• Journal of Intelligence and Information Systems
• /
• v.15 no.2
• /
• pp.49-59
• /
• 2009

Contents-based image retrieval methods are in general more objective and effective than text-based image retrieval algorithms since they use color and texture in search and avoid annotating all images for search. SIM(Self-organizing Image browsing Map) is one of contents-based image retrieval algorithms that uses only browsable mapping results obtained by SOM(Self Organizing Map). However, SOM may have an error in selecting the right BMU in learning phase if there are similar nodes with distorted color information due to the intensity of light or objects' movements in the image. Such images may be mapped into other grouping nodes thus the search rate could be decreased by this effect. In this paper, we propose an improved SIM that uses HSV color model in extracting image features with color quantization. In order to avoid unexpected learning error mentioned above, our SOM consists of two layers. In learning phase, SOM layer 1 has the color feature vectors as input. After learning SOM Layer 1, the connection weights of this layer become the input of SOM Layer 2 and re-learning occurs. With this multi-layered SOM learning, we can avoid mapping errors among similar nodes of different color information. In search, we put the query image vector into SOM layer 2 and select nodes of SOM layer 1 that connects with chosen BMU of SOM layer 2. In experiment, we verified that the proposed SIM was better than the original SIM and avoid mapping error effectively.

• The Korean Journal of Applied Statistics
• /
• v.26 no.5
• /
• pp.847-856
• /
• 2013

We propose a modified learning process for generalized neural network using a learning algorithm by Liu et al. (2001). We consider the effect of initial weights, training results and learning errors using a modified learning process. We employ an incremental training procedure where training patterns are learned systematically. Our algorithm starts with a single training pattern and a single hidden layer neuron. During the course of neural network training, we try to escape from the local minimum by using a weight scaling technique. We allow the network to grow by adding a hidden layer neuron only after several consecutive failed attempts to escape from a local minimum. Our optimization procedure tends to make the network reach the error tolerance with no or little training after the addition of a hidden layer neuron. Simulation results with suitable initial weights indicate that the present constructive algorithm can obtain neural networks very close to minimal structures and that convergence to a solution in neural network training can be guaranteed. We tested these algorithms extensively with small training sets.

• The Journal of the Korea Contents Association
• /
• v.10 no.5
• /
• pp.99-106
• /
• 2010

Multilayer perceptrons(MLPs) or feed-forward neural networks are widely applied to many areas based on their function approximation capabilities. When implementing MLPs for application problems, we should determine various parameters and training methods. In this paper, we discuss the design of MLPs especially for pattern classification problems. This discussion includes how to decide the number of nodes in each layer, how to initialize the weights of MLPs, how to train MLPs among various error functions, the imbalanced data problems, and deep architecture.

• Journal of KIBIM
• /
• v.12 no.2
• /
• pp.40-48
• /
• 2022

It is very important to accurately predict construction costs in the early stages of the construction project. However, it is difficult to accurately predict construction costs with limited information from the initial stage. In recent years, with the development of machine learning technology, it has become possible to predict construction costs more accurately than before only with schematic construction characteristics. Based on machine learning technology, this study aims to analyze plans to more accurately predict construction costs by using only the factors influencing construction costs. To the end of this study, the effect of the error rate according to the activation function and the node configuration of the hidden layer was analyzed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.109-111
• /
• 2014

본 논문에서는 노드의 속성정보를 통해 노드의 움직임을 예측하는 PPoP(The Path Prediction algorithm based on Probability) 알고리즘을 제안한다. 기존 이동 예측 알고리즘들은 GPS(Global Positioning System)를 사용해 노드의 이동을 학습을 통해 패턴화 하여 예측한다. 이때, 노드들이 이동 패턴을 벗어날 경우 예측률이 떨어진다. 따라서 본 논문에서는 스테른 게를라흐의 실험(Stern-Gerlach experiment)을 분석하여 노드의 이동성을 예측하는 알고리즘을 제안한다. 본 논문에서 제안된 알고리즘에서는 노드의 이동 경로를 staore-carry-forward 방식으로 상황 인지에 의한 경로 설정 변경 예측 방법으로 이동 예측 확률 기법이다. 모의실험 결과 제안한 방법을 사용하여 노드의 이동성 및 패턴을 벗어난 상황에서도 노드의 예측 하고자 한다.

