Insect infestation is an alarming concern in stored wheat grain, accounting for losses in quality as well as quantity. Infested wheat with Sitophilus granarius for four different storage periods with various degrees of infestation were evaluated through E-nose. A fuzzy logic based approach was undertaken to screen the relatively more sensitive sensors towards infestation. Multiple linear regression (MLR) models were further used to predict the uric acid and protein content as infestation indices. Principal component analysis (PCA) and hierarchical cluster analysis (HCA) efficiently classified the most infested wheat grain samples among the stored samples. The developed MLR models were found best fit with higher regression co-efficient (R2) value and lower root mean square error (RMSE). The E-nose sensor responses closely predicted the uric acid (R2 = 0.958; RMSE = 1.401) and protein content (R2 = 0.978; RMSE = 0.275). The findings of this study will open up a convenient, rapid yet nondestructive approach for quality determination of insect infested wheat grains at various stages during the storage.