Abstract   Most  expert  system  designers  suffer  from  knowledge   acquisition  complications.  Expert  system  shells  contain  facilities  that  can  simplify  knowledge  acquisition  to  make  domain  experts  themselves  responsible  for  k nowledge  structuring  and  encoding.  The  aim  of  this  research  is  to  develo p  an  Arabic  Expert  System  Shell  (AESS)  for  diagnosi ng diseases  based  on  natural language. The suggested AESS mainly consist s of two phases. The first phase is responsible for automatic acquiring of  human  expert  knowledge.  The  acquired  knowledge  is  a nalyzed  by  Arabic  morphological  system.  The  Arabic morphological  system  analyzes  the  given  Arabic  phrase  and  finds  t he  required  keywords  (roots).  The  suggested  system  is  provided  with  the  required domain dictionary to be used by the Arabic  morphological system. The second phase is concerne d with the design of  inference  engine  together  with  user  interface  (base d  on  natural  language)  that  uses  a  backward  chainin g  method  (end-user  interface).When  AESS  tested  by  experts  and  end  user s,  it  was  found  that  AESS  performance  in  constructing  Knowledge-Base  (KB) and diagnosing problems was very exact (the di agnostic ability of AESS is 99%.). Merging of morphological system with  knowledge  acquisition  is  very  effective  in  construc ting  the  target  KB  without  any  duplicate  or  inconsi stent  rules.  The  same  technique  could  be  used  to  build  expert  system  shel l  based  on  any  other  natural  language  (English,  Fre nch,  etc.).  The  only  difference is to build morphological system suitabl e to that language in addition to the desired domai n dictionary.   

References

[1] Al khateeb I., Design and Implementation of Diagnosing Expert System Shell, MSc Thesis, Department of Computer Science, Al Nahrain University, 2002.

[2] Al kholy A., sw Yr s~ur swukV I {N V , ur vOr k VPr , Jordan, 1999.

[3] Al mashhadany K., Building Diagnoses Expert System Shell Using Arabic Interface, MSc Thesis , Department of Computer Science, Al Nahrain University, 2005.

[4] Al muhtaseb H. and Aref M., Khabeer As A Machine Translation Tool, in Proceedings of the 1 st Workshop on Information and Computer Science , Saudi Arabia, pp. 101 109, 1996.

[5] Bing X., Kham N., Long N., Schwartz R., and Makhoul J., Morphological Decomposition for Arabic Broadcast News Transcription, in Proceedings of IEEE International Conference on Acoustic , Speech , and Signal Processing , France, pp. 1089 1092, 2006.

[6] Efraim T. and Jay A., Decision Support System and Intelligent Systems , NJ, A Simon and Schuster Company, 1998.

[7] El sadany A. and Hashish A., An Arabic Morphological System, IBM System Journal, vol. 28, no. 4, pp. 600 612, 1989.

[8] Essam A. and Abdullah B., A Framework to Automate the Parsing of Arabic Language Sentences, The International Arab Journal of Information Technology , vol. 6, no. 2, pp. 191 195, 2009.

[9] George L., Artificial Intelligence: Structures and Strategies for Complex Problem Solvin g, Addison Wesley Longman, 2008.

[10] Hadi N., l] Vr r , sk P or sYWJ r , Baghdad, 1989.

[11] Hussein O., Monzer Q., and Hazim F., Framework Model for Shell Expert System, International Journal of Computer Science and Network Security , vol. 9, no. 11, pp. 56 68, 2009.

[12] Imam R., J r JP W, s PKW J r , Lebanon, 1988.

[13] Jie Y., Chenzhou Y., and Xiaoli Z., An Expert System Shell for Fault Diagnosis, Journal of the International Federation of Robotics , vol. 19, no. 6, pp. 669 674, 2001.

[14] Joseph G. and Gary R., Expert Systems: Principles and Programming , Thomson Course Technology, 2004.

[15] Keith D., The Essence of Expert System , Pearson Education Limited, 2000.

[16] Kendal L. and Creen M., An Introduction to Knowledge Engineering , Springer Verlag London Limited, 2007.

[17] Kiong W., Abd latif R., Mohd Z., and Azwan A., Expert System in Real World Applications, available at: http://www.generation5.org/ content/2005/Expert_System.asp, last visited 2005.

[18] Laurie B., Introducing Linguistic Morphology , 2 nd Edition, Georgetown University Press, Washington, 2003.

[19] Moulana M., From the Treasures of Arabic Morphology , 1 st Edition, Academy for Islamic Research Madrasah In amiyyah, South Africa, 2006.

[20] Norlela I., Amiruddin I., and Riza A., An Overview of Expert Systems in Pavement Management, European Journal of Scientific Research , vol. 30, no. 1, pp. 99 111, 2009.

[21] Pamela G. and Xenogene G., A Map Based Expert Friendly Shell, Bourcier D., (ED.), in Proceedings of Legal Knowledge and Information Systems , Amsterdam, pp. 51 60, 2003.

[22] Ryding K., A Reference Grammar of Modern Standard Arabic , Cambridge University Press, UK, 2005. Venus Samawi is an assistant professor in Al albayt University, Department of Computer Science. Al albayt University, Jordan. She received her BSc from University of Technology at 1987, and the MSc, and PhD degrees from Computer Science Department in Al Nahrain University (Saddam University previously) at 1992 and 1999 respectivel y. She supervises three PhD students in system programming, pattern recognition, and network security. She also leads and teaches modules at BSc , MSc and PhD levels in computer science. She is a reviewer in IEEE conferences (ICIEA 2009 and 2011). Her special area of research is AI, neural networks , genetic algorithms, and image processing. Arabic Expert System Shell 75 Akram Mustafa received his the BSc degree in computer engineering in 1997, MSc degree in computer engineering in 1999 from the National Technical University of Ukraine. And PhD degree in computer engineering from the National Technical University of Ukraine in 2003. From 2001 to 2002, he was an instructor of Computer Science Department at Al Yarmouk University, and from 2004 up to now he is an assistant professor o f Computer Science Department at Al albayt University. He served as a chairman of the Department of Computer Science at Al albayt University and Department of Information System. His research interests include network, image processing, securi ty and artificial intelligence. Abeer Ahmad is lecturer in the Department Of Computer Science, AL Nahrain University, Iraq. She holds MSc degree in computer science from AL Nahrain University, 2005 and BSc in computer science from AL Nahrain University, in 2002. She gains the third Iraq scientific prize in 2002. She has more than 5 years of experience as lecturer . His research interests and AI and natural language processing.