• Information Systems Review
• /
• v.9 no.1
• /
• pp.85-103
• /
• 2007

The purpose of this study is to evaluate the performance of collaborative filtering recommender algorithms for better prediction accuracy of the customer's preference. The accuracy of customer's preference prediction is compared through the MAE of neighborhood based collaborative filtering algorithm and correspondence mean algorithm. It is analyzed by using MovieLens 1 Million dataset in order to experiment with the prediction accuracy of the algorithms. For similarity, weight used in both algorithms, commonly, Pearson's correlation coefficient and vector similarity which are used generally were utilized, and as a result of analysis, we show that the accuracy of the customer's preference prediction of correspondence mean algorithm is superior. Pearson's correlation coefficient and vector similarity used in two algorithms are calculated using the preference rating of two customers' co-rated movies, and it shows that similarity weight is overestimated, where the number of co-rated movies is small. Therefore, it is intended to increase the accuracy of customer's preference prediction through expanding the number of the existing co-rated movies.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.29 no.8
• /
• pp.640-647
• /
• 2018

This study analyzes the tracking accuracy(tracking errors) of fighter radar. Measurement error, detection failure, and radar cross section(RCS) fluctuation in radar measurements degrade the measurement quality and hence affect the tracking accuracy. Therefore, these radar measurement characteristics need to be considered when analyzing the tracking accuracy. In this paper, a method for analyzing the tracking accuracy is proposed; this method considers the detection error, detection probability, and RCS fluctuation. Results from experiments conducted with the proposed method show that the detection probability and RCS fluctuation affect tracking accuracy.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.3
• /
• pp.367-372
• /
• 2012

This paper presents a development of an analog type magnetic positioning system and its positioning accuracy improvement using fuzzy inference system. As the magnetic positioning system used on a magnet-gyro guidance system for AGV(automatic guided vehicle), it measures a position of magnet embedded in floor of the work place. The existing product of the magnetic positioning system is very expensive in Korea because it is being sold in a foreign country exclusively. Moreover, the positioning accuracy of the product is low because it uses digital type unipolar hall sensors. Hence, we developed the magnetic positioning system by ourselves and improved the positioning accuracy of the developed magnetic positioning system using fuzzy inference system. For experiment, we used the analog type magnetic positioning system which we have developed, and compared the performance of the proposed method with the performance of the existing positioning method for the magnetic positioning system. In experimental results, we verified that the proposed method improved the positioning accuracy of the magnetic positioning system.

• Journal of Korean Society of Transportation
• /
• v.33 no.1
• /
• pp.61-69
• /
• 2015

This study compares the forecasting accuracy of five econometric models on domestic total freight volume in South Korea. Applied five models are as follows: Ordinary Least Square model, Partial Adjustment model, Reduced Autoregressive Distributed Lag model, Vector Autoregressive model, Time Varying Parameter model. Estimating models and forecasting are carried out based on annual data of domestic freight volume and an index of industrial production during 1970~2011. 1-year, 3-year, and 5-year ahead forecasting performance of five models was compared using the recursive forecasting method. Additionally, two forecasting periods were set to compare forecasting accuracy according to the size of future volatility. As a result, the Time Varying Parameter model showed the best accuracy for forecasting periods having fluctuations, whereas the Vector Autoregressive model showed better performance for forecasting periods with gradual changes.

• Biomedical Science Letters
• /
• v.25 no.1
• /
• pp.99-106
• /
• 2019

Amyloid positron emission tomography (PET) allows early and accurate diagnosis in suspected cases of Alzheimer's disease (AD) and contributes to future treatment plans. In the present study, a method of implementing a diagnostic system to distinguish ${\beta}$-Amyloid ($A{\beta}$) positive from $A{\beta}$ negative with objectiveness and accuracy was proposed using a machine learning approach, such as the Principal Component Analysis (PCA) and Support Vector Machine (SVM). $^{18}F$-Florbetaben (FBB) brain PET images were arranged in control and patients (total n = 176) with mild cognitive impairment and AD. An SVM was used to classify the slices of registered PET image using PET template, and a system was created to diagnose patients comprehensively from the output of the trained model. To compare the per-slice classification, the PCA-SVM model observing the whole brain (WB) region showed the highest performance (accuracy 92.38, specificity 92.87, sensitivity 92.87), followed by SVM with gray matter masking (GMM) (accuracy 92.22, specificity 92.13, sensitivity 92.28) for $A{\beta}$ positivity. To compare according to per-subject classification, the PCA-SVM with WB also showed the highest performance (accuracy 89.21, specificity 71.67, sensitivity 98.28), followed by PCA-SVM with GMM (accuracy 85.80, specificity 61.67, sensitivity 98.28) for $A{\beta}$ positivity. When comparing the area under curve (AUC), PCA-SVM with WB was the highest for per-slice classifiers (0.992), and the models except for SVM with WM were highest for the per-subject classifier (1.000). We can classify $^{18}F$-Florbetaben amyloid brain PET image for $A{\beta}$ positivity using PCA-SVM model, with no additional effects on GMM.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.172-172
• /
• 2023

