ISSN (Print): 2666-2558
ISSN (Online): 2666-2566
Volume 14, 8 Issues, 2021
ISSN (Print): 2666-2558
ISSN (Online): 2666-2566
Aims & Scope
ChemWeb, CNKI Scholar, Dimensions, EBSCO, EI/Compendex, Genamics JournalSeek, Google Scholar, J-Gate, JournalTOCs, MediaFinder®-Standard Periodical Directory, PubsHub, Norwegian Register, QOAM, Scilit, Scopus, Suweco CZ, TOC Premier and Ulrich's Periodicals Directory
View Full Editorial Board
1 Abstract Ahead of Print are available electronically
128 Articles Ahead of Print are available electronically
It has been a huge challenge successfully completing the special issue titled “Machine Learning for Data Mining, Data Science,
and Data Analytics” under the reputed journal Recent Advances in Computer Science and Communications, formerly
Recent Patents on Computer Science.
Most research contributions related to machine learning are primarily devoted to improving the prediction accuracy and
performance of the learning model. However, it is a fact that less attention is paid towards mining health care data, hybrid machine
learning models, detecting low-frequency attacks [1-3], and addressing optimization. To address these issues, the focus of
this special issue in Recent Advances in Computer Science and Communications is on machine learning for data mining, data
science, and data analytics.
This special issue was planned to receive quality submissions from different parts of the country and the world. Nearly 12
research contributions were received with great enthusiasm from the research and scientific community. Out of these, 4 articles
were accepted for inclusion in the special issue after a stringent and thorough review process, at least by two independent referees.
The special issue includes four contributions, which were selected after reviews were conducted by experts working in these
areas. Here, we present a very brief summary of the selected papers for this special issue and concluding remarks.
The special issue contains 4 papers, briefly discussed as follows:
The first article, “Mathura (MBI) - A Novel Imputation Measure for Imputation of Missing Values in Medical Datasets,” is
written by B. Mathura Bai, N. Mangathayaru, B. Padmaja Rani, and Shadi Aljawarneh , proposes an imputation measure for
filling missing data values to make the incomplete medical datasets as complete datasets. Then the approach is to apply this
imputation measure on imputed datasets to achieve improved classifier accuracies. The basic intention of the research study is
to present an imputation measure to find the proximity between medical records and an approach for imputation of missing
values in medical datasets to improve the accuracy of existing classifiers. The performance of the proposed approach is compared
to existing approaches with respect to classifier accuracy and also by performing a non-parametric test called the Wilcoxon
The second article, “E-mail Fraud Attack Detection Using Hybrid Machine Learning Approach,” is written by Yousef A.
Yaseen, Malik Qasaimeh, Raad S. Al-Qassas, and Mustafa Al-Fayoumi . E-mail is an efficient way to communicate. It is
one of the most commonly used communication methods, and it can be used for achieving legitimate and illegitimate activities.
Many features that can be effective in detecting e-mail fraud attacks are still under investigation. This paper proposes an improved
classification accuracy for fraudulent e-mails implemented through feature extraction and hybrid Machine Learning
(ML) classifier that combines Adaboost and Majority Voting. Eleven machine learning classifiers are evaluated experimentally
within the hybrid classifier. The performance of the e-mail fraud filtering is evaluated by using WEKA and R tool on a data set
of 9298 e-mail messages. The utilized proposed e-mail features with the combination of Adaboost and Voting algorithms prove
the efficiency of fraud e-mail detection
Intrusion detection systems play a key role in system security by identifying potential attacks and giving appropriate responses.
As new attacks are always emerging, intrusion detection systems must adapt to these attacks. More work is continuously
needed to develop and propose new methods and techniques to improve efficient and effective adaptive intrusion systems.
Feature selection [1, 2, 6, 7] is one of the challenging areas that need more work because of its importance and impact on
the performance of intrusion detection systems. The third article, “Intrusion Detection System for Malicious Traffic Using Evolutionary
Search Algorithm” is written by Samar Al-Saqqaa, Mustafa Al-Fayoumib, Malik Qasaimehc, and Raad S. Al-Qassasb
. It applies an evolutionary search algorithm in feature subset selection for intrusion detection systems. The evolutionary
search algorithm is applied to find the best subset of features for the intrusion detection system. The experimental study proved
their approach promising to be used as a feature selection method for intrusion detection. The results showed better performance
for the intrusion detection system in terms of accuracy and detection rate.
The app stores, for example, Google Play and Apple Play Store, provide a platform that allows users to provide feedback on
the apps in the form of reviews. An app review typically includes a star rating followed by a comment. Recent studies have
shown that these reviews possess a vital source of information that can be used by the app developers and vendors for improving
the future versions of an app. However, in most cases, these reviews are present in unstructured form, and extracting useful
information from them requires a great effort. The fourth article, “An Optimized Classification of Apps Reviews for Improving
Requirement Engineering” is written by MPS Bhatia, Akshi Kumar, and Rohit Beniwal . It provides an optimized classification
approach that automatically classifies the reviews into a bug report, feature request, shortcoming, and improvement request
relevant to requirement engineering. The optimized automatic classification improves the requirement engineering where the
developer straightforwardly knows what to improve further in the concerned app.
The lead guest editor, Vangipuram Radhakrishna, and other guest editors, Gunupudi Gali Suresh Reddy, Rajesh Kumar, and
Dammavalam Srinivasa Rao, of the special issue, are heartfully thankful to the Editor-in-Chief of the journal, Francesco Benedetto,
and also to the previous Editor-in-Chief of the journal, Professor Hamid Mcheick for their valuable support. Our special
thanks to the whole editorial staff, especially Wajeeha Syed, Ahmed, and Raheela Anjum, for their continuous support in the
preparation and publication of this special issue. Finally, the lead guest editor and guest editors of the special issue heartfully
express their gratitude to the authors for their quality contributions and the reviewers for providing timely reviews and their
Computer networks, communication systems, and other IT infrastructures have affected the environment adversely due to
excessive power consumption, increasing greenhouse gas emissions, leading to pollution during the production and disposal. To
address these issues and to create a sustainable environment, new energy models, algorithms, methodologies, platforms, tools
and systems are required to support next-generation computing and communication networks. Thus, Green computing and
communication solutions, designed with more renewable energy, higher energy efficiency, lower greenhouse gas emission, and
less harmful materials, are seeking more attention these days. It deals with the methods of utilizing computers in an ecological
The special issue was planned to focus on solutions for all aspects of green computing such as energy efficiency, carbon
footprint reduction and cooling management as well as green communication concepts in diverse fields and to find out new
innovative methods/technologies to reduce energy consumption for a better environment.
