1. Home »
  2. Supervisor: Dr. Kashif Sultan
Supervisor: Dr. Kashif Sultan

 

Dynamic Mobility Prediction and Network Optimization Using Machine Learning on CDR Data for Smart Cities

 

Supervisor: Dr. Kashif Sultan, Senior Assistant Professor

Campus/School/Dept: BUIC H-11/BSEAS/SE

Supervisory Record: 

  • PhD Produced: 0
  • PhD Enrolled: 0
  • MS/MPhil Produced: 9
  • MS/MPhil Enrolled: 1

 

Topic Brief Description: 

The increasing adoption of smart city technologies demands intelligent systems capable of predicting human mobility and optimizing mobile network resources in real-time. Call Detail Record (CDR) data, which encapsulates user activity, location, and network usage, presents an invaluable resource for developing such systems.

This research focuses on using machine learning to model human mobility patterns and dynamically optimize mobile network resources. By leveraging spatial-temporal insights from CDR data, this study will address challenges like network congestion, load balancing, and resource allocation. The research aims to enhance urban connectivity and support smart city initiatives, such as adaptive traffic management and emergency response systems.

 

Research Objectives/Deliverables: 

  1. To design advanced machine learning models for real-time mobility prediction based on spatial-temporal patterns in CDR data.
  2. To develop algorithms for dynamic network optimization, focusing on load balancing and congestion management.
  3. To propose mobility-driven solutions for enhancing urban connectivity and integrating telecommunications data into smart city infrastructure Research Questions:
  4. How can spatial-temporal features in CDR data be used to predict real-time human mobility patterns?
  5. What machine learning approaches can optimize network resource allocation in response to dynamic mobility trends?
  6. How can predictive insights from CDR data enhance smart city applications, such as adaptive traffic control and emergency network prioritization?

 

Candidate’s Eligibility Profile: 

  1. The applicant must have an MS/MPhil/Equivalent degree in Computer Science, Information technology, Software Engineering, or a related field with a CGPA > 3.0. Strong knowledge of machine learning, big data analytics, and telecommunications systems is required.
  2. Proficiency in programming languages like Python, R, or MATLAB and experience with spatial-temporal data processing is advantageous.
  3. The candidate should have excellent problem-solving skills, a keen interest in applying machine learning to smart city challenges, and proficiency in spoken and written English.