The general objective of this project is to develop methodologies based on Artificial Intelligence (AI) to enhance Fluid Antenna Systems (FAS) and to fundamentally address the scalability challenges of 6G multiple access. The focus will be on the application of AI techniques, aiming at their reliable, robust, and effective integration.
Requirements:
– Experience with the Python programming language. Familiarity with frameworks such as TensorFlow and Keras, as well as libraries including Scikit-learn, NumPy, and pandas.
– Experience with machine learning models such as Extreme Learning Machine (ELM), Multilayer Perceptron (MLP), Autoencoders, Convolutional Neural Networks (CNNs), and Kolmogorov–Arnold Networks (KANs). Desirable knowledge of Gradient Boosting models such as HistGBM, LightGBM, and XGBoost.
– Experience with data processing techniques. Desirable knowledge of methods such as Neighborhood Components Analysis (NCA), Locally Linear Embedding (LLE), and t-distributed Stochastic Neighbor Embedding (t-SNE).
– Experience with data balancing techniques.
– Desirable basic knowledge of Multiple Input, Multiple Output (MIMO), Fluid Antenna System (FAS), and Compressive Sensing (CS).
– PhD degree obtained within the last seven years.
Application:
– Applicants should send, by email to gfraiden@unicamp (subject: “x”, by x/x/2026), the following PDF documents: FAPESP Curriculum Vitae Summary; updated Lattes CV; and academic transcripts from both Master’s and PhD programs.