• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.1
• /
• pp.305-326
• /
• 2019

Discriminative correlation filter (DCF) based tracking algorithms have recently shown impressive performance on benchmark datasets. However, amount of recent researches are vulnerable to heavy occlusions, irregular deformations and so on. In this paper, we intend to solve these problems and handle the contradiction between accuracy and real-time in the framework of tracking-by-detection. Firstly, we propose an innovative strategy to combine the template and color-based models instead of a simple linear superposition and rely on the strengths of both to promote the accuracy. Secondly, to enhance the discriminative power of the learned template model, the spatial regularization is introduced in the learning stage to penalize the objective boundary information corresponding to features in the background. Thirdly, we utilize a discriminative multi-scale estimate method to solve the problem of scale variations. Finally, we research strategies to limit the computational complexity of our tracker. Abundant experiments demonstrate that our tracker performs superiorly against several advanced algorithms on both the OTB2013 and OTB2015 datasets while maintaining the high frame rates.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.9
• /
• pp.4461-4475
• /
• 2017

Recently, introduction of the hospital information system has remarkably improved the efficiency of health care services within hospitals. Due to improvement of the hospital information system, the issue of integration of medical information has emerged, and attempts to achieve it have been made. However, as a preceding step for integration of medical information, the problem of searching the same patient should be solved first, and studies on patient identification algorithm are required. As a typical case, similarity can be calculated through MPI (Master Patient Index) module, by comparing various fields such as patient's basic information and treatment information, etc. but it has many problems including the language system not suitable to Korean, estimation of an optimal weight by field, etc. This paper proposes a method searching the same patient using MRI information besides patient's field information as a supplementary method to increase the accuracy of matching algorithm such as MPI, etc. Unlike existing methods only using image information, upon identifying a patient, a highest weight was given to physical information of medical image and set as an unchangeable unique value, and as a result a high accuracy was detected. We aim to use the similarity measurement result as secondary measures in identifying a patient in the future.

• Journal of Korean Society for Geospatial Information Science
• /
• v.24 no.2
• /
• pp.37-46
• /
• 2016

The difference between definition time of GPS (Global Positioning System) position data and actual display time of car positions on a map could reduce the accuracy of car positions displayed in PND (Portable Navigation Device)-type CNS (Car Navigation System). Due to the time difference, the position of the car displayed on the map is not its current position, so an improved method to fix these problems is required. It is expected that a method that uses predicted future positionsto compensate for the delay caused by processing and display of the received GPS signals could mitigate these problems. Therefore, in this study an analysis was conducted to correct late processing problems of map positions by mapmatching using a Kalman filter with only GPS position data and a RRF (Road Reduction Filter) technique in a light-weight CNS. The effects on routing services are examined by analyzing differences that are decomposed into along and across the road elements relative to the direction of advancing car. The results indicate that it is possible to improve the positional accuracy in the along-the-road direction of a light-weight CNS device that uses only GPS position data, by applying a Kalman filter and RRF.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1787-1790
• /
• 2005

We have developed satellite devices for fine attitude control of the Science & Technology Satellite-2 (STSAT-2) scheduled to be launched in 2007. The analog sun sensors which have been continuously developed since the 1990s are not adequate for satellites which require fine attitude control system. From the mission requirements of STSAT-2, a compact, fast and fine digital sensor was proposed. The test of the fine attitude determination for the pitch and roll axis, though the main mission of STSAT-2, will be performed by the newly developed FDSS. The FDSS use a CMOS image sensor and has an accuracy of less than 0.01degrees, an update rate of 20Hz and a weight of less than 800g. A pinhole-type aperture is substituted for the optical lens to minimize the weight while maintaining sensor accuracy by a rigorous centroid algorithm. The target process speed is obtained by utilizing the Field Programmable Gate Array (FPGA) in acquiring images from the CMOS sensor, and storing and processing the data. This paper also describes the analysis of the optical performance for the proper aperture selection and the most effective centroid algorithm.

• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.9 s.186
• /
• pp.61-67
• /
• 2006

Sandwich structures, which are composed of a thick core between two faces, are commonly used in many engineering applications because they combine high stiffness and strength with low weight. Accordingly, the usage of sandwich structure is very widely applied to the aircraft, the automobile and marine industry, etc., because of these advantages. In this paper, we have investigated the buckling protection of an inner structure plate and the useful corrugated configuration for contact, and the fabrication method of the inner structure plate for large area using the continuous molding process. Also, we have guaranteed the accuracy of the molding process through the micro corrugated mold fabrication and secured the accuracy and analyzed aspect properties of the inner structure plate fabricated for a large area using the partial mold process. We have compared molding simulation according to the aspect thickness of the corrugated configuration with the molding experiment results.

