• 한국융합학회논문지
• /
• 제13권1호
• /
• pp.23-30
• /
• 2022

냉동 컨테이너의 고장은 큰 비용의 손실을 야기하지만, 현재 냉동 컨테이너의 알람 체계는 효율성이 떨어진다. 기존에 냉동 시스템의 시뮬레이션 데이터를 활용한 연구는 존재하지만, 냉동 컨테이너의 실제 운영 데이터를 활용한 연구는 부족하다. 이에 본 연구는 실제 냉동 컨테이너 운영 데이터를 활용하여 고장 원인을 분류하였다. 실제 데이터에서는 데이터 불균형이 발생하였으며 ENN-SMOTE, 클래스 가중치를 둔 Logistic 회귀분석과 본 연구에서 개발한 2-stage 알고리즘을 비교하여 데이터 불균형문제를 해결하였다. 2-stage 알고리즘은 XGboost, LGBoost, DNN을 사용하여 첫 번째 단계에서는 고장 및 정상을 분류하고, 두 번째 단계에서는 고장의 원인을 분류하는 알고리즘이다. 2-stage 알고리즘에서 LGBoost를 사용한 모델이 99.16%의 정확도로 가장 우수하였다. 본 연구는 데이터 불균형을 해결하기 위해 2-stage 알고리즘을 활용한 최종모델을 제안하며 이는 다른 산업에도 활용할 수 있을 것으로 사료된다.

• 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.

• 한국멀티미디어학회논문지
• /
• 제21권2호
• /
• pp.98-107
• /
• 2018

In this paper, we propose a method to classify the skeletal maturity with a small amount of hand wrist X-ray image using deep learning-based meta-learning. General deep-learning techniques require large amounts of data, but in many cases, these data sets are not available for practical application. Lack of learning data is usually solved through transfer learning using pre-trained models with large data sets. However, transfer learning performance may be degraded due to over fitting for unknown new task with small data, which results in poor generalization capability. In addition, medical images require high cost resources such as a professional manpower and mcuh time to obtain labeled data. Therefore, in this paper, we use meta-learning that can classify using only a small amount of new data by pre-trained models trained with various learning tasks. First, we train the meta-model by using a separate data set composed of various learning tasks. The network learns to classify the bone maturity using the bone maturity data composed of the radiographs of the wrist. Then, we compare the results of the classification using the conventional learning algorithm with the results of the meta learning by the same number of learning data sets.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2004년도 추계학술대회 논문집 Vol.17
• /
• pp.653-657
• /
• 2004

In this study, PD(partial discharge) signals which occurrs at stator coil of traction Motor are acquired. these data are used for classifying the PD sources. W(Neural Network) has recently applied to classify the PB pattern. The PD data are used for the learning process to classify PD sources. The PD data come from normal specimen and defective specimens such as internal void discharges, slot discharges and surface discharges. PD distribution parameters are calculated from a set of the data, which is used to realize diagnostic algorithm. NN which applies distribution parameters is useful to classify the PD patterns of defective sources generating in stator coil of traction motor.

• 한국컴퓨터정보학회논문지
• /
• 제11권2호
• /
• pp.15-23
• /
• 2006

인터넷에는 많은 문서가 있고 지금도 새로운 문서가 만들어지고 있다. 따라서 인터넷에 존재하는 문서를 의미 있게 분류하는 것은 향후 문서의 관리 및 질의처리에서 중요한 문제이다. 하지만 지금까지 대부분은 키워드에 기초한 문서 분류방법을 사용하고 있다. 이 방법은 문서를 효율적으로 분류하지 못했다. 또한 의미를 포함한 문서의 분류를 하지 못한다. 사람이 문서를 꼼꼼하게 읽어서 문서를 분류하는 방법이 최선이지만, 시간적인 면이나 효율성에 문제가 있다. 따라서 본 논문에서는 신경망 알고리즘과 C4.5 알고리즘을 이용하여 문서를 분류하고자 한다. 실험 데이터로 XML로 만들어진 이력서 데이터를 사용하여 실험하였다. 실험결과 문서 분류에 가능성을 보였다. 또한, 다양한 문서 분류 응용에 적용하여 좋은 결과를 얻을 것으로 기대한다.

• 한국통신학회논문지
• /
• 제25권3A호
• /
• pp.399-405
• /
• 2000

본 논문에서는 블록암호시스템의 대표적인 방법인 IDEA(International Date Encryption Algorithm)알고리즘을 다룬다. IDEA 알고리즘에서의 키생성 알고리즘을 분석함으로서, 라운드별 사용되는 키 비트열과 사용되지 않는 키 비트열을 분류한다. 이를 이용하여 MA(Multiplication/Addition) 구조를 생략한 형태의 IDEA 알고리즘에 대한 MSB (Most Significant Bit) 차분에 의한 차분 분석법(differential analysis)과 입력계열과 각 라운드별 사용 키계 열의 LSB(Least Significant Bit) 비트만을 사용하는 선형 분석법(linear analysis)을 제안한다.

• 제어로봇시스템학회논문지
• /
• 제19권3호
• /
• pp.256-261
• /
• 2013

In the steel manufacturing area, researches for defect inspection receive a big attention for quality control. This paper proposes an algorithm to detect a scratch defect on steel billets. This algorithm takes ROIs (Regions of Interest), and extracts 11 features which represent properties of defect on a ROI. SVM (Support Vector Machine) is used to classify defect and normal ROIs. The algorithm classifies a frame image of a Billet as a defect image if there is one or more defect ROIs. In the experiments, the proposed algorithm had reliable classifying accuracy.

• 한국멀티미디어학회논문지
• /
• 제19권2호
• /
• pp.209-214
• /
• 2016

The purpose of this study was to classify healty persons and Parkinson disease patients from the vocal characteristics of healty persons and the of Parkinson disease patients using Machine Learning algorithms. So, we compared the most widely used algorithms for Machine Learning such as J48 algorithm and REPTree algorithm. In order to evaluate the classification performance of the two algorithms, the results were compared with depending on vocal characteristics. The classification performance of depending on vocal characteristics show 88.72% and 84.62%. The test results showed that the J48 algorithms was superior to REPTree algorithms.

• IEIE Transactions on Smart Processing and Computing
• /
• 제2권5호
• /
• pp.317-321
• /
• 2013

This paper proposes a detection algorithm for view reversal in a stereoscopic video using a disparity map and motion vector field. We obtain the disparity map of a stereo image was obtained using a specific stereo matching algorithm and classify the image into the foreground and background. Next, the motion vector field of the image on a block basis was produced using a full search algorithm. Finally, the stereo image was considered to be reversed when the foreground moved toward the background and the covered region was in the foreground. The proposed algorithm achieved a good detection rate when the background was covered sufficiently by its moving foreground.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제3권1호
• /
• pp.43-53
• /
• 1999

A real $m{\times}n$ matrix A is called an L-matrix if every matrix in its qualitative class has linearly independent rows. Since the number of the sign pattern matrices of the given size is finite, we can list all patterns lexicographically. In [2], a necessary and sufficient condition for a matrix to be an L-matrix was given. We presented an algorithm which decides whether the given matrix is an L-matrix or not. In this paper, we develope an algorithm and C-program which will determine whether a given matrix is an L-matrix or not, or an SNS-matrix or not. In addition, we have extended our algorithm to be able to classify sign-pattern matrices, and to find barely L-matrices from a given matrix and to list all $m{\times}n$ L-matrices.