Computational of Concrete Slump Model Based on H2O Deep Learning framework and Bagging to reduce Effects of Noise and Overfitting
DOI: http://dx.doi.org/10.30630/joiv.7.2.1201
Abstract
Concrete mixture design for concrete slump test has many characteristics and mostly noisy. Such data will affect prediction of machine learning. This study aims to experiment on H2O Deep Learning framework and Bagging for noisy data and overfitting avoidance to create the Concrete Slump Model. The data consists of cement, blast furnace slag, fly ash, water, superplasticizer, coarse aggregate, fine aggregate, age, slump, and compressive strength. A primary data for concrete mixed design using the fine aggregate material from Merapi Volcano, the hills of Muntilan, and Kalioro. The coarse aggregate was obtained from Pamotan, Jepara, Semarang, Ungaran, and Mojosongo Boyolali Central Java. The cement was using Gresik and Holcim product and the water was from Tembalang, Semarang. The experiment model with one input layer with 7 neurons, one hidden layer with 20 neurons, and one output layer with 1 neuron using activation function TanH, with parameter L1=1.0E-5, L2=0.0, max weight=10.0, epsilon=1.0E-8, rho=0.99, and epoch=800 is able to achieve RMSE of 2.272. This result shows that after introducing Bagging, the error can be reduced up to 2.5 RMSE approximately (50% lower) compared to the model without Bagging. The manually tested mixture data was used to model evaluation. The result shows that the model was able to achieve RMSE 0.568. Following this study, this model can be used for further research such as creating slump design practicum equipment/ application software.
Keywords
Full Text:
PDFReferences
A. Attia, S. Guettala, and R. Zaitri, “Using mixture design method to optimizing concretes characteristics made with binary and ternary sands,†World Journal of Engineering, vol. 18, no. 2, pp. 194–205, Jan. 2021, doi: 10.1108/WJE-05-2020-0184.
M. Timur Cihan, “Prediction of Concrete Compressive Strength and Slump by Machine Learning Methods,†Advances in Civil Engineering, vol. 2019, p. e3069046, Nov. 2019, doi: 10.1155/2019/3069046.
N. M. Tuan, Q. V. Hau, S. Chin, and S. Park, “In-situ concrete slump test incorporating deep learning and stereo vision,†Automation in Construction, vol. 121, p. 103432, Jan. 2021, doi: 10.1016/j.autcon.2020.103432.
B. Vakhshouri and S. Nejadi, “Prediction of compressive strength of self-compacting concrete by ANFIS models,†Neurocomputing, vol. 280, pp. 13–22, Mar. 2018, doi: 10.1016/j.neucom.2017.09.099.
C. E. Eki̇nci̇, “THE CALCULATION METHODS OF COMPOUND OF CONCRETE AND A NOVEL CALCULATION METHOD,†Technological Applied Sciences, vol. 1, no. 1, Art. no. 1, Feb. 2006, doi: 10.12739/10.12739.
T. Wangler, N. Roussel, F. P. Bos, T. A. M. Salet, and R. J. Flatt, “Digital Concrete: A Review,†Cement and Concrete Research, vol. 123, p. 105780, Sep. 2019, doi: 10.1016/j.cemconres.2019.105780.
J. B. Pereira and G. F. Maciel, “Automated slump test: An effective alternative in predicting rheological properties and an efficient tool for providing the quality control of materials,†Measurement, vol. 178, p. 109384, Jun. 2021, doi: 10.1016/j.measurement.2021.109384.
P. Gupta and N. N. Kulkarni, “An Introduction of Soft Computing Approach over Hard Computing,†2013.
W.-H. Chine, L. Chen, H.-H. Hsu, T.-S. Wang, and C.-H. Chiu, “Modeling Slump of Concrete Using the Artificial Neural Networks,†in 2010 International Conference on Artificial Intelligence and Computational Intelligence, Oct. 2010, vol. 3, pp. 236–239. doi: 10.1109/AICI.2010.287.
