• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.12
• /
• pp.6009-6027
• /
• 2019

Support vector machine (SVM) classifiers have been widely used for object detection. These methods usually locate the object by finding the region with maximal score in an image. With bag-of-features representation, the SVM score of an image region can be written as the sum of its inside feature-weights. As a result, the searching process can be executed efficiently by using strategies such as branch-and-bound. However, the feature-weight derived by optimizing region classification cannot really reveal the category knowledge of a feature-point, which could cause bad localization. In this paper, we represent a region in an image by a collection of local feature-points and determine the object by the region with the maximum posterior probability of belonging to the object class. Based on the Bayes' theorem and Naive-Bayes assumptions, the posterior probability is reformulated as the sum of feature-scores. The feature-score is manifested in the form of the logarithm of a probability ratio. Instead of estimating the numerator and denominator probabilities separately, we readily employ the density ratio estimation techniques directly, and overcome the above limitation. Experiments on a car dataset and PASCAL VOC 2007 dataset validated the effectiveness of our method compared to the baselines. In addition, the performance can be further improved by taking advantage of the recently developed deep convolutional neural network features.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.11
• /
• pp.1008-1016
• /
• 2015

This paper proposes a method for detecting the front side of vehicles. The method can find the car side with a license plate even with complicated and cluttered backgrounds. A convolutional neural network (CNN) is used to solve the detection problem as a unified framework combining feature detection, classification, searching, and localization estimation and improve the reliability of the system with simplicity of usage. The proposed CNN structure avoids sliding window search to find the locations of vehicles and reduces the computing time to achieve real-time processing. Multiple responses of the network for vehicle position are further processed by a weighted clustering and probabilistic threshold decision method. Experiments using real images in parking lots show the reliability of the method.

• Science of Emotion and Sensibility
• /
• v.14 no.4
• /
• pp.571-580
• /
• 2011

The purpose of this study was to evaluate the effects of secondary task such as sending text message (STM) and searching navigation (SN) using the variable indicating control of vehicle ((Medial-Lateral Coefficient of Variation, MLCV), (Anterior-Posterior Coefficient of Variation, APCV)) and motion signal (Jerk-Cost function, JC). Participants included 50s taxi drivers; 14 males and 14 females. Participants were instructed to keep a certain distance (30m) from the car ahead with constant speed (80km/hr or 100km/hr). Experiement consisted of driving alone for 1minute and driving with secondary task for 1minute. Both MLCV and APCV were significantly increased during Driving + Sending Text Message(STM) and Driving + Searching Navigation(SN) than Driving only. Also, JC was increased during Driving + STM and Driving + SN than Driving only. In this study, we found that even in the experts group who are taxi driver and have 25 years driving experience, the smoothness of motion is decreased and the control of vehicle is disturbed when they were performing secondary tasks like sending text message or searching navigation.

• The Korean Journal of Emergency Medical Services
• /
• v.6 no.1
• /
• pp.141-152
• /
• 2002

