001484266 000__ 05708cam\\22006377i\4500
001484266 001__ 1484266
001484266 003__ OCoLC
001484266 005__ 20240117003318.0
001484266 006__ m\\\\\o\\d\\\\\\\\
001484266 007__ cr\cn\nnnunnun
001484266 008__ 231125s2023\\\\si\\\\\\ob\\\\000\0\eng\d
001484266 019__ $$a1410591900
001484266 020__ $$a9789819974429$$qelectronic book
001484266 020__ $$a9819974429$$qelectronic book
001484266 020__ $$z9819974410
001484266 020__ $$z9789819974412
001484266 0247_ $$a10.1007/978-981-99-7442-9$$2doi
001484266 035__ $$aSP(OCoLC)1410562029
001484266 040__ $$aYDX$$beng$$erda$$cYDX$$dOCLCO$$dGW5XE$$dEBLCP$$dYDX$$dOCLCO
001484266 049__ $$aISEA
001484266 050_4 $$aQ325.5$$b.S26 2023
001484266 08204 $$a006.3/1$$223/eng/20231207
001484266 1001_ $$aSantosh, K. C.
001484266 24510 $$aActive learning to minimize the possible risk of future epidemics /$$cKC Santosh, Suprim Nakarmi.
001484266 264_1 $$aSingapore :$$bSpringer,$$c2023.
001484266 300__ $$a1 online resource
001484266 336__ $$atext$$btxt$$2rdacontent
001484266 337__ $$acomputer$$bc$$2rdamedia
001484266 338__ $$aonline resource$$bcr$$2rdacarrier
001484266 4901_ $$aComputational intelligence
001484266 504__ $$aIncludes bibliographical references.
001484266 5050_ $$aIntro -- Foreword -- Preface -- Contents -- About the Authors -- Acronyms -- 1 Introduction -- 1.1 Background -- 1.2 Summary -- References -- 2 Active Learning-What, When, and Where to Deploy? -- 2.1 Background -- 2.2 Active Learning Scenarios -- 2.2.1 Membership Query Synthesis -- 2.2.2 Stream-Based Selective Sampling -- 2.2.3 Pool-Based Sampling -- 2.3 Query Strategies for AL -- 2.3.1 Uncertainty Sampling -- 2.3.2 Query by Disagreement -- 2.3.3 Query by Committee -- 2.3.4 Estimated Error Reduction -- 2.3.5 Variance Reduction and Fisher Information Ratio -- 2.3.6 Density-Weighted Methods
001484266 5058_ $$a2.4 When and Where to Deploy -- 2.5 Summary -- References -- 3 Active Learning-Review -- 3.1 Background -- 3.2 Querying Techniques -- 3.3 Existing Custom Querying Techniques -- 3.4 Used Cases-Medical Imaging Informatics -- 3.5 Challenges -- 3.6 Summary -- References -- 4 Active Learning-Methodology -- 4.1 Background -- 4.2 Typical Machine Learning (ML) Models -- 4.2.1 Shallow Learning -- 4.2.2 Deep Learning -- 4.3 How Big Data is Big Enough to Begin With? -- 4.4 Active Learning Versus Passive Learning -- 4.5 Implementation-The Proposed AL Framework -- 4.5.1 Introducing Mentoring to ML Models
001484266 5058_ $$a4.5.2 Unsupervised Learning/Clustering -- 4.5.3 K-way n-Shot Learning -- 4.6 Summary -- References -- 5 Active Learning-Validation -- 5.1 Background -- 5.2 Datasets -- 5.2.1 Cough Dataset -- 5.2.2 Chest CT Scans -- 5.2.3 Chest X-rays (CXRs) -- 5.3 Evaluation Metrics -- 5.3.1 Unsupervised Clustering -- 5.3.2 Classification -- 5.4 Validation -- 5.5 Summary -- References -- 6 Case Study #1: Is My Cough Sound Covid-19? -- 6.1 Data Preparation -- 6.2 Results -- 6.2.1 Clustering -- 6.2.2 Classification -- 6.2.3 Comparison -- 6.3 Summary -- References -- 7 Case Study #2: Reading/Analyzing CT Scans
001484266 5058_ $$a7.1 Data Preparation -- 7.2 Results -- 7.2.1 Clustering -- 7.2.2 Classification -- 7.2.3 Comparison -- 7.3 Summary -- References -- 8 Case Study #3: Reading/Analyzing Chest X-rays -- 8.1 Data Preparation -- 8.2 Results -- 8.2.1 Clustering -- 8.2.2 Classification -- 8.2.3 Comparison -- 8.3 Summary -- References -- 9 Summary and Take-Home Messages -- 9.1 Background -- 9.2 Summary -- 9.3 Take-Home Message -- References
001484266 506__ $$aAccess limited to authorized users.
001484266 520__ $$aFuture epidemics are inevitable, and it takes months and even years to collect fully annotated data. The sheer magnitude of data required for machine learning algorithms, spanning both shallow and deep structures, raises a fundamental question: how big data is big enough to effectively tackle future epidemics? In this context, active learning, often referred to as human or expert-in-the-loop learning, becomes imperative, enabling machines to commence learning from day one with minimal labeled data. In unsupervised learning, the focus shifts toward constructing advanced machine learning models like deep structured networks that autonomously learn over time, with human or expert intervention only when errors occur and for limited dataa process we term mentoring. In the context of Covid-19, this book explores the use of deep features to classify data into two clusters (0/1: Covid-19/non-Covid-19) across three distinct datasets: cough sound, Computed Tomography (CT) scan, and chest x-ray (CXR). Not to be confused, our primary objective is to provide a strong assertion on how active learning could potentially be used to predict disease from any upcoming epidemics. Upon request (education/training purpose), GitHub source codes are provided.
001484266 588__ $$aOnline resource; title from PDF title page (SpringerLink, viewed December 7, 2023).
001484266 650_6 $$aApprentissage automatique.
001484266 650_6 $$aExploration de données (Informatique)
001484266 650_6 $$aÉpidémiologie$$xInformatique.
001484266 650_0 $$aMachine learning.$$vCongresses$$0(DLC)sh2008107143
001484266 650_0 $$aData mining.$$vCongresses$$0(DLC)sh2008102035
001484266 650_0 $$aEpidemiology$$xData processing.$$xEpidemiology$$0(DLC)sh2009114520
001484266 655_0 $$aElectronic books.
001484266 7001_ $$aNakarmi, Suprim.
001484266 77608 $$iPrint version: $$z9819974410$$z9789819974412$$w(OCoLC)1397313128
001484266 830_0 $$aSpringerBriefs in applied sciences and technology.$$pComputational intelligence.
001484266 852__ $$bebk
001484266 85640 $$3Springer Nature$$uhttps://univsouthin.idm.oclc.org/login?url=https://link.springer.com/10.1007/978-981-99-7442-9$$zOnline Access$$91397441.1
001484266 909CO $$ooai:library.usi.edu:1484266$$pGLOBAL_SET
001484266 980__ $$aBIB
001484266 980__ $$aEBOOK
001484266 982__ $$aEbook
001484266 983__ $$aOnline
001484266 994__ $$a92$$bISE