"Automated" Archaeology: A Useless Endeavor, an Impossible Dream, or Reality?

"Automated" Archaeology: A Useless Endeavor, an Impossible Dream, or Reality?

Juan A. Barceló (Universitat Autònoma de Barcelona, Spain)
Copyright: © 2009 |Pages: 31
DOI: 10.4018/978-1-59904-489-7.ch001
OnDemand PDF Download:
$37.50

Abstract

The task of this automated archaeologist will be to assign to any artifact, represented by some features, visual or not, some meaning or explanatory concept. In other words, the performance of such an automated archaeologist is a three-stage process: Feature extraction, recognition, and explanation by which an input (description of the archaeological record) is transformed into an explanatory concept, in this case, the function of an archaeologically perceived entity (Figure 1). In order for the system to make a decision as to whether the object is a knife or a scraper, input information should be recognized, that is “categorized,” in such a way that once “activated” the selected categories will guide the selection of a response.
Chapter Preview
Top

Automata: The Awful Truth About Humans And Machines

Let us begin with a trivial example. Imagine a machine with artificial sensors, a brain, and some communication device. Suppose that such a machine is able to “see” prehistoric artifacts made of flint. The purpose of this automated archaeologist should be to “explain” the function of archaeological material. It decides consequently to measure, for instance, three properties: shape, texture, and size. The shape sensor will output a 1 if the prehistoric tool is approximately round and a –1 if it is more elliptical. The texture sensor will output a 1 if the surface of the artifact is smooth and a –1 if it is rough. The size sensor will output a 1 if the artifact is greater than 20 cm, and a –1 if it is less than 20 cm. The three sensor outputs will then be fed as input to the thinking core of the robot, whose purpose is to execute a function deciding which kind of tool has been discovered buried at this precise location. An input pattern is determined to belong to class Knife if there is a function, which relates incoming inputs with an already defined concept “knife,” or otherwise a “scraper.” As each observed element passes through the sensors, it can be represented by a three dimensional vector. The first element of the vector will represent shape, the second element will represent texture, and the third element will represent size.

Therefore, a prototype knife would be represented by

and a prototype scraper would be represented by

The task of this automated archaeologist will be to assign to any artifact, represented by some features, visual or not, some meaning or explanatory concept. In other words, the performance of such an automated archaeologist is a three-stage process: Feature extraction, recognition, and explanation by which an input (description of the archaeological record) is transformed into an explanatory concept, in this case, the function of an archaeologically perceived entity (Figure 1). In order for the system to make a decision as to whether the object is a knife or a scraper, input information should be recognized, that is “categorized,” in such a way that once “activated” the selected categories will guide the selection of a response.

Figure 1.

The performance of an automated archaeologist as a three-stage process

Let us move to a more interesting example. Imagine a specialized mobile robot equipped with video cameras, 3D scanners, remote sensors, excavator arms, suction heads and tubes, manipulation hands for taking samples exploring in the search of evidence for archaeological sites, excavating the site by itself, describing the discovered evidence, and analyzing samples and materials (Barceló, 2007). Or even better, imagine a team of robots doing different kinds of archaeological tasks, those tasks that, up to now, have been a matter of human performance. The idea is to develop an exploration system that allows a robot to explore and extract relevant features from the world around it, expressing them in some specific way. This unit should use visual and non-visual information to make decisions about how to find archaeological evidence. This specialized robot will use stereoscopic CCD cameras, laser rangers, sonar, infrared sensors, georadar, magnetometers, and construct a multidimensional representation of geometric space. From this representation, it will recognize locations, plan trajectories, and distinguish objects by shape, color, and location. The robot should acquire a sense of general spatial awareness, and to be able to do it, it probably needs an especially fine representation of the volume around it to precisely locate archaeological objects and structures and visually monitor performance. In other words, the first member of our team has to learn how to find an archaeological site, based on the perceived properties of the observed archaeological elements.

Complete Chapter List

Search this Book:
Reset
Table of Contents
Foreword
Jean-Claude Gardin
Acknowledgment
Chapter 1
Juan A. Barceló
The task of this automated archaeologist will be to assign to any artifact, represented by some features, visual or not, some meaning or explanatory... Sample PDF
"Automated" Archaeology: A Useless Endeavor, an Impossible Dream, or Reality?
$37.50
Chapter 2
Juan A. Barceló
When a specific goal is blocked, we have a problem. When we know ways round the block or how to remove it, we have less a problem. In our case, the... Sample PDF
Problem Solving in the Brain and by the Machine
$37.50
Chapter 3
Juan A. Barceló
Inverse problems are among the most challenging in computational and applied science and have been studied extensively (Bunge, 2006; Hensel, 1991;... Sample PDF
Computer Systems that Learn
$37.50
Chapter 4
Juan A. Barceló
Let’s build an automated archaeologist! It is not an easy task. We need a highly complex, nonlinear, and parallel information-processing “cognitive... Sample PDF
An Introduction to Neurocomputing
$37.50
Chapter 5
Juan A. Barceló
As we have discussed in previous chapters, an artificial neural network is an information-processing system that maps a descriptive feature vector... Sample PDF
Visual and Non-Visual Analysis in Archaeology
$37.50
Chapter 6
Juan A. Barceló
In order to be able to acquire visual information, our automated “observer” is equipped with range and intensity sensors. The former acquire range... Sample PDF
Shape Analysis in Archaeology
$37.50
Chapter 7
Juan A. Barceló
In this section, we will consider archaeological textures as the archaeological element’s surface attributes having either tactile or visual... Sample PDF
Texture and Compositional Analysis in Archaeology
$37.50
Chapter 8
Spatiotemporal Analysis  (pages 256-296)
Juan A. Barceló
As we have suggested many times throughout the book, the general form of an archaeological problem seems to be “why an archaeological site is the... Sample PDF
Spatiotemporal Analysis
$37.50
Chapter 9
Juan A. Barceló
It is obvious that answering the first question is a condition to solve the second. In the same way as human archaeologists, the automated... Sample PDF
An Automated Approach to Historical and Social Explanation
$37.50
Chapter 10
Juan A. Barceló
We have already argued that an automated archaeologist cannot understand past social actions by enumerating every possible outcome of every possible... Sample PDF
Beyond Science Fiction Tales
$37.50
About the Author