• Title/Summary/Keyword: Learning structure optimization

Search Result 149, Processing Time 0.031 seconds

Visual Model of Pattern Design Based on Deep Convolutional Neural Network

  • Jingjing Ye;Jun Wang
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.18 no.2
    • /
    • pp.311-326
    • /
    • 2024
  • The rapid development of neural network technology promotes the neural network model driven by big data to overcome the texture effect of complex objects. Due to the limitations in complex scenes, it is necessary to establish custom template matching and apply it to the research of many fields of computational vision technology. The dependence on high-quality small label sample database data is not very strong, and the machine learning system of deep feature connection to complete the task of texture effect inference and speculation is relatively poor. The style transfer algorithm based on neural network collects and preserves the data of patterns, extracts and modernizes their features. Through the algorithm model, it is easier to present the texture color of patterns and display them digitally. In this paper, according to the texture effect reasoning of custom template matching, the 3D visualization of the target is transformed into a 3D model. The high similarity between the scene to be inferred and the user-defined template is calculated by the user-defined template of the multi-dimensional external feature label. The convolutional neural network is adopted to optimize the external area of the object to improve the sampling quality and computational performance of the sample pyramid structure. The results indicate that the proposed algorithm can accurately capture the significant target, achieve more ablation noise, and improve the visualization results. The proposed deep convolutional neural network optimization algorithm has good rapidity, data accuracy and robustness. The proposed algorithm can adapt to the calculation of more task scenes, display the redundant vision-related information of image conversion, enhance the powerful computing power, and further improve the computational efficiency and accuracy of convolutional networks, which has a high research significance for the study of image information conversion.

Anomaly Detection for User Action with Generative Adversarial Networks (적대적 생성 모델을 활용한 사용자 행위 이상 탐지 방법)

  • Choi, Nam woong;Kim, Wooju
    • Journal of Intelligence and Information Systems
    • /
    • v.25 no.3
    • /
    • pp.43-62
    • /
    • 2019
  • At one time, the anomaly detection sector dominated the method of determining whether there was an abnormality based on the statistics derived from specific data. This methodology was possible because the dimension of the data was simple in the past, so the classical statistical method could work effectively. However, as the characteristics of data have changed complexly in the era of big data, it has become more difficult to accurately analyze and predict the data that occurs throughout the industry in the conventional way. Therefore, SVM and Decision Tree based supervised learning algorithms were used. However, there is peculiarity that supervised learning based model can only accurately predict the test data, when the number of classes is equal to the number of normal classes and most of the data generated in the industry has unbalanced data class. Therefore, the predicted results are not always valid when supervised learning model is applied. In order to overcome these drawbacks, many studies now use the unsupervised learning-based model that is not influenced by class distribution, such as autoencoder or generative adversarial networks. In this paper, we propose a method to detect anomalies using generative adversarial networks. AnoGAN, introduced in the study of Thomas et al (2017), is a classification model that performs abnormal detection of medical images. It was composed of a Convolution Neural Net and was used in the field of detection. On the other hand, sequencing data abnormality detection using generative adversarial network is a lack of research papers compared to image data. Of course, in Li et al (2018), a study by Li et al (LSTM), a type of recurrent neural network, has proposed a model to classify the abnormities of numerical sequence data, but it has not been used for categorical sequence data, as well as feature matching method applied by salans et al.(2016). So it suggests that there are a number of studies to be tried on in the ideal classification of sequence data through a generative adversarial Network. In order to learn the sequence data, the structure of the generative adversarial networks is composed of LSTM, and the 2 stacked-LSTM of the generator is composed of 32-dim hidden unit layers and 64-dim hidden unit layers. The LSTM of the discriminator consists of 64-dim hidden unit layer were used. In the process of deriving abnormal scores from existing paper of Anomaly Detection for Sequence data, entropy values of probability of actual data are used in the process of deriving abnormal scores. but in this paper, as mentioned earlier, abnormal scores have been derived by using feature matching techniques. In addition, the process of optimizing latent variables was designed with LSTM to improve model performance. The modified form of generative adversarial model was more accurate in all experiments than the autoencoder in terms of precision and was approximately 7% higher in accuracy. In terms of Robustness, Generative adversarial networks also performed better than autoencoder. Because generative adversarial networks can learn data distribution from real categorical sequence data, Unaffected by a single normal data. But autoencoder is not. Result of Robustness test showed that he accuracy of the autocoder was 92%, the accuracy of the hostile neural network was 96%, and in terms of sensitivity, the autocoder was 40% and the hostile neural network was 51%. In this paper, experiments have also been conducted to show how much performance changes due to differences in the optimization structure of potential variables. As a result, the level of 1% was improved in terms of sensitivity. These results suggest that it presented a new perspective on optimizing latent variable that were relatively insignificant.

