• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권10호
• /
• pp.1770-1782
• /
• 2011

A brain-computer interface (BCI) is a communication system that translates brain activity into commands for computers or other devices. In other words, BCIs create a new communication channel between the brain and an output device by bypassing conventional motor output pathways consisting of nerves and muscles. This is particularly useful for facilitating communication for people suffering from paralysis. Due to the low bit rate, it takes much more time to translate brain activity into commands. Especially it takes much time to input characters by using BCI-based typewriters. In this paper, we propose a brain-operated typewriter which is accelerated by a language prediction model. The proposed system uses three kinds of strategies to improve the entry speed: word completion, next-syllable prediction, and next word prediction. We found that the entry speed of BCI-based typewriter improved about twice as much through our demonstration which utilized the language prediction model.

• 한국콘텐츠학회논문지
• /
• 제20권10호
• /
• pp.167-176
• /
• 2020

현재 국내에서 활용되고 있는 자동화된 어류 급이 장치는 특정 시간과 일정량의 사료를 시간에 맞추어 수조에 공급하는 방식이다. 이는 고령화되고 고가인 양식장 관리의 인건비는 줄일 수 있으나 양식 생산성에 결정적 요인이 되는 고가의 사료량을 지능적으로 적절히 조절하기는 매우 어렵다. 본 논문에서는 이러한 기존 자동급이 장치의 문제점을 해결하고, 양식장에서 어류의 성장률을 적절하게 유지하면서 사료 공급의 효율성을 극대화할 수 있는 퍼지추론 기반의 지능형 어류 자동 급이 모델인 FIIFF 추론 모델(Fuzzy Inference based Intelligent Fish Feeding Model)을 제안한다. 본 논문에서 제안하는 FIIFF 지능형 급이 추론모델은 양식어류의 현재 생육 환경 정보 및 실시간 활동 상태를 기반으로 급이량을 산출하기 때문에 사료 급이량 적절성이 매우 높다. 본 연구에서 제안한 FIIFF 추론 모델의 급이량 산출 실험 결과에서는 8개월 동안 양식장에서 실제 투입한 급이량보다 14.8%를 절감하는 효과를 보여준다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권4호
• /
• pp.1887-1898
• /
• 2018

In this paper, a method to classify insider threat activity is introduced. The internal threats help detecting anomalous activity in the procedure performed by the user in an organization. When an anomalous value deviating from the overall behavior is displayed, we consider it as an inside threat for classification as an inside intimidator. To solve the situation, Markov Chain Model is employed. The Markov Chain Model shows the next state value through an arbitrary variable affected by the previous event. Similarly, the current activity can also be predicted based on the previous activity for the insider threat activity. A method was studied where the change items for such state are defined by a transition probability, and classified as detection of anomaly of the inside threat through values for a probability variable. We use the properties of the Markov chains to list the behavior of the user over time and to classify which state they belong to. Sequential data sets were generated according to the influence of n occurrences of Markov attribute and classified by machine learning algorithm. In the experiment, only 15% of the Cert: insider threat dataset was applied, and the result was 97% accuracy except for NaiveBayes. As a result of our research, it was confirmed that the Markov Chain Model can classify insider threats and can be fully utilized for user behavior classification.

• ETRI Journal
• /
• 제45권6호
• /
• pp.1079-1089
• /
• 2023

Stroke is one of the leading causes of long-term disability worldwide, placing huge burdens on individuals and society. Further, automatic human activity recognition is a challenging task that is vital to the future of healthcare and physical therapy. Using a baseline long short-term memory recurrent neural network, this study provides a novel dataset of stretching, upward stretching, flinging motions, hand-to-mouth movements, swiping gestures, and pouring motions for improved model training and testing of stroke-affected patients. A MATLAB application is used to output textual and audible prediction results. A wearable sensor with a triaxial accelerometer is used to collect preprocessed real-time data. The model is trained with features extracted from the actual patient to recognize new actions, and the recognition accuracy provided by multiple datasets is compared based on the same baseline model. When training and testing using the new dataset, the baseline model shows recognition accuracy that is 11% higher than the Activity Daily Living dataset, 22% higher than the Activity Recognition Single Chest-Mounted Accelerometer dataset, and 10% higher than another real-world dataset.

