A Self-organized Multi Agent Decision Making System Based on Fuzzy Probabilities: The Case of Aphasia Diagnosis

Document Type: Research Paper

Authors

Electrical Engineering Department, Ferdowsi University of Mashhad, Mashhad, Iran

Abstract

Aphasia diagnosis is a challenging medical diagnostic task due to the linguistic uncertainty and vagueness, large number of measurements with imprecision, inconsistencies in the definition of Aphasic syndromes, natural diversity and subjectivity in test objects as well as in options of experts who diagnose the disease. In this paper we present a new self-organized multi agent system that diagnoses different types of Aphasia based on fuzzy probabilities. In the proposed multi agent system, the characteristic of self organization is employed as both a decision making feature selection paradigm as well as a mechanism to estimate the probability mass functions of Aphasia factors. The estimated probability mass functions are involved in fuzzy probability calculation of different types of Aphasia. The performance and robustness of the proposed method is compared with several earlier approaches. While the proposed method requires more of the available test parameters, the comparison clearly shows the superiority of the proposed method in terms of accuracy as well as robustness.

Keywords


bibitem{1}
A. F. Adekoya, A.T. Akinwale and O. E. Oke,  {it A medical expert system for managing tropical diseases}, Proceeding of the Third Conference on Science and  National Development, (2008), 74-86.

bibitem{2}
T. Akbarzadeh and M. Moshtagh-Khorasani, {it A hierarchical fuzzy rule-based approach to aphasia diagnosis}, Journal of Biomedical Informatics, {bf 40}textbf{(5)} (2007) 465-475.

bibitem{3}
K. Angelika and T. Heike, {it Data-based fuzzy rule test for fuzzy modeling}, Fuzzy Sets and Systems, {bf 123}textbf{(3)} (2001), 343-358.

bibitem{4}
H. Axer, J. Jantzen and V. K. Graf, {it An aphasia database on the internet: a model for computer-assisted analysis in aphasiology}, Brain Lang, {bf 75}textbf{(3)} (2000), 390-398.

bibitem{5}
H. Axer, J. Jantzen, V. Keyserlingk and G. Berks, {it Aphasia Classification Using Neural Networks}, European Symposium on Intelligent Techniques Aachen, (2000), 111-115.

bibitem{6}
C. Bernon, V. Chevrier, V. Hilaire and P. Marrow, {it Applications of self-organizing multi-agent systems: an initial framework for comparison}, Informatica, {bf 30}textbf{(1)} (2006), 73-82.

bibitem{7}
G. Berks, V. Keyserlingk, J. Jantzen, M. Dotoli and H. Axer, {it Fuzzy clustering - A versatile mean to explore medical databases}, European Symposium on Intelligent Techniques, Aachen, Germany, 2000.

bibitem{8}
J. J. Buckley, {it Fuzzy mathematics in economics and engineering}, Physica-Verlag, Heidelberg, Germany, 2002.

bibitem{9}
G. Castellano, A. M. Fanelli and C. Mencar, {it A fuzzy clustering approach for mining diagnostic rules}, IEEE International Conference on Systems, Man and Cybernetics, (2003), 2007-2012.

bibitem{10}
O. Coltell, M. Arregui, Z. Falomir, D. Corella and J. M. Ordovas, {it multi-agent approaches for biomedical informatics applications in the health framework: genomic epidemiology and nutrigenomics},BioInfo Genomica subgroup of the Systems Integration and Re- Engineering Research Group (IRIS), Universitat Jaume I. Avda. Vicent Sos Baynat, s/n. 12071- Castellón, Spain, 2005.

bibitem{11}
J. M. Corchado, J. Bajo, Y. Paz and D. I. Tapia, {it Intelligent environment for monitoring Alzheimer patients, agent technology for health care}, Decision Support Systems, {bf 44}textbf{(2)} (2008), 382-396.

bibitem{12}
G. Di Marzo, M. P. Gleizes and A. Karageorgos, {it Self-organization and emergence in MAS: an overview}, Informatica (Slovenia), {bf 30}textbf{(1)} (2005), 45-54.

bibitem{13}
J. P. Dunyak and D. Wunsch, {it Fuzzy probability for system reliability}, Proceedings of the 37th IEEE Conference on Decision and Control, {bf 3} (1998), 2934-2935.

bibitem{14}
J. P. Dunyak, {it A theory of independent fuzzy probability for system reliability}, IEEE transactions on fuzzy systems, {bf 7}textbf{(3)} (1999), 286-294.

