International Journal of Innovative Technology and Exploring Engineering (IJITEE)

ISSN: 2278-3075, Volume-8, Issue-9S, July 2019

Latest Tools for Data Mining and Machine

Learning
Kanupriya Verma, Sahil Bhardwaj, Resham Arya, Mir Salim Ul Islam, Megha Bhushan, Ashok Kumar,
Piyush Samant

hands to achieve a system to produce the

Abstract: Nowadays, Data Mining is used everywhere for program based on the input, statistical analysis and the
extracting information from the data and in turn, acquires predicted outcomes [3].
knowledge for decision making. Data Mining analyzes patterns
This paper an overview of the existing tools and
which are used to extract information and knowledge for making
decisions. Many open source and licensed tools like Weka, technologies used for DM and ML. A description of
RapidMiner, KNIME, and Orange are available for Data Mining open-source and licensed tools is provided based on the types
and predictive analysis. This paper discusses about different tools of data that can be mined along with the respective
available for Data Mining and Machine Learning, followed by application domain where they can be used.
the description, pros and cons of these tools. The article provides The organization of the paper is as follows: Section II
details of all the algorithms like classification, regression,
characterization, discretization, clustering, visualization and focuses on the description of DM and ML tools. Section III
feature selection for Data Mining and Machine Learning tools. It includes related work based on tools. Section IV incorporates
will help people for efficient decision making and suggests which a descriptive study of tools. Finally, conclusion is outlined in
tool is suitable according to their requirement. Section V.

Keywords: Data mining, Open source tools, Licensed tools, II. TOOLS DESCRIPTION
Machine learning
This section focuses on description of DM and ML Tools.
I. INTRODUCTION
D2K (Data to Knowledge) [2] toolbox gives a visual
Data Mining (DM) is the procedure for programmed
programming condition and a lot of layouts expected to
revelation of abnormal state learning by acquiring data from associate it with other standard bundles. It gives bundles to
the genuine world, extensive as well as complex perform picture and content mining and furthermore, offers
informational indexes. It is advancement towards more an outside arrangement of transformative strategies for
extensive process, called Knowledge Discovery Databases building up some essential hereditary calculations.
(KDD) [1]. It is a process of finding naturally occurring
information from databases which presents an exceptionally KNIME (Konstanz Information Miner) [4] is easy to use,
alluring and testing assignment, both for the scholarly world secluded and provides an open-source information
and industry. DM and ML tools are used to find the best coordination, preparation, examination and investigation
suitable model through mechanized procedures (called stage. KNIME contains devices for information
machine realizing) which seek through the dataset to pre-handling, changing, grouping, affiliation leads etc. The
distinguish designs. benefit of the tool is that WEKA can be coordinated and
DM and Machine learning (ML) deals with various broaden for conceivable outcomes with KNIME by different
techniques like regression, classification, visualization and administrators.
feature selection. Regression and classification techniques
are categorized as supervised as well as unsupervised WEKA (Waikato Environment for Knowledge Analysis)
learning. Classification is used to predict the class labels, so it [5] is a ML tool. It consists of all ML algorithms which are
can be used to categorize various datasets. It is based on the used to solve the real-life application problems.
model of applying mapping function on the dependent
RapidMiner (RM - some time ago YALE) [6,7] is a free,
variable that can be used to predict the independent variable
adaptable and open-source tool executed in Java. It is a tool
[2]. On the other hand, regression can be applied to continuous data
for ML, DM, image processing and business analytics.
instead of discrete data as in classification. Further, it can be
classified as linear regression based on a single independent
variable whereas polynomial regression is based on multiple
ORANGE [8] uses the Python language which helps in the
visualization of data in DM. It helps in predictive modelling,
Revised Manuscript Received on June 04, 2019. analysis, selection of subset and empirical analysis. This tool
Kanupriya Verma, Deepak Kumar, Resham Arya, Mir Salim Ul Islam, performs tasks like data manipulation and data
and Megha Bhushan*, Ashok Kumar, Chitkara University Institute of transformations.
Engineering and Technology, Chitkara University, Punjab, India.
Piyush Samant, Chandigarh University, Punjab India.
KEEL [2] is an open source
independent variables. Therefore, DM and ML goes hands in software. It stands for
knowledge extraction based

