• Journal of Internet Computing and Services
• /
• v.25 no.2
• /
• pp.21-28
• /
• 2024

Radar is an essential sensor component in autonomous vehicles, and the market for radar applications in this context is steadily expanding with a growing variety of products. In this study, we aimed to enhance the stability and performance of radar systems by developing and evaluating a radar performance prediction model that can predict radar defects. We selected seven machine learning and deep learning algorithms and trained the model with a total of 49 input data types. Ultimately, when we employed an ensemble of 17 models, it exhibited the highest performance. We anticipate that these research findings will assist in predicting product defects at the production stage, thereby maximizing production yield and minimizing the costs associated with defective products.

• Journal of Digital Contents Society
• /
• v.14 no.3
• /
• pp.349-356
• /
• 2013

Products of Wi-Fi devices in recent years offer higher throughput and have longer signal coverage which also bring unnecessary signal interference to neighboring wireless networks, and result in decrease of network throughput. Signal interference is an inevitable problem because of the broadcast nature of wireless transmissions. However it could be optimized by reducing signal coverage of wireless devices. On the other hand, smaller signal coverage also means lower transmission power and lower data throughput. Therefore, in this paper, we analyze the relationship among signal strength, coverage and interference of Wi-Fi networks, and as a tradeoff between transmission power and data throughput, we propose a range-aware Wi-Fi network scheme which controls transmission power according to positions and RSSI(Received Signal Strength Indication) of Wi-Fi devices and analyze the efficiency of the proposed scheme by simulation.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.14 no.4
• /
• pp.86-93
• /
• 2010

The wear of railway track affects loss of rough ride, noise or vibration of train and traveling safety. Moreover as the track is worn away, this promotes destruction of structural mechanism of rail track which can bring about increasing of rail track maintenance cost drastically. For this reason, it is very important and interested research subject to design railway track structure and to analyse train movement mechanism based on systematic analysis of the reasons causing rail wear possible in real field. In this research, for the efficient maintenance, Life Cycle Performance of rail track and maintenance characteristics are computed considering some track components such as track type, contracting type, sleeper type and roadbed type. Time - Wear probabilistic distribution relationship as well as multiple regression analysis based on time, curvature and wear data are computed to predict the service life remainder of railway track and to be adapted to safety assessment.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.21-24
• /
• 2020

대용량의 데이터를 시각적 요소를 활용하여 눈으로 볼 수 있도록 하는 데이터 시각화에 대한 관심이 꾸준히 증가하고 있다. 데이터 시각화는 데이터의 전처리를 거쳐 차원 축소를 하여 데이터의 분포를 시각적으로 확인할 수 있다. 공개된 데이터 셋은 캐글(kaggle), 아마존 AWS 데이터셋(Amazon AWS datasets), UC 얼바인 머신러닝 저장소(UC irvine machine learning repository)등 다양하다. 본 논문에서는 UCI의 화학 가스의 데이터셋을 이용하여 딥러닝을 이용하여 다양한 환경 및 조건에서의 학습을 통한 데이터분석 및 학습 결과가 좋을 경우와 그렇지 않을 경우의 마지막 레이어의 특징 벡터를 시각화하여 직관적인 결과를 확인 가능 하도록 하였다. 또한 다차원 입력 데이터를 시각화 함으로써 시각화 된 결과가 딥러닝의 학습결과와 연관이 있는지를 확인 한다.

• Journal of Korea Water Resources Association
• /
• v.51 no.4
• /
• pp.335-346
• /
• 2018

A vast amount of riverine spatial dataset have recently become available, which include hydrodynamic and morphological survey data by advanced instrumentations such as ADCP (Acoustic Doppler Current Profiler), transect measurements obtained through building various river basic plans, riverine environmental and ecological data, optical images using UAVs, river facilities like multi-purposed weir and hydrophilic sectors. In this regard, a standardized data model has been subsequently required in order to efficiently store, manage, and share riverine spatial dataset. Given that riverine spatial dataset such as river facility, transect measurement, time-varying observed data should be synthetically managed along specified river network, conventional data model showed a tendency to maintain them individually in a form of separate layer corresponding to each theme, which can miss their spatial relationship, thereby resulting in inefficiency to derive synthetic information. Moreover, the data model had to be significantly modified to ingest newly produced data and hampered efficient searches for specific conditions. To avoid such drawbacks for layer-based data model, this research proposed a relational data model in conjunction with river network which could be a backbone to relate additional spatial dataset such as flowline, river facility, transect measurement and surveyed dataset. The new data model contains flexibility to minimize changes of its structure when it deals with any multi-dimensional river data, and assigned reach code for multiple river segments delineated from a river. To realize the newly developed data model, Seom river was applied, where geographic informations related with national and local rivers are available.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.32 no.4_1
• /
• pp.311-318
• /
• 2014

