Detection and clustering of mixed-type defect patterns in wafer bin maps   A new method for detecting and clustering mixed-type defect patterns in wafer bin maps from semiconductor manufacturing is developed   Article  |  Fall 2018     The wafer fabrication process consists of multiple sequential processes, such as oxidation, photolithography, etching, ion implantation, and ...

Discovering polymorphic urban characteristics from social media   A novel methodology is developed that extracts semantic features of urban places, or placeness, based on social media. The methodology performs placeness analysis based on user’s activity, with sentiment analysis, place-user correlation analysis, and hot-spot analysis to extract polymorphic urban characteristics. Based on the methodology,...

Fast proton-conducting solid-state electrolytes for highly efficient energy conversion   Highly densified BaCeO3 polycrystals free from a grain-boundary amorphous phase, through a combination of atomic-scale chemical analysis and physical imaging, were shown to be easily fabricated by a conventional ceramic process and to possess sufficiently high proton conductivity along with significantly improved chemica...

An ultra-low power receiver for an internet-of-things application wireless transceiver   Professor Sang-Gug Lee has developed a new receiver for an internet-of-things application wireless transceiver. It is the world’s first receiver capable of supporting more than -100dBm sensitivity while consuming less than 1mW of power.   Article  |  Fall 2018     Recently, everyt...

It’s time to “3D sketch” your ideas with air scaffolding   By using a new 3D sketching workflow that combines hand motion and pen drawing, you can move your hands in the air to quickly express approximate volumes and then draw detailed shapes on top of them using a pen and a tablet, making it easier and faster to express your ideas in 3D space.   Article  |  Fall 201...

Deep learning predicts drug-drug and drug-food interactions   A deep learning-based computational framework called DeepDDI was developed, which predicts 86 drug-drug interaction (DDI) types with a mean accuracy of 92.4%. DeepDDI was used to suggest potential causal mechanisms for the reported adverse drug events of 12,721 drug pairs and also predicted alternative drug members for 62,707 drug pairs having nega...