• 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.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.10
• /
• pp.1517-1524
• /
• 2022

In this paper, we consider a heterogeneous network (HetNet) consisting of one macro base station and multiple small base stations, and assume the coordinated multi-point transmission between the base stations. In addition, we assume that the channel between the base station and the user consists of path loss and Rayleigh fading. Under these assumptions, we present the energy efficiency (EE) achievable by the user for a given base station and we formulate an optimization problem of dynamic cell selection and transmit power allocation to maximize the total EE of the HetNet. In this paper, we propose an unsupervised deep learning method to solve the optimization problem. The proposed deep learning-based scheme can provide high EE while having low complexity compared to the conventional iterative convergence methods. Through the simulation, we show that the proposed dynamic cell selection scheme provides higher EE performance than the maximum signal-to-interference-plus-noise ratio scheme and the Lagrangian dual decomposition scheme, and the proposed transmit power allocation scheme provides the similar performance to the trust region interior point method which can achieve the maximum EE.

• Journal of Korea Society of Industrial Information Systems
• /
• v.15 no.5
• /
• pp.37-51
• /
• 2010

In this paper, we discuss the program implementation and system optimization for the effective transfer of huge amount of data. In VLBI which is observing the celestial bodies by using radio telescope hundreds thousands km apart, it is necessary for each VLBI observatory to transfer up to terabytes of observed data. For this reason, e-VLBI research based on advanced network is being actively carried out for the transfer of data efficiently. Following this trend, in this paper, we discuss design & implementation of system for the high speed Gbps data transfer rates. As a data transfer protocol, we use UDP for designing data transmission program with much higher speeds than currently available via VTP(VLBI Transport Protocol). Tsunami-UDP algorithms is applied to implementing data transfer program so that transmission performance could be maximize, also we make it possible to transfer observed data more fast and reliable through optimization of computer systems in each VLBI statopm.

• Journal of KIISE:Databases
• /
• v.35 no.6
• /
• pp.459-468
• /
• 2008

A data stream which is a massive unbounded sequence of data elements continuously generated at a rapid rate. Many recent research activities for emerging applications often need to deal with the data stream. Such applications can be web click monitoring, sensor data processing, network traffic analysis. telephone records and multi-media data. For this. data processing over a data stream are not performed on the stored data but performed the newly updated data with pre-registered queries, and then return a result immediately or periodically. Recently, many studies are focused on dealing with a data stream more than a stored data set. Especially. there are many researches to optimize continuous queries in order to perform them efficiently. This paper proposes a query optimization algorithm to manage continuous query which has multiple join operators(Multi-way join) over data streams. It is called by an Extended Greedy query optimization based on a greedy algorithm. It defines a join cost by a required operation to compute a join and an operation to process a result and then stores all information for computing join cost and join cost in the statistics catalog. To overcome a weak point of greedy algorithm which has poor performance, the algorithm selects the set of operators with a small lay, instead of operator with the smallest cost. The set is influenced the accuracy and execution time of the algorithm and can be controlled adaptively by two user-defined values. Experiment results illustrate the performance of the EGA algorithm in various stream environments.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.155-170
• /
• 2018

Predicting a company's financial bankruptcy is traditionally one of the most crucial forecasting problems in business analytics. In previous studies, prediction models have been proposed by applying or combining statistical and machine learning-based techniques. In this paper, we propose a novel intelligent prediction model based on the simulated annealing which is one of the well-known optimization techniques. The simulated annealing is known to have comparable optimization performance to the genetic algorithms. Nevertheless, since there has been little research on the prediction and classification of business decision-making problems using the simulated annealing, it is meaningful to confirm the usefulness of the proposed model in business analytics. In this study, we use the combined model of simulated annealing and machine learning to select the input features of the bankruptcy prediction model. Typical types of combining optimization and machine learning techniques are feature selection, feature weighting, and instance selection. This study proposes a combining model for feature selection, which has been studied the most. In order to confirm the superiority of the proposed model in this study, we apply the real-world financial data of the Korean companies and analyze the results. The results show that the predictive accuracy of the proposed model is better than that of the naïve model. Notably, the performance is significantly improved as compared with the traditional decision tree, random forests, artificial neural network, SVM, and logistic regression analysis.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.1322-1322
• /
• 2024