• Architectural research
• /
• 제21권2호
• /
• pp.41-48
• /
• 2019

The purpose of this study is to research and development of 'Korea B(Benefit)-impact Model' for Sustainable Development. A concept evaluation model is 'B(Benefit)-impact model' in U.S.A. We use the results of surveys that examined the importance of social value issues to stakeholders in Korea to implement the benefit-impact model in Korea. In particular, in this paper, we use the KSI(Korean Sustainability Index) survey data conducted by the Korea Standards Association to evaluate the social value of the construction industry for representative stakeholders in the construction industry. The social value pool and the activity indicator pool used for the survey are created based on relevant International Standards; ISO 26000, ISO 14001, ISO 37001. As a result, Korea B-impact model for construction industry included the following five core social value issues; Strengthen transparency of corporate management, Ensure fair employment and employment relations, Efforts to prevent corruption, Conduct fair competition, Efforts to prevent environmental pollution. In addition, the US B-impact model has three limitations. First, it is unclear whether the key indicators have been derived while considering all issues of social value. Second, US B-impact model indicators are developed by the social responsibility experts, so it is necessary to review by stakeholders in each industry. Finally, it would be more effective for companies to use the B-impact model index as a more detailed activity indicator. When developing a Korea B-impact model, the following methods are used to supplement it. First, we reviewed all social value issues using international standards. Secondly, we used the KSI(Korean Sustainability index) survey results to derive the importance of the social value issue of construction industry in Korea. Finally, we have clearly matched the activity indicators by social value core issues based on the GRI Standard so that companies can actually use the Korea B-impact model for the construction sector. The detailed development stages and results of this study are as follows;.

• 대한지구과학교육학회지
• /
• 제9권2호
• /
• pp.139-151
• /
• 2016

이 연구의 목적은 학생 활동 중심의 고등학교 '과학' 교과서 모델을 개발하고, 개발한 모델을 현장 적용 가능성을 알아보고자 하였다. 이 연구를 위해 학생 활동 중심의 교과서 모델을 개발하기 위하여 국내 및 국외 교과서와 교육과정에 대한 문헌 연구를 수행하였으며, 선행 연구의 결과를 토대로 7E 순환 학습 모델에 기반한 교과서 개발 Framework를 개발하였다. 개발한 Framework를 토대로 '시스템과 상호작용 - 지구시스템'의 성취 기준에 대한 학생 활동 중심의 고등학교 '과학' 교과서 모델을 개발하였다. 개발한 모델은 총 5차시 분량이며 시스템 사고, 융합인재교육에서 추구하는 여러 가지 목표를 반영하였다. 1~4차시까지는 최종산출물을 도출하기 위한 유기적은 연결되어 학생활동 중심의 탐구로 구성하였다. 마지막 5차시는 직업과 진로에 대하여 탐색할 수 있는 단원으로 제시하였다. 개발한 모형을 학교 현장에 투입한 후, 학생들의 반응을 살펴본 결과 수업에 대한 흥미, 교과서 내용, 산출물의 도출 등에서 학생들이 긍정적으로 응답하였다. 이러한 결과를 토대로 개발한 모델을 학교 교육과정에 적합하도록 수정 보완한 교과서가 만들어진다면 학생들의 긍정적인 변화를 이끌어낼 수 있을 것이다.

• 대한간호학회지
• /
• 제50권2호
• /
• pp.271-285
• /
• 2020

Purpose: This study examined the effects of a physical activity promoting program based on the Information-Motivation-Behavioral Skills (IMB) model on physical activity and health outcomes among obese older adults with knee osteoarthritis. Methods: This study utilized a randomized controlled trial with a convenience sample of 75 obese older adults with knee osteoarthritis in a university hospital. The older adults in the intervention group participated in a 12-week program involving weekly group sessions and monitoring calls with education booklets and video clips for exercise dances, while those in the control group received an usual care. Outcomes were measured using self-report questionnaires, anthropometrics, and blood analyses. The intervention effects were analyzed using Mann-Whitney U test and ANCOVA. Results: The mean age of participants was 74.9 years with 84.0% women. The intervention group at 12 weeks showed significantly greater improvements in self-efficacy for physical activity (F=81.92, p<.001), physical activity amounts (Z=-2.21, p=.044), knee joint function (F=15.88, p<.001), and health-related quality of life (F=14.89, p<.001) compared to the control group. Among obese-metabolic outcomes, the intervention group at 12 weeks showed a significant decrease in visceral fat mass (F=7.57, p=.008) and improvement in high-density level cholesterol (F=9.51, p=.003) compared to the control group. Conclusion: Study findings support the need for an IMB based physical activity program for promoting physical activity, knee function and health outcomes in obese older adults with knee osteoarthritis. Longitudinal studies are warranted to confirm the persistence of obese-metabolic effects in clinical settings.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권3호
• /
• pp.1189-1204
• /
• 2018

