Gen Li

Currently a Master's student in Electrical Engineering at Northwestern University, with a Computer Engineering undergraduate degree from North Carolina State University, I specialize in electrical and computer engineering, backed by a strong theoretical foundation and enriched through practical project experience. My technical expertise lies in programming languages like C, Python, LC-3 Assembly, MATLAB, and Verilog, and extends to complex problem-solving in embedded systems, particularly in autonomous vehicle projects. I excel in teamwork and communication, having led and collaborated effectively in diverse group settings, ensuring the successful execution of complex projects.

Sept 2023 - Dec 2023 | Project: Weakly Supervised Pathological Image Analysis

• Description: Applied weak supervision learning techniques to analyze large pathological images, aiming to predict the two-year survival rate of patients with brain tumors.
• Responsibilities: Managed dataset configurations in Google Colab, using Python and TensorFlow for data processing and model development. Efficiently managed structured and unstructured data through custom scripts, optimizing model training and validation processes.
• Outcomes: Achieved a highly accurate model, reaching approximately 80% accuracy on the validation set, and 75% recall and 70% precision on the test set.

Apr 2023 - Sept 2023 | Project: Brain Tumor MRI Image Segmentation

• Description: Focused on precise segmentation of brain tumor MRI imaging, utilizing advanced deep learning models based on U-Net architecture. Aimed to improve segmentation of glioma brain tumors in T1 and T2 weighted MRI scans.
• Responsibilities: Built and optimized U-Net based deep learning models for brain tumor image segmentation. Precisely preprocessed data from the BraTS 2021 challenge.
• Results: Significantly improved the accuracy of brain tumor image segmentation through in-depth research and careful tuning of the U-Net model.

Aug 2022 - May 2023 | Project: EcoPRT Automated Personal Transit System (Road Quality Detection) | Graduation Project

• Background: Sponsored by IBM, EcoPRT Automated Personal Transit System aimed to improve campus transportation through an all-electric, automated fleet.
• Responsibilities: Implemented road quality classification using TensorFlow learning framework and Convolutional Neural Network (CNN) models. Enabled real-time communication of the car with IBM cloud, sending events, car routes, and GPS information. Calibrated gyroscopes and employed multimodal methods to enhance road classification accuracy.
• Design Results: Achieved 87% accuracy in road classification. Detailed project content and results are publicly available on GitHub: EcoPRT-IBM-Cloud-Fleet

Aug 2022 - Dec 2022 | Project: Cache Simulator | Course Project

• Background: Designed and implemented a versatile cache and memory hierarchy simulator, capable of simulating various levels of cache systems like L1, L2, L3, etc.
• Responsibilities: Managed cache block allocation and control, programming in C to enhance code efficiency, accuracy, and the simulator’s versatility and adaptability.
• Effectiveness: Successfully developed a simulator capable of mimicking multi-level cache systems, enhancing problem-solving skills in complex systems.

Aug 2021 - Dec 2021 | Project: Autonomous Driving Car | Course Project

• Background: Realized an autonomously and manually drivable car through assembly and programming.
• Responsibilities: Familiarized and applied MSP430 microcontroller, achieving automatic pathfinding, positioning, and manual control of the car. Utilized key technologies like photodiodes, WiFi modules, and motor control to enhance the car’s performance in embedded systems. Wrote and debugged code for precise positioning, route tracking, and both autonomous and manual driving functionalities.
• Achievements: Gained a deeper understanding of embedded systems and honed skills in practical hardware and software integration.