YO‘LOVCHI OQIMINI PROGNOZLASH ASOSIDA AVTOBUS YO‘NALISHLARINI OPTIMALLASHTIRISHNING KOMBINATSIYALASHGAN MODELI
J.Xoldorov
Farg‘ona davlat texnika universiteti
J.A.Axunov
Farg‘ona davlat texnika universiteti
Abstract
Annotatsiya. Mazkur maqolada avtobus yo‘nalishlarini optimallashtirishda yo‘lovchi oqimini prognozlashning ilmiy-texnik asoslari tahlil qilinadi. Zamonaviy shahar transport tizimlarida yo‘lovchi oqimi murakkab vaqt qatori sifatida namoyon bo‘lib, uning dinamik o‘zgaruvchanligi transportni rejalashtirish jarayonini murakkablashtiradi [1], [2]. Shu sababli maqolada yo‘lovchi oqimini prognozlash uchun statistik va sun’iy intellektga asoslangan yondashuvlar tahlil qilinadi. Tadqiqotda ARIMA modeli hamda Bi-LSTM neyron tarmog‘i asosida prognozlash yondashuvlari ko‘rib chiqilib, ularning afzallik va kamchiliklari solishtirildi [2], [3]. Shuningdek, yo‘lovchi oqimi prognoz natijalariga asoslangan holda avtobus yo‘nalishlarini optimallashtirishning ko‘p omilli matematik modeli taklif etildi. Natijalar shuni ko‘rsatadiki, yo‘lovchi oqimini aniq prognozlash transport tizimining samaradorligini oshiradi, yo‘nalishlarni oqilona tashkil etish imkonini beradi hamda ekspluatatsion xarajatlarni kamaytiradi [1], [4].
Kalit so‘zlar. yo‘lovchi oqimi, prognozlash, ARIMA modeli, Bi-LSTM, avtobus yo‘nalishi, optimallashtirish, jamoat transporti.
Abstract. This article analyzes the scientific and technical foundations of optimizing bus routes based on passenger flow prediction. In modern urban transport systems, passenger flow is represented as a complex time series, and its dynamic variability complicates the transport planning process [1], [2]. Therefore, this study examines both statistical and artificial intelligence-based approaches for passenger flow prediction. In this research, forecasting approaches based on the ARIMA model and the Bi-LSTM neural network are considered, and their advantages and disadvantages are comparatively analyzed [2], [3]. In addition, a multi-factor mathematical model for optimizing bus routes based on passenger flow prediction results is proposed. The results show that accurate passenger flow prediction improves the efficiency of the transport system, enables rational organization of routes, and reduces operational costs [1], [4].
Keywords. passenger flow, forecasting, ARIMA model, Bi-LSTM, bus route, optimization, public transport.
References
1. Pei Y., Ran S., Wang W., Dong C. Bus Passenger Flow Prediction Model Based on WPD, Attention Mechanism, and Bi-LSTM. Sustainability, 2023. https://doi.org/10.3390/su152014889.
2. Ye R. Bus Passenger Flow Dynamic Prediction and Route Optimization Strategy Based on Spatiotemporal Clustering and ARIMA Model. WJIMT, 2025. https://doi.org/10.53469/wjimt.2025.08(04).02.
3. Vuchic V.R. Urban Transit Systems and Technology. Wiley, 2007. https://doi.org/10.1002/9780470168043.
4. Rodrigue J.P. The Geography of Transport Systems. Routledge, 2020. https://doi.org/10.4324/9780429346323.
5. Nagaraj P., et al. Deep Learning-Based Passenger Flow Prediction Using LSTM Models Journal of Transportation Engineering, 2022. https://doi.org/10.1061/JTEPBS.0000600.
6. Hochreiter S., Schmidhuber J. Long Short-Term Memory. Neural Computation, 1997. https://doi.org/10.1162/neco.1997.9.8.1735.
7. Box G.E.P., Jenkins G.M., Reinsel G.C. Time Series Analysis: Forecasting and Control. Wiley, 2015. https://doi.org/10.1002/9781118675021.
