All codes and documents are originally written by me or with my teammate(s) and no AI tool was used for each of them. All rights are reserved.
AI/ML-Based Automatic Modulation
Recognition: Recent Trends and Future
Possibilities
Elaheh Jafarigol, Behnoud Alaghband, Azadeh Gilanpour, Saeid Hosseinipoor, and Mirhamed Mirmozafari
Documents
These are the project documents of different master level computer science classes at UNM that I have written by myself or with my teammate(s).
Continuous and Hybrid Systems with Nonlinear Dynamics Simulations (Individual Study _ CS551 )
In this paper, we simulated nonlinear continuous and hybrid systems using the Scipy library from Python.
Generating Mathematical Sequences with Cellular
Automata ( Complex Adaptive Systems _ CS523 )
This project investigates the dynamic properties and practical uses of cellular automata (CA) relating to their ability to generate mathematical sequences like the Fibonacci sequence.
Crack Detecting with LiDAR ( Data Mining _ CS521 )
In this project, the authors proposed using the LiDAR technology to evaluate the asphalt pavements’ distresses, such as cracking. The general idea is to develop the algorithm to detect the cracks on the asphalt pavement as the surface is detected, and the algorithm is trained to evaluate the long-term performance of asphalt pavement in terms of cracking.
Music Classification with Logistic Regression ( Introduction to Machine Learning _ CS529 )
This report is the outline of the development and evaluation of the project which is classifying different music genres based on their various audio features. In this project, Logistic Regression and Gradient Descent have been implemented from scratch and their accuracies are compared to other machine learning models such as random forest and support vector machines.
Music Classification with Neural Networks ( Introduction to Machine Learning _ CS529 )
In this project, we used the data music data to classify music genres by neural network. We implemented Multi-layer Perceptron (MLP), Convolutional Neural Network (CNN), and Transfer Learning (TL) in this project to classify audio genres based on their features.
