• 전자공학회논문지B
• /
• 제28B권11호
• /
• pp.852-858
• /
• 1991

An adaptive hierarchical classifier(AHCL) for Korean character recognition using a neural net is designed. This classifier has two neural nets: USACL (Unsupervised Adaptive Classifier) and SACL (Supervised Adaptive Classifier). USACL has the input layer and the output layer. The input layer and the output layer are fully connected. The nodes in the output layer are generated by the unsupervised and nearest neighbor learning rule during learning. SACL has the input layer, the hidden layer and the output layer. The input layer and the hidden layer arefully connected, and the hidden layer and the output layer are partially connected. The nodes in the SACL are generated by the supervised and nearest neighbor learning rule during learning. USACL has pre-attentive effect, which perform partial search instead of full search during SACL classification to enhance processing speed. The input of USACL and SACL is a directional edge feature with a directional receptive field. In order to test the performance of the AHCL, various multi-font printed Hangul characters are used in learning and testing, and its processing its speed and and classification rate are compared with the conventional LVQ(Learning Vector Quantizer) which has the nearest neighbor learning rule.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권6호
• /
• pp.3000-3022
• /
• 2019

Full-duplex (FD) technologies enable wireless nodes to simultaneously transmit and receive signal using the same frequency-band. The FD modes could improve their physical layer throughputs. However, in the wireless ad hoc networks, the FD communications also produce new interference risks. On the one hand, the interference ranges (IRs) of the nodes are enlarged when they work in the FD mode. On the other hand, for each FD pair, the FD communication may cause the potential hidden terminal problems to appear around the both sides. In this paper, to avoid the interference risks, we first model the IR of each node when it works in the FD mode, and then analyze the conditions to be satisfied among the transmission ranges (TRs), carrier-sensing ranges (CSRs), and IRs of the FD pair. Furthermore, in the media access control (MAC) layer, we propose a specific method and protocol for collision avoidance. Based on the modified Omnet++ simulator, we conduct the simulations to validate and evaluate the proposed FD MAC protocol, showing that it can reduce the collisions effectively. When the hidden terminal problem is serious, compared with the existing typical FD MAC protocol, our protocol can increase the system throughput by 80%~90%.

• 한국농공학회지
• /
• 제43권2호
• /
• pp.69-77
• /
• 2001

An artificial neural network model was developed to analyze and forecast daily steamflow flow a small watershed. Error Back propagation neural networks (EBPN) of daily rainfall and runoff data were found to have a high performance in simulating stremflow. The model adopts a gradient descent method where the momentum and adaptive learning rate concepts were employed to minimize local minima value problems and speed up the convergence of EBP method. The number of hidden nodes was optimized using Bayesian information criterion. The resulting optimal EBPN model for forecasting daily streamflow consists of three rainfall and four runoff data (Model34), and the best number of the hidden nodes were found to be 13. The proposed model simulates the daily streamflow satisfactorily by comparison compared to the observed data at the HS#3 watershed of the Baran watershed project, which is 391.8 ha and has relatively steep topography and complex land use.

• 대한간호학회지
• /
• 제26권2호
• /
• pp.281-289
• /
• 1996

Neural networks have recently attracted considerable attention in the field of classification and other areas. The purpose of this study was to demonstrate an experiment using back-propagation neural network model applied to nursing diagnosis. The network's structure has three layers ; one input layer for representing signs and symptoms and one output layer for nursing diagnosis as well as one hidden layer. The first prototype of a nursing diagnosis system for patients with stomach cancer was developed with 254 nodes for the input layer and 20 nodes for the output layer of 20 nursing diagnoses, by utilizing learning data set collected from 118 patients with stomach cancer. It showed a hitting ratio of .93 when the model was developed with 20,000 times of learning, 6 nodes of hidden layer, 0.5 of momentum and 0.5 of learning coefficient. The system was primarily designed to be an aid in the clinical reasoning process. It was intended to simplify the use of nursing diagnoses for clinical practitioners. In order to validate the developed model, a set of test data from 20 patients with stomach cancer was applied to the diagnosis system. The data for 17 patients were concurrent with the result produced from the nursing diagnosis system which shows the hitting ratio of 85％. Future research is needed to develop a system with more nursing diagnoses and an evaluation process, and to expand the system to be applicable to other groups of patients.

