• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.10
• /
• pp.5179-5196
• /
• 2019

To explore an effective non-invasion medical imaging diagnostics approach for hepatocellular carcinoma (HCC), we propose a method based on adopting the multiple technologies with the multi-parametric data fusion, transfer learning, and multi-scale deep feature extraction. Firstly, to make full use of complementary and enhancing the contribution of different modalities viz. multi-parametric MRI images in the lesion diagnosis, we propose a data-level fusion strategy. Secondly, based on the fusion data as the input, the multi-scale residual neural network with SPP (Spatial Pyramid Pooling) is utilized for the discriminative feature representation learning. Thirdly, to mitigate the impact of the lack of training samples, we do the pre-training of the proposed multi-scale residual neural network model on the natural image dataset and the fine-tuning with the chosen multi-parametric MRI images as complementary data. The comparative experiment results on the dataset from the clinical cases show that our proposed approach by employing the multiple strategies achieves the highest accuracy of 0.847±0.023 in the classification problem on the HCC differentiation. In the problem of discriminating the HCC lesion from the non-tumor area, we achieve a good performance with accuracy, sensitivity, specificity and AUC (area under the ROC curve) being 0.981±0.002, 0.981±0.002, 0.991±0.007 and 0.999±0.0008, respectively.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.2843-2845
• /
• 2000

A lane detection based on a road model or feature all need correct acquirement of information on the lane in a image, It is inefficient to implement a lane detection algorithm through the full range of a image when being applied to a real road in real time because of the calculating time. This paper defines two searching range of detecting lane in a road, First is searching mode that is searching the lane without any prior information of a road, Second is recognition mode, which is able to reduce the size and change the position of a searching range by predicting the position of a lane through the acquired information in a previous frame. It is allow to extract accurately and efficiently the edge candidates points of a lane as not conducting an unnecessary searching. By means of removing the perspective effect of the edge candidate points which are acquired by using the inverse perspective transformation, we transform the edge candidate information in the Image Coordinate System(ICS) into the plane-view image in the World Coordinate System(WCS). We define linear approximation filter and remove the fault edge candidate points by using it This paper aims to approximate more correctly the lane of an actual road by applying the least-mean square method with the fault-removed edge information for curve fitting.

• The KIPS Transactions:PartD
• /
• v.8D no.6
• /
• pp.715-722
• /
• 2001

In recent years, we recognize a new paradigm in the development process：From object oriented development, to the development process which has focused on the use of standard components. In recent years a lot of research related to the component-based development has been done, especially in business domain. but still there are many open and unresolved problems in this area. such as established development process for a distributed environment, formal process, infrastructure for COTS, development and management tool considering maintenance to guarantee a proper treatment of components. It also required a service and an application integration for component. In this paper, we propose cooperative information systems (CIS) that supports component based development. It must address for component based systems to achieve their full potential. We identify a set of CIS organized 3-tier which is a presentation layer, business logic layer and data control layer. We also discuss the specific roles and activities for the layers. we also define the behavior and managed information for business logic layer as core level. As an illustration of the CIS, we present a successful considerations which is widely helpful to user when they make decision in component development and assemble. Also, we expect to component reusability and efficiency in business domain.

• Korean Journal of Psychosomatic Medicine
• /
• v.24 no.1
• /
• pp.61-65
• /
• 2016

Currently, a variety of Information and Communication Technology(ICT) is being broadly utilized for mental health. Especially, mobile application is one of the effective ICT, and several applications have been developed after the spread of smartphones. The mobile-based mental health has several strengths, such as better treatment accessibility and easier check-ups of symptoms or daily activities by real-time monitoring. Better follow-ups of treatment course, more customized feedback and better transportability enable patients to be more adherent. However, there are some limitations of mobile technology about the mental health, such as technical troubles of electric errors, data safety problems and personal information extrusion. Therefore, full considerations should be given during the development and provision of the technology. Most of all, mental health specialists should actively participate in the development process by incorporation of evidence-based experiences and assurance of good clinical qualities.

• The Journal of the Korea Contents Association
• /
• v.21 no.7
• /
• pp.386-403
• /
• 2021

Preannouncing a new product to its target audiences has been more and more prevalent in a wealth of industries, particularly industries that attach great importance to the speed of entry. Grounded in market signaling theory, the current research advances a theoretical model that takes full cognizance of the relation between preannounced information about an upcoming product and individual customers' behavioral intentions as well as significant moderating effects of prior product knowledge and new product innovativeness. In response, a web-based survey is conducted for data collection and the structural equation model is utilized for data analysis. Results of this study demonstrate that preannounced new product information attributes (i.e., quantity, clarity) may positively influence consumers' attitudes, in turn, lead to a favorable purchase intention. Moreover, the moderating effects of product knowledge and product innovativeness are also confirmed. Specifically, product knowledge moderates the quantity-attitude relation positively and moderates the clarity-attitude relation negatively, whereas product innovativeness does opposite. Both implications and limitations are also described.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.11
• /
• pp.1500-1506
• /
• 2020