P. Chopra, R. K. Sharma, M. Kumar, and T. Chopra, “Comparison of Machine Learning Techniques for the Prediction of Compressive Strength of Concrete,†Advances in Civil Engineering, Apr. 12, 2018. https://www.hindawi.com/journals/ace/2018/5481705/ (accessed Jul. 09, 2020).
D.-C. Feng et al., “Machine learning-based compressive strength prediction for concrete: An adaptive boosting approach,†Construction and Building Materials, vol. 230, p. 117000, Jan. 2020, doi: 10.1016/j.conbuildmat.2019.117000.
C. Liang, C. Qian, H. Chen, and W. Kang, “Prediction of Compressive Strength of Concrete in Wet-Dry Environment by BP Artificial Neural Networks,†Advances in Materials Science and Engineering, Apr. 02, 2018. https://www.hindawi.com/journals/amse/2018/6204942/ (accessed Jul. 09, 2020).
H. Wang, X. Wang, C. Wang, and J. Xu, “Concrete Compression Test Data Estimation Based on a Wavelet Neural Network Model,†Mathematical Problems in Engineering, Feb. 11, 2019. https://www.hindawi.com/journals/mpe/2019/4952036/ (accessed Jul. 09, 2020).
F. Deng, Y. He, S. Zhou, Y. Yu, H. Cheng, and X. Wu, “Compressive strength prediction of recycled concrete based on deep learning,†Construction and Building Materials, vol. 175, pp. 562–569, Jun. 2018, doi: 10.1016/j.conbuildmat.2018.04.169.
R. Hidayat, Hendrick, Riandini, Z.-H. Wang, and H. Gwo-Jiun, “Mask RCNN Methods for Eyes Modelling,†International Journal of Data Science, vol. 2, no. 2, Art. no. 2, Dec. 2021, doi: 10.18517/ijods.2.2.63-68.2021.
- Mambang and F. D. Marleny, “Image Prediction of Exact Science and Social Science Learning Content with Convolutional Neural Network,†JOIV : International Journal on Informatics Visualization, vol. 6, no. 4, Art. no. 4, Dec. 2022, doi: 10.30630/joiv.6.4.923.
G. S. Saragih, Z. Rustam, D. Aldila, R. Hidayat, R. E. Yunus, and J. Pandelaki, “Ischemic Stroke Classification using Random Forests Based on Feature Extraction of Convolutional Neural Networks,†International Journal on Advanced Science, Engineering and Information Technology, vol. 10, no. 5, p. 2177, Oct. 2020, doi: 10.18517/ijaseit.10.5.13000.
S. Albawi, T. Abed Mohammed, and S. ALZAWI, “Understanding of a Convolutional Neural Network,†Aug. 2017. doi: 10.1109/ICEngTechnol.2017.8308186.
S. S. Berutu, Y.-C. Chen, H. Wijayanto, and H. Budiati, “A Conversion of Signal to Image Method for Two-Dimension Convolutional Neural Networks Implementation in Power Quality Disturbances Identification,†JOIV : International Journal on Informatics Visualization, vol. 6, no. 4, Art. no. 4, Dec. 2022, doi: 10.30630/joiv.6.4.1529.
D.-X. Zhou, “Universality of deep convolutional neural networks,†Applied and Computational Harmonic Analysis, vol. 48, Jun. 2019, doi: 10.1016/j.acha.2019.06.004.
M. A. Ghorbani, F. Salmasi, M. K. Saggi, A. S. Bhatia, E. Kahya, and R. Norouzi, “Deep learning under H2O framework: A novel approach for quantitative analysis of discharge coefficient in sluice gates,†Journal of Hydroinformatics, vol. 22, no. 6, pp. 1603–1619, Sep. 2020, doi: 10.2166/hydro.2020.003.
