이동하 교수

The goal of one-class collaborative filtering (OCCF) is to identify the user-item pairs that are positively-related but have not been interacted yet, where only a small portion of positive user-item interactions (e.g., users' implicit feedback) are observed. For discriminative modeling between positive and negative interactions, most previous work relied on negative sampling to some extent, which refers to considering unobserved user-item pairs as negative, as actual negative ones are unknown. H

OBJECTIVE: Recent studies on electronic health records (EHRs) started to learn deep generative models and synthesize a huge amount of realistic records, in order to address significant privacy issues surrounding the EHR. However, most of them only focus on structured records about patients' independent visits, rather than on chronological clinical records. In this article, we aim to learn and synthesize realistic sequences of EHRs based on the generative autoencoder. MATERIALS AND METHODS: We pr

This study developed a smartphone application that provides wireless communication, NRTIP client, and RTK processing features, and which can simplify the Network RTK-GPS system while reducing the required cost. A determination method for an error model in Network RTK measurements was proposed, considering both random and autocorrelation errors, to accurately calculate the coordinates measured by the application using state estimation filters. The performance evaluation of the developed applicati

With the increase of available time series data, predicting their class labels has been one of the most important challenges in a wide range of disciplines. Recent studies on time series classification show that convolutional neural networks (CNN) achieved the state-of-the-art performance as a single classifier. In this work, pointing out that the global pooling layer that is usually adopted by existing CNN classifiers discards the temporal information of high-level features, we present a dynami

Topic taxonomies, which represent the latent topic (or category) structure of document collections, provide valuable knowledge of contents in many applications such as web search and information filtering. Recently, several unsupervised methods have been developed to automatically construct the topic taxonomy from a text corpus, but it is challenging to generate the desired taxonomy without any prior knowledge. In this paper, we study how to leverage the partial (or incomplete) information about

Most recent studies on detecting and localizing temporal anomalies have mainly employed deep neural networks to learn the normal patterns of temporal data in an unsupervised manner. Unlike them, the goal of our work is to fully utilize instance-level (or weak) anomaly labels, which only indicate whether any anomalous events occurred or not in each instance of temporal data. In this paper, we present WETAS, a novel framework that effectively identifies anomalous temporal segments (i.e., consecuti

With the great success of deep learning in various domains, graph neural networks (GNNs) also become a dominant approach to graph classification. By the help of a global readout operation that simply aggregates all node (or node-cluster) representations, existing GNN classifiers obtain a graph-level representation of an input graph and predict its class label using the representation. However, such global aggregation does not consider the structural information of each node, which results in inf

Tensor completion is the task of completing multi-aspect data represented as a tensor by accurately predicting missing entries in the tensor. It is mainly solved by tensor factorization methods, and among them, Tucker factorization has attracted considerable interests due to its powerful ability to learn latent factors and even their interactions. Although several Tucker methods have been developed to reduce the memory and computational complexity, the state-of-the-art method still 1) generates

In a shipyard, it is hard to predict block movement due to the uncertainty caused during the long period of shipbuilding operations. For this reason, block movement is rarely scheduled, while main operations such as assembly, outfitting and painting are scheduled properly. Nonetheless, the high operating costs of block movement compel task managers to attempt its management. To resolve this dilemma, this paper proposes a new block movement analysis framework consisting of the following operation

In mobile SoC applications, the power rails of multicore CPUs have been merged by CPU cluster to simplify the PMIC-SoC power rails in limited PCB area (VDD<inf>LIT</inf>, VDD<inf>MID</inf> and VDD<inf>BIG</inf> in Fig. 14.6.1). In order to optimize the power of each CPU core, integrated LDOs (iLDO) have recently been proposed [1–4]. However, the cost is quite high to allocate additional power-FETs and power routing, which occupy a large area in the SoC. Therefore, reducing power-FET-area is key

본 논문에서는 조선 산업에서 블록 조립 작업에 대한 계획 프로세스와 실적 프로세스를 비교하는 방법을 제안한다. 제안한 방법은 계획과 실적 데이터 기반으로 프로세스 마이닝 기법을 이용하여 프로세스 모델을 도출하고 비교 분석을 수행하는데, 분석 절차는 1) 데이터 전처리, 2) 분석 수준의 정의, 3) 조립 블록 군집화, 4) 군집별 프로세스 모델 도출, 5) 계획과 실적 프로세스 모델 비교, 다섯 단계로 구성된다. 단계 5에서는 프로세스 모델, 작업, 프로세스 인스턴스, 모델 적합도와 같은 다양한 관점에서 계획과 실적의 프로세스를 비교할 것을 제안하고, 각 관점별 비교 인자들을 정의한다. 특히, 적합도 관점에서는 교차 적합도를 정의하여, 도출된 프로세스 모델에 대해 자신의 데이터에 대한 적합도뿐만 아니라, 상대 데이터(계획 모델의 경우 실적 데이터, 실적 모델의 경우 계획 데이터)에 대한 적합도를 계산하고 비교 분석할 것을 제안한다. 제안한 방법의 효용성은 세계 최고 수준의 국내 조선