An Integrated Approach of the Modern Expert System and Its Application
Keywords:
Decision support, Efficiency, Expert system, Knowledge, Scalability, TransparencyAbstract
This research paper examines how modern integrated expert systems democratize decision-making by simulating specialized judgment in complex, domain-specific problems. The central thesis is that these systems provide consistent and efficient access to expertise for non-experts. To demonstrate this, the authors design solutions focused on knowledge preservation, standardized decision-making, rapid problem-solving, and ensuring justification and transparency. A significant finding in 2024 is the shift towards hybrid AI models that combine structured knowledge (rules) with machine learning capabilities, moving away from older standalone rule-based systems. This approach has shown improved performance, with hybrid methods achieving better accuracy in complex diagnostic scenarios compared to single-method systems. By late 2024, a large percentage of expert systems had incorporated machine learning. Knowledge Preservation: Capturing the specialized knowledge of human experts and storing it in a digital format ensures that valuable expertise is not lost when professionals retire or leave an organization. Ultimately, the sustainability of fuzzy logic technology leads to improved quality, performance, better cost management, enhanced decision-making, and minimized risk. By incorporating insights from academic studies, industry analyses, and practical applications, this paper provides a comprehensive overview of the evolution and innovation of modern expert systems. Expert system performance matrices focus on accuracy, speed, and domain-specific metrics (like sensitivity/specificity in medicine), evaluated using ROC curves, AUC, precision, recall, F1-score, and validation methods like cross-validation, with applications spanning medical diagnosis (prostate cancer), process control, and fault diagnosis, aiming to match or exceed human expert capabilities for complex decision-making. Current research focuses on automating complex decision-making in domains where human expertise is scarce or expensive, such as medical diagnostics, industrial maintenance, and personalized education.
References
A. Dattachaudhuri, S. Kr. Biswas, M. Chakraborty, and S. Sarkar, “A transparent rule-based expert system using neural network,” Soft Computing, vol. 25, pp. 7731–7744, Jan. 2021.
J. Straub, “Automating the design and development of gradient descent trained expert system networks,” Knowledge-Based Systems, vol. 254, Oct. 2022.
M. H. GöRing and H. G. Schecker, “HAZEXPERT — an integrated expert system to support hazard analysis in process plant design,” Computers & Chemical Engineering, vol. 17, pp. S429–S434, 1993.
M. Rajabi, S. Hossani, and F. Dehghani, “A literature review on current approaches and applications of fuzzy expert systems,” arXiv.org, Sep. 2019.
A. Rahman, C. Slamet, W. Darmalaksana, Y. A. Gerhana, and M. A. Ramdhani, “Expert system for deciding a solution of mechanical failure in a car using case-based reasoning,” IOP Conference Series: Materials Science and Engineering, vol. 288, no. 1, Art. no. 012011, Jan. 2018.
B. A. Ahmed Ali, S. M. Sapuan, E. S. Zainudin, and M. Othman, “Implementation of the expert decision system for environmental assessment in composite materials selection for automotive components,” Journal of Cleaner Production, vol. 107, pp. 557–567, Nov. 2015.
M. Kurucan, M. Özbaltan, Z. Yetgin, and A. Alkaya, “Applications of artificial neural network based battery management systems: A literature review,” Renewable & Sustainable Energy Reviews, vol. 192, Mar. 2024.
N. Aiello, “A comparative study of control strategies for expert systems: Age implementation of three variations of puff,” in AAAI-83 Proceedings, 1983, pp. 1–4.
P. Hendriks, “Why share knowledge? The influence of ICT on the motivation for knowledge sharing,” Knowledge and Process Management, vol. 6, no. 2, pp. 91–100, Jun. 1999.
R. M. Tawafak, G. Alfarsi, A. Romli, J. Jabbar, S. I. Malik and A. Alsideiri, “A review paper on student-graduate advisory expert system,” 2020 International Conference on Computing and Information Technology (ICCIT-1441), Tabuk, Saudi Arabia, 2020, pp. 1–5.
S. Mahdavifar and A. A. Ghorbani, “DeNNeS: Deep embedded neural network expert system for detecting cyber attacks,” Neural Computing and Applications, vol. 32, pp. 14753–14780, Mar. 2020.
T. Oyedare, V. K. Shah, D. J. Jakubisin and J. H. Reed, “Interference suppression using deep learning: Current approaches and open challenges,” in IEEE Access, vol. 10, pp. 66238–66266, 2022.
Y. Matsuzaka and R. Yashiro, “AI-based computer vision techniques and expert systems,” AI, vol. 4, no. 1, pp. 289–302, Feb. 2023.
Y. Ou, S. -Q. Ye, L. Ding, K. -Q. Zhou and A. M. Zain, “Hybrid knowledge extraction framework using modified adaptive genetic algorithm and BPNN,” in IEEE Access, vol. 10, pp. 72037–72050, 2022.
P. Jackson, Introduction to expert systems, Reading, MA, USA: Addison-Wesley Publishing Company, 1986.
