An Approach for the Automatic Classification of Work Descriptions in Construction Projects

Self Cite

Construction project management produces a huge amount of documents in a variety of formats. The efficient use of the data contained in these documents is crucial to enhance control and to improve performance. A central pillar throughout the project life cycle is the Bill of Quantities (BoQ) document. It provides economic information and details a collection of work descriptions describing the nature of the different works needed to be done to achieve the project goal. In this work, we focus on the problem of automatically classifying such work descriptions into a predefined task organization hierarchy, so that it can be possible to store them in a common data repository. We describe a methodology for preprocessing the text associated to work descriptions to build training and test data sets and carry out a complete experimentation with several well-known machine learning algorithms.

Section: Introductionmentioning

confidence: 91%

Section: Introductionmentioning

confidence: 99%

Using Classification Techniques for Assigning Work Descriptions to Task Groups on the Basis of Construction Vocabulary

Martínez-Rojas

Soto-Hidalgo

Marín

et al. 2018

Self Cite

“…The adopted decision will have to account for some general criteria of internal validity, affordability, and feasibility, by considering the available or obtainable resources, as well as internal and external, current, and future conditions (Martínez‐Rojas et al., ). Decision‐making problems framed within this context can be characterized by a multiplicity of significant aspects and by the presence of several goals and constraints, often not explicit or even conflicting.…”

Section: Multicriteria Analysis In Disaster Managementmentioning

confidence: 99%

Multicriteria Fuzzy Analysis for a GIS‐Based Management of Earthquake Scenarios

D’Urso

Masi

Zuccaro

et al. 2017

Objective of this article is the formulation and the implementation of a decision-making model for the optimal management of emergencies. It is based on the accurate definition of possible scenarios resulting from prediction and prevention strategies and explicitly takes into account the subjectivity of the judgments of preference. To this end, a multicriteria decision model, based on fuzzy logic, has been implemented in a user-friendly geographical information system (GIS) platform so as to allow for the automation of choice processes between several alternatives for the spatial location of the investigated scenarios. In particular, we have analyzed the potentialities of the proposed approach in terms of seismic risk reduction, simplifying the decision process leading to the actions to be taken from directors and managers of coordination services. Due to the large number of variables involved in the decision process, it has been proposed a particularly flexible and streamlined method in which the damage scenarios, based on the vulnerability of the territory, have represented the input data to derive a vector of weights to be assigned to different decision alternatives. As an application of the proposed approach, the seismic damage scenario of a region of 400 km 2 , hit by the 2009 earthquake in L'Aquila (Italy), has been analyzed. C 2017 Computer-Aided Civil and Infrastructure Engineering.

“…The development of algorithms for machine learning has become a very active research topic in civil engineering and SHM recently (Rafiei and Adeli, , ; Lin et al., ; Cha et al., ; Zhang et al., ; Martinez‐Rojas et al., ; Chou and Pham, ). However, most of these methods lack the ability to reason about modeling uncertainty.…”

Section: Introductionmentioning

confidence: 99%

Multitask Sparse Bayesian Learning with Applications in Structural Health Monitoring

Huang

Beck

2018

We focus on a Bayesian approach to learn sparse models by simultaneously utilizing multiple groups of measurements that are marked by a similar sparseness profile. Joint learning of sparse representations for multiple models has been mostly overlooked, although it is a useful tool for exploiting data redundancy by modeling informative relationships within groups of measurements. To this end, two hierarchical Bayesian models are introduced and associated algorithms are proposed for multitask sparse Bayesian learning (SBL). It is shown that the data correlations for different tasks are taken into account more effectively by using the hierarchical model with a common prediction‐error precision parameter across all related tasks, which leads to a better learning performance. Numerical experiments verify that exploiting common information among multiple related tasks leads to better performance, for both models that are highly and approximately sparse. Then, we examine two applications of multitask SBL in structural health monitoring: identifying structural stiffness losses and recovering missing data occurring during wireless transmission, which exploit information about relationships in the temporal and spatial domains, respectively. These illustrative examples demonstrate the potential of multitask SBL for solving a wide range of sparse approximation problems in science and technology.