IoT-Enabled Soil Nutrient Analysis and Crop Recommendation Model for Precision Agriculture

Round 1

Reviewer 1 Report

This paper proposes an IoT-enabled Soil Nutrient Analysis and Crop Recommendation model for precision agriculture.  This model allows for the acquisition of the required soil nutrient data using its sensory system; The algorithm used is MSVM-DAG-FFO.

1. Your literature review on soil analysis based on different models is clear and exhaustive

2. Figures 4 and 5 need further clarification and detail.

3. In table 5, you have compared the performance of the algorithms implemented in precision farming in terms of accuracy, and you have observed that the accuracy rate of the proposed algorithm is better than the other algorithms. But you did not mention in any way the type of crop chosen or the data from different sensors used. Are the results obtained applied to the same types of data? 

4. Presence of redundancy in the article

5. Conclusion too short, to be developed

Author Response

Revision lists and replies to the reviewer’s comments

Re: Manuscript ID: computers-2248713

Type: regular

Title: IoT Enabled Soil Nutrient Analysis and Crop Recommendation Model for Precision Agriculture

Authors: Murali Krishna Senapaty, Abhishek Ray, Neelamadhab Padhy

 

We are grateful to the Editor and the three anonymous reviewers for their helpful comments and suggestions on our manuscript. The corresponding revisions and replies to the manuscript have made and listed as follows.

 

The comments and replies:

Reviewer #1:

1. Your literature review on soil analysis based on different models is clear and exhaustive

Our Reply:

Thank you for your valuable comments Sir.

1. Figures 4 and 5 need further clarification and detail.

Our Reply:

Frist of all, thank you sir for the important points identified in our manuscript, According to your comments, we have revised the manuscript carefully by adding explanation on figure 4 and figure 5.

 

Updated Content:

3.3.4. MSVM-DAG-FFO algorithm

A novel approach is used for MSVM-based classification using Directed Acyclic Graph and Fruit Fly Optimization based parameter optimization. The main objective of this approach is to maximise the separation between the data points by identifying the minimum distance towards the hyperplane.

Here we break down the multiclass SVM into multiple one-vs-rest binary classifications. These binary SVM methods are executed using Direct Acyclic Graph. Here, the FFO algorithm is used to tune the MSVM model. We made a comparative analysis between this novel method and other methods such as linear Support Vector Machine (SVM), SVM Kernel Model and Decision Tree. It is observed that the FFO algorithm can be used in many applications of classification for selecting the optimised kernel function. The MSVM with FFO allows to classify the soil minerals and the recommendation of suitable crops more accurately in comparison with other methods.

 Figure 4. presents a graph on the optimised classification of soil minerals based on four crop categories using the MSVM-DAG-FFO method. Here the classes A,B,C,D  identifies crops Cotton, Ground Nut, Maize and Rice respectively. For each execution of SVM a suitable function shall be selected out of the five kernel functions: linear, non-linear, polynomial, the radial bias function, and the sigmoid function. The Fruit Fly Optimization algorithm is used to choose a suitable kernel function while minimising the range of soil minerals as per crops.

 

Class A : Cotton Class B : Ground Nut Class C: Maize Class D: Rice
Figure 4. MSVM-DAG-FFO

 

 

 

 

 

 

 

 

In Figure 5. The flowchart briefly elaborated about implementation of proposed algorithm MSVM-DAG-FFO on pre-processed crop-wise real-time soil nutrient dataset from cloud storage. Here we have considered dataset based on 4 crop classes and applied Multi Class SVM by recursive class of one-vs-rest SVM as per the no. of classes. For each call of SVM on a subset the Fruit Fly Optimization method is invoked which allows to choose the best kernel function by finding the optimal value of kernel using distance function dist_i=√(X(i)_m ² + Y(i)_m ²)  in which X and Y are initial value , m is the iteration number. Once the kernel function K_f is identified then it is applied in SVM. There by following the voting strategy between all the x_m data and sample x_t. Base on the voting the SVM called recursively either to left subset or to right subset. This recursive process continues until it reaches to a single class which is verified using condition i=j. Once i=j the SVM returns the class R for the sample data x_t .

