• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.21-31
• /
• 2023

In this paper, we focused on the problem of evaluating multi-class classification accuracy and simulation of multiple classifier performance metrics. Multi-class classifiers for sentiment analysis involved many challenges, whereas previous research narrowed to the binary classification model since it provides higher accuracy when dealing with text data. Thus, we take inspiration from the non-linear Support Vector Machine to modify the algorithm by embedding dynamic hyperplanes representing multiple class labels. Then we analyzed the performance of multi-class classifiers using macro-accuracy, micro-accuracy and several other metrics to justify the significance of our algorithm enhancement. Furthermore, we hybridized Enhanced Convolution Neural Network (ECNN) with Dynamic Support Vector Machine (DSVM) to demonstrate the effectiveness and efficiency of the classifier towards multi-class text data. We performed experiments on three hybrid classifiers, which are ECNN with Binary SVM (ECNN-BSVM), and ECNN with linear Multi-Class SVM (ECNN-MCSVM) and our proposed algorithm (ECNNDSVM). Comparative experiments of hybrid algorithms yielded 85.12 % for single metric accuracy; 86.95 % for multiple metrics on average. As for our modified algorithm of the ECNN-DSVM classifier, we reached 98.29 % micro-accuracy results with an f-score value of 98 % at most. For the future direction of this research, we are aiming for hyperplane optimization analysis.

• Proceedings of the Botanical Society of Korea Conference
• /
• 1985.08b
• /
• pp.73-81
• /
• 1985

We have previously isolated OsMADS4 gene that is a member of the class B MADS box genes from rice. In this study, another member of the class B MADS box genes was isolated from rice flower by the yeast two-hybrid screening method using OsMADS4 as bait. RNA blot analyses revealed that the clone, OsMADS16, was expressed in the second and third whorls, whereas the OsMADS4 transcripts were present in the second, third, and fourth whorls. These expression patterns of the OsMADS16 and OsMADS4 genes are very similar with those of AP3 and PI, the class B genes of Arabidopsis, respectively. In the yeast two-hybrid system, OsMADS4 interacted only with OsMADS16 among several rice MADS genes investigated, suggesting that OsMADS4 and OsMADS16 function as a heterodimer in specifying sepal and petal identities. We have also isolated OsMADS6 gene using OsMADS1 as a probe. Both are members of the AGL2 MADS family. Various MADS genes that encode for protein-protein interaction partners of the OsMADS6 protein were isolated by the yeast two-hybrid screening method. A majority of these genes belong to the AGL2 family. Sequence Homology, expression pattern, and ectopic expression phenotypes indicated that one of the interaction partners, OsMADS14, appears to be homologous to API, the class A MADS gene of Arabidopsis.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.12
• /
• pp.980-984
• /
• 2001

When robot manipulatros as mathematically modeled. uncetainties may not be avoided. The uncertain factors come from imperfect knowledge of system parameters, payload change. friction, external disturbance and etc. In this work, we proposed a class of robust hybrid control of manipulatosrs. We propose a class of expanded robust hybrid control with the separated bound function and the simulation results are provided to show the effectiveness of the algorithm.

• Journal of the Korean Society of Costume
• /
• v.54 no.2
• /
• pp.105-119
• /
• 2004

Cultural hybridization and global cross-fertilization, begun since the 1990s, mean the hybrid mixture of the low-class popular arts and the high-class fine arts and have found expression in intertextuality by means of the thinking system of de-constructuralist post-modernism. This study was intended to investigate the artistic intertextuality between fashion and art frontiere, especially between such fields as 'animation', 'music', and 'performing arts' and 'fashion', which shows the greatest characteristic of the phenomenon that the non-mainstream culture flows into the mainstream culture. It also aimed to investigate the intertextuality between 'technology' and 'fashion' as the delivery room of the youth culture and copycat culture due to the benefit of technologies since the 20th-century digital revolution. Animation as the neo-pop art with the popular code coming to the forefront in the 21th century integrated high-class fashion and low-class fashion into one through the combination of fashion and humor, and the musical element referring to the social difference of the cultural field and the social strata is becoming the 21th-century fashion icon through its fusion with the pictorial tendency along with the leisure-time life of the non-mainstream strata. In terms of intertextuality in performing arts, fashion style performs an important role in the presentation of performing arts and since the de-construction of the fin-de-ciecle form and its fusion with media have taken place, fashion works become and element of the origin that has an influence on a series of film, dance, dramatic elements and the like. The paradigm of technology made it socially and culturally possible to achieve the architecture of clothing system necessary for fashionable technical clothing by allowing the possibility of imitation, the function of technology to form popular culture. The intertextual tendency in the 21th-century fashion began from the de-constructive phenomenon of existing norms and now takes the multicultural character of surpassing a certain domain or concept. And it positions itself as the total art of spearheading the low-class culture and the non-mainstream culture as the hybrid domain of mainstream and non-mainstream cultures or high-class and low-class cultures.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.15 no.3
• /
• pp.197-206
• /
• 2019

Telemarketing has been used in finance due to the reduction of offline channels. In order to select telemarketing target customers, various machine learning techniques have emerged to maximize the effect of minimum cost. However, there are problems that the class imbalance, which the number of marketing success customers is smaller than the number of failed customers, and the recall rate is lower than accuracy. In this paper, we propose a method that solve the imbalanced class problem and increase the recall rate to improve the efficiency. The hybrid sampling method is applied to balance the data in the class, and the stacked deep network is applied to improve the recall and precision as well as the accuracy. The proposed method is applied to actual bank telemarketing data. As a result of the comparison experiment, the accuracy, the recall, and the precision is improved higher than that of the conventional methods.

• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.101-106
• /
• 2023

Chronic illnesses are among the most common serious problems affecting human health. Early diagnosis of chronic diseases can assist to avoid or mitigate their consequences, potentially decreasing mortality rates. Using machine learning algorithms to identify risk factors is an exciting strategy. The issue with existing feature selection approaches is that each method provides a distinct set of properties that affect model correctness, and present methods cannot perform well on huge multidimensional datasets. We would like to introduce a novel model that contains a feature selection approach that selects optimal characteristics from big multidimensional data sets to provide reliable predictions of chronic illnesses without sacrificing data uniqueness.[1] To ensure the success of our proposed model, we employed balanced classes by employing hybrid balanced class sampling methods on the original dataset, as well as methods for data pre-processing and data transformation, to provide credible data for the training model. We ran and assessed our model on datasets with binary and multivalued classifications. We have used multiple datasets (Parkinson, arrythmia, breast cancer, kidney, diabetes). Suitable features are selected by using the Hybrid feature model consists of Lassocv, decision tree, random forest, gradient boosting,Adaboost, stochastic gradient descent and done voting of attributes which are common output from these methods.Accuracy of original dataset before applying framework is recorded and evaluated against reduced data set of attributes accuracy. The results are shown separately to provide comparisons. Based on the result analysis, we can conclude that our proposed model produced the highest accuracy on multi valued class datasets than on binary class attributes.[1]

• The Transactions of the Korean Institute of Power Electronics
• /
• v.27 no.6
• /
• pp.489-497
• /
• 2022

This work investigates the commutation characteristics of the current flowing through an electrical-contact-type switch to the semiconductor switch branch during the breaking operation of hybrid DC switchgear. A simple, reliable, low-cost natural commutation method is proposed, and the current commutation characteristics are analyzed in accordance with the conduction voltage drop of the semiconductor switch branch through experiments. A prototype 400 V/10 A class natural commutation type hybrid DC switchgear is set up. Its performance is verified, and its characteristics are analyzed.

• Journal of the Society of Naval Architects of Korea
• /
• v.59 no.6
• /
• pp.362-371
• /
• 2022

As considerable interests in noise emission from the ships have been increased, International Maritime Organization (IMO) standardized the Underwater Radiated Noise (URN) measurement process of commercial ships in deep seas by enacting the related ISO standard ISO 17208-1 and classification societies responded with the enactment or revision of corresponding notations. According to this trend, a new hybrid underwater sound propagation model based on underwater sound propagation theories was developed and its accuracy on analysis was verified through the result comparison with the results of other generally used models. Using the verified model, each URN propagation characteristics adjusted by the correction methods proposed in the ISO standard and class notations were analyzed and compared in two assumed URN measurement cases. The results showed that the effects of transmission loss corrections in the circumstances with less bottom reflections generally similar but they had rather large differences in the model analysis results with bottom-reflection-dominant conditions. It was concluded that the deep consideration of effective bottom-reflection-correction method should be made in future revisions of ISO standard and class notations.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.426-426
• /
• 2000

When real robot manipulators arc mathematically modeled, uncertainties are not avoidable. The uncertainties are often nonlinear and time varying, The uncertain factors come from imperfect knowledge of system parameters, payload change, friction, external disturbance and etc. We proposed a class of robust hybrid position/force control of manipulators and provided the stability analysis in the previous work. In the work, we propose a class of adaptive robust hybrid position/force control of manipulators with bound estimation and the stability based on Lyapunov function is presented. Especially, this controller does not need the information of uncertainty bound. The simulation results are provided to show the effectiveness of the algorithm.

• International Journal of Aeronautical and Space Sciences
• /
• v.17 no.2
• /
• pp.167-174
• /
• 2016

Even though the differential drag type machines of the vertical wind turbines are a bit less efficient than the lift type machines such as Darrieus type machines, they have an advantage of low starting torque. The flapping blade type wind turbine is a specific type of the differential drag machines, and it has no need for orientation as well as quite low starting torque. This work is to develop an innovative 5kW class flapping type vertical wind turbine system which will be applicable to a hybrid power generation system driven by the diesel engine and the wind turbine. The parametric study was carried out to decide an optimum aerodynamic configuration of the wind turbine blade. In order to evaluate the designed blade, the subscale wind tunnel test and the performance test were carried out, and their test results were compared with the analysis results.