Prediction of passenger train using fuzzy time series and percentage change methods

Solikhin, Solikhin; Lutfi, Septia; Purnomo, Purnomo; Hardiwinoto, Hardiwinoto

doi:10.11591/eei.v10i6.2822

Cited by 4 publications

(10 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…After dividing the universe of speech into equal intervals (u1, u2, u3, …un), then partition by frequency. In this section, we use and change a method for dividing frequency that has been described in previous publications [32], [33]. These are the alterations: − Count how many rate of change frequencies fall within each interval.…”

Section: The Procedures For Frequency-based Partitioningmentioning

confidence: 99%

“…In this experiment, we use the Central Statistics Agency's dataset on the change in Indonesian rail passengers between January 2006 and December 2019 [33] to test our model. Figure 1…”

Section: Passengers On Trains: An Experimental Investigationmentioning

confidence: 99%

“…With each frequency, divide the interval into many sub-intervals. In this section, we modify the proposals [32], [33]. Carry on with the same procedure for the next interval division.…”

Section: Passengers On Trains: An Experimental Investigationmentioning

confidence: 99%

“…On the same rail passenger data, we compare our proposed model's performance in forecasting passenger numbers to that of the previous model [33]. We also use statistics on train passengers from the same year for verification.…”

Section: Performance Comparison and Evaluationmentioning

confidence: 99%

“… ISSN: 2302-9285 enhances forecast accuracy. Compare the suggested method to one that Solikhin et al [33] used in a previous study that used the same data about railroad passengers.…”

mentioning

confidence: 99%

See 4 more Smart Citations

A machine learning approach in Python is used to forecast the number of train passengers using a fuzzy time series model

Solikhin¹,

Lutfi²,

Purnomo

et al. 2022

Bulletin EEI

Self Cite

View full text Add to dashboard Cite

Train passenger forecasting assists in planning, resource use, and system management. forecasts rail ridership. Train passenger predictions help prevent stranded passengers and empty seats. Simulating rail transport requires a low-error model. We developed a fuzzy time series forecasting model. Using historical data was the goal. This concept predicts future railway passengers using Holt's double exponential smoothing (DES) and a fuzzy time series technique based on a rate-of-change algorithm. Holt's DES predicts the next period using a fuzzy time series and the rate of change. This method improves prediction accuracy by using event discretization. positive, since changing dynamics reveal trends and seasonality. It uses event discretization and machine-learning-optimized frequency partitioning. The suggested method is compared to existing train passenger forecasting methods. This study has a low average forecasting error and a mean squared error.

show abstract

Section: The Procedures For Frequency-based Partitioningmentioning

confidence: 99%

“…In this experiment, we use the Central Statistics Agency's dataset on the change in Indonesian rail passengers between January 2006 and December 2019 [33] to test our model. Figure 1…”

Section: Passengers On Trains: An Experimental Investigationmentioning

confidence: 99%

“…With each frequency, divide the interval into many sub-intervals. In this section, we modify the proposals [32], [33]. Carry on with the same procedure for the next interval division.…”

Section: Passengers On Trains: An Experimental Investigationmentioning

confidence: 99%

Section: Performance Comparison and Evaluationmentioning

confidence: 99%

“… ISSN: 2302-9285 enhances forecast accuracy. Compare the suggested method to one that Solikhin et al [33] used in a previous study that used the same data about railroad passengers.…”

mentioning

confidence: 99%

See 3 more Smart Citations

A machine learning approach in Python is used to forecast the number of train passengers using a fuzzy time series model

Solikhin¹,

Lutfi²,

Purnomo

et al. 2022

Bulletin EEI

Self Cite

View full text Add to dashboard Cite

show abstract

Photovoltaic Energy Fed DC Motor for Water Pump

Abbes

Abid

2023

Studies in Systems, Decision and Control

View full text Add to dashboard Cite

Prediksi Produksi Biofarmaka Menggunakan Model Fuzzy Time Series dengan Pendekatan Percentage Change dan Frequency Based Partition

