• Journal of the korean academy of Pediatric Dentistry
• /
• v.50 no.3
• /
• pp.263-276
• /
• 2023

The purpose of this study was to evaluate the performance of a model using You Only Look Once (YOLO) for object detection of proximal caries in periapical radiographs of children. A total of 2016 periapical radiographs in primary dentition were selected from the M6 database as a learning material group, of which 1143 were labeled as proximal caries by an experienced dentist using an annotation tool. After converting the annotations into a training dataset, YOLO was trained on the dataset using a single convolutional neural network (CNN) model. Accuracy, recall, specificity, precision, negative predictive value (NPV), F1-score, Precision-Recall curve, and AP (area under curve) were calculated for evaluation of the object detection model's performance in the 187 test datasets. The results showed that the CNN-based object detection model performed well in detecting proximal caries, with a diagnostic accuracy of 0.95, a recall of 0.94, a specificity of 0.97, a precision of 0.82, a NPV of 0.96, and an F1-score of 0.81. The AP was 0.83. This model could be a valuable tool for dentists in detecting carious lesions in periapical radiographs.

• Journal of the Korean Society for information Management
• /
• v.39 no.1
• /
• pp.91-117
• /
• 2022

The number of depressed patients in Korea and around the world is rapidly increasing every year. However, most of the mentally ill patients are not aware that they are suffering from the disease, so adequate treatment is not being performed. If depressive symptoms are neglected, it can lead to suicide, anxiety, and other psychological problems. Therefore, early detection and treatment of depression are very important in improving mental health. To improve this problem, this study presented a deep learning-based depression tendency model using Korean social media text. After collecting data from Naver KonwledgeiN, Naver Blog, Hidoc, and Twitter, DSM-5 major depressive disorder diagnosis criteria were used to classify and annotate classes according to the number of depressive symptoms. Afterwards, TF-IDF analysis and simultaneous word analysis were performed to examine the characteristics of each class of the corpus constructed. In addition, word embedding, dictionary-based sentiment analysis, and LDA topic modeling were performed to generate a depression tendency classification model using various text features. Through this, the embedded text, sentiment score, and topic number for each document were calculated and used as text features. As a result, it was confirmed that the highest accuracy rate of 83.28% was achieved when the depression tendency was classified based on the KorBERT algorithm by combining both the emotional score and the topic of the document with the embedded text. This study establishes a classification model for Korean depression trends with improved performance using various text features, and detects potential depressive patients early among Korean online community users, enabling rapid treatment and prevention, thereby enabling the mental health of Korean society. It is significant in that it can help in promotion.

• Journal of Intelligence and Information Systems
• /
• v.15 no.2
• /
• pp.49-59
• /
• 2009

Contents-based image retrieval methods are in general more objective and effective than text-based image retrieval algorithms since they use color and texture in search and avoid annotating all images for search. SIM(Self-organizing Image browsing Map) is one of contents-based image retrieval algorithms that uses only browsable mapping results obtained by SOM(Self Organizing Map). However, SOM may have an error in selecting the right BMU in learning phase if there are similar nodes with distorted color information due to the intensity of light or objects' movements in the image. Such images may be mapped into other grouping nodes thus the search rate could be decreased by this effect. In this paper, we propose an improved SIM that uses HSV color model in extracting image features with color quantization. In order to avoid unexpected learning error mentioned above, our SOM consists of two layers. In learning phase, SOM layer 1 has the color feature vectors as input. After learning SOM Layer 1, the connection weights of this layer become the input of SOM Layer 2 and re-learning occurs. With this multi-layered SOM learning, we can avoid mapping errors among similar nodes of different color information. In search, we put the query image vector into SOM layer 2 and select nodes of SOM layer 1 that connects with chosen BMU of SOM layer 2. In experiment, we verified that the proposed SIM was better than the original SIM and avoid mapping error effectively.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2012.02a
• /
• pp.202-202
• /
• 2012

