• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.9
• /
• pp.361-368
• /
• 2014

The LPR(License plate recognition) system has been developed to efficient control for complex traffic environment and currently be used in many places. However, because of light, noise, background changes, environmental changes, damaged plate, it only works limited environment, so it is difficult to use in real-time. This paper presents a heuristic segmentation algorithm for robust to noise and illumination changes and introduce a real-time license plate recognition system using it. In first step, We detect the plate utilized Haar-like feature and Adaboost. This method is possible to rapid detection used integral image and cascade structure. Second step, we determine the type of license plate with adaptive histogram equalization, bilateral filtering for denoise and segment accurate character based on adaptive threshold, pixel projection and associated with the prior knowledge. The last step is character recognition that used histogram of oriented gradients (HOG) and multi-layer perceptron(MLP) for number recognition and support vector machine(SVM) for number and Korean character classifier respectively. The experimental results show license plate detection rate of 94.29%, license plate false alarm rate of 2.94%. In character segmentation method, character hit rate is 97.23% and character false alarm rate is 1.37%. And in character recognition, the average character recognition rate is 98.38%. Total average running time in our proposed method is 140ms. It is possible to be real-time system with efficiency and robustness.

• The Journal of Internal Korean Medicine
• /
• v.22 no.3
• /
• pp.285-290
• /
• 2001

Purpose : Impaired glucose tolerance (IGT) was standardized in 1979 by the National Diabetes Data Group and the World Health Organization as a risk factor for type 2 diabetes, replacing groups such as 'borderline' and 'chemical' diabetes. The main clinical significance of IGT is as a risk factor for type 2 diabetes and as a risk factor for cardiovascular disease and as a component of the metabolic syndrome. In 1997 the American Diabetes Association(ADA) was proposed the new classification and diagnostic criteria for diabetes, which is strict with the diagnostic baseline of Diabetes from 140mg/dl to 126mg/dl. And it's main purpose is to prevent chronic complications by early diagnosis and treatments. In the oriental medicine, Supungsunkihwan has been used in treatments of Diabetes including IGT & NIDDM, however there is not enough studies about the its objective hypoglycemic effect. so in order to investigate whether there is hypoglycemic effect of Supungsunkihwan, clinical studies were performed with IGT and mild NIDDM patients. Methods : Prior to the study, fasting blood sugar(FBS) and postprandial 2hrs(PP2hrs) glucose were checked. In addition, ECG, cholesterol, TG, HbA1c levels were measured, and the dinical characteristics of patients that can be influence to the blood sugar level such as age, gender, rest type, diet type were surveyed. Supungsukihwan was administered for 7 days, and FBS & PP2hrs were measured again after the therapy. Result : PP2hrs glucose levels were decreased by the administration of Supungsunkihwan. And It's hypoglycemic effects has the correlation with age. That is, the more age increase, the more hypoglycemic effect decrease. Conclusion : Supungsukihwan has hypoglycmic effects on IGT & mild NIDDM patients and it is more effective when administrated to young patients relatively.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.10
• /
• pp.713-722
• /
• 2013

This paper proposes a method of using depth information to detect the hand region in real-time based on the cascade method. In order to ensure stable and speedy detection of the hand region even under conditions of lighting changes in the test environment, this study uses only features based on depth information, and proposes a method of detecting the hand region by means of a classifier that uses boosting and cascading methods. First, in order to extract features using only depth information, we calculate the difference between the depth value at the center of the input image and the average of depth value within the segmented block, and to ensure that hand regions of all sizes will be detected, we use the central depth value and the second order linear model to predict the size of the hand region. The cascade method is applied to implement training and recognition by extracting features from the hand region. The classifier proposed in this paper maintains accuracy and enhances speed by composing each stage into a single weak classifier and obtaining the threshold value that satisfies the detection rate while exhibiting the lowest error rate to perform over-fitting training. The trained classifier is used to classify the hand region, and detects the final hand region in the final merger stage. Lastly, to verify performance, we perform quantitative and qualitative comparative analyses with various conventional AdaBoost algorithms to confirm the efficiency of the hand region detection algorithm proposed in this paper.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.2
• /
• pp.43-57
• /
• 2021

