• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.9
• /
• pp.49-61
• /
• 1996

Back-propagation(BP) algorithm needs a lot of time to train the artificial neural network (ANN) to get high accuracy level in classification tasks. So there have been extensive researches to process back-propagation algorithm on parallel processors. This paper prsents a linear systolic array which calculates forward-backward propagation of BP algorithm at the same time using effective space-time transformation and PE structure. First, we analyze data flow of forwared and backward propagations and then, represent the BP algorithm into data dapendency graph (DG) which shows parallelism inherent in the BP algorithm. Next, apply space-time transformation on the DG of ANN is turn with orthogonal direction projection. By doing so, we can get a snakelike systolic array. Also we calculate the interval of input for parallel processing, calculate the indices to make the right datas be used at the right PE when forward and bvackward propagations are processed in the same PE. And then verify the correctness of output when forward and backward propagations are executed at the same time. By doing so, the proposed system maximizes parallelism of BP algorithm, minimizes th enumber of PEs. And it reduces the execution time by 2 times through making idle PEs participate in forward-backward propagation at the same time.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.565-568
• /
• 2009

This paper proposes an monitoring system of elder and feeble person's motion activity using an object's motion activity data. The proposed system used wireless 3-axis sensor module, product by Freescale(Wireless Sensing Triple Axis Reference Design Board (ZSTAR)). We distribute sensing data into three classes using Neural Network System SVM. We find performance of proposed system that simulate some case about walk, past walk, fallen. Classify result data and graph of sensing data present succes rate 80%.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.1
• /
• pp.54-60
• /
• 2021

AR (Augmented Reality) is a technology that provides virtual content to the real world and provides additional information to objects in real-time through 3D content. In the past, a high-performance device was required to experience AR, but it was possible to implement AR more easily by improving mobile performance and mounting various sensors such as ToF (Time-of-Flight). Also, the importance of mobile augmented reality is growing with the commercialization of high-speed wireless Internet such as 5G. Thus, this paper proposes a system that can provide AR services via GNN (Graph Neural Network) using cameras and sensors on mobile devices. ToF of mobile devices is used to capture depth maps. A 3D point cloud was created using RGB images to distinguish specific colors of objects. Point clouds created with RGB images and Depth Map perform downsampling for smooth communication between mobile and server. Point clouds sent to the server are used for 3D object detection. The detection process determines the class of objects and uses one point in the 3D bounding box as an anchor point. AR contents are provided through app and web through class and anchor of the detected object.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.374-376
• /
• 2023

최근 환율 예측에 관한 다양한 연구가 진행되어 왔다. 이러한 추세에 대응하여 본 연구에서는 Pearson 상관 계수 및 상호 정보를 사용하여 외환 시장의 환율 변동을 분석하는 다중 연결 네트워크를 구축하였다. 본 연구에서는 이러한 구성된 환율 변화에 대한 시공간 의존성 네트워크를 만들고 그래프 기계 학습의 잠재력을 조사하여 예측 정확도를 향상시키려고 노력하였다. 본 연구 결과는 선형 및 비선형 종속 네트워크 모두에 대해 그래프 신경망을 활용한 임베딩을 활용하여 기존의 기계 학습 알고리즘과 결합시킬 경우 환율 변화의 예측력이 향상될 수 있음을 경험적으로 확인하였다. 특히, 이러한 결과는 통화 간 상호 의존성에만 의존하여 추가 데이터 없이 달성되었다. 이 접근 방식은 데이터 효율성을 강화하고 그래프 시각화를 통해 설명력 있는 통찰력을 제공하며 주어진 데이터 세트 내에서 효과적인 데이터를 생성하여 예측력을 높이는 결과로 해석할 수 있다.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.25-38
• /
• 2019