The data of buildings and structures take over large portions of the mapping database with large numbers. Furthermore, those shapes and attributes of building data continuously change over time. Due to those factors, the efficient methodology of updating database for following the most recent data become necessarily. This study has purposed on extracting needed data, which has been changed, by using overlaying analysis of new and old dataset, during updating processes. Following to procedures, we firstly searched for matching pairs of objects from each dataset, and defined the classification algorithm for building updating cases by comparing; those of shape updating cases are divided into 8 cases, while those of attribute updating cases are divided into 4 cases. Also, two updated dataset are set to be automatically saved. For the study, we selected few guidelines; the layer of digital topographic map 1:5000 for the targeted updating data, the building layer of Korea Address Information System map for the reference data, as well as build-up areas in Gwanak-gu, Seoul for the test area. The result of study updated 82.1% in shape and 34.5% in attribute building objects among all.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.7
• /
• pp.337-352
• /
• 2017

Clone-and-own reuse is an approach to creating new software variants by copying and modifying existing software products. A family of legacy software products developed by clone-and-own reuse often requires high maintenance cost and tends to be error-prone due to patch-ups without refactoring and structural degradation. To overcome these problems, many organizations that have used clone-and-own reuse now want to migrate their legacy products to software product line (SPL) for more systematic reuse and management of software asset. However, with most of existing methods, variation points are embedded directly into design and code rather than modeled and managed separately; variation points are not created ("engineered") systematically based on a variability model. This approach causes the following problems: it is difficult to understand the relationships between variation points, thus it is hard to maintain such code and the asset tends to become error-prone as it evolves. Also, when SPL evolves, design/code assets tend to be modified directly in an ad-hoc manner rather than engineered systematically with appropriate refactoring. To address these problems, we propose a feature-oriented method for extracting a SPL asset from a family of legacy applications. With the approach, we identify and model variation points and their relationships in a feature model separate from implementation, and then extract and manage a SPL asset from legacy applications based on the feature model. We have applied the method to a family of legacy Notepad++ products and demonstrated the feasibility of the method.

• The KIPS Transactions:PartD
• /
• v.18D no.1
• /
• pp.57-66
• /
• 2011

Recently, the necessity of new methods of spatial data integration and analysis in CRM has been increased since it is acknowledged that about eighty percent of all data stored in corporate databases has a spatial component. But conventional CRM systems are either incapable of managing spatial data or are not user-friendly when doing so. This paper has designed and implemented spatially-enabled integration management system that can manage consistently both enterprise and spatial data through a legacy CRM system and object-oriented database and additionally support spatial analysis and map visualization for a gCRM. Through implementation, it is demonstrated that the proposed system can facilitate effectively spatial data management and analysis in a legacy CRM system.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.15-30
• /
• 2023

Recently, generative models based on the Transformer architecture, such as ChatGPT, have been gaining significant attention. The Transformer architecture has been applied to various neural network models, including Google's BERT(Bidirectional Encoder Representations from Transformers) sentence generation model. In this paper, a method is proposed to create a text binary classification model for determining whether a comment on Korean movie review is positive or negative. To accomplish this, a pre-trained multilingual BERT sentence generation model is fine-tuned and transfer learned using a new Korean training dataset. To achieve this, a pre-trained BERT-Base model for multilingual sentence generation with 104 languages, 12 layers, 768 hidden, 12 attention heads, and 110M parameters is used. To change the pre-trained BERT-Base model into a text classification model, the input and output layers were fine-tuned, resulting in the creation of a new model with 178 million parameters. Using the fine-tuned model, with a maximum word count of 128, a batch size of 16, and 5 epochs, transfer learning is conducted with 10,000 training data and 5,000 testing data. A text sentiment binary classification model for Korean movie review with an accuracy of 0.9582, a loss of 0.1177, and an F1 score of 0.81 has been created. As a result of performing transfer learning with a dataset five times larger, a model with an accuracy of 0.9562, a loss of 0.1202, and an F1 score of 0.86 has been generated.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2010.10a
• /
• pp.10-12
• /
• 2010

환경 민감 지도는 해양 유출유 사고 시 효율적이고 신속한 방제 업무를 위한 유용한 정보이다. 그러나 해상교통 및 안전 분야 종사자는 전통적으로 해도 및 전자해도 사용에 익숙하여 현 환경민감지도의 색상 및 심볼의 낮은 친숙도가 지적된 바 있다. 본 연구에서는 전자해도의 제작 표준에 해당하는 수로데이터 표준모델에 따라 환경민감지도 데이터를 제작하고 전자해도 표현방법에 따라 표시 하였다. 세부 연구 내용으로 환경민감정보에 대한 객체와 속성, 표현 심볼 및 색상에 대해 정의하고, 기존 환경민감정보를 내부 전자해도 포맷으로 변환하였다. 다음으로 내부 전자해도 데이터를 전자해도 표현방법에 따라 전자해도 레이어에 중첩시켜 그 결과를 확인 하였다.