A异Acat a B 6 AA1171111 B Category "B B凸B8 Fig. 1.1 Classification when the classes are(a) known and (b) unknown beforehand Biometrics(personal identification based on physical attributes of the face, iris, fingerprints, etc.) Machine vision(e. g, automated visual inspection in an assembly line) Character recognition [e. g, automatic mail sorting by zip code, automated check scanners at ATMs(automated teller machines) Document recognition(e.g, recognize whether an e-mail is spam or not, based on the message header and content) Computer-aided diagnosis [e. g, helping doctors make diagnostic decisions based on interpreting medical data such as mammographic images, ultrasound images, electrocardiograms(ECGs), and electroencephalograms(EEGs) Medical imaging [e.g, classifying cells as malignant or benign based on the results of magnetic resonance imaging(MRI)scans, or classify different emo- tional and cognitive states from the images of brain activity in functional MRI Speech recognition(e. g, helping handicapped patients to control machines) Bioinformatics(e. g, DNA sequence analysis to detect genes related to particul Remote sensing(e.g, land use and crop yield) Astronomy (classifying galaxies based on their shapes; or automated searches such as the Search for Extra-Terrestrial Intelligence (SETD) which analyzes radio telescope data in an attempt to locate signals that might be artificial i The methods used have been developed in various fields, often independently In statistics, going from particular observations to general descriptions is called nference, learning [i.e, using example(training) data] is called estimation, and classification is known as discriminant analysis(McLachlan 1992). In engineer g, classification is called pattern recognition and the approach is nonparametric and much more empirical (Duda et al. 2001). Other approaches have their origins n machine learning(Alpaydin 2010), artificial intelligence(Russell and Norvig 2002), artificial neural networks( Bishop 2006), and data mining(Han and Kamber 2006). We will incorporate techniques from these different emphases to give a more unified treatment( Fig. 1.2)• Biometrics (personal identification based on physical attributes of the face, iris, fingerprints, etc.) • Machine vision (e.g., automated visual inspection in an assembly line) • Character recognition [e.g., automatic mail sorting by zip code, automated check scanners at ATMs (automated teller machines)] • Document recognition (e.g., recognize whether an e-mail is spam or not, based on the message header and content) • Computer-aided diagnosis [e.g., helping doctors make diagnostic decisions based on interpreting medical data such as mammographic images, ultrasound images, electrocardiograms (ECGs), and electroencephalograms (EEGs)] • Medical imaging [e.g., classifying cells as malignant or benign based on the results of magnetic resonance imaging (MRI) scans, or classify different emo￾tional and cognitive states from the images of brain activity in functional MRI] • Speech recognition (e.g., helping handicapped patients to control machines) • Bioinformatics (e.g., DNA sequence analysis to detect genes related to particular diseases) • Remote sensing (e.g., land use and crop yield) • Astronomy (classifying galaxies based on their shapes; or automated searches such as the Search for Extra-Terrestrial Intelligence (SETI) which analyzes radio telescope data in an attempt to locate signals that might be artificial in origin) The methods used have been developed in various fields, often independently. In statistics, going from particular observations to general descriptions is called inference, learning [i.e., using example (training) data] is called estimation, and classification is known as discriminant analysis (McLachlan 1992). In engineer￾ing, classification is called pattern recognition and the approach is nonparametric and much more empirical (Duda et al. 2001). Other approaches have their origins in machine learning (Alpaydin 2010), artificial intelligence (Russell and Norvig 2002), artificial neural networks (Bishop 2006), and data mining (Han and Kamber 2006). We will incorporate techniques from these different emphases to give a more unified treatment (Fig. 1.2). Fig. 1.1 Classification when the classes are (a) known and (b) unknown beforehand 2 1 Introduction