See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/351285887

Fault Detection in Wireless Sensor Network Based on Deep Learning

Algorithms

Article  in  ICST Transactions on Scalable Information Systems · May 2021

DOI: 10.4108/eai.3-5-2021.169578

CITATIONS READS

2 583

3 authors:

Regin Rajan Suman Rajest

Adhiyamaan College of Engineering Vels University
54 PUBLICATIONS   171 CITATIONS    56 PUBLICATIONS   584 CITATIONS   

SEE PROFILE SEE PROFILE

Bhopendra Singh
AMITY UNIVERSITY.DUBAI
27 PUBLICATIONS   168 CITATIONS   

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Supply chain marketing system View project

Optimized Node Clustering based on Received Signal Strength with Particle Ordered-filter Routing Used in VANET View project

All content following this page was uploaded by Regin Rajan on 03 May 2021.

The user has requested enhancement of the downloaded file.

EAI Endorsed Transactions
on Scalable Information Systems Research Article

Fault Detection in Wireless Sensor Network Based on

Deep Learning Algorithms
R. Regin1,*, S. Suman Rajest2 and Bhopendra Singh3

1
Assistant Professor, Department of Information Technology, Adhiyamaan College of Engineering, Tamil Nadu, India.
2
Researcher, Vels Institute of Science, Technology & Advanced Studies (VISTAS), Chennai, Tamil Nadu, India.
3
Associate Professor, Amity University, Dubai. E-mail: [email protected]

Abstract
This paper is about Fault detection over a wireless sensor network in a fully distributed manner. First, we proposed the
Convex hull algorithm to calculate a set of extreme points with the neighbouring nodes and the duration of the message
remains restricted as the number of nodes increases. Second, we proposed a Naïve Bayes classifier and convolution neural
network (CNN) to improve the convergence performance and find the node faults. Finally, we analyze convex hull, Naïve
bayes and CNN algorithms using real-world datasets to identify and organize the faults. Simulation and experimental
outcomes retain feasibility and efficiency and show that the CNN algorithm has better-identified faults than the convex
hull algorithm based on performance metrics.

Keywords: Wireless sensor network, Fault detection, Convolution neural network, convex hull, Naive-Bayes, performance metrics and
energy efficiency.

Received on 04 January 2021, accepted on 17 April 2021, published on 03 May 2021

Copyright © 2021 R. Regin et al., licensed to EAI. This is an open access article distributed under the terms of the Creative
Commons Attribution license, which permits unlimited use, distribution and reproduction in any medium so long as the original work
is properly cited.

doi: 10.4108/eai.3-5-2021.169578

Corresponding author. Email: [email protected]

*

issue based on the preparation set's cardinality. A subset

of the preparation set, known as support vectors,
1. Introduction communicates the subsequent discriminating guideline
[12]. In new studies, distributed SVM preparation was
Due to recent advances in wireless communication and investigated due to tight energy, data transfer capacity,
embedded computing, wireless sensor networks can and various imperatives on wireless sensor systems'
deliver various applications identified. Wireless sensor communication capabilities. One methodology is a
networks have been widely used to support various parallel structure of centralized SVM [16], [10]. When the
monitoring and control applications, such as information collection of training is enormous, partial
environmental surveillance, industrial sensing, or traffic SVMs are obtained using small subsets of training and
checking. WSNs include enormous quantities of small, joined in a combination focus. This methodology can
low power, wireless devices, for example, monitoring the handle huge information sizes but can be applied only if a
environment, industrial sensing, or traffic. WSNs include central processor is accessible to join the incomplete,
huge quantities of wireless devices, small, low power, partial support vectors [17-24]. The arbitrary partitioning
regularly sent at remote and badly arranged locales. of the data set is not constantly guaranteed to the
Various mobile and unavoidable applications are always concentrated SVM [7]. Then again, there are completely
gathering and handling data from the physical world and appropriate methodologies for the whole SVM utilizing
giving data about the detected condition or occasions at a conveyed enhancement strategies [25-32].
high level of detail. Specifically, SVM is a classification Since SVM is a quadratic advancement issue, an
algorithm with the advantages of broad applicability, existing convex optimization method can be utilized. A
sparsity of information, and optimal worldwide. Preparing distributed SVM was introduced in [4] that receive the
an SVM requires a quadratic dimensionality optimization multiplier exchange direction technique [3].

