EAI Endorsed Transactions on Cloud Systems

EAI Endorsed Transactions on Cloud Systems is an open access, peer-reviewed scholarly journal focused on cloud systems and four technology pillars: mobile computing, cloud services, big data analytics, and social networking. The journal publishes research articles, review articles, commentaries, editorials, technical articles, and short communications with a triannual frequency. Authors are not charged for article submission and processing.

Editor(s)-in-Chief: Cathryn Peoples and Guanfeng Liu

Aims & Scope
Indexing
Editors in Chief
Editorial Board
Special Issues

The EAI Endorsed Transactions on Cloud System (ToCS) is an international venue for publishing innovative and cutting edge results on the convergence of next-generation technologies and methodologies reshaping our way of living. The emerging converged platform for growth and innovation is built on four technology pillars: mobile computing, cloud services, big data and analytics, and social networking.

Researchers and practitioners involved in cloud systems can publish information on theory, engineering principles, enabling technologies, and practical experiences related to cloud systems.

ToCS will offer an end-to-end view on the challenges and technologies in cloud systems, foster research that addresses the interaction between and across the different technology pillars, and ultimately help shape the future of cloud systems as they transform business and society.

Topics include, but are not limited to, the following:

Anything as a Service (XaaS), for example: Infrastructure as a service (IaaS), Business process as a service (BPaaS) or Disaster Recovery as a service (DRaaS)
Cloud architecture and foundation services
Big data management and analytics
Internet of things (IoT) and Mobile Cloud
Virtualization technology
The virtual enterprise, software defined networks (SDN), Network Function virtualization (NFV), software defined Storage, Data virtualization, etc.
Cloud security, privacy, and trust
Workload deployment and migration
Resource management provisioning and load balancing
Energy management in cloud centers
Cloud programming models and tools
Private, Public, Hybrid and Federated clouds
API management, collaboration and integration
Content distribution and management
Service lifecycle management
Service management automation
Cloud computing programming models
Multi-tenancy
Discovery of services and data
Monitoring and Metering
Systems of records and systems of engagement
Business models, pricing, and software licensing
Modeling and Testing very large infrastructures
Standardization, regulation and compliance management

Special issue on Top trends in Cloud Computing (Manuscript submission deadline: 2022-01-31; Notification of acceptance: 2022-03-18; Submission of final revised paper: 2022-05-02; Publication of special issue (tentative): 2022-06-30)

Main Guest Editor: Dr. Anupama Chadha (Manav Rachna International Institute of Research and Studies, Faridabad, India) Guest Editor: Dr. Sachin Sharma (Manav Rachna International Institute of Research and Studies, Faridabad, India) Guest Editor: Dr. Anupriya Jain (Manav Rachna International Institute of Research and Studies, Faridabad, India) Guest Editor: Kourosh Ahmadi (Auckland Institute of Study, New Zealand) Guest Editor: Munish Sabharwal (Galgotias University,India)

Editors-in-Chief
Cathryn Peoples, The Open University; Ulster University, UK
Guanfeng Liu, Macquarie University, Australia
Area Editors
Vijayakumar Varadarajan (The University of New South Wales, Australia)
Bharat S. Rawal (Pen State University, USA)
Ahmad Karim (Bahauddin Zakariya University, Pakistan)
Antonio Celesti (University of Messina, Italy)
Dana Petcu (West University of Timisoara, Timişoara, Romania)
Domenico Talia (Università della Calabria, Italy)
Florin Pop (Politehnica University of Bucharest, Romania)
Gokhale Anu (Illinois State University, USA)
Jean-Philippe Martin-Flatin (Switzerland)
K. R. Rao (University of Texas, USA)
Lizhe Wang (Chinese Academy of Sciences (CAS), China)
Luciano Baresi (Politechnico di Milano, Italy)
Manish Kumar (IIT-Allahabad, India)
Marcel Kunze (Karlsruhe Institute of Technology (KIT), Germany)
Maria Dolores Cano Baños (Universidad Politécnica, Spain)
Marios D. Dikaiakos (University of Cyprus, Cyprus)
Marios Dikaiakos (University of Cyprus)
Massimo Villari (University of Messina, Messina, Italy)
Mirco Marchetti (University of Modena and Reggio Emilia, Modena, Italy)
Mohamamad Shojafar (University Sapienza of Rome, Italy)
Nik Bessis Edge (Hill University)
Patrick Siarry (University of Paris)
Siguang Chen (Nanjing University of Posts and Telecommunications, China)
Raouf Boutaba (University of Waterloo, Canada)
Roman Vitenberg (University of Oslo, Norway)
Sri Devi Ravana (University of Malaya, Malaysia)
Syed Rizvi (The Pennsylvania State University, USA)
Vasilios Andrikopoulos (University of Stuttgart, Germany)
Verdiana Grace Masanja (NM-AIST, Tanzania)
V. Subramaniyaswamy (SASTRA Deemed University, India)
Xiao-Zhi Gao (University of Eastern Finland, Finland)
Marco Lucio Scarpa (University of Messina)
Yuvaraja Devajaran (Palo Alto Networks Inc, CA, USA)
Jitendra Kumar Verma (Amity University, India)

