Comparative Study Between Neural Network And Statistic In Handwritten Digit Recognition

Neural network is one of the most Artificial Intelligent techniques. It has been implemented in various applications ranging from non technical applications to highly technical applications. The ability of neural network was originally inherited from statistical models such as regression. Handwritt...

Full description

Saved in:

Bibliographic Details
Main Author:	Noor Azliza, Sabri
Format:	Thesis
Language:	eng eng
Published:	2004
Subjects:	T Technology (General)
Online Access:	https://etd.uum.edu.my/1382/1/NOOR_AZLIZA_BT._SABRI.pdf https://etd.uum.edu.my/1382/2/1.NOOR_AZLIZA_BT._SABRI.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-uum-etd.1382
record_format	uketd_dc
institution	Universiti Utara Malaysia
collection	UUM ETD
language	eng eng
topic	T Technology (General)
spellingShingle	T Technology (General) Noor Azliza, Sabri Comparative Study Between Neural Network And Statistic In Handwritten Digit Recognition
description	Neural network is one of the most Artificial Intelligent techniques. It has been implemented in various applications ranging from non technical applications to highly technical applications. The ability of neural network was originally inherited from statistical models such as regression. Handwritten recognition is one of the promising domains for neural network. Many studies have shown the success and efficacy of neural network in handwritten recognition. Yet, less study compares the performance of neural network and statistical method. Hence, this study aims to compare the generalization performance of neural network and statistical model in handwriting recognition domain. The results obtained are compared and presented in this paper. Multilayer Perceptron is chose as neural network model and Multiple Nonlinear Regression as statistic model. The result (percentage of correctness) indicated that neural network model is better in generalization than the statistic model. A total of 768 datasets was used for training. Neural network has produced a higher generalization value if compared to statistic which is 94.98% and 78.7% respectively.
format	Thesis
qualification_name	masters
qualification_level	Master's degree
author	Noor Azliza, Sabri
author_facet	Noor Azliza, Sabri
author_sort	Noor Azliza, Sabri
title	Comparative Study Between Neural Network And Statistic In Handwritten Digit Recognition
title_short	Comparative Study Between Neural Network And Statistic In Handwritten Digit Recognition
title_full	Comparative Study Between Neural Network And Statistic In Handwritten Digit Recognition
title_fullStr	Comparative Study Between Neural Network And Statistic In Handwritten Digit Recognition
title_full_unstemmed	Comparative Study Between Neural Network And Statistic In Handwritten Digit Recognition
title_sort	comparative study between neural network and statistic in handwritten digit recognition
granting_institution	Universiti Utara Malaysia
granting_department	Sekolah Siswazah
publishDate	2004
url	https://etd.uum.edu.my/1382/1/NOOR_AZLIZA_BT._SABRI.pdf https://etd.uum.edu.my/1382/2/1.NOOR_AZLIZA_BT._SABRI.pdf
_version_	1747827134853808128
spelling	my-uum-etd.13822013-07-24T12:11:43Z Comparative Study Between Neural Network And Statistic In Handwritten Digit Recognition 2004-03-28 Noor Azliza, Sabri Sekolah Siswazah Sekolah Siswazah T Technology (General) Neural network is one of the most Artificial Intelligent techniques. It has been implemented in various applications ranging from non technical applications to highly technical applications. The ability of neural network was originally inherited from statistical models such as regression. Handwritten recognition is one of the promising domains for neural network. Many studies have shown the success and efficacy of neural network in handwritten recognition. Yet, less study compares the performance of neural network and statistical method. Hence, this study aims to compare the generalization performance of neural network and statistical model in handwriting recognition domain. The results obtained are compared and presented in this paper. Multilayer Perceptron is chose as neural network model and Multiple Nonlinear Regression as statistic model. The result (percentage of correctness) indicated that neural network model is better in generalization than the statistic model. A total of 768 datasets was used for training. Neural network has produced a higher generalization value if compared to statistic which is 94.98% and 78.7% respectively. 