Deep Learning, Volume 48 in the Handbook of Statistics series, highlights new advances in the field, with this new volume presenting interesting chapters on a variety of timely topics, including Generative Adversarial Networks for Biometric Synthesis, Data Science and Pattern Recognition, Facial Data Analysis, Deep Learning in Electronics, Pattern Recognition, Computer Vision and Image Processing, Mechanical Systems, Crop Technology and Weather, Manipulating Faces for Identity Theft via Morphing and Deepfake, Biomedical Engineering, and more.

Statistical learning and analysis techniques have become extremely important today, given the tremendous growth in the size of heterogeneous data collections and the ability to process it even from physically distant locations. Recent advances made in the field of machine learning provide a strong framework for robust learning from the diverse corpora and continue to impact a variety of research problems across multiple scientific disciplines. The aim of this handbook is to familiarize beginners as well as experts with some of the recent techniques in this field.

The Handbook is divided in two sections: Theory and Applications, covering machine learning, data analytics, biometrics, document recognition and security.
very relevant to current research challenges faced in various fieldsself-contained reference to machine learning

emphasis on applications-oriented techniques

In today's security-conscious society, real-world applications for authentication or identification require a highly accurate system for recognizing individual humans. The required level of performance cannot be achieved through the use of a single biometric such as face, fingerprint, ear, iris, palm, gait or speech. Fusing multiple biometrics enables the indexing of large databases, more robust performance and enhanced coverage of populations. Multiple biometrics are also naturally more robust against attacks than single biometrics. This book addresses a broad spectrum of research issues on multibiometrics for human identification, ranging from sensing modes and modalities to fusion of biometric samples and combination of algorithms. It covers publicly available multibiometrics databases, theoretical and empirical studies on sensor fusion techniques in the context of biometrics authentication, identification and performance evaluation and prediction.

Theoriginalmotivationsfordevelopingopticalcharacterrecognitiontechnologies weremodesttoconvertprintedtexton?atphysicalmediatodigitalform,prod- ingmachine-readabledigitalcontent. Bydoingthis,wordsthathadbeeninertand bound to physical material would be brought into the digital realm and thus gain newandpowerfulfunctionalitiesandanalyticalpossibilities. First-generation digital OCR researchers in the 1970s quickly realized that by limiting their ambitions primarily to contemporary documents printed in st- dard font type from the modern Roman alphabet (and of these, mostly English language materials), they were constraining the possibilities for future research andtechnologiesconsiderably. Domainresearchersalsosawthatthetrajectoryof OCR technologies if left unchanged would exclude a large portion of the human record. Digitalconversionofdocumentsandmanuscriptsinotheralphabets,scripts, and cursive styles was of critical importance. Embedded in non-Roman alp- bet source documents, including ancient manuscripts, papyri scrolls, clay tablets, and other inscribed artifacts was not only a wealth of scholarly information but alsonewopportunitiesandchallengesforadvancingOCR,imagingsciences,and othercomputationalresearchareas. Thelimitingcircumstancesatthetimeincluded the rudimentary capability (and high cost) of computational resources and lack of network-accessible digital content. Since then computational technology has advancedataveryrapidpaceandnetworkinginfrastructurehasproliferated. Over time, thisexponential decrease inthecost of computation, memory, and com- nicationsbandwidthcombinedwiththeexponentialincreaseinInternet-accessible digitalcontenthastransformededucation,scholarship,andresearch. Largenumbers ofresearchers,scholars,andstudentsuseanddependuponInternet-basedcontent andcomputationalresources. Thechaptersinthisbookdescribeacriticallyimportantareaofinvestigation- addressingconversionofIndicscriptintomachine-readableform. Roughestimates haveitthatcurrentlymorethanabillionpeopleuseIndicscripts. Collectively,Indic historic and cultural documents contain a vast richness of human knowledge and experience. The state-of-the-art research described in this book demonstrates the multiple values associated with these activities. Technically, the problems associated with Indicscriptrecognitionareverydif?cultandwillcontributetoandinformrelated v vi Foreword scriptrecognitionefforts. Theworkalsohasenormousconsequenceforenriching andenablingthestudyofIndicculturalheritagematerialsandthehistoricrecord of its people. This in turn broadens the intellectual context for domain scholars focusingonothersocieties,ancientandmodern. Digital character recognition has brought about another milestone in coll- tivecommunicationbybringinginert,?xed-in-place,textintoaninteractivedi- talrealm. Indoingso,theinformationhasgainedadditionalfunctionalitieswhich expandourabilitiestoconnect,combine,contextualize,share,andcollaboratively pursue knowledge making. High-quality Internet content continues to grow in an explosivefashion. Inthenewglobalcyberenvironment,thefunctionalitiesandapp- cationsofdigitalinformationcontinuetotransformknowledgeintonewundersta- ingsofhumanexperienceandtheworldinwhichwelive. Thepossibilitiesforthe futurearelimitedonlybyavailableresearchresourcesandcapabilitiesandtheim- inationandcreativityofthosewhousethem. Arlington,Virginia StephenM.

Cognitive Computing: Theory and Applications, written by internationally renowned experts, focuses on cognitive computing and its theory and applications, including the use of cognitive computing to manage renewable energy, the environment, and other scarce resources, machine learning models and algorithms, biometrics, Kernel Based Models for transductive learning, neural networks, graph analytics in cyber security, neural networks, data driven speech recognition, and analytical platforms to study the brain-computer interface.

