• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.180-183
• /
• 2020

물리적 정보를 이용해 암호 알고리즘의 비밀정보를 분석하는 부채널분석 분야에서도 딥러닝을 접목한 분석방법들이 활발히 제안되고 있다. 본 논문에서는 소비전력이 시간축상으로 흐트러지는 현상인 지터가 있는 파형을 신경망의 특성을 기반으로 효과적으로 분석하는 방법을 제안한다. 제안한 방법을 실험적으로 검증하기 위해 지터가 있는 AES-128 파형을 Convolutional Neural Network와 Multi-Layer Perceptron을 기반으로 분석한 결과 제안한 방법을 적용한 신경망은 모든 바이트 키 분석에 성공했으나, 이외의 신경망은 일부 혹은 모든 바이트 키 분석에 실패했다.

• International journal of advanced smart convergence
• /
• v.13 no.2
• /
• pp.80-87
• /
• 2024

This paper focuses on improving accuracy in constrained computing settings by employing the ReLU (Rectified Linear Unit) activation function. The research conducted involves modifying parameters of the ReLU function and comparing performance in terms of accuracy and computational time. This paper specifically focuses on optimizing ReLU in the context of a Multilayer Perceptron (MLP) by determining the ideal values for features such as the dimensions of the linear layers and the learning rate (Ir). In order to optimize performance, the paper experiments with adjusting parameters like the size dimensions of linear layers and Ir values to induce the best performance outcomes. The experimental results show that using ReLU alone yielded the highest accuracy of 96.7% when the dimension sizes were 30 - 10 and the Ir value was 1. When combining ReLU with the Adam optimizer, the optimal model configuration had dimension sizes of 60 - 40 - 10, and an Ir value of 0.001, which resulted in the highest accuracy of 97.07%.

• Computers and Concrete
• /
• v.22 no.2
• /
• pp.249-259
• /
• 2018

This paper presents Artificial Neural Network (ANN) models for evaluating bond strength of deformed, plain and cold formed bars in low strength concrete. The ANN models were implemented using the experimental database developed by conducting experiments in three different universities on total of 138 pullout and 108 splitting specimens under monotonic loading. The key parameters examined in the experiments are low strength concrete, bar development length, concrete cover, rebar type (deformed, cold-formed, plain) and diameter. These deficient parameters are typically found in non-engineered reinforced concrete structures of developing countries. To develop ANN bond model for each bar type, four inputs (the low strength concrete, development length, concrete cover and bar diameter) are used for training the neurons in the network. Multi-Layer-Perceptron was trained according to a back-propagation algorithm. The ANN bond model for deformed bar consists of a single hidden layer and the 9 neurons. For Tor bar and plain bars the ANN models consist of 5 and 6 neurons and a single hidden layer, respectively. The developed ANN models are capable of predicting bond strength for both pull and splitting bond failure modes. The developed ANN models have higher coefficient of determination in training, validation and testing with good prediction and generalization capacity. The comparison of experimental bond strength values with the outcomes of ANN models showed good agreement. Moreover, the ANN model predictions by varying different parameters are also presented for all bar types.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.285-288
• /
• 2005

Neural networks are known as kinds of intelligent strategies since they have learning capability. There are various their applications from intelligent control fields; however, their applications have limits from the point that the stability of the intelligent control systems is not usually guaranteed. In this paper we propose a neuro-adaptive controller for robot manipulators using the radial basis function network(RBFN) that is a kind of a neural network. Adaptation laws for parameters of the RBFN are developed based on the Lyapunov stability theory to guarantee the stability of the overall control scheme. Filtered tracking errors between the actual outputs and desired outputs are discussed in the sense of the uniformly ultimately boundedness(UUB). Additionally, it is also shown that the parameters of the RBFN are bounded. Experimental results for a SCARA-type robot manipulator show that the proposed neuro-adaptive controller is adaptable to the environment changes and is more robust than the conventional PID controller and the neuro-controller based on the multilayer perceptron.