Cathryn Peoples¹

Cathryn Peoples received the B.A. degree (with honours and diploma in industrial studies) in business studies with computing, M.Sc. degree in telecommunications and internet systems, and Ph.D. degree in networking from Ulster University, U.K., in 2004, 2005, and 2009, respectively. She is currently employed by The Open University in the School of Computing and Communications within the Faculty of Science, Technology, Engineering & Mathematics as an Associate Lecturer in Software Engineering ((1) South & West & S. Wales, (2) Central & N. Wales) and for the Computing and IT Project (UK and Ireland). Cathryn is also employed on a part-time basis as a Research Associate at Ulster University working on Internet of Things (IoT) research. Prior to these appointments, Cathryn was employed as a Lecturer at Queen Mary University of London in the School of Electronic Engineering and Computer Science, with shared teaching on the Joint Programme at the Beijing University of Posts and Telecommunications. Teaching in this post includes the Networks and Protocols module on the B.Sc.(Eng) Internet of Things Engineering degree, and the Communications and Networks module on the BEng(Hons) Computer Systems Engineering degree. Previously, Cathryn has been employed as a Teaching Fellow in the Faculty of Computing and Engineering at Ulster University, teaching on an M.Sc. degree in Professional Software Development. Prior to her appointment into this post, she worked as a Research Associate at Ulster University in the area of next generation networking. Her research interests include cloud management, cross-layer protocol optimisation, delay-tolerant networking, smart cities, and green IT. She is a member of the Institute of Electrical and Electronics Engineers and the Association for Computing Machinery. Cathryn became a Certified Associate in Project Management in August 2008, an Associate Fellow of the Higher Education Academy in February 2015, and achieved Fellowship of the Higher Education Academy in March 2018. Most recently, Cathryn secured the Cisco Certified Entry Level Technician (CCENT) accreditation in November 2018. In September 2019, Cathryn was awarded Best Reviewer for support to the 16th International System-on-a-Chip (SoC) Design Conference (ISOCC) 2019. She has also won an achievement award in recognition and appreciation of service contributions in the field of network security for the 2013 World Congress in Computer Science, Computer Engineering, and Applied Computing, and the Best Paper award at the 3rd International Conference on Advances in Computing, Communications and Informatics in 2014. Cathryn achieved Full College membership of EPSRC in August 2018.

Guanfeng Liu²

Dr. Guanfeng Liu is currently an Assistant Professor in the Computing Department at Macquarie University, Australia. He received his PhD degree in Computer Science from Macquarie University in 2013. His research focus is trust computing, social network, graph databases. Dr. Liu has published over 100 papers in the most prestigious journals and conferences such as ICDE, AAAI, IJCAI, CIKM, ICWS, ACM Transactions and IEEE Transactions. He has received five best (student) paper awards from WISE, IEEE SCC, and APWEB. He served as the General Co-Chair of EAI2019, the Program Committee Co-Chair of AWC2019, AWC2020, the Special Session Chair of DSAA2020. He has been the Guest Editors for three special issues about trust computing, graph database, and knowledge graph in WWWJ and JDM respectively, and served as the Editorial board of Frontiers in Big Data from 2018.

1: The Open University; Ulster University, UK
2: Macquarie University, Australia

Recently Published
Most Popular

A Taxonomy for Large-Scale Cyber Security Attacks
Appears in:
cs 22(21): e5

Authors:
Fadi Mohsen, Cornelis Zwart, Dimka Karastoyanova, Georgi Gaydadjiev

Published:
2nd Mar 2022

Abstract:
In an effort to examine the spread of large-scale cyber attacks, researchers have created various taxonomies. These taxonomies are purposefully built to facilitate the understanding and the comparison of these attacks, and hence counter their spread. Yet, existing taxonomies focus mainly on the tec…In an effort to examine the spread of large-scale cyber attacks, researchers have created various taxonomies. These taxonomies are purposefully built to facilitate the understanding and the comparison of these attacks, and hence counter their spread. Yet, existing taxonomies focus mainly on the technical aspects of the attacks, with little or no information about how to defend against them. As such, the aim of this work is to extend existing taxonomies by incorporating new features pertaining the defense strategy, scale, and others. We will compare the proposed taxonomy with existing state of the art taxonomies. We also present the analysis of 174
large cyber security attacks based on our taxonomy. Finally, we present a web tool that we developed to allow researchers to explore exiting data sets of attacks and contribute new ones. We are convinced that our work will allow researchers gain deeper insights into emerging attacks by facilitating their categorization, sharing and analysis, which results in boosting the defense efforts against cyber attack.
more »
Design of an Efficient Trustful-Lightweight Cloud Service Provisioning Model using Service Optimizer
Appears in:
cs 22(21): e4

