자연주의적 탐구조사(Naturalistic Inquiry)

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

1. Introduction and Overview. 2. Detecting Influential Observations and Outliers. 3. Detecting and Assessing Collinearity. 4. Applications and Remedies. 5. Research Issues and Directions for Extensions. Bibliography. Author Index. Subject Index.

Regression Diagnostics: Identifying Influential Data and Sources of Collinearity

Social Network Analysis

What makes organizations so similar? We contend that the engine of rationalization and bureaucratization has moved from the competitive marketplace to the state and the professions. Once a set of organizations emerges as a field, a paradox arises: rational actors make their organizations increasingly similar as they try to change them. We describe three isomorphic processes-coercive, mimetic, and normative—leading to this outcome. We then specify hypotheses about the impact of resource centralization and dependency, goal ambiguity and technical uncertainty, and professionalization and structuration on isomorphic change. Finally, we suggest implications for theories of organizations and social change.

The iron cage revisited: Institutional isomorphism and collective rationality in organizational fields (Chinese Translation)

This paper significantly improves on, and finishes to validate, the approach proposed in "Application of Machine Learning to Construction Injury Prediction" (Tixier et al. 2016 [1]). Like in the original study, we use NLP to extract fundamental attributes from raw incident reports and machine learning models are trained to predict safety outcomes (here, these outcomes are injury severity, injury type, bodypart impacted, and incident type). However, in this study, safety outcomes were not extracted via NLP but are independent (human annotations), eliminating any potential source of artificial correlation between predictors and predictands. Results show that attributes are still highly predictive, confirming the validity of the original study. Other improvements brought by the current study include the use of (1) a much larger dataset, (2) two new models (XGBoost andlinear SVM), (3) model stacking, (4) a more straight forward experimental setup with more appropriate performance metrics, and (5) an analysis of per-category attribute importance scores. Finally, the injury severity outcome is well predicted, which was not the case in the original study. This is a significant advancement.

AI Predicts Independent Construction Safety Outcomes from Universal Attributes.

Exploring the Association among Dimensions of Safety Climate and Learning Organization Climate

Impact of Worker Fatigue on Hazard Recognition Skills

www.asse.org OCTOBER 2010 PROFESSIONAL SAFETY 31 THE CONSTRUCTION INDUSTRY accounts for a disproportionate injury rate. According to Bureau of Labor Statistics (BLS), the construction industry consistently employs approximately 5% of theAmerican workforce but accounts for approximately 12% of all occupational fatalities. These occupational injuries have a significant impact on the economy. In 2004, the industry was responsible for 460,000 disabling injuries resulting in a total estimated cost of $15.64 billion (NSC, 2006). Within the construction industry, the highway sector accounts for the highest injury and illness rate (BLS, 2007). When compared to workers on all other types of construction sites, workers on road construction sites were foundmore likely to be killed by vehicles and heavy equipment (BLS, 2007; CPWR, 2008). The estimated direct costs of highway construction zone accidents were as high as $6.2 billion per year between 1995 and 1997with an average cost of $3,687 per accident (Mohan & Gautam, 2002). As highway agencies continue to repairAmerica’s progressively failing transportation infrastructure, roadways must be renewed quickly with minimum disruption to the community. Suchwork requires the use of specific strategies such as nighttimework, continuous work, extended shifts, modularization and others aimed to compress schedules. Based on the observations made by previous researchers, these emerging construction trends are likely to result in an increase in injuries and illnesses. Highway agencies and private contractors use many methods to protect highway work zones, including cones, signage, semipermanent concrete barriers and vehicular barriers created by enclosing the work zone with idle equipment (i.e., ring of steel). This study investigates the benefits and limitations of a newmethod of protecting highwaywork zones: mobile barrier systems. Specifically, this article presents the findings from an in-depth analysis of the MBT-1, a mobile barrier system with unique features targeted at injury prevention, and provides a comparison of this system with existing strategies. The study pays specific attention to lighting schemes associated with the MBT-1 as the lighting-related benefits are the most ambiguous. Causes of Highway Work Zone Injuries Several studies have focused on the causes of highway construction and maintenance injuries. According toNIOSH (2001), nighttimework, contact with heavy equipment and being struck by passing vehicles are the leading root causes of fatalities. Other literature reports that highway workers are also at risk of injury or death from contact with overhead power lines, falls frommachinery or structures, gas line explosions, or being struck by falling objects or materials (Bryden &Andrew 1999).

Matthew R. Hallowell

Papers

AI Predicts Independent Construction Safety Outcomes from Universal Attributes.

Exploring the Association among Dimensions of Safety Climate and Learning Organization Climate

Impact of Worker Fatigue on Hazard Recognition Skills

Mobile Barrier Trailer: Analysis of an Emerging Work Zone Protection System

Incident Investigations and Learning: Methods, Barriers, and Opportunities