 

 

 

 

Figure 5. Flowchart of MSVM using DAG and FFO

 

Figure 6. Shows a group of four classes represented in Binary Graph to understand the flow of execution. The SVM starts execution from the first node, and it calls itself recursively for both of its subset nodes in the binary graph. The recursive execution continues until it reaches the leaf node, i.e., identifies a unique class, so the total set of classes is divided into two subsets each time.

 

Figure 6. Recursive Call of SVM using DAG

 

 

 

2. In table 5, you have compared the performance of the algorithms implemented in precision farming in terms of accuracy, and you have observed that the accuracy rate of the proposed algorithm is better than the other algorithms. But you did not mention in any way the type of crop chosen or the data from different sensors used. Are the results obtained applied to the same types of data? 

Our Reply:

Thank you Sir, We appreciate your valuable comment.  We have gone through the dataset sources, sensors used and the details on accuracy obtained by different authors in their research work and then made comparative analysis using a tabular format.

 

Updated Content:

A comparative analysis is done on performance of the proposed algorithm with other algorithms. It has been observed that the proposed model is the most suitable for predicting crops based on soil. Table 5 presents the State of the Art for comparison on usage of dataset, use of sensors, different algorithms used and their accuracy, along with the proposed algorithm and other algorithms implemented in precision farming. It has been observed that many different algorithms are implemented by researchers in different contexts and on different datasets such as: image datasets, soil datasets collected from agriculture departments and real-time data collections. We have implemented analysis on real-time data collection using the MSVM-DAG-FFO algorithm and achieved a better accuracy of 97.3% compared to others.

 

