Abstract:
Social media like Sina Weibo can show traffic information like road jams, illegal behaviors, and emergency measures. Traffic data mining remains difficult. This paper proposes a deep learning-based traffic jam management method using social media data. The method has two main ideas. First, MC-LSTM-Conv is a multichannel network with LSTM and Conv layers. Two information channels extract abstract text features in this model. Two Conv-layers and one LSTM-layer are added to each channel. MC-LSTM-Conv extracts traffic jam-related check-in microblogs from mass Sina Weibo data. Second, traffic-jam keywords are used to create matching rules. These rules classify the microblogs extracted in the first step into four classes based on road conditions: traffic accidents or large-scale activities, road construction, traffic lights, and government agency inefficiency. The proposed multichannel network outperforms Sina Weibo in extracting traffic jam microblogs. Keyword fuzzy matching can quickly retrieve traffic jam data.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
