Incorporating situationally qualified human observations into a fusion process for intelligence analysis

Since my second year at UB my research assistantship has been funded by a 3 year multi-university research initiative (MURI) grant focused on network based hard/soft information fusion.  The first year of this research (for me at least) was focused on learning about how accurate people are at observing different phenomena in the world given specific contextual factors.  For example, how accurately can people judge distances?  What if it’s nighttime?  What if it’s snowing? etc.

This work was developed to allow human observations to be appropriately characterized in terms of their error/bias so that they could be integrated into a data fusion process along with hard data (which comes from things like radar sensors that are highly calibrated).  The poster below, which was created for a UB School of Engineering and Applied Sciences poster competition, describes the results of these research efforts at a high level.

Procrastinate

I have found myself lacking motivation to focus on my academics lately.  I attribute this to a sense of (temporary) closure to many arcs of my research work.  For example, my joint research on qualifying human observation accuracy was recently presented at the CogSIMA conference in Miami Beach.  So rather than get back into work that was started a while back (or work on my dissertation proposal which still needs a defined topic) I decided to create the “Son of Grumm” paper toy seen above.  Ironically he is standing on a paper that I should probably have been reading instead.

I got the template for the model from an amazing book I picked up at Urban Outfitters on sale.  Grumm isn’t the first model I’ve created, but he’s my favorite so far, especially because he didn’t have any curved cuts.  I find that putting together these models is quite enjoyable; it’s a nice combination of relaxing + rewarding (when you’re done).  My next step is to assemble the Howl’s Moving Caster model; however, I’m also reading up on creating my own models using pepakura designer freeware.  I’ll need to come up with a good idea for what to design first though.   I also think that from a usability/human factors standpoint, if I can get this software to work out well it could become a useful tool for rapid prototyping of 3D objects.   Excelsior!

Back to reading the paper for now though – Son of Grumm has taken his spot guarding my trackball.

Eureka! Human Factors made clear.

I’m a Human Factors specialist (a.k.a. cognitive engineer, usability designer, information architect, etc.) by trade.  Unfortunately for me though, despite the growing prevalence of  human factors I still have one major problem with the field.  Every time I tell someone “I’m  a human factors engineer” or “I’m getting my Ph.D. in human factors engineering” I am faced with a momentary stare while the person escapes into rapid activation of their neural network starting from somewhere around genetics.  This momentary look, usually accompanied by a smile or nod, is then followed by the question “What does that mean?” (or the dismissing “oh, sounds interesting”).

Well, no more I declare!  Thanks to the 2010 Inter-University Workshop I have a 5 second, visual way to quickly explain Human Factors (I hope).  I shall grab a napkin, an arm, or even a dollar from my wallet and quickly draw two circles and explain that one is a job or task that a human will need to perform (ex., using a website, playing a game, driving a car, etc.).  The other represents human capabilities- how fast can we run? how much can we lift? how much information can we handle at once?  What if we’re under stress or time pressure? etc..  And then in a moment of pure enlightenment… I say “and Human Factors is the science of understanding human capabilities and designing jobs/tasks to ensure that they do not exceed human limitations.”

Alright, i’m still working on the last quote, but I really think the diagram helps.  It’s better than nothing.