Submit manuscript...
MOJ
eISSN: 2572-8520

Civil Engineering

Research Article Volume 6 Issue 1

Artificial neural network application to the compressive strength of palm kernel shell concrete

Elinwa Augustine Uchechukwu,1 Okhide Austin2

1Department of Civil Engineering, Abubakar Tafawa Balewa University, Nigeria
2Federal Roads Maintenance Agency, Nigeria

Correspondence: Elinwa, Augustine Uchechukwu, Department of Civil Engineering, Abubakar Tafawa Balewa University, PMB 0248, Bauchi State, Nigeria

Received: January 28, 2020 | Published: February 17, 2020

Citation: Uchechukwu EA, Austin O. Artificial neural network application to the compressive strength of palm kernel shell concrete. MOJ Civil Eng.2020;6(1):1-10. DOI: 10.15406/mojce.2020.06.00164

Download PDF

Abstract

 This work is on the application of Artificial Neural Network (ANN) to study the effects of using palm kernel shells (PKS) as aggregates on the compressive strength of concrete. ANN with an input neuron of 6 factors, 2 hidden layers, 18 and 12 each and 1 output neuron for the compressive strength were used for this work. A mix ratio of 1: 1.5: 3 with cement content of 382kN/m3, water-cement ratio of 0.55 were used for the work, and cured for 90 days. A total of fifty concrete mixes containing PKS in various proportions of 0 % to 40 % by wt. of the coarse aggregate were used for the training. For the validation and testing ten mixes were used.. Therefore, sixty (60) data sets were generated for which approximately eighty (80) percent was used for the training, and twenty (20) percent for the validation and test. The results showed that the distribution characteristic of PKS-concrete using ANN is adequate for the prediction of compressive strength. The predicted and experimental results are strongly correlation, with a model equation with an intercept, 1.5 and a slope of 0.93. The characteristic distribution results of the predicted with the experimental showed that the parameter estimates (ANN and Statistics), are within the 95 % confidence limits (CI), and very significant (P<0.05).

Keywords: ANN, palm kernel shells aggregate, compressive strength, statistical characteristics, PKs-concrete age

Abbreviations

ANN, artificial neural network; NWA, normal weight aggregate; MLRA, multiple linear regression analysis; LWAC, lightweight aggregate concrete; NND, neural network design

Introduction

The development and construction pressures on our conventional materials and the growing needs for sustainability have opened up new areas for research, thus motivating researchers to focus their investigations on the use of waste or recycled materials for potential use as construction materials. The use of palm kernel shells as replacement materials for normal weight aggregate (NWA) have attracted the interest of researchers in the palm oil producing nations for use in the concrete industry. Research works on the use of palm kernel shells as aggregate materials to replace conventional aggregates in concrete have been extensively carried out and some of these works were cited as references.1–12 on the “characteristics of palm kernel shell-concrete.” The testing for strength of concrete specimen is complicated. It is equally a time consuming task. The performance of concrete is affected by many non-linear factors, more importantly, is the cost of running these experiments, when the expected strengths are not achieved using the conventional materials and methods of mix design. The reasons are there are no fixed formulations for mixing concrete constituents to obtain the compressive strength because concrete mixing is predominantly a qualitative knowledge-based approach subjected to variations.

Faraqui et al.,13 and Khashman and Akpinar,14 have argued the fact that reliance on such an approach compromised the precision and accuracy of concrete properties and hence, necessitates the development of a reliable mixing formulation. They also stated that statistical modeling techniques like multiple linear regression analysis (MLRA) which have been used in the past have failed to accurately predict the compressive strength, because of the highly nonlinear relationship between the concrete proportions and its properties. Researchers therefore, have come with a new trend in modern concretes involving the applications of new methods like the artificial neural network (ANN) which will enhance creditability and acceptability of our concrete works containing additives and non conventional materials. ANNs are software constructs that can be trained by example to recognize (clarify), or estimate (predict) results from a variety of inputs. The ANN ability to learn so quickly is what makes them so powerful and useful for a variety of tasks, and contains three main sections, classified as, input layer, hidden layer, and output layer.

