• Proceedings of the Korean Nuclear Society Conference
• /
• 2005.10a
• /
• pp.632-633
• /
• 2005

• Journal of the Ergonomics Society of Korea
• /
• v.12 no.1
• /
• pp.17-24
• /
• 1993

Today, rapid development and timeliness of introducing a new product be- comes a more influencing factor of determing its competitive power due to a shortened product cycle, while rapid improvement of manufacturing technology makes product design and manufacturing fuse together. This implies that prod- uct usability evaluation and improvement starts right from its design phase, resulting in less development time and cost. To make this possible, proper as- sessment of human reach is one of essential functions for ergonomic product us- ability evaluation, specifically in the platform of computer-aided ergonomic evaluation models or any CAD system with a built-in man model. In this study, an analytic reach prediction algorithm ensuring the posture that human naturally takes, is presented by employing the methods developed for robot kinematics. Among robot kinematic methods for solving the multi-link system, the resolved motion method was found to be effective to solve human reach as a redundant manipulator model. Also, the joint range availability was used as a performance fonction to guarantee human naturalness. The result is expected to be directly applicable to product usability evaluations.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.6
• /
• pp.323-330
• /
• 2021

Visual object tracking is a challenging area of study in the field of computer vision due to many difficult problems, including a fast variation of target shape, occlusion, and arbitrary ground truth object designation. In this paper, we focus on the reinforced feature of the dynamic search area to get better performance than conventional discriminative model prediction trackers on the condition when the accuracy deteriorates since low feature discrimination. We propose a reinforced input feature method shown like the spotlight effect on the dynamic search area of the target tracking. This method can be used to improve performances for deep learning based discriminative model prediction tracker, also various types of trackers which are used to infer the center of the target based on the visual object tracking. The proposed method shows the improved tracking performance than the baseline trackers, achieving a relative gain of 38% quantitative improvement from 0.433 to 0.601 F-score at the visual object tracking evaluation.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.136-136
• /
• 2022

This study investigates the possibility of coupling empirical mode decomposition (EMD) for runoff prediction from machine learning (ML) models. Here, support vector regression (SVR) and convolutional neural network (CNN) were considered for ML algorithms. Precipitation (P), minimum temperature (Tmin), maximum temperature (Tmax) and their intrinsic mode functions (IMF) values were used for input variables at a monthly scale from Jan. 1973 to Dec. 2020 in the Grand river basin, Canada. The support vector machine-recursive feature elimination (SVM-RFE) technique was applied for finding the best combination of predictors among input variables. The results show that the proposed method outperformed the individual performance of SVR and CNN during the training and testing periods in the study area. According to the correlation coefficient (R), the EMD-SVR model outperformed the EMD-CNN model in both training and testing even though the CNN indicated a better performance than the SVR before using IMF values. The EMD-SVR model showed higher improvement in R value (38.7%) than that from the EMD-CNN model (7.1%). It should be noted that the coupled models of EMD-SVR and EMD-CNN represented much higher accuracy in runoff prediction with respect to the considered evaluation indicators, including root mean square error (RMSE) and R values.

• Atmosphere
• /
• v.31 no.1
• /
• pp.73-83
• /
• 2021

Numerical weather prediction (NWP) models play an essential role in predicting weather factors, but using them is challenging due to various factors. To overcome the difficulties of NWP models, deep learning models have been deployed in weather forecasting by several recent studies. This study adapts long short-term memory (LSTM), which demonstrates remarkable performance in time-series prediction. The combination of LSTM model input of meteorological features and activation functions have a significant impact on the performance therefore, the results from 5 combinations of input features and 4 activation functions are analyzed in 9 Automated Surface Observing System (ASOS) stations corresponding to cities/islands/mountains. The optimized LSTM model produces better performance within eight forecast hours than Local Data Assimilation and Prediction System (LDAPS) operated by Korean meteorological administration. Therefore, this study illustrates that this LSTM model can be usefully applied to very short-term weather forecasting, and further studies about CNN-LSTM model with 2-D spatial convolution neural network (CNN) coupled in LSTM are required for improvement.

• The KIPS Transactions:PartA
• /
• v.14A no.6
• /
• pp.357-362
• /
• 2007

In distributed systems like cluster systems, in order to get more performance improvement, the initial task placement system precisely estimates and correctly assigns the resource requirement by the process. The resource-based initial job placement scheme needs the prediction of resource usage of a task in order to fit it to the most suitable hosts. However, the wrong prediction of resource usage causes serious performance degradation in dynamic load balancing systems. Therefore, in this paper, to resolve the problem due to the wrong prediction, we propose a new load metric. By the new load metric, the resource-based initial job placement scheme can work without priori knowledge about the type of process. Simulation results show that the dynamic load balancing system using the proposed approach achieves shorter execution times than the conventional approaches.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.41 no.3
• /
• pp.222-226
• /
• 2005

A series of model tests carried out at the CWC of WJFEL for the purpose of prediction of resistance for the performance and improvement of resistance by attaching appendage for the ship of 50 knots class planing hull. The resistance performance evaluation has been carried out for the bare hull and for the appendage hull with two different depth of vertical type wedges. In the bare model test, trim and sinkage is calculated for the planing hull and the resistance is calculated. For minimizing the resistance, wedge appendage is attached and tested. Analysis and tests shows that for a 12.5mm wedge, resistance is minimum and overall power tallied to 5636ps.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.11
• /
• pp.310-318
• /
• 2018

Recently, the importance of big data analysis is increasing as a large amount of data is generated by various devices connected to the Internet with the advent of Internet of Things (IoT). Especially, it is necessary to analyze various large-scale IoT streaming sensor data generated in real time and provide various services through new meaningful prediction. This paper proposes a real-time indoor PM10 concentration prediction LSTM model based on streaming data generated from IoT sensor using AWS. We also construct a real-time indoor PM10 concentration prediction service based on the proposed model. Data used in the paper is streaming data collected from the PM10 IoT sensor for 24 hours. This time series data is converted into sequence data consisting of 30 consecutive values from time series data for use as input data of LSTM. The LSTM model is learned through a sliding window process of moving to the immediately adjacent dataset. In order to improve the performance of the model, incremental learning method is applied to the streaming data collected every 24 hours. The linear regression and recurrent neural networks (RNN) models are compared to evaluate the performance of LSTM model. Experimental results show that the proposed LSTM prediction model has 700% improvement over linear regression and 140% improvement over RNN model for its performance level.

• Korean Journal of Poultry Science
• /
• v.22 no.2
• /
• pp.97-104
• /
• 1995

Recently, DNA fingerprinting has been utilized as the most powerful tool for genetic analysis and improvement of poultry. This technique enables us to solve several problems of poultry breeding ; traits of low heritability, difficulty in keeping the performance records, measuring in late of life, and sex limited traits. Application of DNA fingerprinting is chiefly focused to individual and population identification, evolution force, quantitative trait marker, introgression of new gene, and prediction of heterosis. Thus, research work on DNA fingerprinting will he accelerated to analyze genetic components exactly and improve the performance of poultry.

• Journal of the Korean Data and Information Science Society
• /
• v.14 no.3
• /
• pp.441-450
• /
• 2003

Collaborative filtering is one of the most widely used methodologies for recommendation system. Collaborative filtering is based on a data matrix of each customer's preferences and frequently, there exits missing data problem. We introduced two imputation approach (multiple imputation via Markov Chain Monte Carlo method and multiple imputation via bootstrap method) to improve the prediction performance of collaborative filtering and evaluated the performance using EachMovie data.