1 of 53

Smart Surveillance System for

Coconut Diseases and

Pest Infestations

CocoRemedy

Proposal Presentation

2021 - 042

3/8/2021

2 of 53

3/8/2021

Meet Our Team !

Gunasekara R.P.T.I

IT180517800

Vidhanaarachchi S.P

IT18078510

Akalanka P.K.G.C

IT18045918

Rajapaksha H.M.U.D

IT18051612

2

3 of 53

3/8/2021

3

    • Sri Lanka is ranked as the 5th highest coconut exporter in the world

​

    • Coconut covers an extent of 443,538 ha and comes next to rice

​

    • The high incidence of pests and diseases is considered one of the major constraints related to coconut production and farm productivity

​

    • A smart agricultural solution with automated plant disease detection and classification tools has been identified as a valuable resource of data that supports farm decision-making

​

3/8/2021

​

(a)

​

​

(b)

​

INTRODUCTION

4 of 53

3/8/2021

3/8/2021

4

    • How to classify Weligama Coconut Wilt Disease with magnesium deficiency?

​

    • How to classify Caterpillar Infestation with coconut leaf scorching ?

​

    • How to use crowdsourcing to make stakeholders aware of the dispersion and severity of the diseases ?

​

    • How to determine the dispersion factors to prevent the dispersion?

​

    • How to determine the availability of water resources nearby?

​

RESEARCH QUESTION

5 of 53

3/8/2021

​

​

​

Classification of Coconut Caterpillar Infestation

​

​

​

​

Classification of Weligama Coconut Leaf Wilt Disease

​

5

OBJECTIVES

Surveillance system for Weligama Coconut Leaf Wilt disease & Coconut Caterpillar infestations

​

Main Objective

Sub Objectives

​

Crowdsourcing for information sharing

​

​

Differentiating Magnesium Deficiency, Coconut Leaf Scorching, and Identify Water Resources

​

6 of 53

3/8/2021

System Diagram

6

7 of 53

IT18051780 | Gunasekara R.P.T.I | 2021 - 042

Specialization : Software Engineering

3/8/2021

IT18051780 | Gunasekara R.P.T.I

8 of 53

​

    • Coconut production is hampered by many pests and diseases, including bud

rot, leaf blight, stem bleeding, Ganoderma root, and bole rot, which occur in small patches [1].

​

    • Weligama Coconut Leaf Wilt Disease(WCLWD) - Matara district (late 2006) [2].

​

    • Most devastating coconut phytoplasma disease [3].

​

    • Coconut Cultivation Board (CCB) surveyed the yield loss due to WCLWD [3],
      • Galle district - 18%
      • Hambantota district - 2.42%
      • Matara district - 25.87%

​

    • After infected a tree within two years, a coconut palm will die [3].
    • No proven remedy, and the only feasible ways to avoid the spread of the disease [3].

​

IT18051780 | Gunasekara R.P.T.I | 2021 - 042

3/8/2021

Introduction

Background

8

9 of 53

1

1

1

1

    • Cut down infected coconut trees and incinerate the crowns [3].

​

    • Currently uses quantitative Polymerase Chain Reaction (PCR) to validate the symptomatic WCLWD diagnosis [2].

IT18051780 | Gunasekara R.P.T.I | 2021 - 042

3/8/2021

Background

1

2

3

4

Leaves Flattening

Leaves Flattening

+

Yellowing of Leaflets

Leaves Flattening

+

Yellowing of Leaflets

+

Drying of Leaflets

Leaves Flattening

+

Yellowing of Leaflets

+

Drying of Leaflets

+

Breaking tips of fronds

Symptoms

Stage

1

2

3

4

9

10 of 53

    • A system that detects leaf blight disease, stem bleeding disease, and pest infestation caused by red palm weevil.

IT18051780 | Gunasekara R.P.T.I | 2021 - 042

3/8/2021

​

    • The diseases and pest infestations are identified using the help of a drone flying across the field capturing the images through a GoPro camera.