2004-03 Thesis https://etd.uum.edu.my/1382/ https://etd.uum.edu.my/1382/1/NOOR_AZLIZA_BT._SABRI.pdf application/pdf eng validuser https://etd.uum.edu.my/1382/2/1.NOOR_AZLIZA_BT._SABRI.pdf application/pdf eng public masters masters Universiti Utara Malaysia Adznan, B. J. and Tan, C.L. (2003). Speech Recognition using Formant Analysis and Neural Network. Malaysia - Japan Seminar on Artificial Intelligence Applications in Industry (AIAI 2003), Kuala Lumpur. Ahmad, K. and Suradi, W. (2001). Pengecaman Tulang Melalui Kaedah Rangkaian. National Artificial Intelligent Seminar (AIS 200 I), Malaysia. Aksela, M. (2000). Handwritten Character Recognition: A Palm Top Implementation and Adaptive Committee Experiments. Master's Thesis, Helsinki University of Technology. Alias, A. J., AhMad, I., and Muad, A.M. (2000). Pendekatan Rangkaian Neural di dalam Pengesanan Kecacatan Bagi Teknik Tanpa Musnah. Prosiding Simposium Teknologi Maklumat (ITSim'2K), Malaysia, pp. 29-37. Alimoglu, F. (1994). Combining Multiple Representation and Classifiers Pen-based Hanhvritten Digit Recognition. M.Sc Thesis, Bogazici University, Turkey. Al-Jumaily, A. A., Taib, M.Z., and Shahrim, M. R. (2002). Neural Network Based Recognition Engine for Car Plate Recognition System. International Conference on AI in Engineering and Technology (ICAIET-2002), Malaysia, pp. 298-304. AlNaqeeb A.A (2001). Color Recognition Using Neural Network. National Artificial Intelligent Seminar (AIS 2001), Malaysia. Arjunan, S., Deris, S., Illias, R.M., and Mohamad, M.S. (2003). A Parallelizing Interface for K-Means Type Clustering Algorithms and Neural Network Batch Training (I). Malaysia-Japan Seminar on Artificial Intelligence Applications in Industry (AIM 2003), Kuala Lumpur. Bahlmann, C., Bockhorn, D., Triebel R. and Simon, K. (2003). Frog On Hand. Online: http://lmb.informatik.uni-fieiburg.de/people/bahlmandog.en.html.Accessed date:13" November, 2003. Breuel M. T. (1993). Recognition of Hand printed Digits using Optimal Bounded Error Matching. International Conference on Document Analysis and Retrieval (CDAR),Tsukuba Science City, Japan. Chan, K., F., and Yeung, D.,Y..(1999). Recognizing on-line handwritten alphanumeric characters through flexible structural matching. Pattern Recognition, 32(7). pp. 1099-1114. Chan, K., F., Yeung, D.,Y. (2001). Pen Calc: a novel application of on-line mathematical expression recognition technology. Proceedings of the Sixth International Conference on Document Analysis and Recognition. pp.774-778. Cheung, K.,W., Yeung, D.,Y., and Chin. R.,T. (2002). Bidirectional deformable matching with application to handwritten character extraction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(8). pp. 1133-1139. Cheung, K.,W., Yeung, D., Y., and Chin. R.,T., (1998). A Bayesian framework for deformable pattern recognition with application to handwritten character recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(12). pp. 1382-1388. Duin, P.,W.,R, and Pekalska, E. (2001).Automatic Pattern Recognition By Similarity Representations A Novel Approach. Online: http://citeseer.ist.psu.edu/pekalska01automatic.html. Accessed date 12 & January 2004. Dyer, C., C., and Ip, S., S., P. (2000). An Elementary Introduction to Scientific Computing. Online: http://pathfinder.scar.utoronto.ca/-dyer/csca57lbook-Plbook .html. Accessed date: 15th January 2004. Elfadil N., Salami, M., J., E., Khalil., M., Nor, M., S. (2002). Disk Performance Recognition Using Kohonen Self-organizing Neural Networks & Expert System. International Conference 2002, Malaysia. Hanafi, D. and Rahmat, M.F. (2003). System Identification of Nonlinear Model of A Quarter Car Passive Suspension with Back propagation Neural Network. Malaysia - Japan Seminar on Artificial Intelligence Applications in Industry (AIAI 2003), Kuala Lumpur. Hinton, G. E., Dayan, P., and Revow, M. (1995). Recognizing Handwritten Digits Using Mixtures of Linear Models. Advances in Neural Information Processing Systems Vol(7) MIT Press, Cambridge University, pp. 1015-1022. Hinton, G. E., Dayan P., and Revow, M. (1997). Modeling the Manifolds of Images of Handwritten Digits. IEEE Transactions on Neural Networks Vol (8). Toronto, Canada, pp. 65-74. Hitam, M.S., Muslan, M.Y.H., and Deris, M. M. (2003). Image Texture Classification Using GLCM, Projection and Neural Network. Malaysia - Japan Seminar on Artificial Intelligence Applications in Industry (AIM 2003), Kuala Lumpur. Husin, S. S. F., Khalid, M., and Yusof, R. (2002). Design of and Intelligent License Plate Recognition System : USIONPLATE II. International Conference on A1 in Engineering and Technology (ICAIET-2002), Malaysia, pp. 305-310. Hani, A. F. M. and Irfan, A. R. (2003). Face Recognition using MYKAD Security (I). Malaysia - Japan Seminar on Artificial Intelligence Applications in Industry (AIAI 2003), Kuala Lumpur. Haykin, S . (1999). Neural Networks: A Comprehensive Foundation, 2nd Edition, New Jersey: Prentice Hall. Ishak, W., H., W., and Rahman, A., S. (2003). Neural Network in Handwritten Recognition System: A Survey. Seminar ICT Kebangsaan, Arau, pp. 132-140. Janahiraman, T., Tay, Y. H., Khalid, M., and Yusof, R. (2002). Classification of Handwritten Digits Using Geometrical and Topological Feature Extraction Technique And Neural Network. International Conference on AI in Engineering and Technology (ICAIET-2002), Malaysia, pp. 291-297. Junoh, M.Z.H.M. and Siraj, F. (2001). Evaluating Multilayer Perception and Multiple Regression On Breast Cancer. National Artificial Intelligence Seminar (AIS 2001), Malaysia. Kaastra, I. and Boyd, M. (1996) Designing a Neural Network for Forecasting Financial and Economic Time Series. Neurocomputing 10:215-236. Elsevier Science B.K Khalid, M.A., Muad, A.M., Muhamad, A.A., Hamzah, A.R., and Ghazali, A.B. (1999). Recognition of Welding Defects on Radio graphic Films Using Image Processing and Neural Network. Proceedings of The First National conference on Artificial Intelligence In Industry (AIAI'99), Kuala Lumpur, pp. 16-25. Kuan, M., M., Lim, C.P., Ismail, O., Yuvaraj, R.M., and Singh, I. (2002). Application of Artificial Neural Network to Diagnose of Acute Coronary Syndrome. International Conference on AI in Engineering and Technology (ICAIET-2002), Malaysia. Lay, C.B., Khalid, M., and Yusof, R. (1999). Intelligent Database by Neural Network and Data Mining. Proceedings of The First National conference on Artificial Intelligence In Industry (AIAI'99), Kuala Lumpur. pp.201-219. Laaksonen, J., Aksela, M., Oja, E., and Kangas, J. (1999) Dynamically Expanding Context as Committee Adaptation Method in On-line Recognition of Handwritten Latin Characters. Proceedings of ICDAR '99, India. pp. 489-497. Laaksonen, J., Hurri, J., Oja, E., and Kangas, J. Comparison of Adaptive Strategies for On-Line Character Recognition. Proceedings of ICDAR'99. pp. 245-250. Laaksonen, J., Hurri, J., Oja, E., and Kangas, J. (1998). Experiments with a Self-Supervised Adaptive Classification Strategy in On-Line Recognition of isolated Handwritten Latin Characters. Proceedings of IWFHR98, Korea. pp.475-484. Lazim, M.M., Sap, M.N.M., and Mohamad, D. (1990). Pengecaman Tulisan Tangan: Keperluan Sistem dan Satu Pendekatan Terhadap Penyelesaian Deterministik. Jurnal Teknologi Maklumat 1 (I), pp. 44-53. LeCun, Y., Jackel, L., Bottou, L., Brunot, A., Cortes, C., Denker, J., Drucker, H., Guyon,I., Muller, U., Sackinger, E., Simard, P., and Vapnik V. (1995). Comparison of Learning Algorithm For Handwritten Digit Recognition. Holmdel, USA. LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E, Hubbard, W., and Jackel, L .D. (1 990). Handwritten Digit Recognition with a Back-Propagation Network. Holmdel, USA, pp. 396-404. Lee, N. K., Wang, D. H., and Tan, K. W. (2003). Protein Classification Using Neural Networks : A Review. Malaysia - Japan Seminar on Artificial Intelligence Applications in Industry (AIAI 2003), Kuala Lumpur. Liam, L.W., Chekima, A., Dargham, J.A., and Fan, L.C. (2002). Iris Recognition Using Self-Organizing Neural Network. International Conference on AI in Engineering and Technology (ICAIET-2002), Malaysia. Lim, P.C., Woo, S. C., and Osman, R. (2002). Classification of Speech Signals using Supervised ART-Based Neural Networks. International Conference on AI in Engineering and Technology (ICAET-2002), Malaysia. LiminFu (1994). Knowledge discovery based on neural networks. Neural Network In Computer Intelligence, New York. pp.47-50. Phokaratkul, P., Suedsanit, T., Pantaragphong, P., Pinngern, O., and Kimpan, C. (2002). Printed Thai Characters