bibitem{15}
Q. T. Edwards and M. R. Palomares, {it Assessment of risk for breast cancer utilizing history and quantitative models in primary care}, The Journal for Nurse Practitioners, {bf 10} (2008), 361-369.

bibitem{17}
Y. Gao, Z. Shang and A. Kokossis, {it Agent-based intelligent system development for decision support in chemical process industry}, Expert Systems with Applications, {bf 36}textbf{(8)} (2009), 11099-11107.

bibitem{18}
F. Gechter, V. Chevrier and F. Charpillet, {it Localizing and tracking targets with a reactive multi-agent system}, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, (2004), 255-262.

bibitem{20}
M. Ghijsen, W. N. H. Jansweijer and B. J. Wielinga, {it Agent decision making for dynamic selection of coordination mechanisms}, IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, {bf 2} (2008), 87-91.

bibitem{21}
H. González-Vélez, M. Mier, M. Julià-Sapé, T. N. Arvanitis, J. M. García-Gómez, M. Robles, P. H. Lewis, S. Dasmahapatra, D. Dupplaw, A. Peet, C. Arús, B. Celda, S.V. Huffel and M. Lluch-Ariet, {it Health agents: distributed multi-agent brain tumor diagnosis and prognosis, applied intelligence }, Applied intelligence, {bf 30}textbf{(3)} (2009), 191-202.

bibitem{22}
C. A. Holzmann, C. A. Perez and E. Rosselot, {it A fuzzy model for medical diagnosis}, Medical Progress Through Technology, {bf 13}textbf{(4)} (1988), 171-178.

bibitem{23}
Z. Huang and T. D. Gedeon, {it Information retrieval estimation via fuzzy probability}, World Automation Congress, (2006), 1-6.

bibitem{24}
W. Huber, K. Poeck and K. Willmes, {it The aachen aphasia test}, Advances in Neurology, {bf 42} (1984), 291-303.

bibitem{25}
K. G. Jolly, K. P. Ravindran, R. Vijayakumar and R. Sreerama Kumar, {it Intelligent decision making in multi-agent robot soccer system through compounded artificial neural networks}, Robotics and Autonomous Systems, {bf 55}textbf{(7)} (2007), 589-596.

bibitem{26}
C. Jun Su, {it Mobile multi-agent based. distributed information platform (MADIP) for wide-area ehealth monitoring}, Computers in Industry, {bf 59}textbf{(1)} (2008), 55-68.

bibitem{27}
M. K. Kaleem, {it Role of expert systems in digital mammogram}, International Journal of Computer Science and Technology, {bf 2}textbf{(2)} (2011), 96-99.

bibitem{28}
I. Karimi and E. Hüllermeier, {it Risk assessment system of natural hazards: a new approach based on fuzzy probability}, Fuzzy Sets and Systems, {bf 158}textbf{(9)} (2007), 987-999.

bibitem{29}
R. Kenarangui, {it Event-tree analysis by fuzzy probability}, IEEE transactions on reliability, {bf 40}textbf{(1)} (1991), 120-124.

bibitem{30}
J. H. Kim and P. Vadakkepat, {it Multi-agent systems: a survey from the robot-soccer perspective}, Intelligent Automation and Soft Computing, {bf 6}textbf{(1)} (2000), 3-17.

bibitem{31}
J. Klüver, C. Stoica and R. Unland, {it Multi-Agent system and soft computing technologies as a fruitful symbiosis for reliable medical diagnoses}, BISC FLINT-CIBI International Joint Workshop on Soft Computing for Internet and Bioinformatics, University of Berkeley, US, 2003.

bibitem{32}
B. H. Kumar, {it A fuzzy expert system design for analysis of body sounds and design of an unique electronic stethoscope (development of HILSA kit)}, Biosensors and Bioelectronics, {bf 22}textbf{(6)} (2007), 1121-1125.

bibitem{33}
G. B. Laleci, A. Dogac, M. Olduz, I. Tasyurt, M. Yuksel and A. Okcan, {it SAPHIRE: A multi-agent system for remote healthcare monitoring through computerized clinical guidelines}, Agent technology and ehealth, Whitestein Series in Software Agent Technologies and Autonomic Computing, (2008), 25-44.

bibitem{34}
I. B. Laszlo, {it Cooperative medical diagnoses elaboration by physicians and artificial agents, emergent  properties in natural and artificial complex systems}, from system complexity to emergent properties, Understanding Complex Systems, (2009), 315-339.

