Passenger Flow Prediction of Integrated Passenger Terminal Based on K-Means–GRNN

Tan, Yiling; Liu, Haixu; Yun, Pu; Wu, Xiaorui; Jiao, Yubo

doi:10.1155/2021/1055910

Cited by 5 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Anl [7] developed a long short-term memory-based (LTSM-based) deep learning model to predict short-term transit passenger volume on transport routes in Istanbul using a dataset that included the number of people who used different transit routes at a one-hour interval between January and December 2020 and compared that with popular models such as random forest (RF), support vector machines, autoregressive integrated moving average, multilayer perceptron, and convolutional neural networks. Taking the passenger flow of Chengdu East Railway Station as an example, Tan [8] verified the higher prediction accuracy and better prediction performance of the GRNN neural network model based on parameter optimization (GA) compared with other models. Pekel [9] developed two hybrid forecasting methods, POA-ANN and IWD-ANN, to forecast passenger demand, compared the forecasting results with GA-ANN, and concluded that the new algorithm had a good effect on passenger prediction.…”

Section: Introductionmentioning

confidence: 93%

Research on Short-Term Passenger Flow Prediction of LSTM Rail Transit Based on Wavelet Denoising

Zhao,

Feng,

Zhang

et al. 2023

Mathematics

View full text Add to dashboard Cite

Urban rail transit offers advantages such as high safety, energy efficiency, and environmental friendliness. With cities rapidly expanding, travelers are increasingly using rail systems, heightening demands for passenger capacity and efficiency while also pressuring these networks. Passenger flow forecasting is an essential part of transportation systems. Short-term passenger flow forecasting for rail transit can estimate future station volumes, providing valuable data to guide operations management and mitigate congestion. This paper investigates short-term forecasting for Suzhou’s Shantang Street station. Shantang Street’s high commercial presence and distinct weekday versus weekend ridership patterns make it an interesting test case, making it a representative subway station. Wavelet denoising and Long Short Term Memory (LSTM) were combined to predict short-term flows, comparing the results to those of standalone LSTM, Support Vector Regression (SVR), Artificial Neural Network (ANN), and Autoregressive Integrated Moving Average Model (ARIMA). This study illustrates that the algorithms adopted exhibit good performance for passenger prediction. The LSTM model with wavelet denoising proved most accurate, demonstrating applicability for short-term rail transit forecasting and practical significance. The research findings can provide fundamental recommendations for implementing appropriate passenger flow control measures at stations and offer effective references for predicting passenger flow and mitigating traffic pressure in various cities.

show abstract

Section: Introductionmentioning

confidence: 93%

Research on Short-Term Passenger Flow Prediction of LSTM Rail Transit Based on Wavelet Denoising

Zhao,

Feng,

Zhang

et al. 2023

Mathematics

View full text Add to dashboard Cite

show abstract

“…Salah satu karakteristik dari metode GRNN adalah jumlah neuron pada pattern layer akan bertambah seiring meningkatnya jumlah data pelatihan. Pada umumnya, model prediksi dengan jumlah neuron yang meningkat akan meningkatkan kompleksitas jaringan dan membutuhkan jumlah komputasi yang besar [1]. Selain itu, penggunaan jumlah neuron yang terlalu banyak akan mengakibatkan masalah overfitting [2].…”

Section: A Pendahuluanunclassified

“…Metode K-means pada penelitian ini bertujuan untuk mendapatkan berbagai kelompok data pelatihan yang dikelompokkan berdasarkan karakteristik sehingga GRNN dapat lebih mudah mempelajari data berdasarkan karakteristik yang serupa dalam suatu kelompok [5]. Selain itu, hybrid K-Means dan GRNN dapat mengurangi masalah kompleksitas jaringan dan jumlah komputasi yang besar [1]. Hybrid K-Means dan GRNN dapat meningkatkan kinerja performa model dan memberikan hasil akurasi prediksi yang baik.…”

Section: A Pendahuluanunclassified

Penggunaan Hybrid K-Means dan General Regression Neural Network untuk Prediksi Harga Saham Indeks LQ45

