• Investigative Magnetic Resonance Imaging
• /
• 제25권4호
• /
• pp.313-322
• /
• 2021

Purpose: To find diagnostic image features, to compare diagnostic performance of multiphase CT versus gadoxetic acid disodium-enhanced MRI (GAD-MRI), and to evaluate the impact of analyzing Liver Imaging Reporting and Data System (LI-RADS) imaging features, for distinguishing combined hepatocellular-cholangiocarcinoma (CHC) from hepatocellular carcinoma (HCC). Materials and Methods: Ninety-six patients with pathologically proven CHC (n = 48) or HCC (n = 48), diagnosed June 2008 to May 2018 were retrospectively analyzed in random order by three radiologists with different experience levels. In the first analysis, the readers independently determined the probability of CHC based on their own knowledge and experiences. In the second analysis, they evaluated imaging features defined in LI-RADS 2018. Area under the curve (AUC) values for CHC diagnosis were compared between CT and MRI, and between the first and second analyses. Interobserver agreement was assessed using Cohen's weighted κ values. Results: Targetoid LR-M image features showed better specificities and positive predictive values (PPV) than the others. Among them, rim arterial phase hyperenhancement had the highest specificity and PPV. Average sensitivity, specificity, and AUC values were higher for MRI than for CT in both the first (P = 0.008, 0.005, 0.002, respectively) and second (P = 0.017, 0.026, 0.036) analyses. Interobserver agreements were higher for MRI in both analyses (κ = 0.307 for CT, κ = 0.332 for MRI in the first analysis; κ = 0.467 for CT, κ = 0.531 for MRI in the second analysis), with greater agreement in the second analysis for both CT (P = 0.001) and MRI (P < 0.001). Conclusion: Rim arterial phase hyperenhancement on GAD-MRI can be a good indicator suggesting CHC more than HCC. GAD-MRI may provide greater accuracy than CT for distinguishing CHC from HCC. Interobserver agreement can be improved for both CT and MRI by analyzing LI-RADS imaging features.

• ETRI Journal
• /
• 제33권2호
• /
• pp.210-218
• /
• 2011

Battiti's mutual information feature selector (MIFS) and its variant algorithms are used for many classification applications. Since they ignore feature synergy, MIFS and its variants may cause a big bias when features are combined to cooperate together. Besides, MIFS and its variants estimate feature redundancy regardless of the corresponding classification task. In this paper, we propose an automated greedy feature selection algorithm called conditional mutual information-based feature selection (CMIFS). Based on the link between interaction information and conditional mutual information, CMIFS takes account of both redundancy and synergy interactions of features and identifies discriminative features. In addition, CMIFS combines feature redundancy evaluation with classification tasks. It can decrease the probability of mistaking important features as redundant features in searching process. The experimental results show that CMIFS can achieve higher best-classification-accuracy than MIFS and its variants, with the same or less (nearly 50%) number of features.

• 한국멀티미디어학회논문지
• /
• 제10권9호
• /
• pp.1220-1228
• /
• 2007

본 논문에서는 기존의 서명 비교방법인 픽셀비교 (point-to-point) 방식과 부분비교(segment-to-segment) 방식의 단점을 보완한 효율적인 온라인 서명 인증 방법을 제안한다. 기존의 연구에서는 각각의 비교 방식에 알맞은 특징들이 추출되어서 서명 인증 시스템이 구현되어 왔었다. 본 논문에서는 두 비교방식의 장점을 결합하였다. 제안된 기법은 서명의 제적방향이 변화되는 지점인 변곡점을 이용해서 서명을 비교하고, 학습을 통하여 진서명간의 유사도는 높이고 진서명과 위조서명간의 상이도를 높이는 필자고유특징을 찾아낸다. 본 논문에서 제안된 방식을 사용한 경우, 필자고유특징을 사용하지 않는 경우와 비교해서 서명 인증율이 96.33%로 향상되었다.

• International Journal of Computer Science & Network Security
• /
• 제22권6호
• /
• pp.319-331
• /
• 2022

The latest global COVID-19 pandemic has made the use of facial masks an important aspect of our lives. People are advised to cover their faces in public spaces to discourage illness from spreading. Using these face masks posed a significant concern about the exactness of the face identification method used to search and unlock telephones at the school/office. Many companies have already built the requisite data in-house to incorporate such a scheme, using face recognition as an authentication. Unfortunately, veiled faces hinder the detection and acknowledgment of these facial identity schemes and seek to invalidate the internal data collection. Biometric systems that use the face as authentication cause problems with detection or recognition (face or persons). In this research, a novel model has been developed to detect and recognize faces and persons for authentication using scale invariant features (SIFT) for the whole segmented face with an efficient local binary texture features (DLBP) in region of eyes in the masked face. The Fuzzy C means is utilized to segment the image. These mixed features are trained significantly in a convolution neural network (CNN) model. The main advantage of this model is that can detect and recognizing faces by assigning weights to the selected features aimed to grant or provoke permissions with high accuracy.

