• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.741-747
• /
• 2022

Fatigue lowers an individual's ability and makes it difficult to perform work. As fatigue accumulates, concentration decreases and thus the possibility of causing a safety accident increases. Awareness of fatigue is subjective, but it is necessary to quantitatively measure the level of fatigue in the actual field. In previous studies, it was proposed to measure the level of fatigue by expert judgment by adding objective indicators such as bio-signal analysis to subjective evaluations such as multidisciplinary fatigue scales. However this method is difficult to evaluate fatigue in real time in daily life. This paper is a study on the fatigue classification model that determines the fatigue level of workers in real time using speech data recorded in the field. Machine learning models such as logistic classification, support vector machine, and random forest are trained using speech data collected in the field. The performance evaluation showed good performance with accuracy of 0.677 to 0.758, of which logistic classification showed the best performance. From the experimental results, it can be seen that it is possible to classify the fatigue level using speech signals.

• Phonetics and Speech Sciences
• /
• v.8 no.4
• /
• pp.97-101
• /
• 2016

This paper presents a CART(Classification and Regression Tree)-based model to diagnose mental fatigue using speech technology. The parameters used in the model are the significant speech parameters highly correlated to the fatigue and questionnaire responses obtained before and after imposing the fatigue. It is shown from the experiments that the proposed model achieves classification accuracies of 96.67% and 98.33% using the speech parameters and questionnaire responses, respectively. This implies that the proposed model can be used as a tool to diagnose the mental fatigue, and that speech technology is useful to diagnose the fatigue.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.6
• /
• pp.43-52
• /
• 2022

We can sense somebody's feeling fatigue, which means that fatigue can be detected through sensing human biometric signals. Numerous researches for assessing fatigue are mostly focused on diagnosing the edge of disease-level fatigue. In this study, we adapt quantitative analysis approaches for estimating qualitative data, and propose video analysis models for measuring fatigue state. Proposed three deep-learning based classification models selectively include stages of video analysis: object detection, feature extraction and time-series frame analysis algorithms to evaluate each stage's effect toward dividing the state of fatigue. Using frontal face videos collected from various fatigue situations, our CNN model shows 0.67 accuracy, which means that we empirically show the video analysis models can meaningfully detect fatigue state. Also we suggest the way of model adaptation when training and validating video data for classifying fatigue.

• The Korean Journal of Pain
• /
• v.32 no.2
• /
• pp.120-128
• /
• 2019

Background: We aimed to explore the American College of Rheumatology (ACR) 1990 and 2011 fibromyalgia (FM) classification criteria's items and the components of Fibromyalgia Impact Questionnaire (FIQ) to identify features best discriminating FM features. Finally, we developed a combined FM diagnostic (C-FM) model using the FM's key features. Methods: The means and frequency on tender points (TPs), ACR 2011 components and FIQ items were calculated in the FM and non-FM (osteoarthritis [OA] and non-OA) patients. Then, two-step multiple logistic regression analysis was performed to order these variables according to their maximal statistical contribution in predicting group membership. Partial correlations assessed their unique contribution, and two-group discriminant analysis provided a classification table. Using receiver operator characteristic analyses, we determined the sensitivity and specificity of the final model. Results: A total of 172 patients with FM, 75 with OA and 21 with periarthritis or regional pain syndromes were enrolled. Two steps multiple logistic regression analysis identified 8 key features of FM which accounted for 64.8% of variance associated with FM group membership: lateral epicondyle TP with variance percentages (36.9%), neck pain (14.5%), fatigue (4.7%), insomnia (3%), upper back pain (2.2%), shoulder pain (1.5%), gluteal TP (1.2%), and FIQ fatigue (0.9%). The C-FM model demonstrated a 91.4% correct classification rate, 91.9% for sensitivity and 91.7% for specificity. Conclusions: The C-FM model can accurately detect FM patients among other pain disorders. Re-inclusion of TPs along with saving of FM main symptoms in the C-FM model is a unique feature of this model.