Faruqi et al.,13 developed a neural network model for predicting the compressive strength of concrete for different mix-design parameters. This was based on five (5) hidden layers and trained using the results of a series of previously conducted experiments. Each experiment consisted of five (5) parameters and a corresponding compressive strength obtained from 28-days cylinders tests. They observed that the neural network model performed with satisfactory results in predicting the 28-day compressive strength of concrete.

Yoon et al.,14 worked on the mechanical properties of lightweight aggregate concrete using ANN. The study presented the ANN-based prediction for compressive strength and elastic modulus of lightweight aggregate concrete (LWAC), and concluded that the ANN model showed acceptable prediction accuracy with respect to the compressive strength and elastic with respect to compressive strength and elastic modulus of LWAC, and that the highest prediction accuracy was obtained by the ANN model compared to the use of statistical linear and nonlinear regression model.

The reviewed works on this topic were largely to some extent on the strength at 28days, and are equally based on empirical and statistical methods. These methods have limited applications, and are characterized with the issues of accuracies and precisions. Therefore, the present study on the compressive strength of PKS-concrete addressed these issues, firstly, curing beyond the conventional 28 days to 90 days, and secondly, by employing the ANN to address the issues of accuracies and precisions Khashman and Akpinar,14 Golizadeh and Namini.,15 Faruqi et al.,13 Suryadi et al.,16. The ANN architecture used had six (6) inputs with six (6) neurons, two (2) hidden layers with eighteen (18) and twelve (12) neurons respectively, and one (1) output layer with one neuron.

Materials

The physical and chemical properties of the cement are shown in Tables 1 & 2 and conformed to BS EN 196-3.17 The fine aggregate was river sand which is free from deleterious matters with a specific gravity of 2.64, bulk density of 1528 kg/m3, and moisture content of 0.42. The fine aggregate was uniformly graded and falls into zone 2 of the grading curve. Table 3 is the sieve analysis of the fine aggregate. The coarse aggregate was sourced from a quarry site in Bauchi town and has a maximum size of 20mm. The physical characteristics of the coarse aggregate and PKS are shown in Table 4, while Table 5 is the particle size distribution. Both the fine and coarse aggregates conform to BS EN 1097.18 The palm kernel shell used was sourced from Ekpoma, Edo State, Nigeria. Ekpoma is a town in the savannah region, in the southern part of the country.

Parameter

Value

Specific gravity

2.98

Bulk density(kg/m3)

1475

Specific surface area(Blaine)m2/kg

355

Loss on ignition(%)

1.51

Moisture content

0.39

pH

12.4

Table 1 Physical properties of ashaka pc

Oxide composition

Percentage by weight (%)

CaO

62.12

SiO2

20.69

Al2O3

6.14

Fe2O3

2.32

SO3

1.63

MgO

1.22

Na2O

0.9

K2O

1.01

Table 2 Chemical properties of ashaka pc

Sieve size

Cumulative % passing

5.00mm

 _

2.00mm

93.00

1.18mm

78.00

600μm

43.80

300μm

20.40

150μm

8.20

63μm

8.16

Pan

0.00

Table 3 Sieve analysis of fine aggregate

Physical properties

Gravel

 PKS

Specific gravity

2.75

1.33

Bulk density (kg/m3)

1,714

694

Water absorption (%)

0.04

17.48

Void ratio

0.38

0.48

Porosity

0.27

0.32

ACV (%)

3.69

0.36

AIV (%)

7.28

1.91

Table 4 Characteristics of the coarse aggregate and palm kernel shells

Sieve size(mm)

Cumulative Passing (%)

Coarse aggregate

Palm kernel shell

75

-

-

63

-

-

50

-

-

37

-

-

28

-

-

20

94.4

-

14

65.9

98.5

10

24.9

64.8

6.3

3.7

10.7

5

1.5

3.1

3.35

0.6

1

Pan

0

0

Table 5 Particle size distribution of the coarse aggregate and palm kernel shell

Laboratory experiment on PKS-concrete

The experiment to study the characteristics of PKS-concrete was mounted using a concrete mix ratio of 1:1.5:3, with a cement content of 382 kg/m3 and water-cement ratio of 0.55 (Table 6). Four mix parameters were used and labeled M-00, M-10, M-20, and M-30, respectively. The mix labeled M-00 was the control, while the rest were having the various replacement levels of PKS by wt % of the crushed aggregate. The experiment for the compressive strength test was carried out using mould cube sizes of 100 mm, and tested in accordance with ASTM C192/C192M.19 They were cured for 3 days to 90 days before testing to failure using a motorized ELE-machine. At the end of each curing regime, three samples were tested to failure and the average recorded. The experimental results are shown in Table 7.