From a wide range of interesting research papers on several aspects of green computing, the guest editors, after undergoing
exhaustive peer-reviews from experienced and well-known researchers, have carefully selected 10 research papers. The final
decision for the inclusion of 10 research papers has been strictly based on the outcome of the rigorous peer-review process,
shortlisting successful research papers by researchers as peer review comments and guidelines.
A brief summary of the research papers included in this special issue is enlisted as follows:
The article by Sohal et al.  titled “An Energy Efficient Routing Approach to Enhance Coverage for Application-Specific
Wireless Sensor Networks using Genetic Algorithm” proposes a novel protocol titled “WCEGA” using Genetic Algorithm. The
cluster-based algorithm consists of two phases: cluster formation and data transmission. In cluster formation, the selection of
cluster heads and cluster members areas is based on energy and coverage efficient parameters. The governing parameters are
residual energy, overlapping degree, node density and neighbour’s degree. Experimental results state that WCEGA is better as
compared to existing protocols in terms of the best coverage and network lifetime, approximately by 40% and 45%, respectively.
The article by Vohra and Tiwari  titled “Multisensory Decision Level Fusion for Improvement in Urban Land Classification”
carries out the object based classification in urban environments by using fusion techniques on multisensory data to classify
natural and man-made objects. Multisensory data fusion using spectral and spatial features is done to improve classification
accuracy. The performance of the proposed framework has been verified by investigating the multistage feature level fusion.
Spatial and spectral features are explored using feature level fusion between multisensory data and then the database is classified
using a linear SVM classifier. The individual probabilities (confidence measures) from all such pairs of binary SVMs are
combined to uniquely represent the object feature to one of the classes. After summing up all the probabilities, the class with
the highest probability value represents the object through decision level fusion. The results reveal that the overall accuracies of
the SVM classifier are in the range of 53% to 90% for various classes, which are improved to 96-98% by majority voting rule.
The article by Malik et al.  titled “Reliability Analysis and Modeling of Green Computing Based Software Systems” proposes
a new failure rate behavior-based model centered on the green software development life cycle process. The model integrates
a new modulation factor for incorporating changing needs in every phase of green software development methodology.
The parameter estimation for the proposed model is done using Hybrid Particle Swarm Optimization and Gravitational Search
Algorithm. The model was tested on real-world datasets, i.e., GC-1 and GC-2 and experimental results state that the proposed
model is 60.05% better as compared to other models.
The article by Nigam and Dabas  titled “Enhanced Auxiliary Cluster Head Selection Routing Algorithm in Wireless Sensor
Networks” proposes a new enhanced GC-LEACH Algorithm to minimize the energy utilization and enhance the network
lifetime of WSN. To test the validity, simulations are performed in NS-2 simulator and it was proved that GC-LEACH performs
better as compared to traditional LEACH in terms of cluster head rotation in various rounds, the number of data packets
collected at the base station, energy consumption was reduced by 14-19% and a lifetime of WSN network was enhanced by 8-
The article by Verma et al.  titled “Cost-Effective Cluster-based Energy Efficient Routing for Green Wireless Sensor
Network” proposes a novel protocol titled “CECRP” to reduce the financial burden in cluster head selection for growth of green
WSN and it performs better with only two energy level nodes as compared to other protocols with three level nodes. Experimental
results prove that CECRP performs better as compared to TEDRP, SEECP and DRESEP protocols in varied parameters
and overall, the protocol is 33.33% more cost-effective as compared to the above protocols.
The article by Ahuja et al.  titled “Network Selection in Wireless Heterogeneous Environment Based on Available
Bandwidth Estimation” proposes a novel algorithm to estimate available bandwidth by taking averages, peaks, low points and
bootstrap approximation for network selection. The proposed algorithm is suitable for adaption in varied network conditions in
heterogeneous environments of 2G, 3G and WLAN networks without user intervention and is implemented in temporal and
spatial domains to check robustness. With experimentation, the proposed algorithm improves estimation error- less than 20%,
overhead- between 0.03% to 83% and reliability-99% as compared to existing techniques.
The article by Banda and Singh  titled “Enhance the Quality of Collaborative Filtering Using Tagging” proposes a Tag
and Time weight model with real value genetic algorithm to enhance the recommendation quality by removing the issues of
sparsity and cold start user problems with the help of missing value prediction.
The article by Singh et al.  titled “Adaptive Energy-Aware Algorithms to Minimize Power Consumption and SLA Violation
in Cloud Computing” proposes a novel adaptive heuristics approach that concerns with the utilization of resources for dynamic
consolidation of VMs based on mustered data from the usage of resources by VMs, while ensuring the high level of relevancy
to SLA and once under-load and over-load hosts are identified, VM placement decision is taken to minimize energy efficiency.
The proposed algorithm is tested via real-world workload traces in the CloudSim simulator.
The article by Gupta  titled “An Empirical Study of Predictive Model for Website Quality Analytics using Dataset of
different Domains of Websites” proposes an approach which associates the website assessment with user satisfaction and acceptance.
The proposed WQA (Website Quality Analytic) model considers websites from seven domains and using 13 UXbased
quality attributes to evaluate the quality of website using the real-time dataset of website domains on the categories of
good, average and bad using an algorithm.
The article by Kakamanshadi et al.  titled “Analysis of Relay Node Failure in Heterogeneous Wireless Sensor Networks”
presents a detailed analysis of relay nodes failure under distinct network configurations in heterogeneous wireless sensor
networks. The results state that as the area of the network increases, the average fault tolerance of the networks becomes
almost reduced and when the mean time to failure decreases, then the failure rate increases. The analysis will aid network designers
to decide the quantity of deployment of relay nodes with respect to fault tolerance level.
The main aim of this special issue is to enlighten the researchers regarding the latest advancements and trends in Green
Computing and Communication. It is expected that these papers can benefit students, researchers and academicians to do advanced
work in the area of Green Computing. With this special issue, there is strong, convincing evidence that Green Computing
plays a crucial role in optimizing tremendous problems in diverse areas of computer science.
