25,0.5], u7 = [0.5,0.75], and u8 = [0.75,1]. The midpoints of these intervals are u1′ = −0.875, u2′ = −0.625, u3′ = −0.375, u4′ = −0.125, u5′ = 0.125, u6′ = 0.375, u7′ = 0.625, and u8′ = 0.875. Define fuzzy set Ai based on the redivided intervals; fuzzy set Ai denotes a linguistic value ALK assay of the passenger flow represented by a fuzzy set, 1 ≤ i ≤ 8. The notations A1, A2, A3, and A4 denote that passenger flow decrease is too large, larger, microlarge, and less, respectively. Also, the notations A5, A6, A7, and A8 denote that passenger flow increase is less, microlarge, larger, and too large. Eight membership functions

in this paper sufficiently reflect quasi-periodic variation of high-speed railway passenger flow, and the forecast result of FTLPFFM has better accuracy based on eight membership functions. Define the fuzzy membership function of subset Ai, namely, fA1x=1,−1≤x≤−0.75,−0.5−x0.25,−0.75−0.5,fA2x=x−−10.25,−1−0.25,fA3x=0,x≤−0.75,x−−0.750.25,−0.750,fA4x=0,x≤−0.5,x−−0.50.25,−0.50.25,fA5x=0,x≤−0.25,x−−0.250.25,−0.250.5,fA6x=0,x≤0,x0.25,00.75,fA7x=0,x≤0.25,x−0.50.25,0.25

(1) Different passenger flow change rates can be fuzzified into corresponding fuzzy sets. For example, as seen in Table 1, the passenger flow

change rate from 7:00–8:00 to 8:00–9:00 is 0.273, which is fuzzified to A6. The passenger flow change rate from 8:00–9:00 to 9:00–10:00 is 0.231, which is fuzzified to A5. The passenger flow change rate from 9:00–10:00 to 10:00–11:00 is 0.5158, which is fuzzified to A7. And the passenger flow change rate from 10:00–11:00 to 11:00–12:00 is −0.8145, which is fuzzified to A1. The fuzzification process is depicted in Figure 3. Some fuzzified passenger flow change rates are listed in Table 1. Figure 3 Fuzzified passenger flow change rate. Fuzzy logic relationships are AV-951 established by putting two consecutive fuzzy sets, as follows: Aj⟶Ap,Ap⟶Aq,…,As⟶At. (2) “Aj → Ap” denotes that “the fuzzified passenger flow change rate is Aj from period t − 1 to t and then the fuzzified passenger flow change rate is Ap from period t to t + 1”. As seen in Figure 4, the fuzzified passenger flow change rate from 7:00–8:00 to 8:00–9:00 is A6 and from 8:00–9:00 to 9:00–10:00 is A5. Hence, we can establish an fuzzy logic relationship as A6 → A5. Likewise, from Table 1, we can establish the fuzzy logic relationships as A6 → A5, A5 → A7, A7 → A1, A1 → A3, and so forth. Some fuzzy logic relationships are listed in Table 2. Figure 4 Passenger flow change rate relationships. Table 2 The fuzzy logic relationship of fuzzified passenger flow change rate. 4.