Dislocation detection in field environments: A belief functions contribution

Abstract

Dislocation is defined as the change between discrete sequential locations of critical items in field environments such as large construction projects. Dislocations on large sites of materials and critical items for which discrete time position estimates are available represent critical state changes. The ability to detect dislocations automatically for tens of thousands of items can ultimately improve project performance significantly. Detecting these dislocations in a noisy information environment where low cost radio frequency identification tags are attached to each piece of material, and the material is moved sometimes only a few meters, is the main focus of this study. We propose in this paper a method developed in the frame of belief functions to detect dislocations. The belief function framework is well-suited for such a problem where both uncertainty and imprecision are inherent to the problem. We also show how to deal with the calculations. This method has been implemented in a controlled experimental setting. The results of these experiments show the ability of the proposed method to detect materials dislocation over the site reliably. Broader application of this approach to both animate and inanimate objects is possible.

Introduction

Material tracking is a key performance element in many field environments such as construction. For example, the unavailability of construction materials at the right place and at the right time has been recognized as having a major negative impact on construction productivity. Moreover, poor site materials management potentially delays construction activities, thus threatens project completion dates and raises total installed costs (Grau & Caldas, 2007). While automated controls are often established for engineered and other critical materials during the design and procurement stages of large industrial projects, on-site control practices are still typically based on necessarily fallible direct human observation, manual data entry, and adherence to processes. These are inadequate for overcoming the dynamic and unpredictable nature of construction sites. Node location approaches using signal strength and based on triangulation or relaxation algorithms (Bulusu et al., 2000, Boyd and Vandenberghe, 2004, Doherty and Ghaoui, 2001) are limited because of the cost of required node electronics and their site mobilisation (no current high volume demand exists), and because the anisotropic, dynamic transmission space on a construction site, for example, cannot feasibly be mapped at the temporal or spatial resolution required. In addition, even sophisticated and expensive solutions experience multipath, dead space, and environmentally-related interference to some extent. For example, the Wi-Fi RTLS (real time location systems), such as commercial solutions from AeroScout^©, Ubisense^©, Ekahau^©, and the PanGo^© Network, require extensive and periodic calibration to map the Wi-Fi signals to locations throughout a building site while the existence of 802.11 access points is not guaranteed for any facility being built. Thus we have selected a more cost-effective approach that is applicable to field environment specifications.

However, developing a method for location estimation that is robust to measurement noise but still has a reasonable implementation cost is a challenge. Wireless sensor network-based data collection technologies that leverage the complementary strengths of GPS (high accuracy but high cost) and radio frequency identification (RFID – low cost but low accuracy) are being developed for a wide spectrum of applications. Specifically, more recent research is demonstrating that, coupled with mobile computers, data collection technologies and sensors can provide a cost-effective, scalable, and easy-to-implement materials location sensing system in real world construction sites (Akinci et al., 2002, Caldas et al., 2006, Grau and Caldas, 2007, Jaselskis and El-Misalami, 2003, Kini, 1999, Peyret and Tasky, 2002, Razavi et al., 2008, Sacks et al., 2003, Song et al., 2006, Song et al., 2007, Tommelein, 1998, Vorster and Lucko, 2002). The evident drawback of the current cost-effective and scalable systems is lack of accuracy, precision, and robustness.

The study presented here is an improved formulation for robustly processing uncertainty and imprecision in proximity methods. By proximity we mean a binary spatial-constraint-based method. Hence, it is naturally developed within the belief function (BF) framework and the approach presented here gracefully manages the issue of dislocated tags i.e. of material moving. We therefore make the assumption that estimates of materials’positions are available through a known and given process and we focus our attention on dislocation. During this work we used the software developed by Indentec^©. The BF are used to manage the uncertainty and the imprecision on the estimates provided by the software.

This paper is organized into the following sections. A brief introduction provides background to occupancy cell framework and proximity localization methods. Then, a practical elaboration on formulating belief function theory for detecting dislocated items is presented. A brief description of the field experiment and the acquired data set follows. The results indicating the potential of the belief function theory to detect materials dislocation make up the next section. Finally, the conclusion summarizes the findings of this research study, and suggests additional further works.