Achyar¹,

Rohaeni²

2022

JRM

View full text Add to dashboard Cite

Abstract. General Regression Neural Network (GRNN) is a nonparametric method of developing the concept of an artificial neural network. The GRNN operation is based on the estimated expected output value determined by the input set. One of the characteristics of GRNN is that the number of neurons in the pattern layer will increase with the amount of training data. This problem can be solved with K-means. The K-means method in this study aims to obtain various groups of training data based on similar characteristics so that it is easier for GRNN to study data in a group and reduce the problem of network complexity and large computations. One of the implementations of hybrid K-means & GRNN is to predict the price of the LQ45 stock index. The LQ45 stock price index is a combination of 45 stock members with high liquidity. One of the efforts before market participants make a decision to invest is to predict the stock index in the future to understand the investment prospects of a company in the future so as to reduce the risk for investors in investing. The results of this study indicate that the K-Means & GRNN hybrid model has a MAPE value of 0.943%. The results of the LQ45 index stock price prediction for the next period show the LQ45 index price of Rp1,002,28. Abstrak. General Regression Neural Network (GRNN) merupakan metode nonparametrik dari pengembangan konsep jaringan syaraf tiruan. Operasi GRNN didasarkan pada estimasi nilai harapan output ditentukan oleh himpunan input. Salah satu karakteristik dari GRNN adalah jumlah neuron pada pattern layer akan bertambah seiring meningkatnya jumlah data pelatihan. Permasalahan tersebut dapat diatasi dengan K-means. Metode K-means pada penelitian ini bertujuan untuk mendapatkan berbagai kelompok data pelatihan yang dikelompokkan berdasarkan karakteristik yang serupa sehingga GRNN lebih mudah mempelajari data dalam suatu kelompok serta mengurangi masalah kompleksitas jaringan dan jumlah komputasi yang besar. Salah satu implementasi hybrid K-means & GRNN adalah memprediksi harga saham indeks LQ45. Harga saham indeks LQ45 merupakan gabungan dari 45 anggota saham dengan likuiditas yang tinggi. Salah satu upaya sebelum pelaku pasar mengambil keputusan untuk berinvestasi adalah memprediksi nilai indeks saham pada waktu yang akan datang untuk memahami prospek investasi saham sebuah perusahaan pada masa yang akan datang sehingga mengurangi resiko bagi investor dalam berinvestasi. Hasil dari penelitian ini menunjukkan bahwa model hybrid K-Means & GRNN memiliki nilai MAPE sebesar 0.943%. Hasil prediksi harga saham Indeks LQ45 untuk periode selanjutnya menunjukkan harga indeks LQ45 sebesar Rp1.002,28.

show abstract

“…After preliminary analysis and screening, finally high potassium glass was divided into two subclasses by SPSS using K-means clustering method; while lead-barium glass was divided into three subclasses [12] . Because this cluster analysis involves more variables, each component can be regarded as a variable, so in this cluster analysis we use principal component analysis to reduce the dimensionality, to get two principal components and then clustering; in which the classification of the results of the lead-barium glass cluster analysis is visualised in Fig.…”

mentioning

confidence: 99%

Compositional Analysis and Classification Study of Ancient Glassware Based on K-Means Cluster Analysis

Tan,

Xu,

Zeng

2024

HSET

View full text Add to dashboard Cite

The aim of this study is to gain a deeper understanding of the compositional characteristics of ancient glass artefacts and their relationship with the degree of weathering as well as the rules for subclassification of ancient glass based on compositional variations. Through detailed compositional analyses of high-potassium glass and lead-barium glass, the study reveals their significant differences in terms of SiO2 content, etc., and successfully divides them into subclasses by K-means clustering method, and the clustering results are verified by chi-square test, which shows its effectiveness in distinguishing the degree of weathering. The study not only provides a scientific basis for the classification of cultural relics, but also provides a methodology and preliminary conclusions for further excavation of information on ancient glass relics. This study is of practical significance for the conservation of cultural relics and in-depth understanding of ancient glass craftsmanship.

show abstract

Passenger Flow Prediction of Integrated Passenger Terminal Based on K-Means–GRNN

Cited by 5 publications

References 35 publications

Research on Short-Term Passenger Flow Prediction of LSTM Rail Transit Based on Wavelet Denoising

Research on Short-Term Passenger Flow Prediction of LSTM Rail Transit Based on Wavelet Denoising

Penggunaan Hybrid K-Means dan General Regression Neural Network untuk Prediksi Harga Saham Indeks LQ45

Compositional Analysis and Classification Study of Ancient Glassware Based on K-Means Cluster Analysis

Contact Info

Product

Resources

About