​

Research B

​

    • An Expert System for Coconut Diseases Diagnosis which provides the diagnosis and recommendation of the diseases to the user

​

Research A

​

Research C

Identification of WCLWD

Identification of severity stage of WCLWD

Technology (Using CNN)

Leaves Identification

Mobile Application

Application

Reference

Research A

Research B

Research C

Proposed System

Comparison of existing systems

Introduction

Research Gap

10

11 of 53

IT18051780 | Gunasekara R.P.T.I | 2021 - 042

3/8/2021

How to differentiate WCLWD yellowing with Nutrient deficiency yellowing ?

How to identify Weligama Coconut Leaf Wilt Disease and the severity stage ?

Introduction

Research Question

(a)

​

(b)

​

11

12 of 53

Identification of Coconut leaves

Identification of Weligama Coconut Leaf Wilt Disease

Identification of Weligama Coconut Leaf Wilt Disease severity stage

IT18051780 | Gunasekara R.P.T.I | 2021 - 042

3/8/2021

Specific and Sub Objective

Classification of Weligama Coconut Leaf Wilt Disease

Introduction

Identification of best architecture for transfer learning

12

13 of 53

System Diagram

Methodology

13

14 of 53

​

    • React Native
    • Python
    • Tensorflow
    • Keras
    • Node
    • Flask

​

Algorithms &

Architectures

Algorithms

    • CNN

​

Architectures

    • VGG-16
    • VGG-19
    • GoogleNet
    • Inception v2
    • Inception v4

(will be used to choose the best technique)

Technologies

IT18051780 | Gunasekara R.P.T.I | 2021 - 042

3/8/2021

Technologies, Techniques, Algorithms

Techniques

​

    • Use Transfer learning
    • Data Augmentation

​

Methodology

14

15 of 53

IT18051780 | Gunasekara R.P.T.I | 2021 - 042

3/8/2021

Software Requirements

Personnel Requirements

Functional Requirements

Non-Functional Requirements

    • React Native
    • Python
    • TensorFlow
    • Flask Server
    • Node Server
    • Jupyter Notebook
    • Intellij Idea
    • Keras

​

    • System should be able convert image in to Base64 string
    • System should be able to validate coconut leaf for further processing.
    • System should be identified Weligama Coconut Leaf Wilt disease using the first stage (flaccidity)
    • System should be able to determine the severity stages of Weligama Coconut Leaf Wilt disease
    • Interfaces should be User-friendly
    • Application should properly work for cross platform
    • Application should be reliable
    • Higher accuracy of results
    • Results should be more efficient
    • Application should be able to give fast results

System, Personnel, and Software Specification Requirements

Methodology

15

Resources and Dataset of weligama coconut leaf wilt disease

    • Coconut Research Institute of Sri Lanka
    • Dr. Nayani Aratchige (Principal Entomologist)
    • Coconut landowners near Weligama

16 of 53

IT18051780 | Gunasekara R.P.T.I | 2021 - 042

3/8/2021

Work Breakdown Structure

16

17 of 53

References

[1] E. Pathiraja, G. R. Griffith, R. Farquarson, and

R. Faggian, “The Sri Lankan Coconut Industry: Current Status and Future

Prospects in a Changing Climate,” Australasian Agribusiness Perspectives,

Jan. 2015.

​

[2] Nainanayake AD, Kumarathunga MDP, De Silva PHPR. “A survey of

land for Weligama coconut leaf wilt disease affected palms outside the declared

boundary in the Southern Province”. COCOS. 2016; 22(1):57–64.

​

[3] “Weligama Coconut Leaf Wilt Disease still a

critical threat,” Daily FT, 13-Jan-2014. [Online]. Available:

http://www.ft.lk/article/240426/Weligama-Coconut-Leaf-Wilt-Disease-still-a-critical-threat.

​

[4] “Plantation sector hopes 2019 yields better

results,” The Morning - Sri Lanka News, 26-Jan-2019. [Online].

Available:

http://www.themorning.lk/biz-pg-3-plantation-sector-hopes-2019-yields-better-results/.

