International Journal of Computer Science Trends and Technology (IJCST) – Volume 9 Issue 1, Jan-Feb 2021

RESEARCH ARTICLE OPEN ACCESS

Prediction of Groundwater Quality from The Solid Waste

Dumping Areas of the Perungudi-Kodungayur in Chennai
Prof. Tolga ENSARİ
Istanbul University, Computer Engineering, Avcilar Campus,
Avcilar, Istanbul – Turkey

ABSTRACT
The potentially used for various purpose of groundwater quality prediction and monitor is more important [1].
Moreover, the ground water quality is predicted using the hydro-chemical parameter of salinity. The quality of
sub-surface geochemical process, recharged water, inland surface water and atmospheric precipitation is based
on groundwater quality. Furthermore, the water pollution never only affects the quality of water although it
causes the social prosperity, economic development and health [2]. The people are widely utilized round water
for irrigation, industrial purpose and drinking due to inadequate fresh water resource. Because of hidden
existence and natural, the groundwater is regarded as reliable and safe source of drinking water.

I. INTRODUCTION function is to create the Water Quality Index

(WQI). ANN is one of the most commonly used
One of the valuable natural resource for human life methods for ground water quality prediction that
and the most common substance on the ground is evaluate the groundwater contaminants. The main
water. There is deforestation in rural areas due to factor among this is the non-correlation between
the reduction in infiltration rate and exploitation of several variables. More researches have been
groundwater. The potentially used for various carried out on the quality prediction of groundwater
purpose of groundwater quality prediction and using ANN, but the computation of space and time
monitor is more important [1]. Moreover, the is not extensively done [1-67]. In this paper, we
ground water quality is predicted using the hydro- proposed Multiple Layer Perceptron in neural
chemical parameter of salinity. The quality of sub- network to predict the ground water quality from
surface geochemical process, recharged water, the solid waste dumping areas.
inland surface water and atmospheric precipitation
is based on groundwater quality. Furthermore, the II. LITERATURE REVIEW
water pollution never only affects the quality of
water although it causes the social prosperity, Recently, the researchers have been proposed lot of
economic development and health [2]. The people methods to predict the groundwater quality and few
are widely utilized round water for irrigation, of the methods are discussed in the following
industrial purpose and drinking due to inadequate section.
fresh water resource. Because of hidden existence
and natural, the groundwater is regarded as reliable Jasrotia et al. [4] introduced geospatial technique to
and safe source of drinking water [10]. predict the groundwater quality. The case study is
analyzed from Jammu Himalaya in India. The
Globally, the enlarger amount of remote sensing data such as aquifer parameters,
population leads to enormous amount of waste. The SRTM-DEM and IRS-P6 is to prepare various
municipal disposal of waste across the world is thematic layers. The artificial recharge zone map is
increased day by day so the ground water quality prepared from the weighted overlay method in the
gets degraded. The areas nearer to the landfills GIS environment. The proposed model is
have greater probability in the contamination of implemented in Visual Modflow Flex software.
groundwater because of waste disposal in the solid. The artificial recharge zone is validated by the
Recently, most of the states in India will suffer comparison of both groundwater modeling zones
from heavy shortages of water [6, 8]. Therefore, the and GIS based artificial recharge zone map. Bansal
groundwater management is very much important et al. [5] proposed artificial neural network to
and the necessary actions are required in future. predict the water quality index, which can easily
The average water withdrawals are increased by estimate the water pollution. The water quality
50% for the developing countries and 18% for the index is a tedious task to select the weight value of
developed countries in the year of 2015 [3]. The water quality parameters. The missing value
presentation and choice of the accumulation weights are calculated with the help of
mathematical functions and traditional methods

