• Journal of IKEEE
• /
• v.28 no.3
• /
• pp.352-359
• /
• 2024

This paper proposes a CNN-ViT hybrid model that automatically evaluates the aesthetic quality of images by combining local and global features. In this approach, CNN is used to extract local features such as color and object placement, while ViT is employed to analyze the aesthetic value of the image by reflecting global features. Color composition is derived by extracting the primary colors from the input image, creating a color palette, and then passing it through the CNN. The Rule of Thirds is quantified by calculating how closely objects in the image are positioned near the thirds intersection points. These values provide the model with critical information about the color balance and spatial harmony of the image. The model then analyzes the relationship between these factors to predict scores that align closely with human judgment. Experimental results on the AADB image database show that the proposed model achieved a Spearman's Rank Correlation Coefficient (SRCC) of 0.716, indicating more consistent rank predictions, and a Pearson Correlation Coefficient (LCC) of 0.72, which is 2~4% higher than existing models.

• Journal of Korea Multimedia Society
• /
• v.5 no.5
• /
• pp.512-522
• /
• 2002

In this paper, we propose a hybrid method which is mixed with frame selection and weighting model rank method, based on GMM(gaussian mixture model), for real-time text-independent speaker recognition system. In the system, maximum likelihood estimation was used for GMM parameter optimization, and maximum likelihood was used for recognition basically Proposed hybrid method has two steps. First, likelihood score was calculated with speaker models and test data at frame level, and the difference is calculated between the biggest likelihood value and second. And then, the frame is selected if the difference is bigger than threshold. The second, instead of calculated likelihood, weighting value is used for calculating total score at each selected frame. Cepstrum coefficient and regressive coefficient were used as feature parameters, and the database for test and training consists of several data which are collected at different time, and data for experience are selected randomly In experiments, we applied each method to baseline system, and tested. In speaker recognition experiments, proposed hybrid method has an average of 4% higher recognition accuracy than frame selection method and 1% higher than W method, implying the effectiveness of it.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.6
• /
• pp.457-462
• /
• 2003

In this paper, we propose a speaker pruning method for real-time processing and improving performance of speaker identification system based on GMM(Gaussian Mixture Model). Conventional speaker identification methods, such as ML (Maximum Likelihood), WMR(weighting Model Rank), and MWMR(Modified WMR) we that frame likelihoods are calculated using the whole frames of each input speech and all of the speaker models and then a speaker having the biggest accumulated likelihood is selected. However, in these methods, calculation cost and processing time become larger as the increase of the number of input frames and speakers. To solve this problem in the proposed method, only a part of speaker models that have higher likelihood are selected using only a part of input frames, and identified speaker is decided from evaluating the selected speaker models. In this method, fm can be applied for improving the identification performance in speaker identification even the number of speakers is changed. In several experiments, the proposed method showed a reduction of 65% on calculation cost and an increase of 2% on identification rate than conventional methods. These results means that the proposed method can be applied effectively for a real-time processing and for improvement of performance in speaker identification.

• Environmental and Resource Economics Review
• /
• v.30 no.1
• /
• pp.79-105
• /
• 2021

In the circumstance of standing out the climate change issue, the purpose of this study is to compare the efficiency of offshore and coastal fisheries according to whether or not greenhouse gas (GHG) emissions are considered, and then to present policy alternatives based on the analysis results. For analysis, the traditional data envelopment analysis (DEA), the slacks-based measure (SBM) and the SBM-undesirable models were used, and robust analysis of variance (ANOVA) and Wilcoxon Signed-rank tests were performed. As a result, the study showed that the average efficiency of fisheries decreased as the traditional DEA extended to the SBM model considering the slack and the SBM-undesirable model including the GHG emissions. Specifically, the average efficiency of the traditional DEA model, SBM model, and SBM-undesirable model was analyzed as 0.7350, 0.5820 and 0.4976 respectively. In addition, the results of the robust ANOVA and Wilcoxon Signed-rank tests all showed that there are statistically significant differences in efficiency between offshore and coastal fisheries as well as among traditional DEA, SBM and SBM-undesirable models. As a policy alternative to the analysis, it was suggested that to improve the efficiency of coastal and offshore fisheries, it is necessary to actively implement the new fishing vessel project and develop smart and electric hybrid fishing vessels.

• Journal of Radiation Protection and Research
• /
• v.15 no.2
• /
• pp.101-112
• /
• 1990

For the performance assessment of the radioactive waste disposal system (repository), a biosphere model is suggested. This biosphere model is intended to calculate the annual doses to man caused by the contaminated river water for eight pathways and four radionuclides. This model can also be applied to assess the radiological effects of contaminated well water. To account for the uncertainties on the model parameter values, parameter distributions are assigned to these model parameters. Then, Monte Carlo simulation method with Latin Hypercube sampling technique is used. Also, sensitivity analysis is performed by using the Spearman rank correlation coefficients. It is found that these methods are a very useful tool to treat uncertainties and sensitivities on the model parameter values and to analyze the biosphere model. A conversion factor is proposed to calculate the annual dose rate to humans arising from a unit radionuclide concentration in river water. This conversion factor allows for the substitution of the biosphere model in a probabilistic performance assessment computer code by one single variable.