​

17

18 of 53

IT18078510 | Vidhanaarachchi S. P | 2021 - 042

IT18078510 | S. P. Vidhanaarachchi

Specialization : Software Engineering

3/8/2021

19 of 53

IT18078510 | Vidhanaarachchi S. P | 2021 - 042

3/8/2021

​

    • Coconut caterpillar Opisina arenosella Walker is one of the major pests of coconut in Sri Lanka, first reported in 1898 [1].

​

    • Moderate to high densities of coconut caterpillar is capable of causing huge economic yield losses to farmers [2].

​

    • Naturally, the population of coconut caterpillar is kept under control by natural enemies but the low temperature and humid nature create an unfavorable environment for them to survive [3].

    • Outbreaks are mostly reported between the months of February and October [3].

​

​

​

​

Introduction

Background

19

​

(a)

​

​

(b)

​

20 of 53

    • Caterpillars feed on the dorsal surface for about 30-40 days resulting in the characteristic scorched appearance [3].

​

    • Differentiating coconut caterpillar Infestation palms are difficult to people due to the misidentification caused with leaf scorch disorder [3].

​

​

IT18078510 | Vidhanaarachchi S. P | 2021 - 042

3/8/2021

Background

​

Survey report on reasons for browning in coconut leaves

​

​

(a)

CCI Infestation

20

​

(b)

Coconut leaf scorching

21 of 53

IT18078510 | Vidhanaarachchi S. P | 2021 - 042

3/8/2021

Background

​

​

​

    • As the recommendation of control measures are based on the pest populations, assessment of the pest population is conducted before recommending the control measures [3]

​

    • Currently, manual methods are carried out by researchers to assess the pest population.

​

    • Those manual methods are error-prone and time-consuming

​

​

Sample sheet of how data is collected for coconut caterpillar infestation

​

21

22 of 53

IT18078510 | Vidhanaarachchi S. P | 2021 - 042

3/8/2021

Introduction

Research Gap

Damaged

leaf area

Number of

caterpillars

Mobile-based identification approach

Identification

of

CCI

Application Reference

Research A

Research B

Research C

Proposed System

Comparison of former researches

Progression level detection

​

​

​

    • First in Sri Lanka

​

    • First-ever mobile-based identification system

​

    • First to calculate the progression level CCI

​

22

23 of 53

IT18078510 | Vidhanaarachchi S. P | 2021 - 042

3/8/2021

​

    • our community is not familiar with coconut caterpillar damage and the symptoms associated with it.

​

23

Introduction

Research Question

How to identify coconut caterpillar infestation?

24 of 53

IT18078510 | Vidhanaarachchi S. P | 2021 - 042

3/8/2021

24

Research Question

How to identify the severity of caterpillar infestation?

​

    • According to the increase of severity, the biological control method needs to be supported with chemical control of the pest

​

25 of 53

IT18078510 | Vidhanaarachchi S. P | 2021 - 042

3/8/2021

25

Introduction

Specific and Sub Objective

​

Specific Objective

​

Identification of Coconut Caterpillar Infestation (CCI).

​

​

Calculating the damaged leaf area of Coconut Caterpillar Infestation (CCI).

​

​

Extracting the number of caterpillars available.

​

​

Create a smart mobile-based identification system

​

​

Classification

of

Coconut Caterpillar Infestation (CCI)

26 of 53

IT18078510 | Vidhanaarachchi S. P | 2021 - 042

3/8/2021

26

Methodology

System Diagram

27 of 53

​

​

    • React Native
    • Expo
    • Python
    • TensorFlow
    • Flask Server
    • Node Server
    • OpenCV
    • Intellij Idea
    • Keras

​

IT18078510 | Vidhanaarachchi S. P | 2021 - 042

3/8/2021

27

Technologies, Techniques, Algorithms

Technologies

Techniques

Algorithms

​

    • Data Augmentation
    • Feature Selection

​

Algorithms

​

    • CNN
    • Mask R-CNN

​

​

​

Architecture

​

    • Inception-V4
    • Inception-V3
    • ResNet-152
    • ResNet-101
    • MobileNet

​

​

​

28 of 53

IT18078510 | Vidhanaarachchi S. P | 2021 - 042

3/8/2021

Functional Requirements

​

​

    • CCI identification results should be appropriately displayed to the stakeholder.