In this paper, we study a scheduling problem based on reinforcement learning for overlay device-to-device (D2D) communication networks. Even though various technologies for D2D communication networks using Q-learning, which is one of reinforcement learning models, have been studied, Q-learning causes a tremendous complexity as the number of states and actions increases. In order to solve this problem, D2D communication technologies based on Deep Q Network (DQN) have been studied. In this paper, we thus design a DQN model by considering the characteristics of wireless communication systems, and propose a distributed scheduling scheme based on the DQN model that can reduce feedback and signaling overhead. The proposed model trains all parameters in a centralized manner, and transfers the final trained parameters to all mobiles. All mobiles individually determine their actions by using the transferred parameters. We analyze the performance of the proposed scheme by computer simulation and compare it with optimal scheme, opportunistic selection scheme and full transmission scheme.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.26 no.6
• /
• pp.404-410
• /
• 2021

This paper proposes a high step-up converter with zero-voltage transition (ZVT) cell for fuel cell electric vehicle. The proposed converter applies a ZVT cell to a dual floating output boost converter (DFOBC) so that not only the main switch but also the ZVT switch can achieve full-range soft switching. The current rating of the ZVT switch is 17% of the main switch. The proposed converter has high reliability in that no timing issue occurs. Therefore, online calculation is not required. The minimum turn-on time of the ZVT switch that guarantees soft switching at all loads and input/output voltage is obtained by analysis. In addition, the proposed DFOBC allows the use of a 650 V device even at 800 V output and has the advantage of being able to boost the voltage by 3.5 times with 0.56 duty. Planar coupled inductor with PCB winding was successfully implemented with the converter operated at 300 kHz. The 25 kW prototype achieves peak efficiency of 99% and power density of 63 kW/L.

• Current Optics and Photonics
• /
• v.5 no.4
• /
• pp.431-443
• /
• 2021

Sparse unmixing has been proven to be an effective method for hyperspectral unmixing. Hyperspectral images contain rich spectral and spatial information. The means to make full use of spectral information, spatial information, and enhanced sparsity constraints are the main research directions to improve the accuracy of sparse unmixing. However, many algorithms only focus on one or two of these factors, because it is difficult to construct an unmixing model that considers all three factors. To address this issue, a novel algorithm called multiview-based spectral weighted and low-rank row-sparsity unmixing is proposed. A multiview data set is generated through spectral partitioning, and then spectral weighting is imposed on it to exploit the abundant spectral information. The row-sparsity approach, which controls the sparsity by the l_2,0 norm, outperforms the single-sparsity approach in many scenarios. Many algorithms use convex relaxation methods to solve the l_2,0 norm to avoid the NP-hard problem, but this will reduce sparsity and unmixing accuracy. In this paper, a row-hard-threshold function is introduced to solve the l_2,0 norm directly, which guarantees the sparsity of the results. The high spatial correlation of hyperspectral images is associated with low column rank; therefore, the low-rank constraint is adopted to utilize spatial information. Experiments with simulated and real data prove that the proposed algorithm can obtain better unmixing results.

• Women's Health Nursing
• /
• v.29 no.1
• /
• pp.12-19
• /
• 2023

Purpose: The aim of this study was to conduct a scoping review of knowledge and information delivery modes related to preconception care (PCC) among adolescent girls and women. Methods: A scoping review was performed on studies selected from five electronic databases (Cochrane Library, PubMed, Science Direct, CINAHL/EBSCO, and ProQuest), published between 2012 and 2022, with predetermined keywords and criteria. We included English-language research articles available in full text and excluded irrelevant articles. Results: This study included eight articles, comprising seven quantitative studies and one qualitative study conducted among adolescent girls and women. Five were from low- and middle-income countries and three were from high-income countries. The synthesized themes generated from the data were PCC knowledge and PCC information delivery modes and effectiveness. In general, adolescent girls and women were found to have basic PCC knowledge, including risk prevention and management and a healthy lifestyle, although more extensive knowledge was found in higher-income countries than in lower-income countries. The delivery modes of PCC information have grown from individual face-to-face conventional methods, which are used predominantly in lower-income countries, to more effective digital mass media. Conclusion: Globally, many women still have insufficient knowledge regarding PCC, as not all of them receive access to PCC information and support. PCC promotion efforts should be initiated earlier by involving a wider group of reproductive-age women and combining individual, in-group, face-to-face, and electronic delivery modes.

• The Journal of Information Systems
• /
• v.32 no.3
• /
• pp.151-164
• /
• 2023

Purpose This study aims to analyze the current status of consumer awareness on Internet banks by conducting a full investigation and collecting user opinions presented on Google Play. After cateogorizing the current dissatisfaction, we would like to present not only the direction of the Internet bank service of but also the improvements of the platform. Design/methodology/approach Using opinion mining, subjectivity analysis, polarity analysis, and polarity information analysis of comments were conducted step by step to extract negative and positive keywords. The extracted keywords analyzed the weights of the frequently appearing positive and negative keywords using the TF-IDF model. Based on previous studies that negative information is more sensitive to positive information, we tried to confirm the connection, proximity, and mediation of negative keywords. Semantic Network Analysis (SNA) was used to visualize the connection relationship between the negative comment keywords of the three Internet banks. Findings Domestic Internet banks such as Kakao Bank, K-Bank, and Toss Bank have attracted a lot of attention even before they were established, and after establishment, they have secured a wide range of users through platforms that are completely different from existing banks. This study found out that the convenience of the app affects the opening and transaction of non-face-to-face accounts, which are characteristics of domestic Internet banks, which also affects the bank's business strategy. In addition, this study shows that the business characteristics of the company can be identified.