• Title/Summary/Keyword: 신경망 모델링

Search Result 333, Processing Time 0.026 seconds

Comparisons of Experimental Designs and Modeling Approaches for Constructing War-game Meta-models (워게임 메타모델 수립을 위한 실험계획 및 모델링 방법에 관한 비교 연구)

  • Yoo, Kwon-Tae;Yum, Bong-Jin
    • Journal of the military operations research society of Korea
    • /
    • v.33 no.1
    • /
    • pp.59-74
    • /
    • 2007
  • Computer simulation models are in general quite complex and time-consuming to run, and therefore, a simpler meta-model is usually constructed for further analysis. In this paper, JANUS, a war-game simulator, is used to describe a certain tank combat situation. Then, second-order response surface and artificial neural network meta-models are developed using the data from eight different experimental designs. Relative performances of the developed meta-models are compared in terms of the mean squared error of prediction. Computational results indicate that, for the given problem, the second-order response surface meta-model generally performs better than the neural network, and the orthogonal array-based Latin hypercube design(LHD) or LHD using maximin distance criterion may be recommended.

Improved Performance of Image Semantic Segmentation using NASNet (NASNet을 이용한 이미지 시맨틱 분할 성능 개선)

  • Kim, Hyoung Seok;Yoo, Kee-Youn;Kim, Lae Hyun
    • Korean Chemical Engineering Research
    • /
    • v.57 no.2
    • /
    • pp.274-282
    • /
    • 2019
  • In recent years, big data analysis has been expanded to include automatic control through reinforcement learning as well as prediction through modeling. Research on the utilization of image data is actively carried out in various industrial fields such as chemical, manufacturing, agriculture, and bio-industry. In this paper, we applied NASNet, which is an AutoML reinforced learning algorithm, to DeepU-Net neural network that modified U-Net to improve image semantic segmentation performance. We used BRATS2015 MRI data for performance verification. Simulation results show that DeepU-Net has more performance than the U-Net neural network. In order to improve the image segmentation performance, remove dropouts that are typically applied to neural networks, when the number of kernels and filters obtained through reinforcement learning in DeepU-Net was selected as a hyperparameter of neural network. The results show that the training accuracy is 0.5% and the verification accuracy is 0.3% better than DeepU-Net. The results of this study can be applied to various fields such as MRI brain imaging diagnosis, thermal imaging camera abnormality diagnosis, Nondestructive inspection diagnosis, chemical leakage monitoring, and monitoring forest fire through CCTV.

EPS Gesture Signal Recognition using Deep Learning Model (심층 학습 모델을 이용한 EPS 동작 신호의 인식)

  • Lee, Yu ra;Kim, Soo Hyung;Kim, Young Chul;Na, In Seop
    • Smart Media Journal
    • /
    • v.5 no.3
    • /
    • pp.35-41
    • /
    • 2016
  • In this paper, we propose hand-gesture signal recognition based on EPS(Electronic Potential Sensor) using Deep learning model. Extracted signals which from Electronic field based sensor, EPS have much of the noise, so it must remove in pre-processing. After the noise are removed with filter using frequency feature, the signals are reconstructed with dimensional transformation to overcome limit which have just one-dimension feature with voltage value for using convolution operation. Then, the reconstructed signal data is finally classified and recognized using multiple learning layers model based on deep learning. Since the statistical model based on probability is sensitive to initial parameters, the result can change after training in modeling phase. Deep learning model can overcome this problem because of several layers in training phase. In experiment, we used two different deep learning structures, Convolutional neural networks and Recurrent Neural Network and compared with statistical model algorithm with four kinds of gestures. The recognition result of method using convolutional neural network is better than other algorithms in EPS gesture signal recognition.