​

    • CCI damaged area should be calculated with high accuracy.

​

    • The number of caterpillars should be extracted correctly.

​

    • The progression level should be determined correctly using the damaged area and caterpillar count.

28

System, Personnel, and

Software Specification Requirements

Non-Functional Requirements

Software Requirements

Personnel Requirements

​

    • Interfaces should be User-friendly

​

    • Should properly work for android and IOS devices

​

    • The application should be reliable

​

    • Higher accuracy of results

​

    • Results should be more efficient

​

​

    • Python
    • Node
    • Jupyter Notebook
    • Intellij Idea

Resources and Dataset of coconut caterpillar infestation

    • Coconut Research Institute of Sri Lanka
    • Dr. Nayani Aratchige (Principal Entomologist)
    • Coconut landowners near Puttalam

29 of 53

IT18078510 | Vidhanaarachchi S. P | 2021 - 042

3/8/2021

29

Work Breakdown Structure

30 of 53

[1]. I. A. Alshawwa, A. A. Elsharif, and S. S. Abu-Naser, "An Expert System for Coconut Diseases Diagnosis," International Journal of Academic Engineering Research (IJAER), Vol. 3, Issue 4, pp. 8-13, April 2019.

​

[2]. P. A. C. R. Perera, M. P. Hassell, and H. C. J. Godfray "Population dynamics of the coconut caterpillar, Opisina arenosella Walker (Lepidoptera: Xyloryctidae), in Sri Lanka," COCOS, vol. 7, pp. 42–57, 1989.

​

[3]. "Coconut caterpillar and its control," Advisory circular B2, Coconut Research Institute, Sri Lanka [Online] Available: https://www.cri.gov.lk/web/images/pdf/leaflet/series_b/b2.pdf. [Accessed 2 February 2021].

​

[4]. A. Chandy, "Pest infestation identification in coconut trees using deep learning," Journal of Artificial Intelligence and Capsule Networks, Vol. 01, No. 01, pp.10-18, 2019. [Online] Available: https://www.irojournals.com/aicn/V1/I1/02.pdf. [Accessed 5 February 2021].

​

[5]. P. Singh, A. Verma, and J. S. R. Alex, 'Disease and pest infection detection in coconut tree through deep learning techniques," Computers and Electronics in Agriculture, Vol. 182, March 2021, [Online] Available: https://www.sciencedirect.com/science/article/pii/S0168169921000041. [Accessed 2 February 2021].

​

[6]. E. A. Lins, J. P. M. Rodriguez, S. I. Scoloski, J. Pivato, M. B. Lima, J. M. C. Fernandes, P. R. Valle da Silva Pereira, D. Lau, and R. Rieder, "A method for counting and classifying aphids using computer vision," Computers and Electronics in Agriculture, Vol. 169, February 2020, [Online] Available: https://www.canva.com/design/DAEXiXDvMLI/YbsWu2jO2RiqiBKvFM6-Yg/edit. [Accessed 8 February 2021].

IT18078510 | Vidhanaarachchi S. P | 2021 - 042

3/8/2021

30

References

31 of 53

Specialization : Software Engineering

3/8/2021

IT18045918 | Akalanka P.K.G.C

IT18045918 | Akalanka P.K.G.C | 2021 - 042

32 of 53

​

​

    • Mature fronds of the leaflets turning yellow
    • The Leaflet would be pale yellow, and a green band on either side of the ekel will be visible.
    • The basal areas will continue to be green, and a green band will be visible on both sides of the entire frond.
    • Eventually, the tips of the leaflets dry out, and the whole frond will get the appearance of the rachis[1]

​

Magnesium Deficiency

​

​

Visual Symptoms

​

3/8/2021

Background

Health leaf

​

IT18045918 | Akalanka P.K.G.C | 2021 - 042

32

Mg deficiency leaf

Figure 1.1

33 of 53

​

​

Visual Symptoms

​

​

​

    • necrosis or scorching of the tips on the leaflets of the lower leaves can be seen.
    • whole leaves will curl and wither[2]

​

3/8/2021

Background

Leaf Scorch Decline

​

​

    • Leaf scorch decline is a coconut palm disorder of coconut in Sri Lanka, first reported[2] in 1955. [2]

​

IT18045918 | Akalanka P.K.G.C | 2021 - 042

33

Figure 1.2

34 of 53

​

​

How to differentiate yellowing of Mg deficiency with yellowing of WCLWD ?