Ref. No.	Algorithm Applied	Best Algorithm	Accuracy Rate	Dataset Source	Sensors Used	Crops used/ Accuracy rate on variables
33	Extreme Learning Machine (ELM) along with the activation functions: sine-squared, gaussian radial basis, hyperbolic tangent, triangular basis.	Extreme Learning Machine (Average Accuracy Rate obtained for all minerals)	90%	North Central Laterite region datasets and Marathwada region datasets	No	90% accuracy in Soil pH classification
34	Support Vector Machine and Decision Tree methods	Decision Tree	94%	Real-time dataset collection done	Sensors for measuring pH , Humidity, moisture NPK value and microcontroller equipped with Cloud	87% accuracy in SVM for crop prediction, 90% accuracy in Decision Tree in crop prediction
35	C 4.5 Decision Tree	C 5.0 ADT Classifier for Soil Fertility Prediction	92%	Soil data for Virudhunagar District, Tamilnadu from http://soilhealth.dac.gov.in for 2015–2016. It contains soil testing report of 11 blocks of Virudhunagar District.	No	92% accuracy in Soil Fertility Level prediction and 95% accuracy in predicting crops such as Gingelly, Cotton, Onion, Sunflower, Block gram, Paddy, Groundnut, Sugarcane, Cumbu, Pulses, Vegetables
		C 5.0 ADT Classifier for   Crop Prediction	95%
36	Rule based Classifier	Rule based Classifier	91%	an ontology-based knowledge base is created for storing the details of soil composition with different minerals.	No	Accuracy 91% obtained by analyzing the 21 rules are strongly associated out of 28 rules that allows classifying soil composition
37	Artificial Neural Network, Fuzzy C-Means method, Support Vetcor Machine	Artificial Neural Network	88.27%	A dataset of 4049 leafs and Fruits images collected from  https://growabundant.com/nutrient-deficiencies/	No	Accuracy of 77% in thresholding scheme and 88.27% in Hue based scheme on leaf image analysis of crops for find nutrient deficiency.
38	SVM, SVM with Kernel, Decision Tree	SVM with Kernel	92%	1700 samples for soil NPK, pH, temperature, Humidity etc. collected from different parts of the  Chhattisgarh state.	Yes	rice, wheat, and sugarcane using micronutrients along with weather data
39	AdaSVM, SVM, AdaNaive and Naive Bayes	AdaNaive	96.52% for rice, 93.45% for cotton, 96.10% for sugarcane, 92.6% for black gram	climate data obtained from indianwaterportal.org and the crop production data obtained from faostat3.fao.org	No	Rice paddy, Cotton, Sugarcane, Groundnut and Blackgram
40	KNN, ANN, Naïve Bayes, Multinomial Logistic Regression, and Random Forest	Random Forest	94.13%	Real-time Data has been collected from Department of Agriculture, Talab, Tillo, Jammu;	Yes	Mustard Crop
17	Random Forest(RF), Gaussian Naïve Bayes  and SVM	Random Forest	72.74%	Historical municipality-level soybean yield data (2003–2016) was obtained from IBGE (https://sidra.ibge.gov.br/pesquisa/pam/tabelas).	No	soybean yield: study was conducted in the northern region of the Rio Grande do Sul (RS) state, Brazil
18	Artificial neural network, Recurrent neural network and deep neural network.	Hybrid network with re-enforcement learning multiple network=90%	90%	Yield datasets are gathered from the Directorate of Agriculture, Gandhinagar. Weather datasets are collected from the Agro-meteorology Department, Gujarat	No	wheat crop
43	simple nonlinear regression, SNR; backpropagation neural network, BPNN; and random forest, Regression, RF	Random Forest (Average Accuracy rate )	80.47%	Soil image dataset	No	Rice Crop
44	CP-ANNs, Supervised Kohonen Networks and XY-fused Networks (XY-Fs)	Supervised Kohonen Networks	81.65%	The study site was a 22 ha Horn End Field at Duck End Farm, Wilstead, Bedfordshire, U.K	spectroscopy sensor	wheat yield
45	SVM, DT, Multi-Layer Perception(MLP)	Multi-Layer Perception(MLP) (Average Accuracy rate of NPK Nutrients)	94%	Data were collected from Department of Soil science, Agricultural University located at trichendur and from soil science laboratory, kanyakumari district	No	Banana, Varieties of Rice, Varieties of Maize and Ragi
46	K Mean Clustering Algorithm.	K Mean Clustering	77%	Paddy Crop Images	No	Different crops
47	CNN, MLP	Convolution Neural Network (Average score of wheat, maize, sunflower, soybeans, and sugar beet)	85%	Kyiv region of Ukraine using multi-temporal multisource images	Landsat-8 and Sentinel-1A satellites	wheat, maize, sunflower, soybeans, and sugar beet
48	DT, KNN, KNN with cross validation, Linear regression, naïve bayes, Neural network, SVM	Neural Network	89.80%	Various datasets from government website : https://data.gov.in/ and Kaggle : https://www.kaggle.com/notebook	No	16 major crops grown such as : Rice, Maize, Ragi, Wheat, groundnut, Soyabean, cotton, Jute etc. across all the Andhra Pradesh state, India
49	Linear algorithms: logistic regression and linear discriminant analysis (LDA) and nonlinear tools: NB, KNN, CART and SVM	Linear Discriminant Analysis algorithm ( LDA)	61%	Collected for seven years in five countries of the ESA region, namely Ethiopia, Kenya, Tanzania, Malawi and Mozambique.	No	Maize Grain
PROPOSED ALGORITHM: Multi Class Support Vector Machine using Directed Acyclic Graph and Fruit Fly Optimization. (MSVM-DAG-FFO)			97.3%	Real-Time dataset collected using IoTSNA-CR Model	Sensors for temperature, moisture, GPA, water level, NPK, pH along with Node MCU and Arduino, Wi-Fi Hotspot	Crops: Rice, Cotton, Maize, Ground Nuts

 

3. Presence of redundancy in the article

Our Reply:

Thank you for your helpful suggestion. The important comments given by you are noted and necessary precaution measured.

4. Conclusion too short, to be developed

Our Reply:

First of all, thank you very much for your comments to improve our manuscript. According to your comments and suggestions, we have revised the conclusion part our manuscript carefully.

Content Updated:

The real-time data collection and its analysis are closer to enabling effective predictions. The IoTSNA-CR Model allows us to acquire soil nutrient data along with GPS location, moisture, temperature, and water level using its sensors. A common farmer can maintain his own field soil information using this device and can maintain the same in a low-cost cloud service. This helps a farmer to have updated about his soil health to know the suggested crops. The proposed MSVM-DAG-FFO algorithm allows farmers to access and analyse the pre-processed soil data. An Android application is developed to access this cloud data, analyse it, and predict the most suitable crops. The role of the FFO algorithm is to tune the MSVM model through the selection of kernel functions. A detailed experimental validation is carried out in 5 different time intervals on the real-time data of 4 different crops using SVM, SVM Kernel, Decision Tree, and MSVM-DAG-FFO. It has been observed that there is a significant improvement in the accuracy rate compared to other methods. The average accuracy rate of the proposed model overall over the 5 runs is 0.969. This is a more appropriate approach to predicting the suitable crops for a particular cultivation area. Also It allows to maintain the periodic soil health details in a low-cost cloud, which allows not only to guide the farmer in choosing a crop but also to give appropriate input regarding the usage of minerals.