ISSN: 2347-8578 www.ijcstjournal.org Page 78

International Journal of Computer Science Trends and Technology (IJCST) – Volume 9 Issue 1, Jan-Feb 2021

were used to increase the accuracy. The are widely suffered from heavy shortages
contamination status alert is delivered to the of water.
authorities based on mobile app and web interface. • The necessary actions about ground water
Rahim Barzegar et al. [6] introduced radial basis management are more important. So,
function and multiple layer perceptron to detect the sufficient availability and water supply
salinity of groundwater quality. East Azabaijan quality direct to the huge growth for the
regional water company provided the groundwater countries. The solid waste dumping areas
− − cause the quality of ground water so the
samples. They used chlorides Cl , nitrates NO3 ,
ground water quality prediction in the
2− 2+
sulphates SO4 and magnesium Mg are the early stage is more difficult and very
input parameters. The training and testing results important.
are evaluated by using mean absolute error, root 2. Methodology:
mean square error and determination coefficient.
In this work, we analyze the ground water quality
Batur et al. [7] proposed PCA data fusion and from the solid waste dumping areas such as
mining method that easily predict the groundwater Perungudi and Kodungayur in Chennai. This area
quality and salinity. They used TDS, pH, Secchi receives the maximum rainfall from the June and
disk depth, Chlorophyll and Chlorophyll-a as the September (southwest monsoonal wind) and
input parameters for water quality determination. 750mm of average annual precipitation is received.
The proposed model is executed in MATLAB During summer and winter season, the annual
R2015a. As a result, the surface water quality temperature ranges from 39 to10oC. During pre-
prediction accuracy is low. Moghaddam et al. [8] monsoon (May 2018) and post-monsoon
introduced a ground water quality prediction (November 2018), 39 dug well samples were
method of BN and ANN method. The author were collected and analyzed. We proposed Multiple
used input parameters for ground water quality Layer Perceptron (MLP) of neural network is to
prediction are namely average temperature, total predict the groundwater quality. Here, the
monthly evaporation, aquifer recharge and − − 2−
chlorides Cl , nitrates NO3 , sulphates SO4 , its
discharge. The experimental works are evaluated
pH range, total dissolved solids (TDS) and the total
using MODFLOW and Hugin Lite 8.3 software.
hardness (TH) of the water are given to the input
Sengorur et al. [9] established SOM-ANN
parameters of each neuron for ground water quality
approach that detected the pollution source and
prediction.
water quality evaluation. The proposed SOM-ANN
model is evaluated in MATLAB with Intel i4 One of the most common utilized approaches of
processor. As result, the water quality prediction Artificial Neural Network (ANN) is Multiple Layer
method required more time and cost. The water Perceptron (MLP). The structure of MLP consists
quality detection method of PLS-ANN is proposed of one input layer, one output layer and one or
by Song et al. [10]. The ground water quality more than one hidden layer section. The multiple
without contamination is easily detected but the layers Perceptron for ground water quality
root mean square error (RMSE) rate is high. prediction is shown in Fig 1. Usually, the available
data through the use of trial and error procedure is
1. Problem Formulation
to optimize the number of neurons in the hidden
• The extremely sensitive and crucial issue layer. The connections among all the element via
is ground water quality management synaptic weights is to perform the hidden and
because of solid waste and pesticides.
layers calculation in neural network.
• The increasing amount of population leads
to enlarger amount of waste also the The representation of w is the weight applied to
landfills employed as the endpoint for the the neurons. The output value of three layered MLP
municipal disposal of waste across the with its explicit expression is shown in equation
world. (1).
• The infiltration of groundwater is caused
by the waste that is present in the landfills.
 IJ  JJ  
The disposal of waste in the landfills can Yn = Fo  wnm  Fg   wm l X l + wm 0  + wn 0 
affect the areas closer to the landfills that  l =1  l =1  
have greater probability in the
(1)
contamination of groundwater.
• Particularly, one of the major features of th
water management is drinking water From the above equation, the l neurons in the
th
management. Most of the states in India input layer and m neurons in the hidden layer
connected to the hidden layer weight is denoted

