Beruflich Dokumente
Kultur Dokumente
DOI 10.1007/s11069-015-1842-3
ORIGINAL PAPER
Received: 16 May 2014 / Accepted: 30 May 2015 / Published online: 10 June 2015
Springer Science+Business Media Dordrecht 2015
Abstract The prediction of pillar stability (PS) in hard rock mines is a crucial task for
which many techniques and methods have been proposed in the literature including
machine learning classification. In order to make the best use of the large variety of
statistical and machine learning classification methods available, it is necessary to assess
their performance before selecting a classifier and suggesting improvement. The objective
of this paper is to compare different classification techniques for PS detection in hard rock
mines. The data of this study consist of six features, namely pillar width, pillar height, the
ratio of pillar width to its height, uniaxial compressive strength of the rock, pillar strength,
and pillar stress. A total of 251 pillar cases between 1972 and 2011 are analyzed. Six
supervised learning algorithms, including linear discriminant analysis, multinomial logistic
regression, multilayer perceptron neural networks, support vector machine (SVM), random
forest (RF), and gradient boosting machine, are evaluated for their ability to learn for PS
based on different input parameter combinations. In this study, the available data set is
randomly split into two parts: training set (70 %) and test set (30 %). A repeated tenfold
cross-validation procedure (ten repeats) is applied to determine the optimal parameter
values during modeling, and an external testing set is employed to validate the prediction
performance of models. Two performance measures, namely classification accuracy rate
and Cohens kappa, are employed. The analysis of the accuracy together with kappa for the
School of Resources and Safety Engineering, Central South University, Changsha 410083, China
Department of Mining and Materials Engineering, McGill University, Montreal, QC H3A 2A7,
Canada
123
292
PS data set demonstrates that SVM and RF achieve comparable median classification
accuracy rate and Cohens kappa values. All models are fitted by R programs with the
libraries and functions described in this study.
Keywords Pillar stability Pillar design Hard rock mine Supervised learning
Classification Repeated cross-validation R system
1 Introduction
Underground mining almost invariably involves leaving portions of the ore in the form of
pillars, which are key structural columns (Brady and Brown 2003; Deng et al. 2003; Zhou
et al. 2011). Pillar stability is an essential prerequisite for safe working conditions in roomand-pillar mines (Salamon 1970; Ghasemi et al. 2014a). Unstable pillars can result in rock
sloughing from the pillar and can lead to the collapse of the roof if one or more pillars
should fail (Mortazavi et al. 2009). As mining goes deeper, pillar failure becomes more
frequent and critical due to the increase in ambient stresses. Consequently, pillar design
and stability are two of the most complicated, extremely important and extensive problems
in mining related to rock mechanics and ground control subjects.
Because of their significance in safe and economical extraction of underground ores
over the past decades, a great deal of valuable results on this topic has been reported by a
number of authors on a variety of aspects and has made admirable efforts over the pillar
design and layout applied in rocks. Various researchers have proposed a number of
empirical design methods for pillar strength determination and often applied in practice,
which have been reviewed and summarized in the literature (Hustrulid 1976; Lunder 1994;
Brady and Brown 2003; Mark 2006; Mitri 2007; Jawed et al. 2013), i.e., the linear shape
effect formula (Bieniawski and van Heerden 1975; York 1998), the power shape effect
formula (Salamon and Munro 1967; Bieniawski 1968; Hedley and Grant 1972), the size
effect formula (Hustrulid 1976), the HoekBrown formula (Hoek and Brown 1980), and
analysis of retreat mining pillar stability method (Mark and Barton 1997; Ghasemi and
Shahriar 2012). In an underground pillar design, it is difficult to determine the actual stress
that will be acting on a pillar. However, the three main methods of calculating pillar stress
are tributary area theory, numerical modeling (Lunder 1994), and neural network method
(Monjezi et al. 2011). Thus, the stability of a pillar can be evaluated by calculating a safety
factor (SF), which is the ratio of the average strength to the average stress in the pillar
(Zhou et al. 2011). Theoretically, the SF value greater than 1 means that the pillar is stable,
while the SF value lower than 1 means unstable. More often than not, these methods are
questionable because pillar failures did occur even though the failed pillars had been
considered stable, i.e., SF [ 1 (Deng et al. 2003; Zhou et al. 2011). Moreover, empirical
methods are based on interpretation of available databases, which are compiled from
ongoing or completed projects. It is therefore difficult to generalize the obtained results
beyond the scope of the original site characteristics.
