• Journal of Internet Computing and Services
• /
• v.25 no.4
• /
• pp.7-21
• /
• 2024

There are various machine learning techniques such as Reinforcement Learning, Deep Learning, Neural Network Learning, and so on. In recent, Large Language Models (LLMs) are popularly used for Generative AI based on Reinforcement Learning. It makes decisions with the most optimal rewards through the fine tuning process in a particular situation. Unfortunately, LLMs can not provide any explanation for how they reach the goal because the training is based on learning of black-box AI. Reinforcement Learning as black-box AI is based on graph-evolving structure for deriving enhanced solution through adjustment by human feedback or reinforced data. In this research, for mutually exclusive decision-making, Mutually Exclusive Learning (MEL) is proposed to provide explanations of the chosen goals that are achieved by a decision on both ends with specified conditions. In MEL, decision-making process is based on the tree-based structure that can provide processes of pruning branches that are used as explanations of how to achieve the goals. The goal can be reached by trade-off among mutually exclusive alternatives according to the specific contextual conditions. Therefore, the tree-based structure is adopted to provide feasible solutions with the explanations based on the pruning branches. The sequence of pruning processes can be used to provide the explanations of the inferences and ways to reach the goals, as Explainable AI (XAI). The learning process is based on the pruning branches according to the multi-dimensional contextual conditions. To deep-dive the search, they are composed of time window to determine the temporal perspective, depth of phases for lookahead and decision criteria to prune branches. The goal depends on the policy of the pruning branches, which can be dynamically changed by configured situation with the specific multi-dimensional contextual conditions at a particular moment. The explanation is represented by the chosen episode among the decision alternatives according to configured situations. In this research, MEL adopts the tree-based learning model to provide explanation for the goal derived with specific conditions. Therefore, as an example of mutually exclusive problems, employment process is proposed to demonstrate the decision-making process of how to reach the goal and explanation by the pruning branches. Finally, further study is discussed to verify the effectiveness of MEL with experiments.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.39 no.5
• /
• pp.8-15
• /
• 2002

We optimally designed the VCO(voltage-controlled oscillator) with spiral inductor using the MOSIS HP 0.5${\mu}{\textrm}{m}$ CMOS process. With the developed SPICE model of spiral inductor, the quality factor of spiral inductor was maximized at the operating frequency by varying the layout parameters, e.g., metal width, number of turns, radius, space of the metal lines. For the operation frequency of 2㎓, the inductance of about 3nH, and the MOSIS HP 0.5 CMOS process with the metal thickness of 0.8${\mu}{\textrm}{m}$, oxide thickness of 3${\mu}{\textrm}{m}$, the optimal width of metal lines is about 20${\mu}{\textrm}{m}$ for the maximum Quality factor. With the optimized spiral inductor, the VCO with LC tuning tank was designed, fabricated and measured. The measurements were peformed on-wafer using the HP8593E spectrum analyzer. The oscillation frequency was about 1.610Hz, the frequency variation of 250MHz(15%) with control voltage of 0V - 2V, and the phase noise of -108.4㏈c(@600KHz) from output spectrum.

• Clean Technology
• /
• v.25 no.4
• /
• pp.283-288
• /
• 2019

Monodisperse microparticles has been particularly enabling for various applications in the encapsulation and delivery of pharmaceutical agents. The microfluidic devices are attractive candidates to produce highly uniform droplets that serve as templates to form monodisperse microparticles. The microfluidic devices that have micro-scale channel allow precise control of the balance between surface tension and viscous forces in two-phase flows. One of its essential abilities is to generate highly monodisperse droplets. In this paper, a microfluidic approach for preparing monodisperse polycaprolactone (PCL) microparticles is presented. The microfluidic devices that have a flow-focusing generator are manufactured by soft-lithography using polydimethylsiloxane (PDMS). The crucial factors in the droplet generation are the controllability of size and monodispersity of the microdroplets. For this, the volumetric flow rates of the dispersed phase of oil solution and the continuous phase of water to generate monodisperse droplets are optimized. As a result, the optimal flow condition for droplet dripping region that is able to generate uniform droplet is found. Furthermore, the droplets containing PCL polymer by solvent evaporation after collection of droplet from device is solidified to generate the microparticle. The particle size can be controlled by tuning the flow rate and the size of the microchannel. The monodispersity of the PCL particles is measured by a coefficient of variation (CV) below 5%.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.2
• /
• pp.101-112
• /
• 1995