ISSN: 2347-8578 www.ijcstjournal.org Page 79

International Journal of Computer Science Trends and Technology (IJCST) – Volume 9 Issue 1, Jan-Feb 2021

th
as wm l . For m hidden neurons, the bias function compression technique for data transmission
on industrial Internet of things
and the activation function is denoted applications. Transactions on Emerging
th
as wm 0 and Fg . The m neurons in the hidden Telecommunications Technologies, e3976.
th [5] Ezhilarasu, P., Krishnaraj, N., &Dhiyanesh,
layer and n neurons in the output layer is B. (2015). Arithmetic Coding for Lossless
connected to the output weight is expressed Data Compression–A Review. International
th
as wnm . The n output neurons with its bias and Journal of Computer Science Trends and
Technology, 3(3).
activation function are expressed by wn 0 and F0 . [6] Porkodi, V., Singh, A. R., Sait, A. R. W.,
The input variable is X l and the output variable is Shankar, K., Yang, E., Seo, C., & Joshi, G.
P. (2020). Resource Provisioning for Cyber–
computed using Ym . The number of neurons in the Physical–Social System in Cloud-Fog-Edge
input layer and hidden layer is denoted as Computing Using Optimal Flower
I J and J J . During training process, the input and Pollination Algorithm. IEEE Access, 8,
105311-105319.
output layers have different weight and it become [7] Gao, D., Wang, G. G., &Pedrycz, W. (2020).
changed in nature. Using different weight is to Solving fuzzy job-shop scheduling problem
connect each layer neurons with adjacent layer. The using DE algorithm improved by a selection
previous layer weight is to provide the signal to mechanism. IEEE Transactions on Fuzzy
each neuron except in the input layer. By passing Systems.
the summed signal via activation function is to [8] Sivaram, M., Mohammed, A. S., Yuvaraj,
produce an output signal. The output minimizes the D., Porkodi, V., Manikandan, V., &Yuvaraj,
error value rate thereby delivering the optimal N. (2019, February). Advanced expert
water quality. system using particle swarm optimization
based adaptive network based fuzzy
3. Possible Outcome inference system to diagnose the physical
constitution of human body. In International
This paper proposed Multiple Layer Perceptron of
Conference on Emerging Technologies in
neural network for the prediction of groundwater
quality. The dataset details are collected from solid Computer Engineering (pp. 349-362).
Springer, Singapore.
waste dumping areas such as Perungudi and
[9] Jiménez, A. C., García-Díaz, V., González-
Kodungaiyur in Chennai. We fed eight neurons to
Crespo, R., &Bolaños, S. (2018).
the hidden layers. The training and testing
Decentralized Online Simultaneous
parameters of proposed method is evaluated using
state-of-art approaches namely linear regression, Localization and Mapping for Multi-Agent
Systems. Sensors, 18(8), 2612.
fuzzy approach, AFSO, and asymmetric neuro-
[10] Venkatraman, S., Surendiran, B., & Kumar,
fuzzy. The experimental results demonstrate that
the proposed MLP delivers low RMSE value and P. A. R. (2020). Spam e-mail classification
for the Internet of Things environment using
high water quality prediction performance.
semantic similarity approach. The Journal of
Supercomputing, 76(2), 756-776.
REFERENCES
[11] Lydia, E. L., Raj, J. S., PandiSelvam, R.,
[1] Feng, Y., Yi, J. H., & Wang, G. G. (2019). Elhoseny, M., & Shankar, K. (2019).
Enhanced Moth Search Algorithm for the Application of discrete transforms with
Set-Union Knapsack Problems. IEEE selective coefficients for blind image
Access, 7, 173774-173785. watermarking. Transactions on Emerging
[2] Sivaram, M., Batri, K., Amin Salih, M., Telecommunications Technologies, e3771.
&Porkodi, V. (2019). Exploiting the Local [12] Ezhilarasu, P., Prakash, J., Krishnaraj, N.,
Optima in Genetic Algorithm using Tabu Kumar, D. S., Babu, K. S., &Parthasarathy,
Search. Indian Journal of Science and C. (2015). A Novel Approach to Design the
Technology, 12(1), 1-13. Finite Automata to Accept the Palindrome
[3] Venkatraman, S., &Surendiran, B. (2020). with the Three Input Characters. Indian
Adaptive hybrid intrusion detection system Journal of Science and Technology, 8(28).
for crowd sourced multimedia internet of [13] Devaraj, A. F. S., Elhoseny, M.,
things systems. Multimedia Tools and Dhanasekaran, S., Lydia, E. L., & Shankar,
Applications, 79(5), 3993-4010. K. (2020). Hybridization of firefly and
[4] Sujitha, B., Parvathy, V. S., Lydia, E. L., Improved Multi-Objective Particle Swarm
Rani, P., Polkowski, Z., & Shankar, K. Optimization algorithm for energy efficient
(2020). Optimal deep learning based image load balancing in Cloud Computing

