• Annual Conference of KIPS
• /
• 2019.10a
• /
• pp.589-591
• /
• 2019

본 논문에서는 고도장비의 운용 및 정비를 위한 교육훈련 시스템 개발을 위해 자연어 처리와 딥러닝 기술을 이용하여 항공정비와 관련된 전문분야의 문서 분류가 가능한 방법을 제안하고자 한다. 문서 분류 모델의 개발을 위해 항공정비 교범을 텍스트 파일로 변환하여 총 4917개의 문서를 생성하였으며, 정비사 개인별 정비능력 관리(IMQC)를 기준으로 12개의 범주로 구분하였다. 수집된 문서는 전문분야의 문서인 점을 고려하여 전문용어 사전을 추가하였으며, KoNLPy를 이용하여 전처리를 수행하였다. 전문분야의 문서는 범주에 상관없이 문서 내용의 유사도가 매우 높은 특징을 가지고 있어, 특정 범주내에서 중요한 정도를 잘 표현 할 수 있는 TF-ICF를 이용하여 특징 추출을 하였다. 이후 합성곱 신경망(CNN)을 이용하여 특징 맵을 생성한 후 완전 결합 계층을 통하여 분류하였으며, 테스트 문서 983건을 분류한 결과 평균 73.6%의 분류성능을 보여주었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1671-1686
• /
• 2022

Face manipulation tools represented by Deepfake have threatened the security of people's biological identity information. Particularly, manipulation tools with deep learning technology have brought great challenges to Deepfake detection. There are many solutions for Deepfake detection based on traditional machine learning and advanced deep learning. However, those solutions of detectors almost have problems of poor performance when evaluated on different quality datasets. In this paper, for the sake of making high-quality Deepfake datasets, we provide a preprocessing method based on the image pixel matrix feature to eliminate similar images and the residual channel attention network (RCAN) to resize the scale of images. Significantly, we also describe a Deepfake detector named Cascaded-Hop which is based on the PixelHop++ system and the successive subspace learning (SSL) model. By feeding the preprocessed datasets, Cascaded-Hop achieves a good classification result on different manipulation types and multiple quality datasets. According to the experiment on FaceForensics++ and Celeb-DF, the AUC (area under curve) results of our proposed methods are comparable to the state-of-the-art models.

• Journal of Intelligence and Information Systems
• /
• v.10 no.2
• /
• pp.65-77
• /
• 2004

This paper presents a priori and the local font classification method. The font classification uses ascenders, descenders, and serifs extracted from a word image. The gradient features of those sub-images are extracted, and used as an input to a neural network classifier to produce font classification results. The font classification determines 2 font styles (upright or slant), 3 font groups (serif sans-serif or typewriter), and 7-font names (Postscript fonts such as Avant Garde, Helvetica, Bookman, New Century Schoolbook, Palatine, Times, and Courier). The proposed a priori and local font classification method allows an OCR system consisting of various font-specific character segmentation tools and various mono-font character recognizers. Experiments have shown font classification accuracies reach high performance levels of about 95.4 percent even with severely touching characters. The technique developed for tile selected 7 fonts in this paper can be applied to any other fonts.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.6
• /
• pp.531-536
• /
• 2002

In this paper, we have applied Genetic Algorithms(GAs) to Intrusion Detection System(TDS), and then proposed and simulated the misuse detection model firstly. We have implemented with the KBD contest data, and tried to simulated in the same environment. In the experiment, the set of record is regarded as a chromosome, and GAs are used to produce the intrusion patterns. That is, the intrusion rules are generated. We have concentrated on the simulation and analysis of classification among the Data Mining techniques and then the intrusion patterns are produced. The generated rules are represented by intrusion data and classified between abnormal and normal users. The different rules are generated separately from three models "Time Based Traffic Model", "Host Based Traffic Model", and "Content Model". The proposed system has generated the update and adaptive rules automatically and continuously on the misuse detection method which is difficult to update the rule generation. The generated rules are experimented on 430M test data and almost 94.3% of detection rate is shown.3% of detection rate is shown.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.2
• /
• pp.230-235
• /
• 2008

