• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.6
• /
• pp.251-256
• /
• 2019

A capsule endoscopy is a medical device that can capture an entire digestive organ from the esophagus to the anus at one time. It produces a vast amount of images consisted of about 8~12 hours in length and more than 50,000 frames on a single examination. However, since the analysis of endoscopic images is performed manually by a medical imaging specialist, the automation requirements of the analysis are increasing to assist diagnosis of the disease in the image. Among them, this study focused on automatic detection of polyp images. A polyp is a protruding lesion that can be found in the gastrointestinal tract. In this paper, we propose a weighted-image generation method to enhance the polyp image learning by multi-scale analysis. It is a way to extract the suspicious region of the polyp through the multi-scale analysis and combine it with the original image to generate a weighted image, that can enhance the polyp image learning. We experimented with SVM and RF which is one of the machine learning methods for 452 pieces of collected data. The F1-score of detecting the polyp with only original images was 89.3%, but when combined with the weighted images generated by the proposed method, the F1-score was improved to about 93.1%.

• Journal of Information Technology Applications and Management
• /
• v.29 no.3
• /
• pp.43-55
• /
• 2022

In this study, with the goal of developing a deep learning-based product recommendation model for effective matching of influencers and products, a deep learning model with a collaborative filtering model combined with generalized matrix decomposition(GMF), a collaborative filtering model based on multi-layer perceptron (MLP), and neural collaborative filtering and generalized matrix Factorization (NeuMF), a hybrid model combining GMP and MLP was developed and tested. In particular, we utilize one-class problem free boosting (OCF-B) method to solve the one-class problem that occurs when training is performed only on positive cases using implicit feedback in the deep learning-based collaborative filtering recommendation model. In relation to model selection based on overall experimental results, the MLP model showed highest performance with weighted average precision, weighted average recall, and f1 score were 0.85 in the model (n=3,000, term=15). This study is meaningful in practice as it attempted to commercialize a deep learning-based recommendation system where influencer's promotion data is being accumulated, pactical personalized recommendation service is not yet commercially applied yet.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.6
• /
• pp.1881-1891
• /
• 2014

Full system of turnkey deliberation committee in 2010 was abolished and permanent Deliberation committee was introduced. So far, ordering organization selected the best method suitable for the design and comprehensive evaluation method in the turnkey bid construction. Comprehensive evaluation method have bid price design score coordination, weighted basis, the best design approach fixed amount, five successful bidder decision method in addition. Design deliberation branch committee in the successful bidder decision way configured and operated branch members of special design consultation committee, But main agent changed from committee deliberation pull system to permanent committee deliberation, as well as and The lobby burden was not improved. This similar to the past at the portion of the design deliberation and the way of the design deliberation in the turnkey bid construction. Therefore it is necessary to improve the design deliberation system. In other words, design score and technology competition should be adapted to determine a successful bid. This study suggested the operating system of the design deliberation, the decision method problems of the successful bidder and ways to improve the design deliberation.

• The Journal of Internal Korean Medicine
• /
• v.27 no.2
• /
• pp.500-509
• /
• 2006

Objectives: We performed this study to check the effect of Cold-Heat attribute analyzed quantitatively by questionnaire on halitosis patient. Methods: We made a questionnaire composed of 15 items(6 categories) about the contents of Cold-Heat and asked 105 subjects to answer in the form Likert-like seven-points score. And then, we extracted Cold-Heat attribute from 15 items, 6 categories, 6 weighted categories, heat score and cold score. On the other hand we measured the halimeter measurements. VAS, winkle tongue coating index. Afterward, the data were analyzed by statistical methods. Results:1) In the 15 items, question number 6, 7, 8 is negative correlated with halimeter measurements. Question number10 is positive correlated with halimeter measurements. And question number 11, 12, 14 is positive correlated with VAS. 2) In the 6 categories, constipation is negative correlated with halimeter measurements. Chill is positive correlated with VAS. And Cold-limbs is positive correlated with halimeter measurements. 3) In the 6 weighted score categories, constipation is negative correlated with halimeter measurements. Chill is positive correlated with VAS. And Cold-limbs is positive correlated with halimeter measurements. Conclusions: Further clinical research is necessary in the development of the questionnaire's items. And to get the better of this study, we should research more analytic method made casual relationship clear between Cold-Heat attributes and the index of halitosis.

• Journal of Korean Institute of Industrial Engineers
• /
• v.37 no.4
• /
• pp.358-366
• /
• 2011

Multi-criteria ABC inventory classification, which aims to classify inventory items by considering more than one criterion, is one of the most widely employed techniques for inventory control. The weighted linear optimization (WLO) model proposed by Ramanathan (2006) solves the problem of multi-criteria ABC inventory classification by generating a set of criterion weights for each inventory item and assigning a normalized score to the item for ABC analysis. However, the WLO model has some limitations. First, many inventory items can share the same optimal score, which can hinder a precise classification of inventory items. Second, the model allows too much flexibility in weighting multiple criteria; each item is allowed to choose its own weights so that it can maximize its score. As a result, if an item dominates the others in terms of a certain criterion, it may be classified into a higher class regardless of other criteria by assigning an overwhelming weight to the criterion. Consequently, an item with a high value in an unimportant criterion and low values in others may be inappropriately classified as class A, leading to an inaccurate classification of inventory items. To overcome these shortcomings, we extend the WLO model by using the cross-efficiency method in data envelopment analysis. We claim that the proposed model can provide a more reasonable and accurate classification of inventory items by mitigating the adverse effect of flexibility in the choice of weights and yielding a unique ordering of inventory items.