EAI Endorsed Transactions on

1 Scalable Information Systems
Online First
R. Regin, S. Suman Rajest and Bhopendra Singh

This methodology relies on neighbourhood message

trading and is proven to be linked to centralized SVM. As
the gradient-based iteration should maintain the
connection between nodes until combination, it may result
in enormous intercommunication costs. Also, the traded
message duration may turn out to be incredibly long in a
nonlinear situation [33-37]. These problems make
wireless sensor network applications inappropriate.
Another distributed SVM class, which did not rely on the
gradient method, relies on the distributed support vectors
obtained from neighbouring information collections [2],
[1]. These gossips based distributed SVM methodologies
ensure intermingling when the marked classes are linearly
divisible. When they are not directly distinguishable,
these methodologies can be rough, even though not
guaranteed, intermingling with the SVM arrangement. Figure 1. Architecture of Sensor Network
The concept of gossip-based gradual SVM with a Application
geometric depiction is used in this article. The geometric
understanding of SVM relies on the concept of the convex
hull and the nearest geometric point calculations [11], [8]. Error is an incorrect distinguishing of a state or
Not at all like the incremental support vectors based on occasion in the given space at the middleware layer due to
gossip [14]. At that point, we recognize the fault in the a deficiency. An error is an effect whose reason is some
system we proposed and analyzed methods, such as lack. This considers a logically outrageous issue with the
convex hull, Naïve Bayes and CNN [15]. The devices since they are alive anyway, identifying
Convolution Neural Network gives better fault detection inaccurately. Therefore, services fail at the application
when compared to the other methods. This paper's level either due to middleware erroror the physical layer
structure is as follows. Section 2 emphasizes the [6]. Therefore, failures in such dynamic and interactive
suggested framework model in this work; section 3 systems can result in user displeasure. For instance,
clarifies the findings of the experiments, and chapter 4 various sensors are used to identify a user in a smart
concludes the paper [38-43]. home. When a user comes home, the system settings are
configured according to user preferences. Failure to
correctly identify the user can result in an unexpected
2. Methodology system configuration. Faults in any device can lead to the
inappropriate control and usage of devices in the physical
We are using algorithms such as the convex hull, Naïve environment [9]. For example, incorrect sensing of
Bayes, and CNN algorithm in this proposed work. In the temperature sensor readings can cause over-cooling or
convex hull algorithm, the message is exchanged only overheating in the room or physical space.
with adjacent nodes [44-51]. The network link's topology
is fundamentally decided with one-hop communication
where the proportion of traded information can be 2.1. Convex Hull Algorithm
controlled, even in the most pessimistic scenario. The
naïve Bayes classifier and CNN algorithms identify the Convex hull for a set Scan likewise be characterized as
system faults in a wireless sensor network to improve the the arrangement of focuses that can be communicated as
power and convergence performance [5]. The CNN arched mixes of the points in that set S. Convex hull have
technique achieves better performance when compared to their image processing applications, design
other techniques [13]. Generally, a fault can happen to a acknowledgement, etc. medicinal recreations. A convex
physical layer device, as shown up underneath Figure 1. hull is diverse for various items since it depends on the
Deficiency is a deviation of, on any occasion, one feature point of each object. The convex hull can be
trademark property or parameter of the system from characterized for the object of any sort with any number
conventional activity [52-59]. For example, of measurements. The convex hull's complexity and
insufficiencies can occur in light of the way that a extreme points are focused on the feature space's
network node is broken due to low battery, dimensionality.
correspondence impedance, physical damage, and
environmental deterrent [60-61]. In Feature Space, Convex Hull Algorithm

Input: set No = {c1} and N=∅, arbitrarily picked c1 ∈ C

Initialize: C* = C − No
Until C* is empty,
Get c ∈ C*, update C* = C* − {c}

EAI Endorsed Transactions on

2 Scalable Information Systems
Online First
 Fault Detection in Wireless Sensor Network Based on Deep Learning Algorithms

If Checkpoint (c, No) = False, N = No {c} Where each attribute set A={ A1, A2... An} is made up of
Until No is empty, the values of n attributes. Instead of calculating the class
Get k ∈ No, update No = No − {y} conditional probability for each grouping of A, only
If Checkpoint (k, N− {k}) = True, N = N− {y} estimate the conditional probability of each Ai given C
No = N with the conditional independence assumption. The latter
Output: the extreme point set of C, E(C) = No strategy is more practical because it does not require a
very big training set to get a decent assessment of the
probability.