We would like to thank the Editor-in-Chief of the journal, Professor Francesco Benedetto, for his huge support for this issue.
Our special thanks go to all editorial staff, especially Baseerat Hashmi, for their valuable and prompt support throughout
the preparation and publication of this special issue. We express our deep thanks to all the authors for their novel contributions
to this special issue. We also extend our thanks to all the reviewers for their time, devotion, hard work and on-time precision
response to ensure the high-quality review of the accepted papers.
olume of data, if it cannot lead us to an effective decision, be it smaller or larger. Artificial intelligence makes this massive amount of
data meaningful. Artificial intelligence simulates the human brain, the way the human brain thinks, acts, and reacts to its actions. Artificial
Intelligence (AI), machine learning, big data, and the internet of things have started to infiltrate our lives in various unexpected ways. The
algorithms of these technologies are beginning to improve ratings and scores on their own for research and investments in automobiles and
personal digital assistants. Technology is advancing to improve machines, and in the coming years, we can start approaching the level of
human intelligence with these systems [1-4].
Internet of Things (IoT) applications are growing exponentially, and an enormous amount of information is required for information
technology professionals. However, the limitations of IoT application layer protocols to send and receive messages from multiple large IoTs
(such as cloud) prevented the development of IoT applications. Today’s smart IoT devices are preventing these barriers from learning
adaptations from other IoT applications.
Big data is known for the large, unstructured, and complex data sets that are of great importance to companies. These data sets are too
complex to manage with traditional data processing software. Recent technological advances have significantly reduced the cost of storing
and processing data, allowing you to easily store large amounts of data like never before. The work of marketers has changed dramatically.
They can gain insight into creating highly effective marketing strategies by interpreting the tons of data available to the business. Big data in
the Internet of Things is a large and rapidly developing field in which many different methods and technologies can play a role. Due to the
rapid advances in machine learning and new advances in hardware, a dynamic change in methods and technologies can be observed.
Therefore, this overview is intended to be comprehensive and of a high standard [5-7].
We can finally conclude that technology is very important in any business today, and we are still struggling to integrate technology
with human efforts. Humans and businesses generate billions of gigabytes of data every day, but to use this data, we need to address
operational challenges and implement a digital strategy that works with cloud tools and initiatives. But the analysis can only be made when
you understand the field well. The combination of the Internet of Things, big data, cloud, and machine learning will take industries to the next
level and revolutionize the classic sense of the word. This special issue is planned with the intention of collecting quality papers from
different parts of the world. The special issue contains 18 papers, selected after a rigorous reviewing process conducted by a team of
renowned experts of the domain. All selected papers discuss the novel work related to AI, ML, IoT, Cloud, and Big data domain.
In the last few years, technologies related to images, video processing, computer graphics, and multimedia have been greatly
employed in various application areas such as image forgery detection, image analysis, image compression, face recognition, etc.
This special issue aims to invite researchers in related fields of image and video forensics, cybersecurity, digital forensics, multimedia
content security and its applications so they can join us in a quest to pinpoint the next-generation image and video forensics
solutions. This Thematic Special Issue of the Recent Advances in Computer Science and Communications incorporates nine
(9) articles identified with the field. A short review about the commitments for this Thematic Special Issue is as follows:
Mohapatra et al. contributes an article entitled “ECG Analysis: A Brief Review.” The objective of this paper is to provide a
short review of earlier techniques used for ECG analysis. It can provide support to the researchers in a new direction. The review
is based on pre-processing, feature extraction, classification, and different measuring parameters for accuracy proof. Also,
different data sources for getting the cardiac signal are presented, and various application areas of the ECG analysis is presented.
It explains the work from 2008 to 2018 .
Gianey et al. proposed an article entitled “Low Cost and Centimeter-Level Global Positioning System Accuracy Using Real-
Time Kinematic Library and Real-Time Kinematic GPSA.” This proposed model addresses the diverse issue of accomplishing
a centimeter-level accuracy framework. To get high precision inside the network, two GPS modules are utilized. One of
them is mounted on the rover, and another GPS is the base station of the setup. Both the GPS will have a double radio wire setup
to increase the reception level to reduce the noise and obtain centimeter-level precision. For long-range communication, the
rover utilizes Wi-Fi with TCP/IP stack protocol .
Singh et al. contribute an article entitled “Pose and Illumination Invariant Hybrid Feature Extraction for Newborns.” In this
work, a hybrid approach using Speeded Up Robust Features (SURF) and Local Binary Pattern (LBP) is proposed for newborns.
Moreover, the experiment is done for a single gallery image with improved results. The proposed method has 97.18% accuracy,
which is an 8% improvement over LBP and 8.6% improvement over SURF for Rank 5 .
Kumari et al. contribute an article entitled “Intuitionistic Fuzzy Shapley-TOPSIS Method for Multi-Criteria Decision Making
Problems based on Information Measures.” In the present paper, a multi-criteria decision-making (MCDM) method known
as the Shapley-TOPSIS approach, which is an extension of the classical TOPSIS method, is developed. After that, the interesting
properties among the developed divergence and entropy measures have also been derived. Then, the criterion weights are
ascertained by the Shapley function via entropy and fuzzy measure approach. Next, Shapley-divergence measures are applied to
calculate the closeness coefficient of alternative .
Tandon et al. contribute an article entitled “A novel and secure hybrid iWD-MASK algorithm for enhanced image security.”
The proposed hybrid concept of MASK with iWD algorithm is implemented on a different set of images. While comparing the
proposed approach with other existing methods, the obtainted results are satisfactory for various parameters like precision, recall,
and F-measure. In future work, the proposed algorithm can be applied for the other types of cryptography, like text, video
sharing, etc. .
Jena et al. proposed an article entitled “A Fully Convolutional Neural Network for Recognition of Diabetic Retinopathy in
Fundus Images.” In this paper, a fully convolutional neural network model is developed to classify the diseased and healthy
fundus images. Here, the proposed neural network consists of six convolutional layers along with rectified linear unit activations
and max-pooling layers. The absence of a fully connected layer reduces the computational complexity of the model and
trains faster as compared to traditional convolutional neural network models .
Usman et al. proposed an article entitled “Threshold Detection Scheme Based on Parametric Distribution Fitting for Optical
Fiber Channels.” A threshold detection mechanism is evaluated in this paper, which uses parametric probability distribution
fitting to the received signal. Based on our earlier work on visible light communication, the idea is extended to a fiber optic
channel, and it is found that the threshold value obtained by fitting a Rayleigh distribution to the received data results in error
probability approaching zero .
