김성태 교수

Recently, deep learning technology has achieved various successes in medical image analysis studies including computer-aided diagnosis (CADx). However, current CADx approaches based on deep learning have a limitation in interpreting diagnostic decisions. The limited interpretability is a major challenge for practical use of current deep learning approaches. In this paper, a novel visually interpretable deep network framework is proposed to provide diagnostic decisions with visual interpretation.

Characterization of masses in computer-aided detection systems for digital breast tomosynthesis (DBT) is an important step to reduce false positive (FP) rates. To effectively differentiate masses from FPs in DBT, discriminative mass feature representation is required. In this paper, we propose a new latent feature representation boosted by depth directional long-term recurrent learning for characterizing malignant masses. The proposed network is designed to encode mass characteristics in two par

Multimodal emotion recognition has gained much traction in the field of affective computing, human–computer interaction (HCI), artificial intelligence (AI), and user experience (UX). There is growing demand to automate analysis of user emotion towards HCI, AI, and UX evaluation applications for providing affective services. Emotions are increasingly being used, obtained through the videos, audio, text or physiological signals. This has led to process emotions from multiple modalities, usually co

In psychology, it is known that facial dynamics benefit the perception of identity. This paper proposes a novel deep network framework to capture identity information from facial dynamics and their relations. In the proposed method, facial dynamics occurred from a smile expression are analyzed and utilized for facial authentication. Detailed changes in the local regions of a face such as wrinkles and dimples are encoded in the facial dynamic feature representation. The latent relationships of th

In digital breast tomosynthesis, the three dimensional (3D) reconstructed volumes only provide quasi-3D structure information with limited resolution along the depth direction due to insufficient sampling in depth direction and the limited angular range. The limitation could seriously hamper the conventional 3D image analysis techniques for detecting masses because the limited number of projection views causes blurring in the out-of-focus planes. In this paper, we propose a novel mass detection

According to the supplementary information hypothesis in psychology, facial motion benefits the perception of identity for human. In this study, we propose a face authentication framework which exploits facial dynamics with appearance to effectively improve the authentication performance. In our face authentication scenario, users are guided to make smile expression and the identity behind smile dynamics has been utilized. In order to model the facial dynamics, the recurrent neural network with

For human identification, facial motion is useful in representing specific dynamic signature. In this paper, we present an effective spatio-temporal representation from facial motion as well as appearance by devising a 3D convolutional neural network (CNN). To maintain the intra-class invariance with limited number of training samples, a multi-task learning approach with human attributes, which are high-level semantic descriptions for identity, has been proposed. Identity-related human attribute

Digital breast tomosynthesis (DBT) is a new 3-D imaging modality that alleviates the tissue overlap problem of mammography. Currently, DBT has been used in combination with full-field digital mammography (FFDM). Although some studies have shown the superiority of combination of DBT and FFDM in diagnosing the breast cancer, this combined procedure has the drawback that radiation doses are increased compared to the FFDM alone. In this paper, we propose a novel approach for generating 2-D synthetic

Longitudinal analysis of a disease is an important issue to understand its progression and design prognosis and early diagnostic tools. From the longitudinal images where data is collected from multiple time points, both the spatial structural information and the longitudinal variations are captured. The temporal dynamics are more informative than static observations of the symptoms, particularly for neurodegenerative diseases such as Alzheimer’s disease, whose progression spans over the years w

In digital breast tomosynthesis (DBT), image characteristics of projection views and reconstructed volume are different and both have the advantage of detecting breast masses, e.g. reconstructed volume mitigates a tissue overlap, while projection views have less reconstruction blur artifacts. In this paper, an improved mass detection is proposed by using combined feature representations from projection views and reconstructed volume in the DBT. To take advantage of complementary effects on diffe

Recent studies have reported that deep learning techniques could achieve high performance in medical image analysis such as computer-aided diagnosis (CADx). However, there is a limitation in interpreting the diagnostic decisions of deep learning due to the black-box nature. To increase confidence in the diagnostic decisions of deep learning, it is necessary to develop a deep neural network with the interpretable structure which could provide a reasonable explanation of diagnostic decisions. In t

정부는 기업에 장기간 누적되어온 사내유보금을 기업에서 가계로 순환시키고자 기업소득환류세제를 도입하였다. 기업소득환류세제란 대기업 집단 소속 기업 및 자기자본 500억 초과 기업이 당기에 벌어들인 소득의 일정부분을 배당․투자․임금 증가로 지출하지 않으면 그 차액만큼 추가적으로 과세하는 제도이다. 기업소득환류세제 입법을 두고 도입 이전부터 많은 논의가 이루어졌으나 결국 국회를 통과하면서 2015과세연도부터 시행되었다. 도입 이전부터 제도의 기대효과를 분석하거나 도입에 따른 주가변동을 예측한 연구는 다수 존재하였으나, 본 연구는 세제 시행 이후인 2015년과 2016년에 공시된 재무제표를 바탕으로 세제 적용 여부가 기업의 배당성향․투자지출․임금증가에 미치는 영향을 실증적으로 분석한 연구이다. 기업소득환류세제 적용 대상 기업의 배당성향․투자지출․임금증가의 평균을 비교한 t-test 결과, 세제 도입 전부터 세제 적용 기업은 비적용 기업에 비해 높은 배당성향과 낮은 투자지출, 높은 임금증가를

The authors present a novel gradient descent algorithm called RAPIDO for deep learning. It adapts over time and performs optimisation using current, past and future information similar to the PID controller. The proposed method is suited for optimising deep neural networks that consist of activation functions such as sigmoid, hyperbolic tangent and ReLU functions because it can adapt appropriately to sudden changes in gradients. They experimentally study the authors' method and show the performa