• The Journal of Engineering Geology
• /
• v.25 no.3
• /
• pp.395-401
• /
• 2015

An investigation of the tunnel face, as well as related measurement data collected during tunneling, is necessary for rock classification and to determine tunnel stability and the cost efficiency of tunneling. However, systematic management and efficient use of such data have yet to be successfully implemented domestically, and the number of experts in this field in Korea is limited. Thus, measures to develop and implement systematic management and effective use of data and expertise are urgently needed. This study aimed to develop measures to efficiently provide online tunnel design and construction data using a building information model (BIM)-based data visualization approach, based on an integrated 3D tunnel model generation module and a web viewer module. The development technology was verified through ○○ tunnel design and construction. Directions for future study and system improvement are proposed.

• Journal of Sasang Constitutional Medicine
• /
• v.24 no.3
• /
• pp.34-41
• /
• 2012

Objectives In this study, we developed a mock-up of the system for Sasang Constitutional (SC) diagnosis. This system consists of 5 devices which are the face analyzer, the voice analyzer, the skin analyzer, the pulse analyzer, and the computer-based questionnaire. Our goal is to evaluate the repeatability of the system. Methods Each device is capable of classifying SC types. The classification probability of the integrated system for the SC types was obtained by summing the probability from each device. For evaluating the repeatability of the system, we collected data for 5 subjects, and repeated the measurement three times for each individual. The average and standard deviation were used for calculating the Coefficient of Variation. Results The results showed that the repeatability of the classification probability of the integrated system is about 8%, which implies the system is repeatable. Conclusions To increase usability of this system, it is desirable for the system to offer information on health condition of the user. The integrated constitutional diagnosis system will be upgraded to complement the convenience and to develop the diagnostic algorithm for the user's health condition.

• Journal of KIISE:Computing Practices and Letters
• /
• v.11 no.3
• /
• pp.284-291
• /
• 2005

I propose a framework for detecting, recognizing and classifying facial features based on learned expression patterns. The framework recognizes facial expressions by using PCA and expression HMM(EHMM) which is Hidden Markov Model (HMM) approach to represent the spatial information and the temporal dynamics of the time varying visual expression patterns. Because the low level spatial feature extraction is fused with the temporal analysis, a unified spatio-temporal approach of HMM to common detection, tracking and classification problems is effective. The proposed recognition framework is accomplished by applying posterior probability between current visual observations and previous visual evidences. Consequently, the framework shows accurate and robust results of recognition on as well simple expressions as basic 6 facial feature patterns. The method allows us to perform a set of important tasks such as facial-expression recognition, HCI and key-frame extraction.

• Journal of the Korean Society of Safety
• /
• v.33 no.4
• /
• pp.111-118
• /
• 2018

Korea is facing a surge in the aging population, showing that population aged 65 and above will be accounted for 42.5% of the total population in 2065 with the emphasis on the over-80 population consisting of 19.2%. In response to this abrupt change in population structure, the number of traffic fatality accident referring to older driver as aged 65+ years had been increasing from 605 fatalities in 2011 to 815 fatalities in 2015 resulting in increases in 34.7% in oppose to happening to decreases in 17.2% about non-older driver. With Logit analysis based on Newton-Raphson algorithm utilizing older driver's traffic fatality data for the 2011-2015 years, it was found that the likelihood of an accident resulting in a fatality for super older driver aged 80 years and above considerably increased compared to other older driver with aging classification: 2.24 times for violation of traffic lane, 2.04 times for violation of U-turn, 1.48 times for violation of safety distance, 1.35 times for violation of obstacle of passing; also average annual increase of traffic accident cost related to super older driver was fairly increased rather than other older driver groups. Hence, this study proposes that improving and amending transport safety system and Road Traffic Act for super older driver needs to be urgently in action about license management, safe driving education, etc. when considering the increase of over-80 population in the near future. Also, implementing a social agreement with all ages and social groups to apply with advanced driver assistance system for older driver groups will be able to become a critical factor to enhance safe driving over the face of the country.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.5
• /
• pp.457-464
• /
• 2009

