• KIPS Transactions on Computer and Communication Systems
• /
• v.2 no.6
• /
• pp.279-290
• /
• 2013

In digital forensics log files have been stored as a form of large data for the purpose of tracing users' past behaviors. It is difficult for investigators to manually analysis the large log data without clues. In this paper, we propose a text mining technique for extracting intrusion logs from a large log set to recommend reliable evidences to investigators. In the training stage, the proposed method extracts intrusion association words from a training log set by using Apriori algorithm after preprocessing and the probability of intrusion for association words are computed by combining support and confidence. Robinson's method of computing confidences for filtering spam mails is applied to extracting intrusion logs in the proposed method. As the results, the association word knowledge base is constructed by including the weights of the probability of intrusion for association words to improve the accuracy. In the test stage, the probability of intrusion logs and the probability of normal logs in a test log set are computed by Fisher's inverse chi-square classification algorithm based on the association word knowledge base respectively and intrusion logs are extracted from combining the results. Then, the intrusion logs are recommended to investigators. The proposed method uses a training method of clearly analyzing the meaning of data from an unstructured large log data. As the results, it complements the problem of reduction in accuracy caused by data ambiguity. In addition, the proposed method recommends intrusion logs by using Fisher's inverse chi-square classification algorithm. So, it reduces the rate of false positive(FP) and decreases in laborious effort to extract evidences manually.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.10
• /
• pp.293-302
• /
• 2016

Since the electricity is produced and consumed simultaneously, predicting the electric load and securing affordable electric power are necessary for reliable electric power supply. In particular, a university campus is one of the highest power consuming institutions and tends to have a wide variation of electric load depending on time and environment. For these reasons, an accurate electric load forecasting method that can predict power consumption in real-time is required for efficient power supply and management. Even though various influencing factors of power consumption have been discovered for the educational institutions by analyzing power consumption patterns and usage cases, further studies are required for the quantitative prediction of electric load. In this paper, we build an electric load forecasting model by implementing and evaluating various machine learning algorithms. To do that, we consider three building clusters in a campus and collect their power consumption every 15 minutes for more than one year. In the preprocessing, features are represented by considering periodic characteristic of the data and principal component analysis is performed for the features. In order to train the electric load forecasting model, we employ both artificial neural network and support vector machine. We evaluate the prediction performance of each forecasting model by 5-fold cross-validation and compare the prediction result to real electric load.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.10
• /
• pp.347-352
• /
• 2016

Recently, IoT technology has been applied in various field. In particular, the technology focuses on analysing large amount of data that has been gathered from the environmental sensors, to provide valuable information. This technique has been actively researched in the agro-industrial sector. Many researches are underway in the monitoring and control for growth crop environment in agro-industrial. Normally, the average weather data is provided by the manual agro-control method but the value may differ due to the different region's weather and environment that may cause problem in the disease and insect-pest prevention. In order to develop a suitable integrated system for fruit tree, all the necessary information is obtained from the Jeollanam-do province, which has the high production rate in the Korea. In this paper, we propose an integrated support platform for the growing crops, to minimize the damage caused due to the weather disaster through image analysis, forecasting models, by using the micro-climate weather information collection and CCTV. The fruit tree damage caused by the weather disaster are controlled by utilizing various IoT technology by maintaining the growth environment, which helps in the disease and insect-pest prevention and also helps farmers to improve the expected production.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.10
• /
• pp.311-318
• /
• 2016

IoT(Internet of Things areas) rich information based on the user easy access to service creation must be one of the power system of specificity due following: The IoT spread obstacle to the act be, and 'Smart Grid information of this is not easy under power plants approach the Directive on the protection measures, particularly when stringent security policies IoT technologies applied to Advanced Metering Infrastructure sector has been desired. This is a situation that occurs is limited to the application and use of IoT technologies in the power system. Power Information Network is whilst closed network operating is has a smart grid infrastructure, smart grid in an open two-way communication for review and although information security vulnerabilities increased risk of accidents increases as according to comprehensive security policies and technologies are required and can. In this paper, the IoT platform architecture design of information systems as part of the power of research and development IoT-based energy information platform aims. And to establish a standard framework for a connection to one 'Sensor-Gateway-Network-platform sensors Service' to provide power based on the IoT services and solutions. Framework is divided into "sensor-gateway" platform to link information modeling and gateways that can accommodate the interlocking standards and handling protocols variety of sensors Based on this real-time data collection, analysis and delivery platform that performs the role of the relevant and to secure technology.