Evolution of Neural Network's Structure and Learn Patterns Based on Competitive Co-Evolutionary Method (경쟁적 공진화법에 의한 신경망의 구조와 학습패턴의 진화)

  • Joung, Chi-Sun;Lee, Dong-Wook;Jun, Hyo-Byung;Sim, Kwee-Bo
    • Journal of the Korean Institute of Telematics and Electronics S
    • /
    • v.36S no.1
    • /
    • pp.29-37
    • /
    • 1999
  • In general, the information processing capability of a neural network is determined by its architecture and efficient training patterns. However, there is no systematic method for designing neural network and selecting effective training patterns. Evolutionary Algorithms(EAs) are referred to as the methods of population-based optimization. Therefore, EAs are considered as very efficient methods of optimal system design because they can provide much opportunity for obtaining the global optimal solution. In this paper, we propose a new method for finding the optimal structure of neural networks based on competitive co-evolution, which has two different populations. Each population is called the primary population and the secondary population respectively. The former is composed of the architecture of neural network and the latter is composed of training patterns. These two populations co-evolve competitively each other, that is, the training patterns will evolve to become more difficult for learning of neural networks and the architecture of neural networks will evolve to learn this patterns. This method prevents the system from the limitation of the performance by random design of neural networks and inadequate selection of training patterns. In co-evolutionary method, it is difficult to monitor the progress of co-evolution because the fitness of individuals varies dynamically. So, we also introduce the measurement method. The validity and effectiveness of the proposed method are inspected by applying it to the visual servoing of robot manipulators.

  • PDF

Wavelet Thresholding Techniques to Support Multi-Scale Decomposition for Financial Forecasting Systems

  • Shin, Taeksoo;Han, Ingoo
    • Proceedings of the Korea Database Society Conference
    • /
    • 1999.06a
    • /
    • pp.175-186
    • /
    • 1999
  • Detecting the features of significant patterns from their own historical data is so much crucial to good performance specially in time-series forecasting. Recently, a new data filtering method (or multi-scale decomposition) such as wavelet analysis is considered more useful for handling the time-series that contain strong quasi-cyclical components than other methods. The reason is that wavelet analysis theoretically makes much better local information according to different time intervals from the filtered data. Wavelets can process information effectively at different scales. This implies inherent support fer multiresolution analysis, which correlates with time series that exhibit self-similar behavior across different time scales. The specific local properties of wavelets can for example be particularly useful to describe signals with sharp spiky, discontinuous or fractal structure in financial markets based on chaos theory and also allows the removal of noise-dependent high frequencies, while conserving the signal bearing high frequency terms of the signal. To date, the existing studies related to wavelet analysis are increasingly being applied to many different fields. In this study, we focus on several wavelet thresholding criteria or techniques to support multi-signal decomposition methods for financial time series forecasting and apply to forecast Korean Won / U.S. Dollar currency market as a case study. One of the most important problems that has to be solved with the application of the filtering is the correct choice of the filter types and the filter parameters. If the threshold is too small or too large then the wavelet shrinkage estimator will tend to overfit or underfit the data. It is often selected arbitrarily or by adopting a certain theoretical or statistical criteria. Recently, new and versatile techniques have been introduced related to that problem. Our study is to analyze thresholding or filtering methods based on wavelet analysis that use multi-signal decomposition algorithms within the neural network architectures specially in complex financial markets. Secondly, through the comparison with different filtering techniques' results we introduce the present different filtering criteria of wavelet analysis to support the neural network learning optimization and analyze the critical issues related to the optimal filter design problems in wavelet analysis. That is, those issues include finding the optimal filter parameter to extract significant input features for the forecasting model. Finally, from existing theory or experimental viewpoint concerning the criteria of wavelets thresholding parameters we propose the design of the optimal wavelet for representing a given signal useful in forecasting models, specially a well known neural network models.

