Repozytorium publikacji - Politechnika Gdańska

Visual content searching, browsing and retrieval tools have been a focus area of interest as they are required by systems from many different domains. Context-based, Content-Based, and Semantic-based are different approaches utilized for indexing/retrieving, but have their drawbacks when applied to systems that aim to mimic the human capabilities. Such systems, also known as Cognitive Systems, are still limited in terms of processing different sources of information (especially when structured in different ways) for decision making purposes. This issue becomes significantly greater when past information is retrieved and taken in account. We address this issue by proposing a Structuralized Context-Aware Indexing and Retrieval using Set of Experience Knowledge Structure (SOEKS) and Decisional DNA (DDNA). SOEKS and DDNA allow the creation of a multi-modal space composed of information from different sources, such as contextual, visual, auditory etc., in a form of a structure and explicit experiential knowledge. SOKES is composed by fields that allow this experiences to participate in the processes of similarity, uncertainty, impreciseness, or incompleteness measures and facilitate the indexing and retrieval of knowledge in Cognitive Systems.

Autorzy

• Caterine De Silva Oliveira,
• Cesar Sanin,
• prof. dr hab. inż. Edward Szczerbicki link otwiera się w nowej karcie