Authors:
Suvarna S. Pawar, Y. Prasanth

Published:
19th Oct 2021

Abstract:
INTRODUCTION: The establishment of trusted cloud services pretends to provide high impactful service with better satisfaction to the web-users and cloud service providers. Moreover, various existing trust-aware algorithms use diverse QoS measurements and related attributes, leading …INTRODUCTION: The establishment of trusted cloud services pretends to provide high impactful service with better satisfaction to the web-users and cloud service providers. Moreover, various existing trust-aware algorithms use diverse QoS
measurements and related attributes, leading to the complex selection of cloud services.

OBJECTIVES: Thus, this research intends to propose a Trustful-Lightweight Cloud Service Provisioning algorithm (TL-CSP) using Service Optimizer (SO).

METHODS: Initially, the QoS metrics are determined by evaluating attributes based on a ranking method based on the users' requests. It is performed with the computation of weighted coefficients of received requests from the users. The service optimization is performed using a global optimizer to assist the cloud users in selecting the service with better satisfaction.

RESULTS: The proposed TL-CSP accuracy is validated and compared with the existing cloud service provisioning algorithm to measure the proposed model's efficiency.

CONCLUSION: The simulation is carried out in a MATLAB environment. The proposed TL-CSP intends to shows a better trade-off in contrast to prevailing approaches.
more »
AuthenIoT: A Lightweight Authentication Protocol for the Internet of Things Based Wireless Sensor Networks
Appears in:
cs 22(21): e3

Author:
Haythem Hayouni

Published:
14th Oct 2021

Abstract:
The Internet of Things is a major development in information technology that increasingly dominates and reigns in the computer systems market. However, due to the threat of cyber attacks, the security of IoT is still one of the major issues holding back the evolution of this technology. For…The Internet of Things is a major development in information technology that increasingly dominates and reigns in the computer
systems market. However, due to the threat of cyber attacks, the security of IoT is still one of the major issues holding back the
evolution of this technology. For this, the authentication of objects is very important in IoT. In this paper, we propose a
lightweight authentication protocol for the IoT Based Wireless Sensor Networks, called AuthenIoT. The objective is to provide
mutual authentication services for connected objects. This protocol must take into account the constraints of the objects and the
used communication technologies. To achieve such protocol, we opted for WSNs as an IoT use case. Furthermore, we
demonstrate that the proposed scheme provides an efficient security for connected devices and that its computation and
communication costs are suitable for extremely low-cost IoT devices.
more »
Modelling an Efficient Three-Tier Fault Tolerance Approach for Resource Provisioning over Cloud
Appears in:
cs 22(21): e2

Authors:
Suvarna S. Pawar, Y. Prasanth

Published:
14th Oct 2021

Abstract:
INTRODUCTION: Nowadays, the cloud computing paradigm encounters newer challenges in offering fault tolerance methods during service provisioning. The failures during service provisioning are unavoidable in the large-scale heterogeneous network. Therefore, the adoption of appropriate fau…INTRODUCTION: Nowadays, the cloud computing paradigm encounters newer challenges in offering fault tolerance methods during service provisioning. The failures during service provisioning are unavoidable in the large-scale heterogeneous network. Therefore, the adoption of appropriate fault tolerance techniques can improve the provided service's efficiency and reliability.

OBJECTIVES: Thus, fault tolerating metrics give better accuracy to enhance the QoS, where the three-tier fault-tolerance approach is proposed to resolve the various failures in service provisioning.

METHODS: Initially, a Collector Model collects the request and ranks it based on the service to be provided. Secondly, the redundancy filter module is designed to filter out the request replication and avoid the unnecessary process to be carried out. Finally, the fairness resource allocation module is designed to perform the prominent request received from the users based on the available resources without service congestion.

RESULTS: This three-tier model operates concurrently to handle the multiple requests from the users of various connected nodes. The experimental analysis demonstrates that the three-tier fault tolerance model can enhance the cloud reliability over
the large-scale heterogeneous network by ensuring QoS.

CONCLUSION: The well-realized fault tolerance approach can efficiently demonstrate the structural model and fault tolerance process over the computing environment, therefore enhancing the cloud extendibility. Moreover, the computing
environment's failure is hugely complex, and failure has to be handled efficiently.
more »
On the Adoption of Erasure Code for Cloud Storage by Major Distributed Storage Systems
Appears in:
cs 22(21): e1

Authors:
Aatish Chiniah, Avinash Mungur

Published:
14th Sep 2021

Abstract:
INTRODUCTION: Traditional Cloud Systems are struggling to cope with the exponential growth of data in todays’ distributed application environment. The amount of data online has continuously increased since 2003. From an estimated 5 Exabyte in 2003 to 988 Exabyte in 2010. Presently i…INTRODUCTION: Traditional Cloud Systems are struggling to cope with the exponential growth of data in todays’ distributed application environment. The amount of data online has continuously increased since 2003. From an estimated 5 Exabyte in 2003 to 988 Exabyte in 2010. Presently it is estimated that 5 Exabyte of data are produced daily. To cope with
such astronomical load of data, Distributed Storage Systems such as Amazon, Google and Microsoft Azure are becoming the de-facto method for the storage of data. Replication is the method used for providing redundancy. However Erasure Coding is a worthy alternative.