In order to construct a feature map-based phoneme classification system for speech recognition, two procedures are usually required. One is clustering and the other is labeling. In this paper, we present a phoneme classification system based on the Kohonen's Self-Organizing Feature Map (SOFM) for clusterer and labeler. It is known that the SOFM performs self-organizing process by which optimal local topographical mapping of the signal space and yields a reasonably high accuracy in recognition tasks. Consequently, SOFM can effectively be applied to the recognition of phonemes. Besides to improve the performance of the phoneme classification system, we propose the learning algorithm combined with the classical K-mans clustering algorithm in fine-tuning stage. In order to evaluate the performance of the proposed phoneme classification algorithm, we first use totaly 43 phonemes which construct six intra-class feature maps for six different phoneme classes. From the speaker-dependent phoneme classification tests using these six feature maps, we obtain recognition rate of $87.2\%$ and confirm that the proposed algorithm is an efficient method for improvement of recognition performance and convergence speed.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.3
• /
• pp.866-872
• /
• 2010

In this paper, we developed a digital soldering station based on PID controller, which supply stable power by controlling the current of heater of soldering iron. The proposed system designed PID controller to converge quickly to the set up temperature by user, and regain the lost of heat by external factors quickly. PID controller, designed by Ziegler-Nichols' tuning method, decides triac's trigger timing using setting temperature and present temperature to control the phase of AC 24V power that supply to the heater. Also, we give the function that shows present temperature and setting temperature of iron, and working time by graphic LCD. And during the rest time, we decided the power saving and extension of iron tip by dropping to the optimal temperature. Two experiments had implemented in $25^{\circ}C$ laboratory to confirm the performance of proposed method. The first experiment took 12sec, 13sec, 16sec, 18sec, reaching to $200^{\circ}C$, $300^{\circ}C$, $400^{\circ}C$, $480^{\circ}C$ respectively which result showed shorten of rising time than previous method. In the loading experiment of $300^{\circ}C$, $400^{\circ}C$, $480^{\circ}C$ steady state showed temperature drop of $3.8^{\circ}C$, $4.1^{\circ}C$, $4.5^{\circ}C$ which result showed the low temperature deviation than previous method.

• Asian-Australasian Journal of Animal Sciences
• /
• v.32 no.12
• /
• pp.1836-1843
• /
• 2019

Objective: Social genetic effects (SGE) are an important genetic component for growth, group productivity, and welfare in pigs. The present study was conducted to evaluate i) the feasibility of the single-step genomic best linear unbiased prediction (ssGBLUP) approach with the inclusion of SGE in the model in pigs, and ii) the changes in the contribution of heritable SGE to the phenotypic variance with different scaling ${\omega}$ constants for genomic relationships. Methods: The dataset included performance tested growth rate records (average daily gain) from 13,166 and 21,762 pigs Landrace (LR) and Yorkshire (YS), respectively. A total of 1,041 (LR) and 964 (YS) pigs were genotyped using the Illumina PorcineSNP60 v2 BeadChip panel. With the BLUPF90 software package, genetic parameters were estimated using a modified animal model for competitive traits. Giving a fixed weight to pedigree relationships (${\tau}:1$), several weights (${\omega}_{xx}$, 0.1 to 1.0; with a 0.1 interval) were scaled with the genomic relationship for best model fit with Akaike information criterion (AIC). Results: The genetic variances and total heritability estimates ($T^2$) were mostly higher with ssGBLUP than in the pedigree-based analysis. The model AIC value increased with any level of ${\omega}$ other than 0.6 and 0.5 in LR and YS, respectively, indicating the worse fit of those models. The theoretical accuracies of direct and social breeding value were increased by decreasing ${\omega}$ in both breeds, indicating the better accuracy of ${\omega}_{0.1}$ models. Therefore, the optimal values of ${\omega}$ to minimize AIC and to increase theoretical accuracy were 0.6 in LR and 0.5 in YS. Conclusion: In conclusion, single-step ssGBLUP model fitting SGE showed significant improvement in accuracy compared with the pedigree-based analysis method; therefore, it could be implemented in a pig population for genomic selection based on SGE, especially in South Korean populations, with appropriate further adjustment of tuning parameters for relationship matrices.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.12
• /
• pp.485-496
• /
• 2018

