• The Korean Journal of Applied Statistics
• /
• v.35 no.6
• /
• pp.685-701
• /
• 2022

FDR is widely used in high-dimensional data inference since it provides more liberal criterion contrary to FWER which is known to be very conservative by controlling Type-1 errors. This paper proposes a sparse VHAR model estimation method controlling FDR by adapting the knockoff introduced by Barber and Candès (2015). We also compare knockoff with conventional method using adaptive Lasso (AL) through extensive simulation study. We observe that AL shows sparsistency and decent forecasting performance, however, AL is not satisfactory in controlling FDR. To be more specific, AL tends to estimate zero coefficients as non-zero coefficients. On the other hand, knockoff controls FDR sufficiently well under desired level, but it finds too sparse model when the sample size is small. However, the knockoff is dramatically improved as sample size increases and the model is getting sparser.

• International Journal of Computer Science & Network Security
• /
• v.23 no.1
• /
• pp.153-163
• /
• 2023

This study is situated in the context of intelligent transport systems, where in-vehicle devices assist drivers to avoid accidents and therefore improve road safety. The vehicles present in a given area form an ad' hoc network of vehicles called vehicular ad' hoc network. In this type of network, the nodes are mobile vehicles and the messages exchanged are messages to warn about obstacles that may hinder the correct driving. Node mobilities make it impossible for inter-node communication to be end-to-end. Recognizing this characteristic has led to delay-tolerant vehicular networks. Embedded devices have small buffers (memory) to hold messages that a node needs to transmit when no other node is within its visibility range for transmission. The performance of a vehicular delay-tolerant network is closely tied to the successful management of the nodes' transit buffer. In this paper, we propose a message transit buffer management model for nodes in vehicular delay tolerant networks. This model consists in setting up, on the one hand, a policy of dropping messages from the buffer when the buffer is full and must receive a new message. This drop policy is based on the concept of intermediate node to destination, queues and priority class of service. It is also based on the properties of the message (size, weight, number of hops, number of replications, remaining time-to-live, etc.). On the other hand, the model defines the policy for selecting the message to be transmitted. The proposed model was evaluated with the ONE opportunistic network simulator based on a 4000m x 4000m area of downtown Bouaké in Côte d'Ivoire. The map data were imported using the Open Street Map tool. The results obtained show that our model improves the delivery ratio of security alert messages, reduces their delivery delay and network overload compared to the existing model. This improvement in communication within a network of vehicles can contribute to the improvement of road safety.

• Journal of Korean Critical Care Nursing
• /
• v.16 no.1
• /
• pp.28-43
• /
• 2023

Purpose : Intensive care unit (ICU) diaries have been implemented across the international ICU community. This study aimed to comprehend the meaning and nature of the lived experience of patients' families using the ICU diary in Korea. Methods : This qualitative study adopted van Manen's hermeneutic phenomenology. The participants comprised eight women and two men who were the family members of patients in the ICU for more than three days. Data were collected using in-depth interviews and observation from July 2018 to January 2019. Results : Patients' families who experienced the ICU diary recognized it with six beings according to time: a good idea, forgotten stuff, burdensome work, touching service, my stuff, and a thing in the memory. The ICU diary had three essential meanings for the families: communication, solace and hope, and a record of life. These findings were rearranged according to van Manen's fundamental existential, and the lived things and lived others were remarkably confirmed. Conclusion : Patients' families experienced various ICU diary forms over time and recognized an ICU diary as a means of communication. Therefore, the ICU diary is expected to be used as an intervention between families and healthcare providers in the ICU to support mutual communication.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.305-307
• /
• 2021

