Ellea All round percent C. cibarius B. edulis A. mellea Overall percent Predicted A. mellea 0 1 5 ten.35 0 1 two 15.79C. cibarius 27 1 2 51.73 6 0 0 31.58B. edulis 1 18 3 37.94 0 ten 0 52.64Percent Right 96.43 90.00 50.00 86.21 100 90.91 100 94.74TrainingHoldoutIn the education step, the overall percent of properly classified PbTx-2 References samples was 86.21 , although for the holdout set, the percent rose to 94.74 . The decrease values obtained for the education set have been as a consequence of a single C. cibarius sample, two B. edulis, and 5 A. mellea, which have been placed to other species. In any case, for the holdout sample, only 1 sample from B. edulis was misclassified. With regards to the characteristics choice, only 3 points have been chosen: 1746 cm-1 , 1510 cm-1 , and 1388 cm-1 . The samples’ distribution in between the two sets, as outlined by selected features, is presented in Figure 3 under: It ought to be noticed that the results obtained applying PCA-LDA and kNN are very comparable with regards to species prediction accuracy. With regards to the obtained predictors, it really should be talked about that, except for 1746 cm-1 , which also appeared in LDA classification, the other two bands are new predictors. This could cause the conclusion that these two approaches are complementary. The number of groups for fuzzy c-means N-Hexanoyl-L-homoserine lactone Autophagy clustering (FCM) evaluation was selected in accordance with the 3 investigated species, namely 3. The sample codes for this evaluation were as follows: code 1 for Armillaria mellea (samples 12), code two for Boletus edulis (samples 133), and code three for Cantharellus cibarius (samples 447). FCM developed threeTrainingAppl. Sci. 2021, 11,HoldoutB. edulis A. mellea Overall percent C. cibarius B. edulis A. mellea General percent1 two 51.73 6 0 0 31.5818 three 37.94 0 10 0 52.641 five ten.35 0 1 2 15.7990.00 50.00 86.21 100 90.91 one hundred 94.747 offuzzy partitions, which have been all represented by a prototype (a cluster center together with the specIn the education step, the general % of correctly classified samples was 86.21 , trum corresponding towards the fuzzy robust signifies on the original FT-IR spectra traits while for the holdout set, the percent rose to 94.74 . The lower values obtained for the for 77 samples weighted by degree of membership (DOM)) corresponding to each partition. coaching set were as a consequence of one C cibarius sample, two B. edulis, and 5 A. mellea, which To examine the partitions, the similarities and variations among samples, the spectra from the were placed to other species. In any case, for the holdout sample, only one sample from prototypes corresponding towards the 3 fuzzy partitions (A1 three) obtained by applying both B. edulis and DOMs of samples corresponding to all fuzzy partitions, have to be analyzed. The FCM was misclassified. Regarding the characteristics selection, only three points had been se-1 lected: 1746 cm-1, 1510Table, 2and 1388 cm-1clearly illustratedistribution amongst the two results presented in cm and Figure 4 . The samples’ the most distinct characteristics sets, in line with chosen and their is presented in Figure 3sample assignment based on options, (dis)similarity and also the under: of each fuzzy partition their DOMs.Figure three. kNN modeling of mushroom samples, with three attributes selected and five neighbors. Figure 3. kNN modeling of mushroom samples, with 3 attributes chosen and 5 neighbors. Table two. The 3 fuzzy partitions obtained by applying the fuzzy c-means clustering method.Fuzzy Partition A A1 A2 A1, 10, 13, 15, 16, 17, 18, 19, 20, 21, 22, 23, two.
