• Composites Research
• /
• 제36권1호
• /
• pp.53-58
• /
• 2023

PIC 설계 방법은 선행 유한요소해석을 통해 하중 유형을 나누어, 각 구간마다 하중 유형에 강한 복합재료의 적층 각도 순서를 배치하는 방법이다. 기존 연구에서는 효율적으로 구간을 나누기 위하여 PIC 설계 방법에 머신 러닝이 적용되었으며, 학습 데이터는 선행 유한요소해석 결과 값을 통해 전체 요소의 일부인 참조 요소에서의 인장, 압축 그리고 전단과 같은 하중 유형으로 나누어 라벨링 되었다. 하지만 좌굴에 대해 고려되지 않아서 좌굴 발생 시, 적절한 하중 유형으로 나눌 수 없기 때문에 이를 해결하기 위한 방법이 필요하다. 본 연구에서는 좌굴이 고려되기 위한 새로운 하중 유형 분석 방법을 기존의 PIC 설계에 적용하는 기법(PIC-NTL)이 제안되었다. 좌굴의 하중 분석은 각 플라이(Ply)별 응력 3축 특성을 통해 진행되었으며, 요소의 두께 방향으로 동일한 크기의 두 영역으로 나누어진 판단 영역 내에서 결정된 하중 유형을 통해 대표 하중 유형이 지정되었다. 학습 데이터의 특성 값은 참조 요소의 좌표, 라벨(Label)은 각 판단 영역의 대표 하중 유형으로 구성되었으며, 이 데이터를 통해 머신 러닝 모델이 학습되었다. 머신 러닝 모델의 성능에 영향을 미치는 하이퍼파라미터는 베이지안 알고리즘을 통하여 최적 값으로 튜닝되었다. 튜닝 된 머신 러닝 모델의 중 SVM 모델이 가장 높은 예측률과 ROC-AUC로 나타났으며, 해당 모델을 통해 예측된 데이터가 유한요소 모델에 매핑되었다. 기존에 제안된 PIC 설계 방법과 비교하기 위하여 사각관 형태의 모델을 압축시키는 유한요소해석이 진행되었으며, 본 연구에서 제안된 설계 방법이 강도와 에너지 흡수율에서 더 우수함이 검증되었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권1호
• /
• pp.334-349
• /
• 2022

The effectiveness of Wi-Fi networks is greatly influenced by the optimization of contention window (CW) parameters. Unfortunately, the conventional approach employed by IEEE 802.11 wireless networks is not scalable enough to sustain consistent performance for the increasing number of stations. Yet, it is still the default when accessing channels for single-users of 802.11 transmissions. Recently, there has been a spike in attempts to enhance network performance using a machine learning (ML) technique known as reinforcement learning (RL). Its advantage is interacting with the surrounding environment and making decisions based on its own experience. Deep RL (DRL) uses deep neural networks (DNN) to deal with more complex environments (such as continuous state spaces or actions spaces) and to get optimum rewards. As a result, we present a new approach of CW control mechanism, which is termed as contention window threshold (CW_Threshold). It uses the DRL principle to define the threshold value and learn optimal settings under various network scenarios. We demonstrate our proposed method, known as a smart exponential-threshold-linear backoff algorithm with a deep Q-learning network (SETL-DQN). The simulation results show that our proposed SETL-DQN algorithm can effectively improve the throughput and reduce the collision rates.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2001년도 추계학술대회 학술발표 논문집
• /
• pp.60-64
• /
• 2001

In this paper, a new learning methodology for Kernel Methods is suggested that results in a sparse representation of kernel space from the training patterns for classification problems. Among the traditional algorithms of linear discriminant function(perceptron, relaxation, LMS(least mean squared), pseudoinverse), this paper shows that the relaxation procedure can obtain the maximum margin separating hyperplane of linearly separable pattern classification problem as SVM(Support Vector Machine) classifier does. The original relaxation method gives only the necessary condition of SV patterns. We suggest the sufficient condition to identify the SV patterns in the learning epochs. Experiment results show the new methods have the higher or equivalent performance compared to the conventional approach.

