural Traceability Model (ATM), Optimal Goal Point Determination Algorithm (OGPDA), Artificial Intelligence Approach (AIA) and Smart Agriculture Framework (SAF). Here, Python has the simulation tool used to execute the results.

3.1. Computation of Positive Likelihood Ratio

The Positive Likelihood Ratio (PLR) is an algorithm used to determine the probability of a given event or outcome, such as a particular crop yield. This algorithm is particularly useful in the realm of IoT-based automated agriculture, where the goal is to accurately predict the yield of a given crop while also providing feedback on crop-growth trends and recommendations on how to best proceed.

Figure 2 shows the comparison of the positive likelihood ratio. In a comparison, the proposed ISA reached an 86.12% positive likelihood ratio. The existing ATM obtained 67.81%, OGPDA reached 53.49%, AIA obtained 83.47% and SAF obtained 58.21% positive likelihood ratios.

3.2. Computation of Negative Likelihood Ratio

The Negative Likelihood Ratio (NLR) IoT-based structural algorithm for automatic agriculture is a method of computing the performance of on-farm systems. It evaluates the accuracy of the system’s decisions by comparing the number of correct decisions to the number of incorrect ones.

Figure 3 shows the comparison of the negative likelihood ratio. In a comparison, the proposed ISA reached an 87.08% negative likelihood ratio. The existing ATM obtained 62.72%, OGPDA reached 52.46%, AIA obtained 85.17% and SAF obtained 61.47% negative likelihood ratios.

3.3. Computation of Specificity

The specificity of a structural algorithm for automated agriculture is an important metric to consider when determining the accuracy of the system. This metric measures the precision of the algorithm, or the number of false positives (false alarms) the system produced.

Figure 4 shows the comparison of specificity. In a comparison, the proposed ISA reached 87.71% specificity. The existing ATM obtained 81.98%, OGPDA reached 54.33%, AIA obtained 71.26% and SAF obtained 57.73% specificity.

4. Conclusions

The IoT-based structural algorithm for automatic agriculture is a system that utilizes sensor-equipped devices, networked computers, and IoT technology to automate the process of cultivation, maintenance, and harvesting of crops. This system is designed to collect real-time information from a variety of sources, such as temperature, humidity, soil moisture, air pressure, and satellite imagery, to analyze and make decisions about the current state of the plants and the surrounding environment. With this information, the system can determine when and how to enter and adjust cultivation and/or maintenance activities to optimize the growth of crops. Furthermore, the system can also monitor the crop’s health in order to preemptively detect any potential issues and ensure that crops do not get damaged due to environmental changes. The future scope of the IoT-based structural algorithm for automatic agriculture is vast. With the advancement of technology and the development of better sensors, controllers, and other components of IoT, these algorithms will enable smarter farming practices.