Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
Tham khảo tài liệu 'nonlinear dynamics part 14', kỹ thuật - công nghệ, cơ khí - chế tạo máy phục vụ nhu cầu học tập, nghiên cứu và làm việc hiệu quả | 318 Nonlinear Dynamics Pooled Peak Period p 1 q 1 p 1 q 1 Degree of differentiation dm 0.24 0.46 AR polynomial coefficients V1 2 0.66 - 0.02 - MA polynomial coefficients 01 02 0.52 - 0.55 - 03 - 04 - 05 - Log-likelihood JB Test Null normality Q2 7 Null serial independence LM ARCH 1 Null no ARCH effect -2622.36 2.02 -1079.26 1.42 136.25 1.41 66.18 1.32 rejection at 5 significance level rejection at 1 significance level Table 1. Estimation Results for the ARFIMA p dm q models for the Heraklion airport. Pooled Peak Period p 1 q 1 p 1 q 1 Degree of differentiation dm 0.15 0.31 AR polynomial coefficients V1 0.66 0.05 2 - - MA polynomial coefficients 01 0.35 0.48 02 - - 03 - 04 - 05 - Log-likelihood -2588.14 -1002.80 JB Test 4.43 1.24 Null normality Q2 7 145.25 64.54 Null serial independence LM ARCH 1 1.65 0.03 Null no ARCH effect rejection at 5 significance level rejection at 1 significance level Table 2. Estimation Results for the ARFIMA p dm q models for the Kerkyra airport. Advanced Computational Approaches for Predicting Tourist Arrivals the Case of Charter Air-Travel 319 Pooled Peak Period p 1 q 1 p 1 q 1 Degree of differentiation dm 0.34 0.37 AR polynomial coefficients V1 0.67 0.05 2 - - MA polynomial coefficients 01 0.43 0.58 02 - - 03 - 04 - 05 - Log-likelihood -2689.31 -1017.48 JB Test 3.48 2.48 Null normality Q2 7 122.52 75.67 Null serial independence LM ARCH 2 0.82 0.10 Null no ARCH effect rejection at 5 significance level rejection at 1 significance level Table 3. Estimation Results for the ARFIMA p dm q models for Rhodes airport. Specifications DATA TR-CV-TE 60 -20 -20 Input layer Gamma memory genetically optimized memory Structure depth 1 hidden layer genetically optimized number of hidden units h Learning Back-propagation Chromosome h e 5 15 Y e 0.01 - 0.1 u e 0.5 - 0.9 T e 1 5 m e 1 12 Fitness function Mean square error cross-validation set Selection Roulette Cross-over Two point p 0.9 0 Mutation Probability p 0.09 Training - Cross-validation - Testing h