scholarly journals Short-Term Bus Passenger Demand Prediction Based on Time Series Model and Interactive Multiple Model Approach

2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Rui Xue ◽  
Daniel (Jian) Sun ◽  
Shukai Chen
Keyword(s):  
Time Series ◽  
Demand Forecasting ◽  
Performance Comparison ◽  
Practical Significance ◽  
Multiple Model ◽  
Short Term ◽  
Demand Prediction ◽  
Passenger Demand ◽  
Bus Scheduling ◽  
Interactive Multiple Model

Although bus passenger demand prediction has attracted increased attention during recent years, limited research has been conducted in the context of short-term passenger demand forecasting. This paper proposes an interactive multiple model (IMM) filter algorithm-based model to predict short-term passenger demand. After aggregated in 15 min interval, passenger demand data collected from a busy bus route over four months were used to generate time series. Considering that passenger demand exhibits various characteristics in different time scales, three time series were developed, named weekly, daily, and 15 min time series. After the correlation, periodicity, and stationarity analyses, time series models were constructed. Particularly, the heteroscedasticity of time series was explored to achieve better prediction performance. Finally, IMM filter algorithm was applied to combine individual forecasting models with dynamically predicted passenger demand for next interval. Different error indices were adopted for the analyses of individual and hybrid models. The performance comparison indicates that hybrid model forecasts are superior to individual ones in accuracy. Findings of this study are of theoretical and practical significance in bus scheduling.

scholarly journals STG2Seq: Spatial-Temporal Graph to Sequence Model for Multi-step Passenger Demand Forecasting

2019 ◽  
Author(s):  
Lei Bai ◽  
Lina Yao ◽  
Salil S. Kanhere ◽  
Xianzhi Wang ◽  
Quan Z. Sheng
Keyword(s):  
State Of The Art ◽  
Demand Forecasting ◽  
Short Term ◽  
Demand Prediction ◽  
On Demand ◽  
Passenger Demand ◽  
Temporal Correlations ◽  
Output Module ◽  
Real World Datasets

Multi-step passenger demand forecasting is a crucial task in on-demand vehicle sharing services. However, predicting passenger demand is generally challenging due to the nonlinear and dynamic spatial-temporal dependencies. In this work, we propose to model multi-step citywide passenger demand prediction based on a graph and use a hierarchical graph convolutional structure to capture both spatial and temporal correlations simultaneously. Our model consists of three parts: 1) a long-term encoder to encode historical passenger demands; 2) a short-term encoder to derive the next-step prediction for generating multi-step prediction; 3) an attention-based output module to model the dynamic temporal and channel-wise information. Experiments on three real-world datasets show that our model consistently outperforms many baseline methods and state-of-the-art models.

Taxi Booking Mobile App Order Demand Prediction Based on Short-Term Traffic Forecasting

2017 ◽  
Vol 2634 (1) ◽  
pp. 57-68 ◽  
Author(s):  
Yunxuan Li ◽  
Jian Lu ◽  
Lin Zhang ◽  
Yi Zhao
Keyword(s):  
High Frequency ◽  
Demand Forecasting ◽  
Low Frequency ◽  
Original Data ◽  
Mobile App ◽  
Support Vector ◽  
Short Term ◽  
Traffic Demand ◽  
Traffic Forecasting ◽  
Demand Prediction

The Didi Dache app is China’s biggest taxi booking mobile app and is popular in cities. Unsurprisingly, short-term traffic demand forecasting is critical to enabling Didi Dache to maximize use by drivers and ensure that riders can always find a car whenever and wherever they may need a ride. In this paper, a short-term traffic demand forecasting model, Wave SVM, is proposed. It combines the complementary advantages of Daubechies5 wavelets analysis and least squares support vector machine (LS-SVM) models while it overcomes their respective shortcomings. This method includes four stages: in the first stage, original data are preprocessed; in the second stage, these data are decomposed into high-frequency and low-frequency series by wavelet; in the third stage, the prediction stage, the LS-SVM method is applied to train and predict the corresponding high-frequency and low-frequency series; in the last stage, the diverse predicted sequences are reconstructed by wavelet. The real taxi-hailing orders data are applied to evaluate the model’s performance and practicality, and the results are encouraging. The Wave SVM model, compared with the prediction error of state-of-the-art models, not only has the best prediction performance but also appears to be the most capable of capturing the nonstationary characteristics of the short-term traffic dynamic systems.

scholarly journals Ultra-Short-Term Load Demand Forecast Model Framework Based on Deep Learning

Energies ◽  
2020 ◽  
Vol 13 (18) ◽  
pp. 4900 ◽  
Author(s):  
Hongze Li ◽  
Hongyu Liu ◽  
Hongyan Ji ◽  
Shiying Zhang ◽  
Pengfei Li
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Meteorological Data ◽  
Demand Forecasting ◽  
Dense Layer ◽  
Load Prediction ◽  
Demand Forecast ◽  
Short Term ◽  
Model Framework ◽  
Load Demand