 Further, an extensive survey of crop fields and the collection of real-time data from different geographical locations suggested as per crops by the department of agriculture of a governmental body are required. Also, the collection of datasets can be improved for more crops, such as sugar cane, potatoes, tomatoes, cauliflowers, mustard, ragi, soybeans, bananas, oil seeds, onions, ginger, etc., as suggested by the agriculture department. Also, if the application is used regularly by a farmer to maintain his own field information, It will allow the farmer to analyse his own field data with a more detailed approach for making better decisions regarding crops and maintaining soil health. The farmer can take the necessary steps to enhance the soil quality with limited investment in minerals.

 

Our reply:

Thank you very much for your suggestion. We have carefully read the articles you recommended and added them in this paper.

Once again, thank you very much for your professional and helpful comments to improve our manuscript.

 

List of revisions:

1. According to the reviewer's suggestion, we have revised our manuscript.
2. Some part of the manuscript has been rewritten.
3. Some figures and tables have been revised.
4. The format of the references, figures and equations have been revised. The revised words have marked with yellow highlight.

 

Thank you very much

Sincerely yours

Murali Krishna Senapaty

Author Response File: Author Response.docx

Reviewer 2 Report

please see the attachment.

Comments for author File: Comments.pdf

Author Response

Revision lists and replies to the reviewer’s comments

Re: Manuscript ID: computers-2248713

Type: regular

Title: IoT Enabled Soil Nutrient Analysis and Crop Recommendation Model for Precision Agriculture

Authors: Murali Krishna Senapaty, Abhishek Ray, Neelamadhab Padhy

 

We are grateful to the Editor and the three anonymous reviewers for their helpful comments and suggestions on our manuscript. The corresponding revisions and replies to the manuscript have made and listed as follows.

 

The comments and replies:

Reviewer #II:

1. 1 The role of oxygen photosynthesis is not shown, which is the basic component of plant life and society, and the impact of industry and energy.

Our Reply:

Thank you very much for your helpful comments on our manuscript. According to your comments and suggestions, we have added the research papers on oxygen photosynthesis.

 

Updated Content in Literature review:

The crop productivity rate is greatly influenced by the rate of photosynthesis in crops. It allows for increased chemical energy in crops and allows for improved growth. The author discussed oxygen sensors used on plants to measure the oxygen consumption by plant cells[50].

The author discussed measuring the photosynthesis of plants and its impact on plant development. He discussed different techniques used for it, such as the electrochemical sensor method, the gas exchange method, the photosynthesis measuring method, and estimation methods. It is observed that photosynthesis is very important for governing all life[51].

The author discussed the importance of Nitrogen for crops. The deficiency of Nitrogen in the soil decreases plant growth, and the leaves turn lemony yellow. Also, the Nitrogen fertilisers leads to environmental pollution and health issues[52].

 

1.2. The Internet of Things is a local component of an intelligent decision-making system to optimize crop growing processes.

Our Reply:

Thanks for your comments. According to your comments and suggestions, we have added the Papers on intelligent decision making system.

Updated Content:

The author identified improper use of irrigation techniques and non-use of arable land as the main causes of low crop production. So an intelligent irrigation support system using IoT sensors is suggested by the author to improve the rate of crop production. The proposed system monitors the water needs and allows for on/off operation of the water motors [53].

The author suggested an intelligent data collection system consisting of sensors, supporting hardware, and Wi-Fi to store the data in the ThinkSpeak cloud. He suggested that the available soil data in the cloud be used for monitoring the field to reduce human effort [54].

 

1.3. Тhe level of concentration of CO2 CO, O2, SO4, NO2 as the basis for the quality of the plant environment, society, animal husbandry and the threat of pollution by harmful complexes to the level of yield, ecosystem, and society, depending on the localization of control, is not controlled.

