November 2018 Issue Vol.8 No.11 IJITCE.CO.UK

Page 1

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018

www.ijitce.co.uk


INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018

UK: Managing Editor International Journal of Innovative Technology and Creative Engineering 1a park lane, Cranford London TW59WA UK

USA: Editor International Journal of Innovative Technology and Creative Engineering Dr. Arumugam Department of Chemistry University of Georgia GA-30602, USA.

India: Editor International Journal of Innovative Technology & Creative Engineering 36/4 12th Avenue, 1st cross St, Vaigai Coliny Ashok Nagar Chennai , India 600083 Email: editor@ijitce.co.uk

www.ijitce.co.uk

www.ijitce.co.uk


INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018

IJITCE PUBLICATION

International Journal of Innovative Technology & Creative Engineering Vol.8 No.11 November 2018

www.ijitce.co.uk

www.ijitce.co.uk


INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018

From Editor's Desk Dear Researcher, Greetings! The month of October witnessed one of the leading conferences of the year in Vizag, India. It was the Vizag Fintech Festival 2018. This event is being feature as a cover story in this issue. Our team also participated in another conference on “Green Power Energy 2018”,in Chennai, India where students from SSN College of Engineering submitted a paper on “Design and implementation of Inductive power transfer for EV Battery charging”. IJITCE was a journal partner in both the above conferences. IJITCE was also invited as a partner for the Watts Humphrey Awards, a prestigious recognition from SPIN Chennai

initiated to honor the software engineering Guru Dr. Watts Humphrey. Teams from various organizations across industries will be invited to nominate their practice / case study. Jury will evaluate the submissions (offline) and shortlisted teams will be invited to present their story and showcase their practices on the day of the awards in front of the Grand Jury. IJITCE team is also invited to be part of the Jury for presentation during the upcoming conference” FICCI’s Digital Disruption and Transformation Summit 2018 (DT3) on 12th December 2018”. IJITCE will also be the Journal partner. International Computer Security will be observed on 30 Nov 2018 . Cyber Society of India will be organizing a one day event in Chennai India to create awareness among the Public. The event will be conducted in association with the Tamil Nadu State Police. IJITCE will be a journal partner. A Research article in this issue discusses about mobile edge computing, Markov Chain model.

Thanks, Editorial Team IJITCE

www.ijitce.co.uk


INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018

Editorial Members Dr. Chee Kyun Ng Ph.D Department of Computer and Communication Systems, Faculty of Engineering,Universiti Putra Malaysia,UPMSerdang, 43400 Selangor,Malaysia. Dr. Simon SEE Ph.D Chief Technologist and Technical Director at Oracle Corporation, Associate Professor (Adjunct) at Nanyang Technological University Professor (Adjunct) at ShangaiJiaotong University, 27 West Coast Rise #08-12,Singapore 127470 Dr. sc.agr. Horst Juergen SCHWARTZ Ph.D, Humboldt-University of Berlin,Faculty of Agriculture and Horticulture,Asternplatz 2a, D-12203 Berlin,Germany Dr. Marco L. BianchiniPh.D Italian National Research Council; IBAF-CNR,Via Salaria km 29.300, 00015 MonterotondoScalo (RM),Italy Dr. NijadKabbaraPh.D Marine Research Centre / Remote Sensing Centre/ National Council for Scientific Research, P. O. Box: 189 Jounieh,Lebanon Dr. Aaron Solomon Ph.D Department of Computer Science, National Chi Nan University,No. 303, University Road,Puli Town, Nantou County 54561,Taiwan Dr. Arthanariee. A. M M.Sc.,M.Phil.,M.S.,Ph.D Director - Bharathidasan School of Computer Applications, Ellispettai, Erode, Tamil Nadu,India Dr. Takaharu KAMEOKA, Ph.D Professor, Laboratory of Food, Environmental & Cultural Informatics Division of Sustainable Resource Sciences, Graduate School of Bioresources,Mie University, 1577 Kurimamachiya-cho, Tsu, Mie, 514-8507, Japan Dr. M. Sivakumar M.C.A.,ITIL.,PRINCE2.,ISTQB.,OCP.,ICP. Ph.D. Project Manager - Software,Applied Materials,1a park lane,cranford,UK Dr. Bulent AcmaPh.D Anadolu University, Department of Economics,Unit of Southeastern Anatolia Project(GAP),26470 Eskisehir,TURKEY Dr. SelvanathanArumugamPh.D Research Scientist, Department of Chemistry, University of Georgia, GA-30602,USA. Dr. S.Prasath Ph.D Assistant Professor, Department of Computer Science, Nandha Arts & Science College, Erode , Tamil Nadu, India

Review Board Members Dr. Paul Koltun Senior Research ScientistLCA and Industrial Ecology Group,Metallic& Ceramic Materials,CSIRO Process Science & Engineering Private Bag 33, Clayton South MDC 3169,Gate 5 Normanby Rd., Clayton Vic. 3168, Australia Dr. Zhiming Yang MD., Ph. D. Department of Radiation Oncology and Molecular Radiation Science,1550 Orleans Street Rm 441, Baltimore MD, 21231,USA Dr. Jifeng Wang Department of Mechanical Science and Engineering, University of Illinois at Urbana-Champaign Urbana, Illinois, 61801, USA Dr. Giuseppe Baldacchini ENEA - Frascati Research Center, Via Enrico Fermi 45 - P.O. Box 65,00044 Frascati, Roma, ITALY. Dr. MutamedTurkiNayefKhatib Assistant Professor of Telecommunication Engineering,Head of Telecommunication Engineering Department,Palestine Technical University (Kadoorie), TulKarm, PALESTINE.