• Proceedings of the KAIS Fall Conference
• /
• 2010.11a
• /
• pp.421-423
• /
• 2010

본 논문에서는 특정한 공간에서 학습하는 학습자들의 학습환경을 최적화하여 학습능률을 향상시키기 위한 방안으로서 유비쿼터스 센서네트워크 기술을 활용한 학습지원시스템을 구축한다. 이를 위해 특정 공간에 실내외에 부착된 센서노드를 활용하여 온도, 습도, 조도 등의 정보를 수집하고, 이들 정보와 학습자들로부터 파악한 정보를 분석하여 최적의 학습환경을 조성하기 시스템에 대해 연구한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.12
• /
• pp.2885-2890
• /
• 2014

Localization of a sensor network node using machine learning has been recently studied. It is easy for Support vector machines algorithm to implement in high level language enabling parallelism. Raspberrypi is a linux system which can be used as a sensor node. Pi can be used to construct IP based Hadoop clusters. In this paper, we realized Support vector machine using python language and built a sensor network cluster with 5 Pi's. We also established a Hadoop software framework to employ MapReduce mechanism. In our experiment, we implemented the test sensor network with a variety of parameters and examined based on proficiency, resource evaluation, and processing time. The experimentation showed that with more execution power and memory volume, Pi could be appropriate for a member node of the cluster, accomplishing precise classification for sensor localization using machine learning.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.12
• /
• pp.2843-2852
• /
• 2013

In the nested mobile network environment, the mobile node selects one of multiple mobile routers. The MR(Mobile Router) by existing top-down or bottom-up methods may not be the optimal MR if the numbers of mobile nodes and routers are substantially increased, and the scale of the network is increased drastically. Since an inappropriate MR decision causes handover or binding renewal to mobile nodes, determining of the optimal MR is important for efficiency. In this paper, we propose an algorithm that decides on the optimal MR using MR QoS(Quality of Service) information, and we describe how to understand the various structured MLP(Multi-Layered Perceptron) based on the algorithm. In conclusion, we prove the ability of the suggested neural network for a nesting mobile network through the performance analysis of each learned MLP.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.4
• /
• pp.883-889
• /
• 2005

Error backpropagation algorithm of multilayer perceptron may result in local-minima because of the insufficient nodes in the hidden layer, inadequate momentum set-up, and initial weights. In this paper, we proposed the ART-1 based fuzzy supervised learning algorithm which is composed of ART-1 and fuzzy single layer supervised learning algorithm. The Proposed fuzzy supervised learning algorithm using self-generation method applied not only ART-1 to creation of nodes from the input layer to the hidden layer, but also the winer-take-all method, modifying stored patterns according to specific patterns. to adjustment of weights. We have applied the proposed learning method to the problem of recognizing a resident registration number in resident cards. Our experimental result showed that the possibility of local-minima was decreased and the teaming speed and the paralysis were improved more than the conventional error backpropagation algorithm.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2003.05a
• /
• pp.469-473
• /
• 2003

다층 구조 신경망에서 널리 사용되는 오류 역전파 알고리즘은 초기 가중치와 불충분한 은닉층의 노드수로 인하여 지역 최소화에 빠질 가능성이 있다. 따라서 본 논문에서는 오류 역전파 알고리즘에서 은닉층의 노드 수를 설정하는 문제와 ARTI에서 경계 변수의 설정에 따라 인식률이 저하되는 문제점을 개선하기 위하여 ARTI과 Max-Min 신경망을 결합한 퍼지 다층 퍼셉트론을 제안한다. 제안된 자가 생성을 이용한 퍼지 다층 퍼셉트론은 입력층에서 은닉층으로 노드를 생성시키는 방식은 ARTI을 적용하였고, 가중치 조정은 특정 패턴에 대한 저장 패턴을 수정하도록 하는 winner-take-all 방식을 적용하였다. 제안된 학습 방법의 성능을 평가하기 위하여 학생증 영상을 대상으로 실험한 결과, 기존의 오류 역전파 알고즘보다 연결 가중치들이 지역 최소화에 위치할 가능성이 줄었고 학습 속도 및 정체 현상이 개선되었다.