• Asia pacific journal of information systems
• /
• v.34 no.1
• /
• pp.209-225
• /
• 2024

This research aims to use machine learning technology in human resource management to predict employees' work-life balance. The study utilized a dataset from IBM Watson Analytics in the IBM Community for the machine learning analysis. Multinomial dependent variables concerning workers' work-life balance were examined, categorized into continuous and categorical types using the Generalized Linear Model. The complexity of assessing variable roles and their varied impact based on the type of model used was highlighted. The study's outcomes are academically and practically relevant, showcasing how machine learning can offer further understanding of psychological variables like work-life balance through analyzing employee profiles.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.33 no.4
• /
• pp.366-372
• /
• 2009

Creep life prediction has been commonly used by a time-temperature parameter (TTP) which is correlated to an applied stress and temperature, such as Larson-Miller (LM), Orr-Sherby-Dorn (OSD), Manson-Haferd (MH) and Manson-Succop (MS) parameters. A stress-temperature linear model (STLM) based on Arrhenius, Dorn and Monkman-Grant equations was newly proposed through a mathematical procedure. For this model, the logarithm time to rupture was linearly dependent on both an applied stress and temperature. The model parameters were properly determined by using a technique of maximum likelihood estimation of a statistical method, and this model was applied to the creep data of Alloy 617. From the results, it is found that the STLM results showed better agreement than the Eno’s model and the LM parameter ones. Especially, the STLM revealed a good estimation in predicting the long-term creep life of Alloy 617.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2000.11c
• /
• pp.560-568
• /
• 2000

The aims of this research were to investigate the preprocessing effect of spectrum data on prediction performance and to develop a robust model to predict SSC in intact apple. Spectrum data of 320 Fuji apples were measured with the on-line transmittance measurement system at the wavelength range of 550∼1100nm. Preprocess methods adopted for the tests were Savitzky Golay, MSC, SNV, first derivative and OSC. Several combinations of those methods were applied to the raw spectrum data set to investigate the relative effect of each method on the performance of the calibration model. PLS method was used to regress the preprocessed data set and the SSCs of samples, and the cross-validation was to select the optimal number of PLS factors. Smoothing and scattering corection were essential in increasing the prediction performance of PLS regression model and the OSC contributed to reduction of the number of PLS factors. The first derivative resulted in unfavorable effect on the prediction performance. MSC and SNV showed similar effect. A robust calibration model could be developed by the preprocessing combination of Savitzky Golay smoothing, MSC and OSC, which resulted in SEP= 0.507, bias=0.032 and R$^2$=0.8823.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.33 no.10
• /
• pp.1119-1124
• /
• 2009

This paper deals with the variability analysis of short term creep rupture test data based on the previous creep rupture tests and the possibility of the creep life prediction. From creep tests performed by constant uniaxial stresses at 600, 650 and $700^{\circ}C$ elevated temperature, in order to investigate the variability of short-term creep rupture data, the creep curves were analyzed for normalized creep strain divided by initial strain. There are some variability in the creep rupture data. And, the difference between general creep curves and normalized creep curves were obtained. The effects of the creep rupture time (RT) and steady state creep rate (SSCR) on the Weibull distribution parameters were investigated. There were good relation between normal Weibull parameters and normalized Weibull parameters. Finally, the predicted creep life were compared with the Monkman-Grant model.

• Proceedings of the KSME Conference
• /
• 2004.11a
• /
• pp.7-12
• /
• 2004

A lifetime prediction of holddown spring screw in nuclear fuel assembly was performed using fracture mechanics approach. The spring screw was designed such that it was capable of sustaining the loads imposed by the initial tensile preload and operational loads. In order to investigate the cause of failure and to predict the stress corrosion cracking life of the screw, a stress analysis of the top nozzle spring assembly was done using finite element analysis. The elastic-plastic finite element analysis showed that the local stresses at the critical regions of head-shank fillet and thread root significantly exceeded than the yield strength of the screw material, resulting in local plastic deformation. Normalized stress intensity factors for PWSCC life prediction was proposed. Primary water stress corrosion cracking life of the Inconel 600 screw was predicted by using integration of the Scott model and resulted in 1.78 years, which was fairly close to the actual service life of the holddown spring screw.