F. Sirait, M. T. Bin Jusoh, K. Dimyati, and M. F. Bin Md Din, “Determining Optimal Zone Radius of Zone Routing Protocol Based on Deep Recurrent Neural Networks in the Next Generation Wireless Backhaul Networks,†International Journal on Advanced Science, Engineering and Information Technology, vol. 12, no. 5, pp. 2147–2155, 2022, Accessed: Jan. 23, 2023. [Online]. Available: http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=15747
X. Li, R. Bai, P.-O. Siebers, and C. Wagner, “Travel time prediction in transport and logistics: Towards more efficient vehicle GPS data management using tree ensemble methods,†VINE Journal of Information and Knowledge Management Systems, vol. ahead-of-print, Jun. 2019, doi: 10.1108/VJIKMS-11-2018-0102.
S. Dahiya, S. S. Handa, and N. Singh, “A feature selection enabled hybrid-bagging algorithm for credit risk evaluation,†Expert Systems, vol. 34, p. e12217, May 2017, doi: 10.1111/exsy.12217.
M. Injadat, A. Moubayed, A. B. Nassif, and A. Shami, “Multi-split Optimized Bagging Ensemble Model Selection for Multi-class Educational Data Mining,†arXiv:2006.05031 [cs], Jun. 2020, doi: 10.1007/s10489-020-01776-3.
H. Hartono and E. Ongko, “Avoiding Overfitting dan Overlapping in Handling Class Imbalanced Using Hybrid Approach with Smoothed Bootstrap Resampling and Feature Selection,†JOIV : International Journal on Informatics Visualization, vol. 6, no. 2, Art. no. 2, Jun. 2022, doi: 10.30630/joiv.6.2.985.
C. E. Chandra, S. Abdullah, and S. Devila, “Estimating Indonesian Complete Life Table and Fair Annual Pure Premium Range from Abridged Life Table with Bayesian Method and Bootstrapping,†International Journal on Advanced Science, Engineering and Information Technology, vol. 12, no. 6, pp. 2226–2236, 2022, Accessed: Jan. 23, 2023. [Online]. Available: http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=14947
Z. Nematzadeh, R. Ibrahim, A. Selamat, and V. Nazerian, “The synergistic combination of fuzzy C-means and ensemble filtering for class noise detection,†Engineering Computations, vol. ahead-of-print, Mar. 2020, doi: 10.1108/EC-05-2019-0242.
L. Rice, E. Wong, and Z. Kolter, “Overfitting in adversarially robust deep learning,†in Proceedings of the 37th International Conference on Machine Learning, Nov. 2020, pp. 8093–8104. Accessed: Jan. 24, 2023. [Online]. Available: https://proceedings.mlr.press/v119/rice20a.html
T. Chen, Z. Zhang, S. Liu, S. Chang, and Z. Wang, “ROBUST OVERFITTING MAY BE MITIGATED BY PROP- ERLY LEARNED SMOOTHENING,†2021.
I.-C. Yeh, “Modeling slump flow of concrete using second-order regressions and artificial neural networks,†Cement and Concrete Composites, vol. 29, no. 6, pp. 474–480, Jul. 2007, doi: 10.1016/j.cemconcomp.2007.02.001.
S. Khaki and D. Nettleton, Conformal Prediction Intervals for Neural Networks Using Cross Validation. 2020.
T. Ergen and M. Pilanci, Training Convolutional ReLU Neural Networks in Polynomial Time: Exact Convex Optimization Formulations. 2020.
A. Panigrahi, A. Shetty, and N. Goyal, Effect of Activation Functions on the Training of Overparametrized Neural Nets. 2019.
A. Giessing and J. Fan, “Bootstrapping lp-Statistics in High Dimensions,†arXiv:2006.13099 [econ, math, stat], Jun. 2020, Accessed: Jul. 10, 2020. [Online]. Available: http://arxiv.org/abs/2006.13099