Pal developed a technique entitled “A Fast Method for Defogging of Outdoor Visual Images.” In this article, a comparative
analysis has been made on different existing image defogging algorithms. Then a technique has been proposed for image
defogging based on dark channel prior strategy. Experimental results show that the proposed method shows efficient results by
significantly improving the visual effects of images in foggy weather. Also, the computational time of the existing techniques
has been reduced by using the proposed technique .
Tagging with Incremental Clustering and Trust.” In the proposed work, a novel model is used to get an accurate result in which
trust and incremental clustering are used. The neighborhood is generated by using scalable clustering by partitioning the users
into several groups of clusters. Neighborhood generation is done based on active user. It determines the clusters that belong to a
particular item and considers only those items in a computation between the active user and neighborhood user which belongs
to the same user clusters as active users .
We would like to thank the previous and current Editor-in-Chief of the journal, Professor Hamid Mcheick and Francesco
Benedetto, for supporting this issue. We would like to thank all the editorial staff, especially Wajeeha Syed, Wajeeha Ahmed,
Raheela Anjum, and Baseerat Hashmi, for their prompt response and support throughout the publication of this special issue.
We express our deep gratitude to all the authors for their novel contributions to this special issue.
We also extend our gratitude to all reviewers for their time devotion, hard work, and on-time precision response to ensure
high-quality review of the accepted papers.
We hope that the quality research work published in this special issue will serve the concerned humanity, science, and technology.
Over the past three decades, the Information Technology has been one of the most interesting fields for research and development.
From commerce, healthcare, education, entertainment, and environmental management, information technology has
played an indispensable role for sustainable development of these sectors, and hopefully will continue to fuel further advances
for the same.
The primary interest of this special issue is to provide the platform for state of art research in information technology for
sustainable development. The focus of this special issue is on real world problems and their prospective solutions through information
technology. The special issue titled "Recent advancement in information technology for sustainable development” is
an excellent collection of review and research articles. From a wide range of interesting 2 reviews & 13 research papers are
selected for this special issue after undergoing exhaustive peer-reviews with experienced and well-known reviewers.
The list of contributions in this special issue is as follows:
Mining of Closed High Utility Itemsets: A Survey, written by Singh et al. . Finding High Utility Itemsets (HUIs) is one of
the major problems in the area of frequent itemsets mining. However, HUIs mine lots of redundant itemsets which degrade the
performance and importance of high utility itemsets mining. For overcoming this limitation, closed HUIs mining has been proposed.
Closed high utility itemsets mining finds complete and nonredundant itemsets. The main goal of this survey is to provide
recent studies and future research opportunities. This paper provides a rough outline of the recent work and gives a general
view of closed high utility itemsets mining field.
Influence Maximization on Social Networks: A Study, written by Singh et al. . Influence Maximization, which selects a
set of k users (called seed set) from a social network to maximize the expected number of influenced users (called influence
spread), is a key algorithmic issue in social influence analysis. In this paper, we give recent studies on influence maximization
algorithms. The main goal of this survey is to provide recent studies and future research opportunities. We give taxonomy of
influence maximization algorithms with the comparative theoretical analysis.
A novel variant of bat algorithm inspired from ‘range determination’ feature of ‘bats’bats written by Sharma et al. . In
this work, many variants of Bat Algorithm are studied developed by various researchers. Despite its drawback of getting
trapped in local optima, it is preferred over other swarm intelligence techniques. Considering the performance of Bat Algorithm
and to extend the existing work, biological behavior of bats is explored in this research work.
Source redundancy management and host intrusion detection in wireless sensor networks, written by Singh et al. . Intrusion
Detection System (IDS) is a Software application which gives the facility to monitor the traffic of network, event or activities
on network and finds out any malicious operation if present. In this paper, a new protocol was developed that can detect the
Wireless Network Attack based on the reference of TCP/IP Model. In the proposed system, the new feature is integrated in the
IDS which is built in the router itself.
SVM-PCA based Handwritten Devanagari Digit Character Recognition written by Khamparia et al. . There is ample information
available on handwritten character recognition on Indian and Non-Indian scripts but very few articles emphasize the
recognition of Devanagari scripts. Therefore, this paper presents an efficient handwritten Devanagari character recognition system
based on block based feature extraction and PCA-SVM classifier. We have collected samples of handwritten Devanagari
characters from different handwritten experts for classification. For experimental work, total of 100 images having Devanagari
digit characters have been used for the purpose of training and testing. The proposed system achieves a maximum recognition
accuracy of 96.6 % and 96.5% for 5 & 10 fold validations with 70% training and 30% testing data using block based feature
and SVM classifier having different kernels.
Localization and Tracking of Mobile Jammer Sensor Node Detection in Multi-Hop Wireless Sensor Network, written by
Gianey et al. . The jammer in a wireless sensor network is located and tracked with open access and shared nature of the
wireless medium. The existing algorithms mainly track the stationary jammer. Mobile jammers often move from one place to
another becoming difficult to be tracked. Mobile jammer location tracker algorithm is proposed to find the location of a mobile
jammer with four steps selection i.e., initial examining node, determination of supporting node, trilateration localization and
examining group handover. The accurate location of the mobile jammer is predicted with the proposed algorithm. The effectiveness
of the proposed scheme is evaluated by conducting simulation experiments. It is observed that the proposed technique
outperforms the mobile jammer tracker effectively and accurately.
A Stack Autoencoders Based Deep Neural Network Approach for Cervical Cell Classification in Pap-Smear Images written
by Singh et al. . Early detection of cervical cancer may give life to women all over the world. Pap-smear test and Human
papillomavirus test are the techniques used for the detection and prevention of cervical cancer. In this paper, pap-smear images
are analysed and cells are classified using stacked autoencoder based deep neural network. Pap-smear cells are classified into 2
classes and 4 classes. Two class classification includes classification of cells in normal and abnormal cells while four-class
classification includes classification of cells in normal cells, mild dysplastic cells, moderate dysplastic cells and severe dysplastic
IMSM: An Interval Migration Based Approach for Skew Mitigation in MAPREDUCE, written by Singh et al. . This
paper proposes an algorithm for MapReduce to balance the load and eliminate the skew on Map tasks. It reduces the execution
time of job by lowering the completion time of the slowest task. Method: The proposed method performs one-time settlement
of load balancing among the Map tasks by analyzing the expected completion time of the Map tasks and redistributes the load.