• 한국환경과학회지
• /
• 제13권7호
• /
• pp.611-618
• /
• 2004

The Neural Network Models which mathematically interpret human thought processes were applied to resolve the uncertainty of model parameters and to increase the model's output for the streamflow forecast model. In order to test and verify the flood discharge forecast model eight flood events observed at Kumho station located on the midstream of Kumho river were chosen. Six events of them were used as test data and two events for verification. In order to make an analysis the Levengerg-Marquart method was used to estimate the best parameter for the Neural Network model. The structure of the model was composed of five types of models by varying the number of hidden layers and the number of nodes of hidden layers. Moreover, a logarithmic-sigmoid varying function was used in first and second hidden layers, and a linear function was used for the output. As a result of applying Neural Networks models for the five models, the N10-6model was considered suitable when there is one hidden layer, and the Nl0-9-5model when there are two hidden layers. In addition, when all the Neural Network models were reviewed, the Nl0-9-5model, which has two hidden layers, gave the most preferable results in an actual hydro-event.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권12호
• /
• pp.5765-5781
• /
• 2018

Extreme learning machine (ELM) is emerging as a powerful machine learning method in a variety of application scenarios due to its promising advantages of high accuracy, fast learning speed and easy of implementation. However, how to select the optimal hidden layer of ELM is still an open question in the ELM community. Basically, the number of hidden layer nodes is a sensitive hyperparameter that significantly affects the performance of ELM. To address this challenging problem, we propose to adopt multiple kernel learning (MKL) to design a multi-hidden-layer-kernel ELM (MHLK-ELM). Specifically, we first integrate kernel functions with random feature mapping of ELM to design a hidden-layer-kernel ELM (HLK-ELM), which serves as the base of MHLK-ELM. Then, we utilize the MKL method to propose two versions of MHLK-ELMs, called sparse and non-sparse MHLK-ELMs. Both two types of MHLK-ELMs can effectively find out the optimal linear combination of multiple HLK-ELMs for different classification and regression problems. Experimental results on seven data sets, among which three data sets are relevant to classification and four ones are relevant to regression, demonstrate that the proposed MHLK-ELM achieves superior performance compared with conventional ELM and basic HLK-ELM.

• 한국지능시스템학회논문지
• /
• 제19권4호
• /
• pp.574-579
• /
• 2009

복잡한 비선형 회귀문제들에서 최적의 신경망을 구축하기 위해서는 구조의 선정 및 노이즈에 의한 과잉학습(overtraining)등에 따른 많은 문제들이 있다. 본 논문에서는 flexible incremental 알고리즘을 이용하여 단계적으로 최적의 신경망을 구축하는 방법을 제안한다. Flexible incremental 알고리즘은 예측 잔류오차를 최소화하기 위해 단계적으로 추가되어지는 은닉노드 개수를 검증데이터를 이용하여 신축성 있게 조절하고, 빠른 학습을 위하여 ELM (Extreme Learning Machine)을 이용한다. 제안된 방법은 신경망의 구축과정에서 사용자의 어떠한 관여 없이도 빠른 학습과 적은 수의 은닉노드들에 의한 범용 근사화 (universal approximation)가 가능한 신경망의 구축이 가능한 장점을 가지고 있다. 다양한 종류의 벤치마크 데이터들을 이용한 실험 결과를 통하여 제안된 방법이 실제 회귀문제들에서 우수한 성능을 가짐을 확인하였다.