Recently, LG chemical corporation developed new material called HYPERIER, which has an excellent barrier characteristic. It has many layers which are made of nano-composite within LDPE(Low-Density Poly Ethylene). In order to guarantee the quality of the final product from the production line, a certain test equipment is required to investigate the existence of layers inside the HYPERIER. In this work, ultrasonic sensor based test equipment for investigating the existence of inner layers is proposed. However, it is a tedious job for human operators to check the existence by just looking at the resounding waveform from ultrasonic sensor. Therefore, to enhance the performance of the ultrasonic test equipment, Fast Fourier Transform(FFT) and Principle Components Analysis(PCA) and Back-Propagation Neural Network(BPNN) are utilized which is used for classification of Quality. To verily the feasibility of the proposed scheme, some experiments are executed.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.4
• /
• pp.354-359
• /
• 2013

In this paper, we suggested the method for implementation of unsupervised nonlinear classification using Binary Harmony Search (BHS) algorithm, which is known as a optimization algorithm. Various algorithms have been suggested for classification of feature vectors from the process of machine learning for pattern recognition or EEG signal analysis processing. Supervised learning based support vector machine or fuzzy c-mean (FCM) based on unsupervised learning have been used for classification in the field. However, conventional methods were hard to apply nonlinear dataset classification or required prior information for supervised learning. We solved this problems with proposed classification method using heuristic approach which took the minimal Euclidean distance between vectors, then we assumed them as same class and the others were another class. For the comparison, we used FCM, self-organizing map (SOM) based on artificial neural network (ANN). KEEL machine learning datset was used for simulation. We concluded that proposed method was superior than other algorithms.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.6 no.2
• /
• pp.95-106
• /
• 2007

This paper proposes an effective tempo feature extraction method for music information retrieval. The tempo information is modeled by the narrow-band temporal modulation components, which are decomposed into a modulation spectrum via joint frequency analysis. In implementation, the tempo feature is directly extracted from the modified discrete cosine transform coefficients, which is the output of partial MP3(MPEG 1 Layer 3) decoder. Then, different features are extracted from the amplitudes of modulation spectrum and applied to different music information retrieval tasks. The logarithmic scale modulation frequency coefficients are employed in automatic music emotion classification and music genre classification. The classification precision in both systems is improved significantly. The bit vectors derived from adaptive modulation spectrum is used in audio fingerprinting task That is proved to be able to achieve high robustness in this application. The experimental results in these tasks validate the effectiveness of the proposed tempo feature.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.1
• /
• pp.29-34
• /
• 2015

Brain-computer interface (BCI) is being studied for convenient life in various application fields. The purpose of this study is to investigate a changing electroencephalography (EEG) for precise motion of a robot or an artificial arm. Three subjects who participated in this experiment performed three-task: Grip, Move, Relax. Acquired EEG data was extracted feature data using two feature extraction algorithm (power spectrum analysis and multi-common spatial pattern). Support vector machine (SVM) were applied the extracted feature data for classification. The classification accuracy was the highest at Grip class of two subjects. The results of this research are expected to be useful for patients required prosthetic limb using EEG.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.3
• /
• pp.306-311
• /
• 2015

This study aims at analyzing the convergence of Internet-of-Things and wearables technologies using cooperative patent classification(CPC). CPC, introduced to an increasing number of technological fields of Korean patents, is expected to be widely used in Patent Informatics because the classification codes in CPC are more specific than those of IPC, which reflect the characteristics of technologies in detail with accuracy. CPC has seldom been used up to date and most of the previous researches on technological convergence used IPC. As a pre-analysis step for analyzing the trend of technological convergence of IoT and wearables, CPC and IPC codes assigned to each patent were compared. By applying association rule mining to the analysis of CPC codes, we identified the technological fields where convergence frequently takes place and examined the trend of technological convergence over time.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.2
• /
• pp.23-29
• /
• 2014

The advanced traffic management system of intelligent transport systems automates the related traffic tasks such as vehicle speed, traffic volume and traffic incidents through the improved infrastructures like high definition cameras, high-performance radar sensors. For the safety of road users, especially, the automated incident detection and secondary accident prevention system is required. Normally, CCTV based image object detection and radar based object detection is used in this system. In this paper, we proposed the algorithm for real time highway incident detection system using multi surveillance cameras to mosaic video and track accurately the moving object that taken from different angles by background modeling. We confirmed through experiments that the video detection can supplement the short-range shaded area and the long-range detection limit of radar. In addition, the video detection has better classification features in daytime detection excluding the bad weather condition.