It uses intervals to migrate the overloaded or slows tasks and appends them on the under loaded tasks.
Greedy Load Balancing Energy Efficient Routing Scheme for Wireless Sensor Networks written by Maratha et al. . Despite
so many constraints, the limited battery power of the sensor nodes is the core issue in Wireless Sensor Networks. This
compels how to extend the lifetime of the network as long as possible. One of the ways to solve the problem is to balance the
relay traffic load to extend the lifetime. In this paper, a load balancing algorithm is suggested that selects the best possible relay
node so that uniform consumption of the battery power of the sensor nodes can be ensured.
Graph-based Application Partitioning Approach for Computational Offloading in Mobile Cloud Computing, written by
Robin Prakash Mathur and Manmohan Sharma . Using the offloading concept, a mobile device can offload its computation
to the cloud servers and receives back the results on the device. An important question that arises in the offloading scenario is
which part of the application needs to be offloaded remotely. In order to identify that, the application needs to be partitioned. In
this paper, the graph partitioning approach is considered which is based upon the spectral graph partitioning with the Kernighan
Lin algorithm. Experimental results show that the proposed approach performs optimally in partitioning the application. The
proposed technique gave better results than the existing techniques in terms of edge cut which is less, concluding minimum
communication cost among components and thus save energy of the mobile device.
Big Data Analysis on Job Trends Using R written by Somula et al. . This work illustrates the use of data mining and
advanced data analysis techniques such as data aggregation, summarization along with data visualization using R tool to understand
and analyse the job trends in the United States of America (USA) and then drill down to analyse job trends for data science-
related job positions from year 2011 to 2016.
Role of Self Phase Modulation and Cross Phase Modulation on Quality of Signal in Optical Links written by Karamjit Kaur
and Anil Kumar . Among the different impairments, the present work focuses on phase modulations owing to the intensities
of signals themselves as well as the neighboring signals. It includes the influence of SPM, SPM and XPM, system parameters
like signal power, wavelength and fiber parameters like attenuation coefficient, dispersion coefficient and their influence on Qvalue
and BER. The analysis is done through a single and two-channel transmitter system with varied power, wavelengths and
system parameters. The corresponding optical spectrums are analysed.
Impact of System Parameters of Optical Fiber Link on Four Wave Mixing written by Kumar and Kaur . The present
work aims to identify and describe the role of FWM in optical networks. The mathematical model of FWM is studied to know
the parameters influencing the overall impact on system performance. The power of optical source, channel spacing, distance of
transmission and presence of dispersion are considered as key factors influencing FWM power being developed. Their impact
on FWM power and hence, FWM efficiency is calculated. In addition, the influence of FWM on Quality of transmission is
quantified in terms of BER and Q-factor.
TraCard: A Tool for Smart City Resource Management based on Novel Framework Algorithm written by Singh et al. .
The model proposed in the paper captures the necessity of development of an efficient method that considers the finiteness of
fossil fuels by monitoring the distribution of fuel and its consumption. The purpose of this project is to save energy with aim of
AI Engine managed logistics and goal of creating Energy-Efficient survival of the human species.
Resource Efficient Deployment and Data Aggregation in Pervasive IoT Applications (Smart Agriculture) written by Zahoor
and Naaz . For heterogeneous scenarios, we propose a clustering approach, Superior Aggregator Resource Efficient Clustering
(SAREC), to address the resource constraints in pervasive Edge-IoT applications. The comparison of homogeneous and
heterogeneous networks is based on LEACH and SAREC protocols, respectively. The results show that SAREC is 25% more
efficient in energy utilization and network lifetime than LEACH. The results also show that SAREC is more efficient in terms
of storage and processing time as compared to LEACH.
The special issue contains research papers exploring novel concepts and applications related to the Internet of Things. This
issue contains research papers elaborating and exploring novel concepts and practices involved in short-range and long-range
communication technologies, data collection, analysis, processing and visualization tools from big market giants and its multifaceted
advantages in network navigability, scalability, evaluation of objects’ trustworthiness, service composition, object discovery,
behavior classification and prediction, giving an accelerated momentum for becoming one of the most popular future
In this special issue, we aim to focus on recent research related to the Internet of Things methods and applications where we
selected research papers after a peer-review process conducted by a team of domain experts. These papers deal with applying SI
techniques in the area of Internet of Things, Cloud computing, Vehicle networks, intelligent networks and security.
SUMMARY OF ACCEPTED PAPERS
This Special issue contains 4 papers that are briefly discussed as follows:
The article by Sivakumar, Veeramani, Pandi and Ganesh Gopal  “A Novel Encryption of Text Messages using Two Fold
Approach” proposes that the amount of digital data created and shared via the internet has been increasing every day. Though
there are several cryptosystems to secure the information, in the proposed security framework, there is a necessity to introduce
new methods in order to protect information from the attackers. A simple encryption method using binary tree traversals and
XOR operation is developed. Encrypting data using binary tree traversals is a different way compared with other traditional
encryption methods. The proposed method is fast, secure and can be used to encrypt short messages in real-time applications.
The article by Bhavani and Srimathi , titled “Optimal adaptive data dissemination protocol for VANET road safety using
optimal congestion control algorithm” presents a vehicular ad-hoc network (VANET) to disseminate traffic information of the
data gathered, and road conditions are forwarded from source vehicle to many destination vehicles on the road. The process of
data dissemination plays an important role in VANET and is used to improve the quality of travelling to avoid unwanted accidents.
The suggested OAddP protocol performs very efficiently when compared with the existing protocols in terms of end-toend
delay, success ratio, redundancy rate, collision rate, number of control OH messages, propagation distance and dissemination
The article titled  “An Accomplished Energy Aware Approach for Server Load Balancing in Cloud Computing” by Alekhya
Orugonda and Dr. V. Kiran Kumar, represents a method for cloud computing, which is the consignment of on-demand
computing services from applications to storage and processing power consistently over the internet and on a pay-as-you-go
basis. The comforts of our day-to-day life almost depend on cloud efficiency. Cloud efficiency means ensuring the finest possible
use of cloud resources at minimum cost. The designed EACLBT (Energy-Aware Cloud Load Balancing Technique) deploys
the virtual machines for power saving purposes. The average power consumption is used as performance metrics and the
result of PALB is used as a baseline. The EACLBT can reduce the number of power-on physical machines and average power
consumption compared to other algorithms with power saving. It exhibited that an idle server consumes approximately 70% of
the power consumed by the server running at the full CPU speed.