The purpose of this study is to provide the basic materials for searching the way of improvement to heighten the emergency medical welfare level by one step further. To achieve this purpose, the subjects of this study were selected 452 college students in Gwangju, using a random sampling method. The statistical analysis methods utilized for analyzing the collected data are frequency analysis, $x^2$ test. The conclusions obtained from these analyses are as following ; 1. In question about necessary optimum number of persons for rescue first aid activity, health and non-health major college students responded by 39.2%, 45.3% respectively that rescue team 15 people, first aid team 3 people is most suitable. But there was no significant difference in major department(p<0.05). 2. In question about security of the public health doctor and the emergency medical technician, all health and non-health major college students are recognizing necessity urgently, but there was no significant difference in major department(p<0.05). 3. In question about 119 rescue first aid team member applying for an examination qualification grant to the department of EMT's graduate, all health and non-health major college students were highest by 52.9%, 52.4% respectively in "necessity" item. But there was no significant difference in major department(p<0.05). 4. Because rescue first aid equipment level appears higher than 41.7% in non-health major college student's case by 54.2% in health major college student's case, health major college students are recognizing that equipment level should be supplemented more but there was no significant difference in major department(p<0.05). 5. In question about equipment supplement, all health and non-health major college students appeared highest by 64.8%, 69.3% in accident type different special equipment. But there was no significant difference in major department(p<0.05). 6. In question about rescue ambulance car size, we could know being thinking that health and non-health major college student each 61.2%, 56.5% is small and narrow that large size of the rescue ambulance amount need. But there was no significant difference in major department(p<0.05). 7. In question about patient's state is worsened, because rescue first aid equipment is inferior, health major college student responded sometimes 55.1%, many 29.5%. very many by 11.5%, while non-health major college student responded 65.8%, 23.1%, 4.0% respectively. There was significant difference in major department(p<0.05). 8. In question about emergency patient must utilize for 119 rescue ambulance car, all health and non-health major college students appeared highest by 38.8%, 41.3% in "not so" item. In question about rescue first aid team's first-aid treatment ability improves more, all health and non-health major college students appeared highest by 58.1% and 58.7% respectively in "improve" item. In question about "119 rescue ambulance car must go more rapidly than now", all health and non-health major college students are recognizing that should be quicker by 58.1%, 60.9% respectively. When called to 119 all health and non-health major college students responded highest by 55.5%, 53.3% respectively that we must receive first-aid treatment direction from a doctor. In question about "119 rescue ambulance car must be made the pay system", all health and non-health major college students responded 74%, 80% respectively in "not so" item. There was significant difference in major department(p<0.05). In conclusions, In oder to provide superior rescue first aid service to people, a public health doctor should be placed in the situation room inside the fire station so that the doctor could instruct the proper emergency treatment suitable for each situation to the rescue first aid team. Also, national education about a first-aid treatment that do to all people is necessarily necessary in emergency delivery system and this should be spread extensively through school education and broadcasting medium and education should be gone side by side, and see that will can save emergency patients' life which is more when these education consists continuously fixed period for public institution of policeman, fire officer etc. specially. And for reinforcement of patient transfer system, public organization must procure special ambulance car so that emergency patient receive first aid treatment while transfer.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.35 no.2
• /
• pp.9-15
• /
• 2012

The purpose of this study was to investigate the effects of the secondary tasks such as sending text message (STM) and searching navigation (SN) on skin conductance level (SCL) and driving performance of relatively aged and high-experienced drivers. The subjects included 26 taxi drivers; 12 males aged $56.3{\pm}4.4$ with $28.4{\pm}6.4$ years of driving experiences and 14 females aged $55.5{\pm}3.5$ with $19.4{\pm}5.0$ years of driving experiences. All subjects were instructed to keep a constant following distance (30m) from the car ahead and a given vehicle speed (80km/h or 100km/h) in a driving simulator. The relative change of SCL, vehicle velocity deviations, and average following distances were measured during driving only and driving with secondary tasks. The relative change of SCL, average following distance, and vehicle velocity deviation were more increased during the driving with secondary tasks than driving only. The relative change of SCL, vehicle velocity deviation, and average following distance were more affected by driving with 100km/hr than 80km/hr of a given vehicle speed. Secondary tasks increased a work load of drivers in term of SCL change, and decreased driving performance in terms of the vehicle velocity deviation and average following distance.

• International Journal of Highway Engineering
• /
• v.14 no.3
• /
• pp.173-182
• /
• 2012

Entry and exits of the rest area are sections where designed speed can be rapidly change and also a weak traffic safety section. In addition, two tasks can be performed simultaneously at entry of the rest area, particularly searching for deceleration and parking spaces/parking sides etc. Thus, design criteria is required in order to procure the stability of accessed vehicle. In case of Korea, geometric structure design criteria of entry facilities, such as toll-gate, interchange, junction etc was established. However there are no presence in a detailed standards for geometric structure of the rest area which affiliated road facilities. In this study, Derive problems in regards to the entry of geometric structure of resting areas by utilizing a sight survey and an investigation research of traffic accidents. The survey was targeting 135 general service areas. After Classifying the design section of resting areas' entry as well as derive design elements on each section, a speed measurement by targeting entry of rest areas and car behavior surveys were performed, then each element's minimum standard was derived through the analyses. According to the speeds at the starting/end point of entrance connector road, the minimum length of the entrance connector road is decided as 40m using Slowing-down length formula and based on the driving pattern, the range of the junction setting angle of the entrance connector road is defined as $12^{\circ}{\sim}17^{\circ}$. Suggest improvement plans for existing rest areas that can be applied realistically. This should be corresponded to the standards of entry and exit of developed rest areas.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.4
• /
• pp.803-809
• /
• 2011