The weak classifier of AdaBoost algorithm is a central classification element that uses a single criterion separating positive and negative learning candidates. Finding the best criterion to separate two feature distributions influences learning capacity of the algorithm. A common way to classify the distributions is to use the mean value of the features. However, positive and negative distributions of Haar-like feature as an image descriptor are hard to classify by a single threshold. The poor classification ability of the single threshold also increases the number of boosting operations, and finally results in a poor classifier. This paper proposes a weak classifier that uses multiple criterions by adding a probabilistic criterion of the positive candidate distribution with the conventional mean classifier: the positive distribution has low variation and the values are closer to the mean while the negative distribution has large variation and values are widely spread. The difference in the variance for the positive and negative distributions is used as an additional criterion. In the learning procedure, we use a new classifier that provides a better classifier between them by selective switching between the mean and standard deviation. We call this new type of combined classifier the "Mixed Weak Classifier". The proposed weak classifier is more robust than the mean classifier alone and decreases the number of boosting operations to be converged.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.1
• /
• pp.85-93
• /
• 2018

Biometric user authentications, day after day, propagate more to human life instead of traditional systems which use passwords and ID cards. However, most of these systems have many problems for given biometric information such noisy data, low-quality data, a limitation of recognition rate, and so on. To deal with these problems, I used Dual QML which is non-linear classification for classifying correctly the real-world data and then proposed preprocessing method for increasing recognition rate and performance by segmenting a specific region on an image. The previous published Dual QML used face, palmprint, ear for the experiment. In this paper, I used iris for experiment and then proved excellence of Dual QML at iris recognition. Finally I demonstrated these results (e.g. increasing recognition rate and performance, suitability for iris recognition) through experiments.

• Health Policy and Management
• /
• v.7 no.2
• /
• pp.46-64
• /
• 1997

Background & Objectives : Korea is face with the social need for health care technology assessment so that it is urgently needed to found principles and methodology in technology assessment in health care. As a groundwork for health care technology assessment, we tried to prioritize medical technology for assessment. Among medical technologies, procedure is somewhat difficult to assess, compared to drug or equipment. In this study, we aimed at the prioritisation of medical procedure to be assessed, in terms of efficay, safety, and adequacy. Method : For the standardized classification of medical procedure, ICD-9-CM(International Classification of Diseases 9th edition - Clinical Modification) was used. Among the list the procedures coming under otorhinolaringjology and thoracic surgery were selected by three family physicians. The list of procedure was mailed to the board certified surgeons of both disciplines, with the question asking about the necessity for assessment in terms of efficay, safety, and adequacy. Replied questionnaires were analyzed in each procedure. Results : Of 560 otorhinolaryngologist and 480 thoracic surgeon, 114 surgeons replied. Of otorhinolaryngological procedure, incision, excision, and destruction of inner ear : fenestration of inner ear : stapedectomy and its revision were the most urgent technology to assess in the aspect of safety. For adequacy, operations on Eustachian tube: fenestration of inner ear: incision, excision, and destruction of inner ear were highly ranked in necessity, and for efficary, operations on Eustachian tube; external maxillary antrotomy; fenestration of inner ear. Thoracic surgeons replied thoracic procedures, lung transplantation; heart transplantation; implantation of heart assist system [pump] are most important for evaluation in terms of safety; and heart transplantation; Lung transplantation; Implantation of heart assist system [pump] in terms of adequacy, and surgical collapse of lung [Artificia니 pnemothorax or pnuexoperitoeum]; lung transplantation; periarterial sympathectomy in terms of efficacy. As a whole, surgeons regard safety evaluation is more urgent than adequacy or efficary. In addition, otorhinolaryngological surgeons regard evaluation of their procedures more urgent than thoracic surgeons regard theirs. Conclusion : By the questionnaire to board certified physicians, we get some preliminary data for prioritisation of technologies to assess. Through the questionnaire like this, much information would be gathered for technology assessment, especially for medical procedure, if not enough. In the near future, well structured expert opinion gathering research, such as modified Delphi or nominal group technique, should be done succeedingly.