The Forward Collision Warning, a representative technology of the Advanced Driver Assistance Systems, was selected as the target technology. The cognitive response time, deceleration, and impact were selected as the measures of effectiveness. And the amount of change with and without the Forward Collision Warning was measured. The experimental scenarios included a sudden stop event (1) of the vehicle in front of the driver and an event (2) in which the vehicle intervened in the next lane. All experiments were divided into day and night. As a result of the analysis, response time and the deceleration rate decreased when the forward collision warning system was installed. It was analyzed that the driver's risk situation could be detected quickly and the number of front-end collisions could be reduced as a result. Reflecting the driver's operating habits and diversifying the experimental scenarios will increase the installation effectiveness of ADAS and be used to estimate the effectiveness of other technologies.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.11
• /
• pp.550-560
• /
• 2018

Many countries have provided support for research and development and implemented policies for Advanced Driver Assistance Systems (ADAS) for enhancing the safety of vehicles. With such efforts, the toll of casualties due to traffic accidents has decreased gradually. Korea has exhibited the lowest toll of casualties due to traffic accidents and is ranked 32nd in mortality among the 35 OECD members. Traffic accidents typically fall into three categories depending on the cause of the accident: vehicle to vehicle (V2V), vehicle to pedestrian (V2P), and vehicle independent. Most accidents are caused by drivers' mistakes in recognition, judgment, or operation. ADAS has been proposed to prevent and reduce accidents from such human errors. Moreover, the global automobile industry has recently been developing various safety measures, but on-road tests are still limited and contain various risks. Therefore, this study investigated the international standards for evaluation tests with regard to the assessment techniques in braking capability to cope with the limitations of on-road tests. A theoretical formula for braking force and a control algorithm are proposed, which were validated by comparing the results with those from an on-road test. These results verified the braking force depending on the functions of ADAS. The risks of on-road tests can be reduced because the proposed theoretical formula allows a prediction of the tendencies.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.1
• /
• pp.174-192
• /
• 2021

The LIDAR sensor, which provides higher cognitive performance than cameras and radar, is difficult to apply to ADAS or autonomous driving because of its high price. On the other hand, as the price is decreasing rapidly, expectations are rising to improve existing autonomous driving functions by taking advantage of the LIDAR sensor. In level 3 autonomous vehicles, when a dangerous situation in the cognitive module occurs due to a sensor defect or sensor limit, the driver must take control of the vehicle for manual driving. If the driver does not respond to the request, the system must automatically kick in and implement a minimum risk maneuver to maintain the risk within a tolerable level. In this study, based on this background, a LIDAR-based LKS MRM algorithm was developed for the case when the normal operation of LKS was not possible due to troubles in the cognitive system. From point cloud data collected by LIDAR, the algorithm generates the trajectory of the vehicle in front through object clustering and converts it to the target waypoints of its own. Hence, if the camera-based LKS is not operating normally, LIDAR-based path tracking control is performed as MRM. The HAZOP method was used to identify the risk sources in the LKS cognitive systems. B, and based on this, test scenarios were derived and used in the validation process by simulation. The simulation results indicated that the LIDAR-based LKS MRM algorithm of this study prevents lane departure in dangerous situations caused by various problems or difficulties in the LKS cognitive systems and could prevent possible traffic accidents.

