• Transactions of the Korean Society of Automotive Engineers
• /
• v.17 no.1
• /
• pp.130-136
• /
• 2009

A lumped parameter model of Li-ion battery in hybrid electric vehicle(HEV) is constructed and system parameters are identified by using recursive least square estimation for different C-rates, SOCs and temperatures. The system characteristics of pole and zero in frequency domain are analyzed with the parameters obtained from different conditions. The parameterized model of Li-ion battery indicates highly dependant of temperatures. The system pole and internal resistance changes 6.6 and 18 times at $-20^{\circ}C$, comparing with those at $25^{\circ}C$, respectively. These results will be utilized on constructing model-based state observer or an on-line identification and an adaptation of the model parameters in battery management systems for hybrid electric vehicle applications.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.6C
• /
• pp.572-579
• /
• 2010

Filtered multi-tone (FMT) is a form of multicarrier modulation utilizing frequency-domain equalization efficient in multi-path fading channels. Doppler frequency information can be employed for channel estimation and link adaptation to improve the performance. However, most previous studies have concentrated on the orthogonal frequency division multiplexing (OFDM) instead of FMT. Moreover, they have not considered the synchronization error that can commonly occur in practical systems. In this paper, we propose Doppler frequency estimation scheme that is effective in FMT systems with residual synchronization error and high noise levels.

• Child Health Nursing Research
• /
• v.18 no.3
• /
• pp.101-108
• /
• 2012

Purpose: This study was designed to analyze recent trends in research about caregivers of hospitalized children in Korea and to suggest future research directions in this area. Methods: Eighty one studies selected from http://www.kan.or.kr, www.childnursing.or.kr, www.riss4u.net, and www.ndsl.kr published from 1995 to 2011 were used. The analysis framework of concepts was derived from client domain (Kim, 2000) and knowledge type (Kim et al., 2004). Results: In terms of research design, nonexperimental studies (82.7%) were the most frequent, followed by experimental studies (14.8%) and qualitative studies (2.5%). Mothers were the most frequent caregivers, and hospitalization was the most frequent health problem of the children. In terms of categories of the concepts, 35 (39.3%) studies included essentialistic concepts like coping and adaptation, 15 (16.9%) studies included problematic concepts like anxiety and uncertainty, and 39 (43.8%) studies included health-care experiential concepts like educational needs and nursing needs. In term of knowledge types, there were 35 (39.3%) studies of the explanatory knowledge type, 44 (49.5%) descriptive ones, and 10 (11.2%) prescriptive ones. Conclusion: The results indicate that further research is necessary on problematic concepts and prescriptive knowledge types for child health nursing practice which will lead to expanding nursing knowledge.

• Journal of Information Processing Systems
• /
• v.13 no.6
• /
• pp.1496-1515
• /
• 2017

One of the most visible developments in Decision Support Systems (DSS) was the emergence of rule-based expert systems. Hence, despite their success in many sectors, developers of Medical Rule-Based Systems have met several critical problems. Firstly, the rules are related to a clearly stated subject. Secondly, a rule-based system can only learn by updating of its rule-base, since it requires explicit knowledge of the used domain. Solutions to these problems have been sought through improved techniques and tools, improved development paradigms, knowledge modeling languages and ontology, as well as advanced reasoning techniques such as case-based reasoning (CBR) which is well suited to provide decision support in the healthcare setting. However, using CBR reveals some drawbacks, mainly in its interrelated tasks: the retrieval and the adaptation. For the retrieval task, a major drawback raises when several similar cases are found and consequently several solutions. Hence, a choice for the best solution must be done. To overcome these limitations, numerous useful works related to the retrieval task were conducted with simple and convenient procedures or by combining CBR with other techniques. Through this paper, we provide a combining approach using the multi-criteria analysis (MCA) to help, the traditional retrieval task of CBR, in choosing the best solution. Afterwards, we integrate this approach in a decision model to support medical decision. We present, also, some preliminary results and suggestions to extend our approach.

• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.55-64
• /
• 2019

In this study, we introduce trends in neural-network-based deep learning research applied to dialogue systems. Recently, end-to-end trainable goal-oriented dialogue systems using long short-term memory, sequence-to-sequence models, among others, have been studied to overcome the difficulties of domain adaptation and error recognition and recovery in traditional pipeline goal-oriented dialogue systems. In addition, some research has been conducted on applying reinforcement learning to end-to-end trainable goal-oriented dialogue systems to learn dialogue strategies that do not appear in training corpora. Recent neural network models for end-to-end trainable chit-chat systems have been improved using dialogue context as well as personal and topic information to produce a more natural human conversation. Unlike previous studies that have applied different approaches to goal-oriented dialogue systems and chit-chat systems respectively, recent studies have attempted to apply end-to-end trainable approaches based on deep neural networks in common to them. Acquiring dialogue corpora for training is now necessary. Therefore, future research will focus on easily and cheaply acquiring dialogue corpora and training with small annotated dialogue corpora and/or large raw dialogues.

• International Journal of Computer Science & Network Security
• /
• v.21 no.11
• /
• pp.97-104
• /
• 2021

The authors provide characteristics of the open educational platforms, classification and quantitative analysis regarding the availability of IT courses, teaching language, thematic directions on the following platforms: Coursera, EdX, Udemy, MIT Open Course Ware, OpenLearn, Intuit, Prometheus, UoPeople, Open Learning Initiative, Open University of Maidan (OUM). The quantitative analysis results are structured and visualized by tables and diagrams. The authors propose to use open educational resources (teaching, learning or research materials that are in the public domain or released with an intellectual property license that allows free use, adaptation, and distribution) for organization of independent work; for organization of distance or correspondence training; for professional development of teachers; for possibility and expediency of author's methods dissemination in the development of their own courses and promoting them on open platforms. Post-project activities are considered in comparing the courses content of one thematic direction, as well as studying the experience of their attending on different platforms.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.320-323
• /
• 2022

상호참조해결은 문서에서 명사, 대명사, 명사구 등의 멘션 후보를 식별하고 동일한 개체를 의미하는 멘션들을 찾아 그룹화하는 태스크이다. 딥러닝 기반의 한국어 상호참조해결 연구들에서는 BERT를 이용하여 단어의 문맥 표현을 얻은 후 멘션 탐지와 상호참조해결을 동시에 수행하는 End-to-End 모델이 주로 연구가 되었으며, 최근에는 스팬 표현을 사용하지 않고 시작과 끝 표현식을 통해 상호참조해결을 빠르게 수행하는 Start-to-End 방식의 한국어 상호참조해결 모델이 연구되었다. 최근에 한국어 상호참조해결을 위해 구축된 ETRI 데이터셋은 WIKI, QA, CONVERSATION 등 다양한 도메인으로 이루어져 있으며, 신규 도메인의 데이터가 추가될 경우 신규 데이터가 추가된 전체 학습데이터로 모델을 다시 학습해야 하며, 이때 많은 시간이 걸리는 문제가 있다. 본 논문에서는 이러한 상호참조해결 모델의 도메인 적응에 Continual learning을 적용해 각기 다른 도메인의 데이터로 모델을 학습 시킬 때 이전에 학습했던 정보를 망각하는 Catastrophic forgetting 현상을 억제할 수 있음을 보인다. 또한, Continual learning의 성능 향상을 위해 2가지 Transfer Techniques을 함께 적용한 실험을 진행한다. 실험 결과, 본 논문에서 제안한 모델이 베이스라인 모델보다 개발 셋에서 3.6%p, 테스트 셋에서 2.1%p의 성능 향상을 보였다.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.26 no.1
• /
• pp.44-53
• /
• 2023

