Data Science News
Ford Motor Company funding success for Dr. Tanaya Guha
Dr. Tanaya Guha (PI) has been awarded a research grant by Ford Motor Company through their Global University Research Program to develop the project "Multimodal Learning for In-Car Driver's Activity Monitoring". This 2-year project aims at developing an AI system that can monitor driver's and passengers' safety through audiovisual scene analysis integrated with short-term driving patterns. For example, by creating alerts when a driver is distracted. The project will be developed in collaboration with Ford's AI research at Michigan.
Hengrui Zhang has abstract accepted to the British Conference of Undergraduate Research 2021
Congratulations to third-year Computer Science student Hengrui Zhang, who has had an abstract accepted at the British Conference of Undergraduate Research 2021 (BCUR 2021). Hengrui’s abstract, titled "Emotional Adjusted Chinese Sentiment Analysis", proposes a new and enhanced sentiment analysis model, SETCM, which combines the advantages of sentiment lexicon, emoji and neural computing technology. The proposed method overcomes the shortcomings of existing sentiment analysis on Chinese-language text. It is based on the work that Hengrui has completed as part of his third-year project, supervised by Dr Greg Watson.
Identifying banknote fingerprints can stop counterfeits on streets
Shen Wang and Professor Feng Hao from the Systems and Security theme at the Department of Computer Science and Ehsan Toreini from Durham University, have had the paper ‘Anti-Counterfeiting for Polymer Banknotes Based on Polymer Substrate Fingerprinting’, published in the journal IEEE Transactions on Information Forensics and Security, in which they propose a novel technique called Polymer Substrate Fingerprinting, which can identify each banknote’s own unique, unclonable fingerprint.
The researchers have found that every polymer banknote has a unique "fingerprint", which is caused by the inevitable imperfection in the physical manufacturing process, whereby the opacity coating, a critical step during the production of polymer notes, leaves an uneven coating layer with a random dispersion of impurities in the ink. This imperfection results in random translucent patterns when a polymer banknote is back-lit by a light source.