Our Reply:

Thank you sir for the valuable suggestion. We have studies these concepts and their importance in farming. We have tried to include the supporting content.

 

 

Our reply:

Thank you very much for your suggestion. We have carefully read the articles you recommended and added them in this paper.

Once again, thank you very much for your professional and helpful comments to improve our manuscript.

 

List of revisions:

1. According to the reviewer's suggestion, we have revised our manuscript.
2. Some part of the manuscript has been rewritten.
3. Some figures and tables have been revised.
4. The format of the references, figures and equations have been revised. The revised words have marked with yellow highlight.

 

Thank you very much

Sincerely yours

Murali Krishna Senapaty

Author Response File: Author Response.docx

Reviewer 3 Report

1.      Structure your abstract as follows- 1) Background 2) Aim/Objective 3) Methodology 4) Results 5) Conclusion. Write 2-4 lines for each and merge everything in one paragraph without any subheading

2.      Abstract must contain the motivation and objective of the article. The Abstract must be very clear and the motive of the paper should be represented in a nutshell.

3.      Introduction should be of 5-7 solid paragraphs and provide structure of work at the end of the Introduction section.

4.      Add more contribution to your study field.

5.      The purpose of study not clear.

6.      Make highlight for objectives

7.      Remove any table or figure which is taken from web. Otherwise you have to get approval from publisher and author in a provided form by springer.

8.      Please avoid to write definitions of terms like Soil Nutrients; pH value; Precision Agriculture, etc., which are already available over web, try to cite work for such information.

9.      In summary, only provide useful content in your work.

10.   These are Title related to your area, you may use.

 

·         Pallathadka, H., Jawarneh, M., Sammy, F., Garchar, V., Sanchez, T., & Naved, M. (2022, April). A Review of Using Artificial Intelligence and Machine Learning in Food and Agriculture Industry. In 2022 2nd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE) (pp. 2215-2218). IEEE.

·         Ansari, A. S., Jawarneh, M., Ritonga, M., Jamwal, P., Mohammadi, M. S., Veluri, R. K., ... & Shah, M. A. (2022). Improved Support Vector Machine and Image Processing Enabled Methodology for Detection and Classification of Grape Leaf Disease. Journal of Food Quality, 2022.

·         Kuthadi, V. M., Selvaraj, R., Rao, Y. V., Kumar, P. S., Mustafa, M., Phasinam, K., & Okoronkwo, E. TOWARDS SECURITY AND PRIVACY CONCERNS IN THE INTERNET OF THINGS IN THE AGRICULTURE SECTOR. Turkish Journal of Physiotherapy and Rehabilitation, 32(3).

 

 

Author Response

Revision lists and replies to the reviewer’s comments

Re: Manuscript ID: computers-2248713

Type: regular

Title: IoT Enabled Soil Nutrient Analysis and Crop Recommendation Model for Precision Agriculture

Authors: Murali Krishna Senapaty, Abhishek Ray, Neelamadhab Padhy

 

We are grateful to the Editor and the three anonymous reviewers for their helpful comments and suggestions on our manuscript. The corresponding revisions and replies to the manuscript have made and listed as follows.

 

The comments and replies:

Reviewer #III:

1. Structure your abstract as follows- 1) Background 2) Aim/Objective 3) Methodology 4) Results 5) Conclusion. Write 2-4 lines for each and merge everything in one paragraph without any subheading

 

Our Reply:

 

Thank you very much sir. We have broken down the abstract content as per your instructions and included by reframing the abstract.

 

 

Updated Content:

 

BACKGROUND:

A healthy and sufficient crop and food production is very much essential for everyone as the population is increasing globally. The production of crops affects the economy of a country to a great extent. In agriculture, observing the soil, weather, and water availability and, based on these factors, selecting an appropriate crop, finding the availability of seeds, analysing crop demand in the market, and having knowledge of crop cultivation are important.

At present, many advancements have been made in recent times, starting from crop selection to crop cutting. Mainly, the role of the Internet of Things, cloud computing, and machine learning tools helps a farmer analyse and take better decisions in each stage of cultivation. Once suitable crop seeds are chosen, the farmer shall go for seeding, monitoring crop growth, disease detection, finding the ripening stage of the crop, and then for crop cutting.

