Implementation of Fuzzy Expert System on Skin Diseases

Syarif, Admi; Fauzi, Mayda B; Aristoteles, -; Wantoro, Agus

doi:10.14569/ijacsa.2022.0131264

Cited by 1 publication

(1 citation statement)

References 7 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The representation of the (36) rules is displayed in Figure 11. The study by Soulhi et al [27] and more recently in 2022 by Admi Syarif et al [28] highlighted the utmost importance of a fuzzy medical expert system based on unprecise existing skin symptoms in alleviating human suffering. The system uses the dermatologist specialist's knowledge and know-how to diagnose and provide the patient's severity level for the disease, succeeding in all tests with an accuracy of 95.6%.…”

Section: Inference Rulesmentioning

confidence: 99%

Enhancing Supply Chain Resilience and Efficiency through Fuzzy Logic-based Decision-Making Automation in Volatile Environments

Berbiche,

Hlyal,

El Alami

2024

ISI

View full text Add to dashboard Cite

In light of recent mutations and economic volatility stemming from unforeseen global events and increasing security concerns, supply chains are confronted with the complex challenge of fulfilling uncertain customer demands while ensuring sustained value addition. This study introduces a novel approach utilizing fuzzy logic decision-making automation to address and mitigate the impact of current disruptions. By employing if-then scenarios, this methodology facilitates the generation of more accurate predictions and smarter supply planning, enabling effective decision-making, particularly in critical areas such as semiconductor supply sourcing. The integration of Artificial Intelligence within this framework provides dynamic visibility into real-world supply chain operations, thereby aiding in more informed and effective regulatory decisions and fostering continuous improvement. The core innovation of this research lies in the development of a unique Mamdani-fuzzy logic model designed to enhance supply planning. This model extends beyond the realm of efficient inventory management to encompass safer demand forecasting and market segmentation, showcasing its superiority in versatility and effectiveness compared to conventional methods, and leveraging expert knowledge to navigate uncertainties. Through the process of fuzzification, relevant indicators such as Consumption Severity, Market Sensitivity, and Commodity Importance are identified and modeled, with input variables being assigned membership functions and categorized into varying degrees of significance. The Mamdani-inference rules are then formulated, and the output of the fuzzy logic model is defuzzified using the centroid technique to derive precise supply quantities. Simulations conducted in MATLAB demonstrate the model's capacity to convert uncertainty into optimal supply measures across diverse scenarios, thereby enhancing safety and efficiency within the supply chain by minimizing excess inventory and preventing stockouts. This hybrid approach, combining mathematical reasoning with human expertise, validates the efficacy and robustness of fuzzy logic as a potent cognitive and modeling technique for facilitating precise and responsive decision-making in the face of unexpected incidents, imprecision, and qualitative factors affecting the supply chain.

show abstract

Section: Inference Rulesmentioning

confidence: 99%