Meanwhile, considerable work related to the prediction of PS has been undertaken by
means of numerical simulation methods that allow for consideration of complex boundary
conditions and material behavior. For example, a design methodology was proposed by
York (1998) using the fast Lagrangian analysis of continua (FLAC) code to enable the
yield point of the foundation of deep-level stabilizing pillars to be predicted in terms of the
123
293
cohesion, friction angle, and depth. Hutchinson et al. (2002) recommended the use of
simulation methods for considerations crown pillar stability risk assessment in mine
planning. Jaiswal et al. (2004) used three-dimensional boundary element method (BEM) to
model asymmetry in the induced stresses over coal mine pillars with complex geometries
and have enabled successful simulation of mining conditions. Griffiths et al. (2007)
combined random field theory with an elastoplastic finite element method (FEM) algorithm
in a Monte Carlo framework to estimate the stability of pillars. By using an explicit finite
difference program FLAC3D, a model of numerical calculation was established by Li et al.
(2007) for a deep mining pillar with dynamic disturbance under high stress. Numerical
modeling was carried out by Jaiswal and Shrivastva (2009) using a three-dimensional FEM
code to study the stressstrain behavior of coal pillars. Mortazavi et al. (2009) delved into
the mechanisms involved in pillar failure as well as to investigate the nonlinear behavior of
rock pillars within the FLAC model. Elmo and Stead (2010) investigated the use of the
hybrid FEM/DEM code ELFEN in studying the failure modes of jointed pillars. Recently,
Li et al. (2013) established 3D numerical modeling based on FLAC3D to determine the
minimum thickness of the crown pillar for the subsea gold mine. Each of the numerical
methods has its advantages and disadvantages. However, the estimation of reliable values
of model input parameters is found to be an increasingly difficult task.
Besides the numerical modeling approach, statistical and analytical methods, the
probabilistic methods, and artificial intelligence-based methods or their hybrids have been
investigated in recent years and successfully used for designing pillars in coal or hardrock.
Esterhuizen (1993) showed that variability in rock mass properties and mining factors
could be taken into consideration for hard rock pillar design by statistical methods and
point estimate method. Griffiths et al. (2002) and Cauvin et al. (2009) investigated the
underground pillar stability based on probabilistic methods. Ghasemi et al. (2010) studied
the effect of variability in parameters such as uniaxial compressive strength of coal
specimen, pillar width, pillar height, entry width, and depth of cover on pillar safety factors
using a Monte Carlo simulation. Zhou et al. (2011) presented two models for predicting
pillar stability applying support vector machine and Fisher discriminant analysis techniques. Wattimena et al. (2013) developed the logistic regression model for predicting the
probability of stability of a coal pillar. On the other hand, different types of artificial neural
networks are based on combining different learning techniques, such as hybrid or ensemble
techniques. These have been reported on pillar stability analysis in recent years. Deng et al.
(2003) proposed a pillar design based on Monte Carlo simulation by combining finite
element methods, neural networks, and reliability analysis. Four ANNs, based on two
different architectures, the multilayer perceptron (MLP) and the radial basis function
(RBF), were constructed by Tawadrous and Katsabanis (2007) to predict the stability of
surface crown pillars. Monjezi et al. (2011) developed a MLP neural network model
methodology to predict the pillar stress concentration in the bord and pillar method and
compare the results with BEM numerical solution. Recently, Ghasemi et al. (2014a, b)
developed two models for the evaluation and prediction of global stability in room-andpillar coal mines considering the retreat mining conditions by employing the logistic
regression and the fuzzy logic techniques. In these studies, all the data are separated into
training and testing sets. However, cross-validation process is not implemented, and thus,
the accuracy of the predictive model is not fully understood. Hence, the issue of pillar
stability prediction still poses considerable challenge for underground mines.
Supervised learning (SL) has become steadily more mathematical and more successful
in applications over the past 20 years. The use of SL algorithms for the development of
predictive and descriptive data mining models has become widely accepted in mining and
123
294
geotechnical applications, promising powerful new tools for practicing engineers (Garzon
et al. 2006; Berrueta et al. 2007; Sakiyama et al. 2008; Pino-Mejas et al. 2008, 2010;
Pozdnoukhov et al. 2009; Tesfamariam and Liu 2010; Zhou et al. 2011, 2012, 2013;
Gonzalez-Rufino et al. 2013; Liu et al. 2013, 2014). Numerous approaches for PS prediction have been developed based on different SL techniques during recent decades
(Tawadrous and Katsabanis 2007; Zhou et al. 2011; Wattimena et al. 2013; Ghasemi et al.
2014a, b). However, there is no comparison of SL techniques over the PS estimation.