• Journal of Advanced Marine Engineering and Technology
• /
• v.39 no.9
• /
• pp.903-910
• /
• 2015

The purpose of this research is to develop a full-spectral fatigue analysis program, based on rigid-body ship motion analysis, in order to perform a full-spectral fatigue analysis that considers hydroelasticity effects. To gain credibility, fatigue analysis results of two ship types, performed by the developed program, were compared with those of a classification society, and it was found that both are identical. Full-spectral fatigue analysis considering hydroelasticity effects would be developed in further studies by including flexible-body ship motion analysis results and by supplementing the developed program with a wide-band fatigue damage model.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.10 no.4
• /
• pp.14-21
• /
• 2001

To estimate crack growth rate and cycle ratio uniquely, many investigators have developed various kinds of mechanical parameters and theories. But, thes have produced local solution space through single parameter. Neural Networks can perform patten classification using several input and output parameters. Fatigue damage model by neural networks was used to recognize the relation between da/dN/N/N(sub)f, and half-value breadth ratio B/Bo, fractal dimension D(sub)f, and fracture mechanical parameters in 2024-T3 aluminium alloy. Learned neural networks has ability to predict both crack growth rate da/dN and cycly ratio /N/N(sub)f within engineering estimated mean error(5%).

• Journal of Advanced Marine Engineering and Technology
• /
• v.21 no.5
• /
• pp.542-548
• /
• 1997

In this study an evaluation method of fatigue strength of membrane type LNG tank is presented with FEM analysis and experimental approach of seam and raised edge welds. The study contains the following : l)FEM analysis of test specimens 2)Fatigue tests of seam and raised edge welds 3)Estimation of cumulative damage factor of the welds on the basis of safe life design concept complying with the rules of classification society 4)Review of the effect of mean stress on the fatigue strength 5)Modelling of fatigue life of the welds which is changeable by weld heights With the results obtained in this study, a model ${\Delta}{\delta}/h^2=0.13553\;{N_{f}}^{-0.3151}$ for seam and raised edge welds having a given weld height is proposed to be useful for designers and inspectors.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.6 no.4
• /
• pp.1096-1110
• /
• 2014

Whipping/springing research started in the 50'ies. In the 60'ies inland water vessels design rules became stricter due to whipping/springing. The research during the 70-90'ies may be regarded as academic. In 2000 a large ore carrier was strengthened due to severe cracking from North Atlantic operation, and whipping/springing contributed to half of the fatigue damage. Measurement campaigns on blunt and slender vessels were initiated. A few blunt ships were designed to account for whipping/springing. Based on the measurements, the focus shifted from fatigue to extreme loading. In 2005 model tests of a 4,400 TEU container vessel included extreme whipping scenarios. In 2007 the 4400 TEU vessel MSC Napoli broke in two under similar conditions. In 2009 model tests of an 8,600 TEU container vessel container vessel included extreme whipping scenarios. In 2013 the 8,100 TEU vessel MOL COMFORT broke in two under similar conditions. Several classification societies have published voluntary guidelines, which have been used to include whipping/springing in the design of several container vessels. This paper covers results from model tests and full scale measurements used as background for the DNV Legacy guideline. Uncertainties are discussed and recommendations are given in order to obtain useful data. Whipping/springing is no longer academic.

• Journal of Drive and Control
• /
• v.20 no.4
• /
• pp.54-63
• /
• 2023

High and intermittent loading cycles induce fatigue damage to transmission components, resulting in premature gearbox failure. To identify gearbox defects, numerous vibration-based diagnostics techniques, using several artificial intelligence (AI) algorithms, have recently been presented. In this paper, an optimized deep belief network (DBN) model for gearbox problem diagnosis was designed based on time-frequency visual pattern identification. To optimize the hyperparameters of the model, a particle swarm optimization (PSO) approach was integrated into the DBN. The proposed model was tested on two gearbox datasets: a wind turbine gearbox and an experimental gearbox. The optimized DBN model demonstrated strong and robust performance in classification accuracy. In addition, the accuracy of the generated datasets was compared using traditional ML and DL algorithms. Furthermore, the proposed model was evaluated on different partitions of the dataset. The results showed that, even with a small amount of sample data, the optimized DBN model achieved high accuracy in diagnosis.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2000.04a
• /
• pp.341-347
• /
• 2000

To estimate crack growth rate and cycle ratio uniquely, many investigators have developed various kinds of mechanical parameters and theories. But, these have produced local solution space through single parameter. Neural Networks can perform pattern classification using several input and output parameters. Fatigue damage model by neural networks was used to recognize the relation between da/dN N/Nf, and half-value breadth ratio B/BO0, fractal dimension Df and fracture mechanical parameters in 2024-T3 ability to predict both crack growth rate da/dN and cycle ratio N/Nf within engineering estimated mean error (5%).