The article titled, “Vedic Arithmetic based High Speed & Less Area MAC Unit for computing devices” by Selvakumar
Jayakumar, Prithiviraj Rajalingam, Rizwan Patan and Manikandan Ramachandran  presents some rapid improvements in the
technology that have enabled the design of high-speed devices, modified computational elements for FPGA implementation.
With complexity increasing day-to-day, there is a demand for modified VLSI computational elements. Basically, for the past
decade, an improvement in the basic VLSI Operators like adder, and multiplier is significant. The basic multiplication operator
is completely refined for FPGA implementation. Results were found very promising and a complete working tool for translation
Collectively, these 4 papers illustrate various issues related to the Internet of Things and Internet applications, which can be
dealt with using IoT processing, cloud computing processing, security, expert systems and network intelligence. It is expected
that these papers will help provide the prospective researchers with valuable resources and motivate them to work on advanced
and challenging issues related to similar research domain. With this special issue, there is strong, convincing evidence that the
Internet of Things and computing Intelligence can play a crucial role in proposing the solutions of multi-disciplinary challenging
problems with appreciable results.
Cognitive Computing focuses on mimicking human behavior and reasoning to solve complex problems where the answers
may be ambiguous and uncertain. AI augments  human thinking to solve complex problems. It focuses on providing accurate
results. The phrase cognitive computing is closely associated with IBM's cognitive computer system, Watson. The goal of cognitive
computing is to simulate human  thought processes in a computerized model. Using self-learning algorithms that use
data mining, pattern recognition and natural language processing, the computer can mimic the way the human brain works.
Cognitive tools are generalizable computer tools that are intended to engage and facilitate cognitive processing. Cognitive
computing systems can analyze and combine more information on a topic than any one person could ever be expected to
The special issue of the journal titled "Recent Advances in Computer Science and Communications" is an excellent collection
of review and research articles in the field of cognitive computing, its methodologies and applications. A call for the paper
was issued for this special issue. The guest editors feel happy to announce this special issue of the most reputed journal of Bentham
From a wide range of interesting research papers on various aspects of cognitive computing, the guest editors, after undergoing
exhaustive peer-reviews from experienced and well-known reviewers, have carefully selected 26 research papers out of
43 submitted papers. The final decision for the inclusion of 26 research papers has been strictly based on the outcome of the
rigorous peer-review process, shortlisting successful research papers by researchers as per reviewers' comments and guidelines.
Resilient, scalable and extensible mission-critical networks are used to interconnect datacenters, enterprise, customer sites
and mobile entities. Fault tolerance, reliability and availability are the important issues addressed by researchers to ensure the
smooth delivery of services by mission critical networks in emergency and disaster scenarios [1, 2]. In this special issue, we
aim to highlight the recent trends in fault-tolerance, reliability and availability for the design of mission-critical network and
services. The role of artificial intelligence based techniques have also been highlighted for the optimization and solving the
problems in developing mission-critical systems and services. All the 13 papers of the Special issue have been selected after an
exhaustive reviewing process conducted by the team of renowned experts in the field. These papers deal with the recent techniques
and trends in mission-critical systems with reference to fault-tolerance, reliability and availability.
In “Summary of Accepted Papers” section, we present a brief summation of the selected papers for this special issue and
“Conclusion” section provides concluding remarks.
SUMMARY OF PAPERS
The article “A Review of Cloud Computing Adoption Issues and Challenges” by A. Dhanapal and P. Nithyanandam 
covers the broad classification of the issues and challenges faced by the organization to adopt the cloud computing model.
The article “Malicious Route Detection in Vehicular Ad-hoc Network using Geographic Routing with Masked Data” by P.
Saravanan, R. Logesh, V. Vijayakumar, V. Subramaniyaswamy, and G. Xiao-Zhi  proposes Geographic Routing Protocol
for malicious route detection in Vehicular Ad-hoc Network with masked data.
The article “Cost-Aware Ant Colony Optimization for Resource Allocation in Cloud Infrastructure” by Punit Gupta, Ujjwal
and Vaishali  has proposed a novel a learning-based cost efficient algorithm for cloud infrastructure. The proposed algorithm
has been compared with existing Round Robin and ACO algorithm.
The article “Machine Learning Based Support System for Students to Select Stream (Subject)” by Kapil Sethi, Varun
Jaiswal and Mohd Dilshad Ansari  proposes different machine learning algorithms were developed to support the students to
The article “Performance Analysis of DCF-Two Way Handshake vs RTS/CTS During Train-Trackside Communication in
CBTC based on WLAN802.11b” by Bhupendra Singh and Rajesh Mishra  handles four-way handshake (FWH), request to
send (RTS) and clear to send (CTS) delay with better packet delay time.
The article “An Energy Efficient Routing Protocol Based On New Variable Data Packet (VDP) Algorithm for Wireless
Sensor Networks” by Veervrat Singh Chandrawanshi, Rajiv Kumar Tripathi, Rahul Pachauri and Nafis Uddin Khan  proposes
an energy-aware algorithm for the transmission of variable data packets from sensor nodes to the base station according to
the balanced energy consumption by all the nodes of a WSN.
The article “Brain Tumor Detection from MR Images Employing Fuzzy Graph Cut Technique” by Jyotsna Dogra, Shruti
Jain, Ashutosh Sharma, Rajiv Kumar and Meenakshi Sood  presents an approach for the automatic segmentation of brain
MRIs by selecting the seed points and employing fuzzy graph cut technique.
The article “SEGIN-Minus: A New Approach to Design Reliable and Fault-Tolerant MIN” by S. Gupta and G. L. Pahuja
 presents new reliable MIN named as a (Shuffle Exchange Gamma Interconnection Network Minus) SEGIN-Minus, which
provide reliability and fault tolerance with less number of stages.
The article “ANN-Based Relaying Algorithm for Protection of SVC- Compensated AC Transmission Line and Criticality
Analysis of a Digital Relay” by Farhana Fayaz and G.L. Pahuja  presents the protection of transmission line compensated
with static VAR compensator (SVC) and criticality ranking of different failure modes of a digital relay is carried out.