• Smart Media Journal
• /
• v.12 no.7
• /
• pp.59-67
• /
• 2023

Recently, research on behavior analysis tracking human posture and movement has been actively conducted. In particular, OpenPose, an open-source software developed by CMU in 2017, is a representative method for estimating human appearance and behavior. OpenPose can detect and estimate various body parts of a person, such as height, face, and hands in real-time, making it applicable to various fields such as smart healthcare, exercise training, security systems, and medical fields. In this paper, we propose a method for classifying four exercise movements - Squat, Walk, Wave, and Fall-down - which are most commonly performed by users in the gym, using OpenPose-based deep learning models, DNN and CNN. The training data is collected by capturing the user's movements through recorded videos and real-time camera captures. The collected dataset undergoes preprocessing using OpenPose. The preprocessed dataset is then used to train the proposed DNN and CNN models for exercise movement classification. The performance errors of the proposed models are evaluated using MSE, RMSE, and MAE. The performance evaluation results showed that the proposed DNN model outperformed the proposed CNN model.

• Journal of dental hygiene science
• /
• v.23 no.3
• /
• pp.193-198
• /
• 2023

Background: The nose is located at the center of the face, and it is possible to determine race, sex, and the like. Research using the nasal index (NI) classification method to classify the shape of the nose is currently in progress. However, domestic research is required as most research is being conducted abroad. In this study, we used a 3D program to confirm the ratio of the nose shape of Koreans. Methods: One hundred patients (50 males and 50 females) in their 20s were evaluated (IRB approval no. DKUDH IRB 2020-01-007). Cone beam computed tomography was performed using the Mimics ver.22 (Materialise Co., Leuven, Belgium) 3D program to model the patient's skull and soft tissues into three views: coronal, sagittal, and frontal. To confirm the ratio of measurement metrics, analysis was performed using the SPSS ver. 23.0 (IBM Co., Armonk, NY, USA) program. Results: Ten leptorrhine (long and narrow) type, 76 mesorrhine (moderate shape) type, and 14 platyrrhine (broad and short) type noses were observed. In addition, as a result of sex comparison, five males had the leptorrhine (long and narrow) type, 40 mesorrhine (moderate shape), and five platyrrhine (broad and short) types. For females, five patients had the leptorrhine (long and narrow) type, 36 patients had the mesorrhine (moderate shape) type, and nine patients had the platyrrhine (broad and short) type. Conclusion: This study will be helpful when performing nose-related surgeries and procedures in clinical practice and for similar studies in the future.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.1-14
• /
• 2023

As markets and industries continue to evolve rapidly, technology opportunity discovery (TOD) has become critical to a firm's survival. From a common consensus that TOD based on a firm's capabilities is a valuable method for small and medium-sized enterprises (SMEs) and reduces the risk of failure in technology development, studies for TOD based on a firm's capabilities have been actively conducted. However, previous studies mainly focused on a firm's technological capabilities and rarely on business capabilities. Since discovered technologies can create market value when utilized in a firm's business, a firm's current business capabilities should be considered in discovering technology opportunities. In this context, this study proposes a TOD method that considers both a firm's business and technological capabilities. To this end, this study uses patent data, which represents the firm's technological capabilities, and trademark data, which represents the firm's business capabilities. The proposed method comprises four steps: 1) Constructing firm technology and business capability matrices using patent classification codes and trademark similarity group codes; 2) Transforming the capability matrices to preference matrices using the fuzzy function; 3) Identifying a target firm's candidate technology opportunities using the collaborative filtering algorithm; 4) Recommending technology opportunities using a portfolio map constructed based on technology similarity and applicability indices. A case study is conducted on a security firm to determine the validity of the proposed method. The proposed method can assist SMEs that face resource constraints in identifying technology opportunities. Further, it can be used by firms that do not possess patents since the proposed method uncovers technology opportunities based on business capabilities.