ebook img

Multimodal analytics for next-generation big data technologies and applications PDF

391 Pages·2019·10.868 MB·English
Save to my drive
Quick download
Download
Most books are stored in the elastic cloud where traffic is expensive. For this reason, we have a limit on daily download.

Preview Multimodal analytics for next-generation big data technologies and applications

Kah Phooi Seng · Li-minn Ang  Alan Wee-Chung Liew · Junbin Gao Editors Multimodal Analytics for Next-Generation Big Data Technologies and Applications Multimodal Analytics for Next-Generation Big Data Technologies and Applications (cid:129) (cid:129) Kah Phooi Seng Li-minn Ang (cid:129) Alan Wee-Chung Liew Junbin Gao Editors Multimodal Analytics for Next-Generation Big Data Technologies and Applications Editors KahPhooiSeng Li-minnAng SchoolofEngineeringandInformation SchoolofInformationandCommunication Technology Technology UniversityofNewSouthWales GriffithUniversity Canberra,ACT,Australia GoldCoast,QLD,Australia AlanWee-ChungLiew JunbinGao SchoolofInformationandCommunication TheUniversityofSydneyBusinessSchool Technology UniversityofSydney GriffithUniversity Sydney,NSW,Australia GoldCoast,QLD,Australia ISBN978-3-319-97597-9 ISBN978-3-319-97598-6 (eBook) https://doi.org/10.1007/978-3-319-97598-6 ©SpringerNatureSwitzerlandAG2019 Thisworkissubjecttocopyright.AllrightsarereservedbythePublisher,whetherthewholeorpartofthe materialisconcerned,specificallytherightsoftranslation,reprinting,reuseofillustrations,recitation, broadcasting,reproductiononmicrofilmsorinanyotherphysicalway,andtransmissionorinformation storageandretrieval,electronicadaptation,computersoftware,orbysimilarordissimilarmethodology nowknownorhereafterdeveloped. Theuseofgeneraldescriptivenames,registerednames,trademarks,servicemarks,etc.inthispublication doesnotimply,evenintheabsenceofaspecificstatement,thatsuchnamesareexemptfromtherelevant protectivelawsandregulationsandthereforefreeforgeneraluse. The publisher, the authors, and the editorsare safeto assume that the adviceand informationin this bookarebelievedtobetrueandaccurateatthedateofpublication.Neitherthepublishernortheauthorsor theeditorsgiveawarranty,expressorimplied,withrespecttothematerialcontainedhereinorforany errorsoromissionsthatmayhavebeenmade.Thepublisherremainsneutralwithregardtojurisdictional claimsinpublishedmapsandinstitutionalaffiliations. ThisSpringerimprintispublishedbytheregisteredcompanySpringerNatureSwitzerlandAG. Theregisteredcompanyaddressis:Gewerbestrasse11,6330Cham,Switzerland ToGraceAngYi-en,myblesseddaughter,for all the joy you bring. —Kah Phooi Seng To my parents and loved ones, for your unceasing support and love. —Li-minn Ang To Alana and Nicholas, my two lovely children, who bring me joy and headache. —Alan Liew Wee Chung To Zhi Chen, my lovely wife, and Henry Yu Gao, my amazing son, for your constant love and support. —Junbin Gao Preface Thedigitalagebringsmoderndataacquisitionmethodswhichallowthegatheringof different types and modes of data in variety and volume (termed in this book as multimodalBigData)tobeusedasmultipleinputsourcesintoincreasinglysophis- ticated computing systems deploying intelligent techniques and machine-learning abilities to find hidden patterns embedded in combined data. Some examples of different types of data modalities include text, speech, image, video, and sensor- baseddata.Thedatatypescouldoriginatefromvarioussourcesrangingfromsocial medianetworkstowirelesssensorsystemsandcouldbeintheformofstructuredor unstructured data. Big Data techniques are targeted toward large system-level problems that cannot be solved by conventional methods and technologies. The advantage of utilizing multimodal Big Data is that it facilitates a comprehensive view of information and knowledge as it allows data to be integrated, analyzed, modeled,andvisualizedfrommultiplefacetsandviewpoints. While the use of multimodal data gives increased information-rich content for informationandknowledgeprocessing,itleadstoanumberofadditionalchallenges in terms of scalability, decision-making, data fusion, distributed architectures, and predictive analytics. Addressing these challenges requires new approaches for data collection,transmission,storage,andinformationprocessingfromthemultipledata