Reinforced concrete (RC) , a major contributor to resource depletion and harmful emissions, fuels research on optimizing its design. Optimizing RC structures is challenging due to the mix of discrete and continuous variables, hindering traditional differentiation-based methods. Thus, this study aims to optimize RC structures cost-effectively using deep reinforcement learning. When the Agent selects design variables, Environment checks design criteria based on KDS 14-20 code (South Korea) and calculates reward. The Agent updates its Neural Network with this reward. Target for optimization is a simply supported doubly RC beam, with design variables including cross-section dimensions, sizes and quantities of tension and compression reinforcement, and size of stirrups. We used 200,000 training sets and 336 test sets, each with live load, dead load, beam length variables. To exclude labeled data, multiple training iterations were conducted. In the initial training, the reward was the ratio of maximum possible cost at beam length to the designed structure's cost. Next iterations used the ratio of optimal values by the previous Agent to the current Agent as the reward. Training ended when the difference between optimal values from the previous and current Agent was within 1% for test data. Brute Force Algorithm was applied to the test set to calculate the actual cost-optimal design for validation. Results showed within 10% difference from actual optimal cost, indicating successful deep reinforcement learning application without labeled data. This study benefits the rapid and accurate calculation of optimized designs and construction processes in Building Information Modeling (BIM) applications.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.11A
• /
• pp.878-891
• /
• 2011

We consider the throughput-maximization problem for both the up- and downlink in a wireless network with interference channels. For this purpose, we design an iterative and distributive uplink algorithm based on Lagrangian relaxation. Using the uplink power prices and network duality, we achieve throughput-maximization in the dual downlink that has a symmetric channel and an equal power budget compared to the uplink. The network duality we prove here is a generalized version of previous research [10], [11]. Computational tests show that the performance of the up- and downlink throughput for our algorithms is close to the optimal value for the channel orthogonality factor, ${\theta}{\in}$(0.5, 1]. On the other hand, when the channels are slightly orthogonal (${\theta}{\in}$(0, 0.5]), we observe some throughput degradation in the downlink. We have extended our analysis to the real downlink that has a nonsymmetric channel and an unequal power budget compared to the uplink. It is shown that the modified duality-based approach is thoroughly applied to the real downlink. Considering the complexity of the algorithms in [6] and [18], we conclude that these results are quite encouraging in terms of both performance and practical applicability of the generalized duality theorem.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.43 no.12 s.354
• /
• pp.23-32
• /
• 2006

Fast and accurate power bus design (FAPUD) method for multi-layers high-speed digital boards is devised for the power supply network design tool for accurate and precise high speed board. FAPUD is constructed, based on two main algorithms of the PBEC (Path Based Equivalent Circuit) model and the network synthesis method. The PBEC model exploits simple arithmetic expressions of the lumped 1-D circuit model from the electrical parameters of a 2-D power distribution network. The circuit level design based on PBEC is carried with the proposed regional approach. The circuit level design directly calculates and determines the size of on-chip decoupling capacitors, the size and the location of off-chip decoupling capacitors, and the effective inductances of the package power bus. As a design output, a lumped circuit model and a pre-layout of the power bus including a whole decoupling capacitors are obtained after processing FAPUD. In the tuning procedure, the board re-optimization considering simultaneous switching noise (SSN) added by I/O switching can be carried out because the I/O switching effect on a power supply noise can be estimated over the operation frequency range with the lumped circuit model. Furthermore, if a design changes or needs to be tuned, FAPUD can modify design by replacing decoupling capacitors without consuming other design resources. Finally, FAPUD is accurate compared with conventional PEEC-based design tools, and its design time is 10 times faster than that of conventional PEEC-based design tools.

• Journal of Wetlands Research
• /
• v.18 no.4
• /
• pp.404-412
• /
• 2016

This paper not only aims to establish a plan to acquire the water stage data in a constant and proper manner by using limited manpower and costs, but also establishes the fundamental technology for acquiring the water level observation data or the stage data. For this, this paper focuses on how to acquire the stage data, in a uniform manner, that can represent each basin by developing the technology for establishing the optimal observational network. For that, this paper identifies the current status of the stage gauge stations installed in the ChungJu dam including wetland basin mainly along the national rivers. Then, thus obtained factors are used to develop the representative unit hydrograph. After that, the data are converted into the probability density function. Then, the stations are calculated information transfer amount. As a last step, we establish the optimized stage gauge network by the location of the stage station and space impact that takes into account for the combinations of the number of the stations. In other words, we consider the combination of the stage gauge station with information transfer amount and spatial correlation analysis for estimation.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.11
• /
• pp.32-40
• /
• 2016

IEEE 802.15.4 is the one of the protocols for radio communication in a personal area network. Because of low cost and low power communication for IoT communication, it requires the highest optimization level in the implementation. Recently, the studies of location aware algorithm based on IEEE802.15.4 standard has been achieved. Location estimation is performed basically in equal consideration of reference node information and blind node information. However, an error is not calculated in this algorithm despite the fact that the coordinates of the estimated location of the blind node include an error. In this paper, we enhanced a conventual maximum likelihood estimation using weighted coefficient and implement the hardwired location aware engine for small code size and low power consumption. On the field test using test-beds, the suggested hardware based location awareness method results better accuracy by 10 percents and reduces both calculation and memory access by 30 percents, which improves the systems power consumption.