Mix type

Cement (kg/m3)

PKS (kg/m3)

Sand(kg/m3)

Cement (kg/m3)

Water(kg/m3)

W/C

M-0

1265

----

543

382

210

0.55

M-10

1138.5

126.5

543

382

210

0.55

M-20

1012

253

543

382

210

0.55

M-30

885.5

379.5

543

382

210

0.55

Table 6 Concrete mix proportions for the experiments

Mix No

3d

7d

28d

60d

90d

M-00

17.9

21.3

24

28.3

33.8

M-10

22.2

23.3

24

24.8

26.5

M-20

12.9

14.5

16.9

19

21.2

M-30

8.5

10.4

11.8

13.3

15.6

Table 7 Compressive strength experimental result

Discussion on the PKS material/compressive strength of PKS-concrete

The compressive strength of PKS-concrete Table 7 showed that as the replacement levels increased, the compressive strength decreased. The maximum strength was at 10%. At this replacement the strengths at 60days and 90 days above the strengths at 28days are 3% and 10% respectively The reductions in strength have been attributed to many factors such as the low strength of PKS compared to the crushed aggregate, the irregular shape of PKS which could prevent adequate compaction, and the bonding between PKS and cement paste because of the smooth surfaces of the PKS.20

Characteristics of distribution of PKS-concrete

Table 8 shows the distribution characteristics of the PKS-concrete. Measurements were made on the mean, standard error of the mean (SE.Mean), standard deviation (Std.Dev) and coefficient of variation (Coef.Var) for the curing period curing (90 days). The values achieved on the measurements showed good uniform characteristics of PKS-concrete.

The Reliability/Survival studies of the distribution analysis (Arbitrary Censoring), using the Parametric Distribution Analysis (PDA) method in Minitab 17 Software showed the degree to which these tests were consistent and stable in measuring what were intended to measure, and that the tests actually measured what they claimed to measure. These validate the extent to which inferences, conclusions, and decisions made on the basis of these test measurements are appropriate and meaningful. The results are shown in Table 9. The ninety-five percent confidence interval characteristics of the distributions for three parameters Mean, Std. Dev and Median are given in table

Age(Days)

Mean

SE mean

Std. Dev

Variance

CoefVar

3

15.4

3

6

35.5

38.7

7

17.4

3

6

35.8

34.4

28

19.2

3

6

35.4

31

60

21.4

3.3

6.6

43.5

30.9

90

24.3

3.9

7.8

60.1

31.9

Table 8 Distribution characteristics

Age (days)

Parameter

Estimate

Standard error

95 % Confidence

Interval

Mean (MITF)

15.44

2.52

11.21

21.26

Std. Dev

5.02

1.66

2.63

9.6

3

Median

15.43

2.69

10.96

21.71

Mean (MITF)

17.47

2.49

13.21

23.1

Std. Dev

4.96

1.67

2.56

9.61

7

Median

17.58

2.64

13.1

23.59

Mean (MITF)

19.29

2.42

15.08

24.67

Std. Dev

4.83

1.67

2.45

9.51

28

Median

19.49

2.54

15.09

25.17

Mean (MITF)

21.45

2.75

16.67

27.58

Std. Dev

5.49

1.84

2.85

10.58

60

Median

21.65

2.89

16.67

28.13

Mean (MITF)

24.34

3.39

18.52

31.98

Std. Dev

6.74

2.15

3.61

12.58

90

Median

24.51

3.58

18.41

32.62

Table 9 Confidence interval (95%) characteristics of distribution of PKS-concrete

