BDD-based Error Metric Analysis, Computation and Optimization

BACKGROUND Promoting safety and health awareness and mitigating risks are of paramount importance to companies in high-risk industries. Yet, there are very few studies that have synthesized findings from existing online workplace safety and health literature to identify what are the key factors that are related to (a) safety awareness, (b) safety risks, (c) health awareness, and (d) health risks. OBJECTIVE As one of the first systematic reviews in the area of workplace health and safety, this study aims to identify the factors related to safety and health awareness as well as risks, and systematically map these factors within three levels: organizational, cultural, and individual level. Also, this review aims to assess the impact of these workplace safety and health publications in both academic (e.g., academic databases, Mendeley, and PlumX) and non-academic settings (e.g., social media platform). METHODS The systematic review was conducted in line with procedures recommended by Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA). First, Proquest, ScienceDirect and Scopus were identified as suitable databases for the systematic review. Second, after inputting search queries related to safety and health awareness and risks, the articles were evaluated based on a set of inclusion and exclusion criteria. Third, the factors identified in the included articles were coded systematically. Fourth, the research team assessed the impact of the articles through a combination of traditional and new metric analysis methods: citation count, Altmetric Attention Score, Mendeley readers count, usage count, and capture count. RESULTS Out of a total of 4,831 articles retrieved from the three databases, 51 articles were included in the final sample and were systematically coded. The results revealed six categories of organizational (management commitment, management support, organizational safety communication, safety management systems, physical work environment, and organizational environment), two cultural (interpersonal support and organizational culture), and four individual (perception, motivation, attitude and behavior) level factors that relate to safety and health awareness and risk. In terms of impact, the relationship between citation count and the various metrics measuring academic activity (e.g., Mendeley readers, usage count, and capture count) were mostly significant while the relationship between citation count and Altmetric Attention Score was non-significant. CONCLUSIONS This study provides a macro view of the current state of workplace safety and health research and gives scholars an indication on some of the key factors of safety and health awareness and risks. Researchers should also be cognizant that while their work may receive attention from the scholarly community, it is important to tailor their communication messages for the respective industries they are studying to maximize the receptivity and impact of their findings. CLINICALTRIAL N.A.

Download Full-text

A Weighted Mean Absolute Error Metric for Image Quality Assessment

2020 IEEE International Conference on Visual Communications and Image Processing (VCIP) ◽

10.1109/vcip49819.2020.9301889 ◽

2020 ◽

Author(s):

Sihan Hao ◽

Sumei Li

Keyword(s):

Image Quality ◽

Quality Assessment ◽

Image Quality Assessment ◽

Mean Absolute Error ◽

Absolute Error ◽

Weighted Mean ◽

Error Metric

Download Full-text

An Error-Adaptive, Non-Rigid Registration Method for the Analysis of Springback in Sheet Metal Forming

Key Engineering Materials ◽

10.4028/www.scientific.net/kem.651-653.1015 ◽

2015 ◽

Vol 651-653 ◽

pp. 1015-1020 ◽

Cited By ~ 1

Author(s):

Matthias Schweinoch ◽

Alexei Sacharow ◽

Dirk Biermann ◽

Christoph Buchheim

Keyword(s):

