[Lectures] AI in food authentication

2019-09-06

Speaker: Prof. Hui Wang (Ulster University)
Venue: Room 213, Building B3,University Town Campus


Title I: AI in food authentication
Time : Sep 11, Wednesday, 11:00-12:00

Abstract:
AI has recently been on the spotlight in media, and has been identified as a priority area of development in national and international research and industrial strategies. AI has already been applied to numerous industries, including security, finance, healthcare, education, transportation, production and more. AI is also increasingly applied to food industry for tasks from food sorting, quality control, supply chain monitoring, new product design, food safety compliance, food identification food authentication. This talk will provide an overview of AI applications in the food industry. It will focus on a particular application, food authentication, covering the rationale, the techniques, the current challenges, and the opportunities. It will also present latest work by the speaker’s team in this area.

Title II: Sequential subsumption
Time : Sep 12, Thursday, 11:00-12:00

Abstract :
Subsumption is used in knowledge representation and ontology to describe the relationship between concepts. Concept A is subsumed by concept B if the extension of A is always a subset of the extension of B, irrespective of the interpretation. The subsumption relation is also useful in other data analysis tasks such as pattern recognition. For example, in image analysis to detect objects in an image, and in spectral data analysis to detect the presence of a reference pattern in a given spectrum. Sometimes the subsumption relation may not be 100% true, so it is useful to quantify this relationship. In this talk I will present a study on how to quantify subsumption for sequential patterns. I will give an axiomatic characterisation of subsumption, and present one general approach to quantification in terms of set intersection operation over concept extension. Constructing the concept extension set explicitly is impossible without specifying the domain of discourse and the interpretation. Instead, I will focus on concept intension for sequences as patterns and propose to represent concept intension of a sequence by its subsequences. Different types of concept intension set will be considered -- subsequence set, subsequence multiset, embedding set and embedding set with constraints such as warping and selection. I then present a general algorithmic framework for computing set intersections, and specific algorithms for computing different concept intension sets. I will also present an experimental evaluation of these algorithms with regard to their runtime performance.



Announced by the School of Computer Science and Engineering

 

返回原图
/