Numerical and trend k-nearest neighbor combined forecasting method for the number of residents in the passenger transport hub area
A combination forecasting technology for passenger transport hubs, which is applied in the field of intelligent transportation, can solve the problems that short-term forecasts cannot meet the needs of passenger transport hub vehicle dispatching plan formulation, peak warning, etc., and achieve the effect of high forecasting accuracy
Active Publication Date: 2021-11-30
SOUTH CHINA UNIV OF TECH +1
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] In order to solve the problem that the short-term prediction cannot meet the working needs of passenger transport hub vehicle dispatching plan formulation, peak warning, passenger flow control, etc., the present invention provides a combined prediction method for the number of residents in the passenger transport area based on numerical values and trend k nearest neighbors, which is accurate and high And it is applicable to the prediction of the number of residents in the passenger transport hub area for a long period of time
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0021] like figure 1 As shown, a combined forecasting method for the number of people staying in the passenger transport hub area based on the value and trend k-nearest neighbors, the steps of the method are as follows:
[0022] S1: Obtain real-time regional residence data through the detection system;
[0023] The detection system includes a passenger flow detector and mobile phone signaling, and the detection system is used to collect and estimate the number of people staying in the area of the passenger transport hub in each time interval, and obtain historical and current data on the area staying in the area; the staying Situation data includes the number of people staying in the area and the corresponding collection time.
[0024]In this embodiment, 5 minutes is used as the data collection interval, and the historical data of the area residence situation of a certain railway station square from January 1, 2017 to September 30, 2018 is obtained by detecting mobile phone...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a combination prediction method for the number of people staying in a passenger transport hub area based on numerical value and trend k nearest neighbors. The method is as follows: real-time acquisition of data on the area's residence situation; determining the sample space according to the date characteristics of the day to be predicted; according to the Euclidean distance Select k neighboring samples with similar values, and calculate the prediction result curve of the number of residents in the area based on numerical similarity; select k neighboring samples with similar trends according to the incremental ratio standard deviation, and calculate the prediction results of the number of residents in the area based on the trend similarity Curve; according to the time-varying weight coefficient, calculate the combined forecast curve of the number of residents in the area to be predicted. The present invention integrates the characteristics of numerical prediction and trend prediction, can ensure the prediction accuracy of the number of people staying in the area for a long period of time, provides a reliable basis for the resource allocation, vehicle scheduling, early warning notification, passenger flow control and safety guarantee of the passenger transport hub, and can assist the passenger transport hub Carry out real-time effective management and improve service quality. The invention is applicable to the field of intelligent transportation.
Description
technical field [0001] The present invention relates to the field of intelligent transportation, and more specifically, relates to a combined prediction method for the number of residents in passenger transport hub areas based on numerical value and trend k-nearest neighbors. Background technique [0002] The urban passenger transport hub is an important part of the urban transportation system. It is the central point of urban passenger flow collection and distribution. It undertakes the transfer function and direct function of the daily urban passenger flow. It is a transfer center that meets the diverse and complex needs of urban passenger flow. The number of resident passengers in the passenger transport hub directly reflects the crowd density and degree of congestion in the hub, and is one of the most important reference indicators for the passenger flow organization plan and the distribution management plan. Management provides time guarantee, which is of great signific...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06Q10/04G06Q50/30
CPCG06Q10/04G06F18/24147G06Q50/40
Inventor 卢凯林观荣吴蔚田鑫首艳芳
Owner SOUTH CHINA UNIV OF TECH