• 한국융합학회논문지
• /
• 제13권1호
• /
• pp.387-398
• /
• 2022

본 논문은 독거노인의 복합적 행태를 이종 사물인터넷 센서들과 딥러닝 기법을 활용하여 인지하고 낙상, 잦은 기침, 수면의 질 감소, 발열 및 비정상적 생활 동선의 발생 등 위급하거나 건강이 저하되는 상황을 적시에 보호자 및 의료복지 담당자에게 알리고 적정한 후속 서비스를 추천 및 수행할 수 있는 시스템을 논한다. 독거노인들의 생활을 최대한 방해하지 않기 위하여 전면 비접촉식 상황 인식 기술을 선보인다. 본 논문은 센서 데이터의 수집 및 분석 체계의 설계와 구현 방법은 물론, 서울시 총 5개구 거주 독거노인들을 대상으로 실증한 경험을 통해 설치, 설정, 운영 및 유지 보수 측면에서의 다양한 문제점들을 서술하고 해당 시스템의 전국 확산에 대비한 향후 발전 방향을 제언한다.

• 전자공학회논문지
• /
• 제54권4호
• /
• pp.50-58
• /
• 2017

최근 들어, 효과적인 화재감지를 위해 이종 화재센서 데이터들을 융합하는 방안들이 제안되었으나, 룰 기반의 방법의 경우 적응성과 정밀도가 낮고, 퍼지추론의 경우 영상에 대한 고려 미흡으로 검출 속도와 정밀도가 떨어지는 등의 문제점들이 있다. 더불어 영상기반 딥러닝 기술들도 제안되었으나, 실제 상황에서 카메라가 없거나 카메라 영역 밖의 화재 발생에 대한 신속한 탐지가 어렵다. 이에 본 논문에서는 CNN 기반의 딥러닝 알고리즘과 온도 습도 가스 연기를 포함하는 이종 화재센서 데이터기반의 퍼지추론엔진을 결합시킨 새로운 방식의 화재 감지 시스템을 제안한다. 이로써 영상 데이터를 활용한 신속한 화재 감지와 이종 센서 데이터들을 이용한 신뢰성 있는 화재 감지가 가능해짐을 보인다. 또한, 대규모 시스템에서 컴퓨팅 파워의 지나친 서버 집중을 방지하기 위해 화재 인식 알고리즘에 분산 컴퓨팅 구조를 채택하여 확장성을 높인다. 마지막으로, NIST 화재 동역학 시뮬레이터를 이용한 화재 시뮬레이션 데이터와 화재영상을 활용하여 화재가 점진적으로 번지는 환경과 급작스럽게 폭발이 발생하는 환경에서 실험을 수행함으로써 시스템의 성능을 검증한다.

• 수산해양교육연구
• /
• 제25권4호
• /
• pp.757-765
• /
• 2013

The purpose of this study is to examine the effects of peer tutoring on students' achievement and learning satisfaction in a liberal computer class at university level. Traditional teaching method was applied for the control group consisting 55 students for 8 weeks. The experimental group containing 44 students was instructed using both traditional teaching method and peer tutoring. According to the results of diagnosed test, the experimental group was divided into heterogeneous ability group of 3 or 4. The tutor training was provided a week in advance of the class and the students played a role of a tutor and tutee by taking turns. The results showed no significant differences between the two groups on academic achievement; however, in terms of students' learning satisfaction, it displayed a wider range of results. The learning satisfaction data from the experimental group showed a much higher level than that of the control group. It is predicted that the amount of class hours of a week, the quality of the lecture and the application of peer tutoring affect the students' academic achievement. It is suggested that subsequent research on peer tutoring will allow for more in-depth study in this field.