Published By:
18 Blue Eyes Intelligence Engineering
Retrieval Number: I10030789S19/19©BEIESP
DOI: 10.35940/ijitee.I1003.0789S19 & Sciences Publication
 Latest Tools for Data Mining and Machine Learning

on evolutionary learning. It is a JAVA tool which is used for programming skills. KNIME tool provides aid to the users
tasks like data discovery and knowledge extraction. Further, without the knowledge of programming skills. For web
dataset repository is available for performing classification mining purposes, NetTool Spider mining tool is used.
and regression technique. MATLAB and TANGARA have been used for a
comparative study of classification techniques [11]. The
SciKit Learn [9] is supported by python language, grouped performance of different classification techniques is analyzed
with NumPy and SciPy. It is used for plotting outlines and for set of data. Medical diagnosis is an important factor for
performing DM calculations. obtaining the important parameters of the disease as without
diagnosis it is difficult to identify parameter of disease. Tests
III. LITERATUTE REVIEW are conducted which include clusters and classifications
This section includes articles related to the DM and ML techniques. However, many tests could complicate the
tools. process of diagnosis and it would be difficult to obtain
DM tool is presented as open source software with three results. Thus, to overcome ML tools are used. The extraction
features [2]. The key points of this tool include the dataset of of information from large datasets and the correlation of an
KEEL which is a repository that includes the partitions of element in data set will help to analyze the results. Fuzzy
information sets in KEEL format. In this dataset, results of proposition establishes some sort of relation between input
some algorithms are shown. This tool provides the guidelines and output fuzzy set using fuzzy logic. The decision rules are
for using new algorithm. As KEEL is not dependent on any implemented for control output value and input parameters to
operating system, so it can be used by anyone. This study find the result of a diabetic person. The result could be
concludes that Hider method is the best method with respect negative or positive.
to the other methods used for analysis. A theory has been proposed on Unified DM with analysis
RapidMiner is a tool that presents few characteristics of of DM tools, as there is a huge amount of data which has been
extraction operators and individual operations applied on the stored in repository, cloud or databases [12]. There is a need
extension [10]. It is formerly known as YALE, available for to evaluate an efficient data pattern for decision making. So,
data analysis as a stand-alone application. It can also be for predicting the best patterns out of many datasets, the tools
integrated with other applications as DM engine. It can run on are required for different data types. It also provides
major platform or operating system, since it is a flexible, free knowledge on unification theory. For development of
and Open Source platform which is implemented in Java. unification process some sort of measure was suggested
Mikut and Markus have discussed various historical which could be used on set of database and domains. This
developments and presented wide range of current DM and process performed all tasks of mining, classification,
related tools for supporting decision making process [2]. clustering and visualization in group or in unified method
Nine various types of tools are presented in their work. These instead of performing each task individually. The four
tools are BIS, DMS, INT, mats, RES, EXT, libs, sols and algorithms were also used i.e., zero rule, one rule, decision
specs. These vary in characteristics, for example, intended tree and KNN (K-nearest neighbor). The tools offer the
user groups, data structure, implemented tasks and methods, Functionalities like API support and Graphical Presentation.
interaction styles such as export and import abilities, license The algorithm applied over the dataset and percentage
policies and platforms are adjustable. Large dataset with accuracy was served for measuring performance. WEKA is
single feature, unstructured data-like texts and time series can better as it provides zero’s and one’s implementation.
be managed using current tools as well as in absence of A comparison of various open source DM tools has been
comprehensive and powerful DM tools for datasets which are presented in [13]. Their work described the technical
multidimensional such as videos and images. specifications, features, and specialization for each selected
Various algorithms of clustering have been discussed tool along with its applications. By employing this study, the
using by DM using WEKA tool [5]. The main key points choice and selection of tools can be made easy.
include explaining the comparison of various algorithms for The details of the open source tools have been provided for
clustering of WEKA and concluded the best algorithm for supporting the more advanced and specialized research
users. This tool was chosen by the user because it can be used topics like big data, data streams, text mining, etc. [14].
without having a detailed knowledge of DM techniques. They A comparison of DM algorithms and techniques like
have worked only on the clustering algorithm using WEKA clustering, visualization has been given [8]. A comparison
tool. has been made for tools with respect to community support.
Hirudkar and Shereka have given an evaluation of In DM tools, advancements were made and it gives the
database systems and comparative analysis of DM techniques features and quality of WEKA and KNIME. Some of the
and tools [4]. An overview is provided with steps included in tools such as RapidMiner and KNIME are graphically
mining data and methods. A comparative study of freely integrated which help to enable connection, dragging and
available tools such as WEKA tools, RapidMiner Tool and component placement. Structured view of all supported
NetTool Spider for web mining has been provided. Further, functionalities is offered by Orange Tool which was grouped
predicted the behavior’s and future trends that help into different categories i.e., unsupervised learning,
organizations to make heedful knowledge driven decisions. prototype implementation,
Software becomes highly robust for various users using visualization using Qt, data
WEKA tool. RapidMiner tool is used by the users having operation and classification.