​

1

2

​

​

How to differentiate browning and drying up leaves in CCI with leaf scorching disorder?

​

IT18045918 | Akalanka P.K.G.C | 2021 - 042

3/8/2021

Research Question

​

​

How to Identify nearby water resources to avoid outbreaks of coconut caterpillars?

3

34

35 of 53

IT18045918 | Akalanka P.K.G.C | 2021 - 042

3/8/2021

Leaf Scorch Decline Identification

Water Resources

Identify using google map API

Technology (Using CNN)

Mg

Deficiency

Identification

Mobile Application

Application Reference

Research A[3]

Research B[4]

Research C[5]

Proposed System

Research Gap

Comparison of former researches

First in Sri Lanka

First-ever mobile based identification system

First to identify Magnesium

deficiency in coconut

First to identify Leaf scorch

decline in coconut

First to identify water resources

35

36 of 53

​

To identify Water resources located nearby to the

farmer’s current location using Google Map/Open Map Tiles

​

To identify Leaf scorch Decline

​

To identify Magnesium Deficiency

Specific and Sub Objective

IT18045918 | Akalanka P.K.G.C | 2021 - 042

3/8/2021

​

Specific Objective

Differentiating Magnesium Deficiency, Coconut Leaf Scorching, and Identify Water Resources located nearby to the farmer’s current location

36

37 of 53

IT18045918 | Akalanka P.K.G.C | 2021 - 042

3/8/2021

System Diagram

37

38 of 53

Technologies, algorithms to be used

IT18045918 | Akalanka P.K.G.C| 2021 - 042

3/8/2021

Technologies

Algorithms &

Architectures

Techniques

​

    • React Native
    • Expo
    • React
    • Python
    • Node
    • OpenCV
    • TensorFlow
    • Google Map API
    • Open Map Tiles

​

Algorithms

​

    • K Means
    • CNN

​

Architecture

​

    • Inception-V4
    • Inception-V3
    • ResNet-152
    • ResNet-101
    • VGG19
    • VGG16

​

​

    • Data Augmentation
    • Feature Selection

​

38

39 of 53

    • System should be able convert image in to Base64 string

​

    • System should be able to select/capture and upload the image from the smartphone's memory.

​

    • System should be able to identify the Magnesium Deficiency & Leaf Scorch decline in the captured imaged.

​

    • When Coconut caterpilor Infestation detected system should be able to identify water resource within the range of 100m from the farmers’ location.

​

    • Higher Accuracy Of results.
    • Should properly work for IOS and Android devices.
    • Should have high security.
    • Application should be reliable
    • Interfaces should be more user-friendly.

​

​

​

    • Python
    • Node
    • Jupyter Notebook
    • Intellij Idea

​

System, personal, and

software specification Requirements

IT18045918 | Akalanka P.K.G.C| 2021 - 042

3/8/2021

Functional Requirements

Non-Functional Requirements

Software Requirements

Personnel Requirements

39

Resources and Dataset of Magnesium Deficiency and Leaf scorch decline

    • Coconut Research Institute of Sri Lanka
    • Dr. Nayani Aratchige (Principal Entomologist)
    • Coconut landowners near Baddegama,Puttalam and Weligama

40 of 53

IT18045918 | P.K.G.C Akalanka | 2021 - 042

3/8/2021

40

Work Breakdown Structure

41 of 53

IT18045918 | P.K.G.C Akalanka | 2021 - 042

3/8/2021

REFERENCES

41

[3] Izzeddin, A., Abeer, A. and Samy, S., 2019. An Expert System for Coconut Diseases Diagnosis. International Journal of Academic Engineering Research (IJAER), 3(4), pp.8-13.

