• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.11 no.2
• /
• pp.91-98
• /
• 2017

Background & Object: Basic daily activity screening tool such as the Modified Barthel Index (MBI) has been used commonly in rehabilitation clinic and community based rehabilitation setting. Previous studies have shown the significant relations between the level of daily activities and driving ability on stroke or elderly people. However, there is a lack of studies to investigate the usefulness of MBI on prediction of driving ability for stroke patient. This study was to predict driving abilities of stroke survivor using Korean version Modified Barthel Index (K-MBI). Methods: A sample of 48 patients with stroke in rehabilitation hospital was recruited. All participants were tested level of basic daily activities using K-MBI. The driving ability of participants was tested using virtual reality driving simulator. The predictive validity was calculated of the K-MBI among pass or fail group of driving simulator test using receiver operating characteristics curves. Results: The cut-off score of >86.5 on the K-MBI is proper sensitivity to predict on driving performance ability. Conclusion: This pilot result offers clinical reference to therapists and caregivers for reasoning on driving recommendation period during rehabilitation stage of stroke survivors. Further studies need to identify prediction using real on-road test in a large population group.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.161-183
• /
• 2022

Opinion polls have become a powerful means for election campaigns and one of the most important subjects in the media in that they predict the actual election results and influence people's voting behavior. However, the more active the polls, the more often they fail to properly reflect the voters' minds in measuring the effectiveness of election campaigns, such as repeatedly conducting polls on the likelihood of winning or support rather than verifying the pledges and policies of candidates. Even if the poor predictions of the election results of the polls have undermined the authority of the press, people cannot easily let go of their interest in polls because there is no clear alternative to answer the instinctive question of which candidate will ultimately win. In this regard, we attempt to retrospectively grasp public opinion on the 20th presidential election by applying the 'YouTube Analysis' function of Sometrend, which provides an environment for discovering insights through online big data. Through this study, it is confirmed that a result close to the actual public opinion (or opinion poll results) can be easily derived with simple YouTube data results, and a high-performance public opinion prediction model can be built.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.11 no.3
• /
• pp.1-15
• /
• 2016

This study has analyzed predication capabilities leveraging multi-variate model, logistic regression model, and artificial neural network model based on financial information of medium-small sized companies list in KOSDAQ. 83 delisted companies from 2009 to 2012 and 83 normal companies, i.e. 166 firms in total were sampled for the analysis. Modelling with training data was mobilized for 100 companies inlcuding 50 delisted ones and 50 normal ones at random out of the 166 companies. The rest of samples, 66 companies, were used to verify accuracies of the models. Each model was designed by carrying out T-test with 79 financial ratios for the last 5 years and identifying 9 significant variables. T-test has shown that financial profitability variables were major variables to predict a financial risk at an early stage, and financial stability variables and financial cashflow variables were identified as additional significant variables at a later stage of insolvency. When predication capabilities of the models were compared, for training data, a logistic regression model exhibited the highest accuracy while for test data, the artificial neural networks model provided the most accurate results. There are differences between the previous researches and this study as follows. Firstly, this study considered a time-series aspect in light of the fact that failure proceeds gradually. Secondly, while previous studies constructed a multivariate discriminant model ignoring normality, this study has reviewed the regularity of the independent variables, and performed comparisons with the other models. Policy implications of this study is that the reliability for the disclosure documents is important because the simptoms of firm's fail woule be shown on financial statements according to this paper. Therefore institutional arragements for restraing moral laxity from accounting firms or its workers should be strengthened.

• Journal of Korea Water Resources Association
• /
• v.50 no.2
• /
• pp.89-97
• /
• 2017

Turbulent flow structure in the high amplitude meandering channel is complex due to secondary recirculation with helicoidal motions and shear layers formed by flow separation from the curved sidewall. In this work, the secondary flow and the superelevation of the water surface produced in the high-amplitude Kinoshita channel are reproduced by the unsteady Reynolds-averaged Navier-Stokes (RANS) computations using the VOF technique for resolving the variation of water surface elevation and three statistical turbulence models ($k-{\varepsilon}$, RNG $k-{\varepsilon}$, $k-{\omega}$ SST). The numerical results computed by a second-order accurate finite volume method are compared with an existing experimental measurement. Among applied turbulence models, $k-{\omega}$ SST model relatively well predicts overall distribution of the secondary recirculation in the Kinoshita channel, while all three models yield similar prediction of water superelevation transverse slope. The secondary recirculation driven by the radial acceleration in the upstream bend affects the flow structure in the downstream bend, which yields a pair of counter-rotating vortices at the bend apex. This complex flow pattern is reasonably well reproduced by the $k-{\omega}$ SST model. Both $k-{\varepsilon}$ based models fail to predict the clockwise-rotating vortex between a pair of counter-rotating vortices which was observed in the experiment. Regardless of applied turbulence models, the present computations using the VOF method appear to well reproduce the superelevation of water surface through the meandering channel.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.40 no.5
• /
• pp.91-99
• /
• 1998

