Beschreibung
This book focuses on how machine learning techniques can be used to analyze and make use of one particular category of behavioral biometrics known as the gait biometric. A comprehensive Ground Reaction Force (GRF)-based Gait Biometrics Recognition framework is proposed and validated by experiments. In addition, an in-depth analysis of existing recognition techniques that are best suited for performing footstep GRF-based person recognition is also proposed, as well as a comparison of feature extractors, normalizers, and classifiers configurations that were never directly compared with one another in any previous GRF recognition research. Finally, a detailed theoretical overview of many existing machine learning techniques is presented, leading to a proposal of two novel data processing techniques developed specifically for the purpose of gait biometric recognition using GRF.
This book
· introduces novel machine-learning-based temporal normalization techniques
· bridges research gaps concerning the effect of footwear and stepping speed on footstep GRF-based person recognition
· provides detailed discussions of key research challenges and open research issues in gait biometrics recognition
· compares biometrics systems trained and tested with the same footwear against those trained and tested with different footwear
Autorenportrait
James Eric Masonobtained his BSEng and MASc from the University of Victoria, Canada, in 2009and 2014, respectively. During his Masters program, under the supervision ofDr. Issa Traore, his research focused primarily on biometric security solutionswith a particular emphasis on the gait biometric. In 2014 he completed histhesis titledExamining the impact ofNormalization and Footwear on Gait Biometrics Recognition using the GroundReaction Force, which served as an inspiration for the work presented inthis book. His research interests include biometric security, machine learning,software engineering, web development, and weather/climate sciences. Since2011, he has been working with the software startup Referral SaaSquatch as afull stack software developer.
Issa Traoreobtained a PhD in Software Engineering in 1998 from Institute NationalePolytechnique (INPT)-LAAS/CNRS, Toulouse, France. He has been with the facultyof the Department of Electrical and Computer Engineering of the University ofVictoria since 1999. He is currently a Full Professor and the Coordinator ofthe Information Security and object Technology (ISOT) Lab at the University of Victoria. His research interests include biometricstechnologies, computer intrusion detection, network forensics, softwaresecurity, and software quality engineering. He is currently serving as Associate Editor for the InternationalJournal of Communication Systems (IJCS) and the International Journal ofCommunication Networks and Distributed Systems (IJCNDS). Dr. Traore is also aco-founder and Chief Scientist of Plurilock Security Solutions Inc., a network security company which providesinnovative authentication technologies, and is one of the pioneers in bringingbehavioral biometric authentication products to the market.
Isaac Woungangreceivedhis M.Sc.& Ph.D degrees, all in Mathematics, from the University of AixMarseille II, France, and University of South, Toulon and Var, France, in 1990and 1994 respectively. In 1999, he received a MSc degree from theINRS-Materials and Telecommunications, University of Quebec, Montreal, QC,Canada. From 1999 to 2002, he worked as a software engineer at Nortel Networks,Ottawa, Canada, in the Photonic Line Systems Group. Since 2002, he has beenwith Ryerson University, where he is now a full professor of Computer Scienceand Director of the Distributed Applications and Broadband (DABNEL) Lab. His current research interests includeradio resource management in next generation wireless networks, biometricstechnologies, network security. Dr. Woungang has published 8 books and over 89refereed technical articles in scholarly international journals and proceedingsof international conferences. He has served as Associate Editor of theComputers and Electrical Engineering (Elsevier), and the International Journalof Communication Systems (Wiley). He has Guest Edited several Special Issueswithvarious reputed journals such as IET Information Security, Mathematicaland Computer Modeling (Elsevier), Computer Communications (Elsevier), Computersand Electrical Engineering (Elsevier), and Telecommunication Systems(Springer). Since January 2012, He serves as Chair of Computer Chapter, IEEEToronto Section.
Inhalt
Introduction.- Background.- Experimental Design and Dataset.- Feature Extraction.-Normalization.- Classification.- Measured Performance.- Experimental Analysis.- Conclusion.
Informationen zu E-Books
„E-Book“ steht für digitales Buch. Um diese Art von Büchern lesen zu können wird entweder eine spezielle Software für Computer, Tablets und Smartphones oder ein E-Book Reader benötigt. Da viele verschiedene Formate (Dateien) für E-Books existieren, gilt es dabei, einiges zu beachten.
Von uns werden digitale Bücher in drei Formaten ausgeliefert. Die Formate sind EPUB mit DRM (Digital Rights Management), EPUB ohne DRM und PDF. Bei den Formaten PDF und EPUB ohne DRM müssen Sie lediglich prüfen, ob Ihr E-Book Reader kompatibel ist. Wenn ein Format mit DRM genutzt wird, besteht zusätzlich die Notwendigkeit, dass Sie einen kostenlosen Adobe® Digital Editions Account besitzen. Wenn Sie ein E-Book, das Adobe® Digital Editions benötigt herunterladen, erhalten Sie eine ASCM-Datei, die zu Digital Editions hinzugefügt und mit Ihrem Account verknüpft werden muss. Einige E-Book Reader (zum Beispiel PocketBook Touch) unterstützen auch das direkte Eingeben der Login-Daten des Adobe Accounts – somit können diese ASCM-Dateien direkt auf das betreffende Gerät kopiert werden.
Da E-Books nur für eine begrenzte Zeit – in der Regel 6 Monate – herunterladbar sind, sollten Sie stets eine Sicherheitskopie auf einem Dauerspeicher (Festplatte, USB-Stick oder CD) vorsehen. Auch ist die Menge der Downloads auf maximal 5 begrenzt.