OBJECTIVES: The purpose of this paper is to assess the most used distributed storage systems using different evaluation criteria and identifying how erasure code can be integrated into them.

METHODS: This paper provides a survey of well-known Distributed Storage Systems by using the CAP (Consistency, Availability and Partition Tolerance) Theorem. We go by presenting the solution according to the objectives set and trade-off acknowledged by the designers.

RESULTS: A comprehensive survey is presented using five evaluation criteria (design principle, data model, failure detection and recovery, consistency and security). Adoption of erasure code in Distributed Storage Systems is discussed and
its advantages are deliberated. Several open challenges are also put forward.

CONCLUSION: This paper provides researchers in the field with a comprehensive review of Distributed Storage Systems and how the adoption of erasure codes will enhance their capabilities.
more »
Advanced Mechanism to Achieve QoS and Profit Maximization of Brokers in Cloud Computing
Appears in:
cs 21(20): e5

Authors:
Akanksha Sathish, Diana Dsouza, K. Ramitha Ballal, Archana M, Tarun Raj Singh, Glen Joshua Monteiro

Published:
23rd Jun 2021

Abstract:
Cloud computing is a widely used technology today and thus, large number of applications are being stored in the cloud. To cater to the needs of the consumers an intermediate role known as cloud broker has been introduced. It helps to cut down overall expenses of the cloud users. The proposed syste…Cloud computing is a widely used technology today and thus, large number of applications are being stored in the cloud. To cater to the needs of the consumers an intermediate role known as cloud broker has been introduced. It helps to cut down overall expenses of the cloud users. The proposed system concentrates on configuration of the cloud broker to improve profit. This maximization scheme depends upon various factors like customer request, selling price of the resource, purchasing price of the resource, intensity of the request and so on. The system developed, aims at maximizing the profit of the cloud broker who services consumer requirements by providing cloud infrastructure at a lower cost from an infrastructure vendor. Availing pay-as-you-go schemes or on-demand payment has proven to be useful. The complex cloud landscape along with various billing schemes paves a way for a profit maximization model that incorporates temporal multiplexing by a middleman entity for a better economic upfront. The resource multiplexing is further enhanced by incorporating M/D/c queueing model and short-term and long-term renting schemes to optimize the resource allocation. The entire application has been implemented using Java especially the NetBeans IDE 8.2. Different algorithms were compared to further enhance the pricing scheme selection. Finally, Hill-Climbing algorithm is used to allocate the resources dynamically. The system further notifies the cloud broker on resource shortage through dynamic disk utilization graph. The proposed system considers quality of service and price of service as the determining factors in maximizing the net profit of the cloud broker.
more »
Outsourced Auditing With Data Integrity Verification Scheme (OA-DIV) and Dynamic Operations for Cloud Data with Multi-Copies
Appears in:
cs 21(20): e4

Authors:
Arjun U, Vinay S

Published:
27th Apr 2021

Abstract:
Data storage in cloud is widely utilized by different commercial, educational, scientific, healthcare applications and much more. The major concern apart from data security is data integrity. Our work focuses on data integrity. In spite of the presence of Service Level Agreement (SLA) betwe…Data storage in cloud is widely utilized by different commercial, educational, scientific, healthcare applications and much more. The major concern apart from data security is data integrity. Our work focuses on data integrity. In spite of the presence of Service Level Agreement (SLA) between the data owner and CSP, the data integrity may be affected and also todays’ cloud computing platform processes more of real-time data, which involves dynamic data operations. Most of the existing works intend to verify the cloud data integrity however the issues related to data replicas are not usually considered and most of the existing cloud techniques fail to focus on dynamic data operations. This article presents an outsourced auditing with data integrity verification scheme (OA-DIV) scheme that can handle multiple copies of cloud data and supports dynamic data operations such as data insertion, deletion and updation. The performance of the proposed work is tested with respect to communication cost and processing time, while comparing the results with the existing approaches.
more »
Contemporary Development in E-Learning Education, Cloud Computing Technology & Internet of Things
Appears in:
cs 21(20): e3