• Korean Journal of Construction Engineering and Management
• /
• v.24 no.5
• /
• pp.44-51
• /
• 2023

Selecting appropriate bidding system in construction projects considering the characteristic of project can be a make-or-break element, so the understanding for bidding system of public construction projects is ever more important from the perspective of both the owner and the contractor. The design-build bidding is commonly referred to as turnkey in Korea, and is a bidding method that is often applied to large public construction projects because it allows new technologies to be applied to the design and facilitates risk management for the owner. In this bidding method, there are only two factors (design score and price score) that affect the selection of the winning bidder, so it is important to understand the influence of each factor, but there is little research on the subject. This study aims to provide a basis for establishing bidding strategies for understanding the influence between design score and price score by analyzing various design-build bidding data of public construction projects. The results of the study show that design score is the factor that has more influence on the ranking of bidders in all three weighted evaluation methods: design-emphasized, price-emphasized, and equalized evaluation. In addition, we found that the correlation between design and price scores was not significant due to the unique bid evaluation structure in Korea.

• Journal of Environmental Impact Assessment
• /
• v.20 no.1
• /
• pp.61-69
• /
• 2011

Integrated stream naturalness based on abiotic and biotic factors were developed. Abiotic factors considered in this study were types of land use in the riparian area, river bank and high water bed streamside, revetment, bed substrate and artificial construction of streamside. Biotic factors included types of vegetation, assemblages of fish, macroinvertebrate, bird and mammal(Otter) in streams. The presence/absence of legal species and biological assessment index were also weighted as important parameters in this study. Scoring criteria selected for each matrix was five rating system; 1=poor, 2=moderate, 3=fair, 4=good, 5=excellent. Numerical ratings for the matrix were then summed. This resulted in a minimum score of 13 if all matrix at a site were poor, and a maximum score of 65 if all matrix were excellent. Five grade system from poor(I) to excellent condition(V) was employed. To verify its validity in natural environment, the evaluation system was applied to the Gapchun stream which is a test bed selected. Our result showed that stream naturalness of each reach was clearly distinguished by biotic and abiotic characteristics. Determination of correlation coefficient between abiotic and biotic factors was also high ($R^2=0.96$, p<0.05). In conclusion, assessment for stream naturalness reflecting abiotic and biotic factors was useful method representing stream integrated.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.8
• /
• pp.3984-4005
• /
• 2017

Image recognition has become an increasingly important topic for its wide application. It is highly challenging when facing to large-scale database with large variance. The recognition systems rely on a key component, i.e. the low-level feature or the learned mid-level feature. The recognition performance can be potentially improved if the data distribution information is exploited using a more sophisticated way, which usually a function over hidden variable, model parameter and observed data. These methods are called generative score space. In this paper, we propose a discriminative extension for the existing generative score space methods, which exploits class label when deriving score functions for image recognition task. Specifically, we first extend the regular generative models to class conditional models over both observed variable and class label. Then, we derive the mid-level feature mapping from the extended models. At last, the derived feature mapping is embedded into a discriminative classifier for image recognition. The advantages of our proposed approach are two folds. First, the resulted methods take simple and intuitive forms which are weighted versions of existing methods, benefitting from the Bayesian inference of class label. Second, the probabilistic generative modeling allows us to exploit hidden information and is well adapt to data distribution. To validate the effectiveness of the proposed method, we cooperate our discriminative extension with three generative models for image recognition task. The experimental results validate the effectiveness of our proposed approach.

• Journal of the Korean Geotechnical Society
• /
• v.35 no.4
• /
• pp.5-14
• /
• 2019

The typical four conditions related to internal erosion were set from the results of the regular dam safety inspection for 17,500 dams, and a questionnaire survey was conducted for dam safety experts to quantify these four typical current dam conditions with scores between 0 and 10, respectively. In addition, we proposed 'possible score range' for each condition to minimize the decision limits for dam managers to quantify dam conditions while helping to quantify various dam conditions except 4 representative conditions. A case study based on 'quantified score' and 'possible score range' for each condition showed that this method consistently reflects the dangerousness of the dam and provides a reasonable probability of failure. This helps to overcome limitations of dam rating determination by weighted average, and it will help to evaluate dangerous dams as dangerous dams.

• Journal of Environmental Impact Assessment
• /
• v.21 no.5
• /
• pp.813-821
• /
• 2012

Environmental and public health concern for the emission of air pollutants from burn-up process in waste incineration plants located in the vicinity of living environment was increased during the past decade. The purpose of this study was to suggest of the simple and rapid method of priority setting model for the decision of full-scale public health assessment. This method was consists of total 5-step. Step 1 was "secure the satellite map" and we can use the satellite map which serves from the website such as NAVER Co. Step 2 was "drawing mesh on the map" for catch the point of occupation of environmental sensitivity facilities, and step 3 was "identification and sorting of the facilities", Step 4 was "setting of weight" using the "weighted linear combination (WLC) method". Finally, all facility was sorted by score. As a result, we can set a priority of 145 facilities based on 177 facilities which managed in local government. Facilities in Seoul metropolitan area was high rank in priority list. On the other side, Facilities located at the country or rural area was low rank because of low occupation of the house and the environmental sensitivity facilities such as kindergarten, elementary school, and hospital. In this study, we suggested simple and rapid method that using for screening procedure of public health assessment.