The proposed framework advocates the early detection and diagnosis of
disease and increases the efficiency of treatment and recovery. The data
collected from wearable devices are processed in a fuzzy inference
system (FIS) which consists of four main components namely
fuzzification, Knowledge Discovery Dataset (KDD), prediction model, and
defuzzification. The fuzzification data and KDD outcome are forwarded to
the prediction model to train the model to detect the disease. The
inference system’s final component is defuzzification, which converts
the fuzzy set from the prediction model to the desired crisp set values.
The proposed research exploits Weka 3.8.6 tool to analyze the monkeypox
dataset. A fuzzy decision tree is generated from the J48 algorithm and
eight fuzzy rules are formulated from the C4.5 algorithm. The devised
research uses approximately 25000 instances in which 16682 instances are
classified correctly 66.728 % and 8318 instances are classified
incorrectly 33.272 %. The performance metrics like True Positive (TP)
rate, False Positive (FP) rate, precision, recall, and F-measure are
evaluated. The confusion matrix predicts the number of correct and
incorrect predictions. The suggested fuzzy logic-based analytics
advocates the faster detection of disease and reduces hospitalization.
Also, the research promotes effective interaction among healthcare
service providers and patients. The devised work is a research-driven
exploration into the application of fuzzy logic in the domain of medical
diagnosis and prognosis.