Authors:
Ugochukwu O. Matthew, Jazuli S. Kazaure, Nwamaka U. Okafor

Published:
31st Mar 2021

Abstract:
The enterprise educational environment will involve big data technology, cloud computing, Internet of Things (IoT) and artificial intelligence (AI), which will characterize the current society extreme automation and enterprise productivity through reinventing the new world …The enterprise educational environment will involve big data technology, cloud computing, Internet of Things (IoT) and artificial intelligence (AI), which will characterize the current society extreme automation and enterprise productivity through reinventing the new world educational reform. This current paper captured the manageability issues in electronic learning environments and explored ways through which the managerial performances could be improved in the perspective of electronic learning investments through incorporation of context-awareness and self-reconfiguration adaptive systems. The aim is to allow the open source electronic learning system to provide educators, administrators, and learners with a single robust and integrated system for creating a personalized and autonomous learning accomplishments. The paper reviewed the contemporary development in electronic learning system in internet of things and cloud computing and established the prospect for the continued educational investment. A survey of four tertiary institution in the south eastern Nigeria provided a justification for the adoption of cloud computing technology as the best alternative approach for organizational data warehousing in the ongoing society automation. The result of the paper indicated that technology implementation in schools are fundamental to students’ academic accomplishment, which made it obviously imperative that teachers in the 21st century should adjust digitally and technologically and prepare students for the opportunities in the emerging digital new world. The paper concluded that the successful curriculum implementation in the twenty first century will require a blend of technology innovation and enterprise platform adaptability as potential leverages in achieving the global educational sustainability.
more »
Cloud-IoT Implementations & Its Impact on Organizational Performance - A Quantitative Study on IT & Business Leaders
Appears in:
cs 21(20): e2

Authors:
Jipson George Thoomkuzhy, Murugan Thangiah

Published:
15th Jan 2021

Abstract:
In recent years we have seen tremendous growth in two key technologies like Cloud and IoT h. Be that as it may, a few common points of interest getting from their integration have been recognized in the literature and are anticipated later on. From one perspective, IoT can profit by the bo…In recent years we have seen tremendous growth in two key technologies like Cloud and IoT h. Be that as it may, a few common points of interest getting from their integration have been recognized in the literature and are anticipated later on. From one perspective, IoT can profit by the boundless abilities and assets of the Cloud to repay its mechanical requirements (e.g., capacity, handling, vitality). In particular, the Cloud can offer a powerful answer for actualizing IoT service management and structure and additional applications that endeavor the things or the data created by them. Then again, the Cloud can profit by IoT by stretching out its extension to manage genuine things in a more disseminated and dynamic way, and for conveying new services in an expansive number of genuine situations. The integral attributes of Cloud and IoT emerging from the distinctive recommendations in literature and moving the Cloud IoT worldview are accounted for in this paper. The Cloud goes about as a middle layer between the things and the applications, where it conceals all the multifaceted nature and the functionalities important to actualize the last mentioned. This framework will affect future application advancement, where data social occasion, preparing, and transmission will create new difficulties to be tended to, likewise in a multi-cloud condition. In the accompanying, we condense the issues settled and the points of interest acquired while embracing the Cloud IoT worldview. Cutting edge technologies like Cloud & IoT has gained popularity in various businesses and there is great importance for organizations to understand the possible benefits which an organization can benefit by the adoption & implementation of new technologies like Cloud & IoT. This study focuses on a survey-based investigation of various businesses & IT leaders to identify the organizational performance post after the implementation of cloud & IoT. This study focuses on measuring key organizational performance metrics like profit, revenue, customer satisfaction, product delivery, product quality etc.
more »
Effect of Acceleration Coefficient on Particle Swarm optimization for Task Scheduling in Cloud Computing
Appears in:
cs 21(20): e1

Author:
Nagresh Kumar

Published:
15th Jan 2021

Abstract:
Cloud computing emerges as a powerful platform to deliver IT services online. Due to the rapid development of cloud computing the user's dependence on the cloud has increased and hence user request per unit time is increases. Now scheduling and serving the user…Cloud computing emerges as a powerful platform to deliver IT services online. Due to the rapid development of cloud computing the user's dependence on the cloud has increased and hence user request per unit time is increases. Now scheduling and serving the user requests is a major challenge. Particle swarm optimization as a heuristic algorithm is the most suitable algorithm in such scenario to serve user requests for the most appropriate resources. Author written this research paper in continuation with previous research paper called Modified particle swarm optimization (MPSO) in which author controlled the inertia weight in PSO to find the best cost. This research paper investigates the effect of acceleration coefficient to achieve the best cost. The implementation results of PSO with different acceleration coefficient are produced and compared. Author has use MATLab to test the effect of acceleration coefficient on fitness value and also implemented in CloudSim simulator to test variation in execution time in various scenario. The purpose of author is also to test correctness of Reyes-Sierra and Coello [19] suggested acceleration coefficient.
more »