• Journal of Biomedical Engineering Research
• /
• v.23 no.3
• /
• pp.197-205
• /
• 2002

The objectives of this Paper is to implement a diagnostic classifier of differential laryngeal diseases from acoustic signals acquired in a noisy room. For this Purpose, the voice signals of the vowel /a/ were collected from Patients in a soundproof chamber and got mixed with noise. Then, the acoustic Parameters were analyzed, and hierarchical neural networks were applied to the data classification. The classifier had a structure of five-step hierarchical neural networks. The first neural network classified the group into normal and benign or malign laryngeal disease cases. The second network classified the group into normal or benign laryngeal disease cases The following network distinguished polyp. nodule. Palsy from the benign laryngeal cases. Glottic cancer cases were discriminated into T1, T2. T3, T4 by the fourth and fifth networks All the neural networks were based on multilayer perceptron model which classified non-linear Patterns effectively and learned by an error back-propagation algorithm. We chose some acoustic Parameters for classification by investigating the distribution of laryngeal diseases and Pilot classification results of those Parameters derived from MDVP. The classifier was tested by using the chosen parameters to find the optimum ones. Then the networks were improved by including such Pre-Processing steps as linear and z-score transformation. Results showed that 90% of T1, 100% of T2-4 were correctly distinguished. On the other hand. 88.23% of vocal Polyps, 100% of normal cases. vocal nodules. and vocal cord Paralysis were classified from the data collected in a noisy room.

• Structural Monitoring and Maintenance
• /
• v.1 no.3
• /
• pp.249-271
• /
• 2014

This paper presents a unique study of Structural Health Monitoring (SHM) for the maintenance decision making about a real life movable bridge. The mechanical components of movable bridges are maintained on a scheduled basis. However, it is desired to have a condition-based maintenance by taking advantage of SHM. The main objective is to track the operation of a gearbox and a rack-pinion/open gear assembly, which are critical parts of bascule type movable bridges. Maintenance needs that may lead to major damage to these components needs to be identified and diagnosed timely since an early detection of faults may help avoid unexpected bridge closures or costly repairs. The fault prediction of the gearbox and rack-pinion/open gear is carried out using two types of Artificial Neural Networks (ANNs): 1) Multi-Layer Perceptron Neural Networks (MLP-NNs) and 2) Fuzzy Neural Networks (FNNs). Monitoring data is collected during regular opening and closing of the bridge as well as during artificially induced reversible damage conditions. Several statistical parameters are extracted from the time-domain vibration signals as characteristic features to be fed to the ANNs for constructing the MLP-NNs and FNNs independently. The required training and testing sets are obtained by processing the acceleration data for both damaged and undamaged condition of the aforementioned mechanical components. The performances of the developed ANNs are first evaluated using unseen test sets. Second, the selected networks are used for long-term condition evaluation of the rack-pinion/open gear of the movable bridge. It is shown that the vibration monitoring data with selected statistical parameters and particular network architectures give successful results to predict the undamaged and damaged condition of the bridge. It is also observed that the MLP-NNs performed better than the FNNs in the presented case. The successful results indicate that ANNs are promising tools for maintenance monitoring of movable bridge components and it is also shown that the ANN results can be employed in simple approach for day-to-day operation and maintenance of movable bridges.

• Progress in Medical Physics
• /
• v.20 no.3
• /
• pp.132-138
• /
• 2009

Studies on target motion in 4-dimensional radiotherapy are being world-widely conducted to enhance treatment record and protection of normal organs. Prediction of tumor motion might be very useful and/or essential for especially free-breathing system during radiation delivery such as respiratory gating system and tumor tracking system. Neural network is powerful to express a time series with nonlinearity because its prediction algorithm is not governed by statistic formula but finds a rule of data expression. This study intended to assess applicability of neural network method to predict tumor motion in 4-dimensional radiotherapy. Scaled Conjugate Gradient algorithm was employed as a learning algorithm. Considering reparation data for 10 patients, prediction by the neural network algorithms was compared with the measurement by the real-time position management (RPM) system. The results showed that the neural network algorithm has the excellent accuracy of maximum absolute error smaller than 3 mm, except for the cases in which the maximum amplitude of respiration is over the range of respiration used in the learning process of neural network. It indicates the insufficient learning of the neural network for extrapolation. The problem could be solved by acquiring a full range of respiration before learning procedure. Further works are programmed to verify a feasibility of practical application for 4-dimensional treatment system, including prediction performance according to various system latency and irregular patterns of respiration.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.221-241
• /
• 2018