유연성 투명 전도막은 현대 전자산업의 발전에 있어 필수적인 부품소재로서, 가시광선의 투과율이 80% 이상이고 면저항이 $100{\Omega}/sq.$ 전후이며 휘거나 접히고 나아가 두루마리의 형태로도 응용이 가능한 소재를 일컫는다. 이러한 유연성 투명 전도막은 차세대 정보디스플레이 산업 및 유비쿼터스 사회의 중심이 되는 유연성 디스플레이, 터치패널, 발광다이오드, 태양전지 등 매우 다양한 분야에 응용이 기대된다. 이러한 이유로 고 신뢰성 유연성 투명 전도막 개발기술은 차세대 산업에 있어서의 핵심기술로 인식되고 있다. 현재로서는 인듐 주석 산화물(indium tin oxide; ITO) 및 전도성 유기고분자를 사용하여 투명 전도막을 제조하고 있으나, ITO 박막의 경우 인듐 자원의 고갈로 인한 가격상승 및 기판과의 낮은 접착력, 열팽창계수의 차이로 인한 공정상의 문제, 산화물 특유의 취성으로 인한 유연소자로서의 내구성 저하 등의 문제가 제기되고 있다. 전도성 유기고분자의 경우는 낮은 전기전도도와 기계적강도, 유기용매 처리 등의 문제점이 지적되고 있다. 따라서 높은 전기전도도와 투광도 뿐만 아니라 유연성을 지니는 재료의 개발이 요구되고 있는 실정이다. 최근 이러한 재료로서 그래핀(graphene)과 탄소나노튜브(carbon nanotube; CNT)를 중심으로 하는 탄소나노재료가 주목받고 있으며 많은 연구가 활발히 진행되고 있다. 본 연구에서는 열화학기상증착법(thermal vapor deposition; TCVD)으로 합성된 그래핀 및 CNT를 이용하여 탄소나노재료 복합체 기반의 유연성 투명 전도막을 제작하고 그 특성을 평가하였다. 그래핀과 CNT합성을 위한 기판으로는 각각 300 nm 두께의 니켈과 1 nm 철이 증착된 실리콘 웨이퍼를 이용하였으며, 원료가스로는 메탄(CH4)과 아세틸렌(C2H2)등의 탄화수소가스를 이용하였다. 그래핀의 경우 원료가스의 유량, 합성온도, 냉각속도를 변경하여 대면적으로 두께균일도가 높은 그래핀을 합성하였으며, CNT의 경우 합성시간을 변수로 길이 제어합성을 도모하였다. 합성된 그래핀은 식각공정을, CNT는 스프레이 증착공정을 통해 고분자 기판(polyethylene terephthalate; PET) 위에 순차적으로 전사 및 증착하여 탄소나노재료 복합체 기반의 유연성 투명 전도막을 제작하였다. 제작된 탄소나노재료 복합체 기반의 유연성 투명 전도막은 물리적 과부하를 받았을 때 발생할 수 있는 유연성 투명 전도막의 구조적결함에 기인하는 전도성 저하를 보상하는 특징이 있어, 그래핀과 탄소나노튜브 각각으로 제조된 유연성 투명 전도막보다 물리적인 하중이 반복적으로 인가되었을 때 내구성이 향상되는 효과가 있다. 40% 스트레인을 반복적으로 인가하였을 때 그래핀 투명 전도막은 20 사이클 이후에 면저항이 $1-2{\Omega}/sq.$에서 $15{\Omega}/sq.$ 이상으로 급증한 반면 그래핀-CNT 복합체 투명 전도막은 30사이클까지 $1-2{\Omega}/sq.$ 정도의 면저항을 유지하였다.

• Journal of KIISE:Databases
• /
• v.32 no.4
• /
• pp.383-393
• /
• 2005

Retrieval of images from image databases by spatial relationship can be effectively performed through visual interface systems. In these systems, the representation of image with 2D strings, which are derived from symbolic projections, provides an efficient and natural way to construct image index and is also an ideal representation for the visual query. With this approach, retrieval is reduced to matching two symbolic strings. However, using 2D-string representations, spatial relationships between the objects in the image might not be exactly specified. Ambiguities arise for the retrieval of images of 3D scenes. In order to remove ambiguous description of object spatial relationships, in this paper, images are referred by considering spatial relationships using the spatial location algebra for the 3D image scene. Also, we remove the repetitive spatial relationships using the several reduction rules. A reduction mechanism using these rules can be used in query processing systems that retrieve images by content. This could give better precision and flexibility in image retrieval.

