• The Pure and Applied Mathematics
• /
• v.31 no.1
• /
• pp.57-81
• /
• 2024

We introduce a new degree reduction method for homogeneous symmetric polynomials on binary variables that generalizes the conventional degree reduction methods on monomials introduced by Freedman and Ishikawa. We also design an degree reduction algorithm for general polynomials on binary variables, simulated on the graph coloring problem for random graphs, and compared the results with the conventional methods. The simulated results show that our new method produces reduced quadratic polynomials that contains less variables than the reduced quadratic polynomials produced by the conventional methods.

• Korean Journal of Optics and Photonics
• /
• v.17 no.3
• /
• pp.231-239
• /
• 2006

In recent years, a hierarchical security architecture has been widely studied because it can efficiently protect information by allowing an authorized user access to the level of information. However, the conventional hierarchical decryption methods require several decryption keys for the high level information. In this paper, we propose a hierarchical image encryption using random phase masks and Walsh code having orthogonal characteristics. To decrypt the hierarchical level images by only one decryption key, we combine Walsh code into the hierarchical level system. For encryption process, we first perform a Fourier transform for the multiplication results of the original image and the random phase mask, and then expand the transformed pattern to be the same size and shape of Walsh code. The expanded pattern is finally encrypted by multiplying with the Walsh code image and the binary phase mask. We generate several encryption images as the same encryption process. The reconstruction image is detected on a CCD plane by a despread process and Fourier transform for the multiplication result of encryption image and hierarchical decryption keys which are generated by Walsh code and binary random phase image. Computer simulations demonstrate that the proposed technique can decrypt hierarchical information by using only one level decryption key image and it has a good robustness to the data loss such as random cropping.

• The Korean Journal of Applied Statistics
• /
• v.32 no.3
• /
• pp.349-374
• /
• 2019

A class imbalance problem arises when one class outnumbers the other class by a large proportion in binary data. Studies such as transforming the learning data have been conducted to solve this imbalance problem. In this study, we compared resampling methods among methods to deal with an imbalance in the classification problem. We sought to find a way to more effectively detect the minority class in the data. Through simulation, a total of 20 methods of over-sampling, under-sampling, and combined method of over- and under-sampling were compared. The logistic regression, support vector machine, and random forest models, which are commonly used in classification problems, were used as classifiers. The simulation results showed that the random under sampling (RUS) method had the highest sensitivity with an accuracy over 0.5. The next most sensitive method was an over-sampling adaptive synthetic sampling approach. This revealed that the RUS method was suitable for finding minority class values. The results of applying to some real data sets were similar to those of the simulation.

• Journal of the Korean Chemical Society
• /
• v.51 no.4
• /
• pp.312-317
• /
• 2007

Performing random number simulations, we approximated that the distribution of the number of ways for arranging molecules randomly on a lattice is a normal distributon for N12, the number of interactions between the nearest neighbors of different molecules. From this distribution, an approximate equation of the excess Gibbs energy GE for a lattice solution of nonrandom mixing was derived. Using the equation, liquid-vapor equilibria of several binary solutions were calculated and compared with the calculated result of other equations.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.2
• /
• pp.10-21
• /
• 1998

In this paper, we analyze the anynchrous cellular hybrid DS/FH spread spectrum system with diversity on nonselective Nakagami fading channel. Binary Psk scheme is considered and random spreading code sequences and random hopping patterns are used. We compare the performance of system using hard-limiting correlation receiver with diversity and linear corrleation receiver in Nakagami fading channel. We compute the average bit error probabilities with/without diversity according to spreading code sequence and the number of hop-ping frequencies under the same handwith espansion, and analyze near-far effect. The results show that hard-limiting correlation receiver with diversity gives a good performance over severe fading channel.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.2
• /
• pp.549-557
• /
• 2016