• Journal of KIISE
• /
• v.42 no.10
• /
• pp.1195-1206
• /
• 2015

For the management of a knowledge system, systems that automatically infer and manage scalable knowledge are required. Most of these systems use ontologies in order to exchange knowledge between machines and infer new knowledge. Therefore, approaches are needed that infer new knowledge for scalable ontology. In this paper, we propose an approach to perform rule based reasoning for scalable SHIF ontologies in a spark framework which works similarly to MapReduce in distributed memories on a cluster. For performing efficient reasoning in distributed memories, we focus on three areas. First, we define a data structure for splitting scalable ontology triples into small sets according to each reasoning rule and loading these triple sets in distributed memories. Second, a rule execution order and iteration conditions based on dependencies and correlations among the SHIF rules are defined. Finally, we explain the operations that are adapted to execute the rules, and these operations are based on reasoning algorithms. In order to evaluate the suggested methods in this paper, we perform an experiment with WebPie, which is a representative ontology reasoner based on a cluster using the LUBM set, which is formal data used to evaluate ontology inference and search speed. Consequently, the proposed approach shows that the throughput is improved by 28,400% (157k/sec) from WebPie(553/sec) with LUBM.

• Journal of KIISE
• /
• v.42 no.3
• /
• pp.307-319
• /
• 2015

Current ontology studies use the Hadoop distributed storage framework to perform map-reduce algorithm-based reasoning for scalable ontologies. In this paper, however, we propose a novel approach for scalable Web Ontology Language (OWL) Horst Lite ontology reasoning, based on distributed cluster memories. Rule-based reasoning, which is frequently used for scalable ontologies, iteratively executes triple-format ontology rules, until the inferred data no longer exists. Therefore, when the scalable ontology reasoning is performed on computer hard drives, the ontology reasoner suffers from performance limitations. In order to overcome this drawback, we propose an approach that loads the ontologies into distributed cluster memories, using Spark (a memory-based distributed computing framework), which executes the ontology reasoning. In order to implement an appropriate OWL Horst Lite ontology reasoning system on Spark, our method divides the scalable ontologies into blocks, loads each block into the cluster nodes, and subsequently handles the data in the distributed memories. We used the Lehigh University Benchmark, which is used to evaluate ontology inference and search speed, to experimentally evaluate the methods suggested in this paper, which we applied to LUBM8000 (1.1 billion triples, 155 gigabytes). When compared with WebPIE, a representative mapreduce algorithm-based scalable ontology reasoner, the proposed approach showed a throughput improvement of 320% (62k/s) over WebPIE (19k/s).

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.351-360
• /
• 2018

Human emotion recognition is a research topic that is receiving continuous attention in computer vision and artificial intelligence domains. This paper proposes a method for classifying human emotions through multiple neural networks based on multi-modal signals which consist of image, landmark, and audio in a wild environment. The proposed method has the following features. First, the learning performance of the image-based network is greatly improved by employing both multi-task learning and semi-supervised learning using the spatio-temporal characteristic of videos. Second, a model for converting 1-dimensional (1D) landmark information of face into two-dimensional (2D) images, is newly proposed, and a CNN-LSTM network based on the model is proposed for better emotion recognition. Third, based on an observation that audio signals are often very effective for specific emotions, we propose an audio deep learning mechanism robust to the specific emotions. Finally, so-called emotion adaptive fusion is applied to enable synergy of multiple networks. The proposed network improves emotion classification performance by appropriately integrating existing supervised learning and semi-supervised learning networks. In the fifth attempt on the given test set in the EmotiW2017 challenge, the proposed method achieved a classification accuracy of 57.12%.