• Journal of the Korean Electrochemical Society
• /
• v.21 no.3
• /
• pp.55-60
• /
• 2018

The demand for LIBs with higher energy densities has increased continuously because the emergence of wider and more challenging applications including HEV and EV has became imperative. However, in the case of anode material, graphite is insufficient to meet this need. To meet such demand, several type of negative electrode materials like silicon, tin, SiO, and transition metal oxide have been investigated for the advanced lithium secondary batteries. Recently, lithium vanadium oxide, which has a layered structure, is assumed as one of the promising anode material as alternative of graphite. This material shows a high volumetric capacity, which is 1.5 times higher than that of graphite. However, relative low electrical conductivity and particle fracture, which results in the electrolyte decomposition and loss of electric contact between electrode, induce rapid capacity decay. In this report, we investigated the effect of electrolyte additive on the electrochemical characteristics of lithium vanadium oxide.

• Journal of Life Science
• /
• v.14 no.6 s.67
• /
• pp.997-1002
• /
• 2004

This paper deals with the WASPIFA (Web-based Assistant System for Protein-protein Interaction and Function Analysis) system that can provide the comprehensive information on Protein-protein interaction and function concerned with function analysis. Different from existing systems for protein function and protein-protein interaction analysis, which provide fragmentary information restricted to specific field, our system furnishes end-user with comprehensive and synthetic information on the input sequence to be analyzed, including function and annotation information, domain information, and interaction relationship information. The synthetic information that our system contains as local databases has been extracted from many resources related to function, annotation, motif and domain by various pre-processing. Employing our system, end-users can evaluate and judge the synthetic results to do protein interaction and function analysis effectively. In addition, the WASPIFA system is equipped with automatic system management and data update function that facilitates system manager to maintain and manage it efficiently.

• Bioinformatics and Biosystems
• /
• v.1 no.1
• /
• pp.38-45
• /
• 2006

We present a client-server system architecture for inferring genetic interaction networks based on Bayesian networks. It is typical to take tens of hours when genome-wide large-scale genetic interaction networks are inferred in the form of Bayesian networks. To deal with this situation, batch-style distributed system architectures are preferable to interactive standalone architectures. Thus, we have implemented a loosely coupled client-server system for network inference and user interface. The network inference consists of two stages. Firstly, the proposed method divides a whole gene set into overlapped modules, based on biological annotations and expression data together. Secondly, it infers Bayesian networks for each module, and integrates the learned subnetworks to a global network through common genes across the modules.

• Journal of Korea Multimedia Society
• /
• v.8 no.4
• /
• pp.450-460
• /
• 2005

Today, multimedia information is used on the internet and various social areas by rapid development of computer and communication technology. Therefor, the usage is growing dramatically. Multimedia information analysis system is basically based on text. So, there are many difficult problems like expressing ambiguity of multimedia information, excessive burden of works in appending notes and a lack of objectivity. In this study, we suggest a method which uses color and shape information of multimedia image partitions efficiently analyze a large amount of multimedia information. Partitions use field growth and union method. To extract color information, we use distinctive information which matches with a representative color from converting process from RGB(Red Green Blue) to HSI(Hue Saturation Intensity). Also, we use IMI(Improved Moment Invariants) which target to only outline pixels of an object and execute computing as shape information.

• The KIPS Transactions:PartC
• /
• v.13C no.5 s.108
• /
• pp.607-612
• /
• 2006

Universal Mobile Telecommunications System (UMTS) and Wireless Local Area Network (WLAN) have been developed independently. Then, many researchers have studied UMTS-WLAN interworking architecture for the efficiency. However, the transmission capacity difference of two networks causes the transmission quality degradation. Therefore, this paper proposes a UMTS-WLAN interworking architecture for Quality of Service (QoS). The proposed architecture is based on tight coupling and dynamically guarantees QoS by the mobility prediction method. The proposed architecture is simulated by ns-2. Performance experimental results show that the proposed architecture reduces the handover dropping probability comparing with the existing method and enhances the amount of receiving packets comparing with the method without guaranteeing QoS.