• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.6
• /
• pp.2297-2301
• /
• 2015

Background: Despite widely adopted standard methods for follow-up including cystoscopy plus cytology, recurrence rates of non muscle-invasive bladder cancer (NMIBC) have not improved over the past decades, still ranging from 60% through 70%. Hence, widely acceptable surveillance strategies with excellent sensitivity are needed. Early recurrence has led to the development of a novel cystoscopy technique utilizing photodynamic diagnosis (PDD). Although, no studies have evaluated the efficacy of PDD for patients of MIBC, BCG failure or 2nd-transurethelial resection (TUR). Materials and Methods: The present study was performed from October 2012 through May 2013. IRB approved 25 patients initially underwent a cystoscopy examination of white light and blue light followed by the resection of tumors identified. Resections were performed from bladder mucosa areas considered suspicious at PDD, along with PDD negative normal bladder mucosa area resected by random biopsy. Specimens were divided into two groups, PDD positive and negative. Primary endpoints were sensitivity and specificity. Results: A total of 147 specimens extracted from 25 patients were included in the analysis. Some 45 out of 92 PDD-positive specimens were confirmed to have bladder cancer, and 51 out of PDD-negative 55 specimens were confirmed to be cancer negative. The sensitivity of PDD was 91.8% (45/49) and specificity was 52.0% (51/98). The sensitivity:specificity was 89.5% (17/19) : 47.6% (30/63) in 12 2nd-TUR patients, 90.5% (19/21) : 61.1% (11/18) in seven MIBC patients, and 95.0% (19/20) : 48.5% (16/33) in eight failed BCG cases. Conclusions: PDD-TURBT has high sensitivity to diagnose BC even for 2nd-TUR, MIBC or BCG failure cases.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.2
• /
• pp.163-172
• /
• 2005

When tracking a human face in the moving pictures with complex background under irregular lighting conditions, the detected face can be larger including background or smaller including only a part of the face. Even background can be detected as a face area. To solve these problems, this paper proposes a new face tracking method using a block difference image and a Kalman estimator. The block difference image allows us to detect even a small motion of a human and the face area is selected using the skin color inside the detected motion area. If the pixels with skin color inside the detected motion area, the boundary of the area is represented by a code sequence using the 8-neighbor window and the head area is detected analysing this code. The pixels in the head area is segmented by colors and the region most similar with the skin color is considered as a face area. The detected face area is represented by a rectangle including the area and its four vertices are used as the states of the Kalman estimator to trace the motion of the face area. It is proved by the experiments that the proposed method increases the accuracy of face detection and reduces the fare detection time significantly.

• Pediatric Infection and Vaccine
• /
• v.17 no.2
• /
• pp.130-136
• /
• 2010

Purpose : The purpose of this study is to identify the viral etiology of acute respiratory illnesses and to determine epidemiology in outpatients in Busan, Korea. Methods : We collected nasal wash samples from 990 patients who visited the hospital for acute respiratory illnesses between January 2007 and December 2008. Extracted DNA or RNA from specimens was used for viral detection by an RT-PCR method. Results : Of a total of 990 samples, viruses were detected in 351 cases (35.5%). The ratio of male to female was 1.6:1 and 93.7% were less than 5 years old. Rhinovirus was detected year-round in 202 cases (57.5%), respiratory syncytial virus from October to March in 57 cases (16.2%), adenovirus year-round in 37 cases (10.5%), influenza virus from December to April in 21 cases (6%), bocavirus from January to August in 15 cases (4.3%), parainfluenza virus from April to July in 9 cases (2.6%), coronavirus from January to July in 7 cases (2%), and enterovirus from June to September in 3 cases (0.9%). Conclusion : We identified the etiology and epidemiology of viruses that caused the acute respiratory diseases that were prevalent in Busan, 2007-2008. Further surveillance will be necessary.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.12
• /
• pp.201-207
• /
• 2019

In this paper, we propose an effective method to block illegal gambling advertisement on social media. With the increase of smartphone and internet usage, users can easily access various information while sharing information such as text and video with a large number of others. In addition, illegal sports gambling advertisements are also continue to be transmitted on SNS. To avoid most surveillance networks, users are easily exposed to illegal sports gambling advertisement images by including phrases in the images that indicate illegal sports gambling advertisements. In order to cope with these problems, we proposed a method to actively block illegal sports gambling advertisements in a way different from the conventional passive methods. In this paper, we select words frequently used for illegal sports gambling, classifies them into three groups according to their importance, calculate WF for each word using weighted formula by degree of relevance and frequency, and then sum the WF of the words in the image. Blocking, warning, and passing were determined by cv, the total of WF. Experimenting with the proposed method, 193 out of 200 experimental images were correctly judged with 96.5% accuracy, and even though 7 images were illegal sports gambling advertisements. Further research is needed to block 3.5% of illegal sports betting ads that cannot be blocked in the future.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.10
• /
• pp.1840-1848
• /
• 2017

Linear wireless sensor networks typically construct a network topology with a high reliability through sequential 1:1 mapping among sensor nodes, so that they are used in various surveillance applications of major national infrastructures. Most existing techniques for identifying sensor nodes in those networks are using GPS, AOA, and RSSI mechanisms. However, GPS or AOA based node identification techniques affect the size or production cost of the nodes so that it is not easy to construct practical sensor networks. RSSI based techniques may have a high deviation regrading location identification according to propagation environments and equipment quality so that complexity of error correction algorithm may increase. We propose a timestamps based sequential localization algorithm that uses transmit and receive timestamps in a message between sensor nodes without using GPS, AOA, and RSSI techniques. The algorithms for distance measurement between each node are expected to measure distance within up to 1 meter in case of an crystal oscillator of 300MHz or more.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.657-664
• /
• 2003

