Benchmarking Socio-Economic Impacts of High-Speed Rail Networks Using K-Nearest Neighbour and Pearson’s Correlation Coefficient Techniques through Computational Model-Based Analysis

Abstract

Not only have high-speed rail (HSR) services stimulated the economy of many countries, but they have also significantly uplifted quality of lives (QoL) of countless people. For many decades, the aspiration for HSR network development has dramatically risen, and HSR networks have inevitably become an icon of civilisation. However, only a few successful HSR networks globally can truly generate socio-economic impacts on their societies. This research aims to understand the impact of HSR networks on social and economic impacts and to provide recommendations for success. This study is the world’s first to examine the benefits of HSR across all community demographic groups, including young and elderly people. The findings will illustrate the QoL, economic, and educational elements’ advantages in explicit terms. It has established two interconnected models via Python to codify a novel customised model for socio-economic evaluation. ‘Pearson correlation coefficient’ and ‘K-Nearest Neighbour’ techniques are applied to bolster the reliability of the research findings. The outcomes have been reviewed by 30 international HSR specialists. The benchmarking exhibits that socio-economic impacts apparently occur across vast areas. The insight stemming from this benchmarking also offers policy implications and empirical data for long-term HSR improvement, assisting the government in developing new methods for sustainable communities.

The Construction of a Prediction Model for the Teaching Effect of Two Courses Education in Colleges and Universities Based on Machine Learning Algorithms

“…To solve the problem of how to reasonably use, mechanical learning came into being. Nowadays, there are various popular and general machine learning algorithms, including decision tree algorithm which can process incomplete data; there is a naive Bayesian algorithm based on the principle of probability theory; there are vector machine algorithms that can map low-dimensional data to highdimensional data; K nearest neighbor algorithm with K neighbors represents the nearest sample; there is an Ada-Boost adaptive lifting algorithm that can combine multiple weak classifiers into a strong classifier; there is a widely used Apriori mining association algorithm to reveal the association between samples; there are also EM clustering algorithms to establish core reclassification; there is also PageRank algorithm originated from the influence calculation of the paper [7][8][9][10][11][12][13][14]. Using machine learning algorithm technology to mine real data is the ultimate goal of big data processing.…”

Exploration of Chinese cultural communication mode based on the Internet of Things and mobile multimedia technology

“…The Pearson correlation coefficient measures the correlation between different features ( Panrawee, Shen & Sakdirat, 2022 ). The correlation degree is calculated by covariance function, then divided by standard deviation to unify the variables to the same order of magnitude to avoid the oscillation of loss function caused by the difference between features, which will affect the learning ability of the network.…”

Electronic Medical Record Data Analysis and Prediction of Stroke Disease Using Explainable Artificial Intelligence (XAI)

“…K-NN is a classification method based on similarity or proximity between data [21]. The proximity is based on the closest K-data value and is used as a reference in determining the new data class [22]. The technique for finding the nearest k generally uses the Euclidean distance formula [23].…”