While the term Big Data is open to varying interpretation, it is quite clear that the Volume, Velocity, and Variety (3Vs) of data have impacted every aspect of computational science and its applications. The volume of data is increasing at a phenomenal rate and a majority of it is unstructured. With big data, the volume is so large that processing it using traditional database and software techniques is difficult, if not impossible. The drivers are the ubiquitous sensors, devices, social networks and the all-pervasive web. Scientists are increasingly looking to derive insights from the massive quantity of data to create new knowledge. In common usage, Big Data has come to refer simply to the use of predictive analytics or other certain advanced methods to extract value from data, without any required magnitude thereon. Challenges include analysis, capture, curation, search, sharing, storage, transfer, visualization, and information privacy. While there are challenges, there are huge opportunities emerging in the fields of Machine Learning, Data Mining, Statistics, Human-Computer Interfaces and Distributed Systems to address ways to analyze and reason with this data. The edited volume focuses on the challenges and opportunities posed by "Big Data" in a variety of domains and how statistical techniques and innovative algorithms can help glean insights and accelerate discovery. Big data has the potential to help companies improve operations and make faster, more intelligent decisions.

Recent advances in biometrics include new developments in sensors, modalities and algorithms. As new sensors are designed, newer challenges emerge in the algorithms for accurate recognition. Written for researchers, advanced students and practitioners to use as a handbook, this volume captures the very latest state-of-the-art research contributions from leading international researchers. It offers coverage of the entire gamut of topics in the field, including sensors, data acquisition, pattern-matching algorithms, and issues that impact at the system level, such as standards, security, networks, and databases

Recent advances in biometrics include new developments in sensors, modalities and algorithms. As new sensors are designed, newer challenges emerge in the algorithms for accurate recognition. Written for researchers, advanced students and practitioners to use as a handbook, this volume captures the very latest state-of-the-art research contributions from leading international researchers. It offers coverage of the entire gamut of topics in the field, including sensors, data acquisition, pattern-matching algorithms, and issues that impact at the system level, such as standards, security, networks, and databases

Theoriginalmotivationsfordevelopingopticalcharacterrecognitiontechnologies weremodesttoconvertprintedtexton?atphysicalmediatodigitalform,prod- ingmachine-readabledigitalcontent. Bydoingthis,wordsthathadbeeninertand bound to physical material would be brought into the digital realm and thus gain newandpowerfulfunctionalitiesandanalyticalpossibilities. First-generation digital OCR researchers in the 1970s quickly realized that by limiting their ambitions primarily to contemporary documents printed in st- dard font type from the modern Roman alphabet (and of these, mostly English language materials), they were constraining the possibilities for future research andtechnologiesconsiderably. Domainresearchersalsosawthatthetrajectoryof OCR technologies if left unchanged would exclude a large portion of the human record. Digitalconversionofdocumentsandmanuscriptsinotheralphabets,scripts, and cursive styles was of critical importance. Embedded in non-Roman alp- bet source documents, including ancient manuscripts, papyri scrolls, clay tablets, and other inscribed artifacts was not only a wealth of scholarly information but alsonewopportunitiesandchallengesforadvancingOCR,imagingsciences,and othercomputationalresearchareas. Thelimitingcircumstancesatthetimeincluded the rudimentary capability (and high cost) of computational resources and lack of network-accessible digital content. Since then computational technology has advancedataveryrapidpaceandnetworkinginfrastructurehasproliferated. Over time, thisexponential decrease inthecost of computation, memory, and com- nicationsbandwidthcombinedwiththeexponentialincreaseinInternet-accessible digitalcontenthastransformededucation,scholarship,andresearch. Largenumbers ofresearchers,scholars,andstudentsuseanddependuponInternet-basedcontent andcomputationalresources. Thechaptersinthisbookdescribeacriticallyimportantareaofinvestigation- addressingconversionofIndicscriptintomachine-readableform. Roughestimates haveitthatcurrentlymorethanabillionpeopleuseIndicscripts. Collectively,Indic historic and cultural documents contain a vast richness of human knowledge and experience. The state-of-the-art research described in this book demonstrates the multiple values associated with these activities. Technically, the problems associated with Indicscriptrecognitionareverydif?cultandwillcontributetoandinformrelated v vi Foreword scriptrecognitionefforts. Theworkalsohasenormousconsequenceforenriching andenablingthestudyofIndicculturalheritagematerialsandthehistoricrecord of its people. This in turn broadens the intellectual context for domain scholars focusingonothersocieties,ancientandmodern. Digital character recognition has brought about another milestone in coll- tivecommunicationbybringinginert,?xed-in-place,textintoaninteractivedi- talrealm. Indoingso,theinformationhasgainedadditionalfunctionalitieswhich expandourabilitiestoconnect,combine,contextualize,share,andcollaboratively pursue knowledge making. High-quality Internet content continues to grow in an explosivefashion. Inthenewglobalcyberenvironment,thefunctionalitiesandapp- cationsofdigitalinformationcontinuetotransformknowledgeintonewundersta- ingsofhumanexperienceandtheworldinwhichwelive. Thepossibilitiesforthe futurearelimitedonlybyavailableresearchresourcesandcapabilitiesandtheim- inationandcreativityofthosewhousethem. Arlington,Virginia StephenM.