Short-Term and Mid-Term Population Projections Especially of Germany via WASD Neural Network: Theoretical Parts

Population has a direct impact on the demands of consumption, resource, and employment. Population factors, such as size and growth rate, are crucial in making decisions and plans of trade, environment protection, resource allocation and human resource development. Thus, population projection is an essential part of strategy development for companies as well as governments, and draws the attention of many researchers. Some projection methods have been developed, but most of the popular ones require a vast knowledge in demography and only can be operated by skilled professionals. In this paper, as an improvement, we theoretically develop a regression model and a subtrend model of WASD (weights and structure determination) neural network in a simultaneous manner to make population projections especially of Germany in the midterm and near future. Specifically, we aim at utilizing the learning capabilities of the WASD neural-network models with single input and multiple inputs, having been very popular recently, to propose these easy-used and high accuracy models for verifications and projections via later computer experiments.

[1]  Yunong Zhang,et al.  Numerical and Graphical Results of Germany Population Projection Using WASD Neuronet , 2021, 2021 13th International Conference on Advanced Computational Intelligence (ICACI).

[2]  J. Bongaarts,et al.  United Nations Department of Economic and Social Affairs, Population Division World Family Planning 2020: Highlights, United Nations Publications, 2020. 46 p. , 2020 .

[3]  Long Jin,et al.  Weight and Structure Determination Neural Network Aided With Double Pseudoinversion for Diagnosis of Flat Foot , 2019, IEEE Access.

[4]  Sheikh Mohammad Idrees,et al.  A Prediction Approach for Stock Market Volatility Based on Time Series Data , 2019, IEEE Access.

[5]  R. Sarpong,et al.  Bio-inspired synthesis of xishacorenes A, B, and C, and a new congener from fuscol† †Electronic supplementary information (ESI) available. See DOI: 10.1039/c9sc02572c , 2019, Chemical science.

[6]  Dongsheng Guo,et al.  CP-activated WASD neuronet approach to Asian population prediction with abundant experimental verification , 2016, Neurocomputing.

[7]  Jakub Bijak,et al.  Bayesian demography 250 years after Bayes , 2016, Population studies.

[8]  Abhishek K Gupta,et al.  Numerical Methods using MATLAB , 2014, Apress.

[9]  Alison Yacyshyn,et al.  A Practitioner's Guide to State and Local Population Projections , 2013 .

[10]  Plamen P. Angelov,et al.  Uniformly Stable Backpropagation Algorithm to Train a Feedforward Neural Network , 2011, IEEE Transactions on Neural Networks.

[11]  Stanley K. Smith,et al.  Precision, bias, and uncertainty for state population forecasts: an exploratory analysis of time series models , 2007 .

[12]  Wann-Yih Wu,et al.  A prediction method using the grey model GMC(1, n) combined with the grey relational analysis: a case study on Internet access population forecast , 2005, Appl. Math. Comput..

[13]  Broadus Mitchell,et al.  International historical statistics, Europe, 1750-1988 , 2000 .

[14]  Tsu-Tian Lee,et al.  The Chebyshev-polynomials-based unified model neural networks for function approximation , 1998, IEEE Trans. Syst. Man Cybern. Part B.

[15]  G. MELVYN HOWE,et al.  Atlas of world population history , 1979, Medical History.

[16]  Hsieh Hou,et al.  Cubic splines for image interpolation and digital filtering , 1978 .

[17]  Xin Zhang,et al.  Comparison of Econometric Models and Artificial Neural Networks Algorithms for the Prediction of Baltic Dry Index , 2019, IEEE Access.

[18]  Long Jin,et al.  Modified Weights-and-Structure-Determination Neural Network for Pattern Classification of Flatfoot , 2019, IEEE Access.

[19]  Jiliang Zhang,et al.  On Modified Multi-Output Chebyshev-Polynomial Feed-Forward Neural Network for Pattern Classification of Wine Regions , 2019, IEEE Access.

[20]  Jayadeep Pati,et al.  A Comparison Among ARIMA, BP-NN, and MOGA-NN for Software Clone Evolution Prediction , 2017, IEEE Access.

[21]  Zhang Yu-non Comparison on Prediction Abilities of Single-Input Neuronets Activated by Different Polynomials , 2014 .

[22]  W. Marsden I and J , 2012 .

[23]  Yunong Zhang,et al.  Weights Direct Determination of Feedforward Neural Networks without Iterative BP-Training , 2010 .

[24]  Zou A-jin,et al.  Weights-directly-determined and Structure-adaptively-tuned Neural Network Based on Chebyshev Basis Functions , 2009 .

[25]  Chen Yi-song,et al.  Precision �� , 2022 .