19 Published By:
Retrieval Number: I10030789S19/19©BEIESP Blue Eyes Intelligence Engineering
DOI: 10.35940/ijitee.I1003.0789S19 & Sciences Publication
 International Journal of Innovative Technology and Exploring Engineering (IJITEE)
ISSN: 2278-3075, Volume-8, Issue-9S, July 2019
The efficiency of tools can be improved. end, different tools are uniquely defined for different tasks,
A methodology has been proposed to monitor the plan and for example, SQL is used to select data for only particular
execution of Crime location and identified the criminals in month or year, EXCEL is used to refine data set and to
Indian urban areas utilizing DM strategies [15]. Their calculate total employee time before fitting a predictive
methodology is separated into six modules: Data Extraction model to RapidMiner. NodeXL analyzed relationship
(DE), Grouping, Data Pre-processing (DP), Google between posts and all-over textual quality of posts replied by
Delineate, Classification and WEKA execution. DE that employee with the help of Coh Metrix and finally with
extricates the unstructured and undefined criminal dataset Gephi tool. Researchers can visualize the most interesting
from different crime Web Sources. DP cleans, incorporates clusters of employees found within the social network. Each
and lessens separated criminal info to organize number of tool has its own strength and weakness. Efficient discoveries
criminal occurrences. They have resolved these cases can be made using a combination of these tools.
utilizing 35 predefined criminal characteristics. Rest four The components of microstructure of compact graphite
modules were helpful to identify the Crime location, iron based on alloying elements have been identified to find
identification of the criminal and expectation, and the thickness and effect [19]. Linear regression models,
verification of the crime, separately. Criminal identification Segmented regression models with MAR Splines algorithm,
and expectation were cracked by utilizing KNN Artificial Neural Network (ANN), Classification and
classification. Crime verification is done by the results Regression Tree (CART) were used for conducting this
generated by WEKA. The proposed scenario improved the study.
public lifestyle by helping the authorities in crime discovery Siddique and Ahmad have stated that everything is going
as well as identification of criminals and hence, diminishing to be computerized in the present era of software [20]. For
the crime rates. software organizations, it is challenging task to develop
A Binary Classifier tool was used for the diagnosis of standard software within estimated cost on time. DM plays a
patients suffering from brain disorders [9]. This tool provided highly important role in mining software repositories using
a nonexclusive classifier to help and analyze patients tools like Apfel, Chianti, Dynamine, Hipikat, Kenyon and
experiencing cerebrum issue. They have manufactured a tool Softchange. The dimensions of these tools are to be intended,
which utilizes ML taking in calculations from WEKA, Caret informative, infrastructure, effective, interactive,
and SciKit Learn from Java, R and Python separately and materialistic and language dependent.
joins the three bundles into one R bundle which helps in The articles from 2007-2017 years under Fundamental
arranging the patients experiencing cerebrum issue. This tool Concepts of DM, KR (Knowledge Representation), CI
can be utilized as an independent application for arrangement (Computational Intelligence), Classification and Predication
of any paired class information. have been reviewed in [21].
The compounds have been evaluated for their Kodati and Vivekanandam have presented a paper on
pharmacological and toxicological properties which are of Orange and WEKA tools of DM for analyzing heart disease
extraordinary significance for industry and administrative [7].
offices [16]. In this investigation, a methodology utilizing
open source programming and open access databases to IV. VARIOUS DM AND ML TOOLS
assemble screening devices for receptor-interceded impacts This section provides a description of open source and
is introduced. The retinoic corrosive receptor (RAR), as a licensed tools of DM and ML.
pharmacologically and toxicologically applicable target, was
chosen for this examination. RAR agonists were utilized in Fig. 1 shows various Open Source and Licensed Tools.
the treatment of various dermal conditions and explicit kinds Tables 1 and 2 describe Open Source tools and Licensed
of malignancy, for example, intense promyelocytic leukemia. Tools, respectively. WEKA is the most efficient tool for the
The Source ext Rewriting has been used to improve the educational purpose and frees to use. Yellowfin tool is the
best tool according to this descriptive study due to its quick
quality of Machine Translation (MT) [17]. It has been
response, simple to use and highly capable for Big Data
characterized, the undertaking of transformation of substance
integration with excellent capacity.
starting with one dialect then onto the next. In Indian society,
interpretation started with the interpretation of Holy
V. CONCLUSION
Scriptures into Pali, Prakrit, Devanagari and other local
dialects. It helped in transmission of good qualities, ethos, DM is one of the most popular techniques used for
custom, convictions and culture over the globe. Indeed, even Information retrieval and for better decision making. Till
at present, when web has united individuals near one another, date, various open source and licensed tools like WEKA,
the job of interpretation has turned out to be much huger than Rapid Miner, KNIME, Orange and many more have been
past years. developed for generating predictions. This review paper is
A review has been presented on DM tools which are used focused on various available tools for DM and ML. A study
to mine educational dossier [18]. Their work focused on
EDM (educational DM tool) to perform EDM analysis rather
than more traditional or modern statistical analysis. Emerging
methods can be reviewed not only at theoretical level but at
practical level also. Analyzing data sets from beginning to