www.ijitce.co.uk


INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018 Dr.P.UmaMaheswari Prof &Head,Depaartment of CSE/IT, INFO Institute of Engineering,Coimbatore. Dr. T. Christopher, Ph.D., Assistant Professor &Head,Department of Computer Science,Government Arts College(Autonomous),Udumalpet, India. Dr. T. DEVI Ph.D. Engg. (Warwick, UK), Head,Department of Computer Applications,Bharathiar University,Coimbatore-641 046, India. Dr. Renato J. orsato Professor at FGV-EAESP,Getulio Vargas Foundation,São Paulo Business School,RuaItapeva, 474 (8° andar),01332-000, São Paulo (SP), Brazil Visiting Scholar at INSEAD,INSEAD Social Innovation Centre,Boulevard de Constance,77305 Fontainebleau - France Y. BenalYurtlu Assist. Prof. OndokuzMayis University Dr.Sumeer Gul Assistant Professor,Department of Library and Information Science,University of Kashmir,India Dr. ChutimaBoonthum-Denecke, Ph.D Department of Computer Science,Science& Technology Bldg., Rm 120,Hampton University,Hampton, VA 23688 Dr. Renato J. Orsato Professor at FGV-EAESP,Getulio Vargas Foundation,São Paulo Business SchoolRuaItapeva, 474 (8° andar),01332-000, São Paulo (SP), Brazil Dr. Lucy M. Brown, Ph.D. Texas State University,601 University Drive,School of Journalism and Mass Communication,OM330B,San Marcos, TX 78666 JavadRobati Crop Production Departement,University of Maragheh,Golshahr,Maragheh,Iran VineshSukumar (PhD, MBA) Product Engineering Segment Manager, Imaging Products, Aptina Imaging Inc. Dr. Binod Kumar PhD(CS), M.Phil.(CS), MIAENG,MIEEE HOD & Associate Professor, IT Dept, Medi-Caps Inst. of Science & Tech.(MIST),Indore, India Dr. S. B. Warkad Associate Professor, Department of Electrical Engineering, Priyadarshini College of Engineering, Nagpur, India Dr. doc. Ing. RostislavChoteborský, Ph.D. Katedramateriálu a strojírenskétechnologieTechnickáfakulta,Ceskázemedelskáuniverzita v Praze,Kamýcká 129, Praha 6, 165 21 Dr. Paul Koltun Senior Research ScientistLCA and Industrial Ecology Group,Metallic& Ceramic Materials,CSIRO Process Science & Engineering Private Bag 33, Clayton South MDC 3169,Gate 5 Normanby Rd., Clayton Vic. 3168 DR.ChutimaBoonthum-Denecke, Ph.D Department of Computer Science,Science& Technology Bldg.,HamptonUniversity,Hampton, VA 23688 Mr. Abhishek Taneja B.sc(Electronics),M.B.E,M.C.A.,M.Phil., Assistant Professor in the Department of Computer Science & Applications, at Dronacharya Institute of Management and Technology, Kurukshetra. (India). Dr. Ing. RostislavChotěborský,ph.d, Katedramateriálu a strojírenskétechnologie, Technickáfakulta,Českázemědělskáuniverzita v Praze,Kamýcká 129, Praha 6, 165 21

Dr. AmalaVijayaSelvi Rajan, B.sc,Ph.d, Faculty – Information Technology Dubai Women’s College – Higher Colleges of Technology,P.O. Box – 16062, Dubai, UAE

www.ijitce.co.uk


INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018 Naik Nitin AshokraoB.sc,M.Sc Lecturer in YeshwantMahavidyalayaNanded University Dr.A.Kathirvell, B.E, M.E, Ph.D,MISTE, MIACSIT, MENGG Professor - Department of Computer Science and Engineering,Tagore Engineering College, Chennai Dr. H. S. Fadewar B.sc,M.sc,M.Phil.,ph.d,PGDBM,B.Ed. Associate Professor - Sinhgad Institute of Management & Computer Application, Mumbai-BangloreWesternly Express Way Narhe, Pune - 41 Dr. David Batten Leader, Algal Pre-Feasibility Study,Transport Technologies and Sustainable Fuels,CSIRO Energy Transformed Flagship Private Bag 1,Aspendale, Vic. 3195,AUSTRALIA Dr R C Panda (MTech& PhD(IITM);Ex-Faculty (Curtin Univ Tech, Perth, Australia))Scientist CLRI (CSIR), Adyar, Chennai - 600 020,India Miss Jing He PH.D. Candidate of Georgia State University,1450 Willow Lake Dr. NE,Atlanta, GA, 30329 Jeremiah Neubert Assistant Professor,MechanicalEngineering,University of North Dakota Hui Shen Mechanical Engineering Dept,Ohio Northern Univ. Dr. Xiangfa Wu, Ph.D. Assistant Professor / Mechanical Engineering,NORTH DAKOTA STATE UNIVERSITY SeraphinChallyAbou Professor,Mechanical& Industrial Engineering Depart,MEHS Program, 235 Voss-Kovach Hall,1305 OrdeanCourt,Duluth, Minnesota 55812-3042 Dr. Qiang Cheng, Ph.D. Assistant Professor,Computer Science Department Southern Illinois University CarbondaleFaner Hall, Room 2140-Mail Code 45111000 Faner Drive, Carbondale, IL 62901 Dr. Carlos Barrios, PhD Assistant Professor of Architecture,School of Architecture and Planning,The Catholic University of America Y. BenalYurtlu Assist. Prof. OndokuzMayis University Dr. Lucy M. Brown, Ph.D. Texas State University,601 University Drive,School of Journalism and Mass Communication,OM330B,San Marcos, TX 78666 Dr. Paul Koltun Senior Research ScientistLCA and Industrial Ecology Group,Metallic& Ceramic Materials CSIRO Process Science & Engineering Dr.Sumeer Gul Assistant Professor,Department of Library and Information Science,University of Kashmir,India Dr. ChutimaBoonthum-Denecke, Ph.D Department of Computer Science,Science& Technology Bldg., Rm 120,Hampton University,Hampton, VA 23688

Dr. Renato J. Orsato Professor at FGV-EAESP,Getulio Vargas Foundation,São Paulo Business School,RuaItapeva, 474 (8° andar)01332-000, São Paulo (SP), Brazil Dr. Wael M. G. Ibrahim Department Head-Electronics Engineering Technology Dept.School of Engineering Technology ECPI College of Technology 5501 Greenwich Road - Suite 100,Virginia Beach, VA 23462

www.ijitce.co.uk


INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018 Dr. Messaoud Jake Bahoura Associate Professor-Engineering Department and Center for Materials Research Norfolk State University,700 Park avenue,Norfolk, VA 23504 Dr. V. P. Eswaramurthy M.C.A., M.Phil., Ph.D., Assistant Professor of Computer Science, Government Arts College(Autonomous), Salem-636 007, India. Dr. P. Kamakkannan,M.C.A., Ph.D ., Assistant Professor of Computer Science, Government Arts College(Autonomous), Salem-636 007, India. Dr. V. Karthikeyani Ph.D., Assistant Professor of Computer Science, Government Arts College(Autonomous), Salem-636 008, India. Dr. K. Thangadurai Ph.D., Assistant Professor, Department of Computer Science, Government Arts College ( Autonomous ), Karur - 639 005,India. Dr. N. Maheswari Ph.D., Assistant Professor, Department of MCA, Faculty of Engineering and Technology, SRM University, Kattangulathur, Kanchipiram Dt - 603 203, India. Mr. Md. Musfique Anwar B.Sc(Engg.) Lecturer, Computer Science & Engineering Department, Jahangirnagar University, Savar, Dhaka, Bangladesh. Mrs. Smitha Ramachandran M.Sc(CS)., SAP Analyst, Akzonobel, Slough, United Kingdom. Dr. V. Vallimayil Ph.D., Director, Department of MCA, Vivekanandha Business School For Women, Elayampalayam, Tiruchengode - 637 205, India. Mr. M. Moorthi M.C.A., M.Phil., Assistant Professor, Department of computer Applications, Kongu Arts and Science College, India PremaSelvarajBsc,M.C.A,M.Phil Assistant Professor,Department of Computer Science,KSR College of Arts and Science, Tiruchengode Mr. G. Rajendran M.C.A., M.Phil., N.E.T., PGDBM., PGDBF., Assistant Professor, Department of Computer Science, Government Arts College, Salem, India. Dr. Pradeep H Pendse B.E.,M.M.S.,Ph.d Dean - IT,Welingkar Institute of Management Development and Research, Mumbai, India Muhammad Javed Centre for Next Generation Localisation, School of Computing, Dublin City University, Dublin 9, Ireland Dr. G. GOBI Assistant Professor-Department of Physics,Government Arts College,Salem - 636 007 Dr.S.Senthilkumar Post Doctoral Research Fellow, (Mathematics and Computer Science & Applications),UniversitiSainsMalaysia,School of Mathematical Sciences, Pulau Pinang-11800,[PENANG],MALAYSIA. Manoj Sharma Associate Professor Deptt. of ECE, PrannathParnami Institute of Management & Technology, Hissar, Haryana, India RAMKUMAR JAGANATHAN Asst-Professor,Dept of Computer Science, V.L.B Janakiammal college of Arts & Science, Coimbatore,Tamilnadu, India Dr. S. B. Warkad Assoc. Professor, Priyadarshini College of Engineering, Nagpur, Maharashtra State, India Dr. Saurabh Pal Associate Professor, UNS Institute of Engg. & Tech., VBS Purvanchal University, Jaunpur, India Manimala Assistant Professor, Department of Applied Electronics and Instrumentation, St Joseph’s College of Engineering & Technology, Choondacherry Post, Kottayam Dt. Kerala -686579 Dr. Qazi S. M. Zia-ul-Haque Control Engineer Synchrotron-light for Experimental Sciences and Applications in the Middle East (SESAME),P. O. Box 7, Allan 19252, Jordan