Ultra-short-term load demand forecasting is significant to the rapid response and real-time dispatching of the power demand side. Considering too many random factors that affect the load, this paper combines convolution, long short-term memory (LSTM), and gated recurrent unit (GRU) algorithms to propose an ultra-short-term load forecasting model based on deep learning. Firstly, more than 100,000 pieces of historical load and meteorological data from Beijing in the three years from 2016 to 2018 were collected, and the meteorological data were divided into 18 types considering the actual meteorological characteristics of Beijing. Secondly, after the standardized processing of the time-series samples, the convolution filter was used to extract the features of the high-order samples to reduce the number of training parameters. On this basis, the LSTM layer and GRU layer were used for modeling based on time series. A dropout layer was introduced after each layer to reduce the risk of overfitting. Finally, load prediction results were output as a dense layer. In the model training process, the mean square error (MSE) was used as the objective optimization function to train the deep learning model and find the optimal super parameter. In addition, based on the average training time, training error, and prediction error, this paper verifies the effectiveness and practicability of the load prediction model proposed under the deep learning structure in this paper by comparing it with four other models including GRU, LSTM, Conv-GRU, and Conv-LSTM.

scholarly journals Bus Passenger Demand Modelling Using Time-Series Techniques- Big Data Analytics

2019 ◽  
Vol 13 (1) ◽  
pp. 41-47 ◽  
Author(s):  
Anila Cyril ◽  
Raviraj H. Mulangi ◽  
Varghese George
Keyword(s):  
Time Series ◽  
Big Data ◽  
Demand Forecasting ◽  
Information Criteria ◽  
Additive Models ◽  
Series Data ◽  
Transport Planning ◽  
Passenger Demand ◽  
Demand Modelling ◽  
Multiplicative Models

Background: Public transport demand forecasting is the fundamental process of transport planning activity. It plays a pivotal role in the decision making, policy formulations and urban transport planning procedures. In this paper, public bus passenger demand forecasting model is developed using a novel approach. The empirical passenger demand for a bus depot is modelled and forecasted using a data-driven method. The big data generated by Electronic Ticketing Machines (ETM) used for issuing tickets and collecting fares is sourced as the data for demand modelling. This big data is time indexed and hence has the potential for use in time-series applications which were not previously explored. Objectives: This paper studies the application of time-series method for forecasting public bus passenger demand using ETM based time-series data. The time-series approach used is the four Holt-Winters’ modeling methods. Holt-Winters’ additive and multiplicative models with and without damping have been empirically compared in this study using the data from the inter-zonal buses. The data used in the study is a part of the transaction on ticket sales by Kerala State Road Transport Corporation (KSRTC) maintained at the Trivandrum City depot of an Indian state Kerala, for the period between 2010 and 2013. The forecasting performance of four time-series models is compared using Mean Absolute Percentage Error (MAPE) and the model goodness of fit is determined using information criteria. Conclusion: The forecasts indicate that multiplicative models with and without damping, which better account for seasonal variations, outperform the additive models.

scholarly journals A Novel Hierarchical Hybrid Model for Short-Term Bus Passenger Flow Forecasting

2020 ◽  
Vol 2020 ◽  
pp. 1-16 ◽  
Author(s):  
Huawei Zhai ◽  
Ruijie Tian ◽  
Licheng Cui ◽  
Xiaowei Xu ◽  
Weishi Zhang
Keyword(s):  
Time Series ◽  
Hybrid Model ◽  
Time Series Model ◽  
Short Term ◽  
Forecasting Models ◽  
Passenger Flow ◽  
Bus Scheduling ◽  
Learning Machine ◽  
Transport Problems ◽  
Application Requirements

For the increasing travel demands and public transport problems, dynamically adjusting timetable or bus scheduling is necessary based on accurate real-time passenger flow forecasting. In order to get more accurate passenger flow in future, this paper proposes a novel hierarchical hybrid model based on time series model, deep belief networks (DBNs), and improved incremental extreme learning machine (Im-ELM) to forecast short-term passenger flow. The proposed model is named HTSDBNE with two modelling steps. First, referring the idea of parallelization, the hybrid model, constructed by time series model, DBN, and Im-ELM, is used to forecast short-term passenger flow in different time scales hierarchically and parallel. Second, Im-ELM is utilized to analyse the relationship of forecasting results from the first step, and the weighted outputs of Im-ELM are as the final forecasting results. Comparing with single forecasting models and typical hybrid forecasting models, the testing results indicate that HTSDBNE has better performances. The mean absolute percent error of prediction results is around 10% and fully meets the application requirements of bus operation enterprise.