[4] Chandy, A., 2019. PEST INFESTATION IDENTIFICATION IN COCONUT TREES USING DEEP LEARNING. Journal of Artificial Intelligence and Capsule Networks,01(01), pp.10-18.

​

[5] Singh, P., Verma, A. and Alex, J., 2021. Disease and pest infection detection in coconut tree through deep learning techniques. Computers and Electronics in Agriculture, 182, p.105986.

[1] C. R. I. Luniwila, "Cri.gov.lk," 2021. [Online]. Available: https://www.cri.gov.lk/web/images/pdf/leaflet/series_a/a7.pdf.

[2] "Core.ac.uk," 2021. [Online]. Available: https://core.ac.uk/download/pdf/52172811.pdf.

42 of 53

3/8/2021

IT18051612 | Rajapaksha H.M.U.D

Specialization: Software Engineering

IT18051612 | Rajapaksha H.M.U.D | 2021 - 042

43 of 53

​

    • Differences in perceptions and knowledge of coconut diseases constitute a major obstacle in farmer–researcher cooperation, which is necessary for sustainable disease management [7].

​

    • According to Herath et al. (2015):CRISL, production of coconut has a negative relationship with the experience or knowledge of farmers [7].

​

    • Online voluntarily crowdsourcing is an emerging approach to distributed problem solving and knowledge sharing [1].

​

    • The disease and pest infestation dispersion factors are not yet identified properly by the authorities due to the lack of data availability as the process is done manually.

​

IT18051612 | Rajapaksha H.M.U.D | 2021 - 042

3/8/2021

Introduction

Background

The results generated by the study conducted by Herath et al. (2015): CRISL

​

43

44 of 53

IT18051612 | Rajapaksha H.M.U.D | 2021 - 042

3/8/2021

Introduction

Research Gap

​

    • Information sharing will be done by the processed data is directly sent to the specific farmer’s smart device with a user-friendly interface with the help of WIFI.

​

Research A

​

    • An Expert System for Plant Disease Dispersion Prediction and Simulation using concentration maps and Gaussian Plume Model.

​

Research B

    • A system is concerned with the diagnosis of but rot, leaf rot, stem bleed, Tanjore wilt, and diseases of the root (wilt). There is no proper awareness mechanism.

​

Research C

Real time notification

Anonymous

Data gathering

Connecting

farmers and industry professional

Geographical

Information System

Image Feature Extraction

Application

Reference

Research A

Research B

Research C

Proposed System

Comparison of existing systems

44

45 of 53

IT18051612 | Rajapaksha H.M.U.D | 2021 - 042

3/8/2021

Introduction

Research Question

How to reduce the dispersion?

​

    • Target community is not familiar with diseases and their dispersions and extension personnel to be contacted in an incident occurred.

​

How to identify dispersion factors?

    • Dispersion factors are not identified by the authorities due to the lack of data availability.

​

    • Due the recent fluctuations in weather conditions the dispersion has been suspected to be improved.

​

45

46 of 53

IT18051612 | Rajapaksha H.M.U.D | 2021 - 042

3/8/2021

Introduction

Specific and Sub Objectives

Crowdsourcing for

Information Sharing

Specific Objective

​

    • Informing nearest farmers regarding the dispersion and severity.

​

    • Visualization the severity in a concentration map.

​

    • Anonymous data gathering to identify factors of dispersion.

​

    • Image meta data feature extraction to get GPS locations

​

Sub Objectives

46

47 of 53

IT18051612 | Rajapaksha H.M.U.D | 2021 - 042

3/8/2021

Methodology

System Diagram

47

48 of 53

IT18051612 | Rajapaksha H.M.U.D | 2021 - 042

3/8/2021

Non-Functional

Requirements

​

    • System should be able to identify the nearest farmers according to the severity levels based on the GPS locations.

​

    • System should be able to send real time mobile push notifications to farmers and respective CDO of the area and web push notification to CRISL.