So far, the deep learning, a field of artificial intelligence, has achieved remarkable results in solving problems from unstructured data. However, it is difficult to comprehensively judge situations like humans, and did not reach the level of intelligence that deduced their relations and predicted the next situation. Recently, deep neural networks show that artificial intelligence can possess powerful relational reasoning that is core intellectual ability of human being. In this paper, to analyze and observe the performance of Relation Networks (RN) among the neural networks for relational reasoning, two types of RN-based deep neural network models were constructed and compared with the baseline model. One is a visual question answering RN model using Sort-of-CLEVR and the other is a text-based question answering RN model using bAbI task. In order to maximize the performance of the RN-based model, various performance improvement experiments such as hyper parameters tuning have been proposed and performed. The effectiveness of the proposed performance improvement methods has been verified by applying to the visual QA RN model and the text-based QA RN model, and the new domain model using the dialogue-based LL dataset. As a result of the various experiments, it is found that the initial learning rate is a key factor in determining the performance of the model in both types of RN models. We have observed that the optimal initial learning rate setting found by the proposed random search method can improve the performance of the model up to 99.8%.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.309-328
• /
• 2022

This study empirically analyzed a Korean pre-trained language models (PLMs) designed for natural language generation. The performance of two PLMs - BART and GPT - at the task of abstractive text summarization was compared. To investigate how performance depends on the characteristics of the inference data, ten different document types, containing six types of informational content and creation content, were considered. It was found that BART (which can both generate and understand natural language) performed better than GPT (which can only generate). Upon more detailed examination of the effect of inference data characteristics, the performance of GPT was found to be proportional to the length of the input text. However, even for the longest documents (with optimal GPT performance), BART still out-performed GPT, suggesting that the greatest influence on downstream performance is not the size of the training data or PLMs parameters but the structural suitability of the PLMs for the applied downstream task. The performance of different PLMs was also compared through analyzing parts of speech (POS) shares. BART's performance was inversely related to the proportion of prefixes, adjectives, adverbs and verbs but positively related to that of nouns. This result emphasizes the importance of taking the inference data's characteristics into account when fine-tuning a PLMs for its intended downstream task.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.1-32
• /
• 2018

In addition to stakeholders including managers, employees, creditors, and investors of bankrupt companies, corporate defaults have a ripple effect on the local and national economy. Before the Asian financial crisis, the Korean government only analyzed SMEs and tried to improve the forecasting power of a default prediction model, rather than developing various corporate default models. As a result, even large corporations called 'chaebol enterprises' become bankrupt. Even after that, the analysis of past corporate defaults has been focused on specific variables, and when the government restructured immediately after the global financial crisis, they only focused on certain main variables such as 'debt ratio'. A multifaceted study of corporate default prediction models is essential to ensure diverse interests, to avoid situations like the 'Lehman Brothers Case' of the global financial crisis, to avoid total collapse in a single moment. The key variables used in corporate defaults vary over time. This is confirmed by Beaver (1967, 1968) and Altman's (1968) analysis that Deakins'(1972) study shows that the major factors affecting corporate failure have changed. In Grice's (2001) study, the importance of predictive variables was also found through Zmijewski's (1984) and Ohlson's (1980) models. However, the studies that have been carried out in the past use static models. Most of them do not consider the changes that occur in the course of time. Therefore, in order to construct consistent prediction models, it is necessary to compensate the time-dependent bias by means of a time series analysis algorithm reflecting dynamic change. Based on the global financial crisis, which has had a significant impact on Korea, this study is conducted using 10 years of annual corporate data from 2000 to 2009. Data are divided into training data, validation data, and test data respectively, and are divided into 7, 2, and 1 years respectively. In order to construct a consistent bankruptcy model in the flow of time change, we first train a time series deep learning algorithm model using the data before the financial crisis (2000~2006). The parameter tuning of the existing model and the deep learning time series algorithm is conducted with validation data including the financial crisis period (2007~2008). As a result, we construct a model that shows similar pattern to the results of the learning data and shows excellent prediction power. After that, each bankruptcy prediction model is restructured by integrating the learning data and validation data again (2000 ~ 2008), applying the optimal parameters as in the previous validation. Finally, each corporate default prediction model is evaluated and compared using test data (2009) based on the trained models over nine years. Then, the usefulness of the corporate default prediction model based on the deep learning time series algorithm is proved. In addition, by adding the Lasso regression analysis to the existing methods (multiple discriminant analysis, logit model) which select the variables, it is proved that the deep learning time series algorithm model based on the three bundles of variables is useful for robust corporate default prediction. The definition of bankruptcy used is the same as that of Lee (2015). Independent variables include financial information such as financial ratios used in previous studies. Multivariate discriminant analysis, logit model, and Lasso regression model are used to select the optimal variable group. The influence of the Multivariate discriminant analysis model proposed by Altman (1968), the Logit model proposed by Ohlson (1980), the non-time series machine learning algorithms, and the deep learning time series algorithms are compared. In the case of corporate data, there are limitations of 'nonlinear variables', 'multi-collinearity' of variables, and 'lack of data'. While the logit model is nonlinear, the Lasso regression model solves the multi-collinearity problem, and the deep learning time series algorithm using the variable data generation method complements the lack of data. Big Data Technology, a leading technology in the future, is moving from simple human analysis, to automated AI analysis, and finally towards future intertwined AI applications. Although the study of the corporate default prediction model using the time series algorithm is still in its early stages, deep learning algorithm is much faster than regression analysis at corporate default prediction modeling. Also, it is more effective on prediction power. Through the Fourth Industrial Revolution, the current government and other overseas governments are working hard to integrate the system in everyday life of their nation and society. Yet the field of deep learning time series research for the financial industry is still insufficient. This is an initial study on deep learning time series algorithm analysis of corporate defaults. Therefore it is hoped that it will be used as a comparative analysis data for non-specialists who start a study combining financial data and deep learning time series algorithm.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.157-173
• /
• 2021