A Counterfeit Solution for Pharma Supply Chain
Appears in:
cs 18(11): e5

Authors:
Soundarya K., Priyanka Pandey, R. Dhanalakshmi

Downloads:
3358

Abstract:
This paper provides a detailed overview of the blockchain technology and how it can be used to build a foolproof system in eliminating counterfeit products in pharmaceutical industries. Study by various reports indicate that counterfeit products entering the mainstream supply is by far one of the m…This paper provides a detailed overview of the blockchain technology and how it can be used to build a foolproof system in eliminating counterfeit products in pharmaceutical industries. Study by various reports indicate that counterfeit products entering the mainstream supply is by far one of the major issue faced by the pharmaceutical industries. By using blockchain across the whole value chain, various pitfalls and challenges faced by the stakeholders can be resolved as blockchain, by design is (i) robust, (ii) improves transparency, (iii) immutable, (iv) authentic, (v) reliable and (vi) secure. Overall, this paper attempts to provide a roadmap on how blockchain transactions can help various stakeholders improve the counterfeit situation, challenges one might face in implementing a blockchain solution and steps for further research.
more »
Dimensionality Reduction for Handwritten Digit Recognition
Appears in:
cs 18(13): e5

Authors:
Ankita Das, Tuhin Kundu, Chandran Saravanan

Downloads:
3268

Abstract:
Human perception of dimensions is usually limited to two or three degrees. Any further increase in the number of dimensions usually leads to the diﬃculty in visual imagination for any person. Hence, machine learning researchers often commonly have to overcome the curse of dimensionality in high dim…Human perception of dimensions is usually limited to two or three degrees. Any further increase in the number of dimensions usually leads to the diﬃculty in visual imagination for any person. Hence, machine learning researchers often commonly have to overcome the curse of dimensionality in high dimensional feature sets with dimensionality reduction techniques. In this proposed model, two handwritten digit datasets are used: CVL Single Digit and MNIST, and two popular feature descriptors, Histogram of Oriented Gradients (HOG) and Gabor ﬁlters, are used to generate the feature sets. Investigations are carried out on linear and nonlinear transformations of the feature sets using multiple dimensionality reduction techniques such as Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and Isomap. The lower dimension vectors obtained, are then used to classify the numeric digits using Support Vector Machine (SVM). A conclusion arrived is that using HOG as the feature descriptor and PCA as the dimensionality reduction technique resulted in the experimental model achieving the highest accuracy of 99.29% on the MNIST dataset with the time eﬃciency comparable to that of a convolutional neural network (CNN). Further, it is concluded that even though the LDA model with HOG as the feature descriptor achieved a lesser accuracy of 98.34%, but it was able to capture maximum information in just 9 components in its lower dimensional subspace with 75% reduction in time eﬃciency of that of the PCA-HOG model and the CNN model.
more »
Predictive Analytics In Weather Forecasting Using Machine Learning Algorithms
Appears in:
cs 19(14): e4

Authors:
Aastha Sharma, Vijayakumar V

Downloads:
3192

Abstract:
Agriculture is the backbone of every economy. In a country like India, which has ever increasing demand of food due to rising population, advances in agriculture sector are required to meet the needs. To add to it, the present economic conditions and government policies of India are such that it ne…Agriculture is the backbone of every economy. In a country like India, which has ever increasing demand of food due to rising population, advances in agriculture sector are required to meet the needs. To add to it, the present economic conditions and government policies of India are such that it necessitates the adoption of Precision farming or smart farming. It will enable the farmers to maximize their crop yields and minimize the input costs as well as the losses due to reasons like uncertain rainfall, droughts etc. from this model. For Predicting weather forecasting we will use machine
learning Algorithms like Linear Regression, Decision tree.
more »
Task scheduling in cloud computing based on metaheuristic techniques: A review paper
Appears in:
cs 20(17): e4

Authors:
Rasha A. Al-Arasi, Anwar Saif

Downloads:
2864

Abstract:
Cloud computing delivers computing resources like software and hardware as a service to the users through a network. Due to the scale of the modern datacentres and their dynamic resources provisioning nature, we need efficient scheduling techniques to manage these resources. The main objective of…Cloud computing delivers computing resources like software and hardware as a service to the users through a network.
Due to the scale of the modern datacentres and their dynamic resources provisioning nature, we need efficient scheduling
techniques to manage these resources. The main objective of scheduling is to assign tasks to adequate resources in order to
achieve one or more optimization criteria. Scheduling is a challenging issue in the cloud environment, therefore many
researchers have attempted to explore an optimal solution for task scheduling in the cloud environment. They have shown
that traditional scheduling is not efficient in solving this problem and produce an optimal solution with polynomial time in
the cloud environment. However, they introduced sub-optimal solutions within a short period of time. Meta-heuristic
techniques have provided near-optimal or optimal solutions within an acceptable time for such problems. In this work, we
have introduced the major concepts of resource scheduling and provided a comparative analysis of many task scheduling
techniques based on different optimization criteria.
more »
Design Approach for CCSDS Complied Command Operation and Frame Operation Procedure for Integrated Spacecraft Checkout
Appears in:
cs 18(13): e2