 

AIM/OBJECTIVE:

The main objective is to provide a continuous support system to a farmer so that he can get regular inputs about his field and crop. Also, he should be able to take proper decisions at each stage of farming.

Artificial Intelligence, Machine learning, Cloud, Sensors and other automated devices shall be included in the decision support system so that it will provide the right information within a short span of time. By using the support system, a farmer will be able to take decisive measures without fully depending on the local agriculture offices.

 

METHODOLOGY:

We have proposed an IoT-enabled Soil Nutrient Classification and Crop Recommendation (IoTSNA-CR) model to recommend crops. The model helps minimise the use of fertilisers in soil so as to maximise productivity. The proposed model consists of phases, such as the data collection using IoT sensors from cultivation lands, storing this real-time data into cloud memory services, accessing this cloud data using an Android application, and then pre-processing and periodic analysis of it using different learning techniques. A sensory system is prepared with optimised cost that contains different sensors, such as a soil temperature sensor, a soil moisture sensor, a water level indicator, a pH sensor, a GPS sensor, and a colour sensor, along with an Arduino UNO board. This sensory system allows us to collect moisture, temperature, water level, soil NPK colour values, date, time, longitude, and latitude. The studies have revealed that the Agrinex NPK soil testing tablets are to be applied to a soil sample, and then the soil colour is sensed using a LDR colour sensor to predict the Phosphorus (P), Nitrogen (N), and Potassium (K) values. These collected data together is stored in a firebase cloud storage media. Then an Android application is developed to fetch and analyse the data from the Firebase cloud service from time to time by a farmer.

 

RESULTS:

In this study, a novel approach is identified by hybridization of algorithms. We have developed an algorithm using Multi-class Support Vector Machine with Directed Acyclic Graph and optimised it using the Fruit Fly Optimization method (MSVM-DAG-FFO). The highest accuracy rate of this algorithm is 0.973, compared to 0.932 for SVM, 0.922 for SVM Kernel, and 0.914 for Decision Tree. It has been observed that the overall performance of the proposed algorithm in terms of accuracy, recall, precision, and F-Score is high compared to other methods.

 

CONCLUSION:

The IoTSNA-CR device allows the farmer to maintain his field soil information easily in to cloud service using his own mobile with the minimum knowledge. Also it reduces the expenditure to balance the soil minerals and increases the productivity.

 

 

2. Abstract must contain the motivation and objective of the article. The Abstract must be very clear and the motive of the paper should be represented in a nutshell.

Our reply:

Thank you for the valuable suggestion. We have updated the Abstract as per your guidance to represent a clear motive of paper.

 

 

3. Introduction should be of 5-7 solid paragraphs and provide structure of work at the end of the Introduction section.

Our Reply:

Thank you sir for the guidance given. We have enhanced the introduction part by including the addition content into it.

 

 

Updated Content:

 

1. Introduction

The agricultural sector plays a significant role in the development of the whole economy of any country. The global rapid increase in population makes food and crop production important. So a lot of technological changes have been observed in this sector. Many ways the crop production and its storage is carried out. We see the IoT, smart technologies, artificial intelligence, and automated devices as available in smart farming. Sometimes implementing these technologies requires expertise and is also costly. Precision agriculture is a significant part of agriculture, in which data transmission technology is also vital.  The soil minerals can be determined by soil testing, either in a lab or by using sensors. The use of various sensors allows for the collection of real-time data.

We must find recommended crops for a particular field for better cropping. To have better crop prediction and production, the factors influencing it are: soil properties, weather conditions, availability of water, soil temperature, sun light, wind, pollution level, etc. Therefore, by using the sensors, area wise soil properties are to be collected for Phosphorus (P), Nitrogen (N), and Potassium (K), pH value, temperature, moisture, water level, and water pollution, etc. These data allow for the recommendation of crops based on their ideal requirements. But for these sensors, we need much investment, expertise to handle them, and periodic maintenance is also required.

 In present day, the proper integration of IoT sensors, Mobile device, and Cloud and data analysis is essential in the field of precision agriculture. Also, the technologies must fit with farmers' knowledge and experience so as to contribute towards increasing sustainability in agriculture. The soil characteristics and its mineral availability vary to some extent many times. So the real-time data will give better accuracy in predictions for the specific fields compared to the offline dataset as per geographical locations. So an approach to making studies of real-time data much more important is required.