• 센서학회지
• /
• 제30권1호
• /
• pp.15-19
• /
• 2021

Image processing is one of the major techniques that are used for computer vision. Nowadays, researchers are using machine learning and deep learning for the aforementioned task. In recent years, digit recognition tasks, i.e., automatic meter recognition approach using electric or water meters, have been studied several times. However, two major issues arise when we talk about previous studies: first, the use of the deep learning technique, which includes a large number of parameters that increase the computational cost and consume more power; and second, recent studies are limited to the detection of digits and not storing or providing detected digits to a database or mobile applications. This paper proposes a system that can detect the digital number of meter readings using a lightweight deep neural network (DNN) for low power consumption and send those digits to an Android mobile application in real-time to store them and make life easy. The proposed lightweight DNN is computationally inexpensive and exhibits accuracy similar to those of conventional DNNs.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 춘계학술발표대회
• /
• pp.262-264
• /
• 2023

Internet of Things (IoT) networks currently employ an increased number of users and applications, raising their susceptibility to cyberattacks and data breaches, and endangering our security and privacy. Intrusion detection, which includes monitoring and analyzing incoming and outgoing traffic to detect and prohibit the hostile activity, is critical to ensure cybersecurity. Conventional intrusion detection systems (IDS) are centralized, making them susceptible to cyberattacks and other relevant privacy issues because all the data is gathered and processed inside a single entity. This research aims to create a blockchain-based architecture to support federated learning and improve cybersecurity and intrusion detection in IoT networks. In order to assess the effectiveness of the suggested approach, we have utilized well-known cybersecurity datasets along with centralized and federated machine learning models.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.151-153
• /
• 2023

Federated learning (FL)-based network intrusion detection techniques have enormous potential for securing the Industrial Internet of Things (IIoT) cybersecurity. The openness and connection of systems in smart industrial facilities can be targeted and manipulated by malicious actors, which emphasizes the significance of cybersecurity. The conventional centralized technique's drawbacks, including excessive latency, a congested network, and privacy leaks, are all addressed by the FL method. In addition, the rich data enables the training of models while combining private data from numerous participants. This research aims to create an FL-based architecture to improve cybersecurity and intrusion detection in IoT networks. In order to assess the effectiveness of the suggested approach, we have utilized well-known cybersecurity datasets along with centralized and federated machine learning models.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2000년도 THE THIRD INTERNATIONAL CONFERENCE ON AGRICULTURAL MACHINERY ENGINEERING. V.II
• /
• pp.124-131
• /
• 2000

In this study, the NEURAL NETWORK (hereinafter referred to as NN) was applied to control of the nonlinear factors for turning movement of the crawler vehicle and experiment was carried out using a small model of crawler vehicle in order to inspect an application of NN. Furthermore, CHAOS NEURAL NETWORK (hereinafter referred to as CNN) was also applied to this control so as to compare with conventional NN. CNN is especially effective for plane in many variables with local minimum which conventional NN is apt to fall into, and it is relatively useful to nonlinear factors. Experiment of turning on the slope of crawler vehicle was performed in order to estimate an adaptability of nonlinear problems by NN and CNN. The inclination angles of the road surface which the vehicles travel on, were respectively 4deg, 8deg, 12deg. These field conditions were selected by the object for changing nonlinear magnitude in turning phenomenon of vehicle. Learning of NN and CNN was carried out by referring to positioning data obtained from measurement at every 15deg in turning. After learning, the sampling data at every 15deg were interpolated based on the constructed learning system of NN and CNN. Learning and simulation programs of NN and CNN were made by C language ("Association of research for algorithm of calculating machine (1992)"). As a result, conventional NN and CNN were available for interpolation of sampling data. Moreover, when nonlinear intensity is not so large under the field condition of small slope, interpolation performance of CNN was a little not so better than NN. However, when nonlinear intensity is large under the field condition of large slope, interpolation performance of CNN was relatively better than NN.

