MM-UrbanFAC Urban Functional Area Classification Model Based on Multimodal Machine Learning


The majority of the classification methods that are currently used for urban functional areas are only based on the analysis and modeling of data from a single source. As a result, these methods are unable to make full use of the multi-scale and multi-source data that is simple to obtain. This paper therefore proposed a classification model of urban functional areas based on multi-modal Machine Learning. It did so by analyzing regional remote sensing images and behavior data of visitors in the area. Additionally, it utilized a combination of supervised methods to extract the deep-seated features and relationships of different kinds of data. Finally, it filtered and merged the overall and local features of the data. The model used a dual branch neural network that combined SE-ResNeXt and Dual Path Network (DPN) to automatically mine and fuse the overall characteristics of multi-source data. It also used designed feature engineering to deeply mine the behavior data of users in order to obtain more association information. Finally, it combined an algorithm that was based on Gradient Boosting Decision Tree in order to learn the characteristics of different levels and obtain the classification probability for different levels. In conclusion, we continued to use the algorithm that was based on the Gradient Boosting Decision Tree in order to learn the probability distribution of different levels of features in order to obtain the ultimate prediction results of urban functional area classification. The results demonstrated that the MM-UrbanFAC model is capable of successfully integrating the characteristics of multi-modal data. This was accomplished through the analysis and experimental verification of real data sets. This method can effectively integrate the results of multiple models and accurately classify urban functional areas, and the model can provide reference for tourism recommendation, urban land planning, and urban construction. The integration framework based on gradient lifting tree improved the prediction performance when compared to a single classifier.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE : Spatio-Temporal Meta Learning for Urban Traffic Prediction ABSTRACT: It is very difficult to predict urban traffic because of three factors: 1) the complex spatio-temporal correlations of urban traffic, which include
PROJECT TITLE : Foresee Urban Sparse Traffic Accidents: A Spatiotemporal Multi-Granularity Perspective ABSTRACT: Due to the rapid pace of urbanization, car accidents have evolved into a significant threat to both health and development.
PROJECT TITLE : W-GeoR: Weighted Geographical Routing for VANET’s Health Monitoring Applications in Urban Traffic Networks ABSTRACT: The infrastructure-based communication system that is currently in place is susceptible
PROJECT TITLE : Long-Term Urban Traffic Speed Prediction With Deep Learning on Graphs ABSTRACT: The ability to predict the speed of traffic is one of the fundamentals of advanced traffic management, and the gradual deployment
PROJECT TITLE : Incorporating Multi-Source Urban Data for Personalized and Context-Aware Multi-Modal Transportation Recommendation ABSTRACT: The recommendation of appropriate modes of transportation is an essential component of

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry