• Annual Conference of KIPS
• /
• 2022.05a
• /
• pp.309-311
• /
• 2022

Oral cancer is a type of cancer that has a high possibility to be cured if it is threatened earlier. The convolutional neural network is very popular for being a good algorithm for image recognition. In this research, we try to compare 4 different architectures of the CNN algorithm: Convnet, VGG16, Inception V3, and Resnet. As we compared those 4 architectures we found that VGG16 and Resnet model has better performance with an 85.35% accuracy rate compared to the other 3 architectures. In the future, we are sure that image recognition can be more developed to identify oral cancer earlier.

• Annual Conference of KIPS
• /
• 2021.05a
• /
• pp.278-281
• /
• 2021

For a long time, CAPTCHA Recognition has been a major challenge in the field of artificial intelligence. Although there are many related technologies that can solve this identification problem, further breakthroughs are still needed. Based on the existing SSD network, this paper adds a non-block module. Compared with the original SSD network, the recognition rate of SSD + Non-local is improved from 86.12% to 88.47%.In addition, it is worth noting that the recognized character verification code consists of Arabic numerals, uppercase and lowercase English letters.

• Korean Journal of Artificial Intelligence
• /
• v.12 no.3
• /
• pp.33-39
• /
• 2024

In this paper, we explore the application of Kodaly hand signs in enhancing children's music education, performances, and auditory assistance technologies. This research focuses on improving the recognition rate of Multilayer Perceptron (MLP) models in identifying Kodaly hand sign scales through the integration of Artificial Neural Networks (ANN). We developed an enhanced MLP model by augmenting it with additional parameters and optimizing the number of hidden layers, aiming to substantially increase the model's accuracy and efficiency. The augmented model demonstrated a significant improvement in recognizing complex hand sign sequences, achieving a higher accuracy compared to previous methods. These advancements suggest that our approach can greatly benefit music education and the development of auditory assistance technologies by providing more reliable and precise recognition of Kodaly hand signs. This study confirms the potential of parameter augmentation and hidden layers optimization in refining the capabilities of neural network models for practical applications.

• KIEAE Journal
• /
• v.17 no.5
• /
• pp.95-100
• /
• 2017

Purpose: The purpose of this study is to investigate the prior art based on deep learning to objectively calculate the metabolic rate which is the subjective factor for the PMV optimum control and to make a plan for future research based on this study. Methods: For this purpose, the theoretical and technical review and applicability analysis were conducted through various documents and data both in domestic and foreign. Results: As a result of the prior art research, the machine learning model of artificial neural network and deep learning has been used in various fields such as speech recognition, scene recognition, and image restoration. As a representative case, OpenCV Background Subtraction is a technique to separate backgrounds from objects or people. PASCAL VOC and ILSVRC are surveyed as representative technologies that can recognize people, objects, and backgrounds. Based on the results of previous researches on deep learning based on metabolic rate for occupational metabolic rate, it was found out that basic technology applicable to occupational metabolic rate calculation technology to be developed in future researches. It is considered that the study on the development of the activity quantity calculation model with high accuracy will be done.

• Korean Journal of Community Nutrition
• /
• v.27 no.2
• /
• pp.132-145
• /
• 2022

Objectives: This study examined trends in the health status and dietary behavior changes by region using the raw data from the 2008 ~ 2019 Community Health Survey. Methods: This study analyzed the data of 2,738,572 people among the raw data of the Community Health Survey from 2008 to 2019. The regional differences in health status and dietary behavior were examined by classifying the regions into capital and non-capital regions, and the non-capital regions were classified into metropolitan cities and provinces. A chi-square test was conducted on the body mass index (BMI), diagnosis of diabetes and hypertension, frequency of eating breakfast, salty taste in usual diet, recognition of nutrition labeling, reading of nutrition labeling, and utilization of nutrition labeling. Results: In determining obesity using the BMI, the normal weight by year decreased, and the obesity rate by year was 34.6% in 2019, which increased by 13% compared to 2008. In addition, the diabetes diagnosis rate and hypertension diagnosis rate continued to increase with the year. Both diabetes and hypertension diagnosis rates were higher in the non-capital regions than in the capital region. Eating breakfast five to seven times per week was most common and showed a significant decreasing trend by year (P < 0.001). The percentage of respondents who said they eat slightly bland foods increased from 19.5% in 2008 to 19.9% in 2010 and then to 22.1% in 2013. The percentage then decreased to 19.9% in 2019, but showed an overall increasing trend (P < 0.001). According to the region, the capital region had a higher percentage than the non-capital region. The nutrition labeling's recognition rate and utilization rate increased yearly, whereas the reading rate decreased. Conclusions: The study results presented the primary data necessary to develop nutrition education programs and establish strategies for local nutrition management projects to improve disease prevention and dietary problems.

• The KIPS Transactions:PartB
• /
• v.17B no.1
• /
• pp.1-8
• /
• 2010

The researches about gaze recognition which current user gazes and finds the location have increasingly developed to have many application. The gaze recognition of existence all about researches have got problems because of using equipment that Infrared(IR) LED, IR camera and head-mounted of high price. This study propose and implement the gaze recognition system based on SVM using a single PC Web camera. The proposed system that divide the gaze location of 36 per 9 and 4 to recognize gaze location of 4 direction and 9 direction recognize user's gaze. Also, the proposed system had apply on image filtering method using difference image entropy to improve performance of gaze recognition. The propose system was implements experiments on the comparison of proposed difference image entropy gaze recognition system, gaze recognition system using eye corner and eye's center and gaze recognition system based on PCA to evaluate performance of proposed system. The experimental results, recognition rate of 4 direction was 94.42% and 9 direction was 81.33% for the gaze recognition system based on proposed SVM. 4 direction was 95.37% and 9 direction was 82.25%, when image filtering method using difference image entropy implemented. The experimental results proved the high performance better than existed gaze recognition system.

• The Journal of the Korea Contents Association
• /
• v.21 no.8
• /
• pp.315-328
• /
• 2021

The study identified 1,500 adult consumers aged 25-54 years with life insurance within the last year as three groups, top, middle and bottom of need recognition, and demonstrated differences in insurance and finance perception and socioeconomic value perception. In particular, the study sought to identify the influence of socioeconomic value recognition factors in addition to overall recognition factors related to insurance and finance, the number of insurance held and insurance satisfaction. Overall recognition factors related to insurance and finance were classified as 'recognition of insurance as a means of professional management and finance', 'self-directed insurance design and contract' and 'recognition of economic burden on insurance'. Socioeconomic value recognition factors were divided into 'socioeconomic self-sufficiency', 'work-life value pursuit' and 'economic value pursuit'. We identified factors that affect the recognition of a higher need for insurance needs as a higher recognition of need for insurance needs. In particular, the most influential factor for the median group was the recognition of insurance as a professional management asset-tech product, and the upper group was found to be a work-life balance factor. The second influential factor was self-directed insurance design and contract factors for both groups. In order to increase the rate of insurance subscription in the future, insurance should be recognized as an essential product to pursue work-life value, and continuous improvement in information exploration conditions for consumers to explore information and compare products will be important to revitalize the insurance market.

• The KIPS Transactions:PartB
• /
• v.15B no.4
• /
• pp.285-292
• /
• 2008

Color histograms have been used as feature vectors to characterize the color features of given images, but they have a limitation in efficiency by generating high-dimensional feature vectors. In this paper, we present a method to reduce the dimension of the feature vectors by applying PCA (principal components analysis) to the color histogram of a given vehicle image. With SVM (support vector machine) method, the dimension-reduced feature vectors are used to recognize the colors of vehicles. After reducing the dimension of the feature vector by a factor of 32, the successful recognition rate is reduced only 1.42% compared to the case when we use original feature vectors. Moreover, the computation time for the color recognition is reduced by a factor of 31, so we could recognize the colors efficiently.

• The Journal of the Korea Contents Association
• /
• v.5 no.4
• /
• pp.85-93
• /
• 2005

In this paper, we propose recognition system which tracks the unmarked hand of a person performing sign language in complex background. First of all, we measure entropy for the difference image between continuous frames. Using a color information that is similar to a skin color in candidate region which has high value, we extract hand region only from background image. On the extracted hand region, we detect a contour and recognize sign language by applying improved centroidal profile method. In the experimental results for 6 kinds of sing language movement, unlike existing methods, we can stably recognize sign language in complex background and illumination changes without marker. Also, it shows the recognition rate with more than 95% for person and $90\sim100%$ for each movement at 15 frames/second.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.7
• /
• pp.101-111
• /
• 1999

This paper presents concrete pattern recognition method to identify the strength of concrete by evidence accumulation with multiple parameters based on artificial intelligence techniques. At first, variance(VAR), zero-crossing(ZCR), mean frequency(MEANF), and autoregressive model coefficient(ARC) and linear cepstrum coefficient(LCC) are extracted as feature parameters from ultrasonic signal of concrete. Pattern recognition is carried out through the evidence accumulation procedure using distance measured with reference parameters. A fuzzy mapping function is designed to transform the distances for the application of the evidence accumulation method. Results(92% successful pattern recognition rate) are presented to support the feasibility of the suggested approach for concrete pattern recognition.