• 설비공학논문집
• /
• 제17권7호
• /
• pp.669-680
• /
• 2005

The purpose of this study is to develop the air-conditioning unit combined with the lighting unit for workspace and to supply its performance data at architectural design stage. The air-conditioning unit is one of the components of a workspace integrated unit, which can be defined as the planning unit satisfying the environmental comfort criteria of workspace. Air-conditioning diffusers are classified according to throws and features by literature review and case study. Then diffusers are combined with the lighting unit. Through the CFD simulation, the thermal performance of each unit was evaluated and finally various air-conditioning units combined with the lighting units were developed.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1998년도 추계학술대회
• /
• pp.233-234
• /
• 1998

The purpose of this paper is the evaluation of a permeability and blood compatibility for silicone/polypropylene combined membrane. Despite the overall good performances of polypropylene membrane, its long-lasting usage for artificial lung has been limited by serum leakage. In order to overcome this problem, we have newly fabricated polydimethylsiloxane(silicone)/polypropylene combined membrane(SPCM). SPCM has been proved to be serum leakage free in hours experimental. It has shown good long-lasting gas transfer and durability features.

• 한국통신학회논문지
• /
• 제28권12C호
• /
• pp.1200-1208
• /
• 2003

비디오 데이터에 존재하는 감정을 처리하는 것은 지능적인 인간과 컴퓨터와의 상호작용을 위해서 매우 중요한 일이다. 이러한 감정을 추출하기 위해서는 비디오로부터 감정에 관련된 특징들을 검출하기 위한 컴퓨팅 모델을 구축하는 것이 바람직하다. 본 논문에서는 비디오 셧에 존재하는 저급 특징들의 확률적인 분포를 이용하여 감정 이벤트 발생에 관련된 통계학적인 모델을 제안한다. 즉, 비디오 셧의 기본적인 특징을 추출하고 그 특징을 통계적으로 모델화 하여 감정을 유발하는 셧을 찾아낸다. 비디오 셧의 특징으로는 칼라, 카메라 모션 및 셧 길이의 변화를 이용한다. 이러한 특징들을 EM(Expectation Maximization) 알고리즘을 이용하여 GMM(Gaussian Mixture Model) 으로 모델링하고, 감정과 시간과의 관계를 MLE(Maximum Likelihood Estimation)를 이용하여 시간에 따른 확률분포 모델로 구성한다. 이런 두 개의 통계적인 모델들을 융합하여 베이시안 분류법을 적용하여 비디오 데이터로부터 감정에 관련된 셧을 찾아낸다.

• 말소리와 음성과학
• /
• 제1권2호
• /
• pp.95-103
• /
• 2009

We investigated the perceptual structure of Korean consonants by analyzing the confusion among consonants in various vowel contexts. The 36 CV syllable types combined by 18 consonants and 2 vowels (/i/ and /u/) were presented with masking noises or in degraded intensity. The confusion data were analyzed by the INDSCAL (Individual Difference Scaling), ADCLUS (Additive Clustering) and the probability of the transmitted information. The results were compared with those of a previous study with /a/ vowel context (Bae and Kim, 2002). The overall results showed that the laryngeal features-aspiration, lax and tense-are the most salient features in the perception of Korean consonant regardless of vowel contexts, but the perceptual saliency of place features varies across vowel conditions. In high vowel (front and back vowel) contexts, sibilant consonants were perceptually salient compared to in low vowel contexts. In back vowel contexts, grave (labial and velar) consonants were perceptually salient. These findings imply that place features and vowel features strongly interact in speech perception as well as in speech production. All statistical measures from our confusion data ensured that the perceptual structure of Korean consonants correspond to the hierarchical structure suggested in the feature geometry (Clements, 1991). We discuss the link between speech perception and production as the basis of phonology.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권10호
• /
• pp.3390-3405
• /
• 2022

Long Short-Term Memory (LSTM) combined with attention mechanism is extensively used to generate semantic sentences of images in image captioning models. However, features of salient regions and spatial information are not utilized sufficiently in most related works. Meanwhile, the LSTM also suffers from the problem of underutilized information in a single time step. In the paper, two innovative approaches are proposed to solve these problems. First, the Synergy-Gated Attention (SGA) method is proposed, which can process the spatial features and the salient region features of given images simultaneously. SGA establishes a gated mechanism through the global features to guide the interaction of information between these two features. Then, the Recurrent Fusion LSTM (RF-LSTM) mechanism is proposed, which can predict the next hidden vectors in one time step and improve linguistic coherence by fusing future information. Experimental results on the benchmark dataset of MSCOCO show that compared with the state-of-the-art methods, the proposed method can improve the performance of image captioning model, and achieve competitive performance on multiple evaluation indicators.

• 한국멀티미디어학회논문지
• /
• 제19권2호
• /
• pp.138-145
• /
• 2016

LLAH(Locally Likely Arrangement Hashing) is a method which describes image features by exploiting the geometric relationship between their neighbors. Inherently, it is more robust to large view change and poor scene texture than conventional texture-based feature description methods. However, LLAH strongly requires that image features should be detected with high repeatability. The problem is that such requirement is difficult to satisfy in real applications. To alleviate the problem, this paper proposes a method that improves the matching rate of LLAH by exploiting together the brightness of features. Then, it is verified that the matching rate is increased by about 5% in experiments with synthetic images in the presence of Gaussian noise.