Detecting and capturing 3D human structures from the intensity-based image sequences is an inherently arguable problem, which attracted attention of several researchers especially in real-time activity recognition (Real-AR). These Real-AR systems have been significantly enhanced by using depth intensity sensors that gives maximum information, in spite of the fact that conventional Real-AR systems are using RGB video sensors. This study proposed a depth-based routine-logging Real-AR system to identify the daily human activity routines and to make these surroundings an intelligent living space. Our real-time routine-logging Real-AR system is categorized into two categories. The data collection with the use of a depth camera, feature extraction based on joint information and training/recognition of each activity. In-addition, the recognition mechanism locates, and pinpoints the learned activities and induces routine-logs. The evaluation applied on the depth datasets (self-annotated and MSRAction3D datasets) demonstrated that proposed system can achieve better recognition rates and robust as compare to state-of-the-art methods. Our Real-AR should be feasibly accessible and permanently used in behavior monitoring applications, humanoid-robot systems and e-medical therapy systems.

• 한국병원경영학회지
• /
• 제28권2호
• /
• pp.44-65
• /
• 2023

Purposes: As super-aging population and low fertility rates are threatening the sustainability of the National Health Insurance funds, enhancing the efficiency of hospital management is paramount. In the past, studies analyzing the efficiencies of hospitals primarily made inter-hospital comparisons, but it is important to assess hospitals' internal efficiency and develop improvement measures in order to attain practical improvements in hospital efficiencies. The purpose of this study is to analyze the efficiencies of specialists by medical specialty in a hospital in order to provide foundational data for efficient hospital management. Methodology/Approach: We used the activity-based costing (ABC) data and hospital statistical data from one tertiary hospital in Seoul to analyze the efficiency of specialists by medical specialty. Efficiency was analyzed and compared among specialists using the data envelopment analysis developed by Charnes, Cooper, and Rhodes (DEA-CCR) model and the slacks-based measure (SBM) models. The input variables were labor cost, material cost, and operational expenses, and the output variables were the number of outpatients, number of inpatients, outpatient revenue, and inpatient revenue. Findings: First, there was a marked deviation in efficiency across specialists. Second, there was a marked deviation in efficiency across medical specialties. Third, there was little difference in efficiency according to the specialist's sex, age, and job position. Fourth, the SBM model produced more conservative results and better explained efficiency parameters than the CCR model. Practical Implications: The efficiency of a specialist was more influenced by their medical specialty than their personal characteristics, namely sex, age, and job position. Therefore, Further research is needed to analyze the efficiencies of each subspecialty and identify factors that contribute to the variations in efficiencies across medical specialties, such as clinical practices and fee structures.

• 한국음향학회지
• /
• 제28권4호
• /
• pp.401-407
• /
• 2009

본 논문에서는 주파수 영역에서의 가우시안 혼합 모델 (Gaussian Mixture Model, GMM) 기반의 새로운 동시통화 검출 (Double-talk Detection, DTD) 알고리즘을 제안한다. 구체적으로 주파수 영역에서의 음향학적 반향억제 (Acoustic Echo Suppression, AES)를 위한 동시 통화 검출 알고리즘을 구성하기 위해 기존의 시간 영역에서의 동시통화 검출에 사용되는 상호 상관계수를 이산 푸리에 변환을 통해 16개 채널의 주파수 영역으로 변환하였다. 이러한 주파수 영역에서의 상호 상관계수를 GMM의 보다 효과적인 구성을 위해 통계적 분류 특성에 근거하여 우수한 7개를 선별하였다. 본 논문은 이러한 특징 벡터로 패턴인식에서 우수한 성능을 보이는 GMM을 구성하였으며 원단화자만 있는 구간, 동시통화 구간, 근단 화자만 있는 구간을 우도 (Likelihood) 비교에 따라 분류함으로써 별도의 원단 화자 신호에 대한 음성 검출기 (Voice Activity Detector, VAD)의 사용 없이 잡음환경과 반향 경로 변화에서 강인한 동시통화 검출 알고리즘을 제안한다. 다양한 실험 결과 제안된 방법은 기존의 상호 상관계수를 고정된 문턱 값과 가부 비교하여 동시 통화 구간을 검출하는 hard decision 방법에 비해 검출 오류 확률 (Detection Error Probability)을 비교한 결과 우수한 성능을 보였다.