Selecting high-quality information that meets the interests and needs of users among the overflowing contents is becoming more important as the generation continues. In the flood of information, efforts to reflect the intention of the user in the search result better are being tried, rather than recognizing the information request as a simple string. Also, large IT companies such as Google and Microsoft focus on developing knowledge-based technologies including search engines which provide users with satisfaction and convenience. Especially, the finance is one of the fields expected to have the usefulness and potential of text data analysis because it's constantly generating new information, and the earlier the information is, the more valuable it is. Automatic knowledge extraction can be effective in areas where information flow is vast, such as financial sector, and new information continues to emerge. However, there are several practical difficulties faced by automatic knowledge extraction. First, there are difficulties in making corpus from different fields with same algorithm, and it is difficult to extract good quality triple. Second, it becomes more difficult to produce labeled text data by people if the extent and scope of knowledge increases and patterns are constantly updated. Third, performance evaluation is difficult due to the characteristics of unsupervised learning. Finally, problem definition for automatic knowledge extraction is not easy because of ambiguous conceptual characteristics of knowledge. So, in order to overcome limits described above and improve the semantic performance of stock-related information searching, this study attempts to extract the knowledge entity by using neural tensor network and evaluate the performance of them. Different from other references, the purpose of this study is to extract knowledge entity which is related to individual stock items. Various but relatively simple data processing methods are applied in the presented model to solve the problems of previous researches and to enhance the effectiveness of the model. From these processes, this study has the following three significances. First, A practical and simple automatic knowledge extraction method that can be applied. Second, the possibility of performance evaluation is presented through simple problem definition. Finally, the expressiveness of the knowledge increased by generating input data on a sentence basis without complex morphological analysis. The results of the empirical analysis and objective performance evaluation method are also presented. The empirical study to confirm the usefulness of the presented model, experts' reports about individual 30 stocks which are top 30 items based on frequency of publication from May 30, 2017 to May 21, 2018 are used. the total number of reports are 5,600, and 3,074 reports, which accounts about 55% of the total, is designated as a training set, and other 45% of reports are designated as a testing set. Before constructing the model, all reports of a training set are classified by stocks, and their entities are extracted using named entity recognition tool which is the KKMA. for each stocks, top 100 entities based on appearance frequency are selected, and become vectorized using one-hot encoding. After that, by using neural tensor network, the same number of score functions as stocks are trained. Thus, if a new entity from a testing set appears, we can try to calculate the score by putting it into every single score function, and the stock of the function with the highest score is predicted as the related item with the entity. To evaluate presented models, we confirm prediction power and determining whether the score functions are well constructed by calculating hit ratio for all reports of testing set. As a result of the empirical study, the presented model shows 69.3% hit accuracy for testing set which consists of 2,526 reports. this hit ratio is meaningfully high despite of some constraints for conducting research. Looking at the prediction performance of the model for each stocks, only 3 stocks, which are LG ELECTRONICS, KiaMtr, and Mando, show extremely low performance than average. this result maybe due to the interference effect with other similar items and generation of new knowledge. In this paper, we propose a methodology to find out key entities or their combinations which are necessary to search related information in accordance with the user's investment intention. Graph data is generated by using only the named entity recognition tool and applied to the neural tensor network without learning corpus or word vectors for the field. From the empirical test, we confirm the effectiveness of the presented model as described above. However, there also exist some limits and things to complement. Representatively, the phenomenon that the model performance is especially bad for only some stocks shows the need for further researches. Finally, through the empirical study, we confirmed that the learning method presented in this study can be used for the purpose of matching the new text information semantically with the related stocks.

• The Korean Journal of Applied Statistics
• /
• v.22 no.2
• /
• pp.415-424
• /
• 2009

As one of the unsupervised learning neural network methods, self-organizing maps(SOM) are applied to various fields. It reduces the dimension of multidimensional data by representing observations on the low dimensional manifold. On the other hand, the minimal spanning tree(MST) of a graph that achieves the most economic subset of edges connecting all components by a single open loop. In this study, we apply the MST technique to SOM with subnodes. We propose SOM's with embedded MST and a distance measure for optimum choice of the size and shape of the map. We demonstrate the method with Fisher's Iris data and a real gene expression data. Simulated data sets are also analyzed to check the validity of the proposed method.

• Science of Emotion and Sensibility
• /
• v.14 no.2
• /
• pp.197-206
• /
• 2011

The purpose of the study was to suggest automatic recognition of the subject's level of arousal into high arousal and low arousal with neural network SOM learning. The automatic recognition in the level of arousal is composed of three stages. First, it is a stage of ECG measurement and analysis. It measures the subject playing a shooting game with ECG and extracts characteristics for SOM learning. Second, it is a stage of SOM learning. It learns input vectors extracting characteristics. Finally, it is a stage of arousal recognition which recognize the subject's level of arousal when new vectors are input after SOM learning is completed. The study expresses recognition results in the level of arousal and the level of arousal in numerical value and graph when SOM learning results in the level of arousal and new vectors are input. Finally, SOM evaluation was analyzed average 86% by comparing emotion evaluation results of the existing research with automatic recognition results of SOM in order. The study could experience automatic recognition with other levels of arousal by each subject with SOM.

