Search results

Automated technologies have been applied to facility management (FM) practices to address labour demands of, and time consumed by, inputting and processing manual data. Less attention has been focussed on automation of visual information, such as images, when improving timely maintenance decisions. This study aims to develop image classification algorithms to improve information flow in the inspection-repair process through building information modelling (BIM).

To improve and automate the inspection-repair process, image classification algorithms were used to connect images with a corresponding image database in a BIM knowledge repository. Quick response (QR) code decoding and Bag of Words were chosen to classify images in the system. Graphical user interfaces (GUIs) were developed to facilitate activity collaboration and communication. A pilot case study in an inspection-repair process was applied to demonstrate the applications of this system.

The system developed in this study associates the inspection-repair process with a digital three-dimensional (3D) model, GUIs, a BIM knowledge repository and image classification algorithms. By implementing the proposed application in a case study, the authors found that improvement of the inspection-repair process and automated image classification with a BIM knowledge repository (such as the one developed in this study) can enhance FM practices by increasing productivity and reducing time and costs associated with ecision-making.

This study introduces an innovative approach that applies image classification and leverages a BIM knowledge repository to enhance the inspection-repair process in FM practice. The system designed provides automated image-classifying data from a smart phone, eliminates time required to input image data manually and improves communication and collaboration between FM personnel for maintenance in the decision-making process.

The purpose of this paper is to measure a single financial institution's contribution to systemic risk by using extremal quantile regression and analyzing the influential factors of systemic risk.

Extreme value theory is applied when measuring the systemic risk of financial institutions. Extremal quantile regression, where extreme value distribution is assumed for the tail, is used to measure the extreme risk and analyze the changes in and dependencies of risk. Furthermore, influential factors of systemic risk are analyzed using panel regression.

The key findings of the paper are that value at risk and contribution to systemic risk are very different when measuring the risk of a financial institution; banks’ contributions to systemic risk are much higher; and size and leverage ratio are two significant and important factors influencing an institution's systemic risk.

Characterizing variables of financial institutions such as size, leverage ratio and market beta should be considered together when regulating and constraining financial institutions.

To take extreme risk into account, this paper measures systemic financial risk using extremal quantile regression for the first time.

This study aims to investigate the spectral illumination characteristics and geometric features of bicycle parts and proposes an image stitching method for their automatic visual inspection.

The unrealistic color casts of feature inspection is removed using white balance for global adjustment. The scale-invariant feature transforms (SIFT) is used to extract and detect the image features of image stitching. The Hough transform is used to detect the parameters of a circle for roundness of bicycle parts.

Results showed that maximum errors of 0°, 10°, 20°, 30°, 40° and 50° for the spectral illumination of white light light-emitting diode arrays with differential shift displacements are 4.4, 4.2, 7.8, 6.8, 8.1 and 3.5 per cent, respectively. The deviation error of image stitching for the stem accessory in x and y coordinates are 2 pixels. The SIFT and RANSAC enable to transform the stem image into local feature coordinates that are invariant to the illumination change.

This study can be applied to many fields of modern industrial manufacturing and provide useful information for automatic inspection and image stitching.