Periodic real time data shall be maintained in cloud in a systematic manner. The cloud service is best option for storing the collected data over time using the IoT device's Wi-Fi module. At present days smart phone is mostly available with people. The common mobile operating system supports the development of an application through which accessing cloud data is easier. In this context, a timely decision is the prime goal, as it can save time, resources and give us an accurate decision. So a support system for pre-processing the cloud data and then analysing it for predictions is required. The different classification and regression tools are used for data analysis so that prediction is more accurate.

The major contribution in this paper is:

• proposed an IoTSNA-CR model.
• sensors to collect data on soil properties.
• Proposed MSVM-DAG-FFO Algorithm

This paper proposes an IoT-enabled Soil Nutrient Analysis and Crop Recommendation (IoTSNA-CR) model for precision agriculture. It primarily allows the IoT sensors to collect data related to soil moisture, temperature, NPK, and pH value. Besides, the IoTSNA-CR technique involves the design of the MSVM model for the appropriate classification of soil nutrients and crop recommendations. Furthermore, the kernel function of the MSVM model must be optimally chosen using the Fruit Fly Optimization (FFO) algorithm. The benchmark data set is used for detailed experimental validation of the IoTSNA-CR model. This crop recommendation system helps the farmers not only acquire data from the sensors but also maintain them and analyse them suitably using this hybrid approach.

We have analysed the soil for classification using linear SVM and Kernel SVM, Decision Tree. We have datasets based on different types of crops and their mineral needs. So, it is observed that the performance of SVM is better suited for us in multiple classes. It increases the accuracy rate if we can choose a suitable kernel function for it. FFO algorithm can help us select optimised kernels. So a hybridization of MSVM and FFO is used to improve the accuracy rate for classification.

The rest of this paper is organised as follows: Section 2 includes reviews on different models proposed and algorithms applied in precision farming; Section 3 shows the proposed model that contains data acquisition, data storage in the cloud, and data analysis using a novel MSVM-DAG-FFO algorithm; Section 4 presents the proposed method’s experimental results; and at last, Section 5 contains the overall conclusion and future extensions of the paper.

 

4. Add more contribution to your study field.

Our Reply:

As per your guidance more data has been collected from different crop fields from many areas of Rayagada district and included here.

 

Updated Content:

The sensory model built, and we conducted experiments for collecting data from different crop fields in RAYAGADA districts per the geographical information. We have taken the guidance of local agriculture office to identify the crop-wise geo-graphical locations, with a soil science expert validating the crop fields and validating the collected data from crop fields using sensors.

 Data collection has been carried out from different geographical locations of crop fields in Rayagada district in consultation with agriculture experts and experienced farmers. Also, we have taken reference from the geographical map of the district to identify the availability of water. By considering these parameters, the data collection is done and stored in the cloud firebase. The Table 3 below presents the data collection done from different GPA locations and crop fields as:

 

TABLE 3 Represents the data collection from different GPS location.

Sl.No	Crop Field	Longitude	Latitude
1	Rice	19.01979438317244	83.83367378452479
2	Cotton	19.120267916735354	83.79737929760799
3	Rice	19.131993231927446	83.82571241313724
4	Rice	19.153893005673186	83.82711736101244
5	Rice	19.034090509160446	83.81985812937597
6	Cotton	19.14318090988537	83.77053423826487
7	Cotton	19.19957968976411	83.81315098959948
8	Rice	19.311689976321137	83.79038888001347
9	Cotton	19.20391036130566,	83.83906791114363
10	Cotton	19.243039905554685,	83.67781726274391
11	Grount Nut	19.183372074271134,	83.67778906665868
12	Grount Nut	19.12229596117156,	83.40884453177296
13	Cotton	19.19129593761809,	83.6998360113169
14	Ground Nut	19.201211003276704,	83.763592486272
15	Maize	19.130544274204112,	83.8304902190576
16	Ground Nut	19.014452114119926,	83.77777140899494
17	Maize	19.07788826595366,	83.76562479599976
18	Maize	19.09682829341866,	83.8591537106543
19	Maize	19.23175510046014,	83.49582454063922
20	Maize	19.329410878579964,	83.61866194709863

 

 

5. The purpose of study not clear.

 

Our Reply:

We are extremely sorry for the inconvenience.

