Retrospective Look at Machine Learning Techniques for Consistent Pattern Recognition

Author(s)

Sucheta Bhowmick , Atif Ali Khan , Zameer Ahmad ,

Download Full PDF Pages: 40-47 | Views: 342 | Downloads: 109 | DOI: 10.5281/zenodo.5592749

Volume 10 - September 2021 (09)

Abstract

The main goal of example recognition is controlled or unassisted arranging. Of the various structures where pattern recognition is often discussed, this section examines and utilizes 50 relevant evaluations between 2014 and 2020. Recently, brain organizing strategies and approaches derived from quantifiable learning hypothesis have gotten greater attention. Design portrayal, highlight extraction and determination, bunch investigation, classifier plan and learning are some of the difficulties that should be considered while designing an acknowledgement framework. To summarize and examine some of the prominent approaches used in various phases of an example acknowledgement framework, and to identify cutting-edge research subjects and applications in this fascinating and challenging field. Various AI methods have brought pattern recognition systems quicker.

Keywords

Machine learning; neural network; pattern recognition; security; accuracy; classification  

References

i.       Boixader Ibáñez D. Special issue on pattern recognition techniques in data mining. PatternRecognitLett.2017;93:1–2.

ii.     Kumar S, Gao X, Welch I, et al. A machine learning based web spam filtering approach. In 2014 IEEE 30th International Conference on Advanced Information Networking and Applications (AINA), IEEE; 2014.p. 973–980.

iii.    Ermushev SA, Balashov A. A complex machine learning technique for ground target detectionandclassification.IntJApplEngRes.2017;11(1):158–161.

iv.     Wu J, Yinan Y, Chang H, et al. Deep multiple instance learning for image classification and auto-annotation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition;2014.p.3460–3469.

v.      Voyant C, Notton G, Kalogirou S, etal. Machine learning methods for solar radiation forecasting: are view. Renew Energ. 2017;105:569–582.

vi.     Tajbakhsh N, Suzuki K. Comparing two classes of end-to-end machine-learning models in lung nodule detection and classification: MTANN svs. CNNs. Pattern Recognit.2017;63:476–486.

vii.   Aginako N, Echegaray G, Martínez-Otzeta JM, et al. Iris matching by means of machine learningparadigms:anewapproachtodissimilaritycomputation.PatternRecognitLett.2017;91:60–64.

viii.  D’Addona DM, Ullah AS, Matarazzo D. Tool-wear prediction and pattern-recognition using artificial neural network and DNA-based computing.J Intell Manuf. 2017;28(6):1285–1301.

ix.     Gao G, Yang J, Jing XY, et al. Learning robust and discriminative low-rank representations for face recognition with conclusion. Pattern Recognit.2017;66:129–143.

x.      Iwana BK, Frinken V, Riesen K, et al. Efficient temporal pattern recognition by means of dissimilarity space embedding with discriminative prototypes. Pattern Recognit. 2017;64:268–276.

xi.     Mage L, Baati N, Nanchen A, et al. A systematic approach for thermal stability predictions ofchemicals and their risk assessment: Pattern recognition and compounds classification basedonthermaldecompositioncurves.ProcessSafEnvironProt.2017;110:43–52.

xii.   Naz S, Umar AI, Ahmad R, etal. Urdu Nastaliq recognition using convolutional–recursive deep learning. Neuro Computing. 2017;243:80–87.

xiii.  Uhlmann E, Pontes RP, Laghmouchi A, et al. Intelligent pattern recognition of a SLM machine process and sensor data. Procedia CIRP.2017;62:464–469.

xiv.   Peralta D, Triguero I, Garcia S, et al. On the use of convolutional neural networks for robust classification of multiple finger print captures.arXiv preprintarXiv.1703.07270,2017.

xv.    ChatterjeeA,BhatiaV,PrakashS.Anti-spooftouchless3Dfingerprintrecognitionsystemusingsingleshotfringeprojectionandbiospeckleanalysis.OptLasersEng.2017;95:1–7.

xvi.   Peralta D, Triguero I, García S, et al. Distributed incremental fingerprint identification withreduced database penetration rate using a hierarchical classification based on feature fusionandselection.KnowlBasedSyst.2017;126:91–103.

xvii. Zeng Y, Xu X, Shen D, et al. Traffic sign recognition using kernel extreme learning machines withdeepperceptualfeatures.IEEETransIntellTranspSyst.2017;18(6):1647–1653.

