• Safety and Health at Work
• /
• v.15 no.1
• /
• pp.59-65
• /
• 2024

Background: Different job strain formulations based on the Job Demand-Control model have been developed. This study evaluated longitudinal associations between job strain and psychological distress and whether associations were influenced by six formulations of job strain, including quadrant (original and simplified), subtraction, quotient, logarithm quotient, and quartile based on quotient, in randomly selected Japanese workers. Methods: Data were from waves I and II of the Survey of Midlife in Japan (MIDJA), with a 4-year followup period. The study sample consisted of 412 participants working at baseline and had complete data on variables of interest. Associations between job strain at baseline and psychological distress at follow-up were assessed via multivariable linear regression, and results were expressed as β coefficients and 95% confidence intervals including R² and Akaike information criterion (AIC) evaluation. Results: Crude models revealed that job strain formulations explained 6.93-10.30% of variance. The AIC ranged from 1475.87 to 1489.12. After accounting for sociodemographic and behavioral factors and psychological distress at baseline, fully-adjusted models indicated significant associations between all job strain formulations at baseline and psychological distress at follow-up: original quadrant (β: 1.16, 95% CI: 0.12, 2.21), simplified quadrant (β: 1.01, 95% CI: 0.18, 1.85), subtraction (β: 0.39, 95% CI: 0.09, 0.70), quotient (β: 0.37, 95% CI: 0.08, 0.67), logarithm quotient (β: 0.42, 95% CI: 0.12, 0.72), and quartile based on quotient (β: 1.22, 95% CI: 0.36, 2.08). Conclusion: Six job strain formulations showed robust predictive power regarding psychological distress over 4 years among Japanese workers.

• Journal of Food Hygiene and Safety
• /
• v.32 no.6
• /
• pp.507-512
• /
• 2017

There has been increasing concern regarding misuse of disinfectants and sanitizers such as ethanol, sodium hypochlorite, and hydrogen peroxide for food contact surfaces in the food industry. Examining the efficacy of the concentration of currently used disinfectants and sanitizers is urgently required in the Korean society. This study aimed to develop predictive reduction models for Escherichia coli and Staphylococcus aureus in suspension, as a function of $ClO_2$ (chlorine dioxide) and contact time using response surface methodology. E. coli ATCC 10536 and S. aureus ATCC 6538 (initial inoculum, 8-9 log CFU/mL) in tryptic soy broth were treated with different concentrations of $ClO_2$ (5, 20, and 35 ppm) for different contact times (1, 3, and 5 min) following a central composite design. The polynomial reduction models for $ClO_2$ on E. coli and S. aureus were developed under the clean condition. E. coli reduction by 35 ppm $ClO_2$ for 1, 3, and 5 min was 2.49, 2.70, and 3.65 log CFU/mL, respectively. Also, S. aureus reduction by 35 ppm $ClO_2$ for 1, 3, and 5 min was 4.59, 5.25, and 5.81 log CFU/mL, respectively. The predictive response polynomial models developed were $R=0.43231-0.056492^*X_1-0.097771^*X_2+9.24167E-003^*X_1^*X_2+3.06333E-003^*X_1{^2}$ ($R^2=0.98$) on E. coli and $R=1.10542-0.20896^*X_1-0.046062^*X_2+8.30000E-003^*X_1^*X_2+8.73300E-003^*X_1{^2}$ ($R^2=0.99$) on S. aureus, where R was the bacterial reduction (log CFU/mL), $X_1$ was the concentration and $X_2$ was the contact time. Our predictive reduction models should be validated in developing the optimal concentration and contact time of $ClO_2$ for inhibiting E. coli and S. aureus on food contact surfaces.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.3
• /
• pp.397-411
• /
• 2023

The number of deteriorated bridges with a service period of more than 30 years has been rapidly increasing in Korea. Accordingly, the importance of advanced maintenance technologies through the predictions of age-induced deterioration degree, condition, and performance of bridges is more and more noticed. The prediction method of the safety grade of bridges was proposed in this study using the classification models of the Decision Tree and the Random Forest based on machine learning. As a result of analyzing these models for the 8,850 bridges located in national roads with various evaluation indexes such as confusion matrix, balanced accuracy, recall, ROC curve, and AUC, the Random Forest largely showed better predictive performance than that of the Decision Tree. In particular, random under-sampling in the Random Forest showed higher predictive performance than that of other sampling techniques for the C and D grade bridges, with the recall of 83.4%, which need more attention to maintenance because of the significant deterioration degree. The proposed model can be usefully applied to rapidly identify the safety grade and to establish an efficient and economical maintenance plan of bridges that have not recently been inspected.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.2
• /
• pp.51-62
• /
• 2022