𝑃𝑃(𝐶𝐶) ∏𝑛𝑛𝑖𝑖=1 𝑃𝑃(𝐴𝐴𝑖𝑖 \𝐶𝐶)

𝑃𝑃(𝐶𝐶|𝐴𝐴) =
𝑃𝑃(𝐴𝐴)

Since P (A) is set for each A, choosing the class that

maximizes the numerator word is adequate.
𝑛𝑛

𝑃𝑃(𝐶𝐶) � 𝑃𝑃(𝐴𝐴𝑖𝑖 \𝐶𝐶)

𝑖𝑖=1

There are several benefits to the naive Bayesian

classifier. It's simple to use, and unlike other approaches
to classification, you only need to scan the training data
once. The naïve Bayesian classifier can manage missing
Figure 2. Faults in Wireless Sensor Network attribute values readily by merely omitting the likelihood
of membership in each class. The algorithm of the SVM
naïve Bayers classifier is described as follows.
The performance of machine learning techniques to Algorithms
detect faulty sensor readings and classify data and system
fault types in WSNs is shown in Figure 2. Classifying the • Read information
type of data and system faults is necessary to confirm the • Create a cvpartition purpose that defines folds
accuracy of a WSN. Differentiating data faults from • Create a guidance set
system faults is essential to identify the causes of failure • Create an analysis set
and to offer precise recovery action. In the first step, we • compute the class likelihood
collect data from multiple sensors at the base station. We • normal training set distribution percentage
operate under the assumption that at the time that we
collect this data from these sensors, faults have not yet Parameters
conceded into the sensors. At the second step, to apply
machine learning techniques, the fault detection problem • test set probability
is formulated into a binary classification problem where • kernel supply
the fault types are learned from the given dataset and used • test set estimate likelihood
as reference models to classify new runtime observations • re-structure
and concludes whether the sensor reading is faulty or not. • get an anticipated test set output
Our goal is to identify and classify the type of fault and • compare expected output with the actual set
take actions to recover from faults.
Naive Bayes requires better fault detection as it is
2.2 Naïve Bayes necessary to calculate the probabilistic models from a
Naive Bayes is one of the most effective and effective continuous distribution. This means the training phase is
learning algorithms for inductive learning. Naive pretty fast. The computing time, the best algorithm for
Bayesian classifier is a simple classification scheme that classification error, appears to be the Naïve Bayes
estimates the class-conditional probability by assuming algorithm. The Naïve Bayes algorithm is better than the
that the attributes are conditionally independent given the convex hull algorithm.
class label c. The conditional hypothesis of independence
can be indicated officially as follows 2.3 Convolution Neural Network
A convolutional neural network (CNN) is a specific type
𝑛𝑛
of artificial neural network that uses perceptron, a
𝑃𝑃(𝐶𝐶|𝐴𝐴) = 𝑐𝑐 = � 𝑃𝑃(𝐴𝐴𝑖𝑖 \𝐶𝐶 = 𝑐𝑐 machine learning unit algorithm, for supervised learning
𝑖𝑖=1 to analyze data. CNN's apply to image processing, natural
language processing and other kinds of cognitive tasks. A
convolutional neural network is also known as a ConvNet

EAI Endorsed Transactions on

3 Scalable Information Systems
Online First
R. Regin, S. Suman Rajest and Bhopendra Singh

Algorithm

Step 1: Convolution Operation

The first building block in our plan of attack is

convolution operation
Step 1b: ReLU Layer

The second part of this step will involve the Rectified

Linear Unit or ReLU

Step 2: Pooling

In this part, we'll cover pooling and will get to understand

exactly how it generally works. Figure 4. Computation of Extreme Points

Step 3: Flattening
Figure 4 demonstrates extreme points of growing nodes
This will be a brief breakdown of the flattening process using a convex hull algorithm that includes all
and how we move from pooled to flattened layers when information points in the extreme point set. The message
working with Convolutional Neural Networks. length remains bounded as the number of nodes increases.

