A FRAMEWORK FOR DIABETES DIAGNOSIS BASED ON TYPE-2 FUZZY SEMANTIC ONTOLOGY APPROACH
Mr.V.Manikandabalaji 1 and Dr. R.Sivakumar 2
1Research Scholar, Department of Computer Science, A.V.V.M.Sri Pushpam College (Autonomous), Poondi-613503, Thanjavur (Dt), Tamilnadu, India.
Affiliated to Bharathidasan University, Trichirappalli-24.
Email ID: firstname.lastname@example.org
2Associate Professor in the Department of Computer Science, A.V.V.M.Sri Pushpam College (Autonomous), Poondi-613503, Thanjavur (Dt), Tamilnadu, India
Affiliated to Bharathidasan University – Trichirappalli-24
Diabetes mellitus is a significant metabolic disorder that may last a lifetime and affects a great number of people throughout the world. Two major critiques that may be levelled at the ontology-based tools that are presently being used to analyse and treat diabetes are an increase in semantic incompatibility and an inability to interpret the information. Both of these complaints have the potential to be severe issues. Furthermore, clinical decision support systems, often known as CDSSs, play an important role in the diagnosis of diabetes. As a consequence, the outcomes of this study project advised that a new semantically intelligent Type-2 fuzzy CDSS for diabetes diagnosis be developed. The following steps are included in the proposed system: feature definition, semantic modelling, type-2 fuzzy modelling, and knowledge reasoning. This research endeavour is critical since there are currently so few works that address the formal integration of ontology semantics with Functional Electrical Stimulation (FES) reasoning, particularly in the medical arena. The ontology is a feature of FES that may be needed or selected as optional. The system that was constructed takes into consideration the ontology-semantic similarity of the concepts that are relevant to diabetes complications and symptoms while doing a fuzzy rule analysis. The proposed approach is put to the test using a real-world dataset, and the results show that it has the potential to help both individuals and medical experts provide more accurate diabetes diagnoses. The suggested technique was tested on a real dataset, and the findings show that it has the potential to help physicians and patients diagnose diabetes mellitus more correctly.
Keywords: Diabetes mellitus – Clinical decision support system (CDSS) – Ontology reasoning – Functional Electrical Stimulation (FES) – Type-2 Fuzzy.