• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.21 no.6
• /
• pp.171-181
• /
• 2011

Proposed in this paper is the intelligent video surveillance system to effectively detect multiple loitering objects even that disappear from the out of camera's field of view and later return to a target zone. After the background and foreground are segmented using Gaussian mixture model and shadows are removed, the objects returning to the target zone is recognized using the chromaticity histogram and the duration of loitering is preserved. For more accurate measurement of the loitering behavior, the camera calibration is also applied to map the image plane to the real-world ground. Hence, the loitering behavior can be detected by considering the time duration of the object's existence in the real-world space. The experiment was performed using loitering video and all of the loitering behaviors are accurately detected.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.503-523
• /
• 2022

Nowadays, many attendance applications utilise biometric techniques such as the face, fingerprint, and iris recognition. Biometrics has become ubiquitous in many sectors. Due to the advancement of deep learning algorithms, the accuracy rate of biometric techniques has been improved tremendously. This paper proposes a web-based attendance system that adopts facial recognition using open-source deep learning pre-trained models. Face recognition procedural steps using web technology and database were explained. The methodology used the required pre-trained weight files embedded in the procedure of face recognition. The face recognition method includes two important processes: registration of face datasets and face matching. The extracted feature vectors were implemented and stored in an online database to create a more dynamic face recognition process. Finally, user testing was conducted, whereby users were asked to perform a series of biometric verification. The testing consists of facial scans from the front, right (30 - 45 degrees) and left (30 - 45 degrees). Reported face recognition results showed an accuracy of 92% with a precision of 100% and recall of 90%.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.2
• /
• pp.17-32
• /
• 2022

This study explored an approach to estimate a flow-density diagram(FD) on a link in highway traffic environment by utilizing probe vehicles' time headway records. To study empirical flow-density diagram(EFD), the probe vehicles with vision sensors were recruited for collecting driving records for nine months and the vision sensor data pre-processing and GIS-based map matching were implemented. Then, we examined the new EFDs to evaluate validity with reference diagrams which is derived from loop detection traffic data. The probability distributions of time headway and distance headway as well as standard deviation of flow and density were utilized in examination. As a result, it turned out that the main factors for estimation errors are the limited number of probe vehicles and bias of flow status. We finally suggest a method to improve the accuracy of EFD model.

• Journal of Society of Preventive Korean Medicine
• /
• v.25 no.3
• /
• pp.25-37
• /
• 2021

Objectives : To investigate the effectiveness of Korean Medicine services use on the all-cause mortality and incidence of Parkinson's disease(PD) in elderly patients with chronic disease based on the National Health Insurance Service Corhort Database (elderly), called as the NHIS-senior. Methods : This study was a retrospective cohort analysis conducted using the NHIS-senior. Patients with chronic diseases over 65 years old who were not diagnosed PD during 2007-2009 were identified. The case group was defined as patients who used both Korean Medicine and Western Medicine services and the control group consisted of patients who used Western Medicine service only. The all-cause mortality and incidence of PD was analyzed using the Cox proportional hazard model after a propensity score matching(PSM) with a 1:1 ratio. Results : After PSM, the cohort included 47,546 subjects (23,773 in the case group, 23,773 in the control group). Sex, age, comorbidity, severity of disability, and neurology medical service utilization were adjusted in both groups. The mortality was 0.668 times (95% C.I.: 0.646-0.690) lower in the case group than the control group, which was statistically significant (p<0.001). The incidence of PD was 1.051 times (95% C.I.: 0.962-1.148) higher in the case group than the control group, which was not statistically significant(p=0.272). Conclusion : It was not obvious that the use of both Korean Medicine service and Western Medicine services for prevention of PD is benefitial than using only Western Medicine. But it would be possible that using both Korean Medicine and Western Medicine services decreases the mortality than using Western Medicine alone.

• Journal of Internet of Things and Convergence
• /
• v.8 no.5
• /
• pp.41-46
• /
• 2022

This study analyzed the results and implications of the industry-university cooperation human resource nurturing process based on the I-O model for the Motion Graphics major and the Global Hotelier major in Baek seok University. In this study, based on the analysis of the human resources training performance through industry-university cooperation in the motion graphics and hotelier fields for 5 years, what kind of efforts were made for successful human resource training, and the level of performance was analyzed and improvement points were suggested. In this study, four strategies were set for successful industry-university-tailored human resource nurturing: student-industry matching through industry participation in education, industry-university integrated education, education quality advancement, and customized education infrastructure construction. As a result of the analysis, customized human resource training should first be developed through industry demand survey and a mirror-type practice room should be built to fit the corporate environment. Second, it was found that it is possible to be individual only if there is an active participation of industry experts throughout the curriculum such as subjects and non-subjects.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.35-40
• /
• 2022