• 대한의용생체공학회:의공학회지
• /
• 제42권5호
• /
• pp.232-240
• /
• 2021

Heterogeneity in cancer is the major obstacle for precision medicine and has become a critical issue in the field of a cancer diagnosis. Many attempts were made to disentangle the complexity by molecular classification. However, multi-dimensional information from dynamic responses of cancer poses fundamental limitations on biomolecular marker-based conventional approaches. Cell morphology, which reflects the physiological state of the cell, can be used to track the temporal behavior of cancer cells conveniently. Here, we first present a hybrid learning-based platform that extracts cell morphology in a time-dependent manner using a deep convolutional neural network to incorporate multivariate data. Feature selection from more than 200 morphological features is conducted, which filters out less significant variables to enhance interpretation. Our platform then performs unsupervised clustering to unveil dynamic behavior patterns hidden from a high-dimensional dataset. As a result, we visualize morphology state-space by two-dimensional embedding as well as representative morphology clusters and trajectories. This cell morphology profiling strategy by hybrid learning enables simplification of the heterogeneous population of cancer.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권6호
• /
• pp.1620-1634
• /
• 2023

This paper studies the task of embedding nodes with multiple graphs representing multiple information channels, which is useful in a large volume of network clustering tasks. By learning a node using multiple graphs, various characteristics of the node can be represented and embedded stably. Existing studies using multi-channel networks have been conducted by integrating heterogeneous graphs or limiting common nodes appearing in multiple graphs to have similar embeddings. Although these methods effectively represent nodes, it also has limitations by assuming that all networks provide the same amount of information. This paper proposes a method to overcome these limitations; The proposed method gives different weights according to the source graph when embedding nodes; the characteristics of the graph with more important information can be reflected more in the node. To this end, a novel method incorporating a multi-channel gate layer is proposed to weigh more important channels and ignore unnecessary data to embed a node with multiple graphs. Empirical experiments demonstrate the effectiveness of the proposed multi-channel-based embedding methods.

• 사상체질의학회지
• /
• 제34권3호
• /
• pp.31-40
• /
• 2022

Objectives Sasang constitutional medicine is a traditional Korean medicine that classifies humans into four constitutions in consideration of individual differences in physical, psychological, and physiological characteristics. In this paper, we proposed a method to classify Taeeum person (TE) and Non-Taeeum person (NTE), Soeum person (SE) and Non-Soeum person (NSE), and Soyang person (ST) and Non-Soyang person (NSY) using a convolutional neural network with only facial images. Methods Based on the convolutional neural network VGG16 architecture, transfer learning is carried out on the facial images of 3738 subjects to classify TE and NTE, SE and NSE, and SY and NSY. Data augmentation techniques are used to increase classification performance. Results The classification performance of TE and NTE, SE and NSE, and SY and NSY was 77.24%, 85.17%, and 80.18% by F1 score and 80.02%, 85.96%, and 72.76% by Precision-Recall AUC (Area Under the receiver operating characteristic Curve) respectively. Conclusions It was found that Soeum person had the most heterogeneous facial features as it had the best classification performance compared to the rest of the constitution, followed by Taeeum person and Soyang person. The experimental results showed that there is a possibility to classify constitutions only with facial images. The performance is expected to increase with additional data such as BMI or personality questionnaire.