Published By:
20 Blue Eyes Intelligence Engineering
Retrieval Number: I10030789S19/19©BEIESP
DOI: 10.35940/ijitee.I1003.0789S19 & Sciences Publication
 Latest Tools for Data Mining and Machine Learning

Fig. 1 Data Mining and Machine Learning Tools

Table 1. Description of various open source tools for DM and ML

Tool Year Latest Language Method Purpose Application/ Area Advantages Disadvantages
Name Version used
WEKA [5] 1997 3.6.11 Java -Easy analytics of Educational Purposes -Free Extensible -Weak in statistical
data and predictive -ARFF, CSV, C4.5, analysis
modelling binary are formats -For parameter
used to load files optimization of
machine learning (No
automatic facility)
KNIME 2004 2.9 Java -Enables user to Pharmaceutical -Easily visualization -No methods for data
[2] visually create data Research of molecular data wrapper
flows easily -Not automatic facility
-Interactive data for parameter
models Optimization
KEEL [20] 2004 2.0 Java -Evolutionary Used in Scientific -Contains big data -Less efficient due to
Algorithms for DM research preened libraries for large numbers of
big problems analysis, processing algorithms.
prediction
Rapid Miner 2006 6.0 Java -Text Mining, Business, Training, -Full Faculty Model -Only capable of SQL
[7] results in Education, Data Evaluation Offers statements
visualization, Model more procedures -Working with only
validation and Over 1500 methods database files.
optimization for data integration,
analysis, visualization
Compatible for large
users.
SciKit Learn 2007 0.14.1 Python -Add on machine Machine Learning -Include some -Time Consumption
[2] learning package libraries that are -Less durable
suitable for
audio/video files
Orange [20] 2009 2.7 C++ and -Data Data -Debugging is better -Weak in statistical
python Pre-processing, Visualization -Categorization analysis
filtering, and problems like -Limited capabilities of
modelling scripting DM are visual representations
Techniques simple. of data mode