• Journal of KSNVE
• /
• v.5 no.3
• /
• pp.275-283
• /
• 1995

본 글에서는 지능구조물의 개념설명과 더불어 ERF의 특성, ERF를 함유란 함유 한 지능구조물 시스템의 구성, 동적 모델링과 진동제어 그리고 그 응용성에 관한 연구 현황과 방향에 대해 살펴보았다. 설명한 바와 같이 지능구조물은 새로운 차원의 신생 하는 첨단분야로서, 소음 및 진동에 관련된 무한한 잠재력과 다양한 응용성으로 미루 어 볼때 아주 매력적인 연구 분야이다. 그러나, 여러 응용 시스템의 상품화 단계로의 도약에 있어서 각 시스템 구성 요소 분야별 해결해야할 연구 사항들이 있다. 먼저, 액추에이팅을 수행하는 ERF 자체의 내구성 문제로서 고온에서 ERF의 효과 하락과 장시간 사용시 ERF에 의한 마멸, 고체 입자의 침전에 의한 초기 상태 불안정 등이 있다. 아울러 기존의 장치의 성능을 능가하기 위해 보다 큰 효과를 나타내는 새로운 차원의 ERF개발이 요구된다. 그리고 센서기술 분야에서는 호스트 재료에 보다 쉽게 결합이 되고 여러가지 형태의 요구조건을 만족시킬 수 있으며 외부 환경조건에 강건 하고 다양한 센서 개발이 요구된다. 또한, 보다 일번적인 동적 모델링을 통해 적용 시스템에 적합하고 강건한 제어기에 대한 연구가 진행되어야 한다. 마지막으로 능동 제어기를 실제로 구현하기 위한 호스트 재료 각 요소마다 센서의 설치, 페회로 피드백 시스템 장착, 상호간의 인터페이스 등의 기술 발전이 요구되며, 아울러 보다 효율적 인 시스템의 성능 특성을 실현할 수 있는 호스트 재료와 기계 메카니즘이 필요로 된다. 이상의 설명에서 알 수 있듯이 지능구조물에 대한 연구는 어느 한 분야에서만 아니라 기계, 전기전자, 토목, 물리, 재료과학 등 통합형식에 의한 접근 방향으로 추진되어야 할 것이다.서 세탁기의 진동 소음을 저감시키기 위해 진동 소음원에 대해 논술하고, 진동해석을 위해 컴퓨터 시뮬레이션 결과를 이용한 저진동 기술 개발에 대하여 기술하고자 한다.rotary piston)식 압축기는 약 20여년 전 부터 냉방용 압축기에서부터 널리 쓰이게 되었다. 약 10여년전부터 상용화 된 스크롤(scroll) 형 압축기도 현재 상대적으로 용량이 큰 가정용 냉방기를 중심으로 많이 쓰이고 있다. 스크류형 압축기는 보통 중대형 상업용에 주로 쓰인다. 해결하려 하였고, 수치해석은 피스톤의 운동을 배제한 단순화한 흡배기계의 정상상태 유동해석이 주를 이루어왔다. Taghaui and Dupont 등[5]은 KIVA코드를 사용하여 흡기포트와 연소실 그리고 밸브의 움직임을 동시에 고려한 수치해석을 도입하였다. 하지만 이들이 밸브의 운동을 고려하기 위해 사용한 이동격자는 격자점은 시간에 따라 변화하지만 그 격자의 수가 일정하게 유지되어 있어서 밸브의 완전개폐를 해석할 수가 없다. 강희정[6]은 단일 실린더와 단일 배기밸브를 갖는 문제로 단순화하여 피스톤과 밸브의 움직임을 고려하므로써 배기행정 후 소음이 어떻게 전파해 나가는가를 연구하였다. 본 연구에서도 최소밸브간격과 최대밸브간격 사이에서만 계산이 가능하나 흡기의 경우는 밸브가 닫힐 때 생기는 압력파가 중요하므로 실린더와 밸브사이에 벽면조건을 주어 밸브의 개폐를 모사하였다.술을 보유하고자 한다. 이용한 해마의 부피측정은 해마경화증 환자의 진단에 있어 육안적인 MR 진단이 어려운 제한된 경우에만 실제적 도움을 줄 수 있는 보조적인 방법으로 생각된다.ofile whereas relaxivity at high field is not affected by τS.

