• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.5
• /
• pp.581-587
• /
• 2005

This paper presents a hybrid face recognition method of both the first moment of image and the independent component analysis(ICA) of fixed point(FP) algorithm based on Newton method. First moment is a method for finding centroid of image, which is applied to exclude the needless backgrounds in the face recognitions by shifting to the centroid of face image. FP-ICA is also applied to find a set of independent basis images for the faces, which is a set of statistically independent facial features. The proposed method has been applied to the problem for recognizing the 48 face images(12 persons o 4 scenes) of 64*64 pixels. The 3 distances such as city-block, Euclidean, negative angle are used as measures when match the probe images to the nearest gallery images. The experimental results show that the proposed method has a superior recognition performances(speed, rate) than conventional FP-ICA without preprocessing. The city-block has been relatively achieved more an accurate similarity than Euclidean or negative angle.

• Journal of the Korean Society for Railway
• /
• v.20 no.3
• /
• pp.374-381
• /
• 2017

Concrete sleepers, installed on majority of railroad track in this nation can, if not maintained properly, threaten the safety of running trains. In this paper, an algorithm for automatically identifying cracks in a sleeper image, taken by high-resolution camera, is developed based on Adaboost, known as the strongest adaptive algorithm and most actively utilized algorithm of current days. The developed algorithm is trained using crack characteristics drawn from the analysis results of crack and non-crack images of field-installed sleepers. The applicability of the developed algorithm is verified using 48 images utilized in the training process and 11 images not used in the process. The verification results show that cracks in all the sleeper images can be successfully identified with an identification rate greater than 90%, and that the developed automatic crack identification algorithm therefore has sufficient applicability.

• The Journal of Pediatrics of Korean Medicine
• /
• v.35 no.3
• /
• pp.100-117
• /
• 2021

Objectives The purpose of this study is to investigate the satisfaction and improvement points of the current health checkup in infants and children, and recognition of parents about introduction of health examinations for infants and children by Korean medicine. Methods We conducted an online survey through the website of Dongguk University Bundang Korean medicine hospital for the parent of infants and children between 4 and 71 months age who received at least one health checkup. Statistical processing was performed using the SPSS Version 23.0 program. Results As a result of correlation analysis between the degree of necessary improvement point of current health checkup for infants and children and the degree of strength of health examinations for infants and children by Korean medicine, there was a statistically significant positive correlation (r=0.957). With the participation of Korean medical doctors, it can be expected that the number of health examinations centers for infants and children will be expanded, screening services will be increased, and oriental medicine childcare and education to prevention of major pediatrics disease can be provided. Conclusions These results show that health examinations for infants and children by Korean medicine can increase the satisfaction of the parent and the inspection rate.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.47-52
• /
• 2021

Recently, demand for artificial intelligence solutions for production process management has been increasing in the manufacturing industry. However, through the application of AI solutions in the manufacturing industry, there are limitations to legacy smart factory solutions such as POP and MES.Therefore, in order to overcome this, this paper aims to improve production management efficiency by applying guidance, an artificial intelligence concept, to image recognition systems. In the system flow, As_is To be separated and actual work flow was applied, and the process was improved for overall productivity efficiency. The pre-processing plan for AI guidance learning was established and the relevant AI model was designed, developed, and simulated, resulting in a 97% recognition rate.

• 재활복지
• /
• v.17 no.4
• /
• pp.267-289
• /
• 2013

The purpose of this study is to research teachers' recognition for founding and operationg school-companies for each field of handicap. And, the subjects for the questionnaire were the teachers in five schools in Daegu. According to the result, for the foundation of school-company for each field of handicap, it showed that the teachers significantly required it; for the operation, they expected both the increasement of job taking rate and the specialized vocational development of students; and for the operating method, they preferred the supplying way through their production of required goods by local community and companies. For the operation of school-companies for each field of handicap, the time arrangement for curriculum of the students should be flexible, and the curriculum should be incorporated according to the need of each school. And, as for the staff members and teachers in charge of school-company for each field of handcap, this study suggested it to support and assist according to practical situation of each school. Through the result of this study, it was discussed on the direction of following studies and practical meaning for school-companies for each field of handicap.