Adversarial attacks have received great attentions for their capacity to distract state-of-the-art neural networks by modifying objects in physical domain. Patch-based attack especially have got much attention for its optimization effectiveness and feasible adaptation to any objects to attack neural network-based object detectors. However, despite their strong attack performance, generated patches are strongly perceptible for humans, violating the fundamental assumption of adversarial examples. In this paper, we propose a camouflaged adversarial patch optimization method using military camouflage assessment metrics for naturalistic patch attacks. We also investigate camouflaged attack loss functions, applications of various camouflaged patches on army tank images, and validate the proposed approach with extensive experiments attacking Yolov5 detection model. Our methods produce more natural and realistic looking camouflaged patches while achieving competitive performance.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.415-418
• /
• 2019

기계독해 모델에 새로운 도메인을 적용하기 위해서는 도메인에 맞는 데이터가 필요하다. 그러나 추가 데이터 구축은 많은 비용이 발생한다. 사람이 직접 구축한 데이터 없이 적용하기 위해서는 자동 추가 데이터 확보, 도메인 적응의 문제를 해결해야한다. 추가 데이터 확보의 경우 번역, 질의 생성의 방법으로 연구가 진행되었다. 그러나 도메인 적응을 위해서는 새로운 정답 유형에 대한 질의가 필요하며 이를 위해서는 정답 후보 추출, 추출된 정답 후보로 질의를 생성해야한다. 본 논문에서는 이러한 문제를 해결하기 위해 듀얼 포인터 네트워크 기반 정답 후보 추출 모델로 정답 후보를 추출하고, 포인터 제너레이터 기반 질의 생성 모델로 새로운 데이터를 생성하는 방법을 제안한다. 실험 결과 추가 데이터 확보의 경우 KorQuAD, 경제, 금융 도메인의 데이터에서 모두 성능 향상을 보였으며, 도메인 적응 실험에서도 새로운 도메인의 문맥만을 이용해 데이터를 생성했을 때 기존 도메인과 다른 도메인에서 모두 기계독해 성능 향상을 보였다.

• Asian-Australasian Journal of Animal Sciences
• /
• v.30 no.2
• /
• pp.267-274
• /
• 2017

Objective: The objective of this study was to investigate the effect of 20-day litter weight on behavior and heart rate variability (HRV) of piglets under stress. Methods: Forty four original litters were categorized as high litter weight (HW) litters (n = 22) and low litter weight (LW) litters (n = 22) by 20-day litter weight. From each original HW litter, three males and three females were randomly selected after weaning and the 12 piglets from two original litters with similar age of days were regrouped into one new high litter weight (NHW) litter (11 NHW litters in total). The original LW litters were treated with a same program, so that there were 11 new low litter weight (NLW) litters as well. The latencies to first fighting, fighting frequencies and duration within three hours were recorded after regrouping and the lesions on body surface within 48 hours were scored. Besides, HR (heart rate, bpm, beats per minute) and activity count (ACT), time domain indexes and frequency domain indexes of the piglets were measured in an isolation trial to analyze the discrepancy in coping with stress between the original HW and LW litters. Results: The results exhibited that piglets from the HW litters launched fighting sooner and got statistically higher skin lesion score than those from the LW litters (p = 0.03 and 0.02, respectively). Regarding the HRV detection, compared with the HW litters, the LW litters exhibited a lower mean HR (p<0.05). In the isolation test, a highly significant higher ACT value was observed between the HW litters, compared to the LW litters (p<0.01). Significant differences were observed in standard deviation of R-R intervals, standard deviation of all normal to normal intervals, and most frequency-domain indicators: very low-frequency, low-frequency, and high frequency between the HW and LW litters as well. The difference in LF:HF was not significant (p = 0.779). Conclusion: This study suggests that compared with litters of low 20-day litter weights, litters with higher 20-day litter weight take more positive strategies to cope with stress and have stronger HRV regulation capacity; HW litters demonstrate better anti-stress and adaptation capacity in the case of regrouping and isolation.