www.ijitce.co.uk


INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018

Dr. A. Subramani, M.C.A.,M.Phil.,Ph.D. Professor,Department of Computer Applications, K.S.R. College of Engineering, Tiruchengode - 637215 Dr. SeraphinChallyAbou Professor, Mechanical & Industrial Engineering Depart. MEHS Program, 235 Voss-Kovach Hall, 1305 Ordean Court Duluth, Minnesota 558123042 Dr. K. Kousalya Professor, Department of CSE,Kongu Engineering College,Perundurai-638 052 Dr. (Mrs.) R. Uma Rani Asso.Prof., Department of Computer Science, Sri Sarada College For Women, Salem-16, Tamil Nadu, India. MOHAMMAD YAZDANI-ASRAMI Electrical and Computer Engineering Department, Babol"Noshirvani" University of Technology, Iran. Dr. Kulasekharan, N, Ph.D Technical Lead - CFD,GE Appliances and Lighting, GE India,John F Welch Technology Center,Plot # 122, EPIP, Phase 2,Whitefield Road,Bangalore – 560066, India. Dr. Manjeet Bansal Dean (Post Graduate),Department of Civil Engineering,Punjab Technical University,GianiZail Singh Campus,Bathinda -151001 (Punjab),INDIA Dr. Oliver Jukić Vice Dean for education,Virovitica College,MatijeGupca 78,33000 Virovitica, Croatia Dr. Lori A. Wolff, Ph.D., J.D. Professor of Leadership and Counselor Education,The University of Mississippi,Department of Leadership and Counselor Education, 139 Guyton University, MS 38677

www.ijitce.co.uk


INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018

Contents Green Power Energy 2018 ……. Cover Story Vizag Fintech Festival 2018….. Survey on mobile edge computing Techniques Mohanasathiya K.S, Dr.S.Prasath

…………………. [550]

Recognizing Face with Consecutive Occlusion Using Markov Chain G.Rajeswari , Dr. P. Ithaya Rani …………………. [555]

www.ijitce.co.uk


INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018

GREEN POWER ENERGY 2018 – A ONE DAY CONCLAVE CONCLUDED WITH A SATISFYING NOTE ON THE RENEWABLE ENERGY SYSTEM eCargoLog, hosted the conclave, in Chennai, on 11th October @Le Royal Meridien, inviting leaders from the Energy sector, to share their research initiatives at this conference, brought excellent themes and topics to the lime light, in the field of Renewable Energy viz., Solar, Wind & e-Vehicles.

attack gateways, common security vulnerabilities etc., He concluded his remarks by saying, AV is the real future ; Fantastic applications in a social context; Huge benefits in all dimensions of triple bottom line namely Economic, Environmental and Social; India is not far behind in focus & experiments’. The other speakers of the sessions were: Mr. Srikaanth from Hailo Wind Systems, who briefed on the outlook For Wind & Solar Energy; Mr. M G. Ramachandran, Executive Director from the Top auditing Firm on the Post GST impacts and the benefits to the industries – with particular reference to the renewable energy, Mr. Rajanish Saxena, Vice President, ReGen Powertech, who spoke on the subject – Factors influencing EV adaptability and Indian scenario & road ahead and Mr. S Chitbabu, Consultant – Wind & Solar & hybrid on Key Trends in Solar and Mr. K P Chandrasekar, President of STC Logistics.

Inaugurating the session Mr. M S Sundara Rajan, former CMD of Indian Bank said that the newness is to be brought into the industry through proper forum so as to create more awareness in the system with respect to alternative energy and the importance of global warming. He further added detailing with more analytical data – to enhance productivity and business gain. Mr. R. Ramamurthi, Chairman, Cyber Security was also of the view that the younger generation should be inculcated to understand the system and apply their mind to achieve the same. While welcoming the gathering Dr. Rishi Muni Dwivedi, Associate Director of Indian Wind & Turbine Mfrs. Association (IWTMA), narrated the fact – comparing the world energy outlook 2017 with the current scenario. Electricity accounts for nearly half of total energy supply investment in the New Policies Scenario and almost two-thirds in the Sustainable Development Scenario, up from an average of 40% in recent years. Quoting from Estimates of Institute for Energy Economics & Financial Analysis (IEEFA), he further said that India’s offshore wind power generation capacity is seen climbing to 30 Gw by 2030, on par with China and accounting for 30 per cent of the envisaged capacity of 100 Gw in Asian economies. Prof. Dr.K. Narashiman, Director, AU TVS Center, Anna University during his presentation on the subject, ‘Progress In the Indian Market For E-Vehicles’, touched upon various factors with facts and figures – with reference to prevailing market conditions. Mr. Rajaram, CEO of VelTechTBI while speaking on Autonomous Vehicles described how it would be capable of fulfilling the human transportation capabilities of a traditional car, capable of sensing its environment and navigating without human output. Cyber security threats and concerns, potential

Mr. V N Prem Anand, Secretary, Cyber Society of India not only briefed on the Connected eV & Artificial-Intelligence Threat but also called for papers from the students to publish their thesis in the International Journal (IJITCE), when SSN College doctorate students submitted their abstracts. The session concluded with the presentation and talk by Mr. S Krishnan, Sr. Vice President of Ashok Leyland with his impeccable description on the e-Vehicle system.


INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018

Cover Story Vizag Fintech Festival 2018… The Fintech Valley in Vizag is a self-sustainable global Fintech Ecosystem promoted by Government of Andhra Pradesh. It focuses on converging finance and technology to create large avenues of growth through industryenablers, world-class infrastructure, entrepreneurship and innovation. A New Story on the Growth Path. The inaugural edition of VizagFintech Festival 2018, an initiative by Government of Andhra Pradesh and organized by Fintech Valley Vizag was held from 22nd – 26th October 2018 at Hotel Novotel, Vizag.