Sheet Metal ◽

Sheet Metal Forming ◽

Metal Forming ◽

Simulation Software ◽

Registration Method ◽

Rigid Registration ◽

Reference Shape ◽

Geometric Deviations ◽

Error Metric ◽

Test Shape

Springback effects, as occuring in sheet metal forming processes, pose a challenge to manufacturingplanning: the as-built part may deviate from the desired shape rendering it unusable forits intended purpose. A compensation can be achieved by modifying the forming tools to counteractthe shape deviations. A prerequisite to compensation is the knowledge of correspondences (ui; vj),between points ui on the desired and vj on the actual shape. FEM-based simulation software providesmeans to both virtually predict springback and directly obtain correspondences. In case of experimentalprototyping and validation, however, finding correspondences requires solving a registrationproblem: given a test shape Q (scan points of the as-built geometry) and a reference shape R (CADdata of the desired geometry), a transformation S has to be found to fit both objects. Correspondencesbetween S(Q) and R may then be computed based on a metric.If S is restricted to Euclidean transformations, then S(Q) results in a rigid transformation, whereevery point of Q is subject to the same translation and rotation. Local geometric deviations due tospringback are not considered, often resulting in invalid correspondences. In this contribution, a nonrigidregistration method for the efficient analysis of springback is therefore presented. The test shape Q is iteratively partitioned into segments with respect to an error metric. The segments are locally registeredusing rigid registration subject to regulatory conditions. Resulting discontinuities are addressedby minimization of the deformation energy. The error metric uses information about the deviationscomputed based on the correspondences of the previous iteration, e.g. maximum errors or changes ofthe sign. This adaptive per-segment registration allows appropriate correspondences to be determinedeven under local geometric deviations.

Download Full-text

JPEG Quality Transcoding Using Neural Networks Trained with a Perceptual Error Measure

Neural Computation ◽

10.1162/089976699300016917 ◽

1999 ◽

Vol 11 (1) ◽

pp. 267-296 ◽

Cited By ~ 7

Author(s):

John Lazzaro ◽

John Wawrzynek

Keyword(s):

Prototype System ◽

Training Procedure ◽

Human Visual Perception ◽

Error Measure ◽

Jpeg Image ◽

Perceptual Error ◽

Image File ◽

Visual Artifacts ◽

Error Metric ◽

Coded Images

A JPEG Quality Transcoder (JQT) converts a JPEG image file that was encoded with low image quality to a larger JPEG image file with reduced visual artifacts, without access to the original uncompressed image. In this article, we describe technology for JQT design that takes a pattern recognition approach to the problem, using a database of images to train statistical models of the artifacts introduced through JPEG compression. In the training procedure for these models, we use a model of human visual perception as an error measure. Our current prototype system removes 32.2% of the artifacts introduced by moderate compression, as measured on an independent test database of linearly coded images using a perceptual error metric. This improvement results in an average PSNR reduction of 0.634 dB.

Download Full-text

Shape watermarking based on minimizing the quadric error metric

2009 IEEE International Conference on Shape Modeling and Applications ◽

10.1109/smi.2009.5170170 ◽

2009 ◽

Cited By ~ 7

Author(s):

Ming Luo ◽

Adrian G. Bors

Keyword(s):

Error Metric ◽

Quadric Error Metric

Download Full-text

Metric Analysis

Applied Deep Learning ◽

10.1007/978-1-4842-3790-8_6 ◽

2018 ◽

pp. 217-270

Author(s):

Umberto Michelucci

Keyword(s):

Metric Analysis

Download Full-text

MESH COMPARISON USING ATTRIBUTE DEVIATION METRIC

International Journal of Image and Graphics ◽

10.1142/s0219467804001324 ◽

2004 ◽

Vol 04 (01) ◽

pp. 127-140 ◽

Cited By ~ 26

Author(s):

MICHAËL ROY ◽

SEBTI FOUFOU ◽

FRÉDÉRIC TRUCHETET

Keyword(s):

Comparison Method ◽

Error Metric ◽

Color Texture

We propose a mesh comparison method using a new attribute deviation metric. The considered meshes contain geometrical and appearance attributes (material color, texture, temperature, etc.). The proposed deviation metric computes local differences between the attributes of two meshes. A mesh comparison assessment can be done easily and quickly using this metric. The techniques proposed are applicable in a number of ways, e.g. 3D matching and registration, and the example described in the paper is the simplification of a surface by iteratively reducing its complexity according to an error metric. The results are presented showing the success of the algorithm through comparisons with other measures and with three different simplification algorithms.

Download Full-text