• Asian-Australasian Journal of Animal Sciences
• /
• v.20 no.1
• /
• pp.12-18
• /
• 2007

The objective of the study was to compare ranking of Sahiwal bulls selected on the basis of highest lactation milk yield of their dams with their estimated breeding values (EBVs) using an animal model. Data on 23,761 lactation milk yield records of 5,936 cows from five main Livestock Experiment Stations in Punjab province of Pakistan (1964-2004) were used for the study. At present the young A.I bulls are required to be from A-category bull-dams. Dams were categorized as A, B, C and D if they had highest lactation milk yield of ${\geq}$2,700, 2,250-2,699, 1,800-2,249 and <1,800 litres, respectively. The EBVs for lactation milk yield were estimated for all the animals using an individual animal model having fixed effect of herd-year and season of calving and random effect of animal. Fixed effect of parity and random effect of permanent environment were incorporated when multiple lactation were used. There were 396 young bulls used for semen collection and A.I during 1973-2004. However, progeny with lactation yields recorded, were available only for 91 bulls and dams could be traced for only 63 bulls. Overall lactation milk yield averaged 1,440.8 kg. Milk yield was 10% heritable with repeatability of 39%. Ranking bulls on highest lactation milk yield of their dams, the in-vogue criteria of selecting bulls, had a rank correlation of 0.167 (p<0.190) with ranking based on EBVs from animal model analysis. Bulls' EBVs for all lactations had rank correlation of 0.716 (p<0.001) with EBVs based on first lactation milk yield and 0.766 (p<0.001) with average EBVs of dam and sire (pedigree index). Ranking of bulls on highest lactation yield of their dams has no association with their ranking based on animal model evaluation. Young Sahiwal bulls should be selected on the basis of pedigree index instead of highest lactation yield of dams. This can help improve the genetic potential of the breed accruing to conservation and development efforts.

• Journal of Broadcast Engineering
• /
• v.14 no.2
• /
• pp.238-252
• /
• 2009

Due to the rapid increase of available contents via the convergence of broadcasting and internet, the efficient access to personally preferred contents has become an important issue. In this paper, for recommendation scheme for TV programs using a collaborative filtering technique is studied. For recommendation of user preferred TV programs, our proposed recommendation scheme consists of offline and online computation. About offline computation, we propose reasoning implicitly each user's preference in TV programs in terms of program contents, genres and channels, and propose clustering users based on each user's preferences in terms of genres and channels by dynamic fuzzy clustering method. After an active user logs in, to recommend TV programs to the user with high accuracy, the online computation includes pulling similar users to an active user by similarity measure based on the standard preference list of active user and filtering-out of the watched TV programs of the similar users, which do not exist in EPG and ranking of the remaining TV programs by proposed rank model. Especially, in this paper, the BM (Best Match) algorithm is extended to make the recommended TV programs be ranked by taking into account user's preferences. The experimental results show that the proposed scheme with the extended BM model yields 62.1% of prediction accuracy in top five recommendations for the TV watching history of 2,441 people.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.8
• /
• pp.2137-2156
• /
• 2024

Customer reviews are the second-most reliable source of information, followed by family and friend referrals. However, there are many existing customer reviews. Some online shopping platforms address this issue by ranking customer reviews according to their usefulness. However, we propose an alternative method to rank customer reviews, given that this system is easily manipulable. This study aims to create a ranking model for reviews based on their usefulness by combining product and seller service aspects from customer reviews. This methodology consists of six primary steps: data collection and preprocessing, aspect extraction and sentiment analysis, followed by constructing a regression model using random forest regression, and the review ranking process. The results demonstrate that the ranking model with service considerations outperformed the model without service considerations. This demonstrates the model's superiority in the three tests, which include a comparison of the regression results, the aggregate helpfulness ratio, and the matching score.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2007.11a
• /
• pp.446-451
• /
• 2007

An Improved finite element model updating method to address the numerical difficulty associated with ill-conditioning and rank-deficiency. These difficulties frequently occur in model updating problems, when the identification of a larger number of physical parameters is attempted than that warranted by the information content of the experimental data. Based on the standard Bounded Variables Least-squares (BVLS) method, which incorporates the usual upper/lower-bound constraints, the proposed method is equipped with new constraints based on the correlation coefficients between the sensitivity vectors of updating parameters. The effectiveness of the proposed method is investigated through the numerical simulation of a simple framed structure by comparing the results of the proposed method with those obtained via pure BVLS and the regularization method. The comparison indicated that the proposed method and the regularization method yield approximate solutions with similar accuracy.

• Journal of Digital Convergence
• /
• v.14 no.11
• /
• pp.481-488
• /
• 2016

This study is about comparing the mobile user experience of Facebook and Instagram which are most often used among the recent SNSs by the people in their 30s and under. This study analyzed the user experience level after dividing the user experience factors through the Creating Pleasurable Interfaces model, and suggested the mean analysis as well as the result of Wilcoxon rank test which is a nonparametric statistics method. As a result of study, the Display information visually factor in functional factor and the configuration of the main page in convenient factor were a statistically significant difference in the mobile user experience of Facebook and Instagram. It is expected that this study may help seeking the user experience factors to be promoted preferentially in a competitive situation through the statistical comparative evaluation of the experience of two SNS users.