• International Journal of Computer Science & Network Security
• /
• v.21 no.7
• /
• pp.159-168
• /
• 2021

Detecting cyber-attacks using machine learning or deep learning is being studied and applied widely in network intrusion detection systems. We noticed that the application of deep learning algorithms yielded many good results. However, because each deep learning model has different architecture and characteristics with certain advantages and disadvantages, so those deep learning models are only suitable for specific datasets or features. In this paper, in order to optimize the process of detecting cyber-attacks, we propose the idea of building a new deep learning network model based on the association and combination of individual deep learning models. In particular, based on the architecture of 2 deep learning models: Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM), we combine them into a combined deep learning network for detecting cyber-attacks based on network traffic. The experimental results in Section IV.D have demonstrated that our proposal using the CNN-LSTM deep learning model for detecting cyber-attacks based on network traffic is completely correct because the results of this model are much better than some individual deep learning models on all measures.

• ETRI Journal
• /
• v.27 no.3
• /
• pp.294-303
• /
• 2005

In this paper, a supervised algorithm for the evaluation of geophysical sites using a multi-level cellular neural network (ML-CNN) is introduced, developed, and applied to real data. ML-CNN is a stochastic image processing technique based on template optimization using neighborhood relationships of the pixels. The separation/enhancement and border detection performance of the proposed method is evaluated by various interesting real applications. A genetic algorithm is used in the optimization of CNN templates. The first application is concerned with the separation of potential field data of the Dumluca chromite region, which is one of the rich reserves of Turkey; in this context, the classical approach to the gravity anomaly separation method is one of the main problems in geophysics. The other application is the border detection of archeological ruins of the Hittite Empire in Turkey. The Hittite civilization sites located at the Sivas-Altinyayla region of Turkey are among the most important archeological sites in history, one reason among others being that written documentation was first produced by this civilization.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2004.07a
• /
• pp.33-36
• /
• 2004

The process modeling for the growth rate in pulsed laser deposition(PLD)-grown ZnO thin films is investigated using neural networks(NNets) and the process recipes is optimized via genetic algorithms(GAs). D-optimal design is carried out and the growth rate is characterized by NNets based on the back-propagation(BP) algorithm. GAs is then used to search the desired recipes for the desired growth rate. The statistical analysis is used to verify the fitness of the nonlinear process model. This process modeling and optimization algorithms can explain the characteristics of the desired responses varying with process conditions.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.6
• /
• pp.367-374
• /
• 2022

The acceleration of neural networks has become an important topic in the field of computer vision. An accelerator is absolutely necessary for accelerating the lightweight model. Most accelerator-supported operators focused on direct convolution operations. If the accelerator does not provide GEMM operation, it is mostly replaced by CPU operation. In this paper, we proposed an optimization technique for 2-stage tiling-based GEMM routines on VTA. We improved performance of the matrix multiplication routine by maximizing the reusability of the input matrix and optimizing the operation pipelining. In addition, we applied the proposed technique to the DarkNet framework to check the performance improvement of the matrix multiplication routine. The proposed GEMM method showed a performance improvement of more than 2.4 times compared to the non-optimized GEMM method. The inference performance of our DarkNet framework has also improved by at least 2.3 times.

• Advances in nano research
• /
• v.13 no.6
• /
• pp.587-597
• /
• 2022

In the present study, a novel optimization method in formation control of multi -system vehicles based on the trajectory of the nearest neighbor trajectory is presented. In this regard, the state equations of each vehicle and multisystem is derived and the optimization scheme based on minimizing the differences between actual positions and desired positions of the vehicles are conducted. This formation control is a position-based decentralized model. The trajectory of the nearest neighbor are optimized based on the current position and state of the vehicle. This approach aids the whole multi-agent system to be optimized on their trajectory. Furthermore, to overcome the cumulative errors and maintain stability in the network a semi-centralized scheme is designed for the purpose of checking vehicle position to its predefined trajectory. The model is implemented in Matlab software and the results for different initial state and different trajectory definition are presented. In addition, to avoid collision avoidance and maintain the distances between vehicles agents at a predefined desired distances. In this regard, a neural fuzzy network is defined to be utilized in conjunction with the control system to avoid collision between vehicles. The outcome reveals that the model has acceptable stability and accuracy.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.22-25
• /
• 2002