Mix proportions

  1. For Training: The mix proportions used for both the training and validation for the ANN are shown in Tables 10 & 11 A total of 60 data sets were used and they formed both the input and output data sets. Eighty (80) percent of the data sets were used for the training, and twenty (20) percent for testing and validation. The experiments were divided into two sets, one for the network learning, called learning set, and the other for validating the network, called testing set. Each set consisted of six components, cement (kg/m3), FA and CA (kg/m3), PKS (kg/m3), Age and water (kg/m3). The output vector had only one strength component, which is the compressive strength. There were fifty (50) pairs of vectors in the learning set, and ten (10) in the testing set.
  2. For Testing and Validation: The Artificial Neural Network (ANN, The neural network architecture used for this investigation is the ANN. Advantages of ANN is its adaptability to new data inputs, and it is simpler and more accurate in prediction.14 A computer program was developed using the neural network design (NND) toolbox in MATLAB. The model had a 6-2-1 configuration as shown in Figure 1. There were 6 nodes in the input layer with 6 neurons, corresponding to the 6 parameters, 2 in the hidden layers with 18 neurons in the first hidden layer, 12 neurons in the second layer, and 1 in the output layer with 1 neuron corresponding to the compressive strength. It was observed from literature that feed forward neural networks have the ability to do complex mapping of non-linear relations. Hence, the multilayer feed forward network was used in this model. To minimize the error the back propagation was used to perform the training. The feed forward neural network model which has the ability to do complex mapping of nonlinear relations was chosen, based on the accuracy of strength validation, and mean square error (MSE), given as:

MSE= 1mni=1n j=1m (tij yij)2(1)

Figure 1 Neural network architecture

Mix for the training input

Runs

Mix no

Cement(kg/m3)

Fine agg.(kg/m3}

Coarse agg.(kg/m3)

PKS(kg/m3)

Water(kg/m3)

1

M-00

382

543

1265

0

210

2

M-00

382

543

1265

0

210

3

M-10

382

543

1138.5

126.5

210

4

M-10

382

543

1138.5

126.5

210

5

M-10

382

543

1138.5

126.5

210

6

M-20

382

543

1012

253

210

7

M-20

382

543

1012

253

210

8

M-20

382

543

1012

253

210

9

M-30

382

543

885.5

379.5

210

10

M-30

382

543

885.5

379.5

210

11

M-00

382

543

1265

0

210

12

M-00

382

543

1265

0

210

13

M-00

382

543

1265

0

210

14

M-10

382

543

1138.5

126.5

210

15

M-10

382

543

1138.5

126.5

210

16

M-20

382

543

1012

253

210

17

M-20

382

543

1012

253

210

18

M-30

382

543

885.5

379.5

210

19

M-30

382

543

885.5

379.5

210

20

M-30

382

543

885.5

379.5

210

21

M-00

382

543

1265

0

210

22

M-00

382

543

1265

0

210

23

M-10

382

543

1138.5

126.5

210

24

M-10

382

543

1138.5

126.5

210

25

M-10

382

543

1138.5

126.5

210

26

M-20

382

543

1012

253

210

27

M-20

382

543

1012

253

210

28

M-20

382

543

1012

253

210

29

M-30

382

543

885.5

379.5

210

30

M-30

382

543

885.5

379.5

210

31

M-00

382

543

1265

0

210

32

M-00

382

543

1265

0

210

33

M-00

382

543

1265

0

210

34

M-10

382

543

1138.5

126.5

210

35

M-10

382

543

1138.5

126.5

210

36

M-20

382

543

1012

253

210

37

M-20

382

543

1012

253

210

38

M-30

382

543

885.5

379.5

210

39

M-30

382

543

885.5

379.5

210

40

M-30

382

543

885.5

379.5

210

41

M-00

382

543

1265

0

210

42

M-00

382

543

1265

0

210

43

M-10

382

543

1138.5

126.5

210

44

M-10

382

543

1138.5

126.5

210

45

M-10

382

543

1138.5

126.5

210

46

M-20

382

543

1012

253

210

47

M-20

382

543

1012

253

210

48

M-20

382

543

1012

253

210

49

M-30

382

543

885.5

379.5

210

50

M-30

382

543

885.5

379.5

210

Table 10 Mix proportions for network training

Mix Proportion for the Validation

Runs

Mix No

Cement(kg/m3)

