{"id":20074192,"url":"https://github.com/furk4neg3/traffic-volume-forecasting","last_synced_at":"2026-01-03T23:03:14.073Z","repository":{"id":257601113,"uuid":"858767775","full_name":"furk4neg3/Traffic-Volume-Forecasting","owner":"furk4neg3","description":"Traffic volume forecasting with AI using bidirectional LSTM model and React frontend.","archived":false,"fork":false,"pushed_at":"2024-09-17T14:52:39.000Z","size":22721,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-11-13T14:54:45.701Z","etag":null,"topics":["artificial-intelligence","bidirectional-lstm","data-visualization","deep-learning","flask","forecasting","fullstack-development","react","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/furk4neg3.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-09-17T13:56:39.000Z","updated_at":"2024-09-22T18:33:55.000Z","dependencies_parsed_at":"2024-09-17T17:43:04.460Z","dependency_job_id":null,"html_url":"https://github.com/furk4neg3/Traffic-Volume-Forecasting","commit_stats":null,"previous_names":["furk4neg3/traffic-volume-forecasting"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/furk4neg3%2FTraffic-Volume-Forecasting","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/furk4neg3%2FTraffic-Volume-Forecasting/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/furk4neg3%2FTraffic-Volume-Forecasting/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/furk4neg3%2FTraffic-Volume-Forecasting/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/furk4neg3","download_url":"https://codeload.github.com/furk4neg3/Traffic-Volume-Forecasting/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":233678686,"owners_count":18712980,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["artificial-intelligence","bidirectional-lstm","data-visualization","deep-learning","flask","forecasting","fullstack-development","react","tensorflow"],"created_at":"2024-11-13T14:49:52.022Z","updated_at":"2025-09-20T17:31:22.836Z","avatar_url":"https://github.com/furk4neg3.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Explanation of Project:\nProject that I created while my internship in Ministry of Transportation and Infrastructure, Turkiye. Things that I'm about to tell are done in Colab notebooks, and for legal requirements, I can't share these notebooks. \n\nIn the beginning, data I received had so many issues. I cleaned the data, then done some feature engineering on it. After that, I added things to data (the most important things which are lat_bin, lon_bin and count are added by me, they were not in the data). \n\nThen I created AI models to predict traffic volume. Tried MLP, LSTM, GRU, bidirectional LSTM, LSTM - GRU mixed and transformer models. Best performing one was bidirectional LSTM so I chose it. I visualized the predictions and true data, and it was working nearly perfect.\n\nAfterwards, I created frontend for the project using React. Used Flask for data exchange between Python backend and React frontend. Used OpenLayers to draw the map.\n\n## Notes: \n1- There's only day and hour inputs in the project. That's because data that I received only contained 2 weeks. At first, I was going to draw real map on the website too, that's why I created model to take only this amount of day. In the scenario when receiving data for multiple years, month and year inputs can be added.\n\n2- I excluded density_data.csv and bi_lstm_model because I don't want to share them. That's why project wont work in your computer, but I added example images of project to show what it looks like when working. \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffurk4neg3%2Ftraffic-volume-forecasting","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffurk4neg3%2Ftraffic-volume-forecasting","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffurk4neg3%2Ftraffic-volume-forecasting/lists"}