Harmadji,

Solikhin,

Yudatama

et al. 2023

JTIIK

View full text Add to dashboard Cite

Masa depan biofarmasi semakin cerah. Akibat mahalnya harga obat modern, maka permintaan tanaman obat meningkat di dalam dan luar negeri. Hal ini karena biofarmaka banyak digunakan di industri lain, seperti makanan, minuman, dan kosmetik. Konsumen di seluruh dunia termasuk di Indonesia bergerak menuju produk makanan dan kesehatan yang lebih sehat dengan slogan "kembali ke alam". Dengan demikian permintaan tanaman obat sebagai bahan baku industri lainnya juga meningkat. Untuk mengatasi masalah tersebut diperlukan suatu prediksi untuk menentukan besaran kenaikan atau penurunan jumlah produksi komoditas strategis biofarmaka untuk beberapa tahun ke depan, sehingga Memungkinkan analisis pergerakan tren dari perkembangan data sebelumnya. Saat ini belum dijumpai studi peramalan deret waktu untuk memprediksi produksi biofarmaka dengan tingkat akurasi baik. Dalam eksperimen ini kami mengusulkan model peramalan fuzzy time series berdasarkan pendekatan percentage change sebagai himpunan semesta dan frequency-based partition yang dapat memberikan tingkat akurasi peramalan yang tinggi. Prediksi difokuskan pada biofarmaka untuk empat jenis rimpang yaitu Jahe, Lengkuas, Kencur, dan Kunyit yang dinilai menjadi prioritas utama pengembangan tanaman obat di Indonesia. Dalam penelitian ini menggunakan data sekunder yang diperoleh dari Badan Pusat Statistika tahun 1997-2020. Tujuan dari survei adalah untuk memprediksi dan menganalisa perkembangan produksi biofarmaka untuk empat jenis rimpang. Hasil prediksi menunjukan akurasi luar biasa dengan nilai Mean Absolute Percentage Error yang sangat kecil yakni Jahe 0,03%, Lengkuas 0,02%, Kencur 0,14%, dan Kunyit 0,03%. Dengan demikian hasil eksperimen ini dapat berkontribusi dan digunakan bagi pihak yang berkompeten untuk membantu dalam menentukan kebijakan strategis di masa depan. AbstractBiopharmaceuticals' future is brightening. Due to the exorbitant cost of modern treatment, the desire for medicinal herbs is growing. due to their widespread use in different industries such as food, beverages, and cosmetics. Consumers worldwide, especially in Indonesia, are gravitating towards healthier food and health goods. So the demand for medicinal plants as raw materials increases. To solve this issue, a forecast is required for the next few years on the increase or decline in production of strategic biopharmaca commodities. Currently, no reliable time series forecasting study exists for biopharmaca production. To achieve high predicting accuracy, we present a fuzzy time series forecasting model based on percentage change as a universal set and frequency-based partition. Ginger, Galangal, Kencur, and turmeric are predicted to be the most important rhizomes for biopharmaca research in Indonesia. Secondary statistics from the Central Statistics Agency for 1997–2020 This study's goal was to anticipate and analyze biopharmaca synthesis in four rhizomes. The prediction results are incredibly accurate, with Mean Absolute Percentage Error values of just 0.03%, 0.02%, 0.14%, and 0.03% for Ginger, Galangal, Kencur, and Turmeric, respectively. Thus, competent parties can use the outcomes of this experiment to help determine future strategic policies.

show abstract

Prediction of passenger train using fuzzy time series and percentage change methods

Cited by 4 publications

References 23 publications

A machine learning approach in Python is used to forecast the number of train passengers using a fuzzy time series model

A machine learning approach in Python is used to forecast the number of train passengers using a fuzzy time series model

Photovoltaic Energy Fed DC Motor for Water Pump

Prediksi Produksi Biofarmaka Menggunakan Model Fuzzy Time Series dengan Pendekatan Percentage Change dan Frequency Based Partition

Contact Info

Product

Resources

About