• Journal of Internet Computing and Services
• /
• v.20 no.6
• /
• pp.11-20
• /
• 2019

Numerous enterprises, organizations and individual users are exposed to large DDoS (Distributed Denial of Service) attacks. DDoS attacks are performed through a BotNet, which is composed of a number of computers infected with a malware, e.g., zombie PCs and a special computer that controls the zombie PCs within a hierarchical chain of a command system. In order to detect a malware, a malware detection software or a vaccine program must identify the malware signature through an in-depth analysis, and these signatures need to be updated in priori. This is time consuming and costly. In this paper, we propose a botnet detection scheme that does not require a periodic signature update using an artificial neural network model. The proposed scheme exploits Word2Vec and accelerated hierarchical density-based clustering. Botnet detection performance of the proposed method was evaluated using the CTU-13 dataset. The experimental result shows that the detection rate is 99.9%, which outperforms the conventional method.

• The korean journal of orthodontics
• /
• v.52 no.1
• /
• pp.3-19
• /
• 2022

Objective: The purpose of this study was to investigate the accuracy of one-step automated orthodontic diagnosis of skeletodental discrepancies using a convolutional neural network (CNN) and lateral cephalogram images with different qualities from nationwide multi-hospitals. Methods: Among 2,174 lateral cephalograms, 1,993 cephalograms from two hospitals were used for training and internal test sets and 181 cephalograms from eight other hospitals were used for an external test set. They were divided into three classification groups according to anteroposterior skeletal discrepancies (Class I, II, and III), vertical skeletal discrepancies (normodivergent, hypodivergent, and hyperdivergent patterns), and vertical dental discrepancies (normal overbite, deep bite, and open bite) as a gold standard. Pre-trained DenseNet-169 was used as a CNN classifier model. Diagnostic performance was evaluated by receiver operating characteristic (ROC) analysis, t-stochastic neighbor embedding (t-SNE), and gradient-weighted class activation mapping (Grad-CAM). Results: In the ROC analysis, the mean area under the curve and the mean accuracy of all classifications were high with both internal and external test sets (all, > 0.89 and > 0.80). In the t-SNE analysis, our model succeeded in creating good separation between three classification groups. Grad-CAM figures showed differences in the location and size of the focus areas between three classification groups in each diagnosis. Conclusions: Since the accuracy of our model was validated with both internal and external test sets, it shows the possible usefulness of a one-step automated orthodontic diagnosis tool using a CNN model. However, it still needs technical improvement in terms of classifying vertical dental discrepancies.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.115-118
• /
• 2000

Voice conversion technology is essential for TTS systems because the construction of speech database takes much effort. In this paper. male-to-female voice conversion technology in Korean LPC TTS system has been studied. In general. the parameters for voice color conversion are categorized into acoustic and prosodic parameters. This paper adopts LSF(Line Spectral Frequency) for acoustic parameter, pitch period and duration for prosodic parameters. In this paper. Pitch period is shortened by the half, duration is shortened by $25\%, and LSFs are shifted linearly for the voice conversion. And the synthesized speech is post-filtered by a bandpass filter. The proposed algorithm is simpler than other algorithms. for example, VQ and Neural Net based methods. And we don't even need to estimate formant information. The MOS(Mean Opinion Socre) test for naturalness shows 2.25 and for female closeness, 3.2. In conclusion, by using the proposed algorithm. male-to-female voice conversion system can be simply implemented with relatively successful results.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.44-45
• /
• 2019

최근 CNN 등 인공신경망은 최근 이미지 분류, 객체 인식, 자연어 처리 등 다양한 분야에서 뛰어난 성능을 보이고 있다. 그러나, 대부분의 분야에서 보다 더 높은 성능을 얻기 위해 사용한 인공신경망 모델들은 파라미터 수 및 연산량 등이 방대하여, 모바일 및 IoT 디바이스 같은 연산량이나 메모리가 제한된 환경에서 추론하기에는 제한적이다. 따라서 연산량 및 모델 파라미터 수를 압축하기 위한 딥러닝 경량화 알고리즘이 연구되고 있다. 본 논문에서는 임베디트 보드에서의 압축된 CNN 모델의 성능을 검증한다. 인공지능 지원 맞춤형 칩인 QCS605 를 내장한 임베디드 보드에서 카메라로 입력한 영상에 대해서 원 CNN 모델과 압축된 CNN 모델의 분류 성능과 동작속도 비교 분석한다. 본 논문의 실험에서는 CNN 모델로 MobileNetV2, VGG16 을 사용했으며, 주어진 모델에서 가지치기(pruning) 기법, 양자화, 행렬 분해 등의 인공신경망 압축 기술을 적용하였을 때 원래의 모델 대비 추론 시간 및 분류의 정확도 성능을 분석하고 인공신경망 압축 기술의 유용성을 확인하였다.

• Annual Conference on Human and Language Technology
• /
• 1989.10a
• /
• pp.101-106
• /
• 1989

음성 및 문자를 통한 컴퓨터와의 정보 교환을 위한 통합 사용자 인터페이스 (Intelligent Man- Machine interface) 시스템의 일환으로 한국어 단모음의 인식을 위한 시스템을 인공 신경망 모델을 사용하여 구현하였으며 인식시스템의 상위 접속부에 필요한 단어 인식 모듈에 있어서의 인지 실험도 행하였다. 모음인식의 입력으로는 제1, 제2, 제3 포르만트가 사용되었으며 실험대상은 한국어의 [아, 어, 오, 우, 으, 이, 애, 에]의 8 개의 단모음으로 하였다. 사용한 인공 신경망 모델은 Multilayer Perceptron 이며, 학습 규칙은 Generalized Delta Rule 이다. 1 인의 남성 화자에 대하여 약 94%의 인식율을 나타내었다. 그리고 음성 인식시의 인지 현상 실험을 위하여 약 20개의 단어를 인공신경망의 어휘레벨에 저장하여 음성의 왜곡, 인지시의 lexical 영향, categorical percetion등을 실험하였다. 이때의 인공 신경망 모델은 Interactive Activation and Competition Model을 사용하였으며, 음성 입력으로는 가상의 음성 피쳐 데이타를 사용하였다.