Fine agg (kg/m3)

Coarse agg(kg/m3)

PKS(kg/m3)

Water(kg/m3)

1

M-00

382

543

1265

0

210

2

M-30

382

543

88.5

379.5

210

3

M-10

382

543

1138.5

126.5

210

4

M-20

382

543

1012

253

210

5

M-00

382

543

1265

0

210

6

M-30

382

543

885.5

379.5

210

7

M-10

382

543

1138.5

126.5

210

8

M-20

382

543

1012

253

210

9

M-00

382

543

1265

0

210

10

M-30

382

543

885.5

379.5

210

Table 11 Mix proportions for the validation

Where t is the largest target value and y is the output value.

The activation function was the sigmodal function with the epoch number set to 10000 to avoid over fitting and training. The process is defined as a nonlinear input-output relation between the influencing factors (Cement content, FA content, CA content, PKS content, Water content and Age of concrete [3-90days] and the compressive strength cured [3-90days].

The Levenberg Marquardt algorithm was chosen as the most efficient one for the training of the ANN. Approximately; eighty(80) percent of the data in Table 12 was used for the training, and was stopped when the network prediction closely matched the experimental results to avoid over fitting of the network. Figure 2 is the MSE/Epoch results for the training output with a minimum final mean square error of 0.0176 (1.76%). This stabilized at an epoch value of 412. Twenty(20) percent of the total data as shown in Table 13 were used for validation and testing. Figure 3 showed the test and validation of the MSE/Epoch results. The minimum final mean square error for the validation and test was 0.0267 or 2 67%, and stabilizes at 229. After the testing and validation the predicted results were compared with the experimental data. Table 14 shows the predicted output with respect to the experimental results and the error is approximately ±5. This shows a very strong correlation between the two results. The output against target model generated for the predicted and experimental results of the compressive strength is shown in Figure 4, and the model equation is given as:

fpredicted=1.5+0.93fexperimental(2)

Figure 2 Training epoch for compressive strength.

Figure 3 Training epoch for test and validation

Figure 4 Neural network output against target

Training

Training

Runs

Mix No

Age (Days)

Comp. str(kN/m3)

Runs

Mix No

Age(Days)

Comp. str. (kN/m3)

1

M-00

3

18

26

M-20

28

17.2

2

M-00

3

17.7

27

M-20

28

17.2

3

M-10

3

22.7

28

M-20

28

16.5

4

M-10

3

24

29

M-30

28

11.8

5

M-10

3

20.1

30

M-30

28

12

6

M-20

3

14.4

31

M-00

60

28

7

M-20

3

10.8

32

M-00

60

28

8

M-20

3

13.5

33

M-00

60

29

9

M-30

3

8.4

34

M-10

60

25

10

M-30

3

8.6

35

M-10

60

24.8

11

M-00

7

23.2

36

M-20

60

24.6

12

M-00

7

19.2

37

M-20

60

18.8

13

M-00

7

21.6

38

M-30

60

13.5

14

M-10

7

24

39

M-30

60

13.5

15

M-10

7

22

40

M-30

60

13

16

M-20

7

14

41

M-00

90

34.8

17

M-20

7

15.2

42

M-00

90

31

18

M-30

7

10.2

43

M-10

90

17

19

M-30

7

10.4

44

M-10

90

26.4

20

M-30

7

10.6

45

M-10

90

26

21

M-00

28

25,6

46

M-20

90

21

22

M-00

28

23.5

47

M-20

90

21.2

23

M-10

28

24.5

48

M-20

90

21.4

24

M-10

28

23.5

49

M-30

90

16

25

M-10

28

24

50

M-30

90

15.8

Table 12 Output results (training)

Validation output results

Runs

Mix No

Age (days)