The use of low-cost IoT sensors for flow measurement in open channels has gained significant attention due to their potential to provide continuous and real-time data at a low cost. However, the accuracy and reliability of these sensors in real-world scenarios are not well understood. This study aims to compare the performance of low-cost IoT sensors in the laboratory and real-world conditions to evaluate their accuracy and reliability. Firstly, a low-cost IoT sensor was integrated with an IoT platform to acquire real-time flow rate data. The IoT sensors were calibrated in the laboratory environment to optimize their accuracy, including different types of low-cost IoT sensors (HC-SR04 ultrasonic sensor & YF-S201 sensor) using an open channel prototype. After calibration, the IoT sensors were then applied to a real-world case study in the Dorim-cheon stream, where they were compared to traditional flow measurement methods to evaluate their accuracy.The results showed that the low-cost IoT sensors provided accurate and reliable flow rate data under laboratory conditions, with an error range of less than 5%. However, when applied to the real-world case study, the accuracy of the IoT sensors decreased, which could be attributed to several factors such as the effects of water turbulence, sensor drift, and environmental factors. Overall, this study highlights the potential of low-cost IoT sensors for flow measurement in open channels and provides insights into their limitations and challenges in real-world scenarios.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.9
• /
• pp.9-23
• /
• 2024

In this study, we propose a method to improve the classification accuracy of body mass index (BMI) estimation techniques based on three-dimensional gait data. In previous studies on BMI estimation techniques, the classification accuracy was only about 60%. In this study, we identify the reasons for the low BMI classification accuracy. According to our analysis, the reason is the use of the undersampling technique to address the class imbalance problem in the gait dataset. We propose applying oversampling instead of undersampling to solve the class imbalance issue. We also demonstrate the usefulness of anthropometric and spatiotemporal features in gait data-based BMI estimation techniques. Previous studies evaluated the usefulness of anthropometric and spatiotemporal features in the presence of undersampling techniques and reported that their combined use leads to lower BMI estimation performance than when using either feature alone. However, our results show that using both features together and applying an oversampling technique achieves state-of-the-art performance with 92.92% accuracy in the BMI estimation problem.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.28 no.3
• /
• pp.329-336
• /
• 2010

This study deals with the measurement of reflectivity as well as the distance accuracy with Terrestrial Laser Scanner(TLS) using time of flight methods and near infrared wave length, for a variety of user-made targets. Especially, point clouds' reflection to several targets was measured with Gretag Macbeth il spectrophotometer in the office. And the distance accuracy in comparison to reference distance for TLS performance evaluation, was tested after scanning the user-made targets and measuring the inter-pillars distances over the precise EDM calibration baseline. The results of test was shown that except white resin objects, with approx. 10m and 170m inter-pillar distances, other targets achieved the distance accuracy of several millimeters(mm) with respect to standard distances. Future work should be concentrate on a few parameters influencing on the distance accuracy such as atmospheric correction, instrument correction, the additive constant or zero/index correction, etc.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.32 no.4
• /
• pp.43-52
• /
• 2004

In this paper, the performance of the KOMPSAT-1 orbit determination (OD) accuracy at the ground station was analyzed by using the flight data. The Bayesian least squares estimation was used for the orbit determination and the assessment of the orbit accuracy was evaluated based on orbit overlap comparisons. We also compared the result from OD using GPS navigation solutions with NORAD TLE and the result from OD using range data. Furthermore, the effect of observation type and OBT drift on the accuracy was investigated. As a consequence, It is shown that the OD accuracy using only GPS position data is on the order of 5m RMS (Root Mean Square) with 4 hrs arc overlap for the 30hr arc and the GPS velocity data is not proper as a observation for the OD due to its inferior quality. The significant deterioration of the accuracy due to the critical clock bias was not founded by means of the comparison of OD result from other observations.

• Imaging Science in Dentistry
• /
• v.52 no.2
• /
• pp.219-224
• /
• 2022

Purpose: This study aimed to evaluate the performance of transfer learning in a deep convolutional neural network for classifying implant fixtures. Materials and Methods: Periapical radiographs of implant fixtures obtained using the Superline (Dentium Co. Ltd., Seoul, Korea), TS III(Osstem Implant Co. Ltd., Seoul, Korea), and Bone Level Implant(Institut Straumann AG, Basel, Switzerland) systems were selected from patients who underwent dental implant treatment. All 355 implant fixtures comprised the total dataset and were annotated with the name of the system. The total dataset was split into a training dataset and a test dataset at a ratio of 8 to 2, respectively. YOLOv3 (You Only Look Once version 3, available at https://pjreddie.com/darknet/yolo/), a deep convolutional neural network that has been pretrained with a large image dataset of objects, was used to train the model to classify fixtures in periapical images, in a process called transfer learning. This network was trained with the training dataset for 100, 200, and 300 epochs. Using the test dataset, the performance of the network was evaluated in terms of sensitivity, specificity, and accuracy. Results: When YOLOv3 was trained for 200 epochs, the sensitivity, specificity, accuracy, and confidence score were the highest for all systems, with overall results of 94.4%, 97.9%, 96.7%, and 0.75, respectively. The network showed the best performance in classifying Bone Level Implant fixtures, with 100.0% sensitivity, specificity, and accuracy. Conclusion: Through transfer learning, high performance could be achieved with YOLOv3, even using a small amount of data.