Step 4: Full Connection

In this part, everything that we covered throughout the

section will be merged. By learning this, you'll get to
envision a fuller picture of how Convolutional Neural
Networks.

3. Experimental Results
The experimental outcomes of the proposed research are
defined as follows, which will be implemented in the
MATLAB 2018a software platform

Figure 5. Sink node and Fault node

Figure 5 represents the fault and the sink node. All the
communication in the wireless sensor network is taken
place between source and destination. The destination is
called a base station or sink node.

Figure 3. Node Creation

Figure 3 demonstrates a node creation representing the

information in a single data structure. These nodes may
contain exchanged information, condition, or data from
another node. Figure 6. Comparison between Sink node and the
Fault node

EAI Endorsed Transactions on

4 Scalable Information Systems
Online First
 Fault Detection in Wireless Sensor Network Based on Deep Learning Algorithms

Figure 6 demonstrates the comparison between sink and Figure 9 shows the performance analysis of convex hull,
fault node by using naïve Bayes classifier Naïve Bayes and CNN techniques. The deep learning
method provides better results than the Naïve-Bayes
algorithm and the convex hull. This proposed work easily
detects the faults and gives better energy efficiency, and
Here, the time consumption is very low compared to both
techniques.

4. Conclusion
This paper proposed fault detection in wireless sensor
network using different algorithms such as Convex hull,
Naïve Bayes and convolution neural network. The convex
hull algorithm relies on incremental nodes where the
nodes acquired at the extreme points of their local convex
Figure 7. Fault Detection Using CNN hulls' duration of the message, and the number of nodes
increases. The naïve Bayes and CNN improves energy
efficiency and identifies the system faults in a wireless
Figure 7 shows that the performance of Node faults sensor network. Next, we analyzed these three algorithms'
detection by using a convolution neural network. The comparative study to recognize wireless sensor network
CNN technique detects fault easily from all the hidden information and system faults. Our findings show that
nodes. CNN is doing better than other algorithms to detect faults.
Simulation and experimental outcomes promote
feasibility and efficiency. We will study how to use RL
techniques to coordinate multiple MCs to complete the
charging task in future work jointly. And the
implementation of our proposed charging scheme will be
performed and investigated in a practical environment.

References
[1] Bennett, Kristin P., and Erin J. Bredensteiner. "Duality and
geometry in SVM classifiers." In ICML, vol. 2000, pp. 57-
64. 2000.
[2] Caragea, Doina, Adrian Silvescu, and Vasant Honavar.
Figure 8. Power Consumption Analysis "Agents that learn from distributed dynamic data sources."
In Proceedings of the Workshop on Learning Agents,
Agents, pp. 53-61. 2000.
Figure 8 shows a region where both the average length of [3] K. Flouri, B. Beferull-Lozan, and P. Tsakalides,
the path and the estimated power consumption is small. In "Distributed consensus algorithms for SVM training in
this region, with only a negligible rise in energy wireless sensor networks," in Proc. IEEE 16th Eur. Signal
consumption, we can significantly enhance our suggested Process. Conf., Laussane, Switzerland, 2008, pp. 1048–
1054
CNN algorithm's efficiency in terms of convergence [4] Forero, Pedro A., Alfonso Cano, and Georgios B.
velocity. Giannakis. "Consensus-based distributed support Bertsekas
110
Comparison of various classfiers
and J. Tsitsiklis, Parallel and Distributed Computation:
100
fault detection Numerical Methods. Belmont, MA, USA: Athena
Energy efficiency
90
time Scientific, 1997.
[5] Ge, Yong-Feng, Jinli Cao, Hua Wang, Yanchun Zhang,
80
and Zhenxiang Chen. "Distributed Differential Evolution
70
for Anonymity-Driven Vertical Fragmentation in
Outsourced Data Storage." In International Conference on
% values

