Literature Review: Data Clustering for Insect Detection in Agriculture

Desklib provides past papers and solved assignments for students. This literature review explores AI-based insect detection in agriculture.

Review Based Project Literature Review (Secondary Research)
Student's Name and CSU ID
Project Type Review Based Project
Project Name A systematic review of detection techniques based on Clustering methods to identify insects on yields in agriculture
Technology Data Clustering
Techniques Detection technique
Domain Insect identification in agricultural yields.
1

Version 1.0 _ Week 1 (5 Journal Papers from CSU Library)
1
Reference in APA format that will be
in 'Reference List'
(This give the Reference of the
Journal Paper you are working on it)
Banga, K. S., Kotwaliwale, N., Mohapatra, D., Giri, S. K., & Babu, V. B. (2019). Bioacoustic
detection of Callosobruchus chinensis and Callosobruchus maculatus in bulk stored chickpea (Cicer
arietinum) and green gram (Vigna radiata). Food Control.
https://doi.org/10.1016/j.foodcont.2018.07.008
Citation that will be in the content (Banga et al. 2019)
URL of the Reference Level of Journal (Q1, Q2, …Qn) Keywords in this Reference
https://www-sciencedirect-
com.ezproxy.csu.edu.au/science/
article/pii/S095671351930074X
Level of journal- Q1  automatic plant pest detection
 Correspondence filter
 k-means clustering
 Pest recognition
The Name of the Current Solution
(Technique/ Method/ Scheme/
The Goal (Objective) of this Solution &
What is the Problem that need to be
What are the components of it?
2

Algorithm/ Model/ Tool/ Framework/
... etc )
solved
Technique/Algorithm name: detection
technique RCF (Recognition Clustering
Filtration)
Tools:
 Detector
 Lenses
 Thermal imaging cameras
 Electronic nose
Applied Area: In agriculture field for
Bioacoustic detection
Problem: In this research this has been
noticed that insects are destroying the food
grains and reducing the yield of the
agriculture.
Goal:
The goal of research to facilitate pest
detection and mitigating losses in food
storage and maintenance with the use of
RCF technique.
 Bulk density, particle density and porosity
determination
 Acoustic, temperature and relative humidity
measurements-
 Acoustic insect detection
 Signal processing
 Statistical analysis
The Process (Mechanism) of this Work; The process steps of the Technique/system
Process Steps Advantage (Purpose of this step) Disadvantage (Limitation/Challenge)
1 Bulk density, particle density and porosity
determination-bulk density is dry weight of
Knowing the possibility of insects attack. N/A
3

soil per volume. True density is mass of the
product to the volume and porosity depends
on bulk and true density.
2 Acoustic, temperature and relative
humidity measurements- recorded signals
were stored with the help of Audacity
software in computer.
Acoustic shield bin help in this process to
record the sound of insect in every
condition of its surrounding.
Time consuming
3 Acoustic insect detection-it made with the
help of microphone with the range of 20 Hz-
16 KHz
This helps in reducing the interference of
background noise this is achieve with the
microphone.
N/A
4 Signal processing- two channels of sound
spectra use to pre- processed the crawling
This process reduces background noise and
amplifies signals which help to listens
N/A
4

and feeding sounds of insects in distinctive
spectral patterns.
insect sound easily.
5 Statistical analysis- the coefficient of
variation use to find the parameter for insect
detection.
Find significant difference between insect
sound between two conditions with or
without using amplitude of insects sound.
Lengthy process
Validation Criteria (Measurement Criteria)
Dependent Variable Independent Variable
grain kernel amplification and filtering movement and feeding sounds of insect
Based plate Ninhydrin treated filter paper.
Technology Properties involve for detection
Input and Output Critical Thinking: Feature of this work, and
Why (Justify)
Critical Thinking: Limitations of the
research current solution, and Why
(Justify)
Input (Data) Output (View) The features of this work is mentioned below:
 Help in mitigating loses in nutritional
The limitation found in this work are:
 To cover large area more drones
5

 Uric method
 Hidden
infestation
detection
 Electronic
nose
 Level of
infestation
 Hidden
insect
 Volatile
compound
values of grain.
 Provide food security and preservation
of crops and grains.
 Increase the crop yields.
required.
 Time consuming
 Resource consuming
(Describe the research/current solution) Evaluation Criteria How this research/current solution is
valuable for your project
What is the Future work that set by the
author in Conclusion and Future work
section
6