A Study on Emotion Recognition of Chunk-Based Time Series Speech (청크 기반 시계열 음성의 감정 인식 연구)

  • Hyun-Sam Shin;Jun-Ki Hong;Sung-Chan Hong
    • Journal of Internet Computing and Services
    • /
    • v.24 no.2
    • /
    • pp.11-18
    • /
    • 2023
  • Recently, in the field of Speech Emotion Recognition (SER), many studies have been conducted to improve accuracy using voice features and modeling. In addition to modeling studies to improve the accuracy of existing voice emotion recognition, various studies using voice features are being conducted. This paper, voice files are separated by time interval in a time series method, focusing on the fact that voice emotions are related to time flow. After voice file separation, we propose a model for classifying emotions of speech data by extracting speech features Mel, Chroma, zero-crossing rate (ZCR), root mean square (RMS), and mel-frequency cepstrum coefficients (MFCC) and applying them to a recurrent neural network model used for sequential data processing. As proposed method, voice features were extracted from all files using 'librosa' library and applied to neural network models. The experimental method compared and analyzed the performance of models of recurrent neural network (RNN), long short-term memory (LSTM) and gated recurrent unit (GRU) using the Interactive emotional dyadic motion capture Interactive Emotional Dyadic Motion Capture (IEMOCAP) english dataset.

Using Artificial Neural Network for Software Development Efforts Estimation on (인공신경망을 이용한 소프트웨어 개발공수 예측모델에 관한 연구)

  • Jeon, Eung-Seop
    • The Transactions of the Korea Information Processing Society
    • /
    • v.3 no.1
    • /
    • pp.211-224
    • /
    • 1996
  • In the research area of estimation of the software development efforts, a number of researches have been accomplished in order to control the costs and to make software more competitive. However, most of them were restricted to the functional algorithm models or the statistic models. Moreover, since they are dealing with the cases of foreign countries, the results are hard to apply directly to the domestic environment for the efficient project management because of lack of accuracy, fitness, flexibility and portability. Therefore, it is appropriate to suggest and propose a new approach supported by artificial neural network which is composed of back propagation and feel-forward algorithms to improve the exactness of the efforts estimation and to advance practical uses. In this study, the artificial neural network approach is used to model the software cost estimation and the results are compared with the revised COCOMO and the multiregression model in order to validate the superiority of the model.

  • PDF

An Effective Two-Step Model for Speech Act Analysis in a Schedule Management Domain (일정 관리 영역에서의 화행 분석을 위한 효과적인 2단계 모델)

  • Lee, Hyun-Jung;Kim, Hark-Soo;Seo, Jung-Yun
    • Korean Journal of Cognitive Science
    • /
    • v.19 no.3
    • /
    • pp.297-310
    • /
    • 2008
  • Since speech acts implies speakers' intentions, it is essential to determine speakers' speech acts if we want to implement an intelligent dialogue system. We propose a two-step model for effectively determining speakers' speech acts. In the first step, the proposed model returns speech act candidates by using a neural network model based on machine learning and a predictivity model based on statistics, respectively. In the second step, using speech act candidates which are returned by the predictivity model, the proposed model filters out speech act candidates which are returned by the neural network model. Then, the proposed model selects a speech act with maximum output value among the unremoved speech act candidates. In the experiment on a schedule management domain, the proposed two-step modeling method showed better precisions than the previous methods only using a machine learning model or a probability model.

  • PDF

An Empiricl Study on the Learnign of HMM-Net Classifiers Using ML/MMSE Method (ML/MMSE를 이용한 HMM-Net 분류기의 학습에 대한 실험적 고찰)

  • Kim, Sang-Woon;Shin, Seong-Hyo
    • Journal of the Korean Institute of Telematics and Electronics C
    • /
    • v.36C no.6
    • /
    • pp.44-51
    • /
    • 1999
  • The HMM-Net is a neural network architecture that implements the computation of output probabilities of a hidden Markov model (HMM). The architecture is developed for the purpose of combining the discriminant power of neural networks with the time-domain modeling capability of HMMs. Criteria of maximum likehood(ML) and minimization of mean squared error(MMSE) are used for learning HMM-Net classifiers. The criterion MMSE is better than ML when initial learning condition is well established. However Ml is more useful one when the condition is incomplete[3]. Therefore we propose an efficient learning method of HMM-Net classifiers using a hybrid criterion(ML/MMSE). In the method, we begin a learning with ML in order to get a stable start-point. After then, we continue the learning with MMSE to search an optimal or near-optimal solution. Experimental results for the isolated numeric digits from /0/ to /9/, a training and testing time-series pattern set, show that the performance of the proposed method is better than the others in the respects of learning and recognition rates.