The Mass production of ceramic heater has encountered with the estimation for the proper parameters of the printing conditions. This paper presents a method to estimate the squeegee pressure. It uses resistance distribution from the trial run with approximate squeegee pressure which comes from statistical process control (SPC). Then, the resistance distribution and its total resistance are input to the backpropagation neural networks that can recognize resistance's distribution patterns. The value of output network derived from the input value can identify to the appropriate squeegee pressure. The experimental results are demonstrated In ensure the efficiency and the reliability of this method with the accuracy 96.75 percent. Indeed, embedded on this method will aid us to reduce the loss from the normal mass production.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.6
• /
• pp.58-69
• /
• 1998

This paper introduces a novel neuro-fuzzy system based on the polynomial fuzzy neural network(PFNN) architecture. The PFNN consists of a set of if-then rules with appropriate membership functions whose parameters are optimized via a hybrid genetic algorithm. A polynomial neural network is employed in the defuzzification scheme to improve output performance and to select appropriate rules. A performance criterion for model selection, based on the Group Method of DAta Handling is defined to overcome the overfitting problem in the modeling procedure. The hybrid genetic optimization method, which combines a genetic algorithm and the Simplex method, is developed to increase performance even if the length of a chromosome is reduced. A novel coding scheme is presented to describe fuzzy systems for a dynamic search rang in th GA. For a performance assessment of the PFNN inference system, three well-known problems are used for comparison with other methods. The results of these comparisons show that the PFNN inference system outperforms the other methods while it exhibits exceptional robustness characteristics.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2004.05a
• /
• pp.738-741
• /
• 2004

최근 다양한 금융 데이터를 신경망 이론을 비롯한 최적화 기법을 통해 모델링 하려는 시도가 증가하고 있다. 이러한 시도는 블랙숄즈 모델이 가지고 있는 몇 가지 비현실적인 가정들을 극복할 수 있다는 점에서 성공적이다. 그러나 각각의 최적화 기법의 고유한 특성을 고려하지 못한 채 적용하여 성능면에서 큰 향상을 보이지 못하고 있다. 따라서 이론과 기법의 적용에 있어 금융데이터의 특성에 맞는 명확한 절차의 정의가 필요하다. 본 논문에서는 옵션의 가격결정에 적용 가능한 신경망 기법들을 제시하고 절차를 정의, 분석하고 그 성능을 블랙-숄즈 방정식과 비교한다. 비교 분석 결과는 블랙-숄즈 방정식에 의한 가격 오차와 최적화 기법을 통한 가격오차가 통계적으로 유의한 차이가 있는지 여부를 분석함으로써 유의성을 검증하였다.

• The Journal of the Korea Contents Association
• /
• v.7 no.1
• /
• pp.58-64
• /
• 2007

In pattern recognition field, there are many optimization problems having exponential search spaces. To solve of sequential search algorithms seeking sub-optimal solutions have been used. The algorithms have limitations of stopping at local optimums. Recently lots of researches attempt to solve the problems using genetic algorithms. This paper explains the huge search spaces of typical problems such as feature selection, classifier ensemble selection, neural network pruning, and clustering, and it reviews the genetic algorithms for solving them. Additionally we present several subjects worthy of noting as future researches.

• 전기의세계
• /
• v.38 no.2
• /
• pp.23-30
• /
• 1989

과학기술의 고속화에 따라 종래에는 인간이 더 잘수행하던 지능을 요하는 일들이 점점 컴퓨터에 의해 처리되는 경우가 늘어나고 있다. 그러나 아직도 많은 분야에서 종래의 방식에 의한 한개의 processor나 몇개의 간단한 multiprocessor시스템으로는 너무 많은 시간이 걸려서 처리할 수 없는 일들이 산재해 있다. 예를 들어 image를 인식하는 것이나 언어습득과 번역과 같은 문제들에서 인간의 뇌가 현존하고 있는 어떤 컴퓨터의 성능보다 능가하는 것을 알고 있다. 그 이유는 근본적으로 디지탈 컴퓨터와 인간의 뇌 사이의 정보 처리방식이 틀린점에 기인한다. 대부분의 컴퓨터는 한개 또는 몇개의 main procrssor들이 자료들을 sequential하게 처리하는 데에 반하여, 인간의 뇌는 수천억 개의 neuron들이 정보를 병렬로 처리하고 있다. 따라서 인간의 뇌에 대한 깊이 연구와 그에 따른 새로운 형태의 정보처리 기술의 개발이 시급히 요구되어지고 있다. 최근에 이와같은 massive parallelism을 구현하기 위한 시도가 neural network를 중심으로 일어나고 있다. 여기에서 사용되는 algorithm들은 local information을 실현한다. Neural network에는 여러가지 model들이 있으나 본고에서는 optimization model을 중심으로 그 배경 및 응용을 소개하고자 한다.