• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.419-437
• /
• 2023

As the number of thin filers in Korea surpasses 12 million, there is a growing interest in enhancing the accuracy of assessing their credit default risk to generate additional revenue. Specifically, researchers are actively pursuing the development of default prediction models using machine learning and deep learning algorithms, in contrast to traditional statistical default prediction methods, which struggle to capture nonlinearity. Among these efforts, Graph Neural Network (GNN) architecture is noteworthy for predicting default in situations with limited data on thin filers. This is due to their ability to incorporate network information between borrowers alongside conventional credit-related data. However, prior research employing graph neural networks has faced limitations in effectively handling diverse categorical variables present in credit information. In this study, we introduce the Transformer embedded Graph Convolutional Network (TeGCN), which aims to address these limitations and enable effective default prediction for thin filers. TeGCN combines the TabTransformer, capable of extracting contextual information from categorical variables, with the Graph Convolutional Network, which captures network information between borrowers. Our TeGCN model surpasses the baseline model's performance across both the general borrower dataset and the thin filer dataset. Specially, our model performs outstanding results in thin filer default prediction. This study achieves high default prediction accuracy by a model structure tailored to characteristics of credit information containing numerous categorical variables, especially in the context of thin filers with limited data. Our study can contribute to resolving the financial exclusion issues faced by thin filers and facilitate additional revenue within the financial industry.

• Journal of Internet of Things and Convergence
• /
• v.10 no.1
• /
• pp.69-75
• /
• 2024

This paper proposes an innovative cognitive IoT framework specifically designed for fog computing (FC) in the context of industrial Internet of Things (IIoT). The discourse in this paper is centered on the intricate design and functional architecture of the Cognitive IoT platform. A crucial feature of this platform is the integration of machine learning (ML) and artificial intelligence (AI), which enhances its operational flexibility and compatibility with a wide range of industrial applications. An exemplary application of this platform is highlighted through the Predictive Maintenance-as-a-Service (PdM-as-a-Service) model, which focuses on real-time monitoring of machine conditions. This model transcends traditional maintenance approaches by leveraging real-time data analytics for maintenance and management operations. Empirical results substantiate the platform's effectiveness within a fog computing milieu, thereby illustrating its transformative potential in the domain of industrial IoT applications. Furthermore, the paper delineates the inherent challenges and prospective research trajectories in the spheres of Cognitive IoT and Fog Computing within the ambit of Industrial Internet of Things (IIoT).

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.5B
• /
• pp.830-841
• /
• 2000

We extend the sue of the method of least square to develop a recursive algorithm for the design of adaptive transversal filters such that, given the least-square estimate of this vector of the filter at iteration n-1, we may compute the updated estimate of this vector at iteration a upon the arrival of new data. We begin the development of the RLS algorithm by reviewing some basic relations that pertain to the method of least squares. Then, by exploiting a relation in matrix algebra known as the matrix inversion lemma, we develop the RLS algorithm. An important feature of the RLS algorithm is that it utilizes information contained in the input data, extending back to the instant of time when the algorithm is initiated. In this paper, we propose new tap weight updated RLS algorithm in adaptive transversal filter with data-recycling buffer structure. We prove that convergence speed of learning curve of RLS algorithm with data-recycling buffer is faster than it of exiting RL algorithm to mean square error versus iteration number. Also the resulting rate of convergence is typically an order of magnitude faster than the simple LMS algorithm. We show that the number of desired sample is portion to increase to converge the specified value from the three dimension simulation result of mean square error according to the degree of channel amplitude distortion and data-recycle buffer number. This improvement of convergence character in performance, is achieved at the (B+1)times of convergence speed of mean square error increase in data recycle buffer number with new proposed RLS algorithm.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.34 no.4
• /
• pp.333-339
• /
• 2010

Identification of a steady state is the first step in developing a fault detection and diagnosis (FDD) system of a heat pump. In a complete FDD system, the steady-state detector will be included as a module in a self-learning algorithm, which enables the working system's reference model to "tune" itself to its particular installation. In this study, a steady-state detector of a residential air conditioner based on moving windows was designed. Seven representative measurements were selected as key features for steady-state detection. The optimized moving-window size and the feature thresholds were decided on the basis of a startup-transient test and no-fault steady-state test. Performance of the steady-state detector was verified during an indoor load-change test. In this study, a general methodology for designing a moving-window steady-state detector for applications involving vapor compression has been established.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.7
• /
• pp.488-498
• /
• 2007

This paper presents a novel approach for representing the spatio-temporal topology of the camera network with overlapping and non-overlapping fields of view (FOVs) in Ubiquitous Smart Space (USS). The topology is determined by tracking moving objects and establishing object correspondence across multiple cameras. To track people successfully in multiple camera views, we used the Merge-Split (MS) approach for object occlusion in a single camera and the grid-based approach for extracting the accurate object feature. In addition, we considered the appearance of people and the transition time between entry and exit zones for tracking objects across blind regions of multiple cameras with non-overlapping FOVs. The main contribution of this paper is to estimate transition times between various entry and exit zones, and to graphically represent the camera topology as an undirected weighted graph using the transition probabilities.