The widespread use of thin shell structures has created a need for a systematic method of analysis which can adequately account for arbitrary geometric form and boundary conditions as well as arbitrary general type of loading. Therefore, the stress and analysis of thin shell has been one of the more challenging areas of structural mechanics. A wide variety of numerical methods have been applied to the governing differential equations for spherical and cylindrical structures with a few results applicable to practice. The analysis of axisymmetric spherical shell is almost an every day occurrence in many industrial applications. A reliable and accurate finite element analysis procedure for such structures was needed. Dynamic loading of structures often causes excursions of stresses well into the inelastic range and the influence of geometry changes on the response is also significant in many cases. Therefore both material and geometric nonlinear effects should be considered. In general, the shell structures designed according to quasi-static analysis may fail under conditions of dynamic loading. For a more realistic prediction on the load carrying capacity of these shell, in addition to the dynamic effect, consideration should also include other factors such as nonlinearities in both material and geometry since these factors, in different manner, may also affect the magnitude of this capacity. The objective of this paper is to demonstrate the dynamic characteristics of spherical shell. For these purposes, the spherical shell subjected to uniformly distributed step load was analyzed for its large displacements elasto-viscoplastic static and dynamic response. Geometrically nonlinear behaviour is taken into account using a Total Lagrangian formulation and the material behaviour is assumed to elasto-viscoplastic model highly corresponding to the real behaviour of the material. The results for the dynamic characteristics of spherical shell in the cases under various conditions of base-radius/central height(a/H) and thickness/shell radius(t/R) were summarized as follows : The dynamic characteristics with a/H. 1) AS the a/H increases, the amplitude of displacement in creased. 2) The values of displacement dynamic magnification factor (DMF) were ranges from 2.9 to 6.3 in the crown of shell and the values of factor in the mid-point of shell were ranged from 1.8 to 2.6. 3) As the a/H increases, the values of DMF in the crown of shell is decreased rapidly but the values of DMF in mid-point shell is increased gradually. 4) The values of DMF of hoop-stresses were range from 3.6 to 6.8 in the crown of shell and the values of factor in the mid-point of shell were ranged from 2.3 to 2.6, and the values of DMF of stress were larger than that of displacement. The dynamic characteristics with t/R. 5) With the thickness of shell decreases, the amplitude of the displacement and the period increased. 6) The values of DMF of the displacement were ranged from 2.8 to 3.6 in the crown of shell and the values of factor in the mid-point of shell were ranged from 2.1 to 2.2.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.40 no.3
• /
• pp.113-121
• /
• 1998

The widespread use of thin shell structures has created a need for a systematic method of analysis which can adequately account for arbitrary geometric form. Therefore, the stress analysis of thin shell has been one of the more challenging areas of structural mechanics. The analysis of axisymmetric spherical shell is almost an every day occurrence in many industrial applications. A reliable and accurate finite element analysis procedure for such structures was needed. In general, the shell structures designed according to quasi-static analysis may fail under conditions of dynamic loading. For a more realistic prediction on the load carrying capacity of these shell, in addition to the dynamic effect, consideration should also include other factors such as nonlinearities in both material and geometry since these factors, in different manner, may also affect the magnitude of this capacity. The objective of this paper is to demonstrate the dynamic characteristics of spherical Shell. For these purpose, the spherical shell subjected to uniformly distributed step load was analyzed for its large displacements elasto-viscoplastic dynamic response. The results for the dynamic characteristics of spherical shell in the cases under various conditions of base-radius/central height(a/H) and thickness/shell radius(t/R) were summarized as follows: 1. The dynamic characteristics with a/H, 1) As the a/H increases, the amplitude of displacement increased. 2) The values of displacement Dynamic Magnification Factor (DMF) range from 2.9 to 6.3 in the crown of shell and the values of factor in the mid-point of shell range from 1.8 to 2.6. 3) As the a/H increases, the values of DMF in the crown of shell is decreased rapidly but the values of DMF in mid-point of shell is increased gradually. 4) The values of DMF of hoop-stresses range from 3.6 to 6.8 in the crown of shell and the values of factor in the mid-point of shell range from 2.3 to 2.6, the values of DMF of stress were larger than that of displacement. 2. The dynamic characteristics with t/R, 1) With the decrease of thickness of shell decreses, the amplitude of the displacement and the period increased. 2) The values of DMF of the displacement were range from 2.8 to 3.6 in the crown of shell and the values of factor in the mid-point of shell were range from 2.1 to 2.2.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.13 no.3
• /
• pp.72-83
• /
• 2017

