• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1706-1725
• /
• 2024

The unique U-shaped structure of U-Net network makes it achieve good performance in image segmentation. This network is a lightweight network with a small number of parameters for small image segmentation datasets. However, when the medical image to be segmented contains a lot of detailed information, the segmentation results cannot fully meet the actual requirements. In order to achieve higher accuracy of medical image segmentation, a novel improved U-Net network architecture called multi-scale encoder-decoder U-Net+ (MEDU-Net+) is proposed in this paper. We design the GoogLeNet for achieving more information at the encoder of the proposed MEDU-Net+, and present the multi-scale feature extraction for fusing semantic information of different scales in the encoder and decoder. Meanwhile, we also introduce the layer-by-layer skip connection to connect the information of each layer, so that there is no need to encode the last layer and return the information. The proposed MEDU-Net+ divides the unknown depth network into each part of deconvolution layer to replace the direct connection of the encoder and decoder in U-Net. In addition, a new combined loss function is proposed to extract more edge information by combining the advantages of the generalized dice and the focal loss functions. Finally, we validate our proposed MEDU-Net+ MEDU-Net+ and other classic medical image segmentation networks on three medical image datasets. The experimental results show that our proposed MEDU-Net+ has prominent superior performance compared with other medical image segmentation networks.

• Journal of Internet Computing and Services
• /
• v.13 no.2
• /
• pp.99-108
• /
• 2012

Many methods had been developed to improve the accuracy of extracting information from a vast amount of data. This paper combined a number of natural language processing methods such as NER (named entity recognition), sentence extraction, and part of speech tagging to carry out text analysis. The data source is comprised of texts obtained from the web using a domain-specific data extraction agent. A framework for the extraction of information from unstructured data was developed using the aforementioned natural language processing methods. We simulated the performance of our work in the extraction and analysis of texts for the detection of organizational structures. Simulation shows that our study outperformed other NER classifiers such as MUC and CoNLL on information extraction.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.735-740
• /
• 2006

유비쿼터스 가정환경에서 서비스를 제공하기 위한 다양한 장치들은 각기 고유한 인터페이스를 가진다. 사용자는 이 장치들을 제어하기 위해서 각각 다른 인터페이스에 익숙해야 하며, 결국 장치 수만큼의 인터페이스를 다루어야 한다. 이와 같은 불편을 해소하기 위해서는 하나의 입력 장치로 여러 장치들을 조작하는 사용자 인터페이스가 필요하다. 특히 유비쿼터스 가정환경에서는 다양한 장치들의 상태 및 기능 등이 동적으로 변하고, 장치가 설정되는 환경도 일정하지 않기 때문에 사용자 중심의 유비쿼터스 환경을 제공하기 위해서는 다양한 인터페이스를 통합할 필요가 있다. 사용자가 비슷하게 인지하는 이종 장치들의 기능을 통합하여 사용자 인터페이스의 동일한 입력으로 매핑한다면 사용자의 부담을 줄일 수 있을 것이다. 본 논문에서는 유비쿼터스 가정환경의 다양한 장비들과 인터페이스 사이의 입출력 관계를 분석하여 시맨틱 네트워크로 모델링하는 방법을 제안한다. 각 장치의 상태와 기능을 시맨틱 네트워크로 정의하고, 노드나 엣지 사이의 유사도를 평가하여 장치와 사용자 인터페이스 사이를 자동으로 매핑한다. 제안하는 방법을 가정환경 입출력장치에 적용하고, 입출력 매핑을 시뮬레이션하는 환경을 구현하여 유용성을 검증한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.855-870
• /
• 2020

Windows are key components of building facades. Detecting windows, crucial to 3D semantic reconstruction and scene parsing, is a challenging task in computer vision. Early methods try to solve window detection by using hand-crafted features and traditional classifiers. However, these methods are unable to handle the diversity of window instances in real scenes and suffer from heavy computational costs. Recently, convolutional neural networks based object detection algorithms attract much attention due to their good performances. Unfortunately, directly training them for challenging window detection cannot achieve satisfying results. In this paper, we propose an approach for window detection. It involves an improved Faster R-CNN architecture for window detection, featuring in a window region proposal network, an RoI feature fusion and a context enhancement module. Besides, a post optimization process is designed by the regular distribution of windows to refine detection results obtained by the improved deep architecture. Furthermore, we present a newly collected dataset which is the largest one for window detection in real street scenes to date. Experimental results on both existing datasets and the new dataset show that the proposed method has outstanding performance.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.447-450
• /
• 2003

In this research, we propose an automatic knowledge acquisition and composite knowledge expression mechanism based on machine learning and relational database. Most of traditional approaches to develop a knowledge base and inference engine of expert systems were based on IF-THEN rules, AND-OR graph, Semantic networks, and Frame separately. However, there are some limitations such as automatic knowledge acquisition, complicate knowledge expression, expansibility of knowledge base, speed of inference, and hierarchies among rules. To overcome these limitations, many of researchers tried to develop an automatic knowledge acquisition, composite knowledge expression, and fast inference method. As a result, the adaptability of the expert systems was improved rapidly. Nonetheless, they didn't suggest a hybrid and generalized solution to support the entire process of development of expert systems. Our proposed mechanism has five advantages empirically. First, it could extract the specific domain knowledge from incomplete database based on machine learning algorithm. Second, this mechanism could reduce the number of rules efficiently according to the rule extraction mechanism used in machine learning. Third, our proposed mechanism could expand the knowledge base unlimitedly by using relational database. Fourth, the backward inference engine developed in this study, could manipulate the knowledge base stored in relational database rapidly. Therefore, the speed of inference is faster than traditional text -oriented inference mechanism. Fifth, our composite knowledge expression mechanism could reflect the traditional knowledge expression method such as IF-THEN rules, AND-OR graph, and Relationship matrix simultaneously. To validate the inference ability of our system, a real data set was adopted from a clinical diagnosis classifying the dermatology disease.