​

    • System should be able to extract the GPS locations from meta data of the uploaded image.

​

    • System should gather historical and forecast weather data based on the GPS location and analytically visualize to CRISL

​

System,Personnel and Software Specification Requirements

    • Should respond Realtime.

​

    • Should properly work as a mobile cross platform application.

​

    • Should have high security.

​

    • Application should be reliable

​

    • Interfaces should be more user-friendly.

System Requirements

Software

Requirements

​

    • React Native
    • Expo
    • Node
    • JavaScript
    • Node Server
    • Intellij Idea
    • Apache Kafka

48

Personnel

Requirements

    • Coconut Research Institute of Sri Lanka
    • Dr. Nayani Aratchige (Principal Entomologist)

​

49 of 53

IT18051612 | Rajapaksha H.M.U.D | 2021 - 042

3/8/2021

Work Breakdown

Structure

49

50 of 53

IT18051612 | Rajapaksha H.M.U.D | 2021 - 042

3/8/2021

References

50

[1] Simperl, E., 2015. How to Use Crowdsourcing Effectively: Guidelines and Examples. LIBER Quarterly, 25(1), p.18.

[2] Blohm, I., Zogaj, S., Bretschneider, U. and Leimeister,J., 2017. How to Manage Crowdsourcing Platforms Effectively?. California Management Review, 60(2), pp.122-149.

[3] Saiz-Rubio, V. and Rovira-Más, F., 2020. From Smart Farming towards Agriculture 5.0: A Review on Crop Data Management. Agronomy, 10(2), p.207.

[4] Ayaz, M., Ammad-Uddin, M., Sharif, Z., Mansour, A. and Aggoune, E., 2019. Internet-of-Things (IoT)-Based Smart Agriculture: Toward Making the Fields Talk. IEEE Access, 7, pp.129551-129583.

[5] R. Miriyagalla et al., "On The Effectiveness of Using Machine Learning and Gaussian Plume Model for Plant Disease Dispersion Prediction and Simulation," 2019 International Conference on Advancements

in Computing (ICAC), Malabe, Sri Lanka, 2019, pp. 317-322, doi: 10.1109/ICAC49085.2019.9103383.

[6] A. Chandy, "PEST INFESTATION IDENTIFICATION IN COCONUT TREES USING DEEP LEARNING", Journal

of Artificial Intelligence and Capsule Networks, vol. 01, no. 01, pp.10-18, 2019. Available: 10.36548/jaicn.2019.1.002.

​

[7] N. Newlands, "Model-Based Forecasting of Agricultural Crop Disease Risk at the Regional Scale, Integrating Airborne Inoculum, Environmental, and Satellite-Based Monitoring Data", Frontiers in Environmental Science, vol. 6, 2018. Available: 10.3389/fenvs.2018.00063.

51 of 53

3/8/2021

51

    • No need of advanced knowledge in technology.

​

    • No age limitation for users.

​

    • No need of prior knowledge regarding coconut.

Target Audience

Market Place

​

    • CRISL - Researchers
    • CDO's
    • Farmers
    • Stakeholders
    • External Parties

Commerlization

Commodity Version:

    • Identification of WCLWD
    • Identification of CCI
    • Identification of Mg deficiency
    • Identification of leaf scorching
    • Realtime notifications
    • Density Map regarding severity

Premium Version:

    • Severity of WCLWD
    • Progression level of CCI

​

Supportive Information

52 of 53

Supportive Information

Budget

3/8/2021

Component

Price

WCLWD Identification

CCI Identification

Travelling cost

Travelling cost

Travelling cost

Nutrient Deficiency Identification

52

Crowdsourcing

OpenWeatherMap API

Deployment cost

Firestore Database cost

Rs. 1960 / location

Rs. 6073 / month

Rs. 5000

Rs. 5000

Rs. 5000

Mobile App -Hosting on Play Store

Mobile App -Hosting on App Store

Rs. 4898

Rs. 19394 /annual

Rs.22 / GB / month

Firebase Messaging Service

Free

53 of 53

Thank You !

3/8/2021

CocoRemedy