The event was a one-of-its-kind in the fintech domain, as the most comprehensive and reputed global platform where India’s key industry players of the Financial and Start-up ecosystem came together to discuss industry trends, challenges and market insights including the Indian regulatory framework. The event also showcased product launches, innovations, and augmented the forethought through the exhibition and a conference platform. The VizagFintech Festival was a 5-day event which saw more than 75 startups as exhibitors and over 2,500 delegates and visitors from around 20 countries.

Hon’ble Chief Minister Mr N. Chandra Babu Naidu, Andhra Pradesh ingurated the event and

distinguished guests included Mr Nara Lokesh, Hon’ble IT Minister, Sri. GantaSrinivasaRao, Hon’ble Minister for Education, Sri. JA Chaudhary, IT Advisor to Govt. of AP, Sri. K. Vijayanand, IAS, Principal Secretary ITE&C Dept., and Sri. Anoop Singh, IFS, Special Secretary – ITE&C Dept. There were a series of exciting events including CXO Golf Tournament, CXO Roundtable, Networking Reception, Comic Relief, Re-Imagine Tour, Demo Day and Awards, and Site Tours.

The VFF 2018 conference program included various industry discussions, new insights pertaining to the sector and industry best practices. With themes includingBankTech, InsurTech, GovTech, Financial Inclusion and EmergeTech, the event hosted a few topics for the speaker sessions and panel discussions including ‘Future of banking’, ‘Social Impact through Fintech’, ‘Fintech Landscape in India and Rest of the World’, Security challenges in Fintech and ‘InsureTech Trends’. VFF 2018 hosted eight keynotes along with panel discussions, case study presentation & fireside chats that brought together stakeholders of the industry on a single platform, allowing exchange of ideas that added value to Indian Fintech ecosystem at large.


INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018 A white paper on Block Chain was launched by Mr.KunalPandey, Head - Financial Services in Risk Consulting, KPMG, Shri. Vijayanand,IAS, Principal Secretary- ITE &C, Govt. of Andhra Pradesh and Shri. JA Chowdary, IT Advisor to CM of Andhra Pradesh.

The third day witnessed the unveiling of the world’s first humanoid citizen robot, Sophia. Sophia is a highly sought-after speaker in business and has showed her prowess and great potential across many industries. She has appeared on-stage as a panel member and a presenter in high-level conferences, covering how robotics and artificial intelligence will become a prevalent part of people’s lives. Her reputation extends beyond business into Andhra Pradesh, in strategic collaboration with its challenge partners, DCF Ventures and Bizofit selected two startups each from Fintech, Agritech and Emergetech, as winners of the first ever 1 Million $ Global Startup Challenge as the grand finale of the 5 day festival. All the 37 startups had an opportunity to exhibit at the VizagFintech Festival 2018 to more than 1500 global delegates comprising of VCs, angel investors and corporate partners. All the winners and finalists were awarded prizes by the Hon’ble IT Minister of Andhra Pradesh, Sri. Nara Lokesh.

Vizag, with its remarkable technology ecosystem, is now the most attractive destination for innovation driven Fintech players. Not only Indian marquee companies but also several foreign companies have pledged to invest in the city, generating jobs in the near future. Vishakhapatnam is being developed as the most preferred global destination for Fintech and other emerging technology companies around the world, to start their operations and to drive innovation.


INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018

SURVEY ON MOBILE EDGE COMPUTING TECHNIQUES Mohanasathiya K.S Ph.D Research Scholar (Part-Time), Department of Computer Science, Nandha Arts & Science College, Erode, Tamil Nadu, India E-mail ID: sathyaanand08@gmail.com Dr.S.Prasath Assistant Professor & Research Supervisor, Department of Computer Science, Nandha Arts & Science College, Erode, Tamil Nadu, India E-mail ID: softprasaths@gmail.com Abstract- Mobile Edge Computing (MEC) is an interconnection of objects (food, home appliance and vehicles) growing design where cloud computing services are with unique identifiers such as Internet Protocol (IP) address extended to the edge of networks mobile base with the ability to communicate, interact or react to given stations. The challenging edge technology are changes with each other [18]. Cloud computing method allows IoT devices to carry applied to mobile, wireless and wire line development using software and hardware platforms, located at executions remotely with the Internet accessible computer the network edge in the vicinity of end-users. MEC (Cloud). This gives IoT devices virtually unlimited capabilities present faultless combination of various application in terms of storage and processing power [2]. Cloud computing service supplier and hawker towards mobile paradigm can hardly satisfy the requirements of high mobility subscribers. The important component in 5G support, location awareness and low latency. To concentrate on architecture which supports variety of new some of these edge computing are proposed. Edge computing methodology shifted computation applications and services where especially little latency is required. In this paper intended to current from remote cloud to the computational devices that are closer a broad analysis of related technical improvement in to the front-end IoT devices within edge networks [12]. The area of MEC. It provides the definition of MEC, closeness of edge devices has improved the efficiency IoT architectures and application in particular devices as it enables them to do real-time operations with less highlighted and future directions. It concluded with latency limitation. Mist Computing an immerging methodology goes security and privacy issues related to existing are further beyond Edge computing as it pushes the computation to discussed. the sensors and actuators. Hence, this even saves more power since communication from a node to Edge nodes takes more Keywords: MEC, IOT, Fog Computing, Cloud Computing. power than computation at the nodes [14]. Chen et al. [4] designed an efficient computation 1. INTRODUCTION offloading model using a game theoretic approach in a Mobile Edge Computing (MEC) is a technology that distributed manner. Game theory is a persuasive tool that helps brings the IT service environment and cloud computing simultaneously connected users to make the correct decision capabilities into the Radio Access Network. The close when connecting a wireless channel based on the strategic proximity to mobile devices reduces latency and creates a better interactions. If all user devices offload computation activities quality of experience for end users. MEC accelerates using the same wireless channel, it might cause signal applications with real-time requirements which may improve interference with each other and wireless quality reduction. effectiveness of radio resource usage. Connectivity Specifically, the game theory targets the NP-hard problem of management applications for mobile devices are good computation offloading incurred by multi-user computation candidates for deployment onto a MEC platform. offloading and provides a solution by attaining Nash Connectivity management is the ability to connect and equilibrium of multi-user computation offloading game. manage mobile devices in Machine-to-Machine (M2M) Wei Gao [7] proposed a opportunistic peer-to peer communications. Resilient and scalable connectivity mobile cloud computing framework. The probabilistic management is fundamental to M2M solutions. Connectivity framework is comprised of peer mobile devices that are management of mobile M2M devices is a complex task when connected via their short-range radios. These mobile devices dealing with various network protocols, physical or virtual are enabled to share both the energy and computational interfaces. resources depending on their available capacity. He proposed the probabilistic method to estimate the opportunistic network 2. RELATED WORKS transmission status and ensure the resultant computation is Internet of Things (IoT) established by AutoID labs timely delivered to its initiator. The purpose of the proposed [1] was initially used for radio frequency identification (RFID) framework is to facilitate war fighters at the tactical edge in a tags system. Internet of things (IoT) refers to a global