ISSN: 2347-8578 www.ijcstjournal.org Page 80

International Journal of Computer Science Trends and Technology (IJCST) – Volume 9 Issue 1, Jan-Feb 2021

environments. Journal of Parallel and [24] Porkodi, V., Khan, J., Mohammed, A. S.,
Distributed Computing. Bhuvana, J., & Sivaram, M. OPTIMIZED
[14] Zou, D., Wang, G. G., Sangaiah, A. K., & COOPERATIVE QOS ENHANCED
Kong, X. (2017). A memory-based DISTRIBUTED MULTIPATH ROUTING
simulated annealing algorithm and a new PROTOCOL.
auxiliary function for the fixed-outline [25] Geerthik, S., Venkatraman, S., & Gandhi, R.
floorplanning with soft blocks. Journal of (2016). AnswerRank: Identifying Right
Ambient Intelligence a+nd Humanized Answers in QA system. International Journal
Computing, 1-12. of Electrical and Computer
[15] Kumar, A., Ahuja, H., Singh, N. K., Gupta, Engineering, 6(4), 1889.
D., Khanna, A., & Rodrigues, J. J. (2018). [26] Samad, A., Salima, R., Lydia, E. L., &
Supported matrix factorization using Shankar, K. (2020). Definition and Features
distributed representations for personalised of Rural Marketing Strategies for Encourage
recommendations on twitter. Computers & Development in Rural Areas. TEST
Electrical Engineering, 71, 569-577. Engineering & Management, 82, 4983-4988.
[16] Sivaram, M., Porkodi, V., Mohammed, A. [27] Palani, E., Nagappan, K., &Alhadidi, B.
S., Manikandan, V., &Yuvaraj, N. (2019). (2016). Segmentation and Texture Analysis
Retransmission DBTMA protocol with fast for Efficient Classification of Breast Tumors
retransmission strategy to improve the from Sonograms. Current Signal
performance of MANETs. IEEE Access, 7, Transduction Therapy, 11(2), 84-90.
85098-85109. [28] Rajagopal, A., Ramachandran, A., Shankar,
[17] Venkatraman, S., & Kumar, P. A. R. (2019). K., Khari, M., Jha, S., Lee, Y., & Joshi, G.
Improving Adhoc wireless sensor networks P. (2020). Fine-tuned residual network-
security using distributed automaton. Cluster based features with latent variable support
Computing, 22(6), 14551-14557. vector machine-based optimal scene
[18] Lydia, E. L., Govindaswamy, P., classification model for unmanned aerial
Lakshmanaprabu, S., &Ramya, D. (2018). vehicles. IEEE Access, 8, 118396-118404.
Document clustering based on text mining [29] Mondragon, V. M., García-Díaz, V., Porcel,
K-means algorithm using euclidean distance C., & Crespo, R. G. (2018). Adaptive