In this paper, we propose a method of constructing clinical knowledge with clinical concept relations and predicting diseases based on a deep learning model to support clinical decision-making. Clinical terms in UMLS(Unified Medical Language System) and cancer-related medical knowledge are classified into five categories. Medical related documents in Wikipedia are extracted using the classified clinical terms. Clinical concept relations are established by matching the extracted medical related documents with the extracted clinical terms. After deep learning using clinical knowledge, a disease is predicted based on medical terms expressed in a query. Thereafter, medical terms related to the predicted disease are selected as an extended query for clinical document retrieval. To validate our method, we have experimented on TREC Clinical Decision Support (CDS) and TREC Precision Medicine (PM) test collections.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.4
• /
• pp.29-34
• /
• 2023

A clear and efficient design method for a microstrip-to-waveguide inline transition, which is based on an analytical model, is presented. The transition consists of three parts: a microstrip-to-SIW transition, a dielectric-loaded waveguide with substrate-height, and a stepped-height waveguide. The shape of the transitional structure is formed for impedance matching. Two equivalent type0s of dielectric-loaded transitional structures are proposed. The design method is applicable to any size of the waveguide, but a design method of two Ka-band transitions is demonstrated. The proposed transitions, in a back-to-back configuration, have less than 1.2 dB insertion loss and more than 15 dB return loss from 29.8 GHz to 38.2 GHz.

• Journal of the Korean Geotechnical Society
• /
• v.24 no.12
• /
• pp.85-92
• /
• 2008

It is necessary to develop a rational design method for surface reinforcement of very soft ground because most current design works rely on merely crude empirical correlations. In this paper, the mechanical behavior of very soft ground that is surficially reinforced was investigated with the aid of a series of numerical analyses. Several material properties of each dredged soft ground, reinforcement and backfill sand mat have been exercised in the numerical analysis. The result of numerical analysis was compared with those of the laboratory model test. Through the matching process between the numerical and experimental result, it is possible to determine representative material properties of the dredged soft ground, reinforcements and backfill sand mat. These verified material properties permit to evaluate the effect of the stiffness of reinforcement and the thickness of sand mat on the overall deformation of the reinforced soft ground.

• Korean Journal of Clinical Pharmacy
• /
• v.32 no.1
• /
• pp.37-46
• /
• 2022

Background: Non-valvular atrial fibrillation (NVAF) is associated with ischemic stroke risk in the aging population. Observational studies have indicated beneficial effects of direct-acting oral anticoagulant (DOAC) against ischemic stroke compared to warfarin. This study aimed to investigate ischemic stroke incidence and bleeding risk in patients on DOAC therapy. Methods: Using the database of Korean Health Insurance Review and Assessment-Aged Patient Sample 2015, we conducted a retrospective cohort study. Study subjects with NVAF diagnosis and prescribed anticoagulants were enrolled. Propensity score (PS) matching by age, sex, comorbidities, and medications were used. The clinical outcomes were major adverse cerebro-cardiovascular events (MACCEs, ischemic stroke/systemic embolism, myocardial infarction, cardiac death) and bleeding events. A cox proportional hazard model analysis was performed to compare the outcomes with hazard ratio (HR) and 95% confidence interval (CI). Results: Total 4,773 elderly patients with NVAF were initially included. Four PS-matched groups including rivaroxaban vs. warfarin-only (n=1,079), dabigatran vs. warfarin-only (n=721), rivaroxaban vs. dabigatran (n=721), and switchers of warfarin to rivaroxaban vs. warfarin-only (n=287) were analyzed. Every group showed statistically similar results of MACCEs and bleeding events, except for the group of rivaroxaban vs. dabigatran. Rivaroxaban users showed higher risks of bleeding events than dabigatran users (HR 2.25, 95% CI 1.01-4.99). Conclusion: In the elderly patients with NVAF, efficacy and safety outcomes among oral anticoagulants including DOACs and warfarin were similar, while rivaroxaban are more likely to have higher bleeding risks than dabigatran. Further research using large size sample is needed.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.3D
• /
• pp.307-315
• /
• 2008

The aim of this study is to develop travel time estimation model by using Self-Organized Neural network(in brief, SON) algorithm. Travel time data based on vehicles equipped with GPS and number-plate matching collected from National road number 3 (between Jangji-IC and Gonjiam-IC), which is pilot section of National Highway Traffic Management System were employed. We found that the accuracies of travel time are related to location of detector, the length of road section and land-use properties. In this paper, we try to develop travel time estimation using SON to remedy defects of existing neural network method, which could not additional learning and efficient structure modification. Furthermore, we knew that the estimation accuracy of travel time is superior to optimum located detectors than based on existing located detectors. We can expect the results of this study will make use of location allocation of detectors in highway.