This study suggests a design of predictive modeling for a hospital fall risk based on inpatients' posture. Inpatient's profile, medical history, and body measurement data along with basic information about a bed they use, were used to predict a fall risk and suggest an algorithm to determine the level of risk. Fall risk prediction is largely divided into two parts: a real-time fall risk evaluation and a qualitative fall risk exposure assessment, which is mostly based on the inpatient's profile. The former is carried out by recognizing an inpatient's posture in bed and extracting rule-based information to measure fall risk while the latter is conducted by medical staff who examines an inpatient's health status related to hospital fall risk and assesses the level of risk exposure. The inpatient fall risk is determined using a sigmoid function with recognized inpatient posture information, body measurement data and qualitative risk assessment results combined. The procedure and prediction model suggested in this study is expected to significantly contribute to tailored services for inpatients and help ensure hospital fall prevention and inpatient safety.

• Geomechanics and Engineering
• /
• v.37 no.4
• /
• pp.307-321
• /
• 2024

This paper delves into the critical assessment of predicting sidewall displacement in underground caverns through the application of nine distinct machine learning techniques. The accurate prediction of sidewall displacement is essential for ensuring the structural safety and stability of underground caverns, which are prone to various geological challenges. The dataset utilized in this study comprises a total of 310 data points, each containing 13 relevant parameters extracted from 10 underground cavern projects located in Iran and other regions. To facilitate a comprehensive evaluation, the dataset is evenly divided into training and testing subset. The study employs a diverse array of machine learning models, including recurrent neural network, back-propagation neural network, K-nearest neighbors, normalized and ordinary radial basis function, support vector machine, weight estimation, feed-forward stepwise regression, and fuzzy inference system. These models are leveraged to develop predictive models that can accurately forecast sidewall displacement in underground caverns. The training phase involves utilizing 80% of the dataset (248 data points) to train the models, while the remaining 20% (62 data points) are used for testing and validation purposes. The findings of the study highlight the back-propagation neural network (BPNN) model as the most effective in providing accurate predictions. The BPNN model demonstrates a remarkably high correlation coefficient (R2 = 0.99) and a low error rate (RMSE = 4.27E-05), indicating its superior performance in predicting sidewall displacement in underground caverns. This research contributes valuable insights into the application of machine learning techniques for enhancing the safety and stability of underground structures.

• Journal of the Korean Geotechnical Society
• /
• v.40 no.2
• /
• pp.65-79
• /
• 2024

This study employs traditional statistical auto-regressive integrated moving average (ARIMA) and deep learning-based long short-term memory (LSTM) models to predict the deformation of earth retaining walls using inclinometer data from excavation sites. It compares the predictive capabilities of both models. The ARIMA model excels in analyzing linear patterns as time progresses, while the LSTM model is adept at handling complex nonlinear patterns and long-term dependencies in the data. This research includes preprocessing of inclinometer measurement data, performance evaluation across various data lengths and input conditions, and demonstrates that the LSTM model provides statistically significant improvements in prediction accuracy over the ARIMA model. The findings suggest that LSTM models can effectively assess the stability of retaining walls at excavation sites. Additionally, this study is expected to contribute to the development of safety monitoring systems at excavation sites and the advancement of time series prediction models.

• Journal of the Society of Disaster Information
• /
• v.18 no.1
• /
• pp.146-153
• /
• 2022

Purpose: In the case of domestic port facilities, port structures that have been in use for a long time have many problems in terms of safety performance and functionality due to the enlargement of ships, increased frequency of use, and the effects of natural disasters due to climate change. A big data analysis method was studied to develop an approximate model that can predict the aging pattern of a port facility based on the maintenance history data of the port facility. Method: In this study, member-level maintenance history data for caisson-type quay walls were collected, defined as big data, and based on the data, a predictive approximation model was derived to estimate the aging pattern and deterioration of the facility at the project level. A state-based aging pattern prediction model generated through Gaussian process (GP) and linear interpolation (SLPT) techniques was proposed, and models suitable for big data utilization were compared and proposed through validation. Result: As a result of examining the suitability of the proposed method, the SLPT method has RMSE of 0.9215 and 0.0648, and the predictive model applied with the SLPT method is considered suitable. Conclusion: Through this study, it is expected that the study of predicting performance degradation of big data-based facilities will become an important system in decision-making regarding maintenance.

