• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.9-17
• /
• 2021

In this paper, an autonomous multi-agent path planning using reinforcement learning for monitoring of infrastructures and resources in a computationally distributed system was proposed. Reinforcement-learning-based multi-agent exploratory system in a distributed node enable to evaluate a cumulative reward every action and to provide the optimized knowledge for next available action repeatedly by learning process according to a learning policy. Here, the proposed methods were presented by (a) approach of dynamics-based motion constraints multi-agent path-planning to reduce smaller agent steps toward the given destination(goal), where these agents are able to geographically explore on the environment with initial random-trials versus optimal-trials, (b) approach using agent sub-goal selection to provide more efficient agent exploration(path-planning) to reach the final destination(goal), and (c) approach of reinforcement learning schemes by using the proposed autonomous and asynchronous triggering of agent exploratory phases.

• Design & Manufacturing
• /
• v.15 no.4
• /
• pp.24-31
• /
• 2021

In this study, an artificial neural network model was constructed to convert CAE analysis data into similar experimental data. In the analysis and experiment, the injection molding data for 50 conditions were acquired through the design of experiment and random selection method. The injection molding conditions and the weight, height, and diameter of the product derived from CAE results were used as the input parameters for learning of the convert model. Also the product qualities of experimental results were used as the output parameters for learning of the convert model. The accuracy of the convert model showed RMSE values of 0.06g, 0.03mm, and 0.03mm in weight, height, and diameter, respectively. As the next step, additional randomly selected conditions were created and CAE analysis was performed. Then, the additional CAE analysis data were converted to similar experimental data through the conversion model. An artificial neural network model was constructed to predict the quality of injection molded product by using converted similar experimental data and injection molding experiment data. The injection molding conditions were used as input parameters for learning of the predicted model and weight, height, and diameter of the product were used as output parameters for learning. As a result of evaluating the performance of the prediction model, the predicted weight, height, and diameter showed RMSE values of 0.11g, 0.03mm, and 0.05mm and in terms of quality criteria of the target product, all of them showed accurate results satisfying the criteria range.

• Architectural research
• /
• v.24 no.2
• /
• pp.21-27
• /
• 2022

For the past decade, South Korea had experienced catastrophic building fires, which resulted in consider-ably high number of casualties. This motivated research to develop fire-safe wall assemblies. In this study Fire Risk Analysis (FRA) is conducted as part of the project designing phase to ensure fire safety of the final product. Traditional approach was to consider fire performance at the end of the designing stage, when PASS/FAIL fire test results are required to be submitted to the Authority Having Jurisdiction (AHJ). By applying a fire risk analysis to guide the designing phase, overall fire safety of a wall assembly can be achieved more systematically as conducting FRA allows designers to clearly identify elements that are more vulnerable to fire and simply replace them with other practical options. Severity of fire risk is determined by considering the fire hazards of a wall assembly such as the exterior layer, insulation, vertical connectivity, and external ignition sources (e.g., photovoltaic panels). Frequency of fire risk is assessed based on the factors affecting fire likelihood, which are air cavity and fire-stopping applied in the design, and random design changes occurring during on-site construction. Fire risk matrix is proposed based on these fire risk factors and efforts to reduce the fire risk level associated with the wall assembly are given by systematically assessing the fire risk factors identified from fire risk analysis. Current study demonstrates how fire risk analysis can be applied to develop fire-safe walls by reducing the relevant fire risks- both severity and frequency.

• Journal of Biomedical Engineering Research
• /
• v.44 no.1
• /
• pp.11-18
• /
• 2023

Currently, studies to predict the risk of rectal cancer surgery select MRI image slices based on the clinical experience of surgeons. The purpose of this study is to semi-automatically select and classify 2D MRI image slides to predict the risk of rectal cancer surgery using biomarkers. The data used were retrospectively collected MRI imaging data of 50 patients who underwent laparoscopic surgery for rectal cancer at Gachon University Gil Medical Center. Expert-selected MRI image slices and non-selected slices were screened and radiomics was used to extract a total of 102 features. A total of 16 approaches were used, combining 4 classifiers and 4 feature selection methods. The combination of Random Forest and Ridge performed with a sensitivity of 0.83, a specificity of 0.88, an accuracy of 0.85, and an AUC of 0.89±0.09. Differences between expert-selected MRI image slices and non-selected slices were analyzed by extracting the top five significant features. Selected quantitative features help expedite decision making and improve efficiency in studies to predict risk of rectal cancer surgery.