60

50 Web Information Systems Engineering, pp. 213-226.

40 Springer, Cham, 2020.
30 [6] Ge, Yong-Feng, Wei-Jie Yu, Jinli Cao, Hua Wang, Zhi-
20
Hui Zhan, Yanchun Zhang, and Jun Zhang. "Distributed
10
Memetic Algorithm for Outsourced Database
Fragmentation." IEEE Transactions on Cybernetics (2020).
1
Convex-hull
2
Naive-Bayer-Classifier
3
CNN
[7] Graf, Hans P., Eric Cosatto, Leon Bottou, Igor
Dourdanovic, and Vladimir Vapnik. "Parallel support
Figure 9. Performance Analysis

EAI Endorsed Transactions on

5 Scalable Information Systems
Online First
R. Regin, S. Suman Rajest and Bhopendra Singh

vector machines: The cascade svm." In Advances in neural [22] U. Naseem, S. K. Khan, M. Farasat, and F. Ali, "Abusive
information processing systems, pp. 521-528. 2005. Language Detection: A Comprehensive Review," Indian
[8] He, Q. Peter, and Jin Wang. "Fault detection using the k- Journal of Science Technology, vol. 12, no. 45, pp. 1-13,
nearest neighbor rule for semiconductor manufacturing 2019.
processes." IEEE transactions on semiconductor [23] Rupapara, V., Narra, M., Gonda, N. K., & Thipparthy, K.
manufacturing 20, no. 4 (2007): 345-354. (2020). Relevant Data Node Extraction:A Web Data
[9] Islam, Md Rafiqul, Muhammad Ashad Kabir, Ashir Extraction Method for Non Contagious Data. 2020 5th
Ahmed, Abu Raihan M. Kamal, Hua Wang, and International Conference on Communication and
AnwaarUlhaq. "Depression detection from social network Electronics Systems (ICCES), 500–505.
data using machine learning techniques." Health [24] U. Naseem, I. Razzak, S. K. Khan, and M. Prasad, "A
information science and systems 6, no. 1 (2018): 1-12. Comprehensive Survey on Word Representation Models:
[10] Kim, Woojin, Jaemann Park, JaehyunYoo, H. Jin Kim, and From Classical to State-Of-The-Art Word Representation
Chan Gook Park. "Target localization using ensemble Language Models," arXiv preprint arXiv:.15036, 2020.
support vector regression in wireless sensor networks." [25] Ishaq, A., Sadiq, S., Umer, M., Ullah, S., Mirjalili, S.,
IEEE transactions on cybernetics 43, no. 4 (2012): 1189- Rupapara, V., & Nappi, M. (2021). Improving the
1198. Prediction of Heart Failure Patients’ Survival Using
[11] Theodoridis, Sergios, and Michael Mavroforakis. SMOTE and Effective Data Mining Techniques. IEEE
"Reduced convex hulls: a geometric approach to support Access, 9, 39707–39716.
vector machines [lecture notes]." IEEE Signal Processing [26] U. Naseem, S. K. Khan, I. Razzak, and I. A. Hameed,
Magazine 24, no. 3 (2007): 119-122. "Hybrid words representation for airlines sentiment
[12] Vapnik, Vladimir Naumovich, and V. Vapnik. "Statistical analysis," in Australasian Joint Conference on Artificial
Learning Theory, vol. 1. Hoboken." (1998). Intelligence, 2019, pp. 381-392: Springer
[13] Vimalachandran, Pasupathy, Hong Liu, Yongzheng Lin, [27] S. Suman Rajest, D.K. Sharma, R. Regin and Bhopendra
Ke Ji, Hua Wang, and Yanchun Zhang. "Improving Singh, “Extracting Related Images from E-commerce
accessibility of the Australian My Health Records while Utilizing Supervised Learning”, Innovations in
preserving privacy and security of the system." Health Information and Communication Technology Series, pp.
Information Science and Systems 8, no. 1 (2020): 1-9. 033-045, 28 February, 2021.
[14] Warriach, Ehsan Ullah, Kenji Tei, Tuan Anh Nguyen, and [28] Souvik Ganguli, Abhimanyu Kumar, Gagandeep Kaur,
Marco Aiello. "Fault detection in wireless sensor networks: Prasanta Sarkar and S. Suman Rajest, “A global