(Banga et al. 2019) introduced the usage of
clustering technique help in agriculture to
detect insects. From naked eyes it is not that
much possible to detect, so few methods are
introduced which will help in protecting the
crop and increasing the revenue.
These methods help to detect insect in all the
aspects and the conditions to yield the
agriculture, this will increase the production
which will result in helping the farmers to grow
more valuable crop.
According to (Banga et al. 2019), the future
work is linked with the advancement in this
technology will help farmers by reducing the
cost development of acoustic mobile app for
specific species.
Diagram/Flowchart
7

Figure 1. Block Diagram of Machine Vision
Reference in APA format that will be in 'Reference List'
 Kumar, S., Mohapatra, D., Kotwaliwale, N., & Singh, K. K. (2017). Vacuum hermetic fumigation: A review. Journal of Stored Products
Research, 71, 47–56.
8

 Aviara, N. A., Fabiyi, O. E., Ojediran, J. O., Ogunniyi, O. I., & Onatola, I. T. (2016). Application of computer vision in food grain quality
inspection, evaluation and control during bulk storage. 37th Annual conference and annual general meeting–“minna 2016”
Citation that will be in the content
 Kumar et al. (2017)
 Aviara et al. (2016)
9

2
Reference in APA format that will be
in 'Reference List'
Srivastava, S., Mishra, G., & Mishra, H. N. (2018). Identification and differentiation of insect infested
rice grains varieties with FTNIR spectroscopy and hierarchical cluster analysis. Food chemistry, 268,
402-410. Doi: https://doi.org/10.1016/j.foodchem.2018.06.095
Citation that will be in the content (Srivastava et al.2019)
URL of the Reference Level of Journal (Q1, Q2, …Qn) Keywords in this Reference
https://www-sciencedirect-
com.ezproxy.csu.edu.au/science/
article/pii/S0308814618310707
Q1 Cluster, histograms, infested rice, dendrograms,
algorithms, hierarchical
The Name of the Current Solution
(Technique/ Method/ Scheme/
Algorithm/ Model/ Tool/ Framework/
... etc )
The Goal (Objective) of this Solution &
What is the Problem that need to be
solved
What are the components of it?
Technique/Algorithm name:
Hierarchical cluster analysis (HCA),
dendrogram (DA), and conformity
Problem: In this research it has been
noticed that the variety of cereal crop rice  FTNIR(The Fourier transform near infrared
10

analysis (CA)
Tools:
 OPUS 5.5 software
 The Fourier transform near
infrared spectroscopy (FTNIR)
for screening
 PbS detector
 integrated Michelson
interferometer
Applied Area:
Identification of infested rice stored
varieties
is getting infested due the insects.
Goal: The goal of this research is to
identify the level of infestation in the
variety of rice by using FTNIR(The
Fourier transform near infrared
spectroscopy)
spectroscopy) spectroscopic computation
 Pearson correlation coefficient for cluster
analysis
 Ward algorithm for cluster analysis
 Hierarchical cluster analysis
 Conformity test
The Process (Mechanism) of this Work; The process steps of the Technique/system
Process Steps Advantage (Purpose of this step) Disadvantage (Limitation/Challenge)
1 FTNIR(The Fourier transform near infrared
spectroscopy) spectroscopic computation-
By this process the spectral scan of rice
grain is done.
N/A
11

this is furnished with quartz beam, and
spectra is formed of wave 13,000–3500
cm−1
2 Pearson correlation coefficient for cluster
analysis- this is used to define the
correlation between the two spectra named
as a and b.
This process gives the differences among
the spectra generated by FTNIR.
N/A
3 Ward algorithm for cluster analysis- The
software OPUS 5.5 is used in this with
minimum variance method.
This helps in storing homogenous groups Lengthy
4 Hierarchical cluster analysis- the distance
between the spectra is calculated.
This method helps in forming the new
cluster.
N/A
5 Conformity test- it easily measures the
deviation of FTNIR spectra
This process at last checks the quality of
the food.
N/A
Validation Criteria (Measurement Criteria)
Dependent Variable Independent Variable
12