• Research in Community and Public Health Nursing
• /
• v.33 no.3
• /
• pp.340-355
• /
• 2022

Purpose: This study aimed to examine the effects of non-pharmacological sleep intervention programs in improving sleep quality among older adults in long-term care facilities. Methods: A literature search and selection was performed on nine different databases using the guidelines of PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses). Overall, 14 studies met the inclusion criteria and were systematically reviewed. For the meta-analysis, the effect size was estimated using the random-effects model in Review Manager (RevMan) desktop version 5.4 of the Cochrane Library. Results: The meta-analysis of overall non-pharmacological interventions obtained a total effect size of 1.0 (standardized mean difference [SMD]=1.0, 95% confidence interval [CI]: 0.64~1.35), which was statistically significant (Z=5.55, p<.001). The most frequently studied non-pharmacological intervention was aroma therapy, with an effect size of 0.61 (SMD=0.61, 95% CI: 0.14~1.08), which was statistically significant (Z=2.55, p=.010). In the subgroup analysis, group-based interventions, interventions for >4 weeks, and untreated control studies were more effective. Conclusion: This study confirms that non-pharmacological interventions are effective in improving sleep quality among older adults in long-term care facilities. However, the sample size was small and the risk of bias in assessing the interventions of individual studies was unclear or high, thereby limiting the generalizability of the results. Further reviews that evaluate randomized control trials, evidence-based interventions that consider older adult participants' physical activity levels, different intervention methods and durations, and different control group intervention types are needed to obtain more conclusive evidence.

• Korean Journal of Remote Sensing
• /
• v.38 no.4
• /
• pp.327-341
• /
• 2022

Cloud removal is often required to construct time-series sets of optical images for environmental monitoring. In regression-based cloud removal, the selection of an appropriate regression model and the impact analysis of the input images significantly affect the prediction performance. This study evaluates the potential of Gaussian process (GP) regression for cloud removal and also analyzes the effects of cloud-free optical images and spectral bands on prediction performance. Unlike other machine learning-based regression models, GP regression provides uncertainty information and automatically optimizes hyperparameters. An experiment using Sentinel-2 multi-spectral images was conducted for cloud removal in the two agricultural regions. The prediction performance of GP regression was compared with that of random forest (RF) regression. Various combinations of input images and multi-spectral bands were considered for quantitative evaluations. The experimental results showed that using multi-temporal images with multi-spectral bands as inputs achieved the best prediction accuracy. Highly correlated adjacent multi-spectral bands and temporally correlated multi-temporal images resulted in an improved prediction accuracy. The prediction performance of GP regression was significantly improved in predicting the near-infrared band compared to that of RF regression. Estimating the distribution function of input data in GP regression could reflect the variations in the considered spectral band with a broader range. In particular, GP regression was superior to RF regression for reproducing structural patterns at both sites in terms of structural similarity. In addition, uncertainty information provided by GP regression showed a reasonable similarity to prediction errors for some sub-areas, indicating that uncertainty estimates may be used to measure the prediction result quality. These findings suggest that GP regression could be beneficial for cloud removal and optical image reconstruction. In addition, the impact analysis results of the input images provide guidelines for selecting optimal images for regression-based cloud removal.

• Communications for Statistical Applications and Methods
• /
• v.30 no.1
• /
• pp.95-107
• /
• 2023

Purpose: The statistical analysis of point processes on linear networks is a recent area of research that studies processes of events happening randomly in space (or space-time) but with locations limited to reside on a linear network. For example, traffic accidents happen at random places that are limited to lying on a network of streets. This paper applies techniques developed for point processes on linear networks and the tools available in the R-package spatstat to estimate the intensity of traffic accidents in Leon County, Florida. Methods: The intensity of accidents on the linear network of streets is estimated using log-linear Poisson models which incorporate cubic basis spline (B-spline) terms which are functions of the x and y coordinates. The splines used equally-spaced knots. Ten different models are fit to the data using a variety of covariates. The models are compared with each other using an analysis of deviance for nested models. Results: We found all covariates contributed significantly to the model. AIC and BIC were used to select 9 as the number of knots. Additionally, covariates have different effects such as increasing the speed limit would decrease traffic accident intensity by 0.9794 but increasing the number of lanes would result in an increase in the intensity of traffic accidents by 1.086. Conclusion: Our analysis shows that if other conditions are held fixed, the number of accidents actually decreases on roads with higher speed limits. The software we currently use allows our models to contain only spatial covariates and does not permit the use of temporal or space-time covariates. We would like to extend our models to include such covariates which would allow us to include weather conditions or the presence of special events (football games or concerts) as covariates.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.152-159
• /
• 2023