bibitem{35}
S. Li, {it AgentStra: an Internet-based multi-agent intelligent system for strategic decision-making}, Expert Systems with Applications, {bf 33}textbf{(3)} (2007), 565-571.

bibitem{36}
C. Linard, N. Ponc, D. Fontenille and E. F. Lambin, {it A multi-agent simulation to assess the risk of malaria re-emergence in southern France}, Ecological modeling, {bf 220}textbf{(2)} (2009), 160-174.

bibitem{37}
M. B. Menhaj, {it Computational intelligence: fundamentals of neural networks}, {bf 1} (2008), 332-346.

bibitem{38}
M. Moshtagh-Khorasani, M. R. Akbarzadeh. T, N. Jahangiri and M. Khoobdel, {it An intelligent system based on fuzzy probabilities for medical diagnosis – a study in aphasia diagnosis}, Journal of Research in Medical Sciences, {bf 14}textbf{(2)} (2009), 89-103.

bibitem{40}
U. K. Nagah, S. A. Aziz, M. E. Aziz, M. Murad, N. M. Mahdi, A. Y. Shakaff, N. A. Isa, M. Y. Mashor and M. R. Arshad, {it A BI-RADS based expert systems for the diagnoses of breast diseases}, American Journal of Applied Sciences, {bf 4}textbf{(11)} (2007), 865-873.

bibitem{41}
M. Neshat, M. B. Naghibi and A. Esmaelzadeh, {it Fuzzy expert system design for diagnosis of liver disorder}, International Symposium on Knowledge Acquisition And Modeling, (2008), 252-256.

bibitem{42}
M. T. Nguyen, P. Fuhrer and J. Pasquier-Rocha, {it Enhancing e-health information systems with agent technology}, International Journal of Telemedicine and Applications, 2009.

bibitem{43}
B. Orgun and J. Vub, {it HL7 ontology and mobile agents for interoperability in heterogeneous medical information systems}, Computers in Biology and Medicine, {bf 36}textbf{(7-8)} (2006), 817-836.

bibitem{44}
C. Outsojannis, M. Tsimara and E. Nabil, {it HIROFILOS: a medical expert system for prostate diseases}, Proc. of the 7th WSEAS Int. Conf. on Computational Intelligence, Man-Machine Systems and Cybernetics, Wisconsin, USA, (2008), 254-259.

bibitem{45}
A. Pan, S. Y. S. Leung, K. L. Moon and K. W. Yeung, {it Optimal reorder decision-making in the agent-based apparel supply chain}, Expert Systems with Applications, {bf 36}textbf{(4)} (2009), 8571-8581.

bibitem{46}
G. Picard, C. Bernon and M. P. Gleizes, {it G. Picard, C. Bernon and M.-P. Gleizes}, Engineering Self-Organizing systems, Third International Workshop on Engineering Self-Organizing Applications (ESOA’05), Utrecht, The Netherlands, (2005), 31-45.

bibitem{48}
R. Radha and S. P. Rajagopalan, {it Fuzzy logic approach for diagnosis of diabetis}, Information Technology Journal, {bf 6}textbf{(1)} (2007), 96-102.

bibitem{49}
L. Ralescu, D. A. Ralescu and Y. Yamakata, {it Inference by aggregation of evidence with applications to fuzzy probabilities}, Information Sciences, {bf 177}textbf{(2)} (2007), 378-387.

bibitem{50}
F. Tatari and M. R. Akbarzadeh. T, {it Intensity assessment of pedestrian collisions in city of Mashhad based on fuzzy probabilities}, Proceedings of the Joint International Fuzzy Systems Association World Congress and European Society of Fuzzy Logic and Technology Conference, Lisbon, Portugal, 2009.

bibitem{51}
F. Tatari,  M. R. Akbarzadeh. T and A. Azemi, {it Agent-based centralized fuzzy kalman filtering for uncertain stochastic estimation}, Fifth International Conference on Soft Computing, Computing with Words and Perceptions in System Analysis, Decision and Control, Cyprus, 2009.

bibitem{52}
F.  Tatari, M. R. Akbarzadeh. T and A. Sabahi, {it Fuzzy-probabilistic multi agent system for breast cancer risk assessment and insurance premium assignment}, Journal of Biomedical informatics, {bf 45}textbf{(6)} (2012) 1021-1034.

