• 산업기술연구
• /
• 제18권
• /
• pp.379-384
• /
• 1998

Conventional short-term load forecasting techniques have limitation in their use on holidays due to dissimilar load behaviors of holidays and insufficiency of pattern data. Thus, a new short-term load forecasting method for special days in anomalous load conditions is proposed in this paper. The proposed method uses two Artificial Neural Networks(ANN); one is for the estimation of load curve, and the other is for the estimation of minimum and maximum value of load. The forecasting procedure is as follows. First, the normalized load curve is estimated by ANN. At next step, minimum and maximum values of load in a special day are estimated by another ANN. Finally, the estimate of load in a whole special day is obtained by combining these two outputs of ANNs. The proposed method shows a good performance, and it may be effectively applied to the practical situations.

• 한국사회복지학
• /
• 제62권2호
• /
• pp.279-306
• /
• 2010

본 연구는 정책네트워크이론을 적용하여 한국과 일본의 노인장기요양(개호)보험제도의 정책결정과정을 상호 비교, 분석하고 우리나라에의 정책적 이론적 시사점을 도출하고자 하였다. 연구결과로는, 한국과 일본 모두 노인요양(개호)문제에 대한 정책의제형성은 정부 주도로 이루어지고 정책과정단계별 특성에 따라 정책참여자의 범위가 확대되었으나, 두 나라간 노인요양문제에 대한 정책의제형성 배경에는 차이가 있음을 알 수 있다. 그리고 두 나라 모두 정책의제형성 초기단계부터 정책참여자간의 상호 작용은 비교적 협력적이었으나, 제도골격이 국민들에게 공표되면서 급격히 갈등관계 내지 비판적으로 변화해 갔으며, 정책과정단계별 특성에 따라 주도적 참여자들의 역할이 두드러졌고, 연계형태도 비슷한 모습을 보여주고 있다. 또한 정책과정별로 정책참여자의 범위와 정책산출에의 정책참여자들의 의견 반영 정도가 다르지만, 한국, 일본 모두 정부주도로 노인요양문제에 대한 정책 추진결과로 정책의제형성기부터 국회심의결정기까지 매우 유사한 정책네트워크모형을 보여주고 있다. 정책참여자의 범위 뿐만 아니라 개방적인 상호작용시스템 구축의 중요성, 개호보험제도 정책결정과정의 많은 한계점, 과도한 정부주도 정책네트워크로 인한 정책산출에 정부의지가 너무 많이 반영되는 단점 등이 본 연구의 시사점으로 볼 수 있다.

• 디지털융복합연구
• /
• 제15권4호
• /
• pp.259-266
• /
• 2017

무선 홈 IoT (Internet of Things)상에서 대용량 트래픽 간섭은 패킷 손실의 원인이 되며, 패킷 손실은 무선 홈 네트워크의 QoS와 처리율을 떨어뜨린다. 본 논문에서는 실시간 트래픽과 비실시간 트래픽을 탐지하여 무선 홈 IoT 서비스의 QoS 및 처리율을 향상시키기 위한 새로운 적응형 트래픽 간섭 제어 시스템, ATICS(Adaptive Traffic Interference Control System)을 제안한다. 제안된 시스템은 트래픽 특성에 따라 단기(short term) 트래픽 혼잡 프로세스와 장기(long-term) 트래픽 혼잡 프로세스로 구분하여 트래픽 간섭을 제어한다. 시뮬레이션 결과 제안된 기법은 다른 비교 기법들에 비해서 트래픽 간섭 제어 성능 척도가 더 효율적임을 보인다.

• 디지털산업정보학회논문지
• /
• 제15권1호
• /
• pp.1-7
• /
• 2019

The objective of this study is to examine the trends in big data. Research abstracts were extracted from 4,019 articles, published between 1995 and 2018, on Web of Science and were analyzed using topic modeling and time series analysis. The 20 single-term topics that appeared most frequently were as follows: model, technology, algorithm, problem, performance, network, framework, analytics, management, process, value, user, knowledge, dataset, resource, service, cloud, storage, business, and health. The 20 multi-term topics were as follows: sense technology architecture (T10), decision system (T18), classification algorithm (T03), data analytics (T17), system performance (T09), data science (T06), distribution method (T20), service dataset (T19), network communication (T05), customer & business (T16), cloud computing (T02), health care (T14), smart city (T11), patient & disease (T04), privacy & security (T08), research design (T01), social media (T12), student & education (T13), energy consumption (T07), supply chain management (T15). The time series data indicated that the 40 single-term topics and multi-term topics were hot topics. This study provides suggestions for future research.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제11권4호
• /
• pp.238-246
• /
• 2011

This paper proposes a new semantic representation and its associated similarity measure. The representation expresses textual context observed in a context of a certain term as a network where nodes are terms and edges are the number of cooccurrences between connected terms. To compare terms represented in networks, a graph kernel is adopted as a similarity measure. The proposed representation has two notable merits compared with previous semantic representations. First, it can process polysemous words in a better way than a vector representation. A network of a polysemous term is regarded as a combination of sub-networks that represent senses and the appropriate sub-network is identified by context before compared by the kernel. Second, the representation permits not only words but also senses or contexts to be represented directly from corresponding set of terms. The validity of the representation and its similarity measure is evaluated with two tasks: synonym test and unsupervised word sense disambiguation. The method performed well and could compete with the state-of-the-art unsupervised methods.