  • PDF

Blurring of Swear Words in Negative Comments through Convolutional Neural Network (컨볼루션 신경망 모델에 의한 악성 댓글 모자이크처리 방안)

  • Kim, Yumin;Kang, Hyobin;Han, Suhyun;Jeong, Hieyong
    • Journal of Korea Society of Industrial Information Systems
    • /
    • v.27 no.2
    • /
    • pp.25-34
    • /
    • 2022
  • With the development of online services, the ripple effect of negative comments is increasing, and the damage of cyber violence is rising. Various methods such as filtering based on forbidden words and reporting systems prevent this, but it is challenging to eradicate negative comments. Therefore, this study aimed to increase the accuracy of the classification of negative comments using deep learning and blur the parts corresponding to profanity. Two different conditional training helped decide the number of deep learning layers and filters. The accuracy of 88% confirmed with 90% of the dataset for training and 10% for tests. In addition, Grad-CAM enabled us to find and blur the location of swear words in negative comments. Although the accuracy of classifying comments based on simple forbidden words was 56%, it was found that blurring negative comments through the deep learning model was more effective.

ADSTM Methodology for Signal Pattern Classification (신호 패턴 분류를 위한 ADSTM 기법)

  • Kim A-Ram;Lee Seung-Jae;Kim Chang-Hwa
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2006.05a
    • /
    • pp.379-382
    • /
    • 2006
  • 일반적으로 센서 어레이는 많은 채널의 센서를 가지고 있으므로 분석해야 할 데이터의 양이 많다. 따라서 다변량(多變量) 분석 방법을 이용하는데, 크게 통계적 방법과 신경망 방법을 분석하고자 하는 데이터의 특성이나 분석에 필요한 환경 조건에 맞는 분석 방법을 선택하여 이용한다. 센서 어레이의 신호 패턴을 분석하기 위해 본 연구에서는 상태 천이 모델을 이용하여 측정된 가스의 특성을 반영할 수 있는 통계적 방법에 대해 연구하였다. 센서 어레이 신호 데이터를 패턴 모양의 특성을 나타낼 수 있는 상태 천이 모델로 변환하여 가스 종류 식별이 보다 정확하게 이루어 질 수 있도록 모델을 설계하는데 중점을 두고, 모델링 요소인 '상태'는 일정한 시간 간격으로 샘플링 하였을 때의 신호값으로,'천이 관계는 각 천이 벡터의 각으로 각각 정의하여 각도변이 기반 상태천이 모델링을 고안하였다.

  • PDF

Effective Reduction of BSM Audit Data for Intrusion Detection System by Normal Behavior Modeling (정상행위 모델링을 통한 침입탐지 시스템에서 BSM 감사기록의 효과적인 축약)

  • 서연규;조성배
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 1999.10c
    • /
    • pp.318-320
    • /
    • 1999
  • 정보시스템의 보호를 위한 침입탐지의 방법으로 오용탐지와 비정상행위 탐지방법이 있다. 오용탐지의 경우는 알려진 침입 패턴을 이용하는 것으로 알려진 침입에 대해서는 아주 높은 탐지율을 나타내지만 알려지지 않은 침입이나 변형패턴에 대해서는 탐지할 수 없다는 단점이 있다. 반면 비정상행위 탐지는 정상행위 모델링을 통해 비정상패턴을 탐지하는 것으로 알려지지 않은 패턴에 대해서도 탐지할 수 있는 장점이 있는데 국내외적으로 아직까지 널리 연구되어 있지 않다. 본 논문에서는 BSM으로부터 얻은 다양한 정보를 추출하고 이러한 정보를 자기조직화 신경망을 이용하여 축약함으로써 고정된 크기의 순서정보로 변환하는 방법을 제안한다. 이렇게 생성된 고정크기의 순서정보는 비정상행위 탐지에 효과적으로 사용될 수 있을 것이다.

  • PDF