Alzheimer's Disease (AD) is a cognitive disorder characterized by memory impairment that can be assessed at early stages based on administering clinical tests. However, the AD pathophysiological mechanism is still poorly understood due to the difficulty of distinguishing different levels of AD severity, even using a variety of brain modalities. Therefore, in this study, we present a hybrid EEG-fNIRS modalities to compensate for each other's weaknesses with the help of Machine Learning (ML) techniques for classifying four subject groups, including healthy controls (HC) and three distinguishable groups of AD levels. A concurrent EEF-fNIRS setup was used to record the data from 41 subjects during Oddball and 1-back tasks. We employed both a traditional neural network (NN) and a CNN-LSTM hybrid model for fNIRS and EEG, respectively. The final prediction was then obtained by using majority voting of those models. Classification results indicated that the hybrid EEG-fNIRS feature set achieved a higher accuracy (71.4%) by combining their complementary properties, compared to using EEG (67.9%) or fNIRS alone (68.9%). These findings demonstrate the potential of an EEG-fNIRS hybridization technique coupled with ML-based approaches for further AD studies.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.198-198
• /
• 2021

최근 자연적, 사회적, 정책적 관점에서 하천관리의 중요성이 증대되면서 국가하천 정비를 통한 하천시설 관리의 책임이 증대되고 있다. 국가하천 5대강 본류의 친수지구 이용도 변화를 살펴보면 2015년에 비해 2019년에 면적당 이용객 수가 630,813(명/km²)이 증가하였음을 알 수 있었고(국토교통부, 2020) 본 연구에서는 이용자 수 증가율이 높은 편인 한강 내 하천이용시설을 대상으로 선정하여 해당 지역을 기계학습 기반의 수위예측 알고리즘에 적용하였다. 하천이용시설은 하천이용자가 편리하게 하천을 이용하기 위하여 설치한 시설로 공원시설(강서, 난지, 양화, 망원, 여의도, 이촌, 반포, 잠원, 뚝섬, 잠실, 광나루, 구리)을 위주로 분석하였다. 해당 시설의 침수피해를 고려하기 위해 시계열 자료에 특화된 LSTM(Long Short-term Memory)기법을 활용하여 수위예측 알고리즘을 개발하였고 이를 통해 도출된 홍수 예보로 재난을 대비하고 시설물을 체계적으로 관리하는 유지관리의 효과를 분석하고자 하였다. 입력 자료(input data)는 수위 (EL.m), 팔당댐 방류량 (m³/s), 강화대교의 조위(EL.m)를 사용하였으며 수위예측 알고리즘을 통해 6시간 후 예측 수위값을 도출하여 기존 2단계(주의보, 경보)였던 홍수 예보 단계에서 4단계(관심, 보행자통제, 차량통제, 경계)로 구축하였다. 기존과 세분화된 홍수예보를 적용했을 경우의 유지관리 비용과 편익을 산정하여 하천이용시설의 경제성을 비교·분석한 결과, 유지관리 비용이 기존 대비 약 5% 이상 절감되었고 편익은 약 1.5배 이상 증가하였으며 관리등급은 평균 C등급(보통) 이상 달성하였다. 이는 수위예측 알고리즘의 적용으로 하천이용 활성화 및 투자의 효율성에 목적을 두었으며 향후 분석결과를 토대로 경제성모델을 개발하여 국가하천 내 관리그룹에 적용하면 효율적인 유지관리체계를 제시할 수 있을 것으로 기대된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.333-333
• /
• 2021