Based on these considerations, the main objective of this study is to investigate the
suitability of different SL algorithms for the prediction of pillar stability (PS) in underground engineering. To achieve this goal, a research methodology is developed for the
comparison of the performance of different SL algorithms, including linear discriminant
analysis (LDA), multinomial logistic regression (MLR), multilayer perceptron neural
networks (MLPNN), support vector machine (SVM), random forest (RF), and gradient
boosting machine (GBM). These methods are specifically chosen because they are being
increasingly used in engineering, yet have not been compared with one another exhaustively and also thanks to the open-source software availability. The rest of this paper is
organized as follows: Sect. 2 briefly presents hard rock pillars data set and provides an
overview of SL techniques. In Sect. 3, these methods are applied to the PS prediction, and
in Sect. 4, the results are discussed by performance criteria. Finally, the conclusion is
provided in Sect. 5.
123
295
The circles represent outliers (observations greater than the third quartile plus 1.5 times the
interquartile range or smaller than the first quartile minus 1.5 times the interquartile range).
For most of the data groups, the median is not in the center of the box, which indicates that
the distribution of most data groups is not symmetric (Fig. 2). In addition, all dependent
variables have some outliers expect pillar stress and pillar strength for all PS types, UCS
for S and U types, and pillar width for U type. As shown in Fig. 3, the scatterplot matrix in
the upper panel describes the pairwise relationship between parameters with corresponding
correlation coefficients showing in the lower panel, whereas the marginal frequency distribution for each parameter is demonstrated on the diagonal. It can be seen that the
parameter UCS is notably correlated with pillar strength and pillar stress and that pillar
height is notably correlated with pillar width.
123
296
Monte Carlo simulation. Ghasemi et al. (2014a, b) used major contributing parameters on
pillar stability such as mining height, depth of cover, entry width, panel width, pillar width,
pillar length, crosscut angle, roof strength rating, and loading condition. Moreover, the
UCS of the intact rock is used as it is an index that can be utilized in a simpler way without
carrying out pillar strength estimation (Wattimena 2014). Pillar shape expressed by the
ratio of the pillar width to pillar height (K) that accounts for the increased strength provided by the shape and confinement of the pillar. As noted above, various researchers have
determined strength of the hard rock pillars based on empirical formulas, which is based on
parameter pillar width, pillar height, and UCS (Hedley and Grant 1972; Lunder 1994;
Martin and Maybee 2000; Esterhuizen et al. 2011). On the other hand, the pillar stability
graph typically involves two parameters: (1) pillar stress to UCS ratio and pillar width to
height ratio (K) (Lunder and Pakalnis 1994; Martina and Maybee 2000; Wattimena et al.
2014) or (2) pillar strength to stress ratio (SF) and K (Wattimena et al. 2013). Based on
these conditions, six relevant indicators are adopted in this study. There are as follows:
pillar width, pillar height, K, the uniaxial compressive strength (UCS) of the rock, pillar
strength, and pillar stress. Those indicators are recognized as the major parameters to
quantitatively discover the activities in context of pillar. Theoretically, there may be
additional indicators, but the data collection is a massive challenge for their applicability.
Hence, the six indicators are adopted, and compositions of the indicators are investigated to
discover the effects of varying indicators in the current study. In terms of pillar shape,
pillar strength, and pillar load, a number of experiments are performed using different
combinations of input parameters to assess the performance SL methods for PS, as listed in
Table 1.
Numerous scholars have conducted a variety of PS classification methods. In all of the
cases in the combined database, pillar stability assessments, which range from a simple
assessment of Stable/Failed to a more rigorous approach based upon a five- or six-stage
stability classification method (Hedley and Grant 1972; Von Kimmelman et al. 1984;
Lunder 1994), have been investigated. Reviewing the combined database and the suggestion of Lunder (1994), the PS is classified into three stages, which can be provided
adequate results for the combined database, i.e., stable (S), unstable (U), and failed (F), as
depicted in Table 2.
123
297
Pillar height
Pillar width
UCS
Pillar strength
Pillar stress
Table 2 Description of hard rock pillar stability classification for the combined database (Modified from
Lunder 1994)
Pillar stability
classification
Failed
Unstable
Stable
123
298
(c) they have efficient implementations; and (d) the resulting model allows for fast classification processing. The following six methods are compared with respect to their predictive performance. In this study, the feature vector X consists of six PS performance
modifiers {X1, X2, X3, X4, X5, X6}, which correspond to the variables discussed in Sect. 3.
