Search

The paper is concerned with the development and comparison of alternative machine learning methods of determining the type of truck crossing a bridge from the dynamic response it induces within the bridge structure, the so-called weigh-in-motion problem. Weigh-in-motion is a rich engineering problem presenting many challenges for current machine learning technologies, and for this reason is proposed as a benchmark for guiding and assessing advances in the application of this field of artificial intelligence. A review is first provided of existing methods of determining truck types and loading attributes using both machine learning and heuristic search techniques. The most promising approach to date, that of artificial neural networks, is then compared to support vector machines in a comprehensive study considering a range of configurations of both modeling techniques. A local scatter point smoothing schema is adopted as a means of selecting an optimal set of design parameters for each model type. Three main model formats are considered: (i) a monolithic model structure with a one-versus-all truck type classification strategy; (ii) an array of sub-models each dedicated to one truck type with a one-versus-all classification strategy; and (iii) an array of sub-models each dedicated to selecting between pairs of trucks in a one-versus-one classification strategy. Overall, the formats that used an array of sub-models performed best at truck classification, with the support vector machines having a slight edge over the artificial neural networks. The paper concludes with some suggestions for extending the work to a broader scope of problems. [ABSTRACT FROM AUTHOR]

The paper provides a review of empirical modeling and its application within construction engineering and management. The scope of application and trends in use of this approach are first assessed, and the potential for its further development is identified. This is followed by an examination of the key components of empirical modeling, namely: the structure and operation of the model and the scheme used in its development. The paper then provides a rigorous methodology that must be followed to ensure the validity and value of the end model, covering the steps: strategizing; data collation and assessment; model development; model evaluation and final selection; final validation; and implementation. The methodology is designed to cater for all forms of empirical modeling including the procedurally more demanding development algorithms that have become available in recent years, such as simulated evolution. Overall, the paper is designed to provide researchers embarking on an empirical modeling study with an overview of when it is appropriate to use this approach, what type of system to adopt, and how to ensure development of a successful end product. CE Database subject headings: Empirical equations; Dynamic models; Algorithms; Data collection; Data analysis; Validation; Construction management. Author keywords: Empirical modeling; Structured model; Static model; Dynamic model; Development algorithm; Data collection; Data analysis; Model validation. DOI: 10.1061/(ASCE)CO.1943-7862.0000138

The note reports on recent developments to the coarse-grain method (CGM) of modeling transient heat flow in buildings. CGM was originally developed as an alternative to conventional fine-grain modeling techniques [such as the finite-difference method (FDM) and finite-element method (FEM)] to increase simulation speed to a degree that facilitates three-dimensional modeling, and to ease the tasks of model development and experimentation. Earlier work has shown that CGM can provide reasonably accurate simulations at a processing speed several orders of magnitude faster than FDM or FEM. This note describes and demonstrates refinements to the CGM approach that increase its modeling accuracy to a level comparable to FEM, while doubling its processing speed. These refinements are: (1) the use of a hybrid linear regression model with an artificial neural network (ANN) to represent each coarse-grain modeling element (the hybridization of the ANN effectively halves its complexity); and (2) a linear calibration of the ANN-based coarse-grain modeling elements to account for an observed positive bias in their predictions. The improved approach is demonstrated for a two-dimensional model of a bay in a research building located at the University of Florida. The note concludes with some suggestions for continuing research. DOI: 10.1061/(ASCE)0887-3801(2007)21:5(379) CE Database subject headings: Neural networks; Energy consumption; Finite element method; Grains material; Heat flow.