• Journal of Food Hygiene and Safety
• /
• v.26 no.3
• /
• pp.203-208
• /
• 2011

This study was to evaluate the efficacy of sanitizer concentrations and treatment time against two major toad-borne pathogenic microorganisms such as Escherichia coli and Staphylococcus aureus on a stainless steel surface. As a result, stainless steel, treated with 100 ppm of chlorine showed reduction of E. coli(1.56, 1.49, 1.95 log cfu/25 $cm^2$) and S. aureus(0.49, 0.88, 1.27 log cfu/25 $cm^2$) after 0, 5 and 10 min, but none was not detected in treatment with 200 ppm. The population of E. coli(0.73, 0.90, 1.55 log cfu/25 $cm^2$) and S. aureus(0.37, 1.00, 1.45 log cfu/25 $cm^2$) reduced in 35.5% ethanol treated group, but none was not detected in treatment with 70%. The population was reduced E coli(0.28, 0.64, 1.07 cfu/25 $cm^2$) and S. aureus(0.53, 0.87, 0.99 log cfu/25 $cm^2$) by treatment with 45.5 ppm of hydrogen peroxide, but none was not detected in treatment with 91 ppm. Quarternary ammonium compound with 100 ppm was reduced E. coli(0.82, 1.62, 1.71 log cfu/25 $cm^2$) and S. aureus(0.46, 0.93, 1.38 log cfu/25 $cm^2$), but none was not detected in treatment with 200 ppm. Predictive models of sterilization for all 4 disinfectants were suitable to use with $r^2$ value of higher than 0.94. These models may be of use to food services and manufacture of safe products by controlling E. coli and S. aureus without the need for further detection of the organisms.

• International Journal of Highway Engineering
• /
• v.20 no.1
• /
• pp.87-95
• /
• 2018

PURPOSES : A geo-grid pavement, e.g., a stress-absorbing membrane interlayer (SAMI), can be applied to an asphalt-overlay method on the existing surface-pavement layer for pavement maintenance related to reflection cracking. Reflection cracking can occur when a crack in the existing surface layer influences the overlay pavement. It can reduce the pavement life cycle and adversely affect traffic safety. Moreover, a failed overlay can reduce the economic value. In this regard, the objective of this study is to evaluate the bonding properties between the rigid pavement and a SAMI by using the direct shear test and the pull-off test. The predicted fractural energy functions with the shear stress were determined from a numerical analysis of the moving average method and the polynomial regression method. METHODS : In this research, the shear and pull-off tests were performed to evaluate the properties of mixtures constructed using no interlayer, a tack-coat, and SAMI with fabric and without fabric. The lower mixture parts (describing the existing pavement) were mixed using the 25-40-8 joint cement-concrete standard. The overlay layer was constructed especially using polymer-modified stone mastic asphalt (SMA) pavement. It was composed of an SMA aggregate gradation and applied as the modified agent. The sixth polynomial regression equation and the general moving average method were utilized to estimate the interlayer shear strength. These numerical analysis methods were also used to determine the predictive models for estimating the fracture energy. RESULTS : From the direct shear test and the pull-off test results, the mixture bonded using the tack-coat (applied as the interlayer between the overlay layer and the jointed cement concrete) had the strongest shear resistance and bonding strength. In contrast, the SAMI pavement without fiber has a strong need for fractural energy at failure. CONCLUSIONS : The effects of site-reflection cracking can be determined using the same tests on cored specimens. Further, an empirical-mechanical finite-element method (FEM) must be done to understand the appropriate SAMI application. In this regard, the FEM application analy pavement-design analysis using thesis and bonding property tests using cored specimens from public roads will be conducted in further research.

• Journal of the Society of Disaster Information
• /
• v.17 no.2
• /
• pp.254-265
• /
• 2021

Purpose: Inspection and diagnosis on the performance and safety through domestic port facilities have been conducted for over 20 years. However, the long-term development strategies and directions for facility renewal and performance improvement using the diagnosis history and results are not working in realistically. In particular, in the case of port structures with a long service life, there are many problems in terms of safety and functionality due to increasing of the large-sized ships, of port use frequency, and the effects of natural disasters due to climate change. Method: In this study, the maintenance history data of the gravity type quay in element level were collected, defined as big data, and a predictive approximation model was derived to estimate the pattern of deterioration and aging of the facility of project level based on the data. In particular, we compared and proposed models suitable for the use of big data by examining the validity of the state-based deterioration pattern and deterioration approximation model generated through machine learning algorithms of GP and SGP techniques. Result: As a result of reviewing the suitability of the proposed technique, it was considered that the RMSE and R² in GP technique were 0.9854 and 0.0721, and the SGP technique was 0.7246 and 0.2518. Conclusion: This research through machine learning techniques is expected to play an important role in decision-making on investment in port facilities in the future if port facility data collection is continuously performed in the future.