With the development of information technology, the amount of available information increases daily. However, having access to so much information makes it difficult for users to easily find the information they seek. Users want a visualized system that reduces information retrieval and learning time, saving them from personally reading and judging all available information. As a result, recommendation systems are an increasingly important technologies that are essential to the business. Collaborative filtering is used in various fields with excellent performance because recommendations are made based on similar user interests and preferences. However, limitations do exist. Sparsity occurs when user-item preference information is insufficient, and is the main limitation of collaborative filtering. The evaluation value of the user item matrix may be distorted by the data depending on the popularity of the product, or there may be new users who have not yet evaluated the value. The lack of historical data to identify consumer preferences is referred to as data sparsity, and various methods have been studied to address these problems. However, most attempts to solve the sparsity problem are not optimal because they can only be applied when additional data such as users' personal information, social networks, or characteristics of items are included. Another problem is that real-world score data are mostly biased to high scores, resulting in severe imbalances. One cause of this imbalance distribution is the purchasing bias, in which only users with high product ratings purchase products, so those with low ratings are less likely to purchase products and thus do not leave negative product reviews. Due to these characteristics, unlike most users' actual preferences, reviews by users who purchase products are more likely to be positive. Therefore, the actual rating data is over-learned in many classes with high incidence due to its biased characteristics, distorting the market. Applying collaborative filtering to these imbalanced data leads to poor recommendation performance due to excessive learning of biased classes. Traditional oversampling techniques to address this problem are likely to cause overfitting because they repeat the same data, which acts as noise in learning, reducing recommendation performance. In addition, pre-processing methods for most existing data imbalance problems are designed and used for binary classes. Binary class imbalance techniques are difficult to apply to multi-class problems because they cannot model multi-class problems, such as objects at cross-class boundaries or objects overlapping multiple classes. To solve this problem, research has been conducted to convert and apply multi-class problems to binary class problems. However, simplification of multi-class problems can cause potential classification errors when combined with the results of classifiers learned from other sub-problems, resulting in loss of important information about relationships beyond the selected items. Therefore, it is necessary to develop more effective methods to address multi-class imbalance problems. We propose a collaborative filtering model using CGAN to generate realistic virtual data to populate the empty user-item matrix. Conditional vector y identify distributions for minority classes and generate data reflecting their characteristics. Collaborative filtering then maximizes the performance of the recommendation system via hyperparameter tuning. This process should improve the accuracy of the model by addressing the sparsity problem of collaborative filtering implementations while mitigating data imbalances arising from real data. Our model has superior recommendation performance over existing oversampling techniques and existing real-world data with data sparsity. SMOTE, Borderline SMOTE, SVM-SMOTE, ADASYN, and GAN were used as comparative models and we demonstrate the highest prediction accuracy on the RMSE and MAE evaluation scales. Through this study, oversampling based on deep learning will be able to further refine the performance of recommendation systems using actual data and be used to build business recommendation systems.