This paper reports on the development of a new approach for simulating the thermal behavior of buildings that overcome the limitations of conventional heat-transfer simulation methods such as the finite difference method and the finite element method. The proposed technique uses a coarse-grain approach to model development whereby each element represents a complete building component such as a wall, internal space, or floor. The thermal behavior of each coarse-grain element is captured using empirical modeling techniques such as artificial neural networks (ANNs). The main advantages of the approach compared to conventional simulation methods are (1) simplified model construction for the end-user; (2) simplified model reconfiguration; (3) significantly faster simulation runs (orders of magnitude faster for two- and three-dimensional models); and (4) potentially more accurate results. The paper demonstrates the viability of the approach through a number of experiments with a model of a composite wall. The approach is shown to be able to sustain highly accurate long-term simulation runs, lf the coarse-grain modeling elements are implemented as ANNs. In contrast, an implementation of the coarse-grain elements using a linear model is shown to function inaccurately and erratically. The paper concludes with an identification of on-going work and future areas for development of the technique. CE Database subject headings: Simulation models; Neural networks; Energy consumption; Finite difference method; Thermal factors; Buildings, residential.

Heuristic construction knowledge generated while contracting is seldom recorded and transferred to other workers. Experiences of past mistakes as well as efficient work practices are crucial means for saving money, time, and improving the safety and quality of construction. With the rising costs of construction and the increased demand of time constraints on contractor schedules, few members of the construction industry can afford to waste time and resources on errors or ineffective work practices. The Constructability Lessons Learned Database (CLLD) prototype described in this paper is a leading edge method of automatically gathering, systematically organizing and efficiently applying vital construction information to a contractor's daily activities. This paper presents a review of previous and current attempts at database constructability programs, uses of constructability feedback systems, challenges to develop and utilize such systems, and an overview of the design and development of the CLLD prototype. The overview describes knowledge elicitation techniques used to gather constructability knowledge, the design of the system (organizing and classifying construction information for efficient retrieval and expansion), and system's implementation, validation, and operation. The conclusion discusses future extensions of the CLLD concept in the construction industry.

This is the first of two papers providing a discourse on the understanding, usage, and potential for application of artificial neural networks within civil engineering. The present paper develops an understanding of how these devices operate and explains the main issues concerning their use. A simple structural-analysis problem is solved using the most popular form of neural-networking system - a feedforward network trained using a supervised scheme. A graphical interpretation of the way in which neural networks operate is first presented. This is followed by discussions of the primary concepts and issues concerning their use, including factors affecting their ability to learn and generalize, the selection of an appropriate set of training patterns, theoretical limitations of alternative network configurations, and network validation. The second paper demonstrates the ways in which different types of civil engineering problems can be tackled using neural networks. The objective of the two papers is to ensure the successful development and application of this technology to civil engineering problems.

The first paper of this two-paper series developed an understanding of how artificial neural networks work and explained the primary issues involved in their use. This second paper demonstrates the versatility of neural networks as a problem-solving tool, and shows how they can be applied to different problems in civil engineering. Initially, the basic characteristics of neural networks and the variety of systems available are identified. The significance of these characteristics in terms of solving different classes of problems is considered. A range of different types of civil engineering problems is examined (in particular, vector mapping, dynamic-systems modeling, problems in which objectives vary with time, and optimization problems) and approaches to their solutions using different neural network paradigms are demonstrated.

Byline: Ian Flood This paper describes the Soft Boundary Frequency Assignment (SBFA) method employed by Ofcom in the 18 GHz frequency band where microwave fixed links systems are separated in frequency on the basis of the modulation scheme assumed for frequency assignment purposes. This approach aims to encourage the development of fixed links communities where inequalities between members are mitigated but without strict segmentation. Analysis of frequency assignment criteria identifies the hardest objective on the interference path for candidate transmitters in the mixed modulation environment and in the Soft Boundary environment. Possible refinements to the Soft Boundary method are investigated.

Byline: Ian Flood, David Bacon Due to an increasing demand for access to fixed links spectrum, Ofcom engineers have considered a number of ideas that would enable higher spectral utilisation in point-topoint link deployment through various adjustments to the present frequency-assignment method. It is expected that moving from a noise-limited towards an interference-limited assignment criteria results in the use of less spectrum for a specific deployment of links and simulated reassignment of links has quantified this. Some initial changes to the assignment criteria have been implemented and further changes are being considered. A radically new approach based on joint signal-level probability distributions is discussed.