Reliable tracking of moving humans is essential to motion estimation, video surveillance and human-computer interface. This paper presents a new approach to human motion tracking that combines appearance-based and model-based techniques. Monocular color video is processed at both pixel level and object level. At the pixel level, a Gaussian mixture model is used to train and classily individual pixel colors. At the object level, a 3D human body model projected on a 2D image plane is used to fit the image data. Our method does not use inverse kinematics due to the singularity problem. While many others use stochastic sampling for model-based motion tracking, our method is purely dependent on nonlinear programming. We convert the human motion tracking problem into a nonlinear programming problem. A cost function for parameter optimization is used to estimate the degree of the overlapping between the foreground input image silhouette and a projected 3D model body silhouette. The overlapping is computed using computational geometry by converting a set of pixels from the image domain to a polygon in the real projection plane domain. Our method is used to recognize various human motions. Motion tracking results from video sequences are very encouraging.

• Korean Journal of Remote Sensing
• /
• v.34 no.2_2
• /
• pp.327-338
• /
• 2018

The possibility of ship detection monitoring at operational level using KOMPSAT-5 Synthetic Aperture Radar (SAR) and Automatic Identification System (AIS) data is investigated. For the analysis, the KOMPSAT-5 SLC images, which are collected from the west coast of Shinjin port and the northern coast of Jeju port are used along with portable AIS data from near the coast. The ship detection algorithm based on HVAS (Human Visual Attention System) was applied, which has significant advantages in terms of detection speed and accuracy compared to the commonly used CFAR (Constant False Alarm Rate). As a result of the integrated analysis, the ship detection from KOMPSAT-5 and AIS were generally consistent except for small vessels. Some ships detected in KOMPSAT-5 but not in AIS are due to the data absence from AIS, while it is clearly visible in KOMPSAT-5. Meanwhile, SAR imagery also has some false alarms due to ship wakes, ghost effect, and DEM error (or satellite orbit error) during object masking in land. Improving the developed ship detection algorithm and collecting reliable AIS data will contribute for building wide integrated surveillance system of marine territory at operational level.

• Journal of Digital Convergence
• /
• v.15 no.2
• /
• pp.173-181
• /
• 2017

In this paper, we have studied tracking as a training stage of considering the position and the scale of a person given its previous position, scale, as well as next and forward image fraction. Unlike other learning methods, CNN is thereby learning combines both time and spatial features from the image for the two consecutive frames. We introduce multiple path ways in CNN to better fuse local and global information. A creative shift-variant CNN architecture is designed so as to alleviate the drift problem when the distracting objects are similar to the target in cluttered environment. Furthermore, we employ CNNs to estimate the scale through the accurate localization of some key points. These techniques are object-independent so that the proposed method can be applied to track other types of object. The capability of the tracker of handling complex situations is demonstrated in many testing sequences. The accuracy of the SVM classifier using the features learnt by the CNN is equivalent to the accuracy of the CNN. This fact confirms the importance of automatically optimized features. However, the computation time for the classification of a person using the convolutional neural network classifier is less than approximately 1/40 of the SVM computation time, regardless of the type of the used features.

• Journal of Preventive Medicine and Public Health
• /
• v.27 no.3 s.47
• /
• pp.547-556
• /
• 1994

In order to identify the necessary information of biochemical Indices for renal effect of lead for the early detection in medical surveillance of lead worker, the reference values of urinary N-acetyl-$\beta$-D-glucosaminidase (NAG) activities were studied with 205 office workers in one industrial complex area who were not exposed to lead occupationally. While study variables selected for lead exposure were blood lead (PbB), blood zinc protoporphyrin(ZPP) and $\delta$-aminolevulinic acid (DALA) in urine, those for renal effect were urinary N-acetyl-$\beta$-D-glucosaminidase (NAG), blood urea nitrogen (BUN), serum creatinine(Cr), serum uric acid (Ua), and urinary total protein(U-TP). The results obtained were as follows: 1. The mean values of blood lead, ZPP and DALA in all subjects were $14.39{\pm}4.02{\mu}g/dl,\;21.61{\pm}8.00{\mu}g/dl,\;and\;2.73{\pm}0.90mg/l$ respectively. 2. The mean value of urinary NAG activities in all subjects was $3.51{\pm}2.01U/l$. The mean value of urinary NAG activities, which calculated from NAG activities divided by urinary creatinine concentration (CNAG), was $5.42{\pm}5.53U/g$ creatinine and log-arithmic normal distributed. 3. The reference value of urinary NAG activity was 12.06 U/g creatinine(95% CU=10.57-14.76 U/g creatinine). 4. Logarithmic CNAG(r=0.781 p<0.0l), U-TP(r=0.670 p<0.01) and ZPP(r=0.172 p<0.05) showed statistically significant correlation with CNAG.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.2
• /
• pp.133-140
• /
• 2017

In this paper, we has proposed an automatic vehicle monitoring system based on computer vision technology. The real-time display system has displayed a system that can be performed in automatic monitoring and control while meeting the essential requirements of ITS. Another advantage has that for a powerful vehicle tracking, the main obstacle handing system, which has the shadow tracking of moving objects. In order to obtain all kinds of information from the tracked vehicle image, the vehicle must be clearly displayed on the surveillance screen. Over time, it's necessary to precisely control the vehicle, and a three-dimensional model-based approach has been also necessary. In general, each type of vehicle has represented by the skeleton of the object or wire frame model, and the trajectory of the vehicle can be measured with high precision in a 3D-based manner even if the system has not running in real time. In this paper, we has applied on segmentation method to vehicle, background, and shadow. The validity of the low level vehicle control tracker was also detected through speed tracking of the speeding car. In conclusion, we intended to improve the improved tracking method in the tracking control system and to develop the highway monitoring and control system.