• Journal of the Korea Computer Industry Society
• /
• v.8 no.4
• /
• pp.281-288
• /
• 2007

In this paper, we set 6 interesting points around lips. Analyzed and characterized is the distance change of these 6 interesting points when people pronounces 5 vowels of Korean language. 450 data are gathered and analyzed. Based on this analysis, the system is constructed and the recognition experiments are performed. In this system, we used the camera connected to computer to measure the distance vector between 6 interesting points. In the experiment, 80 normal persons were sampled. The observational error between samples was corrected using normalization method. We analyzed with 30 persons and experimented with 50 persons. We constructed three recognition systems and of those the neural net system gave the best recognition result of 87.44 %.

• Journal of Multimedia Information System
• /
• v.6 no.4
• /
• pp.225-234
• /
• 2019

Deep learning has become increasingly popular in both academic and industrial areas nowadays. Various domains including pattern recognition, Computer vision have witnessed the great power of deep neural networks. However, current studies on deep learning mainly focus on quality data sets with balanced class labels, while training on bad and imbalanced data set have been providing great challenges for classification tasks. We propose in this paper a method of data analysis-based data reduction techniques for selecting good and diversity data samples from a large dataset for a deep learning model. Furthermore, data sampling techniques could be applied to decrease the large size of raw data by retrieving its useful knowledge as representatives. Therefore, instead of dealing with large size of raw data, we can use some data reduction techniques to sample data without losing important information. We group PCB characters in classes and train deep learning on the ResNet56 v2 and SENet model in order to improve the classification performance of optical character recognition (OCR) character classifier.

• Nuclear Engineering and Technology
• /
• v.52 no.6
• /
• pp.1188-1200
• /
• 2020

In this paper, we consider a SDMS (Self-Diagnostic Monitoring System) for a reciprocating pump for the purpose of not only diagnosis but also prognosis. We have replaced a multi class estimator that selects only the most probable one with a multi label estimator such that we are able to see the state of each of the components. We have introduced a measure called certainty so that we are able to represent the symptom and its state. We have built a flow loop for a reciprocating pump system and presented some results. With these changes, we are not only able to detect both the dominant symptom as well as others but also to monitor how the degree of severity of each component changes. About the dominant ones, we found that the overall recognition rate of our algorithm is about 99.7% which is slightly better than that of the former SDMS. Also, we are able to see the trend and to make a base to find prognostics to estimate the remaining useful life. With this we hope that we have gone one step closer to the final goal of prognosis of SDMS.

• Proceedings of the Korean Society for Cognitive Science Conference
• /
• 2000.05a
• /
• pp.311-321
• /
• 2000

본 논문에서는 정신분석과 두 종류의 정서이론, 인공지능과 신경회로망 그리고 퍼지 페트리 네트 등을 사용하여 사람의 인지과정을 모방한 인지모형시스템을 개발하였다. 먼저 프로이트의 정신분석을 사용하여 정신의 구조를 그래프로 표현한 후 이것을 '마음의 지도'라 명명하였다. 인지모형시스템을 구현하기 위한 첫 번째 작업으로 동적인 추론을 할 수 있는 지능 모델인 KNBN(Kohonen Network based Belief Network)을 제안하였다. KNBN으로 표현한 마음의 약도 내에서 연결강도 값으로 사용할 상대적 데이터를 만들기 위한 근거로서는 '정서'를 사용하였는데, 플라칙의 진화론에 근거한 정서이론과 오토니의 인지적 정서이론을 결합하여 데이터로 만든후 이 수치를 연결강도로 사용하였다. 이 두 개의 정서이론을 결합하는 알고리즘을 만들기 위해 페트리네트를 변형한 퍼지 페트리네트를 제안하였다. 또한 오토니가 주장하는 정서의 인지구조를 사람들이 그대로 이해하는지 여부를 알기 위해 대학생 100명을 대상으로 설문지를 사용해 정서의 인지구조에 대해 조사하였고 그 결과 값에 근거하여 두 개의 정서이론 결합 알고리즘을 만들었다. 이것으로 정서 발화에 대한 상대적인 수치가 산출되었고, 이것을 KNBN으로 표현한 마음의 약도에 결합하기 위해 0과 1사이의 수치로 정규화 하였다. 이렇게 정규화된 데이터를 이용해 인지 모형 시스템을 개발하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.5
• /
• pp.403-412
• /
• 1991

This paper proposes a type of self organizing neural network which recognizes arbitrary symbols as well as numerical or alphabetic characters. The proposed algorithm autonomically organizes and classifies similar patterns on the basis of the distribution types of characteristics in the input images. Thus it can be appliced for the recognition of arbitrary images when it is difficult to establish a learning rule. It performs a stale recognition process with in the limit of the memory capacity. The cheme was applied and tested to 50 different image patterns with increased noise level up to 44%(SNR 2dB). The implementation results demonstrate that the proposed algorithm successfully recognizes the image patterns changed due to the various noise levels and thus proves excellent antinoise characteristics.