Authors:
Parul Sharma, Sangeetha K., Vithal Metri

Downloads:
2816

Abstract:
Consultative Committee for Space Data Systems (CCSDS) complied Telemetry and Telecommand Processor’s (TTCP) development was taken up by Spacecraft Checkout Group (SCG) of U. R. Rao Satellite Centre, Indian Space Research Organization (ISRO) as a part of ‘Make in India’ campaign. As SCG is responsib…Consultative Committee for Space Data Systems (CCSDS) complied Telemetry and Telecommand Processor’s (TTCP) development was taken up by Spacecraft Checkout Group (SCG) of U. R. Rao Satellite Centre, Indian Space Research Organization (ISRO) as a part of ‘Make in India’ campaign. As SCG is responsible for conducting exhaustive tests at integrated spacecraft level to evaluate and qualify the flight worthiness of subsystems onboard the spacecraft. This inhouse Technology Demonstration/ Development of Consultative Committee for Space Data Systems (CCSDS) complied TTCP for spacecraft checkout applications in a cost effective and easy maintainable way, was taken up as a challenge. The in-house developed Processor was successfully deployed for the first time in checkout for Indian communication satellite and subsequently to Indian Remote Sensing (IRS) satellite. In future, TTCP will be used in Integrated Spacecraft Testing of ISROs Low Earth Orbit, Geostationary Orbit and Interplanetary Spacecraft missions. The telecommand system plays a vital role in the success of any satellite mission. For effective control of various satellite subsystems, under all conditions, a highly efficient and responsive telecommand system is absolutely essential. This paper will brief about the design approach taken for implementation of CCSDS complied telecommand management and processing {Command Operation and Frame Operation Procedure (COP/FOP)} for TTCP developed by SCG.
more »
Intelligent Character Recognition System Using Convolutional Neural Network
Appears in:
cs 20(19): e5

Authors:
S. Suriya, Dhivya S, Balaji M

Downloads:
2503

Abstract:
Computational Linguistics involves the techniques of Computer Science which play a vital role in recognizing written or printed characters such as numbers or letters to change them into a form that the computer can use it efficiently. Convolutional Neural Network differs fro…Computational Linguistics involves the techniques of Computer Science which play a vital role in recognizing written or printed characters such as numbers or letters to change them into a form that the computer can use it efficiently. Convolutional Neural Network differs from other approaches by extracting the features automatically. The proposed approach is capable of recognizing characters in a variety of challenging conditions using the Convolutional Neural Network, where traditional character recognition systems fail, notably in the presence of low resolution, substantial blur, low contrast, and other distortions. Intellectual Character Recognition System is an application that uses Convolutional Neural Network (CNN) to recognize the Tamil character dataset accurately developed by HP Labs India. The novelty of this system is that, it recognizes the characters of the Predominant Tamil language. With the help of suitable datasets consisting of the Tamil Scripts, the model is trained efficiently. This work has produced a training accuracy of 99.16% which is far better compared to the traditional approaches.
more »
Deep Learning based MURA Defect Detection
Appears in:
cs 19(15): e6

Authors:
Ramya Bagavath Singh, Gaurav Kumar, Gaurav Sultania, Shashank Shrikant Agashe, Priya Ranjan Sinha, Chulmoo Kang

Downloads:
2501

Abstract:
INTRODUCTION: MURA defects in LED/LCD panels are one of the most challenging defects for Automatic Defect Classification and Localization (ADC) due to their extremely low contrast when compared with the background. Manual detection is subjective, error prone, very tedious and time consuming. Even w…INTRODUCTION: MURA defects in LED/LCD panels are one of the most challenging defects for Automatic Defect Classification and Localization (ADC) due to their extremely low contrast when compared with the background. Manual detection is subjective, error prone, very tedious and time consuming. Even when the type of MURA defects can be ascertained manually, the exact bounding box for defect is hard to determine. Various heuristic based image processing
techniques have been applied giving sub-optimal accuracy over generic datasets.

OBJECTIVES: The primary objective of this paper is to check whether the state of the art DL (Deep Learning) network for general object classification and localization (MSCOCO PASCAL VOC etc.) can be applied successfully for MURA Defect Classification and Localization.

METHODS: In this paper we present a single DL pipeline for classification and localization which for the first time is applied for MURA defects. Naive DL network - Single Shot multi-box Detector (SSD, pre-trained on ImageNet) was not sufficient to give a good F1 score because of the nature of the defect. Accuracy improved a little after applying various DL
specific optimization methods such as loss function optimization, network optimization etc. Utilizing the knowledge from MURA domain for data augmentation, like filtering based on image capture wavelength etc. improved the results significantly.