The set of all feature vectors is denoted as H. Three PS states are defined, i.e., stable (S),
unstable (U), and failure (F), respectively, as Zi(i = 1, 2, 3). Each class Zi is associated
with a discriminant function fi(x). Several articles are published that compare multiple SL
techniques (e.g., Garzon et al. 2006; Berrueta et al. 2007; Sakiyama et al. 2008; PinoMejas et al. 2008, 2010; Pozdnoukhov et al. 2009; Zhou et al. 2011; Gonzalez-Rufino
et al. 2013). Based on these articles and the focus herein on PS classifications, only a brief
description of each classification technique will be presented. For a more in-depth discussion, the reader is referred to the relevant references.
where jRzj is the determinant of Rz, or, equivalently, to the class Z which maximizes the
linear function as follows:
The matrix
where X is the N 9 n-order training set matrix, Q is the N 9 M-order matrix of class
indicators, and M is the M 9 n matrix with the class means, n, N, and M denote the number
of inputs, training patterns, and classes, respectively.
123
299
123
300
2.5 R Software
R (R Development Core Team 2013) is a popular open-source software environment for
statistical computing and data visualization available for most mainstream platforms
(http://www.R-project.org/). All data processing is performed using R software (version
3.02). R provides the most common SL classification methods. Herein, we will only list
some of them. Further details about input parameters, implementation, and references can
be found in package documentation manuals. The packages necessary for each method and
the functions utilized to build the models are summarized in Table 3.
R package
R function
Tuning
parameters
References
LDA
MASS
lda
None
MLR
nnet
multinom
{g}
ANN
nnet
nnet
{L, g}
SVM
kernlab
svmRadial
{C, r}
RF
randomForest
randomForest
ntree, mtry
GBM
gbm
gbm
{ntree, v, J}
Default function parameters are considered, optimized by tenfold CV whenever possible; mtry = number of
variables to choose the best split; ntree = number of trees; L = number of hidden neurons in the MLP;
g = decay parameter; C = penalization error coefficient; r = width of radial basis in the SVM function;
v = shrinkage; J = interaction.depth
123
301
PS are predicted and subsequently the misclassification error rate is calculated with the
preferred classifier being the one with the lowest misclassification error rate. Scaling of the
inputoutput data is generally required prior to processing. All input variables are scaled
with function preProcess, which can be used to impute data sets based only on information
in the training set (Kuhn 2008).
m
nRm
i1 rii Ri1 ri ri
m
2
n Ri1 ri ri
where xii is the cell count in the main diagonal, n is the number of examples, Z is the
number of class values, and r?i, ri? are the columns and rows total counts, respectively.
Table 4 Population confusion matrix with rij representing the proportion of area in the prediction category
i and the observation category j
Predicted
Observed
1
Total
UA (%)
(r11/r1?) 9 100 %
r11
r12
r1m
r1?
r21
r22
r2m
r2?
(r22/r2?) 9 100 %
rm1
rm2
rmm
rm?
(rmm/rm?) 9 100 %
Total
r?1
r?1
r?m
PA (%)
(r11/r?1) 9
100 %
(r22/r?2) 9
100 %
(rmm/r?m) 9
100 %
123
302
Table 5 Relative strength of
agreement associated with kappa
statistic
Kappa statistic
Strength of agreement
0.811.00
Almost perfect
0.610.80
Substantial
0.410.60
Moderate
0.210.40
Fair
0.000.20
Slight
-1.000.00
Poor
The kappa measures the correct classification rate after the probability of chance
agreement has been removed (Congalton 1991). Landis and Koch (1977) proposed a scale
to describe the degree of concordance (Table 5); the kappa ranges from -1 (total disagreement) through 0 (random classification) to 1 (perfect agreement), as can be seen from
Table 5; a value of kappa below 0.4 is an indication of poor agreement and a value of 0.4
and above is an indication of good agreement (Landis and Koch 1977; Sakiyama et al.
2008).
According to Congalton and Green (2009), producers accuracy of class i (PAi) can be
computed by
pii
pii
100 %
100 %
10
PAi
pm
Rm
i1 pim
and the users accuracy of class i (UAi) can be computed by
!
pii
pii
100 %
100 %
UAi
pm
Rm
j1 pmj
11
123
303
Stable
Unstable
Failed
Training Set
(70%)
Test Set
(30%)
R environment
Fig. 4 Overall procedure flowchart for performance evaluation for PS classification using SL methods
123
304
Turning parameters
Model A
Model B
Model C
Model D
LDA
None
None
None
None
MLR
g = 0.1000
g = 0.1000
g = 0.0001
g = 0.1000
RF
ANN
{L, g} = {15,
0.0421}
{L, g} = {17,
0.0074}
{L, g} = {19,
0.0075}
SVM
GBM
{ntree, v, J} = {400,
0.1, 2}
{ntree, v, J} = {150,
0.1, 10}
{ntree, v, J} = {50,
0.1, 10}
{ntree, v, J} = {500,
0.1, 6}
value 500 and mtry is tested for t values, where t is the number of input layers in each
classification setup.