• Integrative Medicine Research
• /
• v.3 no.2
• /
• pp.60-66
• /
• 2014

Background: Medically unexplained symptoms (MUSs) are common in primary care. Atpresent, there are no proven, comprehensive treatments available in primary care forpatients with MUSs. However, MUS has parallels with "subhealth" or Mibyeong from tradi-tional East-Asian medicine, and thus, Mibyeong interventions could be effective in treatingMUS. Unfortunately, studies on Mibyeong and its intervention methods are relatively rare.Methods: We administered a web-based survey to 17,279 Korean medicine (KM) practitionersregistered with the Association of Korean Medicine. The response rate was 4.9% (n = 849).Based on the responses received, we assessed how much they agreed with concepts relatedto Mibyeong on a 7-point scale from "do not agree" to "strongly agree." Respondents werealso asked to indicate how frequently they encountered various subtypes and patterns ofMibyeong, and how frequently they use listed intervention methods.Results: Data from 818 respondents were analyzed after excluding those with no clinicalexperience. On average, respondents were male general practitioners aged between 30 yearsand 49 years, working or living in metropolitan areas such as Seoul, Incheon, and Gyeonggi-do. Responses did not differ by demographics. Respondents generally thought that Mibyeongreferred to subjective or borderline findings without certain disease, and that Mibyeong hasvarious subtypes and patterns. Subtypes included fatigue, pain, and digestion problems; pat-terns were either deficiencies (e.g., qi, blood, and yin deficiency) or stagnations (e.g., liver qidepression and qi stagnation). Decoction was the most frequently used type of interventionfor Mibyeong of all items listed, followed by acupuncture and moxibustion. Patient educa-tion was also recommended, suggesting healthy eating, promoting healthy environment,and exercise.Conclusion: We were able to provide preliminary results on KM practitioners' recognition ofand interventions for Mibyeong, but further research is needed to develop a detailed defi-nition of Mibyeong and its myriad subtypes and patterns, and evaluations of the efficacy ofMibyeong interventions.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.7
• /
• pp.45-55
• /
• 2021

Information obtained through various sensors embedded in a smartphone can be used to identify and analyze user's movements and situations. In this paper, we propose two rule-based motion detection systems that can detect three alphabet motions, 'I', 'S', and 'Z' by analyzing data obtained by the acceleration and gyroscope sensors in a smartphone. First of all, the characteristics of acceleration and angular velocity for each motion are analyzed. Based on the analysis, two rule-based systems are proposed and implemented as an android application and it is used to verify the detection performance for each motion. Two rule-based systems show high recognition rate over 90% for each motion and the rule-based system using ensemble shows better performance than another one.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.3
• /
• pp.11-20
• /
• 2022

Currently, the black-white QR (Quick Response) codes have been used widely in consumer advertising fields and the study of color QR codes have received a growing demand because of much higher data encoding capacity. Color QR codes can be reproduced by the printing and scanning processes, however, these encounter colors distortion caused by insufficient lighting, low resolution of camera and geometric deformation during the capturing processes. In order to overcome these problems, this paper proposes an efficient decoding algorithm for color QR codes with inserted patterns, which are dealt with conventional studies. These are evaluated in view of the recognition rate under different noise conditions, for example, Gaussian noises/blurring and geometric deformation. Experimental results demonstrate that the color QR codes with simple pattern can resist the distortion of Gaussian noises/blurrings.

• Journal of Internet Computing and Services
• /
• v.23 no.4
• /
• pp.1-9
• /
• 2022

Recently, the functions of smart speakers have diversified, and the penetration rate of smart speakers is increasing. As it becomes more widespread, various techniques have been proposed to cause anomalous behavior against smart speakers. Dolphin Attack, which causes anomalous behavior against the Voice Controllable System (VCS) during various attacks, is a representative method. With this method, a third party controls VCS using ultrasonic band (f>20kHz) without the user's recognition. However, since the method uses the ultrasonic band, it is necessary to install an ultrasonic speaker or an ultrasonic dedicated device which is capable of outputting an ultrasonic signal. In this paper, a smart speaker is controlled by generating an audio signal modulated at a frequency (18 to 20) which is difficult for a person to hear although it is in the human audible frequency band without installing an additional device, that is, an ultrasonic device. As a result with the method proposed in this paper, while humans could not recognize voice commands even in the audible band, it was possible to control the smart speaker with a probability of 82 to 96%.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.6
• /
• pp.1199-1206
• /
• 2022

In this paper, unlike door locks that are controlled only by the existing keypad because electronic devices can be easily operated through apps on smartphones in modern society, an app was created using app inventory so that door locks can be controlled using smartphones. Through the Bluetooth module experiment, the communication distance with the smartphone was controlled up to 10m when there were no obstacles, and through the voice recognition experiment, the recognition rate was 85% and 90% at 500~1000Hz and 1000~1500Hz, respectively, and 70% and 80% at 80dB noise. Through the results of the experimental evaluation, it was confirmed that convenience and security could be improved.