a hybrid approach." In Proceedings of the 11th optimization technique for modeling and control of
international conference on Information Processing in permanent magnet synchronous motor drive”, Innovations
Sensor Networks, pp. 87-88. ACM, 2012. in Information and Communication Technology Series, pp.
[15] Yin, Jiao, MingJian Tang, Jinli Cao, Hua Wang, Mingshan 074-081, 28 February, 2021.
You, and Yongzheng Lin. "Adaptive Online Learning for [29] Jappreet Kaur, Tejpal Singh Kochhar, Souvik Ganguli and
Vulnerability Exploitation Time Prediction." S. Suman Rajest, “Evolution of Management System
In International Conference on Web Information Systems Certification: An overview”, Innovations in Information
Engineering, pp. 252-266. Springer, Cham, 2020. and Communication Technology Series, pp. 082-092, 28
[16] Zhu, Kaihua, Hao Wang, Hongjie Bai, Jian Li, February, 2021.
ZhihuanQiu, Hang Cui, and Edward Y. Chang. [30] R. Regin, S. Suman Rajest and Bhopendra Singh, “Spatial
"Parallelizing support vector machines on distributed Data Mining Methods Databases and Statistics Point of
computers." In Advances in Neural Information Processing Views”, Innovations in Information and Communication
Systems, pp. 257-264. 2008. Technology Series, pp. 103-109, 28 February, 2021.
[17] Narcisa Roxana Mosteanu, The International EFA-IT [31] Rustam, F., Khalid, M., Aslam, W., Rupapara, V.,
BLOG, The International EFA-IT BLOG Information Mehmood, A., & Choi, G. S. A performance comparison
Technology innovations in Economics, Finance, of supervised machine learning models for Covid-19
Accounting, and Law. tweets sentiment analysis. PLOS ONE, 16(2), e0245909,
[18] Narcisa Roxana Mosteanu, Using Internet And Edutech 2021. https://doi.org/10.1371/journal.pone.0245909
Become A Primary Need Rather Than A Luxury-The [32] Yousaf, A., Umer, M., Sadiq, S., Ullah, S., Mirjalili, S.,
Reality: A New Skilled Educational System-Digital Rupapara, V., & Nappi, M. Emotion Recognition by
University Campus, International Journal of Engineering Textual Tweets Classification Using Voting, 2021b.
Science Technologies, Volume 4, Number 6, pages 1-9, [33] S. K. Khan, M. Farasat, U. Naseem, and F. Ali, "Link‐level
2020. Performance Modelling for Next-Generation UAV Relay
[19] Rupapara, V., Narra, M., Gonda, N. K., Thipparthy, K., & with Millimetre‐Wave Simultaneously in Access and
Gandhi, S. Auto-Encoders for Content-based Image Backhaul," Indian Journal of Science Technology, vol. 12,
Retrieval with its Implementation Using Handwritten no. 39, pp. 1-9, 2019.
Dataset. 2020 5th International Conference on [34] S. K. Khan, U. Naseem, H. Siraj, I. Razzak, and M. J. I. W.
Communication and Electronics Systems (ICCES), 289– C. Imran, "The role of unmanned aerial vehicles and
294, 2020. mmWave in 5G: Recent advances and challenges,"
[20] Vijai C.& Wisetsri, W. Rise of Artificial Intelligence in Transactions on Emerging Telecommunications
Healthcare Startups in India. Advances In Management. 14 Technologies, p. e4241.
(1) March (2021):48-52. [35] Pandya, S.; Ambient Acoustic Event Assistive Framework
[21] Rupapara, V., Thipparthy, K. R., Gunda, N. K., Narra, M., for Identification, Detection, and Recognition of Unknown
& Gandhi, S. Improving video ranking on social video Acoustic Events of a Residence, Advanced Engineering
platforms. 2020 7th International Conference on Smart Informatics, Elsevier.
Structures and Systems (ICSSS), 1–5, 2020. (http://www.sciencedirect.com/science/article/pii/S147403
462030207X)

