Abstract
Medical information systems such as Internet of Medical Things (IoMT) are gained special attention over recent years. X-ray and MRI images are important sources of information to be examined for a particular type of anomalies. Reports based on the images and laboratory examination results could be mined with machine learning techniques as well. Thyroid disease diagnosis is an important capability of medical information systems. The main objective of this study is to improve the diagnosis accuracy of thyroid diseases from semantic reports and examination results using artificial neural network (ANN) in IoMT systems. In order to improve generalization and avoid over-fitting of ANN during the training process, a set of multiple multilayer perceptron (MMLP) neural network with the back-propagation error ability is proposed in this paper. Moreover, an adaptive learning rate algorithm is used to deal with the slow convergence and the local minima problem of the back-propagation error algorithm. The proposed MMLP significantly increased the overall accuracy of thyroid disease classification. With MMLP with a set of 6 networks, an improvement of 0.7% accuracy is achieved compared to a single network. In addition, comparing to the standard back-propagation, by using an adaptive learning rate algorithm in the proposed MMLP, an improvement of 4.6% accuracy and the final accuracy of 99% have been obtained in IoMT systems. The proposed MMLP is compared to recent researches reported for thyroid disease diagnosis, and its superiority is shown.
Similar content being viewed by others
References
Chi J, Walia E, Babyn P, Wang J, Groot G, Eramian M (Aug 2017) Thyroid nodule classification in ultrasound images by fine-tuning deep convolutional neural network. J Digit Imag 30:477–486
Ahmad W, Ahmad A, Lu C, Khoso BA, Huang L (2018) A novel hybrid decision support system for thyroid disease forecasting. Soft Comput 22:5377–5383
Takase T, Oyama S, Kurihara M (May 2018) Effective neural network training with adaptive learning rate based on training loss. Neural Netw 101:68–78
Liang J, Xu Y, Bao C, Quan Y, Ji H (2019) Barzilai–Borwein-based adaptive learning rate for deep learning. Pattern Recogn Lett 128:197–203
Kolbusz J, Rozycki P, Lysenko O, Wilamowski BM. (2019) "Error Back Propagation Algorithm with Adaptive Learning Rate," In: 2019 International Conference on Information and Digital Technologies (IDT), pp 216–222
Nawi NM, Hussein AS, Samsudin NA, Hamid NA, Yunus M, Amin M et al (2017) The effect of pre-processing techniques and optimal parameters selection on back propagation neural networks. Int J Adv Sci Eng Inf Technol 7:770–777
Hamid NA, Nawi NM, Ghazali R, Salleh MNM (2012) Solving local minima problem in back propagation algorithm using adaptive gain, adaptive momentum and adaptive learning rate on classification problems. In: International Journal of Modern Physics: Conference Series, 2012, pp 448–455
Gorunescu F, Belciug S (2016) Boosting backpropagation algorithm by stimulus-sampling: application in computer-aided medical diagnosis. J Biomed Inform 63:74–81
Belciug S, Gorunescu F (2018) Learning a single-hidden layer feedforward neural network using a rank correlation-based strategy with application to high dimensional gene expression and proteomic spectra datasets in cancer detection. J Biomed Inform 83:159–166
Sundaram NM, Renupriya V (2016) Artificial neural network classifiers for diagnosis of thyroid abnormalities. Technology 206:211
Ioniţă I, Ioniţă L (2016) "Prediction of thyroid disease using data mining techniques. BRAIN Broad Res Artif Int Neurosci 7:115–124
Chen D, Niu J, Pan Q, Li Y, Wang M (2017) A deep-learning based ultrasound text classifier for predicting benign and malignant thyroid nodules. In: 2017 International Conference on Green Informatics (ICGI), 2017, pp 199–204
Alkhasawneh MS (2019) Hybrid cascade forward neural network with elman neural network for disease prediction. Arab J Sci Eng 44:9209–9220
Ahmad W, Huang L, Ahmad A, Shah F, Iqbal A (2017) Thyroid diseases forecasting using a hybrid decision support system based on ANFIS, k-NN and information gain method. J Appl Environ Biol Sci 7:78–85
Ozyilmaz L, Yildirim T (2002) Diagnosis of thyroid disease using artificial neural network methods. In: Proceedings of the 9th International Conference on Neural Information Processing, 2002, pp 2033–2036
Iranmanesh S, Mahdavi MA (2009) A differential adaptive learning rate method for back-propagation neural networks. World Acad Sci Eng Technol 50:285–288
Kathirvalavakumar T, Subavathi SJ (2009) Neighborhood based modified backpropagation algorithm using adaptive learning parameters for training feedforward neural networks. Neurocomputing 72:3915–3921
Nawi NM, Ransing RS, Salleh MNM, Ghazali R, Hamid NA (2010) An improved back propagation neural network algorithm on classification problems. In: Database Theory and Application, Bio-Science and Bio-Technology, pp 177–188
Jha SK, Pan Z, Elahi E, Patel N (2019) A comprehensive search for expert classification methods in disease diagnosis and prediction. Expert Syst 36:e12343
Nguyen DT, Pham TD, Batchuluun G, Yoon HS, Park KR (2019) Artificial intelligence-based thyroid nodule classification using information from spatial and frequency domains. J clin Med 8:1976
M. Al-Khafajiy, L. Webster, T. Baker, and A. Waraich, "Towards fog driven IoT healthcare: challenges and framework of fog computing in healthcare," In: Proceedings of the 2nd International Conference on Future Networks and Distributed Systems, 2018, pp. 1–7.
