Xiang Zhang

PhD Candidate in Electrical Engineering | Machine Learning & Signal Processing Researcher
Columbus, US.

About

Highly innovative PhD Candidate in Electrical Engineering with a robust background in deep learning, signal processing, and machine learning, driving advancements in areas like medical imaging and anomaly detection. Proven ability to design and implement cutting-edge algorithms, publish in top-tier journals, and translate complex research into tangible results. Seeking Research Scientist or Machine Learning Engineer roles to leverage expertise in developing impactful AI solutions.

Work

The Ohio State University
|

Graduate Research Associate

Columbus, OH, US

Summary

Led advanced research in deep learning and signal processing, developing novel algorithms for medical imaging and anomaly detection as part of PhD studies.

Highlights

Developed a novel deep learning framework for accurate image reconstruction and artifact reduction in Magnetic Resonance Imaging (MRI), achieving a 15% improvement in signal-to-noise ratio and faster acquisition times.

Designed and implemented a robust unsupervised anomaly detection system for industrial sensor data, reducing false positives by 20% and identifying critical equipment failures 2 weeks in advance of traditional methods.

Authored and co-authored 5 peer-reviewed publications in top-tier IEEE journals and conferences, contributing to the academic community and advancing the state-of-the-art in medical imaging and time-series analysis.

Collaborated with cross-functional teams of clinicians and engineers to translate research findings into practical solutions, successfully integrating models into experimental prototypes for real-world validation.

Mentored junior graduate students on research methodologies, experimental design, and technical writing, fostering a collaborative research environment and accelerating project timelines.

GE Healthcare
|

Research Intern

Wauwatosa, WI, US

Summary

Contributed to the development of advanced deep learning solutions for medical imaging applications, enhancing diagnostic capabilities and patient care.

Highlights

Developed and optimized deep learning algorithms for medical image segmentation and reconstruction, improving model accuracy by 10% and reducing processing time by 15% for critical diagnostic tasks.

Implemented and evaluated various neural network architectures, including U-Net and GANs, to address challenges in low-dose CT reconstruction, resulting in superior image quality with reduced radiation exposure.

Conducted comprehensive data analysis and preprocessing on large-scale medical datasets, ensuring data integrity and optimizing input for machine learning models.

Collaborated with senior research scientists and clinical experts, presenting weekly progress reports and contributing to strategic discussions on product development and research directions.

The Ohio State University
|

Graduate Teaching Associate

Columbus, OH, US

Summary

Instructed undergraduate courses in electrical engineering, facilitating student learning and improving academic performance.

Highlights

Taught and assisted in undergraduate courses including 'Signals and Systems' and 'Introduction to Electrical and Computer Engineering,' supporting over 150 students annually.

Developed supplementary course materials, led recitation sessions, and provided one-on-one tutoring, which contributed to a 10% improvement in average student exam scores.

Graded assignments and exams, providing constructive feedback to students that enhanced their understanding of complex engineering concepts.

Held regular office hours to provide academic support and guidance, fostering a positive learning environment and improving student engagement.

Education

The Ohio State University
Columbus, OH, United States of America

PhD

Electrical Engineering

Grade: 3.9/4.0

Courses

Deep Learning

Digital Signal Processing

Machine Learning

Convex Optimization

Advanced Image Processing

University of California, Irvine
Irvine, CA, United States of America

M.S.

Electrical Engineering

Grade: 3.8/4.0

Courses

Advanced Digital Signal Processing

Statistical Signal Processing

Introduction to Machine Learning

Stochastic Processes

University of California, Riverside
Riverside, CA, United States of America

B.S.

Electrical Engineering

Grade: 3.7/4.0

Courses

Circuits and Systems

Electromagnetics

Digital Logic Design

Data Structures

Awards

Best Student Paper Award

Awarded By

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

Recognized for innovative research in deep learning-based signal processing for medical applications.

Graduate Fellowship

Awarded By

The Ohio State University

Awarded for outstanding academic achievement and research potential in Electrical Engineering.

Publications

Deep Learning for Accelerated MRI Reconstruction: A Comprehensive Review

Published by

IEEE Transactions on Medical Imaging

Summary

A comprehensive review of recent advances in deep learning techniques for accelerating MRI reconstruction, highlighting key methodologies and future research directions.

Unsupervised Anomaly Detection in Time Series Data using Generative Adversarial Networks

Published by

Journal of Machine Learning Research

Summary

Introduced a novel GAN-based approach for unsupervised anomaly detection in complex time-series data, demonstrating superior performance over traditional methods.

Sparse Coding-Inspired Deep Networks for Image Denoising

Published by

IEEE Signal Processing Letters

Summary

Proposed a deep neural network architecture inspired by sparse coding principles, achieving state-of-the-art results in image denoising tasks.

Languages

English
Mandarin Chinese

Skills

Programming Languages

Python, MATLAB, C++, Julia.

Machine Learning & Deep Learning

PyTorch, TensorFlow, Keras, Scikit-learn, OpenCV, Generative Adversarial Networks (GANs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Transformer Networks, Unsupervised Learning, Reinforcement Learning.

Signal & Image Processing

Digital Signal Processing (DSP), Image Reconstruction, Medical Imaging (MRI, CT), Compressed Sensing, Sparse Representation, Wavelet Transforms, Spectral Analysis.

Tools & Platforms

Git, Docker, Jupyter Notebook, VS Code, Linux, AWS (EC2, S3).

Data Analysis & Visualization

NumPy, Pandas, Matplotlib, Seaborn, Data Preprocessing, Statistical Modeling.

Projects

MRI Image Reconstruction with Deep Learning

Summary

Developed advanced deep learning models to reconstruct high-quality MRI images from undersampled k-space data, significantly reducing scan times and improving image clarity.

Time-Series Anomaly Detection for Industrial IoT

Summary

Created an unsupervised deep learning framework for detecting anomalies in multivariate time-series data from industrial IoT sensors, aiming to predict equipment failures.