EAI Endorsed Transactions on

6 Scalable Information Systems
Online First
 Fault Detection in Wireless Sensor Network Based on Deep Learning Algorithms

[36] Srivastava A, Jain S, Miranda R, Patil S, Pandya S, [49] D.S. Hooda and D.K. Sharma “Exponential Survival
Kotecha K. 2021. Deep learning-based respiratory sound Entropies and Their Properties” Advances in Mathematical
analysis for detection of chronic obstructive pulmonary Sciences and Applications, Vol. 20, pp. 265-279, 2010.
disease. PeerJ Computer Science 7:e369 [50] Rao, A. N., Vijayapriya, P., Kowsalya, M., & Rajest, S. S.
https://doi.org/10.7717/peerj-cs.369, imf:3.09. Computer Tools for Energy Systems. In International
[37] Ghayvat, H.; Pandya, S.; Awais, M. ReCognizing SUspect Conference on Communication, Computing and
and PredictiNg ThE SpRead of Contagion Based on Electronics Systems (pp. 475-484). Springer, Singapore,
Mobile Phone LoCation DaTa: A System of identifying 2020.
COVID-19 infectious and hazardous sites, detecting [51] Gupta J., Singla M.K., Nijhawan P., Ganguli S., Rajest
disease outbreaks based on internet of things, edge S.S. An IoT-Based Controller Realization for PV System
computing and artificial intelligence, Sustainable Cities Monitoring and Control. In: Haldorai A., Ramu A., Khan
and Society. S. (eds) Business Intelligence for Enterprise Internet of
[38] Pandya, S.; Ghayvat, H.; Sur, A.; Awais, M.; Kotecha, K.; Things. EAI/Springer Innovations in Communication and
Saxena, S.; Jassal, N.; Pingale, G. Pollution Weather Computing. Springer, Cham, 2020.
Prediction System: Smart Outdoor Pollution Monitoring [52] Sharma M., Singla M.K., Nijhawan P., Ganguli S., Rajest
and Prediction for Healthy Breathing and Living. Sensors, S.S. An Application of IoT to Develop Concept of Smart
2020, 20, 5448. https://doi.org/10.3390/s20185448. ) Remote Monitoring System. In: Haldorai A., Ramu A.,
[39] Pandya, S., Sur, A. and Kotecha, K., "Smart epidemic Khan S. (eds) Business Intelligence for Enterprise Internet
tunnel: IoT-based sensor-fusion assistive technology for of Things. EAI/Springer Innovations in Communication
COVID-19 disinfection", International Journal of and Computing. Springer, Cham, 2020.
Pervasive Computing and Communications, Emerald [53] Ganguli S., Kaur G., Sarkar P., Rajest S.S. An Algorithmic
Publishing, 2020, https://doi.org/10.1108/IJPCC-07-2020- Approach to System Identification in the Delta Domain
0091. Using FAdFPA Algorithm. In: Haldorai A., Ramu A.,
[40] Awais, M.; Ghayvat, H.; Krishnan Pandarathodiyil, A.; Khan S. (eds) Business Intelligence for Enterprise Internet
Nabillah Ghani, W.M.; Ramanathan, A.; Pandya, S.; of Things. EAI/Springer Innovations in Communication
Walter, N.; Saad, M.N.; Zain, R.B.; Faye, I. Healthcare and Computing. Springer, Cham, 2020.
Professional in the Loop (HPIL): Classification of [54] Singla M.K., Gupta J., Nijhawan P., Ganguli S., Rajest
Standard and Oral Cancer-Causing Anomalous Regions of S.S. (2020) Development of an Efficient, Cheap, and
Oral Cavity Using Textural Analysis Technique in Flexible IoT-Based Wind Turbine Emulator. In: Haldorai
Autofluorescence Imaging. Sensors, 2020, 20, 5780. A., Ramu A., Khan S. (eds) Business Intelligence for
[41] Patel, C.I.; Labana, D.; Pandya, S.; Modi, K.; Ghayvat, H.; Enterprise Internet of Things. EAI/Springer Innovations in
Awais, M. Histogram of Oriented Gradient-Based Fusion Communication and Computing. Springer, Cham