sources.TheaimofthisbookistoprovideacomprehensiveguidetomultimodalBig Data technologies and analytics and introduce the reader to the current state of multimodal Big Data information processing. We hope that the reader will share ourenthusiasminpresentingthisvolumeandwillfindituseful. Intended Audience The target audience for this book is very broad. It includes academic researchers, scientists, lecturers, and advanced students and postgraduate students in various disciplineslikeengineering,informationtechnology,andcomputerscience.Itcould vii viii Preface be an essential supportfor fellowship programs in BigDataresearch. This bookis alsointendedforconsultants,practitioners,andprofessionalswhoareexpertsinIT, engineering, and business intelligence to build decision support systems. The fol- lowing groups will also benefit from the content of the book: scientists and researchers, academic and corporate libraries, lecturers and tutors, postgraduates, practitionersandprofessionals,undergraduates,etc. ACT,Australia KahPhooiSeng GoldCoast,Australia Li-minnAng GoldCoast,Australia AlanWee-ChungLiew Sydney,Australia JunbinGao Acknowledgments We express our deepest appreciation to all the people who have helped us in the completionofthisbook.Wethankallthereviewersofthebookfortheirtremendous service bycritically reviewing thechapters and offeringuseful suggestions, partic- ularly Ch’ng Sue Inn, Chew Li Wern, and Md Anisur Rahman. We gratefully acknowledgeourSpringereditorRonanNugentandthepublicationteam,fortheir diligenteffortsandsupporttowardthepublicationofthisbook. KahPhooiSeng Li-minnAng AlanWee-ChungLiew JunbinGao ix Contents PartI Introduction 1 MultimodalInformationProcessingandBigDataAnalytics inaDigitalWorld. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 KahPhooiSeng,Li-minnAng,AlanWee-ChungLiew, andJunbinGao PartII Sentiment,AffectandEmotionAnalysisforBig MultimodalData 2 Speaker-IndependentMultimodalSentimentAnalysis forBigData. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 ErikCambria,SoujanyaPoria,andAmirHussain 3 MultimodalBigDataAffectiveAnalytics. . .. . . . . . . .. . . . . . . .. . 45 NusratJahanShoumy,Li-minnAng,andD.M.MotiurRahaman 4 HybridFeature-BasedSentimentStrengthDetection forBigDataApplications. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 73 YanghuiRao,HaoranXie,FuLeeWang,LeonardK.M.Poon, andEndongZhu PartIII UnsupervisedLearningStrategiesforBigMultimodalData 5 MultimodalCo-clusteringAnalysisofBigDataBased onMatrixandTensorDecomposition. . . . . . . . . . . . . . . . . . . . . . . 95 HongyaZhao,ZhenghongWei,andHongYan 6 Bi-clusteringbyMulti-objectiveEvolutionaryAlgorithm forMultimodalAnalyticsandBigData. . . . . . . . . . . . . . . . . . . . . . 125 MaryamGolchinandAlanWee-ChungLiew 7 UnsupervisedLearningonGrassmannManifoldsforBigData. . . . 151 BoyueWangandJunbinGao xi xii Contents PartIV SupervisedLearningStrategiesforBigMultimodalData 8 Multi-productNewsvendorModelinMulti-taskDeepNeural NetworkwithNormRegularizationforBigData. . . . . . . . . . . . . . 183 YanfeiZhang 9 RecurrentNeuralNetworksforMultimodalTimeSeries BigDataAnalytics. . .. . . . .. . . .. . . .. . . .. . . .. . . .. . . . .. . . .. 207 MingyuanBaiandBoyanZhang 10 ScalableMultimodalFactorizationforLearningfromBigData. . . 245 QuanDoandWeiLiu PartV MultimodalBigDataProcessingandApplications 11 BigMultimodalVisualDataRegistrationforDigitalMedia Production. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 271 HansungKimandAdrianHilton 12 AHybridFuzzyFootballScenesClassificationSystemforBig VideoData. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 299 SongWeiandHaniHagras 13 MultimodalBigDataFusionforTrafficCongestionPrediction. . . . 319 TaiwoAdetiloyeandAnjaliAwasthi 14 ParallelandDistributedComputingforProcessingBigImage andVideoData. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 337 PraveenKumar,ApekshaBodade,HarshadaKumbhare, RuchitaAshtankar,SwapnilArsh,andVatsalGosar 15 MultimodalApproachesinAnalysingandInterpretingBigSocial MediaData. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 361 EugeneCh’ng,MengdiLi,ZiyangChen,JingboLang,andSimonSee

See more

The list of books you might like

Most books are stored in the elastic cloud where traffic is expensive. For this reason, we have a limit on daily download.