• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제7권4호
• /
• pp.103-110
• /
• 2018

Internet of Things(IoT) 기술이 발전하면서 다양한 IoT 기기들을 이용하여 사용자의 편의성을 높이기 위한 서비스가 늘어나고 있다. 또한, IoT 센서가 다양해지고 가격이 낮아지고 있어서 다양한 데이터를 수집 및 활용하여 서비스를 제공하는 사업자도 증가하는 추세이다. 스마트 IoT 홈 시스템은 IoT 기기를 이용하여 사용자의 편의성을 향상하는 대표적인 활용 사례이다. 본 논문에서는 스마트 IoT 홈 시스템의 사용자 편의성을 향상하기 위하여 데이터를 분석하여 연관 기기의 제어를 위한 방법을 제안한다. 스마트 IoT 홈 시스템의 센서에서 수집한 내부 환경 측정 데이터, 기기 제어 엑츄에이터에서 수집한 데이터 및 사용자의 판단 데이터를 학습하여 현재 홈 내부 상태를 분석하고 기기 제어 방법을 결정한다. 특히 기존 기술들과 다르게 최신 딥 러닝 기반의 심층 신경망을 도입하여 데이터를 분석하여 홈 내부 상태를 판단하고 최적의 홈 내부 환경 유지를 위한 정보를 제공한다. 실험에서는 실제 장기간 측정한 데이터와 추론 결과를 비교하여 제안한 방법의 판별 성능에 대한 분석을 수행하였다.

• 한국항행학회논문지
• /
• 제23권4호
• /
• pp.296-301
• /
• 2019

인공지능은 우리 실생활과 밀접하게 연관되어 다양한 분야에서 혁신을 주도하고 있다. 특히 인공지능을 보유한 이동수단으로서, 자율무인이동체의 연구가 활발하게 이루어지고 곧 실용화를 앞두고 있다. 자율자동차와 무인기 등이 스스로 경로를 설정하고 목적지까지 이동하기 위해서는 정확한 위치정보를 제공하는 항법장비가 필수적이다. 현재 운용되고 있는 이동수단들의 항법은 대부분 GPS에 의존하고 있다. 그러나 GPS는 외부 교란에 취약하다. 지난 2010년부터 북한은 수차례 GPS교란을 감행하여 우리 측에 이동통신, 항공기 운항 등에심각한 장애를 유발했다. 따라서 자율무인이동체의 안전성을 보장하고 교란으로 인한 피해를 방지하기 위해서는 신속한 상황판단과 대응이 요구된다. 본 논문에서는 빅데이터, 머신러닝 기술을 기반으로 John Boyd의 OODA LOOP Cycle(탐지-방향설정-결심-행동)을 적용한 조치방안 도출과 결심을 지원하는 GPS 전파교란 대응체계를 제시하였다.

• 해양환경안전학회지
• /
• 제24권3호
• /
• pp.311-318
• /
• 2018

In accordance with the stipulations of the STCW Convention, simulation training has been enforced in order to develop practical skills so as to prevent accidents by predetermining the risks in special marine environments. Simulation training is a useful way to acquire navigation abilities, and can continuously measure the ability of a trainee by applying an appropriate evaluation. However, the result of training is evaluated by the instructor's subjective judgment without quantitative criteria. Therefore, this study aims to quantitatively evaluate the effectiveness of simulation training. For this purpose, evaluation items were derived by analyzing legal standards, earlier studies, and the current status of MET institutions. The simulations were then performed three times in the same scenarios and analyzed the results. As a result, it has been shown that the objectively analyzed ability to keep the route and to make safe passage with other vessel, as well as subjectively evaluated ability by the apprentice officer has been improved as training progressed. Through the evaluation of simulation training results, it can be derived that simulation education needs supplementation, and can be provided as a basic form of data to quantify the evaluation results of the simulation training in the future.

• 한국수학교육학회지시리즈A:수학교육
• /
• 제46권4호
• /
• pp.407-421
• /
• 2007

The purpose of this study is to identify the item characteristics that are supposed to affect item difficulty and to estimate the regression equations for predicting item difficulty of mathematics in the College Scholastic Ability Test(CSAT). We selected six variables related to item characteristics based on learning theories: contents, cognitive domain, novelty, item type, number of concepts, and the amount of computation. With data of the CSAT mathematics test administered in 2004-2006, item difficulty was regressed on the six variables, the location of an item, and the item writer's judgment on difficulty. The novelty of an item was found to be a statistically insignificant variable in explaining item difficulty. Four regression equations with different sets of independent variables could explain $70%{\sim}80%$ of the item difficulty variance and were validated as predicting item difficulty of the mock CSAT in 2006.

• 동의신경정신과학회지
• /
• 제26권3호
• /
• pp.201-210
• /
• 2015

This study aims to investigate the specific functions of the five spirits based on the characteristics of five phases. In Korean medicine, the mind is classified into five spirits and seven emotions. The spirits (hon, sin, ui, baek, ji) are a way of analyzing of people's mental structures, and they are affected by each other, influencing life activities both directly and indirectly. They are also related to the five viscera and come into their own functions through the characteristics of the five phases that are assigned to the viscera. Sin is the main agent of mental activity that is normal, correct, and perfect, and it directs the other four. Hon is activity that is exposed to the outside from mental and physical aspects such as planning, creative thinking, creating, judgment, speech, and emotional expression. Baek is internal activity, such as obtaining information, learning, seeing, hearing, smell, taste, and touch. Ui is meant to decide between new and already saved information based on comparative analysis. Ji is the activity of making the final decision and saving it in ui. Based on the above, we suppose that the five spirits' functions match the characteristics of the five phases.