• Steel and Composite Structures
• /
• v.46 no.3
• /
• pp.435-449
• /
• 2023

Time domain method and frequency domain method are commonly used in the current fatigue life calculation theory. The time domain method has complicated procedures and needs a large amount of calculation, while the frequency domain method has poor applicability to different materials and different spectrum, and improper selection of spectrum model will lead to large errors. Considering that artificial neural network has strong ability of nonlinear mapping and generalization, this paper applied this technique to random fatigue life prediction, and the effect of average stress was taken into account, thereby achieving more accurate prediction result of random fatigue life.

• Journal of the Korean Ceramic Society
• /
• v.31 no.10
• /
• pp.1141-1146
• /
• 1994

Cyclic fatigue experiment was carried out to predict the life time of alumina ceramics. Four kinds of model were suggested to obtain the adequate representative static stress corresponding to the cyclic stress applied to the alumina specimens. Arithmetic mean stress model gives 21.81 of the crack growth exponent, integrated stress model gives 22.15, maximum stress model gives 24.57, and equivalent static stress model gives 24.43. It is considered that the equivalent static stress model is the most reasonable and gives the best adequate crack growth exponents value.

• Transactions of Materials Processing
• /
• v.24 no.4
• /
• pp.264-271
• /
• 2015

In the current study, a method was proposed to quantitatively predict the wear and fatigue life of a shearing die in order to determine an effective replacement period for the die. The shearing die model of a retainer manufacturing process was used for the proposed method of quantitative life prediction. The retainer is produced through shearing steps, such as piercing and notching. The shearing die of the retainer is carefully controlled because the dimensional accuracy of the retainer is critical. The fatigue life for the shearing die was predicted using ANSYS considering S-N curves of STD11 and Gerber’s equation. The wear life for the shearing die was predicted using DEFORM-3D considering the Archard’s wear model. Experimental shearing of the retainer was conducted to verify the effectiveness of the proposed method for predicting die life. The fatigue failure of the shearing die was macroscopically measured. The wear depth was measured using a 3D coordinate measuring machine. The results showed that the wear and fatigue life in the FE analysis agree well with the experimental results.

• 한국균학회소식:학술대회논문집
• /
• 2018.05a
• /
• pp.22-22
• /
• 2018

Fungal genome sequencing and assembly have been trivial in these days. Genome analysis relies on high quality of gene prediction and annotation. Automatic fungal genome annotation pipeline is essential for handling genomic sequence data accumulated exponentially. However, building an automatic annotation procedure for fungal genomes is not an easy task. FunGAP (Fungal Genome Annotation Pipeline) is developed for precise and accurate prediction of gene models from any fungal genome assembly. To make high-quality gene models, this pipeline employs multiple gene prediction programs encompassing ab initio, evidence-, and homology-based evaluation. FunGAP aims to evaluate all predicted genes by filtering gene models. To make a successful filtering guide for removal of false-positive genes, we used a scoring function that seeks for a consensus by estimating each gene model based on homology to the known proteins or domains. FunGAP is freely available for non-commercial users at the GitHub site (https://github.com/CompSynBioLab-KoreaUniv/FunGAP).

• Corrosion Science and Technology
• /
• v.8 no.2
• /
• pp.81-88
• /
• 2009

Chloride induced corrosion of steel reinforcement inside concrete is a major concern for concrete structures exposed to a marine environment. It is well known that transport of chloride ions in concrete occurs mainly through ionic/molecular diffusion, as a gradient of chloride concentration in the concrete pore solution is set. In the process of chloride transport, a portion of chlorides are bound in cement matrix then to be removed in the pore solution, and thus only the rest of chlorides which are not bound (i.e. free chlorides) leads the ingress of chlorides. However, since the measurement of free/bound chloride content is much susceptible to environmental conditions, chloride profiles expressed in total chlorides are evaluated to use in many studies In this study, the capacity of chloride binding in cement matrix was monitored for 150 days and then quantified using the Langmuir isotherm to determine the portions of free chlorides and bound chlorides at given total chlorides and the redistribution of free chlorides. Then, the diffusion of chloride ion in concrete was modeled by considering the binding capacity for the prediction of chloride profiles with the redistribution. The predicted chloride profiles were compared to those obtained from conventional model. It was found that the prediction of chloride profiles obtained by the model has shown slower diffusion than those by the conventional ones. This reflects that the prediction by total chloride may overestimate the ingress of chlorides by neglecting the redistribution of free chlorides caused by the binding capacity of cement matrix. From the evaluation, it is also shown that the service life prediction using the free chloride redistribution model needs different expression for the chloride threshold level which is expressed by the total chlorides in the conventional diffusion model.