• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.2
• /
• pp.83-92
• /
• 2024

Currently, various countries are enhancing accessibility by providing bicycle rental services for convenient usage within daily life. This paper introduces the Nubija public bicycle service in Changwon, South Korea, aiming to address the imbalance between demand and supply of Nubija bicycles. We propose a Highest Priority Reallocation Scheme to prevent this disparity. Comparing this scheme with others that randomly visit terminals for redistribution and those that prioritize terminals closest to current locations, we illustrate its superior efficiency. Our proposed Highest Priority Reallocation Scheme prioritizes terminals with the highest demand and shortest distances nearby. Through experiments, our proposed scheme demonstrates superior performance, with the lowest average of 817.44km distance and an average of 6437.45 times, i.e., 88.14% successful rental occurrences. This highlights its superiority over the other two algorithms.

• The Korean Journal of Applied Statistics
• /
• v.37 no.2
• /
• pp.239-253
• /
• 2024

This research applies both point-wise and pair-wise learning strategies within the learning-to-rank (LTR) framework to predict horse race rankings in Seoul. Specifically, for point-wise learning, we employ a linear model and random forest. In contrast, for pair-wise learning, we utilize tools such as RankNet, and LambdaMART (XGBoost Ranker, LightGBM Ranker, and CatBoost Ranker). Furthermore, to enhance predictions, race records are standardized based on race distance, and we integrate various datasets, including race information, jockey information, horse training records, and trainer information. Our results empirically demonstrate that pair-wise learning approaches that can reflect the order information between items generally outperform point-wise learning approaches. Notably, CatBoost Ranker is the top performer. Through Shapley value analysis, we identified that the important variables for CatBoost Ranker include the performance of a horse, its previous race records, the count of its starting trainings, the total number of starting trainings, and the instances of disease diagnoses for the horse.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.31-40
• /
• 2024

In the realm of domestic online fashion platform industry the manual registration of product information by individual business owners leads to inconvenience and reliability issues, especially when dealing with simultaneous registrations of numerous product groups. Moreover, bias is significantly heightened due to the low quality of product images and an imbalance in data quantity. Therefore, this study proposes a ResNet50 model aimed at minimizing data bias through oversampling techniques and conducting multiple classifications for 13 fashion categories. Transfer learning is employed to optimize resource utilization and reduce prolonged learning times. The results indicate improved discrimination of up to 33.4% for data augmentation in classes with insufficient data compared to the basic convolution neural network (CNN) model. The reliability of all outcomes is underscored by precision and affirmed by the recall curve. This study is suggested to advance the development of the domestic online fashion platform industry to a higher echelon.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.11a
• /
• pp.1270-1273
• /
• 2007

최근 인터넷의 급속한 발달은 온라인 뱅킹, 인터넷 쇼핑몰 등에서의 실물 경제행위를 온라인상으로 처리할 수 있는 환경을 제공하지만 온라인상의 업무처리는 개인정보유출, 개인정보의 위조 및 변조 등의 문제를 가지고 있다. 사용자가 CA에게서 받은 인증서의 공개키로 전자서명 함으로써 개인정보유출, 정보의 위조 및 변조 등의 문제를 해결한 PKI(Public Key Infrastructure)기반의 인증서 검증시스템이 제안되어 사용되고 있다. 인증서 상태검증 방법에는 CRL(Certificate Revocation List)기반의 검증방식, OCSP(Online Certificate Status Protocol)기반의 검증방식 등이 있다. CRL기반의 인증서 검증방식은 인증서 취소목록을 검색해서 인증서의 유효성 여부를 응답하는 방식으로 시간이 지남에 따라 크기 증가와 오프라인 방식으로 인해서 목록을 다운받는 시간의 부담으로 인해서 OCSP방식이 제안되었다. 하지만 OCSP 방식 역시 서비스의 요청이 집중될 경우 문제가 발생될 수 있다. 그래서 분산된 OCSP를 구축하고 각 서버의 부하의 균형을 유지하기 위해 로드밸런싱 기법을 사용하고 있지만 그 방법 역시 지속적인 서비스 제공이 불가한 문제를 가지고 있다. 본 논문에서는 서비스 요청의 집중으로 인한 시스템 마비나 각 응답서버의 부하가 불균형적임으로써 생길 수 있는 문제를 해결할 수 있는 방법을 제안한다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.173-180
• /
• 2024

Along with its importance, the real estate market poses risks of various fraudulent activities. Recently, a surge in real estate-related scams, such as lease fraud, has caused great financial damage to many ordinary people. These problems are often caused by the complexity of real estate transactions and information imbalance. Therefore, there is an urgent need to secure reliability and improve transparency in the transaction process. In this paper, to solve this real estate fraud problem, we propose a chatbot system using digital technology and artificial intelligence, especially GPT (Generative Pre-Trained Transformer). This system serves to protect users from fraud by providing them with precautions and confirmations in the lease transaction process. In addition, GPT-based chatbots respond to questions from users in time, contributing to reducing uncertainty in the transaction process and increasing reliability.