In this paper we propose multiclassification method for large data sets by ensembling least squares support vector machines (LS-SVM) with principal components instead of raw input vector. We use the revised one-vs-all method for multiclassification, which is one of voting scheme based on combining several binary classifications. The revised one-vs-all method is performed by using the hat matrix of LS-SVM ensemble, which is obtained by ensembling LS-SVMs trained using each random sample from the whole large training data. The leave-one-out cross validation (CV) function is used for the optimal values of hyper-parameters which affect the performance of multiclass LS-SVM ensemble. We present the generalized cross validation function to reduce computational burden of leave-one-out CV functions. Experimental results from real data sets are then obtained to illustrate the performance of the proposed multiclass LS-SVM ensemble.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.8
• /
• pp.2023-2032
• /
• 1996

In this paper, we calculate average bit error probabilities of asynchronous hybrid DS/FH-SSMA systems in AWGN chnnel and nonselective Rayleigh fading channel. We analyze and compare the performance of systems in AWGN channel and Rayleigh fading channel by using linear correlation receiver and hard limiting correlation receiver(nonlinear correlation receiver). Binary PSK scheme is considered and random spreading code sequences and random hopping patterns are used. Bit error probabilities of the systems with/without near-far problem under the same bandwidth expansion are calculated. the result shows that the performance of hard limiting correlation receiver is better than that of linear correlation receiver over nonselective Rayleigh fading channel.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.317-320
• /
• 2004

The exponential back-off algorithm doubles the back-off size after each collision without considering network traffic status, which causes degradation of system performance. In this paper, we propose a linear random back-off mechanism which dynamically selects the back-off window size based on the channel status which includes the number of active stations and collisions to significantly increase the protocol capacity. We present an analytical model for the saturated throughput of our linear random back-off algorithm. Simulation results show that performance can be substantially enhanced if binary exponential back-off algorithm is replaced by a linear back- off algorithm.

• 전기의세계
• /
• v.20 no.3
• /
• pp.8-16
• /
• 1971

The proper design of man-machine systems requires as much understanding of the human element as of the machine. Although the modern systems engineer can obtain a very high degree of repeatability and accuracy for the characteristics of a machine, these of the human elements are much less well known. Due to the complexity and importance of modern man-machine systems, this difficult problem has recently received increasing attention. In this paper, the dynamic characteristics of the human operator have been newly determined by impulse estimation using Pseuo-random binnary signals as a test signal and the quasi-linear human operator models used as an element of a closed-loop control system adopted from McRuer & Krendel and Bekey. Also the techniques and instruments are presented for correlating the actual characteristics of the constructed system with anticipated theoretical values. Consequently, in spite of many problems remain yet, experimental results were very satisfactory.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.601-603
• /
• 2012

본 논문에서는 의료영상의 특성을 반영하여 영상의 그래디언트 방향 값을 특징으로 하는 Oriented Center Symmetric Local Binary Patterns (OCS-LBP) 특징을 개발하고 추출된 특징 값에 대해 차원을 줄이고 의미 있는 특징 단위로 재 생성하기 위해 Bag-of-Feature (BoF)를 적용하였다. 검색을 위해서는 기존의 영상 검색 방법과는 다르게, 학습 영상을 이용하여 랜덤 포리스트 (Random Forest)를 사전에 학습시켜 데이터베이스 영상을 N 개의 클래스로 자동 분류 시키고, 질의로 입력된 영상을 같은 방법으로 랜덤 포리스트에 적용하여 상위 확률 값을 갖는 2 개의 클래스에서만 K-nearest neighbor 방법으로 유사 영상을 검색결과로 제시하는 새로운 영상검색 방법을 제시하였다. 실험결과에서 본 논문의 우수성을 증명하기 위해 일반적인 유사성 측정 방법과 랜덤 포리스트를 이용한 방법의 검색 성능 및 시간을 비교하였고, 검색 성능과 시간 면에서 상대적으로 매우 우수한 성능을 보여줌을 증명하였다.