Application of deep learning methods for urban water demand forecast modelling

2021 ◽  
Author(s):  
Anjana G Rajakumar ◽  
Avi Anthony ◽  
Vinoth Kumar
Keyword(s):  
Deep Learning ◽  
Water Demand ◽  
Demand Forecasting ◽  
Forecast Model ◽  
Demand Forecast ◽  
Short Term ◽  
Learning Methods ◽  
Demand Prediction ◽  
Learning Framework ◽  
Water Demand Forecast

<p>Water demand predictions forms an integral part of sustainable management practices for water supply systems. Demand prediction models aides in water system maintenance, expansions, daily operational planning and in the development of an efficient decision support system based on predictive analytics. In recent years, it has also found wide application in real-time control and operation of water systems as well. However, short term water demand forecasting is a challenging problem owing to the frequent variations present in the urban water demand patterns. There are numerous methods available in literature that deals with water demand forecasting. These methods can be roughly classified into statistical and machine learning methods. The application of deep learning methods for forecasting water demands is an upcoming research area that has found immense traction due to its ability to provide accurate and scalable models. But there are only a few works which compare and review these methods when applied to a water demand dataset. Hence, the main objective of this work is the application of different commonly used deep learning methods for development of a short-term water demand forecast model for a real-world dataset. The algorithms studied in this work are (i) Multi-Layer Perceptron (MLP) (ii) Gated Recurrent Unit (GRU) (iii) Long Short-Term Memory (LSTM) (iv) Convolutional Neural Networks (CNN) and (v) the hybrid algorithm CNN-LSTM. Optimal supervised learning framework required for forecasting the one day ahead water demand for the study area is also identified. The dataset used in this study is from Hillsborough County, Florida, US. The water demand data was available for a duration of 10 months and the data frequency is about once per hour. These algorithms were evaluated based on the (1) Mean Absolute Percentage Error (MAPE) and (ii) Root Mean Squared Error (RMSE) values. Visual comparison of the predicted and true demand plots was also employed to check the prediction accuracy. It was observed that, the RMSE and MAPE values were minimal for the supervised learning framework that used the previous 24-hour data as input. Also, with respect to the forecast accuracy, CNN-LSTM performed better than the other methods for demand forecast, followed by MLP. MAPE values for the developed deep learning models ranged from 5% to 25%. The quantity, frequency and quality of data was also found to have substantial impact on the accuracy of the forecast models developed. In the CNN-LSTM based forecast model, the CNN component was found to effectively extract the inherent characteristics of historical water consumption data such as the trend and seasonality, while the LSTM part was able to reflect on the long-term historical process and future trend. Thus, its water demand prediction accuracy was improved compared to the other methods such as GRU, MLP, CNN and LSTM.</p>

Application of Machine Learning Methods for Passenger Demand Prediction in Transfer Stations of Istanbul's Public Transportation System

2020 ◽  
pp. 196-216
Author(s):  
Hacer Yumurtaci Aydogmus ◽  
Yusuf Sait Turkan
Keyword(s):  
Machine Learning ◽  
Public Transportation ◽  
Demand Forecasting ◽  
Transportation System ◽  
Machine Learning Algorithms ◽  
Demand Prediction ◽  
Passenger Demand ◽  
World Demand ◽  
Public Transportation System ◽  
Transfer Stations

The rapid growth in the number of drivers and vehicles in the population and the need for easy transportation of people increases the importance of public transportation. Traffic becomes a growing problem in Istanbul which is Turkey's greatest urban settlement area. Decisions on investments and projections for the public transportation should be well planned by considering the total number of passengers and the variations in the demand on the different regions. The success of this planning is directly related to the accurate passenger demand forecasting. In this study, machine learning algorithms are tested in a real-world demand forecasting problem where hourly passenger demands collected from two transfer stations of a public transportation system. The machine learning techniques are run in the WEKA software and the performance of methods are compared by MAE and RMSE statistical measures. The results show that the bagging based decision tree methods and rules methods have the best performance.

scholarly journals Early-Stage Gas Identification Using Convolutional Long Short-Term Neural Network with Sensor Array Time Series Data

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4826
Author(s):  
Kai Zhou ◽  
Yixin Liu
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Sensor Array ◽  
Time Series Data ◽  
Practical Significance ◽  
Series Data ◽  
Support Vector ◽  
Identification Performance ◽  
Short Term ◽  
Gas Identification

Gas identification/classification through pattern recognition techniques based on gas sensor arrays often requires the equilibrium responses or the full traces of time-series data of the sensor array. Leveraging upon the diverse gas sensing kinetics behaviors measured via the sensor array, a computational intelligence- based meta-model is proposed to automatically conduct the feature extraction and subsequent gas identification using time-series data during the transitional phase before reaching equilibrium. The time-series data contains implicit temporal dependency/correlation that is worth being characterized to enhance the gas identification performance and reliability. In this context, a tailored approach so-called convolutional long short-term memory (CLSTM) neural network is developed to perform the identification task incorporating temporal characteristics within time-series data. This novel approach shows the enhanced accuracy and robustness as compared to the baseline models, i.e., multilayer perceptron (MLP) and support vector machine (SVM) through the comprehensive statistical examination. Specifically, the classification accuracy of CLSTM reaches as high as 96%, regardless of the operating condition specified. More importantly, the excellent gas identification performance of CLSTM at early stages of gas exposure indicates its practical significance in future real-time applications. The promise of the proposed method has been clearly illustrated through both the internal and external validations in the systematic case investigation.

Sign in / Sign up

Export Citation Format

Share Document