In this paper, we present a very useful method for updating digital satellite radio broadcast channel information. When a devices equipped with function to receive Digital Satellite Radio such as Home Theater, MP3 player, mobile phones, car audio system and various other types of Digital Devices, receives new Digital satellite radio (will be mentioned as XM radio onwards) broadcast channel information, only the current received XM radio broadcast channel and N number of pre/post nearby broadcast channels are scanned randomly in zigzag manner. Then the previous XM radio broadcast channel information updated with the newly received XM radio broadcast channel information. Since this method can prevent batch update for all XM radio channel, including some channels which less likely did not select by user, update process for real time frequently changed XM radio broadcast channel information can be performed efficiently with minimal or without delay.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.4
• /
• pp.739-746
• /
• 2020

The fourth industrial revolution introduced at world economic forum in 2016 has had huge effects on tourism industries as well as the change of core technologies in ICT such as big data, IoT, etc, This paper proposes the methods to propel tourism of Yoesu city through big data analysis and questionnaires. Sensitive words and positive-negative trend are extracted by Social Metrics and the keywords for Yeosu tour trends are extracted and analyzed by Naver datalab, and the results are visualized by R language. And frequency, difference, factor, covariance and regression analysis in SPSS are executed for the questionnaires for 493 visitors who traveled in Yeosu city. Sentiment analysis for Yeosu tour and maritime cable car shows that positive effect is much more than negative one. The analyses for questionnaires in SPSS show that Yeosu area is statistically significant to tour satisfaction index and tour revitalization for Yeosu, and favorite sightseeing places and searching electronic devices for age groups are different. The sightseeing places such as a maritime park with soft contents that give joyfulness and healing to tourists are highly attracted in both the big data and questionnaires analysis.

• Journal of Korean Society for Geospatial Information Science
• /
• v.10 no.1 s.19
• /
• pp.59-66
• /
• 2002

The rapid change of industrial structure causes to increase distribution cost and requires necessity of physical distribution system urgently. Traffic situation is getting extremely worse and traffic jam has led to increasing expense of physical distribution delivery which dominates 20% of distribution cost. In this situation, the shortest and most suitable path search system is required by modern people who must waste a lot of time for moving with a car or on the street as well as many companies. for these reasons, we developed the shortest-path-searching system applying the dijkstra algorithm which is one of the effective shortest path algorithm to GIS, and it was constructed by considering realistic urban traffic and the pattern of street in a physical situation. Also, this system was developed to be updated weight data automatically, considering the dynamic change of traffic situation such as a traffic information service which will be served in real time. Finally, we designed this system to serve on web by using MapObjects IMS.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.7 no.5
• /
• pp.53-63
• /
• 2008

In this paper, we propose the regional travel time measurement algorithm using the sequence pattern matching to the type of vehicles between the origin of the region and the end of the region, that could be able to overcome the limit of conventional method such as Probe Car Method or AVI Method by License Plate Recognition. This algorithm recognizes the vehicles as a sequence group with a definite length, and measures the regional travel time by searching the sequence of the origin which is the most highly similar to the sequence of the end. According to the assumption of similarity cost function, there are proposed three types of algorithm, and it will be able to estimate the average travel time that is the most adequate to the information providing period by eliminating the abnormal value caused by inflow and outflow of vehicles. In the result of computer simulation by the length of region, the number of passing cars, the length of sequence, and the average maximum error rate are measured within 3.46%, which means that this algorithm is verified for its superior performance.