  • PDF

Wavelet Thresholding Techniques to Support Multi-Scale Decomposition for Financial Forecasting Systems

  • Shin, Taek-Soo;Han, In-Goo
    • Proceedings of the Korea Inteligent Information System Society Conference
    • /
    • 1999.03a
    • /
    • pp.175-186
    • /
    • 1999
  • Detecting the features of significant patterns from their own historical data is so much crucial to good performance specially in time-series forecasting. Recently, a new data filtering method (or multi-scale decomposition) such as wavelet analysis is considered more useful for handling the time-series that contain strong quasi-cyclical components than other methods. The reason is that wavelet analysis theoretically makes much better local information according to different time intervals from the filtered data. Wavelets can process information effectively at different scales. This implies inherent support for multiresolution analysis, which correlates with time series that exhibit self-similar behavior across different time scales. The specific local properties of wavelets can for example be particularly useful to describe signals with sharp spiky, discontinuous or fractal structure in financial markets based on chaos theory and also allows the removal of noise-dependent high frequencies, while conserving the signal bearing high frequency terms of the signal. To data, the existing studies related to wavelet analysis are increasingly being applied to many different fields. In this study, we focus on several wavelet thresholding criteria or techniques to support multi-signal decomposition methods for financial time series forecasting and apply to forecast Korean Won / U.S. Dollar currency market as a case study. One of the most important problems that has to be solved with the application of the filtering is the correct choice of the filter types and the filter parameters. If the threshold is too small or too large then the wavelet shrinkage estimator will tend to overfit or underfit the data. It is often selected arbitrarily or by adopting a certain theoretical or statistical criteria. Recently, new and versatile techniques have been introduced related to that problem. Our study is to analyze thresholding or filtering methods based on wavelet analysis that use multi-signal decomposition algorithms within the neural network architectures specially in complex financial markets. Secondly, through the comparison with different filtering techniques results we introduce the present different filtering criteria of wavelet analysis to support the neural network learning optimization and analyze the critical issues related to the optimal filter design problems in wavelet analysis. That is, those issues include finding the optimal filter parameter to extract significant input features for the forecasting model. Finally, from existing theory or experimental viewpoint concerning the criteria of wavelets thresholding parameters we propose the design of the optimal wavelet for representing a given signal useful in forecasting models, specially a well known neural network models.

  • PDF

Improving Generalization Performance of Neural Networks using Natural Pruning and Bayesian Selection (자연 프루닝과 베이시안 선택에 의한 신경회로망 일반화 성능 향상)

  • 이현진;박혜영;이일병
    • Journal of KIISE:Software and Applications
    • /
    • v.30 no.3_4
    • /
    • pp.326-338
    • /
    • 2003
  • The objective of a neural network design and model selection is to construct an optimal network with a good generalization performance. However, training data include noises, and the number of training data is not sufficient, which results in the difference between the true probability distribution and the empirical one. The difference makes the teaming parameters to over-fit only to training data and to deviate from the true distribution of data, which is called the overfitting phenomenon. The overfilled neural network shows good approximations for the training data, but gives bad predictions to untrained new data. As the complexity of the neural network increases, this overfitting phenomenon also becomes more severe. In this paper, by taking statistical viewpoint, we proposed an integrative process for neural network design and model selection method in order to improve generalization performance. At first, by using the natural gradient learning with adaptive regularization, we try to obtain optimal parameters that are not overfilled to training data with fast convergence. By adopting the natural pruning to the obtained optimal parameters, we generate several candidates of network model with different sizes. Finally, we select an optimal model among candidate models based on the Bayesian Information Criteria. Through the computer simulation on benchmark problems, we confirm the generalization and structure optimization performance of the proposed integrative process of teaming and model selection.

