• 한국멀티미디어학회논문지
• /
• 제13권5호
• /
• pp.722-729
• /
• 2010

예측 문제를 해결하기 위한 데이타마이닝 기법은 다양한 분야에서 주목받고 있다. 이것에 대한 한 예로 컴퓨터-기반의 질병의 예측 혹은 진단은 CDSS(Clinical Decision support System)에서 가장 중요한 요소이기도 하다. 이러한 예측 문제를 해결하기 위해서 RBF커널 같은 비선형 커널을 사용한 SVM이 가장 널리 사용되고 있는데, 이는 비선형 SVM이 어떠한 다른 분류기법보다 정확한 성능을 보이기 때문이다. 하지만 비선형 SVM을 사용한 경우에는 모델내부를 시각화하는 일이 어려워서 예측결과에 대한 직관적인 이해가 힘들고, 의학 전문가들은 이러한 비선형 SVM의 사용을 기피하고 있는 실정이다. Nomogram은 SVM을 시각화하기 위해 제안된 기법이다. 하지만 이는 선형 SVM의 경우에만 사용이 가능하고. 이 문제를 해결하기 위해서 LRBF 커널이 제안된 바 있다. LRBF 커널은 기존의 RBF 커널을 사용한 SVM과 대등한 결과를 보이면서도 예측결과의 선형적 분석도 가능하게 한다. 본 논문에서는 노모그램(Nomogram)과 LRBF 커널을 사용한 SVM이 통합되어 있는 예측 툴 VRIFA를 제안한다. 이 툴은 사용자와 상호작용하며 비선형 SVM 모델의 내부구조를 데이타의 각 속성별로 보여주는 방법으로 사용자가 예측결과를 직관적으로 이해하도록 도와준다. VRIFA는 Nomogram기반의 피쳐선택(feature selection) 기능도 포함하고 있는데, 이 기능은 예측결과에 부정적인 영향을 끼치거나 중복된 연관성을 보이는 속성을 제거함으로써 모델의 정확도를 높이는 데 기여한다. 그리고 데이터에 포함된 클래스의 비율이 한 쪽으로 치우쳐져 있는 경우에는 ROC 곡선 넓이(AUC)를 예측결과를 평가하기 위한 측도로 사용할 수 있다. 이 툴은 컴퓨터-기반의 질병 예측 혹은 질병의 위험 요소 분석에 대해 연구하는 연구자들에게 유용하게 사용될 것으로 전망하는 바이다.

• Journal of Pharmaceutical Investigation
• /
• 제40권spc호
• /
• pp.75-82
• /
• 2010

Specific diseases like cancer and acquired immune deficiency syndrome (AIDS) occur at various organs including lymphatics and spread through lymphatic system. Thus, if therapeutic agents for such diseases are more distributed or targeted to lymphatic system, we can obtain several advantages like reduction of systemic side effect and increase of efficacy. For these reasons, much interest has been focused on the nature of lymphatics and a lot of studies for lymphatic delivery of drugs have been carried out. Because lymphatics consist of single layer endothelium and have high permeability compared with blood capillaries, especially, the studies using nano-sized carriers have been performed. Polymeric nano-particle, liposome, and lipid-based vehicle have been adopted for lymphatic delivery as carriers. According to the administration route and the kind of carrier, the extent of lymphatic delivery efficiency of nano-sized carriers has been changed and influenced by several factors such as size, charge, hydrophobicity and surface feature of carrier. In this review, we summarized the key factors which affect lymphatic uptake and the major features of carriers for achieving the lymphatic delivery. Lymphatic delivery of drug using nano-sized carriers has many fold improved ability of lymphatic delivery compared with that of conventional dosage forms, but it has not shown whole lymph selectivity yet. Even though nano-sized carriers still have the potential and worth to study as lymphatic drug delivery technology as before, full understanding of delivery mechanism and influencing factors, and setting of pharmacokinetic model are required for more ideal lymphatic delivery of drug.