• Tuberculosis and Respiratory Diseases
• /
• v.62 no.3
• /
• pp.184-191
• /
• 2007

Background: For the diagnosis of pleural tuberculosis, polymerase chain reaction (PCR) of pleural effusion specimens has shown very low sensitivity, which might be due to the small number of bacilli in the samples. The purpose of this investigation is to determine whether the sensitivity of PCR testing can be improved when increasing the amount of pleural effusion specimens. Methods: We prospectively analyzed pleural effusion specimens obtained from 53 patients for whom the exclusion of the possibility of tuberculous pleural effusion was necessary. We performed Mycobacterium tuberculosis PCR testing using the Cobas Amplicor MTB test (Roche Diagnostic Systems) with three different amounts (10ml, 25ml, and 50ml) of pleural effusion specimen in each patient. Pleural tuberculosis was defined as having one of the following: culture-positive pleural fluid sample, histopathologic finding consistent with tuberculosis on pleural biopsy, culture-positive sputum specimen, and/or positive response to anti-tuberculous medication without other possible causes of pleural effusion. Results: Of the 53 patients, 26 received the diagnosis of pleural tuberculosis. The sensitivities of AFB smearing, Mycobacterium tuberculosis culture of pleural effusion specimen, pleural biopsy, and measurement of ADA were 3.8%, 15.4%, 84.6%, and 88.5%, respectively. The results of PCR testing were positive for 3 (11.5%), 4 (15.4%), and 3 (11.5%) of the 26 patients when using 10ml, 25ml, and 50ml of pleural effusion specimens, respectively. These results did not show a statistically significant difference in the sensitivity of PCR testing when increasing the amount of pleural effusion samples (p>0.05, symmetry exact test). Conclusion: For specimens such as pleural effusion, in which the bacillary load is very low, the clinical utility of PCR testing seems highly limited with the kits designed for the diagnosis of pulmonary tuberculosis. An increased amount of pleural effusion sample does not improve the sensitivity of PCR testing.

• Tuberculosis and Respiratory Diseases
• /
• v.46 no.1
• /
• pp.17-24
• /
• 1999

Background : A sizable percentage of tuberculous pleurisy patients are known to have residual pleural thickening(RPT) despite adequate anti-tuberculous chemotherapy. But, the predictive factors related to the development of RPT is not well known. Therefore, we studied to determine which factors are related to the development of RPT after completion of therapy. Methods: By retrospective review of medical records, fifty-eight patients initially diagnosed as having tuberculous pleurisy between March 1995 and January 1998 were separated into two groups : 27 patients in group 1 had RPT on simple chest radiography, while 31 patients in group 2 had no RPT after 6 month of anti-tuberculous chemotherapy. The clinical characteristics, radiologic findings and pleural fluid findings of the two group were compared at the time of diagnosis and during the course of therapy. Results: 47% of patients had RPT after 6 month of chemotherapy, and RPT was more common in man than in women(54% vs 29%, p=0.092). In group 2 patients, complete resorption of pleural lesion occurred rather late stage of therapy(1-2 month: 26%, 3-4 month: 29%, 5-6 month: 45%). Group 1 patients had increased percentage of loculated pleural lesion(26 % vs 19%) and increased white blood cell and lymphocyte count, lactate dehydrogenase level in pleural fluid ($3527\pm5652$ vs $2467\pm2201$/ml, $2066\pm2022$ vs $1698\pm1835$/ml and $1636\pm1143$ vs $1441\pm923$IU/mL respectively) than group 2 at the time of diagnosis, but statistically insignificant. Duration of symptom prior to treatment, size of pleural effusion, presence of parenchymal lung lesion, level of total protein, glucose and adenosine deaminase(ADA)activity in pleural fluid were similar in both group. Conclusion: 53% of tuberculous pleurisy patients showed slow but complete resorption of pleural lesion after 6 month of chemotherapy. But, no clinical, radiological and pleural fluid findings are predictive for the development of RPT.