GPUs can provide high throughput with latency hiding by executing many warps in parallel. MSHR(Miss Status Holding Registers) for L1 data cache tracks cache miss requests until required data is serviced from lower level memory. In recent GPUs, excessive requests for cache resources cause underutilization problem of GPU resources due to cache resource reservation fails. In this paper, we propose a new warp scheduling technique to reduce stall cycles under MSHR resource shortage. Cache miss rates for each warp is predicted based on the observation that each warp shows similar cache miss rates for long period. The warps showing low miss rates or computation-intensive warps are given high priority to be issued when MSHR is full status. Our proposal improves GPU performance by utilizing cache resource more efficiently based on cache miss rate prediction and monitoring the MSHR entries. According to our experimental results, reservation fail cycles can be reduced by 25.7% and IPC is increased by 6.2% with the proposed scheduling technique compared to loose round robin scheduler.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.301-307
• /
• 2023

Deep learning requires building a deep neural network, collecting a large amount of training data, and then training the built neural network for a long time. If training does not proceed properly or overfitting occurs, training will fail. When using deep learning tools that have been developed so far, it takes a lot of time to collect training data and learn. However, due to the rapid advent of the mobile environment and the increase in sensor data, the demand for real-time deep learning technology that can dramatically reduce the time required for neural network learning is rapidly increasing. In this study, a real-time deep learning system was implemented using an Arduino system equipped with a fine dust sensor. In the implemented system, fine dust data is measured every 30 seconds, and when up to 120 are accumulated, learning is performed using the previously accumulated data and the newly accumulated data as a dataset. The neural network for learning was composed of one input layer, one hidden layer, and one output. To evaluate the performance of the implemented system, learning time and root mean square error (RMSE) were measured. As a result of the experiment, the average learning error was 0.04053796, and the average learning time of one epoch was about 3,447 seconds.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.121-142
• /
• 2023

As the number and weight of imported food are steadily increasing, safety management of imported food to prevent food safety accidents is becoming more important. The Ministry of Food and Drug Safety conducts on-site inspections of foreign food facilities before customs clearance as well as import inspection at the customs clearance stage. However, a data-based safety management plan for imported food is needed due to time, cost, and limited resources. In this study, we tried to increase the efficiency of the on-site inspection by preparing a machine learning prediction model that pre-selects the companies that are expected to fail before the on-site inspection. Basic information of 303,272 foreign food facilities and processing businesses collected in the Integrated Food Safety Information Network and 1,689 cases of on-site inspection information data collected from 2019 to April 2022 were collected. After preprocessing the data of foreign food facilities, only the data subject to on-site inspection were extracted using the foreign food facility_code. As a result, it consisted of a total of 1,689 data and 103 variables. For 103 variables, variables that were '0' were removed based on the Theil-U index, and after reducing by applying Multiple Correspondence Analysis, 49 characteristic variables were finally derived. We build eight different models and perform hyperparameter tuning through 5-fold cross validation. Then, the performance of the generated models are evaluated. The research purpose of selecting companies subject to on-site inspection is to maximize the recall, which is the probability of judging nonconforming companies as nonconforming. As a result of applying various algorithms of machine learning, the Random Forest model with the highest Recall_macro, AUROC, Average PR, F1-score, and Balanced Accuracy was evaluated as the best model. Finally, we apply Kernal SHAP (SHapley Additive exPlanations) to present the selection reason for nonconforming facilities of individual instances, and discuss applicability to the on-site inspection facility selection system. Based on the results of this study, it is expected that it will contribute to the efficient operation of limited resources such as manpower and budget by establishing an imported food management system through a data-based scientific risk management model.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.5 no.4
• /
• pp.1-34
• /
• 2010

Recently, failure rates of Kosdaq IPO firms are increasing and their survival rates tend to be very low, and when these firms do fail, often times backed by a number of governmental financial supports, they may inflict severe financial damage to investors, let alone economy as a whole. To ensure investors' confidence in Kosdaq and foster promising and healthy businesses, it is necessary to precisely assess their intrinsic values and survivability. This study investigates what contributed to the failure of IPO firms and analyzed how these elements are factored into corresponding firms' stock returns. Failure risks are assessed at the time of IPO. This paper considers factors reflecting IPO characteristics, a firm's underwriter prestige, auditor's quality, IPO offer price, firm's age, and IPO proceeds. The study further went on to examine how, if at all, these failure risks involved during IPO led to post-IPO stock prices. Sample firms used in this study include 98 Kosdaq firms that have failed and 569 healthy firms that are classified into the same business categories, and Logit models are used in estimate the probability of failure. Empirical results indicate that auditor's quality, IPO offer price, firm's age, and IPO proceeds shown significant relevance to failure risks at the time of IPO. Of other variables, firm's size and ROA, previously deemed significantly related to failure risks, in fact do not show significant relevance to those risks, whereas financial leverage does. This illustrates the efficacy of a model that appropriately reflects the attributes of IPO firms. Also, even though R&D expenditures were believed to be value relevant by previous studies, this study reveals that R&D is not a significant factor related to failure risks. In examing the relation between failure risks and stock prices, this study finds that failure risks are negatively related to 1 or 2 year size-adjusted abnormal returns after IPO. The results of this study may provide useful knowledge for government regulatory officials in contemplating pertinent policy and for credit analysts in their proper evaluation of a firm's credit standing.