• Journal of the Korean Society of Radiology
• /
• v.83 no.4
• /
• pp.931-937
• /
• 2022

Chronic inflammatory condition associated with metallic implant insertion is a risk factor for diffuse large B-cell lymphoma (DLBCL). Metal ions play a role in the pathogenesis of lymphoma. We report a rare case of DLBCL in a patient who had a metallic implant in the proximal tibia for 15 months. Radiologic studies, including US and MRI, showed disproportionately large extraosseous soft-tissue mass and bone marrow involvement without prominent bone destruction. Multiple complications are associated with metallic implants, and misdiagnosis may lead to inappropriate treatment. Therefore, distinguishing lymphomas caused by a metallic implant-induced chronic inflammatory condition from other periprosthetic benign lesions and malignant soft tissue masses is challenging, but it is critical.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.2
• /
• pp.177-184
• /
• 2024

In the situation of increasing data at fast speed, we use all kinds of complex ensemble and deep learning algorithms to get the highest accuracy. It's sometimes questionable how these models predict, classify, recognize, and track unknown data. Accomplishing this technique and more has been and would be the goal of intensive research and development in the data science community. A variety of reasons, such as lack of data, imbalanced data, biased data can impact the decision rendered by the learning models. Many models are gaining traction for such interpretations. Now, LIME and SHAP are commonly used, in which are two state of the art open source explainable techniques. However, their outputs represent some different results. In this context, this study introduces a coupling technique of LIME and Shap, and demonstrates analysis possibilities on the decisions made by LightGBM and Keras models in classifying a transaction for fraudulence on the IEEE CIS dataset.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.3
• /
• pp.130-139
• /
• 2024

Artificial intelligence models are being used to detect facility anomalies using physics data such as vibration, current, and temperature for predictive maintenance in the manufacturing industry. Since the types of facility anomalies, such as facility defects and failures, anomaly detection methods using autoencoder-based unsupervised learning models have been mainly applied. Normal or abnormal facility conditions can be effectively classified using the reconstruction error of the autoencoder, but there is a limit to identifying facility anomalies specifically. When facility anomalies such as unbalance, misalignment, and looseness occur, the facility vibration frequency shows a pattern different from the normal state in a specific frequency range. This paper presents an N-segmentation anomaly detection method that performs anomaly detection by dividing the entire vibration frequency range into N regions. Experiments on nine kinds of anomaly data with different frequencies and amplitudes using vibration data from a compressor showed better performance when N-segmentation was applied. The proposed method helps materialize them after detecting facility anomalies.

• Economic and Environmental Geology
• /
• v.38 no.6 s.175
• /
• pp.675-687
• /
• 2005

The rocks of the five storied stone pagoda in the Jeongrimsaji temple site are 149 materials in total with porphyritic biotite granodiorite. They include pegmatite veinlet, basic xenolith and evenly developed plagioclase porphyry. This stone pagoda has comparably small fracture and cracks which are farmed in the times of rock properties, but surface exfoliation and granular decomposition are in process actively since the rocks are generally weakened from the influence of air contaminants and acid rain. Structural instability of constituting rocks in the 4th roof materials are observed to occur from distortion and tilt. Such instability is judged to threat stability of the upper part of the stone pagoda. Also, chemical weathering is operating even more as the contaminants, ferro-manganese hydroxides eluted from water-rock interaction on the rock surface. Most of the rock surface is covered with yellowish brown, dark black and light gray contaminants, and especially occur in the lower part of the roof rocks on each floor. The roof underpinning rocks are severe in surface pigmentation from manganese hydroxides and light gray contaminants. The surface of rocks lives bacteria. algae, lichen, or moss and diverse productions in colors of light gray, dark Bray and dark green. Grayish white crustose lichen grows thick on the surface with darkly discolored by fungi and algae in the first stage on basement rocks, and weeds grows wild on the upper part of each roof rocks. This stone pagoda must closely observe the movements of the upper part rock materials through minute safety diagnosis and long term monitoring for structural stability. Especially since the surface discoloration of rocks and pigmentation of secondary contaminants are severe, establishment of general restoration and scientific conservation treatment are necessary through more detailed study for this stone pagoda.

• Korean Journal of Social Welfare
• /
• v.64 no.1
• /
• pp.199-223
• /
• 2012

The purpose of this study is to clarify the mechanism and essence of problems by understanding the whole structure of the complicated problems that exist in the social welfare field with DEMATEL method, one of structural models. This paper consists of (1) What kind of social welfare problems exist in the community that is related to welfare? (2) What kind of thoughts do people who work in social welfare field have related to these problems? (3) Are there any differences in structure of thoughts among social welfare civil servants who take charge of planning and dividing budgets for community welfare, social workers who provide services personally and civic activists who criticize and keep watch on behalf of civilians? In order to achieve the purpose of this study, data were collected in Busan Busanjingu and the survey was conducted from the year of 2005 when community welfare plan was first established up to now. The major structural problems of the community welfare of the Pusan Jin-gu, Korea, are: 1) welfare budget allocation procedure is not logical, 2) the outskirts of the Pusan Jin-gu are isolated as poor areas, 3) geographic imbalance is severe among communities, and 4) the social welfare response system to support future population structure needs to be more developed. All of these problems are the fundamental origin to the social resource disparity within communities. The major problems of the community social welfare in Pusan Jin-gu, Korea were recognized by different perspective in terms of professional career such as social welfare civil servants, social workers, and civic activists. Majority of the social welfare civil servants thought "severe geographic imbalance"; majority of the social workers believed "lack of the social welfare response system to support the structure of the population in the future" and "disparity in social resources within the communities"; and majority of the civic activists said "limitation for understanding various social welfare needs because of short term need assessments" as main issues of the community social welfare. It seems that this paper is able to be used as a framework to establish community welfare plans and individual programs in Busan Busanjingu.