Table 2. Description of various licensed tools for DM and ML

Tool Language Main purpose Application Year Latest Advantages Disadvantages

Name Area version

21 Published By:
Retrieval Number: I10030789S19/19©BEIESP Blue Eyes Intelligence Engineering
DOI: 10.35940/ijitee.I1003.0789S19 & Sciences Publication
 International Journal of Innovative Technology and Exploring Engineering (IJITEE)
ISSN: 2278-3075, Volume-8, Issue-9S, July 2019
SAS [22] HTML Extraction, Clinical 1976 9.4 -Drag and drop -Although
Formatting and Research And interface is great software is perfect
cleansing to data forecasting -Very accurate but requires some
analysis, -With good graphic work to create a
building design & Speed of model with
sophisticated processing. incoming, read
models -time data
IBM Python/ Interactive and Forecasting, 2010 25 -Not necessary to -To have better
SPSS Java Statistical Healthcare, use complex quality graphics
modeller analysis Risk Knowledge to or mainly we want
[22] Management encode data when to make.
we use qualitative -Presentation it’s
data. not suitable
GMDH C/C++ Knowledge Forecasting 2009 3.8.3 -Takes raw or -With value very
Shell [22] discovery, and Business messy data set in close to absolute
prediction, purpose CSV and provide a max, the model
complex system predictive mode does not converge
modelling, more Quickly at to max but to local
optimization reasonable cost max.
Dundas C, C#, creating and Small 1992 6.0.0 - On any device it -DO not have an
BI [23] Java, C++ viewing Businesses, Revision allows users to interactive user
interactive Mid-size 3 integrate and community
dashboards, Business, connect with data -tool doesn't
reports, Enterprise source in real time. support the 3D
scorecards Charts
Yellowfin JAVA Creating Counting, 2003 7.4.7 -Very fast and very -There are issues
[23] scorecards and advertising, simple product to related to pulling
dashboards, agriculture, create reports and data and
online analytical banking, panels displaying data set
processing insurance, -Integration from a system.
analyses, manufacturing, capacity with Big
predictive media, Data is excellent.
analytics marketing
5. N. Sharma, A. Bajpai, and R. Litoriya, “Comparison the various
clustering algorithms of weka tools,” in facilities, 2012, vol.4, pp.
on these tools has been done to study their respective pros and 78-80.
cons along with the application areas where they can be more 6. https://rapidminer.com/glossary/data-mining-tools/
beneficial. This review provides details of all the algorithms 7. Q. M. Yas, A.A. Zaidan, B.B. Zaidan, B. Rahmatullah and H.A.
Karim,“Comprehensive insights into evaluation and benchmarking of
like classification, regression, characterization, discretization, real-time skin detectors: Review, open issues & challenges, and