The article “An Intelligent Resource Manager Over Terrorism Knowledge Base” by Archana Patel, Abhisek Sharma and
Sarika Jain  makes an effort at creating the largest comprehensive knowledge base of terrorism and related activities, people
and agencies involved, and extremist movements; and providing a platform to the society, the government and the military
personnel in order to combat the threat of the global menace terrorism.
The article “Dimensionality Reduction Technique in Decision Making Using Pythagorean Fuzzy Soft Matrices” by Rakesh
Kumar Bajaj and Abhishek Guleria  presents a technique for finding a threshold element and value for the information provided
in the form of Pythagorean fuzzy soft matrix. A comparative analysis in contrast with the existing methodologies has also
The article “Optimization of PV Based Standalone Hybrid Energy System using Cuckoo Search Algorithm” by Vinay
Anand Tikkiwal, Sajai Vir Singh and Hariom Gupta  deals with the design and optimization of a stand-alone hybrid renewable
The article “Probabilistic and Fuzzy based Efficient Routing Protocol for Mobile Ad Hoc Networks” by M.M. Agarwal,
Hemraj Saini and M.C. Govil  proposes a new energy efficient routing protocol for best route selection using fuzzy logic
from multiple routes with efficiency in overheads and energy consumption.
Collectively, these 13 papers present the diverse range of issues regarding mission critical systems, network and services
with reference to the recent trends in artificial intelligence techniques for fault-tolerance, reliability and availability. With this
special issue, there is a strong convincing evidence that fault-tolerance, reliability and availability with artificial intelligence
techniques plays an important role towards solving mission critical problems with encouraging results. We hope that the quality
research work published in this special issue will be able to serve the concerned humanity, science and technology.
We would like to thank the Editor-in-Chief of the journal, for his continuous support for completing this issue. The Guest
Editors are thankful to the authors and reviewers who contributed to this special issue with their scientific work and useful
comments, respectively. Moreover, the guest editors also want to thank Mr. Ashutosh Sharma, Research Scholar, JUIT, India
for his back end support for publicizing and completing the SI.
The special issue contains research papers elaborating advancements in Swarm Intelligence for optimizing problems in the
Next Generation Networks. Swarm Intelligence [1-3], as demonstrated by natural biological swarms, exhibits numerous powerful
features that are desirable in many engineering systems, such as communication networks. In addition, new paradigms for
designing autonomous and scalable systems may results from analytically understanding and extending the design principles
and operations in intelligent biological swarms. The communication network management is becoming increasingly difficult
due to the increase in network size, topological changes, complexity and security. A new class of algorithms, inspired by swarm
intelligence, is currently developed that can solve numerous problems related to the communication networks, and these algorithms
are optimized enough to rely on the interaction of a multitude of simultaneously interacting agents.
In this special issue, we aim to highlight the importance of Swarm Intelligence based optimized algorithms for solving problems
and optimizing next generation communication networks.
The special issue contains 5 papers, selected after a vigorous reviewing process conducted by the team of renowned Swarm
Intelligence and Communication networks experts. These papers deal with applying the SI based techniques in the area of
In “Summary” section, we present a brief summation of the selected papers for this special issue (Part-3) and “Conclusion”
section provides concluding remarks.
This Part-3 of the Special issue contains 5 papers, that are briefly discussed as follows:
The article “Tree-based Ant Colony Optimization Algorithm for Effective Multicast Routing in Mobile Adhoc Network” by
Priyanka Sharma, Manish Kumar Nunia, Madhushree B and Sudeep Tanwar  proposes an ACO based approach for the optimization
of QoS based multicast routing algorithm for multimedia streaming applications. The routing protocol being proposed
is simulated as the tree structure where the nodes are stations and the edges are links. Simulation-based-results state that
proposed approach is better in performance as compared to AntNet due to trace maintenance, tree approach for path selection
and implementation of local and global update of pheromone values.
The article “Determining Network Communities based on Modular Density Optimization” by Seema Rani and Monica
Mehrotra  addresses the problem of the resolution limit posed by modularity as fitness function and novel algorithm is proposed
using discrete bat algorithm. To test the novelty of algorithm, experimentation was conducted on four real-world datasets
and it was observed that proposed algorithm is better as compared to the traditional and evolutionary community detection algorithms
in terms of number of communities, maximum modularity and average modularity.
The article “Learning-Based Task Scheduling Using Big Bang Big Crunch for Cloud Computing Environment” by Pradeep
Singh Rawat, Priti Dimri and Punit Gupta  proposes a meta-heuristic approach-based cost-aware algorithm using the Big-
Bang Big-Crunch for reducing the execution time and cost paid for resources in cloud computing. The results are compared
with Genetic Algorithm and it was found that proposed algorithm has better performance in terms of time and cost.
The article “Catechize Global Optimization through leading Edge Firefly based Zone Routing Protocol” by Neha Sharma,
Sherin Zafar and Usha Batra  proposes a novel protocol i.e. FRA-ZRP to improvise the performance of zone routing protocol
by reducing the amount of reactive traffic to provide solution to degraded network performance in case of large networks. In
addition to this, researchers have made use of Firefly algorithm to achieve global optimization. The proposed approach is tested
using simulation and it was observed that FRA-ZRP is better as compared to Traditional ZRP and RA-ZRP in terms of End-to-
End delay, route aggregation and overall QoS in MANETs.
The article “Into the World of Underwater Swarm Robotics: Architecture, Communication, Applications and Challenges”
by Keerthi K.S, Bandana Mahapatra and Varun G. Menon  provides comprehensive review of the Underwater Swarm Robotic
Technology and the paper outlines concepts, technical background, architecture and communication mediums and also
highlights the various issues and challenges surrounding underwater swarm robots.
Collectively, these 5 papers illustrate the diverse range of issues regarding Communication Networks which can be solved
via applying Swarm Intelligence techniques. It is expected that these papers can provide strong base to researchers with valuable
resources and motivation to work on more advanced challenging issues matching this research. With this special issue, there
is a strong convincing evidence that Swarm Intelligence plays a crucial role towards optimizing tremendous problems in Communication
Networks with encouraging results.