RESULTS: Using optimization techniques that are from both DL domain as well as specific to MURA domain, we show improvement in the accuracy of the base DL pipeline from ~30% to ~80%. Minimum heuristics were used to define the pipeline so that it can easily adapt to any new MURA dataset. The paper shows the importance of domain specific preprocessing steps for the designed network in case of MURA defects.

CONCLUSION: Using DL, MURA classification and localization had not been tried before. For the first time we demonstrated results for both classification and localization of MURA defects using state-of-the-art DL network with F1~80%. We also conclude that state-of-the-art network for general object detection can be reused with the help of Transfer Learning (TL) concept and fine-tuned with MURA domain specific optimizations mentioned in paper for optimal
performances in MURA domain.
more »
Video Steganography using MATLAB
Appears in:
cs 17(10): e3

Authors:
G. Paramesh, K. V. Pavithra, N. Ranjitha, S. Swetha, T. Anushalalitha

Downloads:
2396

Abstract:
This paper discusses a Video Steganographic scheme that can provide approvable security with high computing speed, by embedding data in video frames. The technique of embedding data in a video file by using LSB before which the secret information is encrypted using symmetric XOR operation, thereby …This paper discusses a Video Steganographic scheme that can provide approvable security with high computing speed, by embedding data in video frames. The technique of embedding data in a video file by using LSB before which the secret information is encrypted using symmetric XOR operation, thereby providing two layers of security. Data Hiding and
Extraction procedure are experimented successfully. All experiments are done using Matlab 2010a simulation software. This method proves to be more efficient than other methods with the amount of data that can be embedded in it, showing a PSNR of above 30 dB.
more »
Hyperparameter optimisation for Capsule Networks
Appears in:
cs 19(14): e2

Authors:
Gagana B, S Natarajan

Downloads:
2166

Abstract:
Convolutional Neural Networks and its contemporary variants have proven to be ruling benchmarks for most image processing tasks but resort to pooling techniques and routing mechanisms that aﬀect classiﬁcation accuracy and lose spatial relationship information between involved data points. Hence, Hi…Convolutional Neural Networks and its contemporary variants have proven to be ruling benchmarks for most image processing tasks but resort to pooling techniques and routing mechanisms that aﬀect classiﬁcation accuracy and lose spatial relationship information between involved data points. Hence, Hinton et al, proposed a layered architecture called Capsule Networks (Capsnets) which outperform traditional systems by replacing pooling techniques with dynamic routing abilities. Capsnets are, thus, en-route to proving themselves as prospective future benchmarks in visual imagery tasks by surpassing existing state-of-theart results on the MNIST dataset. The two novel aspects inspected in this paper are: the enhancement of this performance on CIFAR-10 through regularization and hyperparameter optimization which, henceforth, augment applicability to stochastic numeric healthcare data helping uncover newer challenges of predictive neural networks.
more »
Novel Method for Increased Power Conservation in Voice over NR (VoNR) devices
Appears in:
cs 19(15): e7

Authors:
Kashmira Kapoor, Dandra Prasad Basavaraj, Shrinath Ramamoorthy, Tushar Vrind

Downloads:
1953

Abstract:
With the introduction of 5G New Radio (NR), telecom operators are planning to integrate network elements of NR in different configurations for a phased and overlaid deployment and coexistence with 4G. Third Generation Partnership Project (3GPP) standardizes the deployment operation mode of the next…With the introduction of 5G New Radio (NR), telecom operators are planning to integrate network elements of NR in different configurations for a phased and overlaid deployment and coexistence with 4G. Third Generation Partnership Project (3GPP) standardizes the deployment operation mode of the next-generation network, viz. working in Stand Alone (SA) NR scenarios and Non-Stand Alone (NSA) NR mode scenarios. As defined in the specification, Option 7 is where UE
connects to 5G Core Network (5GCN) via either 4G enhanced Node B (eNB) cell or 5G next-generation NodeB (gNB) cell. The power consumption for a User Equipment (UE) is dependent on the physical resource allocation strategy in the serving cell. Available procedures of system selection defined in 3GPP are based on measurement of reference signal
power levels and priority criteria as defined in the System Information of the 5G/4G network. In this paper, we have discussed novel protocol and algorithm through which the UE maintains a history of availability of features like Semi-Persistent Scheduling (SPS), Connected Mode Discontinuous Reception (CDRX) and Voice over NR (VoNR) in the serving area of a cell and uses this information later during system reselection evaluation due to mobility. Through our proposed changes, a UE a) gets VoNR service more often and b) conserve more energy when the user activates VoNR
service. We present an analytical model and through simulation show that during VoNR service, power is conserved due to SPS and CDRX on the selected cell.
more »

Publisher: EAI
ISSN: 2410-6895
Number of Volumes: 7

Last Published: 2022-03-02

EAI Endorsed Transactions on Cloud Systems

Cathryn Peoples1

Guanfeng Liu2

Cathryn Peoples¹

Guanfeng Liu²