similarity. J. Adv. Res. Dyn. Control contents for interactive TV guided by
Syst.(JARDCS), 10(2), 208-214. machine learning based on predictive
[19] Ortin, F., Mendez, S., García‐Díaz, V., & sentiment analysis of data. Soft
Garcia, M. (2014). On the suitability of Computing, 22(8), 2731-2752.
dynamic languages for hot‐reprogramming a [30] Feng, Y., Yu, X., & Wang, G. G. (2019). A
robotics framework: a Python case Novel Monarch Butterfly Optimization with
study. Software: Practice and Global Position Updating Operator for
Experience, 44(1), 77-104. Large-Scale 0-1 Knapsack
[20] Krishnaraj, N., Ezhilarasu, P., & Gao, X. Z. Problems. Mathematics, 7(11), 1056.
Hybrid Soft Computing Approach for [31] Mohammed, A. S., & Sivaram, P. (2018).
Prediction of Cancer in Colon Using Securing the Sensor Networks Along With
Microarray Gene Data. Current Signal Secured Routing Protocols for Data Transfer
Transduction Therapy, 11(2). in Wireless Sensor Networks.
[21] Le Nguyen, B., Lydia, E. L., Elhoseny, M., [32] Geerthik, S., Venkatraman, S., & Gandhi, K.
Pustokhina, I., Pustokhin, D. A., Selim, M. R. (2016, February). Reward rank: A novel
M., ... & Shankar, K. (2020). Privacy approach for positioning user answers in
Preserving Blockchain Technique to community question answering system.
Achieve Secure and Reliable Sharing of IoT In 2016 International Conference on
Data. CMC-COMPUTERS MATERIALS & Information Communication and Embedded
CONTINUA, 65(1), 87-107. Systems (ICICES) (pp. 1-6). IEEE.
[22] Chavhan, S., Gupta, D., Chandana, B. N., [33] Sivaram, M., Lydia, E. L., Pustokhina, I. V.,
Khanna, A., & Rodrigues, J. J. (2019). IoT- Pustokhin, D. A., Elhoseny, M., Joshi, G. P.,
based Context-Aware Intelligent Public & Shankar, K. (2020). An optimal least
Transport System in a metropolitan square support vector machine based
area. IEEE Internet of Things Journal. earnings prediction of blockchain financial
[23] Gu, Z. M., & Wang, G. G. (2020). products. IEEE Access, 8, 120321-120330.
Improving NSGA-III algorithms with [34] Ghantasala, G. P., &KrishnaRaj, N. Support
information feedback models for large-scale Vector Machine Based Automatic
many-objective optimization. Future Mammogram Classification Using Hybrid
Generation Computer Systems, 107, 49-69. Optimization Algorithm.

ISSN: 2347-8578 www.ijcstjournal.org Page 81

International Journal of Computer Science Trends and Technology (IJCST) – Volume 9 Issue 1, Jan-Feb 2021