• Tuberculosis and Respiratory Diseases
• /
• v.50 no.5
• /
• pp.607-614
• /
• 2001

Background : Residual pleural thickening is frequently seen following treatment for tuberculous pleurisy, and pleural decortication is performed occasionally in patients with severe residual pleural thickening. However, predictive factors for the development of residual pleural thickening are uncertain at the initial diagnosis of the tuberculous pleurisy. Therefore, the purpose of this study was to identify the associated factors for residual pleural thickening at initial diagnosis. Methods : We separated 63 patients diagnosed as tuberculous pleurisy into two groups; group 1 consisted of patients without residual pleural thickening and group 2 comprised patients with residual pleural thickening at the end of tuberculous pleurisy treatment. We analyzed the clinical characteristics, radiological findings, pleural biopsy and characteristics of pleural fluid between group 1 and group 2. Results : The study population and clinical symptoms of the two groups were not significantly different and the duration of symptoms before treatment and the peripheral WBC were similar between the two groups. The presence of pulmonary tuberculosis, pleural fluid loculation or the amount of pleural effusion sid not differ significantly between the two groups. The incidence of positive AFB staining(group 1 : 8%, group 2 : 38%) and granuloma(group 1 : 30%, group 2: 62%)on pleural biopsy specimens was significantly higher in group 2 than in group 1. Pleural fluid WBC and differential count, adenosine deaminase level, pH, protein level or glucose level did not differ between the two groups. However, group 2 had higher LDH levels ($1370{\pm}208mg/dL$) than group 1 ($860{\pm}71mg/dL$, p<0.05). Conclusion : In tuberculous pleurisy, patients with residual pleural thickening following treatment demonstrated a higher incidence of positive AFB staining and granuloma on the pleural biopsy specimens or higher LDH level in the pleural fluid than patients without residual pleural thickening From these results, we speculate that the amount of tuberculous bacilli and granuloma are probably correlated with residual pleural thickening in the tuberculous pleurisy.

• Tuberculosis and Respiratory Diseases
• /
• v.51 no.6
• /
• pp.559-569
• /
• 2001

Background : Pleural effusion is one of the most common clinical manifestations associated with a variety of pulmonary diseases such as malignancy, tuberculosis, and pneumonia. However, there are no useful laboratory tests to determine the specific cause of pleural effusion. Therefore, an attempt was made to analyze the various types of pleural effusion and search for useful laboratory tests for pleural effusion in order to differentiate between the diseases, especially between a malignant pleural effusion and a non-malignant pleural effusion. Methods : 93 patients with a pleural effusion, who visited the Severance hospital from January 1998 to August 1999, were enrolled in this study. Ultrasound-guided thoracentesis was done and a confirmational diagnosis was made by a gram stain, bacterial culture, Ziehl-Neelsen stain, a mycobacterial culture, a pleural biopsy and cytology. Results : The male to female ratio was 56 : 37 and the average age was $47.1{\pm}21.8$ years. There were 16 cases with a malignant effusion, 12 cases with a para-malignant effusion, 36 cases with tuberculosis, 22 cases with a para-pneumonic effusion, and 7 cases with transudate. The LDH2 fraction was significantly higher in the para-malignant effusion group compared to the para-pneumonic effusion group [$30.6{\pm}6.4%$ and $20.2{\pm}7.5%$, respectively (p<0.05)] and both the LDH1 and LDH2 fraction was significantly in the para-malignant effusion group compared to those with tuberculosis [$16.4{\pm}7.2%$ vs. $7.6{\pm}4.7%$, and $30.6{\pm}6.4%$ vs.$17.6{\pm}6.3%$, respectively (p<0.05)]. The pleural effusion/serum LDH4 fraction ratio was significantly lower in the malignant effusion group compared to those with tuberculosis [$1.5{\pm}0.8$ vs. $2.1{\pm}0.6$, respectively (p<0.05)]. The LDH4 fraction and the pleural effusion/serum LDH4 fraction ratio was significantly lower in the para-malignant effusion group compared to those with tuberculosis [$17.0{\pm}5.8%$ vs. $23.5{\pm}4.6%$ and $1.3{\pm}0.4$ vs. $2.1{\pm}0.6$, respectively (p<0.05)]. Conclusion : These results suggest that the LDH isoenzyme was the only useful biochemical test for a differential diagnosis of the various diseases. In particular, the most useful test was the pleural effusion/serum LDH4 fraction ratio to distinguish between a para-malignant effusion and a tuberculous effusion.