Table 1.
Literature review of PPV estimation using AI and SC methods.
| References | Year | Model | Inputs | Model performance (R2) |
|---|---|---|---|---|
| Singh et al.40 | 2005 | ANN | D, N, HD, B, S, ST, MC, HDI, RDI | 0.82 |
| Iphar et al.39 | 2007 | ANFIS | DI, CD | 0.99 |
| Monjezi et al.41 | 2011 | ANN | CD, DI, ST, HD | 0.95 |
| Mohamed42 | 2011 | ANN, FIS | DI, MC |
ANN = 0.94 FIS = 0.90 |
| Khandelwal et al.43 | 2011 | ANN | DI, MC | 0.92 |
| Fişne et al.44 | 2011 | FIS | DI, MC | 0.92 |
| Mohamadnejad et al.11 | 2012 | SVM, ANN | DI, MC |
SVM = 0.89 ANN = 0.85 |
| Ghasemi et al.45 | 2013 | FIS | B, S, ST, N, MC, DI | 0.95 |
| Masoud et al.46 | 2013 | ANN | MC, DI, TC | 0.93 |
| Armaghani et al.47 | 2014 | PSO-ANN | S, B, ST, PF, MC, D, N, RD, SD | 0.94 |
| Hajihassani et al.20 | 2015 | ICA-ANN | BS, ST, PF, MC, DI, Vp, E | 0.98 |
| Dindarloo48 | 2015 | SVM | RD, E, UCS, TS, Js, B, S, HD/B, SC, ST, DPR, DI | 0.99 |
| Hajihassani et al.49 | 2015 | PSO-ANN | BS, MC, HD, ST, SD, DI, PF, RQD | 0.89 |
| Hasanipanah et al.50 | 2015 | SVM | DI, MC | 0.96 |
| Armaghani et al.51 | 2015 | ANFIS | DI, MC | 0.97 |
| Ghoraba et al.52 | 2016 | ANN, ANFIS | DI, MC |
ANFIS = 0.95 ANN = 0.89 |
| Faradonbeh et al.10 | 2016 | GEP | B, S, ST, D, HD, PF, MC, DI | 0.88 |
| Hasanipanah et al.53 | 2017 | CART | DI, MC | 0.95 |
| Shahnazar et al.54 | 2017 | PSO-ANFIS | DI, MC | 0.98 |
| Armaghani et al.6 | 2018 | ICA | DI, MC | 0.95 |
| Nguyen et al.55 | 2019 | HKM-CA | DI, MC, PF, B, S, HD | 0.99 |
| Nguyen et al.56 | 2020 | SVR-GA | DI, MC, B, S, N | 0.99 |
| Zhang et al.57 | 2020 | RF,CART,CHAID | B/S, DI, ST, MC, PF, HD |
RF = 0.94 CART = 0.97 CHAID = 0.91 |
| Zhou et al.58 | 2020 | RF | DI, ST, MC, PF, HD | 0.93 |
| Huang et al.21 | 2020 | FA-ANN | B/S, DI, ST, MC, PF, HD, RQD, N, SD | 0.91 |
| Zhou et al.12 | 2021 | GEP-MC | B/S, DI, ST, MC, PF, HD | 0.91 |
| Lawal et al.59 | 2021 | ANN-MFO | DI, MC, N, HD, RMR | 0.97 |
| He et al.60 | 2022 | RF-WOA | B/S, DI, ST, MC, PF, HD | 0.99 |
| Ragam et al.61 | 2022 | XGBoost-RF | N, B, S, HD, D, HD, ST, MC, DI | 0.95 |
| Nguyen et al.62 | 2023 | SSO-ELM | B, S, PF, MC, f | 0.91 |
B Burden, S Spacing, HL Hole length, ST Stemming, PF Powder factor, B Blastability index, SVM Support vector machine, MC Maximum charge per delay, RD Rock density, D Hole diameter, HD Hole depth, BS Burden to spacing, N Number of row, PSO Particle swarm optimization, SD Sub-drilling, DI Distance from the blast face, TC Total charge, RQD Rock quality designation, E Young’s modulus, ICA Imperialist competitive algorithm, Vp p-wave velocity, ANFIS Adaptive neuro-fuzzy inference system, FIS Fuzzy inference system, R2 Coefficient of determination, UCS Uniaxial compression strength, TS Tensile strength, Js Joint spacing, HD/B Hole depth-to-burden ratio, SC Specific charge, DPR Delay per row, GEP Gene expression programming, RMR Rock mass rating, f Rock hardness, CART Classification and regression tree, CHIAD Chi-square automatic interaction detection, RF Random forest, HKM K-means clustering, FA Firefly algorithm, WOA Whale optimization algorithm, XGBoost Extreme gradient boosting, SSO Sparrow search optimization, ELM Extreme learning machine.