ANN: The number H of hidden neurons in the range 1 \ H \ 19 (ten values), and
trying 10 random weight initializations (decay). Delay = {0, 1e-04, 0.000237,
0.000562, 0.00133, 0.00316, 0.0075, 0.0178, 0.0422, and 0.1}.
SVM: The parameter C is tuned for 12 values (2-2, 2-1, 20, 21, 22, 23, 24, 25, 26, 27, 28,
and 29) to find the optimal model. The caret package initially estimates an
approximate value for the sigma parameter using the sigest function based on the
training data.
GBM: The GBM has three tweaking parameters: the total number of iterations
(n.trees), the learning rate (shrinkage parameter v), and the complexity of the tree
(indexed by interaction.depth J). Tuning parameter shrinkage is held constant at a
value of 0.1, n.trees = 50, 100, 150, 200, 250, 300, 350, 400, 450, 500; J = 1, 2, 3, 4,
5, 6, 7, 8, 9, 10.
123
305
(a) Model A
(b) Model B
(c) Model C
(d) Model D
123
306
(a) Model A
(b) Model B
(c) Model C
(d) Model D
123
307
Model A
Model B
Model C
Model D
OA (%)
Kappa
OA (%)
Kappa
OA (%)
Kappa
OA (%)
Kappa
LDA
67.8
0.461
59.5
0.345
63.5
0.389
64.9
0.424
MLR
66.2
0.436
63.5
0.392
63.5
0.388
63.5
0.400
RF
82.4
0.723
75.7
0.609
71.6
0.543
73.0
0.576
ANN
81.1
0.703
75.7
0.611
75.7
0.613
75.7
0.615
SVM
82.4
0.726
68.9
0.502
71.6
0.550
79.7
0.684
GBM
79.7
0.678
77.0
0.636
66.2
0.474
75.7
0.616
2013). Figure 6 illustrates density plots of the 200 bootstrap estimates of accuracy and
kappa for the final model. Table 7 summarizes the overall predictability of test set by
comparing two measures between six classifiers, OA and kappa. The kappa is a measure of
true accuracy which takes into account the agreement that may have occurred by chance. It
is considered to be preferable when it is larger than 0.4 (Landis and Koch 1977). Not
surprisingly, the linear methods, such as LDA and MLR, did not do well herein, and this is
likely due to the model inability to handle nonlinear class boundaries. For the model A, in
terms of average accuracy rate for training set, SVM predictor achieved the highest OA
(84.3 %) and followed by ANN, GBM, and RF with average accuracy rates of 83.2, 80.9,
and 77.8 %, respectively. MLR performed relatively worse with an average accuracy rate
of 69.3 %, and LDA with the lowest average accuracy rate of 67.0 %. However, RF and
SVM achieved the highest OA (82.4 %) for test set. ANN performed relatively worse with
OA (81.1 %), and LDA with the lowest OA (66.2 %). One the other hand, the kappa of the
LDA, MLR, RF, ANN, SVM, and GBM techniques for training set and test set in model
calibration data is from moderate to substantial on the basis of the scale of concordance
presented by Landis and Koch (1977). The accuracies of all modeling techniques for the
model evaluation test set are from moderate to substantial according to the scale of concordance. For the model B, ANN predictor achieves the highest OA (80.3 %) for training
set and followed by RF, GBM, and SVM with average accuracy rates of 79.1, 78.4, and
76.9 %, respectively. LDA performs relatively worse with an average accuracy rate of
65.7 %, and MLR with the lowest average accuracy rate of 65.3 %. However, GBM
achieves the highest OA (77.0 %) for test set. GBM, ANN, and SVM performed relatively
worse with OA (75.778.4 %), and LDA with the lowest OA (59.5 %). One the other hand,
the kappa of LDA, MLR, RF, ANN, SVM, and GBM techniques for training set in model
calibration data is from moderate to substantial. The accuracies of all modeling techniques
for the model evaluation test set are from fair to substantial. Similarly, results for model C
and D can be seen in Fig. 5 and Table 7. We can observe the following facts: For the six
SL techniques, the performance (in terms of accuracy) of the training set falls into the
range of (65.384.3 %) across the four models, while the performance (in terms of
accuracy) of the test set performance falls into the range of (59.582.4 %). The predictive
accuracy of LDA, MLR, RF, ANN, SVM, and GBM techniques for the training set in
model calibration data ranges from moderate to substantial. The accuracy of all modeling
techniques for the test set ranges from fair to substantial.