• Korean Journal of Biological Psychiatry
• /
• v.19 no.4
• /
• pp.211-218
• /
• 2012

Objectives Body image distortion is found in eating disorder and obesity and there are some evidence that schizophrenia is associated with body image distortion. This study sought to find whether schizophrenic patients report more body image distortion than healthy individuals and whether it is related with symptomatology. Methods A total of 88 inpatients with schizophrenia and 88 healthy controls were recruited. Weight, height, and body image accuracy were assessed in all participants, and assessment of mood, psychotic symptom severity and self-esteem, and personal and social performance scale were conducted. Results The patients with schizophrenia had higher Body Mass Index (p < 0. 001) and underestimated their body size more than controls (26.14% vs. 5.13%, p < 0.001). Multiple regression analysis showed that lower depressive symptoms and higher scores of general psychopathology predicted underestimation of body size. Conclusion Weight gain and metabolic syndrome are common adverse events of pharmacological treatment of schizophrenia. Thus, underestimation of body size among patients with schizophrenia may interfere with effort to lose weight or seek weight reduction programs. Clinicians need to consider possible unterestimation of underestimation of body size in patients whose general symptomatology is severe.

• Journal of Sensor Science and Technology
• /
• v.16 no.6
• /
• pp.413-418
• /
• 2007

Uroflowmetry is of great convenience to diagnose benign prostate hypertrophy common in aged men. The urinary flow rate is obtained by weight measurement using load cell, however, sensitive to impact noise. An alternative technique was recently proposed to measure hydraulic pressure instead of weight and demonstrated to introduce significantly reduced noise. In this paper, we described the measured diagnostic parameters between the weight and pressure measuring techniques in 10 normal men. The weight and pressure signals were simultaneously acquired during urination, converted into urine volumes, then differentiated to obtain flow rate signals, which showed very similar waveforms. Diagnostic parameters evaluated by pressure measuring technique were well correlated with the standard weight measuring technique (correlation coefficient > 0.99). Therefore, the new uroflowmetry based on hydraulic pressure measurement can provide accurate diagnostic parameters, which would be clinically valid.

• Journal of the Korean Society for Precision Engineering
• /
• v.27 no.9
• /
• pp.86-93
• /
• 2010

Any relative deformation between the cutting tool and the workpiece at the machining point, results directly in form and dimensional errors. The source of relative deformations between the cutting tool and the workpiece at the contact point may be due to thermal, weight, and cutting forces. Thermal and weight deformations can be measured at various positions of the machine tool and stored in the compensation registers of the CNC unit and compensated the errors during machining. However, the cutting force induced errors are difficult to compensate because estimation of cutting forces are difficult. To minimize the error induced by cutting forces, it is important to improve the machining accuracy. This paper presents the pre-calculated method of form error induced by cutting forces. In order to estimate cutting forces, Isakov method is used and the method is verified by comparing with the experimental results. In order to this, a cylindrical-outer-diameter turning experiments are carried out according to cutting conditions.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.127-133
• /
• 2022

Many manufacturers applying third party logistics (3PLs) have some challenges to increase their logistics efficiency. This study introduces an effort to estimate the weight of the delivery trucks provided by 3PL providers, which allows the manufacturer to package and load products in trailers in advance to reduce delivery time. The accuracy of the weigh estimation is more important due to the total weight regulation. This study uses not only the data from the company but also many general prediction variables such as weather, oil prices and population of destinations. In addition, operational statistics variables are developed to indicate the availabilities of the trucks in a specific weight category for each 3PL provider. The prediction model using XGBoost regressor and permutation feature importance method provides highly acceptable performance with MAPE of 2.785% and shows the effectiveness of the developed operational statistics variables.

• Korean Journal of Remote Sensing
• /
• v.38 no.4
• /
• pp.395-409
• /
• 2022

The purpose of this study is to evaluate the classification performance and applicability when land cover datasets constructed for AI training are cross validation to other areas. For study areas, Gyeongsang-do and Jeolla-do in South Korea were selected as cross validation areas, and training datasets were obtained from AI-Hub. The obtained datasets were applied to the U-Net algorithm, a semantic segmentation algorithm, for each region, and the accuracy was evaluated by applying them to the same and other test areas. There was a difference of about 13-15% in overall classification accuracy between the same and other areas. For rice field, fields and buildings, higher accuracy was shown in the Jeolla-do test areas. For roads, higher accuracy was shown in the Gyeongsang-do test areas. In terms of the difference in accuracy by weight, the result of applying the weights of Gyeongsang-do showed high accuracy for forests, while that of applying the weights of Jeolla-do showed high accuracy for dry fields. The result of land cover classification, it was found that there is a difference in classification performance of existing datasets depending on area. When constructing land cover map for AI training, it is expected that higher quality datasets can be constructed by reflecting the characteristics of various areas. This study is highly scalable from two perspectives. First, it is to apply satellite images to AI study and to the field of land cover. Second, it is expanded based on satellite images and it is possible to use a large scale area and difficult to access.