As urbanization accelerates and global populations rise, the concept of smart cities is becoming increasingly vital. Smart cities aim to deliver intelligent, data-driven solutions to address challenges in everyday life, environmental sustainability, public safety, and urban services. Among these, the development of Intelligent Transportation Systems (ITS) and Advanced Traffic Management Systems (ATMS) plays a crucial role in shaping the future of urban mobility.

These systems integrate communication technologies, sensors, and data analytics to create an efficient, real-time, and responsive transportation network. A key challenge in ITS and ATMS is accurate traffic prediction, which is essential for mitigating congestion, enhancing safety, and ensuring smoother travel experiences.

This research will focus on exploring and applying machine learning techniques to model and predict traffic behavior using real-world sensor data. You will investigate data-driven approaches to improve transportation efficiency and reliability in the context of smart cities.

Possible Tasks
You may work on one or more of the following topics:

• Data Cleaning and Preprocessing
• Traffic Flow Prediction
• Congestion Detection and Forecasting
• Road Network Clustering

Students are also encouraged to propose their own project ideas related to this theme.

Required Skills

• Basic proficiency in Python
  • Familiarity with one or more of the following libraries: Pandas, NumPy, Matplotlib, Tslearn, Keras, TensorFlow, Scikit-learn
• Foundational knowledge of data analysis and machine learning principles