Xiang Zhang

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.

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.

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.