123
308
123
69.2 %
PA (%)
26
26
88.5 %
Total
PA (%)
90.6 %
32
29
56.3 %
16
0.0 %
26
74
74
13
35
69.2 %
82.9 %
88.5 %
0.0 %
PA (%)
Total
PA (%)
Total
92.3 %
26
24
88.5 %
26
23
88.5 %
26
23
Observed
90.6 %
32
29
90.6 %
32
29
90.6 %
32
29
37.5 %
16
56.3 %
16
50.0 %
16
74
11
35
28
74
14
31
29
74
14
34
26
Total
54.5 %
82.9 %
85.7 %
64.3 %
93.5 %
79.3 %
57.1 %
85.3 %
88.5 %
UA (%)
Diagonal elements (correct decisions) are marked in bold letters. OA overall classification accuracy, PA producers accuracy, UA users accuracy
23
96.9 %
16
66.0 %
69.2 %
PA (%)
32
47
GBM
26
Total
69.2 %
PA (%)
RF
31
Total
18
74
SVM
6.3 %
16
50.0 %
MLR
96.9 %
32
26
67.4 %
Total
46
31
69.2 %
26
ANN
Predicted
UA (%)
18
Total
Observed
LDA
Predicted
Table 8 Confusion matrices and associated classifier accuracies for best model predictions based on test data of hard rock pillars
123
310
Furthermore, Lunder and Pakalnis (1997) proposed that the pillar stability could be
adequately expressed by two SF lines. Pillars with a SF [1.4 stable while those with a SF
\1 are failed, and the transition zone from stable condition to failed condition
(1\SF \ 1.4) is referred to as unstable, and pillars in this region are prone to spalling and
slabbing but have not completely failed (Lunder and Pakalnis 1997; Martin and Maybee
2001). Similarly, work on classification of pillars in marble mines has been established by
Gonzalez-Nicieza et al. (2006); they suggested: SF [1.25 (stable), 0.90 \ SF \ 1.25
(unstable), and SF \0.90 (failed). The predictive accuracy of two methods is 68.9 %
(Lunder and Pakalnis 1997) and 68.5 % (Gonzalez-Nicieza et al. 2006) of the original data,
respectively. It is obvious judging from the predictive accuracy that the empirical methods
cannot generate satisfactory predictions on these pillar instances.
123
311
Strengths
Weaknesses
LDA
MLR
Computationally intensive
RF
SVM
ANN
GBM
the most sensitive factor among all response variables for model B and Model C, followed
by the indicator pillar strength, K, UCS. Figure 7d shows the different results between
model A and model D for variable importance of UCS and pillar width. However, these
results demonstrate that pillar stress is the most relevant predictor among the indicators for
the prediction of PS classification.
123
312
(a) Model A
(b) Model B
(c) Model C
(d) Model D
stability than other models. RF demonstrates that pillar stress is the most relevant PS
predictor for all models A, B, C, and D. Finally, for the six SL classifiers studied, the
performance (in terms of accuracy) of the training set falls in the range of 65.384.3 %
across the six models with different input parameter combination, while the performance
(in terms of accuracy) of the test set performance falls into the range of 59.582.4 %.
123
313
Acknowledgments This research was partially supported bythe National Natural Science Foundation
Project (Grant Nos. 11472311 and 41272304) of China, the Graduated Students Research, Innovation Fund
Project (Grant No. CX2011B119) of Hunan Province of China, Project (Grant No. 1343-76140000022)
supported by the Scholarship Award for Excellent Doctoral Student of Ministry of Education of China and
the Valuable Equipment Open Sharing Fund of Central South University. The authors would like to express
thanks to these foundations. The first author would like to thank the Chinese Scholarship Council for
financial support to the joint PhD at McGill University, Canada. We also would like to thank the three
anonymous referees and editors for their valuable comments and suggestions which improved a previous
version of this manuscript.
References
Berrueta LA, Alonso-Salces RM, Heberger K (2007) Supervised pattern recognition in food analysis.
J Chromatogr A 1158(12):196214
Bieniawski ZT (1968) The effects of specimen size on the compressive strength of coal. Int J Rock Mech
Min Sci Geomech Abstr 5(4):325335
Bieniawski ZT, Van Heerden WL (1975) The significance of in situ tests on large rock specimens. Int J
Rock Mech Min Sci Geomech Abstr 12(4):101113.
Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, New York
Brady B, Brown ET (2003) Rock mechanics for underground mining, 2nd edn. Chapman and Hall, London
Breiman L (2001) Random forests. Mach Learn 45:532
Breiman L, Cutler A (2007) Randomforestsclassification description: randomforests. http://stat-www.
berkeley.edu/users/breiman/RandomForests/cc_home.htm. Accessed 15 Jan 2014
Cauvin M, Verde T, Salmon R (2009) Modeling uncertainties in mining pillar stability analysis. Risk Anal
29(10):13711380
Clark M (2013) An introduction to machine learning: with applications in R. http://www3.nd.edu/
*mclark19/learn/ML.pdf
Congalton RG, Green K (2009) Assessing the accuracy of remotely sensed data: principles and practices,
2nd edn. Lewis, Boca Raton
Deng J, Yue ZQ, Tham LG, Zhu HH (2003) Pillar design by combining finite element methods, neural
networks and reliability: a case study of the Feng Huangshan copper mine, China. Int J Rock Mech
Min Sci 40(4):585599
Elmo D, Stead D (2010) An integrated numerical modellingdiscrete fracture network approach applied to
the characterisation of rock mass strength of naturally fractured pillars. Rock Mech Rock Eng
43(1):319
Esterhuizen GS (1993) Variability considerations in hard rock pillar design. In: Proceedings of the SANGORM symposium: rock engineering problems related to hard rock mining at shallow to intermediate
depth, Rustenburg, South Africa
Esterhuizen GS, Dolinar DR, Ellenberger JL (2011) Pillar strength in underground stone mines in the United
States. Int J Rock Mech Min Sci 48(1):4250
Fisher DH (1936) The use of multiple measurements in taxonomic problems. Ann Eugen 7(7):179188
Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat
29(5):11891232
Garzon MB, Blazek R, Neteler M, de Dios RS, Ollero HS, Furlanello C (2006) Predicting habitat suitability
with machine learning models: the potential area of Pinus sylvestris L. in the Iberian Peninsula. Ecol
Model 97:383393
Ghasemi E, Shahriar K (2012) A new coal pillars design method in order to enhance safety of retreat mining
in room and pillar mines. Saf Sci 50:579585
Ghasemi E, Shahriar K, Sharifzadeh M, Hashemolhosseini H (2010) Quantifying the uncertainty of pillar
safety factor by Monte Carlo simulationa case study. Arch Min Sci 55:623635
Ghasemi E, Ataei M, Shahriar K (2014a) An intelligent approach to predict pillar sizing in designing room
and pillar coal mines. Int J Rock Mech Min Sci 65:8695
Ghasemi E, Ataei M, Shahriar K (2014b) Prediction of global stability in room and pillar coal mines. Nat
Hazards 118
Gonzalez-Nicieza C, Alvarez-Fernandez MI, Menendez-Daz A, Alvarez-Vigil AE (2006) A comparative
analysis of pillar design methods and its application to marble mines. Rock Mech Rock Eng
39(5):421444
123
314
123
315
Mark C, Barton TM (1997) Pillar design and coal strength. In: Proceedings of the New Technology for
Ground Control in Retreat Mining. US Department of Health and Human Services, Public Health
Service, Centers for Disease Control and Prevention, National Institute for Occupational Safety and
Health, Pittsburgh, PA, pp 4959, DHHS (NIOSH) Publication (No. 97122)
Martin CD, Maybee WG (2000) The strength of hard-rock pillars. Int J Rock Mech Min Sci 37:12391246
Mitri HS (2007) Assessment of horizontal pillar burst in deep hard rock mines. Int J Risk Assess Manag
7(5):695707
Molinaro AM, Simon R, Pfeiffer RM (2005) Prediction error estimation: a comparison of resampling
methods. Bioinformatics 21(15):33013307
Monjezi M, Hesami SM, Khandelwal M (2011) Superiority of neural networks for pillar stress prediction in
bord and pillar method. Arab J Geosci 4(56):845853
Mortazavi A, Hassani FP, Shabani M (2009) A numerical investigation of rock pillar failure mechanism in
underground openings. Comput Geotech 36(5):691697
Pandya DH, Upadhyay SH, Harsha SP (2014) Fault diagnosis of rolling element bearing by using multinomial logistic regression and wavelet packet transform. Soft Comput 18(2):255266
Pino-Mejas R, Carrasco-Mairena M, Pascual-Acosta A, Cubiles-De-La-Vega M, Joaqun Munoz-Garca J