[35] Sikkandar, M. Y., Alrasheadi, B. A., transfer in IoT networks. Wireless Networks,
Prakash, N. B., Hemalakshmi, G. R., 1-14.
Mohanarathinam, A., & Shankar, K. (2020). [46] Subbarayalu, V., Surendiran, B., &Arun Raj
Deep learning based an automated skin Kumar, P. (2019). Hybrid Network Intrusion
lesion segmentation and intelligent Detection System for Smart Environments
classification model. Journal of Ambient Based on Internet of Things. The Computer
Intelligence and Humanized Computing, 1- Journal, 62(12), 1822-1839.
11. [47] Rosa, A. T. R., Pustokhina, I. V., Lydia, E.
[36] Zhang, Z., Wang, G. G., Zou, K., & Zhang, L., Shankar, K., & Huda, M. (2019).
J. (2014). A solution quality assessment Concept of electronic document
method for swarm intelligence optimization management system (EDMS) as an efficient
algorithms. The Scientific World tool for storing document. Journal of Critical
Journal, 2014. Reviews, 6(5), 85-90.
[37] Sivaram, Murugan et al. ‘Data Fusion Using [48] Espada, J. P., Diaz, V. G., Crespo, R. G.,
Tabu Crossover Genetic Algorithm in Bustelo, B. C. P. G., &Lovelle, J. M. C.
Information Retrieval’. 1 Jan. 2020 : 1 – 10. (2015). An intelligent Mobile Web Browser
[38] Khamparia, A., Pandey, B., Tiwari, S., to adapt the mobile web as a function of the
Gupta, D., Khanna, A., & Rodrigues, J. J. physical environment. IEEE Latin America
(2020). An integrated hybrid CNN–RNN Transactions, 13(2), 503-509.
model for visual description and generation [49] Kumar, R. S., Krishnaraj, N., &Keerthana,
of captions. Circuits, Systems, and Signal G. (2017). Assessment of Quality of Service
Processing, 39(2), 776-788. in Communication Network and Evaluating
[39] Geerthik, S., Gandhi, K. R., &Venkatraman, Connectivity Among IP Networks. Asian
S. (2016, December). Domain expert Journal of Applied Science and Technology
ranking for finding domain authoritative (AJAST), 1(3), 319-322.
users on community question answering [50] Elhoseny, M., Rajan, R. S., Hammoudeh,
sites. In 2016 IEEE International Conference M., Shankar, K., &Aldabbas, O. (2020).
on Computational Intelligence and Swarm intelligence–based energy efficient
Computing Research (ICCIC) (pp. 1-5). clustering with multihop routing protocol for
IEEE. sustainable wireless sensor
[40] Muruganantham, A., Nguyen, P. T., Lydia, networks. International Journal of
E. L., Shankar, K., Hashim, W., &Maseleno, Distributed Sensor Networks, 16(9),
A. (2019). Big data analytics and 1550147720949133.
intelligence: A perspective for health care. [51] Chu, H. C., Wang, G. G., & Park, J. H.
[41] Ramkumar, V., &Krishnaraj, N. Weight (2015). The digital fingerprinting analysis
Based LSA to Retrieve Information from concerning google calendar under ubiquitous
Web Pages Based On Document Score. mobile computing era. Symmetry, 7(2), 383-
[42] Balakiruthiga, B., Deepalakshmi, P., 394.
Mohanty, S. N., Gupta, D., Kumar, P. P., & [52] Manikandan, V., Sivaram, M., Mohammed,
Shankar, K. (2020). Segment routing based A. S., &Porkodi, V. (2020). Nature Inspired
energy aware routing for software defined Improved Firefly Algorithm for Node
data center. Cognitive Systems Research. Clustering in WSNs. CMC-COMPUTERS
[43] Chu, H. C., Wang, G. G., & Deng, D. J. MATERIALS & CONTINUA, 64(2), 753-
(2016). The social networking investigation 776.
of metadata of forensic artifacts of a typical [53] Kuppusamy, P., Venkatraman, S.,
WeChat session under Windows. Security Rishikeshan, C. A., & Reddy, Y. P. (2020).
and Communication Networks, 9(18), 5698- Deep learning based energy efficient optimal
5709. timetable rescheduling model for intelligent
[44] Sivaram, M., Yuvaraj, D., Mohammed, A. metro transportation systems. Physical
S., Manikandan, V., Porkodi, V., &Yuvaraj, Communication, 101131.
N. (2019). Improved Enhanced Dbtma with [54] Asih, E. S., Nguyen, P. T., Lydia, E. L.,
Contention-Aware Admission Control to Shankar, K., Hashim, W., &Maseleno, A.
Improve the Network Performance in (2019). Mobile E-commerce website for
Manets. CMC-COMPUTERS MATERIALS technology-based buying selling
& CONTINUA, 60(2), 435-454. services. International Journal of
[45] Gochhayat, S. P., Lal, C., Sharma, L., Engineering and Advanced
Sharma, D. P., Gupta, D., Saucedo, J. A. M., Technology, 8(6), 884-888.
&Kose, U. (2019). Reliable and secure data [55] Lydia, E. L., &Swarup, M. B. (2015). Big
data analysis using hadoop components like