최근 전 지구적인 기후변화 및 온난화의 영향으로 태풍 및 집중호우가 빈번하게 일어나고 있으며, 이로 인한 한천범람 등 홍수재해로 인명 및 재산 피해가 크게 증가하고 있다. 우리나라에서도 태풍 및 집중호우로 인한 호수피해는 매년 발생하고 있으며, 피해 빈도와 강도가 증가하고 있는 실정이다. 이러한 현실을 고려하였을 때에 하천 인근 주민의 생명과 재산을 보호하기 위하여 실시간으로 홍수위 예측을 수행하는 것은 매우 중요하다 할 수 있다. 국내에서 수위예측을 위하여 대표적으로 저류함수모형(Storage Function Model, SFM)을 채택하고 있지만, 유역면적이 작아 홍수 도달시간이 짧은 중소하천에서는 충분한 선행시간과 정확도를 확보하기 어려운 문제점이 있다. 이는 유역면적이 작은 중소하천에서는 유역 및 기상 특성과 관련된 여러 인자 사이의 비선형성이 대하천 유역에 비해 커지는 문제점이 있기 때문이다. 본 연구에서는 위와같은 문제를 해결할 수 있도록, 수문자료와 딥러닝 기법을 적용하여 실시간으로 홍수위를 예측할 수 있는 방법론을 제시하였다. 지난 태풍 및 집중호우로 인하여 급격한 수위상승이 있던 낙동강 지류하천에 대하여 LSTM(Long-Short Term Memory) 모형 기반 실시간 수위예측 모형을 개발하였으며, 선행시간 30~180분 별로 홍수위를 예측하고 관측 수위와 비교함으로써 모형의 적용성을 검증하였다. 선행시간 180분 기준으로 영강 유역 수위예측 결과와 실제 관측치의 평균제곱근 오차는 0.29m, 상관계수는 0.92로 나타났으며, 밀양강 유역의 경우 각각 0.30m, 0.94로 나타났다. 본 연구에서 제시된 딥러닝 기반모형에 10분 단위 실시간 수문자료가 입력된다면, 다음 관측자료가 입력되기 전 홍수예측 결과가 산출되므로 실질적인 홍수예경보체계에 유용하게 사용될 수 있을 것이라 보인다. 모형에 적용할 수 있는 더욱 다양한 수문자료와 매개변수 조정을 통하여 예측결과에 대한 신뢰성을 더욱 높일 수 있다면, 기존의 저류함수모형과 연계하여 홍수대응 능력을 향상시키는데 도움이 될 수 있다.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.699-706
• /
• 2023

Recently, the 4 generation industry revolution is developed with advanced and combined with a variety of new technologies. Conventional healthcare system is applied with IoT application. It provides many advantages with mobility and swift data transfers to patient and doctor. In despite of these kinds of advantages, it occurred security issues between basic devices and protocols in their applications. Especially, internet of things have restricted and limited resources such as small memory capacity, low capability of computing power, etc. Therefore, we can not utilize conventional mechanism. In this paper, we analyzed attacks and vulnerability in terms of security issues. To analyze security structure, features, demands and requirements, we solve the methods to be reduced security issues.

• Structural Engineering and Mechanics
• /
• v.85 no.4
• /
• pp.469-484
• /
• 2023

A deep recursive bidirectional Cuda Deep Neural Network Long Short Term Memory (Bi-CuDNNLSTM) layer is recruited in this paper to predict the entire force time histories, and the corresponding hysteresis and backbone curves of reinforced concrete (RC) bridge piers using experimental fast and slow cyclic tests. The proposed stacked Bi-CuDNNLSTM layers involve multiple uncertain input variables, including horizontal actuator displacements, vertical actuators axial loads, the effective height of the bridge pier, the moment of inertia, and mass. The functional application programming interface in the Keras Python library is utilized to develop a deep learning model considering all the above various input attributes. To have a robust and reliable prediction, the dataset for both the fast and slow cyclic tests is split into three mutually exclusive subsets of training, validation, and testing (unseen). The whole datasets include 17 RC bridge piers tested experimentally ten for fast and seven for slow cyclic tests. The results bring to light that the mean absolute error, as a loss function, is monotonically decreased to zero for both the training and validation datasets after 5000 epochs, and a high level of correlation is observed between the predicted and the experimentally measured values of the force time histories for all the datasets, more than 90%. It can be concluded that the maximum mean of the normalized error, obtained through Box-Whisker plot and Gaussian distribution of normalized error, associated with unseen data is about 10% and 3% for the fast and slow cyclic tests, respectively. In recapitulation, it brings to an end that the stacked Bi-CuDNNLSTM layer implemented in this study has a myriad of benefits in reducing the time and experimental costs for conducting new fast and slow cyclic tests in the future and results in a fast and accurate insight into hysteretic behavior of bridge piers.

