Dongkuan Xu is a prominent inventor based in State College, PA (US). He has made significant contributions to the field of deep learning and time series analysis. With a total of 7 patents, his work focuses on advanced methodologies for processing and predicting trends in multivariate time series data.

Latest Patents

Dongkuan Xu's latest patents include "Tensorized LSTM with adaptive shared memory for learning trends in multivariate time series." This innovative method involves collecting multivariate time series data from various sensors and utilizing a tensorized long short-term memory (LSTM) with adaptive shared memory to learn historical dependencies. Additionally, he has developed a "Spatio temporal gated recurrent unit," which implements a spatial and temporal attention-based gated recurrent unit (GRU) for node classification over temporal attributed graphs. This method computes embeddings of nodes at different snapshots and applies a classification model to determine classified nodes within temporal attributed graphs.

Career Highlights

Dongkuan Xu is currently employed at NEC Corporation, where he continues to advance his research and development efforts. His work has garnered attention for its innovative approach to machine learning and data analysis.

Collaborations

Some of his notable coworkers include Wei Cheng and Haifeng Chen, who contribute to the collaborative efforts in their research projects.

Conclusion

Dongkuan Xu's contributions to the field of deep learning and time series analysis are noteworthy. His innovative patents and ongoing work at NEC Corporation highlight his commitment to advancing technology in this area.