xviii.       Afridi MJ, Ross A, Shapiro EM. On automated source selection for transfer learning in convolutional neural networks.Pattern Recognit.2018;73:65–75.

xix.   Ahmed OB, Benois-Pineau J, Allard M, et al. Alzheimer’s disease neuro imaging initiative, recognition of Alzheimer’s disease and mild cognitive impairment with multimodal image-derived biomarkers and multiple kernel learning.Neuro-computing.2017;220:98–110.

xx.    Aslan MS, Hailat Z, AlafifT K, etal.Multi-channel multi-model feature learning for face recognition.Pattern Recognit Lett.2017;85:79–83.

xxi.   Ashfaq RR, Wang X-Z, Huang JZ, et al. Fuzziness based semi-supervised learning approach for intrusion detection system.InfSci(Ny). 2017;378:484–497.

xxii. Burlina P, Pacheco KD, Joshi N, et al. Comparing humans and deep learning performance for grading AMD: a study in using universal deep features and transfer learning for automated AMD analysis. ComputBiolMed.2017;82:80–86.

xxiii.       ColeJH, PoudelPPK, Tsagkrasoulis D,etal.Predictingbrainagewithdeeplearningfromrawimagingdataresultsinareliableandheritablebiomarker.Neuroimage.2017;163:115–124.

xxiv. Hu K, Yang W, Gao X. Microcalcification diagnosis in digital mammography using extreme learn-ingmachinebasedonhiddenMarkovtreemodelofdual-treecomplexwavelettransform.ExpertSystAppl.2017; 86:135–144.

xxv.  Kalyanam J, Katsuki T, Gert Lanckriet RG, et al. Exploring trends of nonmedical use of prescriptiondrugs and polydrug abuse in the Twitter sphere using unsupervised machine learning. AddictBehav.2017;65:289–295.

xxvi. Layouni M, Hamdi MS, Tahar S. Detection and sizing of metal-loss defects in oil and gas pipelinesusingpattern-adaptedwaveletsandmachinelearning.ApplSoftComput.2017;52:247–261.

xxvii.       Schnyer DM, Clasen PC, Gonzalez C, et al. Evaluating the diagnostic utility of applying a machinelearningalgorithmtodiffusiontensorMRImeasuresinindividualswithmajordepressivedisor-der.PsychiatrResNeuroimag.2017;264:1–9.

xxviii.     SánchezD,MelinP.Optimizationofmodulargranularneuralnetworksusinghierarchicalgeneticalgorithms for human recognition using the ear biometric measure. Eng Appl Artif Intell.2014;27:41–56.

xxix. SánchezD,MelinP,CastilloO.Optimizationofmodulargranularneuralnetworksusingafireflyalgorithmforhumanrecognition.EngApplArtifIntell.2017;64:172–186.

xxx.  Melin P, Sanchez D. Multi-objective optimization for modular granular neural networks appliedtopatternrecognition.InfSci(Ny).2018;460-461:594–610.

xxxi. Yan Z, Yiqiang Z, Zhigang P, et al. Multi-instance deep learning: discover discriminative localanatomiesforbodypartrecognition.IEEETransMedImaging.2014;35:1502–1343.

xxxii.       HadidA,HeikkilaJY,SilvénO,etal.Faceandeyedetectionforpersonauthenticationinmobilephones. 2007 First ACM/IEEE International Conference on Distributed Smart Cameras; 2007.p.101–108.

xxxiii.     Tao Q, Veldhuis R. Biometric authentication system on mobile personal devices. IEEE TransInstrumMeas.2010;59(4):763–773.

xxxiv.      Xi K, Hu J, Han F. Mobile device access control: an improved correlation based face authenticationschemeanditsjavameapplication.ConcurrComp-PractE.2012;24(10):1066–1085.

xxxv.FindlingRD,HölzlM,MayrhoferR.Mobilematch-on-cardauthenticationusingoffline-simplifiedmodels withgait andface biometrics.IEEE TransMob Comput.2018;17(11):2578–2590.

xxxvi.      Chen S, Pande A, Mohapatra P. Sensor-assisted facial recognition: an enhanced biometricauthentication system for smartphones. Proceedings of the 12th Annual International Confer-enceonMobileSystems,Applications,andServices;2014.p.109–122.

xxxvii.     Monté-RubioGC,FalcónC,Pomarol-ClotetE,etal.AcomparisonofvariousMRIfeaturetypesforcharacterizingwholebrainanatomicaldifferencesusinglinearpatternrecognitionmethods.NeuroImage.2018;178:753–768.

Cite this Article: