• The Journal of the Acoustical Society of Korea
• /
• v.22 no.5
• /
• pp.375-382
• /
• 2003

Lip-reading technique based on bimodal is to enhance speech recognition rate in noisy environment. It is most important to detect the correct lip-image. But it is hard to estimate stable performance in dynamic environment, because of many factors to deteriorate Lip-reading's performance. There are illumination change, speaker's pronunciation habit, versatility of lips shape and rotation or size change of lips etc. In this paper, we propose the IIR filtering in time-domain for the stable performance. It is very proper to remove the noise of speech, to enhance performance of recognition by digital filtering in time domain. While the lip-reading technique in whole lip image makes data massive, the Principal Component Analysis of pre-process allows to reduce the data quantify by detection of feature without loss of image information. For the observation performance of speech recognition using only image information, we made an experiment on recognition after choosing 22 words in available car service. We used Hidden Markov Model by speech recognition algorithm to compare this words' recognition performance. As a result, while the recognition rate of lip-reading using PCA is 64%, Time-domain filter applied to lip-reading enhances recognition rate of 72.4%.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.1023-1026
• /
• 2006

There are some cases in trouble with monitoring emergency patient by existing electrode sensor in measuring instrument in home and hospital etc. And there are problem to measure because of coming down electrode in emergency car or vessel of shaking and fat, humidity of patient. In this study, it has designed band-type for patient to put on the breast easily and go around anywhere freely putting band electrode on his body. Gold has used as electrode material in this electrocardiogram because of its excellent electronic resistance peculiarity and no trouble with skin. And it is able to monitor multi-body-signal by additional design of periphery temperature. There are good results of body signal transmission in the breast or the rib, and get a little body signal in abdomen. We get a result it is better case of gold than usual electrode on signal detection, and know usual electrode was disposable, but we have more correct result from gold electrode sensor, being semi-permanent ana. great contact ability even if movement.

• Journal of the Society of Disaster Information
• /
• v.17 no.4
• /
• pp.733-746
• /
• 2021

Purpose: This study was conducted for the purpose of selecting important events from among various events that may pose a risk to railway passengers. For this purpose, opinions of various railroad vehicle passengers and railway operator workers were investigated and analyzed. Method: The survey was conducted on 1,000 men and women in their 20s and 60s and 429 workers at 11 company across the country. A survey was conducted on the dangerous situations that may occur in subways, general railroads and high-speed rail vehicles targeting passengers. For railway operator workers, the questionnaire is limited to subway vehicles. Result: Among the passenger risk factors(abnormal behavior and dangerous situations) selected based on the frequency and importance of occurrence of passenger risk factors, the main risk factors are selected 'car door jamming', 'sexual harassment', 'intoxicating behavior', 'fighting' /assault', 'wandering around', and 'not wearing a mask'. Conclusion: The major risk factors affecting passengers were selected by surveying passengers and railway operators. we plan to develop a CCTV detection system with AI technology that can quickly and continuously detect the major risk factors of railway vehicles selected as a result of this study.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.2
• /
• pp.370-376
• /
• 2022

Smart ships related studies are being conducted in various fields owing to the development of technology, and an engine room patrol robot that can patrol the unmanned engine room is one such study. A patrol robot moves around the engine room based on the information learned through artificial intelligence and checks the machine normality and occurrence of abnormalities such as water leakage, oil leakage, and fire. Study on engine room patrol robots is mainly conducted on machine detection using artificial intelligence, however study on movement and control is insufficient. This causes a problem in that even if a patrol robot detects an object, there is no way to move to the detected object. To secure maneuverability to quickly identify the presence of abnormality in the engine room, this study experimented with whether a patrol robot can determine the shortest path by applying the A* algorithm. Data were obtained by driving a small car equipped with LiDAR in the ship engine room and creating a map by mapping the obtained data with SLAM(Simultaneous Localization And Mapping). The starting point and arrival point of the patrol robot were set on the map, and the A* algorithm was applied to determine whether the shortest path from the starting point to the arrival point was found. Simulation confirmed that the shortest route was well searched while avoiding obstacles from the starting point to the arrival point on the map. Applying this to the engine room patrol robot is believed to help improve ship safety.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.3
• /
• pp.239-247
• /
• 2022

Cities are becoming more complex due to rapid industrialization and population growth in modern times. In particular, urban areas are rapidly changing due to housing site development, reconstruction, and demolition. Thus accurate road information is necessary for various purposes, such as High Definition Map for autonomous car driving. In the case of the Republic of Korea, accurate spatial information can be generated by making a map through the existing map production process. However, targeting a large area is limited due to time and money. Road, one of the map elements, is a hub and essential means of transportation that provides many different resources for human civilization. Therefore, it is essential to update road information accurately and quickly. This study uses Semantic Segmentation algorithms Such as LinkNet, D-LinkNet, and NL-LinkNet to extract roads from drone images and then apply hyperparameter optimization to models with the highest performance. As a result, the LinkNet model using pre-trained ResNet-34 as the encoder achieved 85.125 mIoU. Subsequent studies should focus on comparing the results of this study with those of studies using state-of-the-art object detection algorithms or semi-supervised learning-based Semantic Segmentation techniques. The results of this study can be applied to improve the speed of the existing map update process.

• Analytical Science and Technology
• /
• v.22 no.3
• /
• pp.235-246
• /
• 2009

The analyses of minor and trace elements in glass debris were performed using LA-ICP-MS in order to identify manufacturers using real commercial samples. At first, a calibration curve was made using standard glass samples of NIST 610, 612, 614 and 616. $^{29}Si$ was used as an internal standard, and the ratios of metal/Si for each metal were compared with their concentrations. Based on elements in each sample and standard materials, 24 metals were quantified and the LOD in analysis, according to the blank sample, was in the range of 0.11 mg/kg (Ti)-4.91 mg/kg (Ca). Eleven samples from two manufacturers were collected and five sub-samples were taken from each sample for analysis. 15 elements (Co, Ce, Ca, Mn, Sr, Ba, Li, Rb, U, La, Th, Na, Al, Zr and Hf) were selected to identify manufacturers because some elements (Cu, Cr, Cd and Ni) were below the detection limit and some elements (Ti, Pr, Mg, Nb, Nd) were absent in the analysis of standards and others (Pb and Sn) had a problem of homogeneity. The attempts to identify manufacturers and the manufacturing period were performed through a triangular diagram. In the manufacturer discrimination by discriminant analysis, a canonical discriminant function was made based on Mn, Ce and Rb, and each sample could be identified.

• Analytical Science and Technology
• /
• v.28 no.6
• /
• pp.398-408
• /
• 2015

Carbon monoxide (CO) intoxication, arising from CO from an ignited charcoal briquette (ICB), is a popular means of committing suicide in Korea. Most CO intoxications are related to suicide attempts; however, the possibility of a homicide disguised as a suicide cannot be ruled out. Therefore, forensic investigation of the deceased and the crime scene is crucial to confirm that the deceased committed suicide. Detection of the components of an ICB on the objects suspected of being contacted by the deceased, such as the hands, nostrils, and doorknobs, is essential for linking the crime scene to the victim in the case of suicides by ignited ICBs. The traces from an ICB were analyzed by investigating the morphological characteristics and obtaining elemental compositions. The ICBs were completely different from blackened wood, as detected by discriminant analysis with the elements of carbon and oxygen. We analyzed one case of CO intoxication to demonstrate an excellent procedure for verifying whether a suicide occurred with an ICB. We employed SEM-EDX for the analysis of an ICB, microscope-FT/IR and pyrolysis-GC/MS for a partly burnt resin-type substance, GC/MS for diphenhydramine (a sleeping drug), and GC/TCD for the CO-Hb level. We detected traces of an ICB on the hands, nostrils, and doorknobs, which were all discriminated into an ICB group. Detection of ICB traces from the nostrils could indicate that the deceased started the fire themselves to commit suicide. The partially burnt black material was analyzed as an acrylronitrilestyrene polymer, which is normally used to make bags for carrying or wrapping and could be assumed to have been used to transport the ICB. Diphenhydramine, a sleeping drug, was detected at a level of 2.3 mg/L in the blood, which was lower than that in fatal cases (8-31 mg/L; mean 16 mg/L). A CO-Hb level of 79% was found in the blood, which means that the cause of death was CO intoxication. The steps shown here could represent an ideal method for reaching a verdict of suicide by CO intoxication produced by burning an ICB in a sealed room or a car.