This study endeavors to enrich investment prospects in cryptocurrency by establishing a rationale for investment decisions. The primary objective involves evaluating the predictability of four prominent cryptocurrencies - Bitcoin, Ethereum, Litecoin, and EOS - and scrutinizing the efficacy of trading strategies developed based on the prediction model. To identify the most effective prediction model for each cryptocurrency annually, we employed three methodologies - AutoRegressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), and Prophet - representing traditional statistics and artificial intelligence. These methods were applied across diverse periods and time intervals. The result suggested that Prophet trained on the previous 28 days' price history at 15-minute intervals generally yielded the highest performance. The results were validated through a random selection of 100 days (20 target dates per year) spanning from January 1st, 2018, to December 31st, 2022. The trading strategies were formulated based on the optimal-performing prediction model, grounded in the simple principle of assigning greater weight to more predictable assets. When the forecasting model indicates an upward trend, it is recommended to acquire the cryptocurrency with the investment amount determined by its performance. Experimental results consistently demonstrated that the proposed trading strategy yields higher returns compared to an equal portfolio employing a buy-and-hold strategy. The cryptocurrency trading model introduced in this paper carries two significant implications. Firstly, it facilitates the evolution of cryptocurrencies from speculative assets to investment instruments. Secondly, it plays a crucial role in advancing deep learning-based investment strategies by providing sound evidence for portfolio allocation. This addresses the black box issue, a notable weakness in deep learning, offering increased transparency to the model.

• Journal of the Korean Society of Physical Medicine
• /
• v.18 no.4
• /
• pp.109-119
• /
• 2023

PURPOSE: The definition and scope of biofeedback are broad and lack a clear framework. Therefore, efforts are needed to clearly understand the exact range and definition of biofeedback based on the research and development conducted to date. Thus, the purpose of this study was to arrive at the definition and scope of biofeedback through a literature review and analysis of its application methods. METHODS: This study is a systematic literature review conducted to understand the various types and effects of biofeedback. International databases such as Google Scholar and PubMed were used. Domestic databases utilized for keyword searches included the Research Information Sharing Service (RISS) and the National Digital Science Library (NDSL). Quality assessment of the selected studies in the selection process was done using the Cochrane risk of bias, and the research was analyzed according to the population, intervention, control, and outcomes (PICO) format. RESULTS: Studies conducted between 2019 and 2021 were selected, with 4 papers falling under physiological classifications and 7 under biomechanical classifications. The quality assessment results showed that random sequence generation, allocation concealment, performance bias, and reporting bias were unclear. Detection bias was moderate, and attrition bias and other biases were low. Out of the 11 papers, 9 dealt with physical function outcomes, 5 with daily life activities, and 3 with mental functions. CONCLUSION: Physiological biofeedback tended to influence psychological factors more than physical functions, while biomechanical biofeedback tended to have a positive impact on physical functions.

• Journal of Veterinary Science
• /
• v.25 no.3
• /
• pp.41.1-41.12
• /
• 2024

Importance: Equines are indispensable in reducing the huge burden on children and women and income generation. On the other hand, minimal attention is given to improving their health and welfare. Objective: This study examined the prevalence and associated risk factors of helminth parasites of equine in the Gamo Gofa Zone. Methods: A cross-sectional study was employed from June 2019 to March 2020. The study districts and Kebeles were selected purposively based on agroecology whereas selection of study households and animals were performed based on simple random sampling techniques. Identification of nematode, trematode parasite ova and larvae of D. arnfieldi were done by floatation, sedimentation, and Baermann techniques respectively. Descriptive statistics and logistic regression was applied to estimate the prevalence and association of risk factors with helminth parasites. Results: The overall helminth parasite prevalence in the study area was 90.4%, 425/470 (95% [CI], 87.16-92.9). The prevalence of Strongyle, Fasciola, O. equi, P. equorum, D. arnfieldi, and mixed parasite infections were 65.1%, 21.7%, 17.4%, 34%, 34%, and 58.1%, respectively. Infections from Fasciola species and D. arnfieldi infection were four ([AOR], 4.4; 95% CI, 2-9.4) and two times (AOR, 2; 95% CI, 1.1-3.6) respectively more likely occur in donkeys than in mules. The occurrence of Strongyle species in midland agroecology was two times (AOR, 2.6; 95% CI, 1.4-4.7) more likely than lowland agroecology. Conclusions and Relevance: The present study identified diverse species of equine helminth parasites that necessitate urgent disease control and prevention measures.