 

Here we shall bring the purpose of my study to your notice as follows:

• Dataset Preparation: A real time soil nutrient data collection from different areas as per geographically suggested crops fields.
• Filtering data and storing: The data is analysed, removed unwanted anomalies, stored into firebase cloud storage.
• Training Dataset: Training the cloud data using the MSVM-DAG-FFO proposed algorithm
• Mobile Application: developed a mobile application for accessing the cloud data, data analysis using the algorithm.
• Testing Dataset: Collecting the real time data by a farmer from his own field using the IoTSNA-CR device and testing using proposed algorithm to identify recommended crops.
• Periodic collection of farmer’s field data and analyse to maintain the soil health and mineral deficiency.
• This approach will provide a decision support system to a common farmer using a mobile device application.

 

The graphical abstract is presented for the clarity as shown below:

 

 

6. Make highlight for objectives

Our Reply:

Thank you sir, We have taken care to high light the objectives.

 

7. Remove any table or figure which is taken from web. Otherwise you have to get approval from publisher and author in a provided form by springer.

Our Reply:

Thank you for your valuable suggestions. We have noted your line of guidance and removed the un-authentic details.

 

8. Please avoid to write definitions of terms like Soil Nutrients; pH value; Precision Agriculture, etc., which are already available over web, try to cite work for such information.

Our Reply:

Thank you very much for the suggestion sir. We tried our level best to remove the general content and terms.

 

 

9. In summary, only provide useful content in your work.

Our Reply:

Thank you sir for the suggestion, We have tried to remove unwanted contents and

 

10. These are Title related to your area, you may use.

 [55]    Pallathadka, H., Jawarneh, M., Sammy, F., Garchar, V., Sanchez, T., & Naved, M. (2022, April). A Review of Using Artificial Intelligence and Machine Learning in Food and Agriculture Industry. In 2022 2nd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE) (pp. 2215-2218). IEEE.

[56]   Ansari, A. S., Jawarneh, M., Ritonga, M., Jamwal, P., Mohammadi, M. S., Veluri, R. K., ... & Shah, M. A. (2022). Improved Support Vector Machine and Image Processing Enabled Methodology for Detection and Classification of Grape Leaf Disease. Journal of Food Quality, 2022.

[57]   Kuthadi, V. M., Selvaraj, R., Rao, Y. V., Kumar, P. S., Mustafa, M., Phasinam, K., & Okoronkwo, E. TOWARDS SECURITY AND PRIVACY CONCERNS IN THE INTERNET OF THINGS IN THE AGRICULTURE SECTOR. Turkish Journal of Physiotherapy and Rehabilitation, 32(3).

 

Our Reply:

Thank you for suggesting to include the said papers. We have studied the relevant papers and included the information in literature review by siting them.

Food production, food storage, and better supply chain management are important factors today. As the population is increasing, to increase crop production, the latest technologies such as Artificial Intelligence and machine learning are used. The author discussed the implementation of machine learning on various stages such as crop selection, irrigation, crop disease detection, and weather data analysis[55].

The image analysis of crop leaves, stems, and fruits will allow us to quickly analyse and predict the disease. Regular monitoring of plant health is important for better crop production. The author discussed finding the grape leaf diseases by using image analysis using Support Vector Machine[56]. 

IoT is used globally in many sectors to improve efficiency, such as farming, fitness centres, homes, government offices, medical facilities, vehicles, etc. IoT sensors, drones, and automated devices play an important role in various situations of farming, from crop seeding to crop cutting and delivery. The author mainly focused on security and privacy issues in agriculture when IoT devices were used[57].

 

Our reply:

Thank you very much for your suggestion. We have carefully read the articles you recommended and added them in this paper.

Once again, thank you very much for your professional and helpful comments to improve our manuscript.

 

List of revisions:

1. According to the reviewer's suggestion, we have revised our manuscript.
2. Some part of the manuscript has been rewritten.
3. Some figures and tables have been revised.
4. The format of the references, figures and equations have been revised. The revised words have marked with yellow highlight.

 

Thank you very much

Sincerely yours

Murali Krishna Senapaty

Author Response File: Author Response.docx