• 한국멀티미디어학회논문지
• /
• 제20권8호
• /
• pp.1299-1311
• /
• 2017

Sounds based machine fault diagnosis recovers all the studies that aim to detect automatically faults or damages on machines using the sounds emitted by these machines. Conventional methods that use mathematical models have been found inaccurate because of the complexity of the industry machinery systems and the obvious existence of nonlinear factors such as noises. Therefore, any fault diagnosis issue can be treated as a pattern recognition problem. We present here an automatic fault diagnosis system of hand drills using discrete wavelet transform (DWT) and pattern recognition techniques such as principal component analysis (PCA) and artificial neural networks (ANN). The diagnosis system consists of three steps. Because of the presence of many noisy patterns in our signals, we first conduct a filtering analysis based on DWT. Second, the wavelet coefficients of the filtered signals are extracted as our features for the pattern recognition part. Third, PCA is performed over the wavelet coefficients in order to reduce the dimensionality of the feature vectors. Finally, the very first principal components are used as the inputs of an ANN based classifier to detect the wear on the drills. The results show that the proposed DWT-PCA-ANN method can be used for the sounds based automated diagnosis system.

• 한국콘텐츠학회논문지
• /
• 제10권10호
• /
• pp.54-67
• /
• 2010

종래에 헬스케어 영역에서 주로 사용해왔던 기계학습 기법을 U-health 서비스 분석단계에 적용하기에는 여러 가지 문제점들이 있다. 첫째, 아직 U-health 분야의 연구가 초기단계에 불과하여 기존의 기법들을 U-health 환경에 적용한 사례가 매우 부족하다. 둘째, 기계학습 기법은 학습시간이 많이 소요되기 때문에 실시간으로 질환을 관리해야만 하는 U-health 서비스 환경에는 적용하기 어렵다. 셋째, 그동안 다양한 기계 학습 기법들이 제시되었으나 질환 연관변수에 가중치를 부여할 수 있는 방법이 없어, 개인 맞춤형 질병예측 시스템으로 구축할 수 없는 한계를 가진다. 본 논문에서는 이러한 문제점들을 개선하고, U-health 서비스 시스템의 바이오 데이터 분석 과정을 프로세스로 해석하기 위하여, 개인 맞춤형 질병예측 기법인 PCADP를 제안하였다. 또한 이러한 PCADP를 바탕으로 U-health 데이터 및 서비스 명세의 의미 있는 표현을 위하여 U-health 온톨로지 프레임워크를 시멘틱스형으로 모델링하였다. 또한 PCADP 예측 기법은 U-health 환경에서 판별 기법이 갖추어야 할 조건인 유연성과 실시간성이 기존의 방식에 비하여 향상되었고, 판별과정의 모니터링 및 시스템의 지속적인 개선측면에서도 효율적으로 작용함을 확인하였다.

• 융합보안논문지
• /
• 제20권2호
• /
• pp.111-121
• /
• 2020

딥뉴럴네트워크는 머신러닝 분야 중 이미지 인식, 사물 인식 등에 좋은 성능을 보여주고 있다. 그러나 딥뉴럴네트워크는 적대적 샘플(Adversarial example)에 취약점이 있다. 적대적 샘플은 원본 샘플에 최소한의 noise를 넣어서 딥뉴럴네트워크가 잘못 인식하게 하는 샘플이다. 그러나 이러한 적대적 샘플은 원본 샘플간의 최소한의 noise을 주면서 동시에 딥뉴럴네트워크가 잘못 인식하도록 하는 샘플을 생성하는 데 시간이 많이 걸린다는 단점이 있다. 따라서 어떠한 경우에 최소한의 noise가 아니더라도 신속하게 딥뉴럴네트워크가 잘못 인식하도록 하는 공격이 필요할 수 있다. 이 논문에서, 우리는 신속하게 딥뉴럴네트워크를 공격하는 것에 우선순위를 둔 신속한 오인식 샘플 생성 공격을 제안하고자 한다. 이 제안방법은 원본 샘플에 대한 왜곡을 고려하지 않고 딥뉴럴네트워크의 오인식에 중점을 둔 noise를 추가하는 방식이다. 따라서 이 방법은 기존방법과 달리 별도의 원본 샘플에 대한 왜곡을 고려하지 않기 때문에 기존방법보다 생성속도가 빠른 장점이 있다. 실험데이터로는 MNIST와 CIFAR10를 사용하였으며 머신러닝 라이브러리로 Tensorflow를 사용하였다. 실험결과에서, 제안한 오인식 샘플은 기존방법에 비해서 MNIST와 CIFAR10에서 각각 50%, 80% 감소된 반복횟수이면서 100% 공격률을 가진다.