• 여성건강간호학회지
• /
• 제26권1호
• /
• pp.19-27
• /
• 2020

Purpose: This study was conducted to develop a simulation-based postpartum care education program for women with postpartum hemorrhage and to verify the effects of the program on postpartum care. Methods: This program was developed according to the ADDIE model of instructional system design, which consists of analysis, design, development, implementation, and evaluation phases. This quasi-experimental study used a non-equivalent control group pre- and post-test design, and data were collected from April 23 to May 4, 2015. To verify the effects of the program, 33 nursing students in the experimental group participated in a simulation program, whereas 31 students in the control group were given a case study. Results: The experimental group had statistically significantly higher scores for clinical performance (t=-4.80, p<.001), clinical judgment (t=-4.14, p<.001), and learning satisfaction (t=-10.45, p<.001) than the control group. Conclusion: The results of this study indicate that the simulation-based postpartum care education program for women with postpartum hemorrhage was effective for developing students' competency, implying that a similar program should be integrated into the clinical training component of the maternal nursing curriculum.

• 한국인공지능학회지
• /
• 제7권2호
• /
• pp.13-17
• /
• 2019

Currently, the sports market continues to grow every year, and among them, professional baseball's entry income is larger than the rest of the professional league. In sports, strategies are used differently in different situations, and the analysis is based on data to decide which direction to implement. There is a part that a person misses in an analysis, and there is a possibility of a false analysis by subjective judgment. So, if this data analysis is done through artificial intelligence, the objective analysis is possible, and the strategy can be more rationalized, which helps to win the game. The most popular baseball to be applied to artificial intelligence to analyze athletes' strengths and weaknesses and then efficiently establish strategies to ease the competition. The data applied to the experiment were provided on the KBO official website, and the algorithms for forecasting applied linear regression. The results showed that the accuracy was 87%, and the standard error was ±5. Although the results of the experiment were not enough data, it would be possible to effectively use baseball strategies and predict the results of the game if the amount of data and regular data can be applied in the future.

• 대한의용생체공학회:의공학회지
• /
• 제44권5호
• /
• pp.354-361
• /
• 2023

Most of spinal diseases are diagnosed based on the subjective judgment of a specialist, so numerous studies have been conducted to find objectivity by automating the diagnosis process using deep learning. In this paper, we propose a method that combines segmentation and feature extraction, which are frequently used techniques for diagnosing spinal diseases. Four models, U-Net, U-Net++, DeepLabv3+, and M-Net were trained and compared using 1000 X-ray images, and key-points were derived using Douglas-Peucker algorithms. For evaluation, Dice Similarity Coefficient(DSC), Intersection over Union(IoU), precision, recall, and area under precision-recall curve evaluation metrics were used and U-Net++ showed the best performance in all metrics with an average DSC of 0.9724. For the average Euclidean distance between estimated key-points and ground truth, U-Net was the best, followed by U-Net++. However the difference in average distance was about 0.1 pixels, which is not significant. The results suggest that it is possible to extract key-points based on segmentation and that it can be used to accurately diagnose various spinal diseases, including spondylolisthesis, with consistent criteria.

• 정보처리학회논문지B
• /
• 제16B권1호
• /
• pp.85-92
• /
• 2009

오늘날 웹이 일반화되면서 사람들은 원하는 정보를 웹을 통해 얻고, 또한 제공하고 있다. 웹이 다양한 정보의 제공과 습득의 장이라는 편의성을 제공하고 있지만, 반면에 너무 많은 정보, 무분별한 유해 정보의 범람 등 여러 가지 문제를 내포하고 있다. 현재 유해 웹 문서를 분류하기 위한 다양한 방법이 연구되고 사용되고 있다. 그러나 각각의 방법들이 갖는 단점들로 인해 획기적인 성과를 내지 못하고 있다. 본 논문에서는 유해 정보로부터 사회적으로 보호를 받아야 할 사용자들을 보호하기 위한 수단으로 유해 웹 문서 차단 방법에 대해 제안하고자 한다. 본 논문에서는 키워드 필터링과 SVM 알고리즘을 이용한 2단계 분류 과정을 통해 분류의 정확률을 높이고자 하였다.

• 전자통신동향분석
• /
• 제38권6호
• /
• pp.62-74
• /
• 2023

In response to diverse external stimuli, sensory receptors generate spiking nerve signals. These generated signals are transmitted to the brain along the neural pathway to advance to the stage of recognition or perception, and then they reach the area of discrimination or judgment for remembering, assessing, and processing incoming information. We review research trends in neuromorphic sensory perception technology inspired by biological sensory perception functions. Among the various senses, we consider sensory nerve decoding technology based on sensory nerve pathways focusing on touch and smell, neuromorphic synapse elements that mimic biological neurons and synapses, and neuromorphic processors. Neuromorphic sensory devices, neuromorphic synapses, and artificial sensory memory devices that integrate storage components are being actively studied. However, various problems remain to be solved, such as learning methods to implement cognitive functions beyond simple detection. Considering applications such as virtual reality, medical welfare, neuroscience, and cranial nerve interfaces, neuromorphic sensory recognition technology is expected to be actively developed based on new technologies, including combinatorial neurocognitive cell technology.