A granular computing approach to provide transparency of intelligent systems for criminal investigations

Book chapter


Zhang, L. 2021. A granular computing approach to provide transparency of intelligent systems for criminal investigations. in: Pedrycz, W. and Chen, S.-M. (ed.) Interpretable Artificial Intelligence: A Perspective of Granular Computing Cham Springer.
AuthorsZhang, L.
EditorsPedrycz, W. and Chen, S.-M.
Abstract

Criminal investigations involve repetitive information retrieval requests in high risk, high consequence, and time pressing situations. Artificial Intelligence (AI) systems can provide significant benefits to analysts, by sharing the burden of reasoning and speeding up information processing. However, for intelligent systems to be used in critical domains, transparency is crucial. We draw from human factors analysis and a granular computing perspective to develop Human-Centered AI (HCAI). Working closely with experts in the domain of criminal investigations we have developed an algorithmic transparency framework for designing AI systems. We demonstrate how our framework has been implemented to model the necessary information granules for contextual interpretability, at different levels of abstraction, in the design of an AI system. The system supports an analyst when they are conducting a criminal investigation, providing (i) a conversational interface to retrieve information through natural language interactions, and (ii) a recommender component for exploring, recommending, and pursuing lines of inquiry. We reflect on studies with operational intelligence analysts, to evaluate our prototype system and our approach to develop HCAI through granular computing.

KeywordsGranular computing; Interpretable AI; Intelligence analysis; Conversational agents
Year2021
Book titleInterpretable Artificial Intelligence: A Perspective of Granular Computing
PublisherSpringer
Output statusPublished
Place of publicationCham
SeriesStudies in Computational Intelligence
ISBN9783030649494
Publication dates
Print26 Mar 2021
Publication process dates
Deposited03 Nov 2021
Digital Object Identifier (DOI)https://doi.org/10.1007/978-3-030-64949-4_11
Related URLhttps://link.springer.com/book/10.1007/978-3-030-64949-4
Permalink -

https://repository.canterbury.ac.uk/item/8z655/a-granular-computing-approach-to-provide-transparency-of-intelligent-systems-for-criminal-investigations

  • 1
    total views
  • 0
    total downloads
  • 1
    views this month
  • 0
    downloads this month

Export as

Related outputs

Developing conversational agents for use in criminal investigations
Hepenstal, S., Zhang, L., Kodagoda N. and Wong B.L.W 2021. Developing conversational agents for use in criminal investigations. ACM Transactions on Interactive Intelligent Systems. 11 (3-4), pp. 1-35. https://doi.org/10.1145/3444369