Comp. Str

1

M-00

3

17.9

2

M-30

3

8.6

3

M-10

7

23.8

4

M-20

7

15.2

5

M-00

28

23

6

M-30

28

11.5

7

M-10

60

24.6

8

M-20

60

19.2

9

M-00

90

35.6

10

M-30

90

15

Table 13 Validation results

Property

Experimental versus predicted

Mix no

Age(days)

Experiment

Predicted

Error

Compressive Strength

M-00

3

17.9

22.9

-5

M-30

3

8.6

10.1

-5.2

M-10

7

23.8

19.1

4.7

M-20

7

15.2

14.7

0.5

M-00

28

23

25.6

-2.6

M-30

28

11.5

12.1

-0.6

M-10

60

24.6

24.2

0.4

M-20

60

19.2

19.4

-0.2

M-00

90

35.6

32

3.6

M-30

90

15

16.5

-1.5

Table 14 Experimental versus predicted results

with a correlation coefficient (r2) of 97.0 %. This shows a very high correlation between the experiment and the predicted. Sensitivity analysis on the experimental and predicted results using the Minitab 17 Statistical Software is given as:

fpredicted=3.99+0.806fexperimental     (3)

The regression model is significant with a p-value of 0.000, a standard deviation (s) of 2.532, and a correlation coefficient (r2) of 87.24%, The constant and experiment are significant with p-values of 0.116 and 0.000, respectively. Figures 5,6 are the normality and residual plots.

Figure 5 Normal probability plots.

Figure 6 Residual Plot.

Figures 7, 8 are the 3D surface plots of the experimental, predicted and age of PKS-concrete on one hand and the experimental, predicted and the error. The errors are within ±5.

Figure 7 Surface plots of the experiment, prediction and age.

Figure 8 Experiment, predicted and error.

The distribution characteristics of the experiment and the predicted results Table 15 are within the 95% CI, and very significant (p<0.05). The narrower the CI the better it is Mannan MA et al.21 If the CI is narrow, we can be quite confident that any effects far from this range had been ruled out by the study.22,23

Goodness of fit. [Anderson-Darling Adj]

Basic statistics

Estimates

Std. error

95 % Normal CI

Lower

Upper

Parameter

Mean (MTTF)

19.47

2.37

15.33

24.71

Experiment Result

1.443

Standard Deviation

7.46

1.48

5.05

11.02

Median

19.2

2.53

14.83

24.85

14.06

2.56

9.84

20.09

Mean (MTTF)

19.69

2.03

16.09

24.1

Predicted Result

Standard Deviation

6.4

1.27

4.34

9.44

1.365

Median

19.68

2.16

15.87

24.4

15.1

2.32

11.25

20.5

Table 15 Characteristics of distribution for the experimental and predicted results

Conclusion

The application of ANN to study the compressive strength of palm kernel shell (PKS) concrete has been evaluated, and the following are the conclusions.

  1. The compressive strength of PKS-concrete decreased as the percentage replacement increased, and the optimum replacement level was at 10%.
  2. The reduction in strength have been attributed to factors like PKS lower strength, irregular shapes and poor bonding of the cement paste.
  3. The distribution characteristics of PKS-concrete showed that PKS can be used for producing good concrete.
  4. The use of ANN for compressive strength evaluation gives reliable results.
  5. The comparison of the predicted and experimental results shows very strong correlation, and model equation has an intercept of 1.5, and a sloe of 0.93. The correlation coefficient is 97.0%.
  6. The Minitab 17 Statistical Software values for the predicted and experimental has an intercept of 3.99 and a slope of 0.806, with a correlation coefficient of 87.24%. This shows that the ANN gives more refined model output.
  7. The characteristic distribution results showed that the estimates are within the 95% confidence limits (CI), and very significant (P<0.05). The estimated values are within the specified lower and upper limits of CI.

Acknowledgement

None.

Conflicts of interest

The author declares that there are no conflicts of interest.

Funding

None.