• Journal of Internet Computing and Services
• /
• v.16 no.2
• /
• pp.49-55
• /
• 2015

According to the statistics of traffic accidents over recent 5 years, traffic accidents during the night times happened more than the day times. There are various causes to occur traffic accidents and the one of the major causes is inappropriate or missing street lights that make driver's sight confused and causes the traffic accidents. In this paper, with smartphones, we designed and implemented a lane luminance measurement application which stores the information of driver's location, driving, and lane luminance into database in real time to figure out the inappropriate street light facilities and the area that does not have any street lights. This application is implemented under Native C/C++ environment using android NDK and it improves the operation speed than code written in Java or other languages. To measure the luminance of road, the input image with RGB color space is converted to image with YCbCr color space and Y value returns the luminance of road. The application detects the road lane and calculates the road lane luminance into the database sever. Also this application receives the road video image using smart phone's camera and improves the computational cost by allocating the ROI(Region of interest) of input images. The ROI of image is converted to Grayscale image and then applied the canny edge detector to extract the outline of lanes. After that, we applied hough line transform method to achieve the candidated lane group. The both sides of lane is selected by lane detection algorithm that utilizes the gradient of candidated lanes. When the both lanes of road are detected, we set up a triangle area with a height 20 pixels down from intersection of lanes and the luminance of road is estimated from this triangle area. Y value is calculated from the extracted each R, G, B value of pixels in the triangle. The average Y value of pixels is ranged between from 0 to 100 value to inform a luminance of road and each pixel values are represented with color between black and green. We store car location using smartphone's GPS sensor into the database server after analyzing the road lane video image with luminance of road about 60 meters ahead by wireless communication every 10 minutes. We expect that those collected road luminance information can warn drivers about safe driving or effectively improve the renovation plans of road luminance management.

• Analytical Science and Technology
• /
• v.26 no.4
• /
• pp.287-297
• /
• 2013

The optimization of analytical method for the thermal desorption of seven VOCs (volatile organic compounds) by TD-GC/MS (thermal desorption-gas chromatograph-mass spectrometer) with solid phase sorbent tube, and comparative analysis for the determination of VOCs plotted by standard sorbent tubes prepared using both gas phase and liquid phase materials were investigated. The result of paired t-test showed that a liquid phase standard sorbent tube method was in agreement with a gas phase standard sorbent tube method for six species of VOCs including benzene, toluene, ethylbenzene, o-, m-, and p-xylene except for styrene at the significance level (${\alpha}=0.01$), while the 15.6% of difference in response factor between both of gas phase and liquid phase standard plotting for the determination of styrene showed that both methods were significantly different at the significance level. Therefore, the liquid phase standard plotting method was employed to reduce erroneous data for the determination of styrene including BTEX. Under the optimized analytical method by liquid phase standard sorbent tube, recovery was between $100{\pm}5%$ for 7 species of VOCs, reproducibility ranged from 0.3 to 7.7%, and method detection limit (MDL) ranged from $0.01{\mu}g/m^3$ for o-xylene to $0.27{\mu}g/m^3$ for toluene. The optimized standard method was applied to determine VOCs VOCs from indoor air of of dormitory, one bedroom apartment, and a new car.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.28 no.4
• /
• pp.613-619
• /
• 2001

The aims of this study were to compare the accuracy, sensitivity and specificity of cnventional visual examination, radiography and a new laser fluorescence method, KaVo Diagnodent, for the detection of occlusal caries lesions. One hundred sound human premolars and molars which had no restorations or interproximal cavities were tested by three methods. Tooth lesions depth was assessed at histologic examination using Caries detector dye The following results were obtained. 1. Diagnodent show 7.8 in sound tooth, 25.4 in initial caries, 30.5 in enamel caries, and 53.8 in dentin caries with average score 2. Spearman and Pearson relation coefficient was high between tooth-specimen test with dye and Diagnodent(0.736, 0.619), visual examination(0.664, 0.666), and was low between tooth-specimen test with dye and radiographic examination(P<0.01, total) 3. Accuracy of occlusal caries was highest on Diagnodent(65%) and lowest on radiographic examination(35%) 4. In initial caries, the sensitivity and specificity of Diagnodent method was the highest. In enamel caries, the sensitivity of visual examination was the highest and specificity of Diagnodent method was the highest. In dentinal caries, the sensitivity and specificity of Diagnodent method was the highest and sensitivity of visual examination was the lowest.