ISSN: 2347-8578 www.ijcstjournal.org Page 82

International Journal of Computer Science Trends and Technology (IJCST) – Volume 9 Issue 1, Jan-Feb 2021

flume, mapreduce, pig and [66] Wei, C. L., & Wang, G. G. (2020). Hybrid
hive. International Journal of Science, Annealing Krill Herd and Quantum-Behaved
Engineering and Computer Particle Swarm
Technology, 5(11), 390. Optimization. Mathematics, 8(9), 1403.
[56] Sengar, S. S., Hariharan, U., &Rajkumar, K. [67] Sivaram, M., Yuvaraj, D., Mohammed, A.
(2020, March). Multimodal Biometric S., &Porkodi, V. Estimating the Secret
Authentication System using Deep Learning Message in the Digital Image. International
Method. In 2020 International Conference Journal of Computer Applications, 975,
on Emerging Smart Computing and 8887.
Informatics (ESCI) (pp. 309-312). IEEE. [68] Nieto, Y., Gacía-Díaz, V., Montenegro, C.,
[57] Maseleno, A., Hashim, W., Perumal, E., González, C. C., & Crespo, R. G. (2019).
Ilayaraja, M., & Shankar, K. (2020). Access Usage of machine learning for strategic
control and classifier-based blockchain decision making at higher educational
technology in e-healthcare applications. institutions. IEEE Access, 7, 75007-75017.
In Intelligent Data Security Solutions for e-
Health Applications (pp. 151-167).
Academic Press.
[58] Li, J., Lei, H., Alavi, A. H., & Wang, G. G.
(2020). Elephant Herding Optimization:
Variants, Hybrids, and
Applications. Mathematics, 8(9), 1415.
[59] Mohammed, A. S., Kareem, S. W., Al
Azzawi, A. K., & Sivaram, M. (2018). Time
series prediction using SRE-NAR and SRE-
ADALINE. Journal of Advanced Research
in Dynamical and Control Systems, Pages,
1716-1726.
[60] Shankar, K., Elhoseny, M., Chelvi, E. D.,
Lakshmanaprabu, S. K., & Wu, W. (2018).
An efficient optimal key based chaos
function for medical image security. IEEE
Access, 6, 77145-77154.
[61] Geerthik, S., Gandhi, R., &Venkatraman, S.
(2006). CATEGORY BASED EXPERT
RANKING: A NOVEL APPROACH FOR
EXPERT IDENTIFICATION IN
COMMUNITY QUESTION ANSWERING.
[62] Laxmi, C. V., &Somasundaram, K. (2014).
Application Level Scheduling (AppLeS) in
Grid with Quality of Service
(QoS). International Journal of Grid
Computing & Applications, 5(2), 1.
[63] Kumar, R. S., Krishnaraj, N., &Keerthana,
G. Highly Energy Efficient and Scalable
Distributed Clustering Procedure for Dense
Wireless Sensor Networks.
[64] Krishnaraj, N., Kumar, K. A., & Kumar, P.
K. (2018). DESIGN OF ADAPTIVE
SCHEDULER TO IMPROVE
PERFORMANCE OF COMPUTATIONAL
GRIDS. International Journal of Pure and
Applied Mathematics, 119(18), 1741-1751.
[65] Shankar, K., & Eswaran, P. (2016, January).
A new k out of n secret image sharing
scheme in visual cryptography. In 2016 10th
International Conference on Intelligent
Systems and Control (ISCO) (pp. 1-6).
IEEE.

ISSN: 2347-8578 www.ijcstjournal.org Page 83