(2008) A comparison of classification models to identify the Fragile X Syndrome. J Appl Stat
35(3):233244
Pino-Mejas R, Cubiles-de-la-Vega MD, Anaya-Romero M, Pascual-Acosta A, Jordan-Lopez A, Bellinfante-Crocci N (2010) Predicting the potential habitat of oaks with data mining models and the R
system. Environ Model Softw 25(7):826836
Potvin Y, Hudyma M, Miller HDS (1989) Rib pillar design in open stope mining. Bull Can Inst Min Metall
82(927):3136
Pozdnoukhov A, Foresti L, Kanevski M (2009) Data-driven topo-climatic mapping with machine learning
methods. Nat Hazards 50(3):497518
R Development Core Team (2013) R: a language and environment for statistical computing. R Foundation
for Statistical Computing, Vienna, Austria. ISBN 3-900051-07-0. http://www.R-project.org/
Ridgeway G (2007) Generalized boosted models: a guide to the gbm package. http://cran.r-project.org/web/
packages/gbm/index.html
Ripley B (2009) Nnet: feed-forward neural networks and multinomial log-linear models. http://cran.rproject.org/web/packages/nnet/index.html
Sadat-Hashemi SM, Kazemnejad A, Lucas C, Badie K (2005) Predicting the type of pregnancy using
artificial neural networks and multinomial logistic regression: a comparison study. Neural Comput
Appl 14(3):198202
Sakiyama Y, Yuki H, Moriya T, Hattori K, Suzuki M, Shimada K, Honma T (2008) Predicting human liver
microsomal stability with machine learning techniques. J Mol Graph Model 26:907915
Salamon MDG (1970) Stability, instability and design of coal pillar workings. Int J Rock Mech Min Sci
Geomech Abstr 7(6):613631
Salamon MDG, Munro AH (1967) A study of the strength of coal pillars. J South Afr Inst Min Metall
68:5567
Sheng JH, Liao WJ, Li WM (2010) Analysis of pillar safety factor in Gaoshan gypsum mine. Metal Mine
(suppl.):791793
Sjoberg JS (1992) Failure modes and pillar behaviour in the Zinkgruvan mine. In: Tillerson JA, Wawersik
WR (eds) Proceedings of the 33rd U.S. rock mechanics symposium. A.A. Balkema, Sante Fe. Rotterdam, pp 491500
Tawadrous AS, Katsabanis PD (2007) Prediction of surface crown pillar stability using artificial neural
networks. Int J Numer Anal Meth Geomech 31(7):917931
Tesfamariam S, Liu Z (2010) Earthquake induced damage classification for reinforced concrete buildings.
Struct Saf 32(2):154164
Vapnik VN (1995) The nature of statistical learning theory. Springer, New York
Venables WN, Ripley BD (2002) Modern applied statistics with S. Springer, New York
Von Kimmelman MR, Hyde B, Madgwick RJ (1984) The use of computer applications at BCL Limited in
planning pillar extraction and design of mining layouts. In: Proceedings of the ISRM symposium:
design and performance of underground excavations. British Geotechnical Society, London, p 53J63
Wattimena RK (2014) Predicting the stability of hard rock pillars using multinomial logistic regression. Int J
Rock Mech Min Sci 71:3340
Wattimena RK, Kramadibrata S, Sidi ID, Azizi MA (2013) Developing coal pillar stability chart using
logistic regression. Int J Rock Mech Min Sci 58:5560
York G (1998) Numerical modelling of the yielding of a stabilizing pillar/foundation system and a new
design consideration for stabilizing pillar foundations. J. S.A. Inst Min Metall 98:281293
123
316
Zhou J, Shi XZ, Dong L, Hu HY, Wang HY (2010) Fisher discriminant analysis model and its application
for prediction of classification of rockburst in deep-buried long tunnel. J Coal Sci Eng 16(2):144149
Zhou J, Li XB, Shi XZ, Wei W, Wu BB (2011) Predicting pillar stability for underground mine using Fisher
discriminant analysis and SVM methods. Trans Nonferrous Metals Soc China 21(12):27342743
Zhou J, Li XB, Shi XZ (2012) Long-term prediction model of rockburst in underground openings using
heuristic algorithms and support vector machines. Saf Sci 50(4):629644
Zhou J, Li XB, Mitri HS, Wang SM, Wei W (2013) Identification of large-scale goaf instability in
underground mine using particle swarm optimization and support vector machine. Int J Min Sci
Technology 23(5):701707
123