clustering, visualization and feature selection for DM and ML recommended solutions,” in Measurement,2018, vol. 114, pp. 243-260
tools. It will benefit people in efficient decision making and 8. A. Jovic, B. Karla, and B. Nikola, “An overview of free software tools
suggest which tool is more appropriate as per their for general data mining,” in IEEE 37th International Convention on
Information and Communication Technology, Electronics and
requirement. There are always different approaches used to Microelectronics (MIPRO), 2014, pp. 1112-1117.
solve different problems, each with their own particular 9. N. Borude, C. Maher, V. Sarda, and A. Santra, “Generic binary
strengths and weaknesses. Therefore, by using a combination classifier tool for diagnosis of patients suffering from brain disorders in
R,” in International Conference on Computing, Analytics and
of aforementioned tools and algorithms, complex analyses Security Trends (CAST), 2016, IEEE pp. 173-178.
can be done by future researchers which will result in useful 10. B. Radim, K. Jan, S. Zdeněk, U. Václav, and D. Otto, “Rapidminer
discoveries on data. image processing extension: A platform for collaborative research,” in
33rd International Conference on Telecommunication and Signal
Processing, TSP, 2010, pp. 114-118.
REFERENCES 11. R.M. Rahman, and F. Afroz, “Comparison of various classification
techniques using different data mining tools for diabetes diagnosis,” in
1. U. Fayyad, G. Piatetsky-Shapiro, and P. Smyth, “From data mining to Journal of Software Engineering and Applications, 2013, vol. 6, p. 85.
knowledge discovery in databases,” in AI Magazine, 1996, vol. 17, no. 12. H. Solanki, “Comparative study of data mining tools and analysis with
3, pp. 37–54. unified data mining theory,” in International Journal of Computer
2. J. Alcala-Fdez et al. “KEEL: a software tool to assess evolutionary Applications,2013, vol. 75, pp. 23-28.
algorithms for data mining problems,” in Soft Computing, 2009, vol. 13. K. Rangra, and K. L. Bansal, “Comparative study of data mining
13, pp. 307-318. tools,” in International journal of advanced research in computer
3. R. Mikut, and R. Markus, “Data mining tools," in Wiley science and software engineering, 2014, vol. 4.
Interdisciplinary Reviews: Data Mining and Knowledge Discovery 14. X. Wu, X. Zhu, G.Q. Wu, and W. Ding, “Data mining with big data,”
2011, vol. 1, pp. 431-443. in IEEE Transactions on Knowledge and Data Engineering, 2013,
vol. 26, pp. 97-107.
15. DK. Tayal, A. Jain, S. Arora, S. Agarwal, T. Gupta, and N. Tyagi,
4. A. M. Hirudkar, and SS. Sherekar, “Comparative analysis of data “Crime detection and criminal identification in India using data
mining tools and techniques for evaluating performance of database mining techniques,” in AI &
system,” in International Journal of Computer Science Appllications, society, 2015, vol. 30, pp.
2013, vol. 6, pp. 232-237. 117-127.