551


INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018 war zone. This framework is beneficial for situation awareness or surrounded ground environment understanding, with the help of data processed by in-situ (on site) sensors. The preamble novel framework thus efficiently shares computational tasks by migrating workloads among war fighters mobile hand held devices, perhaps taking an account of timeliness of computational workload for successive resultant migration. Cloud computing methodology usage in past decade in IoT networks has provided on-demand access to shared computing resources pool (storage, applications, services and software) that are hosted in the cloud. These are easily provisioned when needed by any authorised device in need of them with minimal vendor interaction [16, 11]. The architecture of cloud computing model. The threat of insecurity of data transmitted between devices, service instability, and latency are major drawbacks of Cloud computing [Wb10]. As Cloud computing participant’s machines, may be many hops away from each other, some data packets can be lost or man in middle attacks can be done on the transmitted data. To reduce on the drawbacks of far way cloud, usage of cloudlets was proposed as it brought, a limited local Cloud nearby [17]. Fog computing pushes closer Cloud computing paradigm down to the edge network by processing data at fog nodes or IoT gateway. This has solved some of Cloud computing challenges such as high latency and failure ensure total location awareness [6,19]. These fog nodes can be deployed at factories, parks, health care units, transport stations [3]. Edge computing brings, even more, closer the intelligence and application logic past the fog nodes, as it directly does these computations at devices programmable automation controllers that are in the edge networks [Pt04]. This increases the infrastructure efficiency as it provides intermediate layers of computation, networking and storage closer to IoT devices [10]. Niroshinie et al [5] describe Mobile Cloud computing. MCC gives applications ability to be run on remote machines in the cloud so that they can be accessed by client mobile devices that use resources being served over an internet connection. MCC clusters resources in a peer network among mobile devices. This forms a local cloud of mobile devices in the vicinity that provides different services to each other. Mobile cloud computing enables mobile devices to use cloudlet computers with in the proximity, to carry out executions that would have been carried out in the cloud. Even though Mobile cloud computing reduces high latency and bandwidth usage when compared to Cloud computing though itself also has some drawbacks such as low reliability and privacy related issues [8]. Pahl et al [21] review about the impact container virtualization on edge devices when being placed into clusters. It focus on how Edge clouds could go tough computation to scattered lightweight assets close to users. They used containerization technology to build clusters that consisted of customized platforms of SBCs nodes, running different

containers with orchestration services that enabled the communication of these SBCs nodes in the clusters. Riccardo et al [13] proposes the designing of gateways used in Cloud of Things which distributes a collection of resources, enabled in a horizontal integration with various IoT platforms and applications. These gateways oversee, manage data from IoT devices and act as endpoint for communication between cloud data-centers and local devices. The proposed gateways in their study used container based virtualization which gave an improvement of 2.67%, 6.04% and 10% in CPU, memory performance and Disk I/O. Ramalho et al [15] study evaluates the performance difference between containerized based and the hypervisorbased virtualization at the network edge. The use of hypervisorbased virtualization had good results in regards of isolation in the last decade but containerization abilities such fast to boot up, fast migration and easy to maintain have taken virtualization to next level. Mist Computing (Mist) represents a paradigm in which edge network devices, that have predictable accessibility, provide their computational and communicative resources as services to their vicinity via Device-to-Device communication protocols. Requesters in Mist can distribute software processes to Mist service providers for execution [9]. Takahashi et al. [20] proposed Edge Accelerated web Browsing (EAB) prototype designed for web application execution using a better offloading technique. The purpose of EAB is to improve user experience by pushing application offloading to the edge server which is implemented within the RAN. EAB-frontend at the client-side retrieves the rendered web content which is processed in the EAB server, whereas, audio and video streams travel through the EAB-backend and are decoded depending on the capabilities of the client hardware. Sardellitti et al. [21] proposed an algorithm-based design, called Successive Convex Approximation (SCA). This algorithm optimizes computational offloading across densely deployed multiple radio access points. The authors considered the MIMO multicell communication system where several mobile users request for their computational tasks to be carried at the central cloud server. They first tested a single user offloading computational task on the cloud server which resulted in the non-convex optimization problem. In the multiuser scenario, the SCA-based algorithm attained local optimal solution of the original non-convex problem. According to the formulation results, authors claimed their algorithms to be surpassed disjoint optimization schemes. Moreover, they stated that the proposed SCA design is more suitable for applications acquiring high computational tasks and minimizes energy consumption. Zhang et al. [22] proposed the contract-based computation resource allocation scheme. This scheme improves the utility of vehicular terminals which intelligently utilize services offered by MEC service providers under low computational conditions. The MEC provider receives the payment from vehicles on the basis of the computation task

552


INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018 they offloaded to the MEC servers. Using a wireless communication service, information of the contract and payment information is broadcasted to the vehicles on the road. Habak et al. [23] proposed the FemtoCloud system which forms a cloud of orchestrated co-located mobile devices that are self-configurable into a correlative mobile cloud system. A FemtoCloud client computing service is installed on each mobile device to calculate device computing capability and capacity for sharing with other mobile devices, and energy information. Mobile properties are built and maintained inside a user profile that is shared in a mobile cluster connected to a cloudlet or a control device that is available in a WiFi network. Intensive computational tasks in the form of codes are sent to cloudlets to leverage the computational capacity of other connected mobile devices. The FemtoCloud model is designed to reduce the computational load from the centralized location and bring it to the edge of the mobile network. Abdelwahab et al. [24] proposed REPLISOM which is a edge cloud architecture and LTE enhanced memory replication protocol to avoid latency issues. LTE bottleneck occurs due to allocating memory to a large number of IoT devices in the backend cloud servers. These devices offload computational tasks by replicating and transmitting tiny memory objects to a central cloud which makes IoT to be scalable and elastic. The LTE-integrated edge cloud provides its compute and storage resources at the edge to resource intensive services. Thus, the proposed REPLISOM reduces the stress of LTE by intelligently scheduling memory replication events at the LTE-edge to resolve any conflicts during the memory replication process for the radio resources. Nunna et al. [25] proposed a real-time contextaware collaboration system by combining MEC with 5G networks. By integrating MEC and 5G, it empowers realtime collaboration systems utilizing context-aware application platforms. These systems require context information combined with geographical information and low latency communication. The 4G network might not be capable to fulfill such requirements, instead 5G networks and MEC are proficient to utilize contextual information to provide real-time collaboration. The above suggested model is beneficial for scenarios such as life Remote Robotic Tele-surgery and Road Accident that demand high bandwidth and ultra low latency. Kumar et al. [26] proposed a vehicular delaytolerant network-based smart grid data management scheme. The authors investigated the use of Vehicular Delay-Tolerant Networks (VDTNs) to transmit data to multiple smart grid devices exploring the MEC environment. With the use of a store-and-carry forward mechanism for message transmission, the possible network bottleneck and data latency is avoided. Due to the high mobility of vehicles, a smart grid environment supported by MEC is used to monitor large data sets transmitted by several smart devices. According to the data movement, these devices make computation charging and discharging decisions with respect to message transmission delay, response time and high network throughput for movable vehicles.