• Fashion & Textile Research Journal
• /
• v.9 no.6
• /
• pp.663-670
• /
• 2007

Arts is the expression of reasoning and conscious life of human and arouse human the concept of existence, utmost emotion and excellent thoughts. Also it makes humans life very abundant. I make it come first to get rid of the art thirst on the opposite sight of technical one for hair as on part of humans body. Next purpose is that to confirm the esthetic value of 'hair arts' by solidify the academic ground of beauty arts through creating 'hair arts' works and learning and make the direction for the beauty industry and education of the next generation. In this study I investigated the Greek myth and the hair styles of ancient Greek Goddesses. On the basis of that symbols I elaborated hair formative works made of metal and studied, analyzed and displayed that. Work No.1 'aphne' pictures the second of changing into a laurel tree avoiding the love. Secondly 'Muse Erato' was exhibited the peaceful figure that have enough the fine melodies. 'Leda' brings out the feature of Leda resembling a swan and the fourth piece, 'Eos' conveys the brilliant and mystery of dawn. So this study conducted based on the concept of practical hair and have made efforts to be close to theoretical manufacturing research needed at making hair arts works and academic one needed at organic design composition for pioneering new field, 'art hair.' I hope these 'hair arts' works make creativity of the practise hair alive. It will be very thankful to me if this study can help even though slightly for splendid beauty arts to make its status firm as a one part of arts, and there are following studies.

• Journal of Digital Convergence
• /
• v.11 no.12
• /
• pp.295-302
• /
• 2013

Many reported methods assume that the people in an image or an image sequence have been identified and localization. People detection is one of very important variable to affect for the system's performance as the basis technology about the detection of other objects and interacting with people and computers, motion recognition. In this paper, we present an efficient linear discriminant for multi-view people detection. Our approaches are based on linear discriminant. We define training data with fisher Linear discriminant to efficient learning method. People detection is considerably difficult because it will be influenced by poses of people and changes in illumination. This idea can solve the multi-view scale and people detection problem quickly and efficiently, which fits for detecting people automatically. In this paper, we extract people using fisher linear discriminant that is hierarchical models invariant pose and background. We estimation the pose in detected people. The purpose of this paper is to classify people and non-people using fisher linear discriminant.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.10
• /
• pp.231-238
• /
• 2020

With a large number of documents appearing on the web, document-level novelty detection has become important since it can reduce the efforts of finding novel documents by discarding documents sharing redundant information already seen. A recent work proposed a convolutional neural network (CNN)-based novelty detection model with significant performance improvements. We observed that it has a restriction of using document-level information in determining novelty but assumed that the document-level information is more important. As a solution, this paper proposed two methods of effectively incorporating document-level information using a CNN-based novelty detection model. Our methods focus on constructing a feature vector of a target document to be classified by extracting relative information between the target document and source documents given as evidence. A series of experiments showed the superiority of our methods on a standard benchmark collection, TAP-DLND 1.0.

• Journal of KIISE
• /
• v.44 no.3
• /
• pp.306-313
• /
• 2017

Named entity recognition (NER) seeks to locate and classify named entities in text into pre-defined categories such as names of persons, organizations, locations, expressions of times, etc. Recently, many state-of-the-art NER systems have been implemented with bidirectional LSTM CRFs. Deep learning models based on long short-term memory (LSTM) generally depend on word representations as input. In this paper, we propose an approach to expand word representation by using pre-trained word embedding, part of speech (POS) tag embedding, syllable embedding and named entity dictionary feature vectors. Our experiments show that the proposed approach creates useful word representations as an input of bidirectional LSTM CRFs. Our final presentation shows its efficacy to be 8.05%p higher than baseline NERs with only the pre-trained word embedding vector.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.2
• /
• pp.49-59
• /
• 2007

This paper is about an system which can perform automatic semantic annotation to actualize "Semantic Web." Since it is impossible to tag numerous documents manually in the web, it is necessary to gather large Korean web documents as training data, and extract features by using natural language techniques and a thesaurus. After doing these, we constructed concept classifiers through the SVM (support vector machine) teaming algorithm. According to the characteristics of Korean language, morphological analysis and syntax analysis were used in this system to extract feature information. Based on these analyses, the concept code is mapped with Kadokawa thesaurus, which made it possible to map similar words and phrase to one concept code, to make training vectors. This contributed to rise the recall of our system. Results of the experiment show the system has a some possibility of semantic annotation.