Fahim M, Baker T, Khattak AM, Alfandi O (2017) Alert me: Enhancing active lifestyle via observing sedentary behavior using mobile sensing systems. In: 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom), 2017, pp 1–4
Åström F, Koker R (2011) A parallel neural network approach to prediction of Parkinson’s disease. Expert Syst Appl 38:12470–12474
Zeiler MD (2012) ADADELTA: an adaptive learning rate method. arXiv preprint arXiv:1212.5701
Sharma A (2018) Guided Stochastic gradient descent algorithm for inconsistent datasets. Appl Soft Comput 73:1068–1080
Lichman M (2013) UCI Machine Learning Repository. Irvine, University of California, Irvine, School of Information and Computer Sciences, Irvine
Bensenor IM, Olmos RD, Lotufo PA (2012) Hypothyroidism in the elderly: diagnosis and management. Clin Interv Aging 7:97
Kaur A, Singh N, Bahrdwaj A (2013) A comparison of supervised multilayer back propagation and unsupervised self organizing maps for the diagnosis of thyroid disease. Int J Comp Appl 82:39–43
Souri A, Hosseinpour S, Rahmani AM (2018) Personality classification based on profiles of social networks’ users and the five-factor model of personality. Human-centric Comput Inf Sci 8:24
Nweke HF, Teh YW, Mujtaba G, Alo UR, Al-garadi MA (2019) Multi-sensor fusion based on multiple classifier systems for human activity identification. Human-centric Comput Inf Sci 9:34
Heidari AA, Faris H, Mirjalili S, Aljarah I, Mafarja M (2020) Ant Lion optimizer: theory, literature review, and application in multi-layer perceptron neural networks. In: Nature-Inspired Optimizers, 2020, pp 23–46
Guliyev NJ, Ismailov VE (2018) Approximation capability of two hidden layer feedforward neural networks with fixed weights. Neurocomputing 316:262–269
Henríquez PA, Ruz GA (2018) A non-iterative method for pruning hidden neurons in neural networks with random weights. Appl Soft Comput 70:1109–1121
Qian X, Zhong X (2019) Optimal individualized multimedia tourism route planning based on ant colony algorithms and large data hidden mining. Multimedia Tools Appl 78(15):22099–22108
Taherkhani A, Belatreche A, Li Y, Maguire LP (2018) A supervised learning algorithm for learning precise timing of multiple spikes in multilayer spiking neural networks. IEEE Trans Neural Netw Learn Syst 29:5394–5407
Yakopcic C, Hasan R, Taha TM (2018) Flexible memristor based neuromorphic system for implementing multi-layer neural network algorithms. Int J Parallel Emerg Distrib Syst 33:408–429
Nagarajan HP, Mokhtarian H, Jafarian H, Dimassi S, Bakrani-Balani S, Hamedi A, et al. (2019) Knowledge-based design of artificial neural network topology for additive manufacturing process modeling: a new approach and case study for fused deposition modeling. J Mech Des 141:1–12
Rene ER, López ME, Park HS, Murthy D, Swaminathan T (2012) ANNs for identifying shock loads in continuously operated biofilters: application to biological waste gas treatment. In: Handbook of Research on Industrial Informatics and Manufacturing Intelligence: Innovations and Solutions, 2012, pp 72–103
Sheel S, Varshney T, Varshney R (2007) Accelerated learning in MLP using adaptive learning rate with momentum coefficient. In: 2007 International Conference on Industrial and Information Systems, pp 307-310
Seth N, Ubrani A, Mane S, Kazi FA (2019) Comparative analysis of major Jacobian and gradient backpropagation optimizers of ANN on SVPWM. In: Soft Computing and Signal Processing, 2019, pp 345–357
Belciug S, Gorunescu F (2016) Improving performance in neural networks using feature selection based on random forests : application to automated medical diagnosis. Int J Inf Technol Knowl 10(1):33–46
Shankar K, Lakshmanaprabu S, Gupta D, Maseleno A, De Albuquerque VHC (2020) Optimal feature-based multi-kernel SVM approach for thyroid disease classification. J Supercomput 76:1128–1143
Yadav DC, Pal S (2019) Thyroid prediction using ensemble data mining techniques. Int J Inf Technol 1–11
Boger Z, Guterman H (1997) Knowledge extraction from artificial neural network models. In: 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation, 1997, pp 3030–3035
Acknowledgement
This paper derives from the Research Project with code 98-2-37-15607 and Approval ID IR.IUMS.REC.1398.798.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Hosseinzadeh, M., Ahmed, O.H., Ghafour, M.Y. et al. A multiple multilayer perceptron neural network with an adaptive learning algorithm for thyroid disease diagnosis in the internet of medical things. J Supercomput 77, 3616–3637 (2021). https://doi.org/10.1007/s11227-020-03404-w
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-020-03404-w