Beck et al. [27] proposed ME-VoLTE which is an architecture that integrates MEC to voice over LTE. The encoding of video calls is offloaded to the MEC server located at the base station (eNodeB). The offloading of video encoding through external services helps escalating battery lifetime of the user equipment. Encoding is high computational-intensive and hence is very power consuming. In the proposed system, encoding techniques are wisely used to stream video on the MEC server. MEC transcodes video by using a special codec program before responding to the user device request. This phenomenon significantly increases data transmission and enhances power management. Jalali et al. [28] proposed a flow-based and time based energy consumption model. They conducted number of experiments for efficient energy consumption using centralized nano Data Centers (nDCs) in a cloud computing environment. The authors claim that nDCs energy consumption is not yet been investigated. Therefore, several models were presented to perform energy consumption tests on both shared and unshared network equipment. In the paper, it concludes that nDCs may lead to energy savings if the applications, especially IoT applications generate and process data within user premises. Jararweh et al. [29] proposed a Software Defined system for Mobile Edge Computing (SDMEC). The proposed framework connects software defined system components to MEC to further extend MCC capabilities. The components jointly work cohesively to enhance MCC into the MEC services. Working with Software Defined Networking (SDN), Software Defined Compute (SDCompute), Software Defined Storage (SDStorage), and Software Defined Security (SDSec) are the prime focus of the proposed framework which enables applications requiring compute and storage resources. Applications like traffic monitoring, content sharing and mobile gaming will benefit from SDMEC. El-Barbary et al. [30] proposed DroidCloudlet which is based on commodity mobile devices. DroidCloudlet is legitimized with resource-rich mobile devices that take the load of resource-constraint mobile devices. The purpose of the proposed architecture is to enhance mobile battery lifetime by migrating data-intensive and compute-intensive tasks to richmedia. DroidCloulet works as a client device or as a server device running an application that supplements resource-poor devices by offering their available resources. One of the devices takes the role of an agent which is responsible for coordinating resources with other groups of devices. 3. CONCLUSION Mobile edge computing processing has a brilliant ability to be the future facet innovation supplying statistics switch ability, battery life and capacity to the asset requirement cell phones. This paper surveys and the research efforts made on the mobile edge network, which is a paradigm integrating computing, caching and communication resources. The related problems of processing, storing and interchanges are tested respectively. Then the advances of communication techniques and the synergy with computing and caching are discussed. The novel applications and use cases are the driven force of the

553


INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018 mobile edge network architecture. The applications and uses cases that mobile edge networks can fully enable. This new paradigm faces many challenges and opportunities.

[13]

REFERENCES Kevin Ashton. That 'internet of things' thing. RFID Journal,2009. http://www.rfidjournal.com/ articles/view?4986. Alessio Botta, Walter de Donato, Valerio Persico, Antonio Pescapé. On the Integration of Cloud Computing and Internet of Things. International Conference on Future Internet of Things and Cloud, Barcelona, (2014), pp. 23-30. Cisco. IoT http://cisco.com [accessed 15 Feb. 2017] X. Chen, L. Jiao, W. Li, and X. Fu, “Efficient multiuser computation offloading for mobile-edge cloud computing,” IEEE/ACM Transactions on Networking, vol. 24, no. 5, pp. 2795–2808, Oct 2016. Niroshinie Fernando, Seng W. Loke, Wenny Rahayu, Mobile Cloud computing: A survey, Future Generation Computer Systems, Volume 29, Issue 1, January 2013, Pages 84-106, ISSN 0167-739X. Bonomi Flavio, Milito Rodolfo, Natarajan Preethi, Zhu Jiang. Fog Computing: A Platform for Internet of Things and Analytics. Big Data and Internet of Things: A Roadmap for Smart Environments in Springer International Publishing Springer International Publishing (2014). W. Gao, “Opportunistic peer-to-peer mobile cloud computing at the tactical edge,” in 2014 IEEE Military Communications Conference,Oct 2014, pp. 1614– 1620. Karthik Kumar,Yung-Hsiang Lu. Cloud Computing for Mobile Users: Can Offloading Computation Save Energy? in Computer, vol. 43, no. 4, pp. 51-56, April 2010. Liyanage M, Chang C, Srirama SN (2016).mePaaS: mobile-embedded platform as a service for distributing fog computing to edge nodes. In: 17th international conference on parallel and distributed computing, applications and technologies (PDCAT16). Roberto Morabito, Nicklas Beijar. Enabling Data Processing at the Network Edge through Lightweight Virtualization Technologies. IEEE International Conference on Sensing, Communication and Networking (SECON Workshops). London, United Kingdom, (2016), pp. 1-6. NIST, Definition of Cloud computing v15 (2009), National Institute of Standards and Technology: Gaithersburg Editor. 2009. Claus Pahl, Sven Helmer, Lorenzo Miori, Julian Sanin, Brian Lee. A Container-Based Edge Cloud PaaS Architecture Based on Raspberry Pi Clusters. IEEE 4th International Conference on Future Internet of Things and Cloud Workshops (FiCloudW), Vienna, (2016), pp. 117-124.

[14]

[1]

[2]

[3] [4]

[5]

[6]

[7]

[8]

[9]

[10]

[11]

[12]

[15]

[16]

[17]

[18]

[19]

[20]

[21]

[22]

[23]

[24]

554

Petrolo, Riccardo, Roberto Morabito, Valeria Loscrì, and Nathalie Mitton. "The design of the gateway for the Cloud of Things." Annals of Telecommunications (2015): 1-10. Jürgo S. Preden,Kalle Tammemäe, Axel Jantsch, Mairo Leier, Andri Riid,Emine Calis. The Benefits of Self-Awareness and Attention in Fog and Mist Computing. in Computer, vol. 48, no. 7, pp. 37-45, (July 2015). Flávio Ramalho, Augusto Neto. Virtualization at the network edge: A performance comparison, 2016 IEEE 17th International Symposium on A World of Wireless, Mobile and Multimedia Networks (WoWMoM), Coimbra, 2016, pp. 1-6. B. B Prahlada Rao, Paval Saluia, Neetu Sharma, Ankit Mittal, Shivay Veer Sharma. Cloud computing for Internet of Things & sensing based applications, 2012 Sixth International Conference on Sensing Technology (ICST), Kolkata, 2012, pp. 374-380. Mahadev Satyanarayanan, Paramvir Bahl, Ramon Caceres, Nigel Davies. The Case for VM-Based Cloudlets in Mobile Computing in IEEE Pervasive Computing, vol. 8,no. 4, pp. 14-23, (Oct.-Dec. 2009). Madakam, Somayya. International Journal of Future Computer and Communication; Singapore4.4 (Aug 2015): 250-253. Ivan Stojmenovic, Sheng Wen. The Fog computing paradigm: Scenarios and security issues. Federated Conference on Computer Science and Information Systems, Warsaw,(2014), pp. 1-8. N. Takahashi, H. Tanaka and R. Kawamura, “Analysis of process assignment in multi-tier mobile cloud computing and application to edge accelerated web browsing,” in Mobile Cloud Computing, Services and Engineering (MobileCloud), 2015 3rd IEEE International Conference on, March 2015, pp. 233– 234. S. Sardellitti, G. Scutari, and S. Barbarossa, “Joint optimization of radio and computational resources for multicell mobile-edge computing,” IEEE Transactions on Signal and Information Processing over Networks, vol. 1, no. 2, pp. 89–103, June 2015. K. Zhang, Y. Mao, S. Leng, A. Vinel, and Y. Zhang, “Delay constrained offloading for mobile edge computing in cloud-enabled vehicular networks,” in 2016 8th International Workshop on Resilient Networks Design and Modeling (RNDM), Sept 2016, pp. 288–294. K. Habak, M. Ammar, K. A. Harras, and E. Zegura, “Femto clouds: Leveraging mobile devices to provide cloud service at the edge,” in 2015 IEEE 8th International Conference on Cloud Computing, June 2015, pp. 9–16. S. Abdelwahab, B. Hamdaoui, M. Guizani, and T. Znati, “Replisom: Disciplined tiny memory replication for massive iot devices in lte edge cloud,”


INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018

[25]

[26]

[27]

IEEE Internet of Things Journal, vol. 3, no. 3, pp. 327– 338, June 2016. S. Nunna, A. Kousaridas, M. Ibrahim, M. Dillinger, C. Thuemmler, H. Feussner, and A. Schneider, “Enabling real-time context-aware collaboration through 5g and mobile edge computing,” in Information Technology - New Generations (ITNG), 2015 12th International Conference on, April 2015, pp. 601–605. N. Kumar, S. Zeadally, and J. J. P. C. Rodrigues, “Vehicular delaytolerant networks for smart grid data management using mobile edge computing,” IEEE Communications Magazine, vol. 54, no. 10, pp. 60– 66, October 2016. M. T. Beck, S. Feld, A. Fichtner, C. Linnhoff-Popien, and T. Schimper, “Me-volte: Network functions for energy-efficient video transcoding at the mobile edge,” in Intelligence in Next Generation Networks

(ICIN), 2015 18th International Conference on, Feb 2015, pp. 38–44. [28] F. Jalali, K. Hinton, R. Ayre, T. Alpcan, and R. S. Tucker, “Fog computing may help to save energy in cloud computing,” IEEE Journal on Selected Areas in Communications, vol. 34, no. 5, pp. 1728–1739, May 2016. [29] Y. Jararweh, A. Doulat, A. Darabseh, M. Alsmirat, M. Al-Ayyoub and E. Benkhelifa, “Sdmec: Software defined system for mobile edge computing,” in 2016 IEEE International Conference on Cloud Engineering Workshop (IC2EW), April 2016, pp. 88–93. [30] A. E. H. G. El-Barbary, L. A. A. El-Sayed, H. H. Aly, and M. N. El-Derini, “A cloudlet architecture using mobile devices,” in 2015 IEEE/ACS 12th International Conference of Computer Systems and Applications (

555


INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018

RECOGNIZING FACE WITH CONSECUTIVE OCCLUSION USING MARKOV CHAIN G.Rajeswari Assistant Professor, Department of CSE, Sree Sowdambika College of Engineering, Aruppukottai, Tamil Nadu, India. Dr. P. Ithaya Rani Associate Professor, Department of CSE, Sethu Institute of Technology, Kariapatti, Tamil Nadu, India. Abstract- Face Recognition (FR) technology is software that can identify human face from any digital image/ video. In the real world, faces with occlusion such as sunglasses, scarf, mask etc., are quite common, especially in uncooperative scenario. The facial occlusion is one critical factor that affects the performance of face recognition. One cannot predict human face, when the face has been occluded. In recent years, Markov chain model a hotspot of dealing with face recognition under different illuminations and facial occlusions. The basic idea of Markov chain model is to recover clean images from degraded images or occluded images by using the clean training samples. Then the reconstructed images are used for face recognition. Note that the residual image which is a difference between the raw and reconstructed image containing most of the occluded information. In this paper two contributions are created for occlusion detection: i) a new occlusion detection method is presented by combining the information of both raw image and residual image; ii) the non-occluded part for face recognition has a better result than using reconstructed image is empirically displayed. The main objective of this paper is to get information.

And the nuclear norm based matrix regression (NMR) method proposed by Yang et al. significantly outperforms the other methods in recovering the clean image . All these method used the reconstructed images for classification. We consider the fact that the reconstructed images might remove some useful information and introduce some incidental information. Therefore, whether the reconstructed images are suitable for occluded face recognition needs study. During face recognition, the occluded face image may generate error. In this paper, the main goal is to know information about error in advance in sequential occlusion to get free from occlusion.

Keywords: Face recognition with occlusion, Markov Chain, residual image.

1. INTRODUCTION Face recognition technology is playing a more and more important role in our daily lives, such as access control, credit card verification, video surveillance etc. Many researchers developed many techniques and algorithms in FR. Even though, there comes a problem when the face is occluded. Nevertheless, the acquisition facial images might be occluded by other objects (sunglasses, scarf, mask etc.) which have a harmful effect on face recognition systems. In recent years, Markov Chain model were proposed to solve the occluded face recognition problem by recovering the clean image from one occluded image. These methods like linear regression classifier (LRC), sparse representation based classification (SRC) and collaborative representation based classification (CRC) all achieved expected results.

Fig.1: Example Training Data a) Occluded face image b) Normal face image 2. LITERATURE SURVEY In the literature of face recognition, traditional holistic feature based approaches are sensitive to outlier pixels, performing poorly against occlusion. Local feature based approaches are roughly divided into two categories in terms of patch-dependent or data-dependent. Combined with partial matching methods, the local features are more robust because they are not extracted from the entire image. Nonetheless, they are still inevitably affected by invalid pixels and far from being robust enough in practical classification tasks. An alternative solution addresses occlusion via a two-stage approach. It first identifies and discards the occluded pixels, and then performs the classification on the rest [1].