Deep learning is getting attention recently. The deep learning technique which had been applied in competitions of the International Conference on Image Recognition Technology(ILSVR) and AlphaGo is Convolution Neural Network(CNN). CNN is characterized in that the input image is divided into small sections to recognize the partial features and combine them to recognize as a whole. Deep learning technologies are expected to bring a lot of changes in our lives, but until now, its applications have been limited to image recognition and natural language processing. The use of deep learning techniques for business problems is still an early research stage. If their performance is proved, they can be applied to traditional business problems such as future marketing response prediction, fraud transaction detection, bankruptcy prediction, and so on. So, it is a very meaningful experiment to diagnose the possibility of solving business problems using deep learning technologies based on the case of online shopping companies which have big data, are relatively easy to identify customer behavior and has high utilization values. Especially, in online shopping companies, the competition environment is rapidly changing and becoming more intense. Therefore, analysis of customer behavior for maximizing profit is becoming more and more important for online shopping companies. In this study, we propose 'CNN model of Heterogeneous Information Integration' using CNN as a way to improve the predictive power of customer behavior in online shopping enterprises. In order to propose a model that optimizes the performance, which is a model that learns from the convolution neural network of the multi-layer perceptron structure by combining structured and unstructured information, this model uses 'heterogeneous information integration', 'unstructured information vector conversion', 'multi-layer perceptron design', and evaluate the performance of each architecture, and confirm the proposed model based on the results. In addition, the target variables for predicting customer behavior are defined as six binary classification problems: re-purchaser, churn, frequent shopper, frequent refund shopper, high amount shopper, high discount shopper. In order to verify the usefulness of the proposed model, we conducted experiments using actual data of domestic specific online shopping company. This experiment uses actual transactions, customers, and VOC data of specific online shopping company in Korea. Data extraction criteria are defined for 47,947 customers who registered at least one VOC in January 2011 (1 month). The customer profiles of these customers, as well as a total of 19 months of trading data from September 2010 to March 2012, and VOCs posted for a month are used. The experiment of this study is divided into two stages. In the first step, we evaluate three architectures that affect the performance of the proposed model and select optimal parameters. We evaluate the performance with the proposed model. Experimental results show that the proposed model, which combines both structured and unstructured information, is superior compared to NBC(Naïve Bayes classification), SVM(Support vector machine), and ANN(Artificial neural network). Therefore, it is significant that the use of unstructured information contributes to predict customer behavior, and that CNN can be applied to solve business problems as well as image recognition and natural language processing problems. It can be confirmed through experiments that CNN is more effective in understanding and interpreting the meaning of context in text VOC data. And it is significant that the empirical research based on the actual data of the e-commerce company can extract very meaningful information from the VOC data written in the text format directly by the customer in the prediction of the customer behavior. Finally, through various experiments, it is possible to say that the proposed model provides useful information for the future research related to the parameter selection and its performance.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_2
• /
• pp.1307-1315
• /
• 2021

The Changjiang Diluted Water (CDW) spreads over the East China Sea every summer and significantly affects the sea surface salinity changes in the seas around Jeju Island and the southern coast of Korea peninsula. Sometimes its effect extends to the eastern coast of Korea peninsula through the Korea Strait. Specifically, the CDW has a significant impact on marine physics and ecology and causes damage to fisheries and aquaculture. However, due to the limited field surveys, continuous observation of the CDW in the East China Sea is practically difficult. Many studies have been conducted using satellite measurements to monitor CDW distribution in near-real time. In this study, an algorithm for estimating Sea Surface Salinity (SSS) in the East China Sea was developed using the Geostationary Ocean Color Imager (GOCI). The Multilayer Perceptron Neural Network (MPNN) method was employed for developing an algorithm, and Soil Moisture Active Passive (SMAP) SSS data was selected for the output. In the previous study, an algorithm for estimating SSS using GOCI was trained by 2016 observation data. By comparison, the train data period was extended from 2015 to 2020 to improve the algorithm performance. The validation results with the National Institute of Fisheries Science (NIFS) serial oceanographic observation data from 2011 to 2019 show 0.61 of coefficient of determination (R²) and 1.08 psu of Root Mean Square Errors (RMSE). This study was carried out to develop an algorithm for monitoring the surface salinity of the East China Sea using GOCI and is expected to contribute to the development of the algorithm for estimating SSS by using GOCI-II.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.6
• /
• pp.1291-1300
• /
• 2020

Recently, a deep learning-based non-profiling side-channel analysis was proposed. The deep learning-based non-profiling analysis is a technique that trains a neural network model for all guessed keys and then finds the correct secret key through the difference in the training metrics. As the performance of non-profiling analysis varies greatly depending on the neural network training model design, a correct model design criterion is required. This paper describes the two types of loss functions and eight labeling methods used in the training model design. It predicts the analysis performance of each labeling method in terms of non-profiling analysis and power consumption model. Considering the characteristics of non-profiling analysis and the HW (Hamming Weight) power consumption model is assumed, we predict that the learning model applying the HW label without One-hot encoding and the Correlation Optimization (CO) loss will have the best analysis performance. And we performed actual analysis on three data sets that are Subbytes operation part of AES-128 1 round. We verified our prediction by non-profiling analyzing two data sets with a total 16 of MLP-based model, which we describe.