• 한국산업정보학회논문지
• /
• 제19권2호
• /
• pp.1-13
• /
• 2014

In IEEE 802.11p/1609-based vehicular networks, vehicles are allowed to exchange safety and control messages only within time periods, called control channel (CCH) interval, which are scheduled periodically. Currently, the length of the CCH interval is set to the fixed value (i.e. 50ms). However, the fixed-length intervals cannot be effective for dynamically changing traffic load. Hence, some protocols have been recently proposed to support variable-length CCH intervals in order to improve channel utilization. In existing protocols, the CCH interval is subdivided into safety and non-safety intervals, and the length of each interval is dynamically adjusted to accommodate the estimated traffic load. However, they do not consider the presence of hidden nodes. Consequently, messages transmitted in each interval are likely to overlap with simultaneous transmissions (i.e. interference) from hidden nodes. Particularly, life-critical safety messages which are exchanged within the safety interval can be unreliably delivered due to such interference, which deteriorates QoS of safety applications such as cooperative collision warning. In this paper, we therefore propose a new interference-aware Dynamic Safety Interval (DSI) protocol. DSI calculates the number of vehicles sharing the channel with the consideration of hidden nodes. The safety interval is derived based on the measured number of vehicles. From simulation study using the ns-2, we verified that DSI outperforms the existing protocols in terms of various metrics such as broadcast delivery ration, collision probability and safety message delay.

• 한국통신학회논문지
• /
• 제34권10B호
• /
• pp.955-963
• /
• 2009

본 논문에서는 해양센서네트워크에서 에너지 소비를 줄이고 전송효율을 높이기 위한 매체접근제어 프로토콜을 제안한다. 수중환경에서는 지상에 비해 전송지연이 길며 데이터 전송률이 낮은 점을 고려하여 효율적으로 에너지를 관리하며 처리율을 향상시킬 수 있는 프로토콜을 제안한다. 제안된 프로토콜은 데이터충돌을 줄이기 위해 채널예약방식을 사용하며, 애드혹 네트워크에서 발생할 수 있는 숨겨진 노드문제와 노출된 노드문제를 제어할 수 있는 매커니즘을 사용한다. 제안된 프로토콜은 슬롯기반의 전송프레임으로 구성되며, 전송프레임은 전송예약을 위한 예약구간을 별도로 두어 노드 간 충돌을 줄인다. 전송예약과정에서 송수신 노드 간에 예약정보를 이용하여 숨겨진 노드문제와 노출된 노드문제를 해결한다. 본 논문에서는 시뮬레이션을 이용하여 평균에너지 소비량, 충돌횟수비율, 처리율, 평균지연시간 관점에서 제안된 프로토콜의 성능을 평가하였으며, 수중환경의 기존 MAC 프로토콜과 비교 분석하였다. 시뮬레이션 결과에서 제안된 방식이 기존의 방식에 비해 성능이 우수함을 볼 수 있었다.

• 한국컴퓨터정보학회논문지
• /
• 제5권2호
• /
• pp.30-36
• /
• 2000

은닉노드는 주어진 문제에서 입력패턴(input pattern)들의 특징을 구분해주는 중요한 역할을 한다. 이 때문에 최적의 은닉노드 수로 구성된 신경망 구조가 성능에 가장 큰 영향을 주는 요인으로 중요성이 대두되고 있다. 그러나 역전파(back-propagation) 학습 알고리즘을 기반으로 하여 은닉노드 수를 결정하는데는 문제점이 있다. 은닉노드 수가 너무 적게 지정되면 주어진 입력패턴을 충분히 구분할 수 없게 되어 완전한 학습이 이루어지지 않는 반면, 너무 많이 지정하면 불필요한 연산의 실행과 기억장소의 낭비로 과적응(overfitting)이 일어나 일반성이 떨어져 인식률이 낮아지기 때문이다. 따라서 본 논문에서는 백 프로퍼게이션 알고리즘을 이용하여 학습을 수행하는 다층 신경망의 학습오차 감소와 수렴율 개선을 위하여 신경망을 구성하는 매개변수를 가지고 은닉노드의 특징 값을 구하고, 그 값은 은닉노드를 제거(pruning)하기 위한 평가치로 사용된다. 구해진 특징 값 중 최대 값과 최소 값을 갖는 노드를 감소(pruning)대상에서 제외하고 나머지 은닉노드 특징 값의 평균과 각 은닉노드의 특징 값을 비교하여 평균보다 작은 특징 값을 갖는 은닉노드를 pruning시키므로서 다층 신경망의 최적 구조를 결정하여 신경망의 학습 속도를 개선하고자 한다.