556


INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018 As one can imagine, its classification performance is greatly determined by the occlusion identification accuracy. If too much discriminative information is abandoned, the following classification becomes difficult. To enhance the accuracy of occlusion identification, [2] adopts the prior that the occlusion is spatially continuous and consequently achieves excellent performance. However, such unsupervised approach might cause misestimate when occlusion is severe. For instance, a scarf larger than half of the testing face may be considered as a useful signal, and therefore face pixels may be discarded in each iteration. We call it a degenerate solution. Besides, the algorithm in [3] has to be carried out subject-by-subject and exhaustively search the class with the minimum normalized error, which is time-consuming and detrimental to real-time applications Recently, several occlusion dictionary based approaches [4] for robust face recognition have been attached more and more importance. This kind of method is capable of efficiently handling various occlusions. They exploit characteristics of non-occluded and occluded region, assuming that both of them can be coded over the corresponding part of dictionary [5]. These methods act in the similar way with each other. Concretely, an occlusion dictionary is concatenated to the original dictionary to perform occlusion coding. The goal is to jointly represent the occluded image. Fig. 1 illustrates how occlusion dictionary methods work. By seeking a sparse solution, the occluded image successfully decomposes into face and occlusion. The classification is carried out via the corresponding coefficients. Hence, they cast the recognition problem with occlusion as the one without occlusion, since occlusion is regarded as an extra and special class in training samples. On the other hand, these occlusion dictionary based approaches choose different occlusion dictionary, leading to very different performance. More specifically, sparse representationbased classification (SRC) [6] employs an identity matrix as the occlusion dictionary, showing promising robustness to random pixel corruption and small contiguous occlusion. exploits the local characteristics of Gabor feature, and proposes Gabor feature based sparse representation classification (GSRC). The Gabor feature of identity matrix exists high redundancy, so it can be compressed to a compact form for efficiency. Extended SRC (ESRC) [7] points out that intra-class variant dictionary contains useful information. By exploiting the difference images between two samples in the same class, ESRC can handle certain occlusion. The recent improvement is made by [8], namely structured sparse representation based classification (SSRC). They obtain common occlusion samples from occluded images with projection residuals, and utilize K-SVD to train occlusion dictionary, making appended occlusion atoms to be more representative. SSRC achieves higher accuracy in both recovery and recognition. Texture Features can be extracted using local binary pattern (LBP).

Markov chains have many applications as statistical models of real-world processes, such as studying cruise control systems in motor vehicles, queues or lines of customers arriving at an airport, exchange rates of currencies, storage systems such as dams, and population growths of certain animal species.[9] The algorithm known as PageRank, which was originally proposed for the internet search engine Google, is based on a Markov process. Furthermore, Markov processes are the basis for general stochastic simulation methods known as Gibbs sampling and Markov chain Monte Carlo, are used for simulating random objects with specific probability distributions, and have found extensive application in Bayesian statistics Hence, this work Markov chain model is proposed to recover clean images from degraded images or occluded images by using the clean training samples. Then the reconstructed images are used for face recognition. Note that the residual image which is a difference between the raw and reconstructed image containing most of the occluded information. In this paper two contributions are created for occlusion detection: i) a new occlusion detection method is presented by combining the information of both raw image and residual image; ii) the non-occluded part for face recognition has a better result than using reconstructed image is empirically displayed. The main objective of this paper is to get information about the error distribution in advance. 3. PROPOSED WORK

Formally, a Markov chain is a probabilistic automaton. The probability distribution of state transitions is typically represented as the Markov chain’s transition matrix. If the Markov chain has N possible states, the matrix will be an N x N matrix, such that entry (I, J) is the probability of transitioning from state I to state J. Additionally, the transition matrix must be a stochastic matrix, a matrix whose entries in each row must add up to exactly 1. This makes complete sense, since each row represents its own probability distribution. Fig.2: Sample Markov Chain, With States as Circles and Edges as Transitions As discussed above, face recognition can be cast as a problem of recovering an input signal x 2 Rn from corrupted measurements y = Ax + e, where A 2 Rm_n

557


INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018 with m > n. Let F be a matrix whose rows span the left null space of A2. Applying F to both sides of the measurement equation gives ~y := Fy = F(Ax + e) = Fe: So the recovery problem is reduced to the problem of reconstructing a sparse error vector e from the observation Fe. While this problem is very hard in general, in many situations solving the convex relaxation min kvk1 s.t. Fv = ~y= Fe exactly recovers e. Candes et. al. [6] have characterized the recoverability of the sparse solution to the above problem in terms of the restricted isometry property (RIP) of the matrix F. The k-restricted isometry constant _k 2 R is defined as the smallest quantity such that for any ksparse typical result states 1-minimization is guaranteed to recover any k-sparse x whenever the matrix F satisfies _2k < 1. Notice that this argument treats every possible k-sparse supports equally. However, in many applications, we have prior information about the distribution of the supports. To extend the theory to such structured sparsity, [8] introduced the (k; _)-probabilistic RIP (PRIP). A matrix F is said to satisfy the PRIP if there exists a constant _k > 0 such that for a k-sparse signal x whose support is a considered as a random variable, (2) holds with probability f1. Based on results from Compressed Sensing theory, for a randomly chosen matrix to have RIP of order k requires at least m = O(k log(n=k)) measurements [6]. However, it has been shown that a matrix can have PRIP of order k with only m = O(k + log(D)) measurements, where D is the cardinality of the smallest set of supports of size k for which the probability that the support of a ksparse signal x does not belong to the set is less than _ [8]. Then for distributions that allow a small D, the required number of measurements essentially grows linearly in k, much less than the general case. The distribution of contiguous supports precisely falls into this category3. Thus, we should expect to recover sparse errors with such supports from much fewer measurements. Or equivalently, from a fixed number measurements, we should expect to correct a larger fraction of errors from `1-minimization if we know how to properly harness information about the distribution.

[2]

[3]

[4]

[5]

[6]

[7]

[8]

[9]

4. CONCLUSION In this paper, we propose a Markov model, which simultaneously separates the occlusion and classifies the test image by coding over the occlusion sample. In future Comprehensive experimental results show that Markov chain can better deal with face recognition with occlusion than most existing well-performing algorithms.

[1]

REFERENCES T. Ahonen, A. Hadid, and M. Pietikainen. Face description with local binary patterns: Application to face recognition.PAMI, 28(12):2037–2041, 2013.

558

Effective Representation Using ICA for Ieee Transactions On Pattern Analysis And Machine Intelligence, Vol. 27, No. 12, 2008. Learning Spatially Localized, Parts-Based Representation, IEEE Computer Society Conference on Computer Vision andPattern Recognition ¡ January 2001 W. Deng, J. Hu, J. Guo, Extended SRC: undersampled face recognition via intraclass variant dictionary, IEEE Trans. Pattern Anal. Mach. Intell. 34 (9) (2012) 1864-1870. W. Liu, Y. Wen, H. Li, B. Zhu, Dictionary construction for sparse representation classification: A novel cluster-based approach, in: International Conference on Symposium on Computers and Communication, IEEE, 2014, pp. 1-6. M. Grant, S. Boyd. Graph implementations for nonsmooth convex programs, Recent advances in learning and control. Springer London, (2008) 95-110. X. Tan, S. Chen, Z. Zhou, J. Liu, Face recognition under occlusions and variant expressions with partial similarity, IEEE Trans. Inf. Forensics Secur. 4 (2) (2009) 217-230. Kim, J Choi, J Yi, M. Turk, Effective representation using ICA for face recognition robust to local distortion and partial occlusion, IEEE Trans. Pattern Anal. Mach. Intell. 27 (12) (2012) 1977-1981. J. Wright, A. Yang, A. Ganesh, S. Sastry, and Y. Ma. Robust face recognition via sparse representation. PAMI, 2014


INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.11 NOVEMBER 2018

559


Turn static files into dynamic content formats.

Create a flipbook
Issuu converts static files into: digital portfolios, online yearbooks, online catalogs, digital photo albums and more. Sign up and create your flipbook.