Recognition Using Rough Classification. International Conference on AI in Engineering and Technology (ICAIET-2002), Malaysia, pp. 284-290. Pofahl, W.E., Walczak, S.M., Rhone, E., and Izenberg, S.D. (1998) Use of an artificial neural network to predict length of stay in acute pancreatic. American Surgeon, pp. 868-872. Ramachandram, D. and Rajeswari, M. (2003). A Short Review of Neural Network Techniques in Visual Serving of Robotic Manipulators. Malaysia - Japan Seminar on Artificial Intelligence Applications in Industry (AIAI 2003), Kuala Lumpur. Rashid, R., Jamaluddin, H., and Arnin, N.A. S. (2003). Application of Multi-Layer Perceptron in Modeling Tapioca Starch Hydrolysis. Malaysia - Japan Seminar on Artificial Intelligence Applications in Industry (AIAI 2003), Kuala Lumpur. Saxena, I., Moerland, P., Fiesler, E., and Pourzand, A. (1 997). Handwritten Digit Recognition with Binary Optical Perception. Proceedings of the International Conference on Artificial Neural Networks (ICANN'97). Online: http://www.alltheweb.corn/r?ck~sm=3379f3&rpos=&lrpge=l &ref=200320086&r/ http://www.idiap.ch/-perry/saxena-97.3.bib.abs.html. Accessed date: 13 & November, 2003. Sarle, W. S. (1994a). Neural Network and Statistical Models. Proceedings of the Nineteenth Annual SAS Users Group International Conference, Cary, NC :SAS Institute, pp. 1538-1580. Sarle, W. S. (1994b). Neural Network Implementation in SAS Software. Proceedings of the Nineteenth Annual SAS Users Group International Conference, Cary, NC : SAS Institute. Stergiou, C., and Siganos, D., (1996) Neural Networks, Volume 4. Seni, G. (1995). Large Vocabulary of on-line Handwritten Cursive Word. Ph.D. Dissertation, Cambridge University. Siraj, F., Zakaria, A., Aziz, A. A., and Abas, Z. (2003). UZBIC: A Web Based Business Insolvency Classifier Using Neural Networks (I). Malaysia - Japan Seminar on Artificial Intelligence Applications in Industry (AIAI 2003), Kuala Lumpur. Sordo, M., Fox, J.&lum, C., Taylor, P. Lee, R. and Alberdi, E. (2001). Combining decision support and image processing: a PRO formal model. Proceedings of the Tenth World Congress on Health and Medical Informatics (medinfo200I), London. Sulaiman, S., Osman, M. R ., and Ahmad, M.M.H.M. (2003). Development of a Knowledge-based Feature Recognition System for Mechanical Parts. Malaysia - Japan Seminar on Artificial Intelligence Applications in Industry (AIAI 2003), Kuala Lumpur. Tsoukalas, L. H., and Uhrig R. E., (1997) Fuzzy and Neural Approaches in Engineering, John Wiley & Sons, Inc. Turban, E., (1993) Decision Support and Expert Systems: Management Support Systems, Macmillan Publishing Company. Vuori, V. (2002). Adaptive Method for On-Line Recognition of Isolated Handwritten Characters. Doctoral Thesis, Helsinki University of Technology. Vuori, V., Laaksonen, J., Oja, E., Kangas, J. (2001). Speeding up On-line Recognition of Handwritten Characters by Pruning the Prototype Set. Proceedings of ICDAR'0I, pp. 501-505, Seattle, USA. Vuori, V. and Oja, E. (2000). Analysis of Different Writing Styles with Self-Organizing Map. Proceedings of the ICONIP2000, volume (2), pp. 1243-1247, Taejon, South Korea. Vuori, V., Aksela, M., Laaksonen, J., Oja, E. and Kangas, J. (2000). Adaptive character recognizer for hand held device: implementation and evaluation setup. Proceedings of the IWFHR2000. Amsterdam, Netherlands. pp. 13-22. Vuori, V., Laaksonen, J., Oja., E., Kangas, J. (1999). On-line Adaptation in Recognition of Handwritten Alphanumeric Characters. Proceeding of ICDAR '99, India. Wahap, A. R., Khalid, M., Ahmad, A. R., and Yusof, R. (2002). A Neural Network Based Bank Cheque Recognition system for Malaysian Cheques. International Conference on AI in Engineering and Technology (ICAIET-2002), Malaysia, pp.273-279. Yusof, K. M., Idris, A., and Morad, N. A. (2003). Artificial Neural Network Modeling of Steady-state Chemical Engineering Systems. Malaysia - Japan Seminar on Artificial Intelligence Applications in Industry (AIAI 2003), Kuala Lumpur. Zin, Z. M., Salleh, S.H.S., and Sulaiman, M.D. (2003). Classifications of Mistral Regurgitation and Normal Heart Sounds based on Artificial Neural Network and Wavelet. Malaysia - Japan Seminar on Artificial Intelligence Applications in Industry (AIAI 2003), Kuala Lumpur.

Comparative Study Between Neural Network And Statistic In Handwritten Digit Recognition

Similar Items