• Tribology and Lubricants
• /
• v.12 no.1
• /
• pp.1-5
• /
• 1996

자성유체는 자연에서 추출한 것이 아니라 자화성(Magnetizability)과 유도성(Flowability)을 동시에 갖도록 합성한 특수액체이다. 자성유체는 1960년대 중반에 미국의 NASA에서 처음 개발된 이후로 윤활, 밀봉, 감쇄, 의료 등의 분야에서 응용연구가 많이 진행되었기 때문에 고도의 정밀도를 요하는 항공, 우주산업, 컴퓨터와 반도체 분야 등에서 실용화가 크게 진전되고 있다. 특수물질일 자성유체는 전기적으로 도체인 10nm 정도의 미세한 자기입자(Magnetic particles)에 코팅을 한 후, 이것을 물, 탄화수소, 플루오르카본, 에스터 등의 매개유체(Carrier Fluids)에 혼합시켜서 콜로이드 상태로 사용하게 된다. 자성유체는 미세한 자기입자들이 매개유체내에서 서로 충돌하면서 반발력을 발생시켜서 상호간에 늘 콜로이드 상태를 유지하고 있으며, 이 특수유체가 자기장의 영향을 받게 되면 점도가 증가하면서 특이한 성질을 갖게 된다. 상대 접촉 운동면에 경계마찰이나 혼합마찰을 하게 되면 윤활상태는 비교적 나쁘다. 이러한 마찰지역에 콜로이드상의 자성유체 윤활제를 공급하면 기존의 윤활제에 비하여 대단히 효과적으로 윤활을 할 수 있게 된다. 그러나 자성유체 윤활제가 마찰부위에 원활하게 공급하기 위해서는 미끄럼 마찰부에서 자기장을 잘 형성시킬 수 있는 도체이어야 하기 때문에 특별한 윤활 시스템 설계가 제시되어야 한다. 자성유체 윤활제는 합성으로 제조된 특수물질로 여러가지 장점을 갖고는 있으나 기존 윤활유와의 적합성, 마찰열, 밀봉압력 등의 조건에서 제한적으로 사용될 수 밖에 없으므로 항공, 우주 산업이나 석유 화학분야와 같이 특수 환경에서만 사용되고, 또한 기존의 광유계 윤활제에 비하여 대단히 고가하는 문제점을 갖고 있다. 그러나 윤활 마찰면의 다양화와 가혹한 사용조건은 자성유체 윤활제의 연구개발 필요성을 크게 증대시키고 있다.xed Effects Model)을 결정하고, 각각에 해당하는 통계모형을 구축하였다. 이 결과 (1) 업종 및 기업규모별로 그룹간에 유의한 특성이 발견되었으며, (2) R&D 및 광고투자는 기업의 시장성과를 설명하는 중요한 변수이나, (3) R&D 투자의 경우는 광고에 비해 불확실성이 존재하는 것으로 나타났고, (4) 수리모형에서 도출된 한계원리가 통계모형에서도 유효한 것으로 드러났다.등을 토대로 한 10대 산업을 육성하기 위하여 과학기술부는 기술수요조사를 바탕으로 49개 주요기술을 도출하여, 과학기술 일류 국가 실현, 국민소득 2만불 달성이라는 국가적 슬로건을 내걸고 “차세대 성장동력” 창출을 위한 범정부차원의 기획과 연구비의 집중투자를 추진하고 있다.달성하기 위해서는 종합류류 전산망의 시급한 구축과 함께 화물차의 적재율을 높이고 공차율을 낮출 수 있는 운송체계의 수립이 필요한 것으로 판단된다. 그라나 이러한 화물전용차선의 효과는 단기적인 치유책일 수밖에 없기 때문에 물류유통 시설의 확충을 위한 사회간접자본의 구축을 서둘러 시행하여야 할 것이다.으로 처리한 Machine oil, Phenthoate EC 및 Trichlorfon WP는 비교적 약효가 낮았다.>$^{\circ}$E/$\leq$30$^{\circ}$NW 단열군이 연구지역 내에서 지하수 유동성이 가장 높은 단열군으로 추정된다. 이러한 사실은 3개 시추공을 대상으로 실시한 시추공 내 물리검층과 정압주입시험에서도 확인된다.. It was resulted from increase of weight of single cocoon. "Manta"2.5ppm produced 22.2kg of cocoon. It is equal to 9% increase in index, as compared to that of control. In case

• Journal of Broadcast Engineering
• /
• v.14 no.4
• /
• pp.438-449
• /
• 2009

To analyze reception environments of ATSC Digital TV, CIR (Channel Impulse Response) analysis systems are widely applied. The receiving performances of conventional CIR analysis systems are not as good as those of commercial state-of-the-art receivers. There are difficulties in measuring and analyzing reception problems caused by multi-path interferences. To solve these problems, commercial DTV chip sets embedded CIR analysis system is proposed. Generally, commercial chip sets provide baseband (In-phase) channel data and field or segment sync data. For more precise analysis of measured I channel data, it is necessary to extract Q (quadrature) channel data components as well. This paper presents the technical requirements of CIR analysis system for DTV. In order to satisfy such requirements and measure more accurate magnitude and phase of CIR, a method to derive the quadrature data from the measured in-phase channel data is proposed. The proposed channel analysis system is implemented with a commercial DTV chip set and expedites the data analysis for use on DTV field test vehicles. Computer simulation and laboratory test results are provided to demonstrate the performance of the proposed channel analysis system.