Hi, I'm Afshin, a passionate Machine Learning Engineer currently completing my Master’s degree in Applied Science at the University of British Columbia. My research has focused on leveraging deep learning models for infrastructure maintenance in transportation engineering, combining my technical expertise with a drive to solve real-world problems.
I hold a Bachelor’s degree in Computer Engineering from Ferdowsi University of Mashhad. Over the past four and a half years, I have developed extensive experience in deep learning, working on a range of projects from academic research to industry applications. Before embarking on my Master's journey, I worked as a Machine Learning Engineer at a FinTech startup, where I applied my skills to create innovative solutions.
I am actively seeking new job opportunities where I can apply my knowledge and grow as a professional. I am open to exciting roles that challenge me to use my skills in machine learning, data science, and AI. I am also flexible with relocation and am eager to explore new opportunities, whether they are local or abroad.
For a detailed overview of my background, experience, and skills, please check out my resume and CV below!
View Academic CV View Professional Resume
Served as a Research Assistant in the SALMALIS Lab at the University of British Columbia, focusing on
developing machine and deep learning applications for transportation engineering under the supervision of
Dr. Suliman Gargoum.
Conducted advanced research on Generative Networks, including DCGAN, WGAN, and Conditional GAN, to create
synthetic road image datasets. This work led to a 5% improvement in crack classification metrics, while
adding stabiliy and agency to data augmentation
showcasing innovation in enhancing road safety analysis.
Developed and executed sophisticated object detection and classification pipelines for road infrastructure,
employing images and 3D point clouds to improve accuracy and efficiency in infrastructure assessment.
Worked on the enhancement of 3D point cloud segmentation models using attention mechanisms.
Undertook the role of Lab Manager for the SALMALIS Lab, responsible for crucial lab operations including
system maintenance, hardware setups, and software installations, ensuring optimal research environment and
infrastructure.
Mentored 3 summer interns, giving them projects, tasks, and research material, while teaching them about
different aspects of deep learning in transportation.
Served as a Teaching Assistant in different capacities for several
courses, with responsibilities ranging from teaching lab sessions,
in-class assistant, invigilation, exam and assignment grading, and
holding problem-solving sessions for students, for classes with
more than 100 students. Gained a satisfaction score of at least
90% for the classes
List of classes:
Researched & worked on price and trend prediction, and
decision-making models on cryptocurrency data.
Developed Deep Reinforcement Learning agents and environments to
automate the trading process, with online data processing and
agents achieving up to 3000% profits even with low training
samples using Transfer Learning
Performed various data extraction, information crawling &
transformation tasks on data using techniques to generate valuable
features from raw data.
Researched and developed several anomaly detection methods in power consumption data. Worked with team on
the design, and development of an anomaly detection and consumption forecasting platform as a service.
Gained experience in machine learning, deep learning, data mining, and big data handling.
The developed models had 92% accuracy in trend prediction and 90% accuracy in fraud detection. Two
peer-reviewed papers regarding anomaly and fraud detection using AI and deep learning were published.
Managed 3 summer interns during my time in the lab, defining projects, evaluating their tasks, and holding
weekly meetings with them.
Teaching assistant for several courses, with responsibilities
including teaching in class, assignment creation and grading, exam
creation and grading, teaching labs, project defining and grading,
and coding assistant.
List of classes:
This project uses Deep Convolutional Generative Adversarial Networks (DCGAN), Wasserstein GAN (WGAN), WGAN with Gradient Penalty (WGAN_GP), and Wasserstein Conditional GAN (cGAN) with Gradient (C_WGAN_GP) Penalty, to generate synthetic images of pavement cracks. These images can be used to augment existing datasets, improve the robustness of machine learning models, and facilitate research in pavement maintenance and repair.
Deep Learning object detection models, including YOLOv5 and Faster R-CNN, were used to detect different objects, such as traffic signs, traffic roads, pavement lane marking, and pavement cracks, in road images. The images were gathered from Canadian roads and public datasets, and were annotated by us using CVAT to be compatible with YOLO and COCO formats.
Developed several deep reinforcement learning agents and environments on cryptocurrency trading data based on custom reward functions, with long-term and short-term benefits prioritization, and multi-currency trading. Used Transfer Learning, and data preprocessing to trade currencies with similar patterns without extensive historical data. The agents showed consistent profitability even in market volatility in various timeframes with 3000% cumulative profits in 2020-2022.
Used deep learning models, such as Autoencoders, RNNs, MLPs, and data analysis techniques, like missing value interpolation, clustering, decision trees, to develop Trend Prediction and Fraud Detection software and website. Preprocessing steps including data normalization, standard scaling, and outlier removal, are performed on the data. The trained deep learning models, data analysis techniques and preprocessing pipelines were incorporated into 2 software, sold to Mashhad Electrical Utility Company, with more than 92% accuracy in both tasks.
Accepted in Proceedings of the Transportation Association of Canada June 2024
Submitted to IEEE Transactions on Intelligent Transportation Systems Journal July 2024
Published in Electric Power Systems Research", Volume 208, 2022, 107895, ISSN 0378-7796
Published in 2021 5th International Conference on Internet of Things and Applications (IoT), 2021, pp. 1-6
This article covers the process of classifying the CIFAR-10 dataset using a simple Convolutional Neural Network (CNN). The CIFAR-10 dataset is widely used for image classification tasks, and the article probably outlines the steps for building a basic CNN model in Python, training it on CIFAR-10 images, and evaluating its performance.
[Get In Touch With Me!]
My E-Mail