Abstract
In this chapter, we investigate the possibility of reconstructing images from reduced dimensions and using narrow artificial intelligence frameworks. This is aimed at addressing the high execution time drawback witnessed when deep neural network frameworks are used. The lower dimensional data is obtained from the bottleneck layer of the deep autoencoder network; in this case, the number of reduced features is 30. The aim is to observe whether this approach preserves accuracy while minimizing execution time.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abdella, M., & Marwala, T. (2005). The use of genetic algorithms and neural networks to approximate missing data in database (Vol. 24, pp. 577–589).
Atalla, M. J., & Inman, D. J. (1998). On model updating using neural networks. Mechanical Systems and Signal Processing, 12, 135–161.
Baek, K., & Cho, S. (2003). Bankruptcy prediction for credit risk using an auto-associative neural network in Korean firms. In IEEE Conference on Computational Intelligence for Financial Engineering (pp. 25–29). Hong Kong, China.
Brain, L. B., Marwala, T., & Tettey, T. (2006). Autoencoder networks for HIV classification. Current Science, 91(11), 1467–1473.
Hines, J. W., Robert, E. U., & Wrest, D. J. (1998). Use of autoassociative neural networks for signal validation. Journal of Intelligent and Robotic Systems, 21(2), 143–154.
Isaacs, J. C. (2014). Representational learning for sonar ATR. In SPIE Defense + Security. International Society for Optics and Photonics.
Leke, C., Twala, B., & Marwala, T. (2014). Modeling of missing data prediction: Computational intelligence and optimization algorithms. In International Conference on Systems, Man and Cybernetics (SMC) (pp. 1400–1404).
LeCun, Y. (2016). The MNIST database of handwritten digits. Retrieved January 1, 2016, from http://yann.lecun.com/exdb/mnist/.
Leke, C., & Marwala, T. (2016). Missing data estimation in high-dimensional datasets: A swarm intelligence-deep neural network approach. In International Conference in Swarm Intelligence (pp. 259–270) Springer International Publishing.
Leke, C., Ndjiongue, A. R., Twala, B., & Marwala, T. (2017). Deep learning-bat high-dimensional missing data estimator. In 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC) (pp. 483–488). IEEE.
Lu, P. J., & Hsu, T. C. (2002). Application of autoassociative neural network on gas-path sensor data validation. Journal of Propulsion and Power, 18(4), 879–888.
Marwala, T. (2001). Probabilistic fault identification using a committee of neural networks and vibration data. Journal of Aircraft, 38(1), 138–146.
Marwala, T., & Chakraverty, S. (2006). Fault classification in structures with incomplete measured data using autoassociative neural networks and genetic algorithm. Current Science, 90(4), 542–548.
Marwala, T. (2013). Economic modelling using artificial intelligence methods. London: Springer.
Mistry, J., Nelwamondo, F., & Marwala, T. (2008). Estimating missing data and determining the confidence of the estimate data. In Seventh International Conference on Machine Learning and Applications (pp. 752–755). San Diego, CA, USA.
Sartori, N., Salvan, A., & Thomaseth, K. (2005). Multiple imputation of missing values in a cancer mortality analysis with estimated exposure dose. Computational Statistics & Data Analysis, 49(3), 937–953.
Smauoi, N., & Al-Yakoob, S. (2003). Analyzing the dynamics of cellular flames using Karhunen-Loeve decomposition and autoassociative neural networks. Society for Industrial and Applied Mathematics, 24, 1790–1808.
Tim, T., Mutajogire, M., & Marwala, T. (2004). Stock market prediction using evolutionary neural networks. In Fifteenth Annual Symposium of the Pattern Recognition, PRASA (pp. 123–133).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Leke, C.A., Marwala, T. (2019). Missing Data Estimation Using Swarm Intelligence Algorithms from Reduced Dimensions. In: Deep Learning and Missing Data in Engineering Systems. Studies in Big Data, vol 48. Springer, Cham. https://doi.org/10.1007/978-3-030-01180-2_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-01180-2_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-01179-6
Online ISBN: 978-3-030-01180-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)