A mobile phone multi-sensor based user travel mode analysis method
A technology of travel mode and analysis method, which is applied in the field of intelligent transportation services, can solve problems such as sensor data difficulty and user behavior recognition, and achieve the effect of improving accuracy
Active Publication Date: 2020-05-29
ZHEJIANG UNIV
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, due to the habituality and complexity of human movement, it is difficult to accurately identify user behavior with a single sensor data. Therefore, research on how to use multiple sensor data for integrated learning to accurately identify user behavior has become an important issue in the field of intelligent transportation services. research problem
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 Construction
[0051] In order to describe the present invention more specifically, the technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0052] The present invention is based on the mobile phone multi-sensor user travel mode analysis method. By collecting and filtering data from the built-in sensors of the mobile phone, such as acceleration, gyroscope, and GPS, etc., the feature vector formed according to the multi-sensor observation results is compared with the feature reference vector, and the weighted The multi-dimensional judgment method is used for preliminary classification, and the improved AdaBoost ensemble learning algorithm is used to combine the preliminary classification results, and finally analyze the optimal decision-making results to realize the function of identifying the user's travel mode.
[0053] Such as figure 1 As shown, the workflow of the user travel mode identific...
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 present invention disclosed a user travel method based on mobile phone multi -sensor. This method for data collection and filtering the built -in sensor such as acceleration, gyroscope, GPS, etc., and based on the feature vector and characteristic benchmark vector formed by the multi -sensor observation resultsFor comparison, use the weighted multi -dimensional judgment method for preliminary classification, use the improved Adaboost integrated learning algorithm to combine the preliminary classification results, finally analyze the optimized decision -making results, and realize the function of identifying the user travel method.The data integrated learning analysis algorithm designed by the present invention is not a simple and average of a variety of data, but to train the original data collected by the mobile phone to train and learn, and then classify and identify the data, and finally make the best decision -making process.
Description
technical field [0001] The invention belongs to the technical field of intelligent traffic services, and in particular relates to a mobile phone multi-sensor-based analysis method for a user's travel mode. Background technique [0002] With the development of related technologies, smart phones are increasingly equipped with various sensors, such as acceleration for mobile phone motion status detection, gyroscope for motion behavior recognition, GPS for map positioning and navigation, etc. Therefore, using the built-in sensors of mobile phones to identify user behaviors and provide users with various intelligent and personalized services according to the identified behavior types has become one of the hot research issues. However, due to the habituality and complexity of human movement, it is difficult to accurately identify user behavior with a single sensor data. Therefore, research on how to use multiple sensor data for integrated learning to accurately identify user behav...
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): G06K9/62
CPCG06F18/24
Inventor 杨国青李红夏瑶章昌仲吴朝晖
Owner ZHEJIANG UNIV