Published By:
22 Blue Eyes Intelligence Engineering
Retrieval Number: I10030789S19/19©BEIESP
DOI: 10.35940/ijitee.I1003.0789S19 & Sciences Publication
 Latest Tools for Data Mining and Machine Learning

16. FP. Steinmetz, CL. Mellor, T. Meinl, and MT. Cronin, “Screening New Delhi, Government of India from 2016 to 2018. Dr. Megha has
Chemicals for Receptor‐Mediated Toxicological and Pharmacological published many research articles on the area of software reuse in
Endpoints: Using Public Data to Build Screening Tools within a international journals and conferences of repute. Her research interest
KNIME Workflow,” in Molecular informatics, 2015, vol. 34, pp. includes Software quality, Software reuse, Ontologies, Artificial
171-178. Intelligence, and Expert systems. After obtaining Bachelors of Technology
17. D. Chopra , N. Joshi , and I. Mathur, “Improving Quality of Machine degree in Information Technology from Himachal Pradesh University, India
Translation Using Text Rewriting,” in Computational Intelligence & in 2010, she obtained her Masters in Engineering degree with specialization
Communication Technology (CICT), Second International Conference in Software Engineering from Thapar University, India in 2012. She
on IEEE, 2016, pp. 22-27.
continued her research in software product line combined with expert
18. S. Slater, S. Joksimovic, V. Kovanovic, RS. Baker, D. Gasevic, “Tools
systems and ontologies obtaining her Ph.D. in 2018 from Thapar University,
for educational data mining: A review,” in Journal of Educational and
Behavioral Statistics, 2017, vol. 42 ,pp. 85-106. Punjab, India. She is also the reviewer and editorial board member of many
19. D. Wilk-Kolodziejczyk, K. Regulski, G. Gumienny, B. Kacprzyk, S. international journals.
Kluska-Nawarecka, K. Jaskowiec, “Data mining tools in identifying
the components of the microstructure of compacted graphite iron based Ashok Kumar is currently an Assistant Professor in
on the content of alloying elements,” in The International Journal of Chitkara University Research and Innovation Network
Advanced Manufacturing Technology, 2018, vol. 95, pp. 3127-3139. (CURIN) Department, Punjab. He is PhD in Computer
20. T. Siddiqui, and A. Ausaf, “Data mining tools and techniques for Science and Engineering from Thapar University, Punjab,
mining software repositories: A systematic review,” in Big Data India. He has 15+ years of teaching and research
Analytics. Springer, Singapore, 2018, pp. 717-726. experience. He has number of publications in International Journals and
21. R. Alcalá, MJ. Gacto, J. Alcalá‐Fdez “Evolutionary data mining and Conferences of repute. His current areas of research interest include Cloud
applications: A revision on the most cited papers from the last 10 years Computing, Internet of Things, and Mist Computing. His teaching interest
(2007–2017),” in Wiley Interdisciplinary Reviews: Data Mining and includes Python, Haskell, Java, C/C++, Advanced Data structures and Data
Knowledge Discovery, 2018 ,vol. 8 , e1239. Mining.
22. S. Yefimenko, “Advances in GMDH-based Predictive Analytics Tools
for Business Intelligence Systems,” in International Conference
Proceedings, ACIT, 2018, pp. 254-257.
23. https://www.softwareadvice.com/bi/dundas-bi-profile/

AUTHORS PROFILE
Kanupriya Verma is presently pursuing Masters of
Engineering from Chitkara University, Punjab Campus
and also working as an Assistant Lecturer. She has done
her Bachelor of Technology from Punjabi University,
Punjab, India. She has also done diploma from
Government Polytechnic College for Girls, Punjab, India. She has published
one paper in National Conference.

Sahil Bhardwaj is presently pursuing Masters in

Computer Science and Engineering from Chitkara
University Punjab and also working as an Assistant
Lecturer. He has done Bachelors of Engineering in CSE
from Chitkara University. He has industrial experience
in Android app Development.

Resham Arya is presently a Ph. D Scholar in

Computer Science and Engineering department from
Chitkara University, Punjab. She has done Masters of
Engineering in CSE from Chitkara University and
Bachelor of Technology from Chitkara Institute of
Auth
Engineering and Technology. She has 3 years of work
experience as an Assistant Lecturer and 1.5 years of Assistant Professor in
Teaching. Her research interests include affective computing, machine
learning and working with physiological signals.

Mir Salim Ul Islam is presently pursuing Ph. D in

Computer Science and Engineering from Chitkara
University Punjab and also working as an Assistant
Professor - Research in Chitkara Research Innovation
Network. He has done Masters of Engineering in CSE
from Kurukshetra University Haryana and Bachelor
of Technology in CSE from Kashmir University. His research areas include
physiological signals, machine learning and deep learning. He has industrial
experience of 4 years in software and solution development and has hands on
experience in Microsoft Dot Net technologies, SQL server and open source
technologies.

Dr. Megha is an Assistant Professor in the Department of

Computer Science & Engineering, Chitkara University,
Punjab, India. She is a recipient of Grace Hopper
Celebration India (GHCI). She was awarded with
fellowship by University Grants Commission (UGC),
Government of India, in 2014. In 2017, she was a recipient
of Grace Hopper Celebration India (GHCI), fellowship. She has worked as
Junior Research Fellow under UGC, New Delhi, Government of India from
2014 to 2016. She has also worked as Senior Research Fellow under UGC,

23 Published By:
Retrieval Number: I10030789S19/19©BEIESP Blue Eyes Intelligence Engineering
DOI: 10.35940/ijitee.I1003.0789S19 & Sciences Publication