• Structural Monitoring and Maintenance
• /
• 제5권1호
• /
• pp.51-65
• /
• 2018

A number of sensing techniques have been implemented for detecting defects in civil infrastructures instead of onsite human inspections in structural health monitoring. However, the issue of faults in sensors has not received much attention. This issue may lead to incorrect interpretation of data and false alarms. To overcome these challenges, this article presents a deep learning-based method with a new architecture of Stateful Long Short Term Memory Neural Networks (S-LSTM NN) for detecting sensor fault without going into details of the fault features. As LSTMs are capable of learning data features automatically, and the proposed method works without an accurate mathematical model. The detection of four types of sensor faults are studied in this paper. Non-stationary acceleration responses of a three-span continuous bridge when under operational conditions are studied. A deep network model is applied to the measured bridge data with estimation to detect the sensor fault. Another set of sensor output data is used to supervise the network parameters and backpropagation algorithm to fine tune the parameters to establish a deep self-coding network model. The response residuals between the true value and the predicted value of the deep S-LSTM network was statistically analyzed to determine the fault threshold of sensor. Experimental study with a cable-stayed bridge further indicated that the proposed method is robust in the detection of the sensor fault.

• Journal of the Korean Data and Information Science Society
• /
• 제26권1호
• /
• pp.151-159
• /
• 2015

이 논문에서는 텍스트마이닝 (text mining) 기법을 이용하여 한국데이터정보과학회지에 게재된 논문의 영어초록을 분석하였다. 먼저 다양한 방법을 통해 단어-문서 행렬 (term-document matrix)을 생성하고 이를 사회연결망 분석 (social network analysis)을 통해 시각화하였다. 또한 토픽을 추출하기 위한 방법으로 LDA (latent Dirichlet allocation)와 CTM (correlated topic model)을 사용하였다. 토픽의 수, 단어-문서 행렬의 생성방법에 따라 엔트로피 (entropy)를 통해 토픽 추출 모형들의 성능을 비교하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권6호
• /
• pp.2612-2633
• /
• 2020

Due to the explosive growth of multimedia speech data, how to protect the privacy of speech data and how to efficiently retrieve speech data have become a hot spot for researchers in recent years. In this paper, we proposed an encrypted speech retrieval scheme based on long short-term memory (LSTM) neural network and deep hashing. This scheme not only achieves efficient retrieval of massive speech in cloud environment, but also effectively avoids the risk of sensitive information leakage. Firstly, a novel speech encryption algorithm based on 4D quadratic autonomous hyperchaotic system is proposed to realize the privacy and security of speech data in the cloud. Secondly, the integrated LSTM network model and deep hashing algorithm are used to extract high-level features of speech data. It is used to solve the high dimensional and temporality problems of speech data, and increase the retrieval efficiency and retrieval accuracy of the proposed scheme. Finally, the normalized Hamming distance algorithm is used to achieve matching. Compared with the existing algorithms, the proposed scheme has good discrimination and robustness and it has high recall, precision and retrieval efficiency under various content preserving operations. Meanwhile, the proposed speech encryption algorithm has high key space and can effectively resist exhaustive attacks.

• International Journal of Knowledge Content Development & Technology
• /
• 제9권3호
• /
• pp.23-41
• /
• 2019

This study combines the concept of degree centrality in complex network with the Term Frequency $^*$ Proportional Document Frequency ($TF^*PDF$) algorithm; the combined method, called PMCN (PDF-Modified similarity and Complex Network), constructs relationship networks among sentences for writing news summaries. The PMCN method is a multi-document summarization extension of the ideas of Bun and Ishizuka (2002), who first published the $TF^*PDF$ algorithm for detecting hot topics. In their $TF^*PDF$ algorithm, Bun and Ishizuka defined the publisher of a news item as its channel. If the PDF weight of a term is higher than the weights of other terms, then the term is hotter than the other terms. However, this study attempts to develop summaries for news items. Because the $TF^*PDF$ algorithm summarizes daily news, PMCN replaces the concept of "channel" with "the date of the news event", and uses the resulting chronicle ordering for a multi-document summarization algorithm, of which the F-measure scores were 0.042 and 0.051 higher than LexRank for the famous d30001t and d30003t tasks, respectively.

• Smart Structures and Systems
• /
• 제31권1호
• /
• pp.45-56
• /
• 2023

Vibration-based structural health monitoring is used to ensure the safety of structures by installing sensors in structures. The peak picking method, one of the applications of vibration-based structural health monitoring, is a method that analyze the dynamic characteristics of a structure using the peaks of the frequency response function. However, the results may vary depending on the person predicting the peak point; further, the method does not predict the exact peak point in the presence of noise. To overcome the limitations of the existing peak picking methods, this study proposes a new method to automate the modal analysis process by utilizing long short-term memory, a type of recurrent neural network. The method proposed in this study uses the time series data of the frequency response function directly as the input of the LSTM network. In addition, the proposed method improved the accuracy by using the phase as well as amplitude information of the frequency response function. Simulation experiments and lab-scale model experiments are performed to verify the performance of the LSTM network developed in this study. The result reported a modal assurance criterion of 0.8107, and it is expected that the dynamic characteristics of a civil structure can be predicted with high accuracy using data without experts.