Human-centric intelligent systems for exploration and knowledge discovery

I C Parmee

doi:10.1039/b307211h

Abstract

This speculative article discusses research and development relating to computational intelligence (CI) technologies comprising powerful machine-based search and exploration techniques that can generate, extract, process and present high-quality information from complex, poorly understood biotechnology domains. The integration and capture of user experiential knowledge within such CI systems in order to support and stimulate knowledge discovery and increase scientific and technological understanding is of particular interest. The manner in which appropriate user interaction can overcome problems relating to poor problem representation within systems utilising evolutionary computation (EC), machine-learning and software agent technologies is investigated. The objective is the development of user-centric intelligent systems that support an improving knowledge-base founded upon gradual problem re-definition and reformulation. Such an approach can overcome initial lack of understanding and associated uncertainty.

Highlights

Uncertainty and poor problem definition are inherent features during early stages of many problem-solving processes
The above could be considered a general description of how we progress when faced with problems that initially seem beyond our perceived analytic capabilities. Using this description the following sections explore the humancentric utilisation of evolutionary computation, machine learning and agent-based approaches integrated with enabling computational technologies to significantly enhance this iterative, knowledge discovery and representation development process
Problems specific to the biotechnology field will necessitate appropriate development of any working system based upon these concepts

Summary

Introduction

Uncertainty and poor problem definition are inherent features during early stages of many problem-solving processes. Problem representation in the first instance may be merely based upon qualitative mental models arising from experiential knowledge, group discussion and slight empiric investigation. Such representations, coupled with user intuition, play a significant role in the identification of future direction and further investigation. Due to the number of possible combinations across multiple reagent libraries some form of computational search and exploration capability is essential to identify potential high performance solutions for further evaluation by the chemist.[1] a machine/human procedure could ensure that experimental effort is concentrated upon ‘best’ candidates thereby significantly reducing design lead time. The analysis of data sets from gene expression experiments to provide insights into gene activity under differing environmental conditions and the identification of gene regulatory networks is another area currently receiving attention.[2]

Problem redefinition and reformulation

Search and exploration in complex space

Problem reformulation

Existing appropriate CI and enabling technologies

The virtual laboratory

Conclusions