• Asia Marketing Journal
• /
• v.14 no.4
• /
• pp.57-75
• /
• 2013

It is a well-established theory that emotion is influential in cognitive processing. Extensive prior research on emotion has shown that emotional factors, such as affect, mood, and feeling, play as information indicating whether he or she has enough knowledge. Most of their findings focused on the effect of emotional valence (i.g., one's subjective positivity or negativity related with the emotion). Recently, several studies on emotion suggest that there is another dimension of emotion, which affects the type of cognitive processing. The studies argue that emotional certainty facilitates heuristic processing, whereas emotional uncertainty promotes systematic processing. Based on the findings, current study examines the effect of certainty on attitudes and recall. Specifically, the authors investigate the effect of certainty on how much effort individuals use to process advertising information and how certainty affects attitude formation toward the advertised product. The authors also focus on recall to clarify the working mechanism of certainty on attitudes, because recall performance reflects the depth of information processing. Based on previous findings, the authors hypothesize that uncertainty (vs. certainty) leads to more favorable attitudes as well as better recall, and conduct an experiment using a fictitious advertisement with 218 participants. The results confirm the predicted effects of certainty only on attitudes not recall. A possible explanation of this discrepancy between attitudes and recall lies in the measurement method, unaided recall. To rule out this possibility, the authors perform an additional analysis with the participants who recall any correct information of the target advertisement. The results show certainty has a negative effect on both attitudes and recall. A bootstrapping test reveals that recall mediates the effect of certainty on attitudes. This result confirms that certainty decreases elaboration, which in turn leads to less favorable attitudes relative to uncertainty. Additionally, our data shows the association among certainty, recall, and attitudes by showing the indirect effect of certainty on attitudes via recall. This research encourages practitioners in the field to emphasize that they should focus on target audiences' emotional certainty before they provide the persuasive message, by showing that uncertainty promotes effortful processing, which in turn leads to better memory and more favorable attitudes.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.06a
• /
• pp.110-110
• /
• 2022

본 연구는 자율운항 선박의 원격 고장 진단 기법 개발의 일부로 수행되었다. 특히, 엔진 연료 계통 장비로부터 계측된 시계열 데이터로부터 상태 진단을 위한 알고리즘 구현 결과를 제시하였다. 엔진 연료 펌프와 청정기를 가진 육상 실험 장비로부터 진동 시계열 데이터 계측하였으며, 이상 감지, 고장 분류 및 고장 예측이 가능한 심층 학습(Deep Learning) 및 기계 학습(Machine Learning) 알고리즘을 구현하였다. 육상 실험 장비에 고장 유형 별로 인위적인 고장을 발생시켜 특징적인 진동 신호를 계측하여, 인공 지능 학습에 이용하였다. 계측된 신호 데이터는 선행 발생한 사건의 신호가 후행 사건에 영향을 미치는 특성을 가지고 있으므로, 시계열에 내포된 고장 상태는 시간 간의 선후 종속성을 반영할 수 있는 학습 알고리즘을 제시하였다. 고장 사건의 시간 종속성을 반영할 수 있도록 순환(Recurrent) 계열의 RNN(Recurrent Neural Networks), LSTM(Long Short-Term Memory models)의 모델과 합성곱 연산 (Convolution Neural Network)을 기반으로 하는 Conv1D 모델을 적용하여 예측 정확성을 비교하였다. 특히, 합성곱 계열의 RNN LSTM 모델이 고차원의 순차적 자연어 언어 처리에 장점을 보이는 모델임을 착안하여, 신호의 시간 종속성을 학습에 반영할 수 있는 합성곱 계열의 Conv1 알고리즘을 고장 예측에 사용하였다. 또한 기계 학습 모델의 효율성을 감안하여 XGBoost를 추가로 적용하여 고장 예측을 시도하였다. 최종적으로 연료 펌프와 청정기의 진동 신호로부터 Conv1D 모델과 XGBoost 모델의 고장 예측 성능 결과를 비교하였다