A study on the 3-step classification algorithm for the diagnosis and classification of refrigeration system failures and their types (냉동시스템 고장 진단 및 고장유형 분석을 위한 3단계 분류 알고리즘에 관한 연구)

  • Lee, Kangbae;Park, Sungho;Lee, Hui-Won;Lee, Seung-Jae;Lee, Seung-hyun
    • Journal of the Korea Convergence Society
    • /
    • v.12 no.8
    • /
    • pp.31-37
    • /
    • 2021
  • As the size of buildings increases due to urbanization due to the development of industry, the need to purify the air and maintain a comfortable indoor environment is also increasing. With the development of monitoring technology for refrigeration systems, it has become possible to manage the amount of electricity consumed in buildings. In particular, refrigeration systems account for about 40% of power consumption in commercial buildings. Therefore, in order to develop the refrigeration system failure diagnosis algorithm in this study, the purpose of this study was to understand the structure of the refrigeration system, collect and analyze data generated during the operation of the refrigeration system, and quickly detect and classify failure situations with various types and severity . In particular, in order to improve the classification accuracy of failure types that are difficult to classify, a three-step diagnosis and classification algorithm was developed and proposed. A model based on SVM and LGBM was presented as a classification model suitable for each stage after a number of experiments and hyper-parameter optimization process. In this study, the characteristics affecting failure were preserved as much as possible, and all failure types, including refrigerant-related failures, which had been difficult in previous studies, were derived with excellent results.

Poststructural Curriculum and Topic-centered Framework of The New Science Curriculum (후기 구조주의 교육과정과 새 과학과 교육과정의 주제 중심 내용 구성)

  • Kwak, Young-Sun;Lee, Yang-Rak
    • Journal of the Korean earth science society
    • /
    • v.28 no.2
    • /
    • pp.169-178
    • /
    • 2007
  • In this research we diagnosed the actual status of the 7th National science elective curriculum and suggested a way to select and organize the content of the new science elective curriculum. The first science education reform was grounded in the structuralism where the structure of discipline was valued above everything else. On the other hand, the second science education reform suggested alternative interpretations of students' opportunity to learn, putting a brake on the structuralist thinking. According to the survey result, the majority of the science elective courses are in need for revision because the contents are overcrowded, too difficult in light of students' learning readiness, failed to draw students' interest in science, and are overlapped and repeated among the 10th grade science, high school science I and II. In particular, Earth Science II and physics II are the most unfavorable courses among students. Thus, we recommended a fundamental change be made in the new curriculum in addition to the optimization of the content. In this paper, we suggested 'topic-centered content organization' for the science elective course I, i.e., Physics I, Chemistry I, Biology I and Earth Science I that is designed for both science track and non-science track students. Since curriculum provides students with an 'opportunity to learn', a curriculum study should focus on what the 'opportunity to learn' is that students ought to be offered. Based on the result of this study, we recommended one way to select and organize the content of high school elective curriculum.

Prediction of Air Temperature and Relative Humidity in Greenhouse via a Multilayer Perceptron Using Environmental Factors (환경요인을 이용한 다층 퍼셉트론 기반 온실 내 기온 및 상대습도 예측)

  • Choi, Hayoung;Moon, Taewon;Jung, Dae Ho;Son, Jung Eek
    • Journal of Bio-Environment Control
    • /
    • v.28 no.2
    • /
    • pp.95-103
    • /
    • 2019
  • Temperature and relative humidity are important factors in crop cultivation and should be properly controlled for improving crop yield and quality. In order to control the environment accurately, we need to predict how the environment will change in the future. The objective of this study was to predict air temperature and relative humidity at a future time by using a multilayer perceptron (MLP). The data required to train MLP was collected every 10 min from Oct. 1, 2016 to Feb. 28, 2018 in an eight-span greenhouse ($1,032m^2$) cultivating mango (Mangifera indica cv. Irwin). The inputs for the MLP were greenhouse inside and outside environment data, and set-up and operating values of environment control devices. By using these data, the MLP was trained to predict the air temperature and relative humidity at a future time of 10 to 120 min. Considering typical four seasons in Korea, three-day data of the each season were compared as test data. The MLP was optimized with four hidden layers and 128 nodes for air temperature ($R^2=0.988$) and with four hidden layers and 64 nodes for relative humidity ($R^2=0.990$). Due to the characteristics of MLP, the accuracy decreased as the prediction time became longer. However, air temperature and relative humidity were properly predicted regardless of the environmental changes varied from season to season. For specific data such as spray irrigation, however, the numbers of trained data were too small, resulting in poor predictive accuracy. In this study, air temperature and relative humidity were appropriately predicted through optimization of MLP, but were limited to the experimental greenhouse. Therefore, it is necessary to collect more data from greenhouses at various places and modify the structure of neural network for generalization.