bibitem{53}
J. Tian and H. Tianfield, {it A multi-agent approach to the design of an E-medicine system}, Multi-agent system technology, Lecture Notes in Computer Science, (2003), 85-94.

bibitem{54}
M. F. Torbaghan and D. Meyer, {it MEDUSA- a fuzzy expert system for medical diagnosis of acute abdominal pain}, Methods of Information in Medicine, {bf 33}textbf{(5)} (1994), 522-529.

bibitem{55}
M. Ulieru, M. Hadzic and E. Chang, {it Soft computing agents for e-Health in application to the research and control of unknown diseases}, Information Sciences, {bf 176} (2006), 1190-1214.

bibitem{56}
S. Uckun, {it Intelligent systems in patient monitoring and therapy management, a survey of research projects}, International Journal of Clinical monitoring and Computing, {bf 11}textbf{(4)} (1994), 241-253.

bibitem{57}
R. Unland and M. Ulieru, {it Swarm intelligence and the holonic paradigm: a promising symbiosis for a medical diagnostic system}, Knowledge-Based Intelligent Information and Engineering Systems, 9th International Conference, KES 2005, Melbourne, Australia, (2005), 154-160.

bibitem{58}
F. E. Uzoka, J. Osuji and O. Obot, {it Clinical DSS in the diagnosis of malaria: a case comparison of two soft computing methodologies}, Expert Systems with Applications, {bf 38}textbf{(3)} (2011), 1537-1553.

bibitem{59}
S. Y. M. Vaghefi and T. M. Isfahani, {it Roses: an expert system for diagnosing six neurologic diseases in children}, International Conference of Intelligent Systems and Agents, (2009), 259-260 .

bibitem{60}
G. Wang, S. Mao and Y. He, {it Optimal decision fusion with fuzzy priori probabilities}, Fourth International Conference on Signal Processing Proceedings,  {bf 2} (1998), 1277-1280.

bibitem{61}
G. Wang, S. Mao and Y. He, {it Distributed detection fusion with fuzzy priori probabilities and fuzzy cost function}, IEEE international radar conference, (2000), 146-150.

bibitem{62}
M. Wooldridge, {it An introduction to multi agent systems}, John Wiley and Sons, 2009.

bibitem{64}
D. Yu and W. S. Park, {it Combination and evaluation of expert opinions characterized in terms of fuzzy probabilities}, Annals of Nuclear Energy, {bf 27}textbf{(8)} (2000), 713-726.

bibitem{65}
L. Yu, S. Wang and K. Keung Lai, {it An intelligent-agent-based fuzzy group decision making model for financial multicriteria decision support: the case of credit scoring}, European Journal of Operational Research, {bf 195}textbf{(3)} (2009), 942-959.

bibitem{66}
L.A. Zadeh, {it Probability measures of fuzzy events}, Journal of Mathematical Analysis and Applications, {bf 23}textbf{(2)} (1968), 421-427.

bibitem{67}
L. A. Zadeh, {it Fuzzy probabilities}, Information processing and management, {bf 20}textbf{(3)} (1984), 363-372.

bibitem{68}
L. A. Zadeh, {it Discussion: probability theory and fuzzy logic are complementary rather than competitive}, Technometrics, {bf 37}textbf{(3)} (1995), 271-276.

bibitem{69}
L. A. Zadeh, {it Toward a perception-based theory of probabilistic reasoning with imprecise probabilities}, Journal of statistical planning and inference, {bf 105}textbf{(1)} (2002), 233-264.

bibitem{70}
S. Zahan, R. Bogdan and R. Capalneanu, {it Fuzzy expert system for cardiovascular disease diagnosis-tests and performance evaluation}, 5th  Seminar on Neural Network Applications in Electrical Engineering, Ugoslavia, (2000), 65-68.

bibitem{71}
T. Zhang and D. Zhang, {it Agent-based simulation of consumer purchase decision-making and the decoy effect}, Journal of Business Research, {bf 60}textbf{(8)} (2007), 912-922.

bibitem{72}
X. Zhao, S. Yuan, Z. Yu, W. Ye and J. Cao, {it Designing strategy for multi-agent system based large structural health monitoring}, Expert Systems with Applications, {bf 34}textbf{(2)} (2008), 1154-1168.

bibitem{73}
J. Zhou, {it Reliability assessment method for pressure piping containing circumferential defects based on fuzzy probability}, International Journal of Pressure Vessels and Piping, {bf 82}textbf{(9)} (2005), 669-678.