• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1992년도 하계학술대회 논문집 A
• /
• pp.46-48
• /
• 1992

Through the last 20 years' study, it is a well-known fact that symbolic approach has limitations in generating a new concept from given concepts. Hence, neural networks having a role of associative memory based on dynamical activation of neurons attract AI scientists' attention. In this paper, recent trials for combining neural networks and Artificial Intelligent systems are systematically reviewed and a prototype ENEDB(Experimental Neuro Expert DataBase) system built on HP9000/300 workstation is introduced to show the possibility of using the trials for real applications.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.679-680
• /
• 2008

When we apply the neural networks to applications, we need to select proper architecture of the network and the activation function of the network is one of most important characteristics. In this research, we propose a method to make a network using multiple activation functions. The performance of the proposed method is investigated through the computer simulations on various regression problems.

• 전자공학회논문지SC
• /
• 제39권2호
• /
• pp.157-165
• /
• 2002

본 논문에서는 PD 제어기와 신경회로망을 이용하여 3상 유도전동기의 속도제어 시스템을 구현하고자 한다. PD 제어기는 초기의 제어를 담당하며 신경회로망의 초기 학습을 담당한다. 또한, 신경회로망은 비선형 매핑능력과 학습능력이 탁월하기 때문에 제어기로 많이 사용되며 특히 전향경로 신경망은 구조가 매우 간단하기 때문에 본 논문에서는 이를 이용하여 유도전동기의 속도제어 시스템에 구현하였다. 신경회로망의 입력으로는 모터의 기준속도, 엔코더를 이용하여 측정한 모터의 실제 속도와 제어입력 전류를 이용하였고, 온라인 상태로 학습되도록 하였다. 본 논문에서 제안된 알고리즘의 타당성을 보이기 위해 기존에 널리 사용되었던 PI 제어기와 비교평가를 하였으며 시뮬레이션과 실험결과로부터 초기운전 상태에서는 PD 제어기가 주로 제어를 담당하지만 시간이 지남에 따라 신경회로망이 학습되어 신경회로망이 주 제어기가 됨을 확인하였다. 아울러, 제안된 하이브리드 제어기가 PI 제어기보다 우수하고 특히 부하변동과 같은 외란에 강인함을 알 수 있었으며, 정상상태 오차가 현저히 감소하여 정밀한 속도제어가 가능함을 확인하였다.

• 전자공학회논문지B
• /
• 제30B권12호
• /
• pp.21-30
• /
• 1993

In this paper, we propose a connected Korean digit recohnition system employing neural networks and lexical constraints of the Korean digits. In the proposed recognition system, firstly, each frame of digit string is labelled by phoneme classification neural networks.which are trained with the reference phoneme segments extracted form an isolated digit based on the position information. And, the frame labels are combined with each other for constructing the phoneme segments. Then, these segments are combined to form a digit candidate using the digit combination rules. The digit candidate is decided based on the condition for digit decision. If the condition is not satisfied, the digit candidate is further recognized using the digit decision neural network in the next step. In our approach, the neural networks are trained with 10 isolated digits uttered by 5 male speakers. To investigate the performance of the proposed recognition system, an intensive computer simulation on the 30 connected digit strings uttered by 5 male speakers is performed. The simulation result indicates that 95.6% digit recognition rate and 82% digit string recognition rate are provided by the proposed Korean digit recognition system.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1992년도 하계학술대회 논문집 A
• /
• pp.401-403
• /
• 1992

For the control of robotic manipulators with unknown or uncertain dynamics, leaming control schemes are very effective control schemes for repeated trajectory following tasks. In this class of controllers, control techniques using neural networks have been gaining much attention in recent years.. In this note, we discuss the leaming control techniques using neural networks and propose a new model-based control scheme using multilayered neural networks. Three-layerd neural network is used as a feedback controller to compensate the mismatched terms between model plant and real plant. Computer simulations are performed to show the applicability and the limitation of the proposed controller.

• 한국산업융합학회 논문집
• /
• 제3권4호
• /
• pp.361-367
• /
• 2000

This paper proposes an efficient feature extraction of the image data using nonlinear principal component analysis neural networks of a new learning algorithm. The proposed method is a learning algorithm with momentum for reflecting the past trends. It is to get the better performance by restraining an oscillation due to converge the global optimum. The proposed algorithm has been applied to the cancer image of $256{\times}256$ pixels and the coin image of $128{\times}128$ pixels respectively. The simulation results show that the proposed algorithm has better performances of the convergence and the nonlinear feature extraction, in comparison with those using the backpropagation and the conventional nonlinear PCA neural networks.

• 한국정밀공학회지
• /
• 제12권5호
• /
• pp.157-165
• /
• 1995

In this paper the comparison between the neural networks and traditional approaches as nonlinear system identification methods are considered. Two model structures of neural networks are the state space model and the input output model neural networks. The traditional methods are the AutoRegressive eXogeneous Input model and the Nonlinear AutoRegressive eXogeneous Input model. Computer simulation for an analytic dynamic model of a single input single output nonlinear system has been done for all the chosen models. Model validation for the obtained models also has been done with testing inputs of the sinusoidal, ramp and the noise ramp.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권12호
• /
• pp.3416-3435
• /
• 2023

Task offloading in vehicular networks is hot topic in the development of autonomous driving. In these scenarios, due to the role of vehicles and pedestrians, task characteristics are changing constantly. The classical deep learning algorithm always uses a pre-trained neural network to optimize task offloading, which leads to system performance degradation. Therefore, this paper proposes a neural network fine-tuning task offloading algorithm, combining with location prediction for pedestrians and vehicles by the Payne model of fluid dynamics and the car-following model, respectively. After the locations are predicted, characteristics of tasks can be obtained and the neural network will be fine-tuned. Finally, the proposed algorithm continuously predicts task characteristics and fine-tunes a neural network to maintain high system performance and meet low delay requirements. From the simulation results, compared with other algorithms, the proposed algorithm still guarantees a lower task offloading delay, especially when congestion occurs.

• 대한치매학회지
• /
• 제17권3호
• /
• pp.83-89
• /
• 2018

Machine learning is where a machine (i.e., computer) determines for itself how input data is processed and predicts outcomes when provided with new data. An artificial neural network is a machine learning algorithm based on the concept of a human neuron. The purpose of this review is to explain the fundamental concepts of artificial neural networks.

• Nuclear Engineering and Technology
• /
• 제53권2호
• /
• pp.657-665
• /
• 2021

Nondestructive evaluation methods play an important role in ensuring component integrity and safety in many industries. Operator fatigue can play a critical role in the reliability of such methods. This is important for inspecting high value assets or assets with a high consequence of failure, such as aerospace and nuclear components. Recent advances in convolution neural networks can support and automate these inspection efforts. This paper proposes using residual neural networks (ResNets) for real-time detection of corrosion, including iron oxide discoloration, pitting and stress corrosion cracking, in dry storage stainless steel canisters housing used nuclear fuel. The proposed approach crops nuclear canister images into smaller tiles, trains a ResNet on these tiles, and classifies images as corroded or intact using the per-image count of tiles predicted as corroded by the ResNet. The results demonstrate that such a deep learning approach allows to detect the locus of corrosion via smaller tiles, and at the same time to infer with high accuracy whether an image comes from a corroded canister. Thereby, the proposed approach holds promise to automate and speed up nuclear fuel canister inspections, to minimize inspection costs, and to partially replace human-conducted onsite inspections, thus reducing radiation doses to personnel.