We would like to thank the previous Editor-in-Chief of the journal, Professor Hamid Mcheick for his huge support for this
issue. Our special thanks go to all the editorial staff, especially Wajeeha Syed, Wajeeha Ahmed and Raheela Anjum for their
valuable and prompt support throughout the preparation and publication of this special issue. We express our deep thanks to all
authors for their novel contributions to this special issue. We also extend our thanks to all reviewers for their time devotion,
hard work and on-time precision response to ensure high quality review of the accepted papers.
Over the past few decades, swarm intelligence has emerged as a powerful approach to solving optimization as well as other
complex problems in the real world. Swarm Intelligence models are inspired by social behaviours of simple agents interacting with
each other as well as with the environment, e.g., foraging behavior of ants and bees, flocking of birds, schooling of fish, etc. [1-3].
The collective behaviours that emerge out of the interactions at the colony level are useful in achieving complex goals.
Algorithms, applications and methodologies of the Swarm Intelligence approach explore the emerging realm of swarm intelligence
that finds its basis in the natural behaviour of animals.
The special issue of the Journal titled “Recent Advances in Computer Science and Communications” is an excellent collection
of review and research articles in the field of swarm intelligence-related algorithms, methodologies and applications. An
open call for paper was issued for this special issue. The guest editors feel happy to announce this special issue of the most reputed
journal of Bentham Science.
From a wide range of interesting research papers on various aspects of swarm intelligence, the guest editors, after undergoing
exhaustive peer-reviews from experienced and well-known reviewers, have carefully selected 6 research papers and 1 review.
The final decision for the inclusion of 6 research and 1 review papers has been strictly based on the outcome of the rigorous
peer-review process, shortlisting successful research papers by researchers as per reviewers’ comments and guidelines.
A brief summary of the research papers included in this special issue is enlisted as follows:
The first article by Ranjendra Singh, Anurag Singh and Arun Solanki  titled “A Binary Particle Swarm Optimization for IC
floorplanning” proposed a novel SI based algorithm “Binary Particle Swarm Optimization” combined with floor plan representation
to optimize the area and wire length for a fixed outline floorplan. The experimental results on the Microelectronic Center of
North Carolina (MCNC) validated the proposed BPSO algorithm towards better convergence for area and wire length optimization,
as compared to other meta-heuristic algorithms. The results obtained were compared with the solutions derived from other
meta-heuristic algorithms, and it was found that area is improvised up to 10% and the wire length is improvised up to 28%.
The second article by Amandeep Kaur Virk and Kawaljeet Singh  titled “On Performance of Binary Flower Pollination
Algorithm for Rectangular Packing Problem” assessed the performance of recent metaheuristic approach named “Binary Flower
Pollination Algorithm” for rectangle packing optimization problem, which was employed to search the optimal placement
order and optimal layout. The algorithm was tested on benchmark datasets and the simulation results proved that the performance
of binary flower pollination algorithms is the best as compared to other existing metaheuristic approaches.
The third article by Sandeep Kumar, Anand Nayyar, Nhu Gia Nguyen and Rajani Kumari titled  “Hyperbolic Spider
Monkey Optimization Algorithm” studied various perturbation techniques used in spider monkey optimization algorithms and
proposed a novel algorithm titled “Hyperbolic Spider Monkey Optimization Algorithm” inspired by hyperbolic growth function.
The proposed algorithm was tested over a set of 23 CEC 2005 benchmark problems and it was observed that the proposed
algorithm is better as compared to other approaches in terms of improved perturbation rate, desirable convergence precision,
rapid convergence rate and improved global search capability.
The fourth article by Avinash Kaur, Pooja Gupta and Manpreet Singh titled  “A Data Placement Strategy Based on Crow
Search Algorithm in Cloud Computing” proposed a novel data placement strategy based on Crow Search Algorithm (CSA) to
dynamically distribute the data sets to appropriate data center’s during the runtime stage of the workflow. Simulation-based
results proved that the CSA outperforms in locating the best data center for data placement for best workflow management as
compared to other algorithms.
The fifth article by Asima Kukkar and Rajni Mohana titled  “Bug Report Summarization by using Swarm Intelligence
Approaches” proposed a novel approach for the extraction of crucial information from extensive reports to summarize the problem
in short description. The objective of this paper was to generate an unsupervised extractive bug report summarization system
to apply on any dataset without much effort and high cost for creating manual summaries of dataset, to handle comments
and summaries in an effective manner, reduce data sparsity, information and redundancy for lengthy data set and to provide
accurate summary information. The proposed approach was tested with other supervised and unsupervised approaches and it
was concluded that the Hybrid swarm intelligence approach provides better results.
The sixth article by Soniya Lalwani, Harish Sharma and Kusum Deep titled  “An Implementation of Three-Level Multi-
Objective ABC Algorithm for RNA Multiple Structural Alignment” presented Artificial Bee Colony algorithm based threelevel
multi-objective approach for performing structural alignment of RNA sequences i.e. MO-3LABC. MO-3LABC algorithm
was compared with MO-TLPSO algorithm and results were compared for pairwise and multiple sequence alignment datasets for prediction accuracy and solution quality criteria. It was proved that MO-3LABC outperforms MO-TLPSO in all evaluation
The seventh article by Chinwe Igiri, Yudhveer Singh and Ramesh F.C. Poonia titled  “A Review Study of Modified
Swarm Intelligence: Particle Swarm Optimization, Firefly, Bat and Gray Wolf Optimizer Algorithms” explored the improvement
strategies of various swarm intelligence algorithms with regard to PSO, Firefly, Bat and Gray Wolf optimizer with a primary
objective to understand the trends and relationships among their performance.
The main aim of this special issue is to enlighten the researchers regarding the latest methodologies, algorithms and applications
with regard to Swarm Intelligence. It is expected that these papers can benefit students, researchers and academicians to
do advanced work in the area of swarm intelligence. With this special issue, there is a strong convincing evidence that Swarm
Intelligence plays a crucial role in optimizing tremendous problems in diverse areas of computer science.
We would like to thank the Editor-in-Chief of the journal, Professor Francesco Benedetto for his huge support for this issue.
Our special thanks go to all editorial staff, especially Wajeeha Syed, Wajeeha Ahmed and Raheela Anjum for their valuable
and prompt support throughout the preparation and publication of this special issue. We express our deep thanks to all authors
for their novel contributions to this special issue. We also extend our thanks to all the reviewers for their time, devotion, hard
work and on-time precision response to ensure the high-quality review of the accepted papers.