• 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.

• Asia pacific journal of information systems
• /
• v.19 no.2
• /
• pp.157-178
• /
• 2009

Corporate credit rating is a very important factor in the market for corporate debt. Information concerning corporate operations is often disseminated to market participants through the changes in credit ratings that are published by professional rating agencies, such as Standard and Poor's (S&P) and Moody's Investor Service. Since these agencies generally require a large fee for the service, and the periodically provided ratings sometimes do not reflect the default risk of the company at the time, it may be advantageous for bond-market participants to be able to classify credit ratings before the agencies actually publish them. As a result, it is very important for companies (especially, financial companies) to develop a proper model of credit rating. From a technical perspective, the credit rating constitutes a typical, multiclass, classification problem because rating agencies generally have ten or more categories of ratings. For example, S&P's ratings range from AAA for the highest-quality bonds to D for the lowest-quality bonds. The professional rating agencies emphasize the importance of analysts' subjective judgments in the determination of credit ratings. However, in practice, a mathematical model that uses the financial variables of companies plays an important role in determining credit ratings, since it is convenient to apply and cost efficient. These financial variables include the ratios that represent a company's leverage status, liquidity status, and profitability status. Several statistical and artificial intelligence (AI) techniques have been applied as tools for predicting credit ratings. Among them, artificial neural networks are most prevalent in the area of finance because of their broad applicability to many business problems and their preeminent ability to adapt. However, artificial neural networks also have many defects, including the difficulty in determining the values of the control parameters and the number of processing elements in the layer as well as the risk of over-fitting. Of late, because of their robustness and high accuracy, support vector machines (SVMs) have become popular as a solution for problems with generating accurate prediction. An SVM's solution may be globally optimal because SVMs seek to minimize structural risk. On the other hand, artificial neural network models may tend to find locally optimal solutions because they seek to minimize empirical risk. In addition, no parameters need to be tuned in SVMs, barring the upper bound for non-separable cases in linear SVMs. Since SVMs were originally devised for binary classification, however they are not intrinsically geared for multiclass classifications as in credit ratings. Thus, researchers have tried to extend the original SVM to multiclass classification. Hitherto, a variety of techniques to extend standard SVMs to multiclass SVMs (MSVMs) has been proposed in the literature Only a few types of MSVM are, however, tested using prior studies that apply MSVMs to credit ratings studies. In this study, we examined six different techniques of MSVMs: (1) One-Against-One, (2) One-Against-AIL (3) DAGSVM, (4) ECOC, (5) Method of Weston and Watkins, and (6) Method of Crammer and Singer. In addition, we examined the prediction accuracy of some modified version of conventional MSVM techniques. To find the most appropriate technique of MSVMs for corporate bond rating, we applied all the techniques of MSVMs to a real-world case of credit rating in Korea. The best application is in corporate bond rating, which is the most frequently studied area of credit rating for specific debt issues or other financial obligations. For our study the research data were collected from National Information and Credit Evaluation, Inc., a major bond-rating company in Korea. The data set is comprised of the bond-ratings for the year 2002 and various financial variables for 1,295 companies from the manufacturing industry in Korea. We compared the results of these techniques with one another, and with those of traditional methods for credit ratings, such as multiple discriminant analysis (MDA), multinomial logistic regression (MLOGIT), and artificial neural networks (ANNs). As a result, we found that DAGSVM with an ordered list was the best approach for the prediction of bond rating. In addition, we found that the modified version of ECOC approach can yield higher prediction accuracy for the cases showing clear patterns.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.12
• /
• pp.403-410
• /
• 2020

In addition to the research on noise removal and super-resolution using the data restoration (Output result) function of Autoencoder, research on the performance improvement of clustering using the dimension reduction function of autoencoder are actively being conducted. The clustering function and data restoration function using Autoencoder have common points that both improve performance through the same learning. Based on these characteristics, this study conducted an experiment to see if the autoencoder model designed to have excellent data recovery performance is superior in clustering performance. Skip connection technique was used to design autoencoder with excellent data recovery performance. The output result performance and clustering performance of both autoencoder model with Skip connection and model without Skip connection were shown as graph and visual extract. The output result performance was increased, but the clustering performance was decreased. This result indicates that the neural network models such as autoencoders are not sure that each layer has learned the characteristics of the data well if the output result is good. Lastly, the performance degradation of clustering was compensated by using both latent code and skip connection. This study is a prior study to solve the Hanja Unicode problem by clustering.