of Features for Human Action Recognition in Action [55] R. Arulmurugan and H. Anandakumar, “Early Detection of
Video Sequences. Sensors 2020, 20, 7299. Lung Cancer Using Wavelet Feature Descriptor and Feed
[42] Ghayvat, H.; Awais, M.; Pandya, S.; Ren, H.; Akbarzadeh, Forward Back Propagation Neural Networks Classifier,”
S.; Chandra Mukhopadhyay, S.; Chen, C.; Gope, P.; Lecture Notes in Computational Vision and Biomechanics,
Chouhan, A.; Chen, W. Smart Aging System: Uncovering pp. 103–110, 2018. doi:10.1007/978-3-319-71767-8_9
the Hidden Wellness Parameter for Well-Being Monitoring [56] Haldorai, A. Ramu, and S. Murugan, “Social Aware
and Anomaly Detection. Sensors 2019, 19, 766. Cognitive Radio Networks,” Social Network Analytics for
[43] Sur S., Pandya, S., Ramesh P. Sah, Ketan Kotecha & Contemporary Business Organizations, pp. 188–202.
Swapnil Narkhede, Influence of bed temperature on doi:10.4018/978-1-5225-5097-6.ch010
performance of silica gel/methanol adsorption refrigeration [57] R. Arulmurugan and H. Anandakumar, “Region-based
system at adsorption equilibrium, Particulate Science and seed point cell segmentation and detection for biomedical
Technology, Taylor and Francis, impact factor: 1.7, 2020. image analysis,” International Journal of Biomedical
[44] Barot, V., Kapadia, V., & Pandya, S., QoS Enabled IoT Engineering and Technology, vol. 27, no. 4, p. 273, 2018.
Based Low Cost Air Quality Monitoring System with [58] M. Suganya and H. Anandakumar, “Handover based
Power Consumption Optimization, Cybernetics and spectrum allocation in cognitive radio networks,” 2013
Information Technologies, 2020, 20(2), 122-140. International Conference on Green Computing,
[45] Sur, A., Sah, R., Pandya, S., Milk storage system for Communication and Conservation of Energy (ICGCE),
remote areas using solar thermal energy and adsorption Dec. 2013.
cooling, Materials Today, Volume 28, Part 3, 2020, [59] D Datta, S Mishra, SS Rajest “Quantification of tolerance
Elsevier, Pages 1764-1770, ISSN 2214-7853. limits of engineering system using uncertainty modeling
[46] D.S. Hooda, Sonali Saxena and D.K. Sharma, “A for sustainable energy” International Journal of Intelligent
Generalized R-Norm Entropy andCoding Theorem” Networks, Vol.1, 2020, pp.1-8,
International Journal of Mathematical Sciences and [60] Leo Willyanto Santoso, Bhopendra Singh, S. Suman
Engineering Applications, Vol.5(2), pp.385-393, 2011. Rajest, R. Regin, Karrar Hameed Kadhim, “A Genetic
[47] D.S. Hooda and D.K. Sharma, “Bounds on Two Programming Approach to Binary Classification Problem”
Generalized Cost Measures” Journal of Combinatorics, EAI Endorsed Transactions on Energy, Vol.8, no. 31, pp.
Information & System Sciences, Vol. 35(3-4), pp. 513- 1-8, 2021. DOI: 10.4108/eai.13-7-2018.165523
530, 2010 [61] Dr. Laxmi Lidiya. S. Suman, Rajest, “Correlative Study
[48] D.K. Sharma and D.S. Hooda, “Generalized Measures of and Analysis for Hidden Patterns in Text Analytics
‘Useful’ Relative Information and Inequalities” Journal of Unstructured Data using Supervised and Unsupervised
Engineering, Management & Pharmaceutical Sciences, Learning techniques” in International Journal of Cloud
Vol.1(1), pp.15-21, 2010. Computing, International Journal of Cloud Computing
(IJCC), Vol. 9, No. 2/3, 2020.

EAI Endorsed Transactions on

7 Scalable Information Systems
Online First

View publication stats