• Wind and Structures
• /
• 제20권3호
• /
• pp.449-468
• /
• 2015

Current wind-resistance designs of large-scale indirect dry cooling towers (IDCTs) exclude an important factor: the influence of the ventilation rate for radiator shutter on wind loads on the outer surfaces of the tower shell. More seemingly overlooked aspects are the effects of various ventilation rates on the wind pressure distribution on the tower surfaces of two IDCTs, and the feature of the flow field around them. In order to investigate the effects of the radiator shutter ventilation rates on the aerodynamic interference between IDCTs, this paper established the numerical wind tunnel model based on the Computational Fluid Dynamic (CFD) technology, and analyzed the influences of various radiator shutter ventilation rates on the aerodynamic loads acting upon a single and two extra-large IDCTs during building, installation, and operation stages. Through the comparison with the results of physical wind tunnel test and different design codes, the results indicated that: the influence of the ventilation rate on the flow field and shape coefficients on the outer surface of a single IDCT is weak, and the curve of mean shape coefficients is close to the reference curve provided by the current design code. In a two-tower combination, the ventilation rate significantly affects the downwind surface of the front tower and the upwind surface of the back tower, and the larger positive pressure shifts down along the upwind surface of the back tower as the ventilation rate increases. The ventilation rate significantly influences the drag force coefficient of the back tower in a two-tower combination, the drag force coefficient increases with the ventilation rate and reaches the maximum in a building status of full ventilation, and the maximum drag coefficient is 11% greater than that with complete closure.

• Biomolecules & Therapeutics
• /
• 제28권4호
• /
• pp.337-343
• /
• 2020

Activation of osteoclast and inactivation of osteoblast result in loss of bone mass with bone resorption, leading to the pathological progression of osteoporosis. The receptor activator of NF-κB ligand (RANKL) is a member of the TNF superfamily, and is a key mediator of osteoclast differentiation. A flavanone glycoside isolated from the fruit of Poncirus trifoliata, poncirin has anti-allergic, hypocholesterolemic, anti-inflammatory and anti-platelet activities. The present study investigates the effect of poncirin on osteoclast differentiation of RANKL-stimulated RAW264.7 cells. We observed reduced formation of RANKL-stimulated TRAP-positive multinucleated cells (a morphological feature of osteoclasts) after poncirin exposure. Real-time qPCR analysis showed suppression of the RANKL-mediated induction of key osteoclastogenic molecules such as NFATc1, TRAP, c-Fos, MMP9 and cathepsin K after poncirin treatment. Poncirin also inhibited the RANKL-mediated activation of NF-κB and, notably, JNK, without changes in ERK and p38 expression in RAW264.7 cells. Furthermore, we assessed the in vivo efficacy of poncirin in the lipopolysaccharide (LPS)-induced bone erosion model. Evaluating the micro-CT of femurs revealed that bone erosion in poncirin treated mice was markedly attenuated. Our results indicate that poncirin exerts anti-osteoclastic effects in vitro and in vivo by suppressing osteoclast differentiation. We believe that poncirin is a promising candidate for inflammatory bone loss therapeutics.

• Journal of Positioning, Navigation, and Timing
• /
• 제2권1호
• /
• pp.81-89
• /
• 2013

Many of the current visual odometry algorithms suffer from some extreme limitations such as requiring a high amount of computation time, complex algorithms, and not working in urban environments. In this paper, we present an approach that can solve all the above problems using a single camera. Using a planar motion assumption and Ackermann's principle of motion, we construct the vehicle's motion model as a circular planar motion (2DOF). Then, we adopt a 1-point method to improve the Ransac algorithm and the relative motion estimation. In the Ransac algorithm, we use a 1-point method to generate the hypothesis and then adopt the Levenberg-Marquardt method to minimize the geometric error function and verify inliers. In motion estimation, we combine the 1-point method with a simple least-square minimization solution to handle cases in which only a few feature points are present. The 1-point method is the key to speed up our visual odometry application to real-time systems. Finally, a Bundle Adjustment algorithm is adopted to refine the pose estimation. The results on real datasets in urban dynamic environments demonstrate the effectiveness of our proposed algorithm.