• 지능정보연구
• /
• 제24권2호
• /
• pp.1-19
• /
• 2018

주가 예측은 학문적으로나 실용적으로나 중요한 문제이기에, 주가 예측에 관련된 연구가 활발히 진행되었다. 빅 데이터 시대에 도입하면서, 빅 데이터를 결합한 주가 예측 연구도 활발히 진행되고 있다. 다수의 데이터를 기반으로 기계 학습을 이용한 연구가 주를 이룬다. 특히 언론의 효과를 접목한 연구 방법들이 주목을 받고 있는데, 그중 온라인 뉴스를 분석하여 주가 예측에 활용하는 연구가 주를 이루고 있다. 기존 연구들은 온라인 뉴스가 개별 회사에 대한 미치는 영향을 주로 살펴보았다. 또한, 관련성이 높은 기업끼리 서로 영향을 주는 것을 고려하는 방법도 최근에 연구되고 있다. 이는 동질성을 가지는 산업군에 대한 효과를 살펴본 것인데, 기존 연구에서 동질성을 가지는 산업군은 국제 산업 분류 표준에 따른다. 즉, 기존 연구들은 국제 산업 분류 표준으로 나뉜 산업군이 동질성을 가진다는 가정하에서 분석을 시행하였다. 하지만 기존 연구들은 영향력을 가지는 회사를 고려하지 못한 채 예측하였거나 산업군 내에서 이질성이 존재하는 점을 반영하지 못했다는 한계점을 가진다. 본 연구는 산업군 내에 이질성이 존재함을 밝히고, 이질성을 반영하지 못한 기존 연구의 한계점을 K-평균 군집 분석을 적용하여, 주가에 영향을 미치는 산업군의 동질적인 효과를 반영할 수 있는 방법론을 제안하였다. 방법론이 적합하다는 것을 증명하기 위해 3년간의 온라인 뉴스와 주가를 통해 실험한 결과, 다수의 경우에서 본 논문에서 제시한 방법이 좋은 결과를 나타냄을 확인할 수 있었으며, 국제 산업 분류 표준 산업군 내에서 이질성이 클수록 본 논문에서 제시한 방법이 좋은 효과를 보인다는 것을 확인할 수 있었다. 본 연구는 국제 산업 분류 표준으로 나누어진 기업들이 높은 동질성을 가지지 않는 다는것을 밝히고 이를 반영한 예측 모형의 효율성을 입증하였다는 점에서 의의를 가진다.

• 한국군사과학기술학회지
• /
• 제17권6호
• /
• pp.773-785
• /
• 2014

For decades, modeling of pilots has been intensively studied due to its advantages in reducing costs for training and enhancing safety of pilots. In particular, research for modeling of pilots' non-kinetic behaviors which refer to the decisions made by pilots is beneficial as the expertise of pilots can be inherent in the models. With the recent growth in the amount of combat logs accumulated, employing statistical learning methods for the modeling becomes possible. However, the combat logs consist of heterogeneous data that are not only continuous or discrete but also sequence independent or dependent, making it difficult to directly applying the learning methods without modifications. Therefore, in this paper, we present a kernel function named hybrid sequence kernel which addresses the problem by using multiple kernel learning methods. Based on the empirical experiments by using combat logs obtained from a simulator, the proposed kernel showed satisfactory results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권12호
• /
• pp.5820-5834
• /
• 2017

This paper investigates the channel selection problem with dynamic users and the asymmetric interference relation in distributed opportunistic spectrum access systems. Since users transmitting data are based on their traffic demands, they dynamically compete for the channel occupation. Moreover, the heterogeneous interference range leads to asymmetric interference relation. The dynamic users and asymmetric interference relation bring about new challenges such as dynamic random systems and poor fairness. In this article, we will focus on maximizing the tradeoff between the achievable utility and access cost of each user, formulate the channel selection problem as a directional graphical game and prove it as an exact potential game presenting at least one pure Nash equilibrium point. We show that the best NE point maximizes both the personal and system utility, and employ the stochastic learning approach algorithm for achieving the best NE point. Simulation results show that the algorithm converges, presents near-optimal performance and good fairness, and the directional graphical model improves the systems throughput performance in different asymmetric level systems.

• 반도체디스플레이기술학회지
• /
• 제21권4호
• /
• pp.121-125
• /
• 2022

This paper deals with the development of a deep-learning-based robot that recognizes various types of stairs and performs a mission to go up to the target floor. The overall motion sequence of the robot is performed based on the ROS robot operating system, and it is possible to detect the shape of the stairs required to implement the motion sequence through rapid object recognition through YOLOv4 and Cuda acceleration calculations. Using the ROS operating system installed in Jetson Nano, a system was built to support communication between Arduino DUE and OpenCM 9.04 with heterogeneous hardware and to control the movement of the robot by aligning the received sensors and data. In addition, the web server for robot control was manufactured as ROS web server, and flow chart and basic ROS communication were designed to enable control through computer and smartphone through message passing.