References

  1. Alengram UJ, Al-Muhit BA, Bin-Jumaat MZ. Utilization of oil palm kernel shell as lightweight aggregate in concrete – A review. Construction and Building Materials. 2013;38:161–172.
  2. Okpala DC. Palm kernel shell as a lightweight aggregate in concrete. Build Environ. 1990;25(4):291–296.
  3. Okafor FO. Palm kernel shell as a lightweight aggregate for concrete. Cement Concrete Research, 1988;18(6):901–910.
  4. Daneshmand S, Saadatian O. Influence of oil palm shell on workability and compressive strength of high strength concrete. Annals of Faculty Engineering Hunedoara – International Journal of Engineering. Fascicule 2. 2011;51–56.
  5. Itam Z, Beddu S, Mohd-Kanol NL, et al. The feasibility of palm kernel shell as a replacement for coarse aggregate in lightweight concrete. International Conference on Advances in Renewable Energy and Technologies (ICARET): Earth and Enviromentl Science. 2016;32:012040.
  6. Osei DY, Jackson EN. Experimental study on palm kernel shells as coarse aggregates in concrete. International Journal of Science and Engineering Research. 2012;2 (8):1–6.  
  7. Teo DCL, Mannan MA, Kurian VJ. Structural concrete using oil palm shell (OPS) as lightweight aggregate. Turkish J Eng Env Sci. 2006;30(4);251–257
  8. Chai LJ, Shafigh P, Mahmud H, et al. Effect of Substitution of Normal Weight Coarse Aggregate with Oil-Palm-Boiler Clinker on Properties of Concrete. Sains Malaysiana. 2017;46(4):645–653.
  9. Traore YB, Messan A, Hannaw K, et al. Experimental investigations on the physical and mechanical properties of a lightweight concrete using oil palm shell as coarse aggregate. Journal of Materials Science and Engineering. 2018;A7(3):157–168.
  10.  Shafigh P, Jumaat MZ, Mahmud BM, et al. Lightweight concrete made from crushed oil palm shell: Tensile strength and effect of initial curing on compressive strength. Construction and Building Materials. 2012;27:252–258.
  11.  Poh-Yap S, Johnson-Alengaram U, Hung-Mo K, et al. High strength oil palm shell concrete beams reinforced with steel fibres. Materiales de Construcción. 2017;67(328):e142.
  12. Elinwa AU. Characteristics of palm kernel shell concrete. Advancements in Materials. 2018;2:75–88.
  13. MA faruqui, R Agarwala, J Sai A. Application of artificial intelligence to predict compressive strength of concrete from mix design parameters: A structural engineering application. Journal of Civil Engineering Research. 2010;5(6):158–161.
  14. A Khashman, P Akpinar. Non destructive prediction of compressive strength using neural networks. Procedia Computer Science. 2017;108C:2358–2362.
  15. Jin Y Yoon, Hyunjun Kim, Young Joo Lee, et al. Prediction model for mechanical properties of lightweight aggregate concrete using artificial neural network. Material. 2019;12(17):1–21.     
  16. Hamed Golizadeh, Saeed B Namini. Predicting the significant characteristics of concrete containing palm oil fuel ash. Journal of Construction in Developing Countries. 2015;20(1):85–98.
  17. Akhmad Suryadi, Trimilan Pujo Aji. Artificial neural networks for evaluating the compressive strength of self compacting concrete. J Basic Appl Sci Res. 2011;1(3):236–241.
  18. Methods of testing cement. Determination of setting times and soundness. 2016.
  19. Tests for mechanical and physical properties of aggregates. 2013.
  20. Standard Practice for Making and Curing Concrete Test Specimens in the Laboratory. 2002.
  21. Mannan MA, Ganapathy C. Mix Design for Oil Palm Shell Concrete. Cement and Concrete Research. 2001;31(9):1323–1325.
  22. Gupta SK. The relevance of confidence interval and P-value in inferential statistics. Indian J Pharmacol. 2012;44(1):143–144.
  23. http://www.medicine.ox.ac.uk/bandolier/painres/download/whatis/what_are_conf_inter.pdf .
  24. Atta A. Why should researchers report the confidence interval in modern research? Middle East Fertil Soc J. 2005;10:78–81.
Creative Commons Attribution License

©2020 Uchechukwu, et al. This is an open access article distributed under the terms of the, which permits unrestricted use, distribution, and build upon your work non-commercially.