• Smart Structures and Systems
• /
• 제16권6호
• /
• pp.1003-1021
• /
• 2015

MR dampers have been proposed for the control of cable vibration of cable-stayed bridge in recent years due to their high performance and low energy consumption. However, the highly nonlinear feature of MR dampers makes them difficult to be designed with efficient semi-active control algorithms. Simulation study has previously been carried out on the cable-MR damper system using a semi-active control algorithm derived based on the universal design curve of dampers and a bilinear mechanical model of the MR damper. This paper aims to verify the effectiveness of the MR damper for mitigating cable vibration through a full-scale experimental test, using the same semi-active control strategy as in the simulation study. A long stay cable fabricated for a real bridge was set-up with the MR damper installed. The cable was excited under both free and forced vibrations. Different test scenarios were considered where the MR damper was tuned as passive damper with minimum or maximum input current, or the input current of the damper was changed according to the proposed semi-active control algorithm. The effectiveness of the MR damper for controlling the cable vibration was assessed through computing the damping ratio of the cable for free vibration and the root mean square value of acceleration of the cable for forced vibration.

• 품질경영학회지
• /
• 제39권3호
• /
• pp.365-376
• /
• 2011

Robust design (RD) has emerged as a key feature in process design and development for more than twenty years. Many researchers and industrial engineers around the world have invested their intensive efforts to develop and apply RD in many fields in order to improve quality of output products. However, there is also room for improvement. The primary objective of this research is to determine "robust formulation" of a medicine by checking its gelation index. In order to achieve this target, based on the nature of problem, at first, a customized experimental format is designed for obtaining data. Second, time-depended responses based models are developed by the proposed inverse problem (IP) methodology. Third, an RD model based on mean square error (MSE) concept is introduced for time-depended responses. Finally, the proposed approach is illustrated by a case study while comparing obtained results to the response surface methodology (RSM) approach.

• Journal of information and communication convergence engineering
• /
• 제15권2호
• /
• pp.104-111
• /
• 2017

The visual presentation is one key feature which gives much consideration in designing mobile applications as it acquires attention from the end user. It takes only a few milliseconds to form an impression on a person and this is not any different to the web and mobile application designs. The first few milliseconds are a crucial time for developers as the impression produced would indicate further engagement of the service. Developers should continuously update the designs based on human needs. A few of these contents have actually paved its way to being continuously used. By synthesizing results of preceding researchers, this paper considers layout, color, and font as UI design elements of SNS messenger, and illustration and animation as the graphic image of it. In this study, the preference for messaging application chat layout was being surveyed and analyzed. As a result, there has been little significance identified since the instant messaging, so chat layout shows very minimal variance in their design.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권6호
• /
• pp.2612-2633
• /
• 2020

Due to the explosive growth of multimedia speech data, how to protect the privacy of speech data and how to efficiently retrieve speech data have become a hot spot for researchers in recent years. In this paper, we proposed an encrypted speech retrieval scheme based on long short-term memory (LSTM) neural network and deep hashing. This scheme not only achieves efficient retrieval of massive speech in cloud environment, but also effectively avoids the risk of sensitive information leakage. Firstly, a novel speech encryption algorithm based on 4D quadratic autonomous hyperchaotic system is proposed to realize the privacy and security of speech data in the cloud. Secondly, the integrated LSTM network model and deep hashing algorithm are used to extract high-level features of speech data. It is used to solve the high dimensional and temporality problems of speech data, and increase the retrieval efficiency and retrieval accuracy of the proposed scheme. Finally, the normalized Hamming distance algorithm is used to achieve matching. Compared with the existing algorithms, the proposed scheme has good discrimination and robustness and it has high recall, precision and retrieval efficiency under various content preserving operations. Meanwhile, the proposed speech encryption algorithm has high key space and can effectively resist exhaustive attacks.

• 대한설비공학회:학술대회논문집
• /
• 대한설비공학회 2008년도 하계학술발표대회 논문집
• /
• pp.282-287
• /
• 2008

Identification of steady-state is the first step in developing a fault detection and diagnosis (FDD) system. In a complete FDD system, the steady-state detector will be included as a module in a self-learning algorithm which enables the working system's reference model to "tune" itself to its particular installation. In this study, a steady-state detector of a residential air conditioner based on moving windows was designed. Seven representing measurements were selected as key features for steady-state detection. The optimized moving window size and the feature thresholds was suggested through startup transient test and no-fault steady-state test. Performance of the steady-state detector was verified during indoor load change test. From the research, the general methodology to design a moving window steady-state detector was provided for vapor compression applications.