• Journal of Intelligence and Information Systems
• /
• v.5 no.1
• /
• pp.13-34
• /
• 1999

Building a knowledge base effectively has been an important research area in the expert systems field. A variety of approaches have been studied including rules, semantic networks, and frames to represent the knowledge base for expert systems. As the size and complexity of the knowledge base get larger and more complicated, the integration of knowledge based with database technology cecomes more important to process the large amount of data. However, relational database management systems show many limitations in handing the complicated human knowledge due to its simple two dimensional table structure. In this paper, we propose Object-Oriented Knowledge Store (OOKS), a knowledge base model on the basis of a frame sturcture using an object-oriented database. In the proposed model, managing rules for inferencing and facts about objects in one uniform structure, knowledge and data can be tightly coupled and the performance of reasoning can be improved. For building a knowledge base, a knowledge script file representing rules and facts is used and the script file is transferred into a frame structure in database systems. Specifically, designing a frame structure in the database model as it is, it can facilitate management and utilization of knowledge in expert systems. To test the appropriateness of the proposed knowledge base model, a prototype system has been developed using a commercial ODBMS called ObjectStore and C++ programming language.

• Journal of Advanced Navigation Technology
• /
• v.24 no.2
• /
• pp.148-154
• /
• 2020

Wrinkles are one of the main features of skin aging. Conventional image processing-based wrinkle detection is difficult to effectively cope with various skin images. In particular, Wrinkle extraction performance is significantly decreased when the wrinkles are not strong and similar to the surrounding skin. In this paper, deep learning is applied to extract wrinkles from microscopic skin images. In general, the microscope image is equipped with a wide-angle lens, so the brightness at the boundary area of the image is dark. In this paper, to solve this problem, the brightness of the skin image is estimated and corrected. In addition, We apply the structure of semantic segmentation network suitable for wrinkle extraction. The proposed method obtained an accuracy of 99.6% in test experiments on skin images collected in our laboratory.

• International Journal of Advanced Culture Technology
• /
• v.8 no.3
• /
• pp.223-230
• /
• 2020

Companies have made an investment of cost and time to optimize processing of a new business model in a cloud environment, applying collaboration technology utilizing business processes in a social network. The collaborative processing method changed from traditional BPM to the cloud and a mobile cloud environment. We proposed a collaborative system for operating processes in social networks using MOXMDR-DAI+ (eXtended Metadata Registry-Data Access & Integration based multimedia ontology). The system operating cloud-based collaborative processes in application of MOXMDR-DAI+, which was suitable for data interoperation. MOXMDR-DAI+ applied to this system was an agent effectively supporting access and integration between multimedia content metadata schema and instance, which were necessary for data interoperation, of individual local system in the cloud environment, operating collaborative processes in the social network. In operating the social network-based collaborative processes, there occurred heterogeneousness such as schema structure and semantic collision due to queries in the processes and unit conversion between instances. It aimed to solve the occurrence of heterogeneousness in the process of metadata mapping using MOXMDR-DAI+ in the system. The system proposed in this study can visualize business processes. And it makes it easier to operate the collaboration process through mobile support. Real-time status monitoring of the operation process is possible through the dashboard, and it is possible to perform a collaborative process through expert search using a community in a social network environment.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.6
• /
• pp.229-234
• /
• 2014

As association between sensor networks that collect environmental information by using numberous sensor nodes and smartphones that are equipped with various sensors, many applications understanding users' context have been developed to interact users and their environments. Collected data should be stored with XML formatted metadata containing semantic information to share the collected data. In case of distance based clustering schemes, the efficiency of data collection decreases because metadata files are extended and changed as the purpose of each system developer. In this paper, we proposed a clustering scheme considering the structural similarity of metadata to reduce clustering construction time and improve the similarity of metadata among member nodes in a cluster.

• Journal of Communications and Networks
• /
• v.13 no.6
• /
• pp.567-582
• /
• 2011

The growing popularity of the Internet has caused the size and complexity of communications and computing systems to greatly increase in recent years. To alleviate this increased management complexity, novel autonomic management architectures have emerged, in which many automated components manage the network's resources in a distributed fashion. However, in order to achieve effective collaboration between these management components, they need to be able to efficiently exchange information in a timely fashion. In this article, we propose a context dissemination framework that addresses this problem. To achieve scalability, the management components are structured in a hierarchy. The framework facilitates the aggregation and translation of information as it is propagated through the hierarchy. Additionally, by way of semantics, context is filtered based on meaning and is disseminated intelligently according to dynamically changing context requirements. This significantly reduces the exchange of superfluous context and thus further increases scalability. The large size of modern federated cloud computing infrastructures, makes the presented context dissemination framework ideally suited to improve their management efficiency and scalability. The specific context requirements for the management of a cloud data center are identified, and our context dissemination approach is applied to it. Additionally, an extensive evaluation of the framework in a large-scale cloud data center scenario was performed in order to characterize the benefits of our approach, in terms of scalability and reasoning time.