• Nutrition Research and Practice
• /
• 제17권6호
• /
• pp.1255-1266
• /
• 2023

BACKGROUND/OBJECTIVES: This study aimed to predict the association between nutritional intake and diabetes mellitus (DM) by developing an artificial neural network (ANN) model for older adults. SUBJECTS/METHODS: Participants aged over 65 years from the 7th (2016-2018) Korea National Health and Nutrition Examination Survey were included. The diagnostic criteria of DM were set as output variables, while various nutritional intakes were set as input variables. An ANN model comprising one input layer with 16 nodes, one hidden layer with 12 nodes, and one output layer with one node was implemented in the MATLAB^® programming language. A sensitivity analysis was conducted to determine the relative importance of the input variables in predicting the output. RESULTS: Our DM-predicting neural network model exhibited relatively high accuracy (81.3%) with 11 nutrient inputs, namely, thiamin, carbohydrates, potassium, energy, cholesterol, sugar, vitamin A, riboflavin, protein, vitamin C, and fat. CONCLUSIONS: In this study, the neural network sensitivity analysis method based on nutrient intake demonstrated a relatively accurate classification and prediction of DM in the older population.

• 치과방사선
• /
• 제29권1호
• /
• pp.149-159
• /
• 1999

Purpose: The purpose of this study was to evaluate cervical lymph node metastasis of oral squamous cell carcinoma patients by MRI film and neural network system. Materials and Methods: The oral squamous cell carcinoma patients(21 patients. 59 lymph nodes) who have visited SNU hospital and been taken by MRI. were included in this study. Neck dissection operations were done and all of the cervical lymph nodes were confirmed with biopsy. In MR images. each lymph node were evaluated by using 6 MR imaging criteria(size. roundness. heterogeneity. rim enhancement. central necrosis, grouping) respectively. Positive predictive value. negative predictive value. and accuracy of each MR imaging criteria were calculated. At neural network system. the layers of neural network system consisted of 10 input layer units. 10 hidden layer units and 1 output layer unit. 6 MR imaging criteria previously described and 4 MR imaging criteria (site I-node level II and submandibular area. site II-other node level. shape I-oval. shape II-bean) were included for input layer units. The training files were made of 39 lymph nodes(24 metastatic lymph nodes. 10 non-metastatic lymph nodes) and the testing files were made of other 20 lymph nodes(10 metastatic lymph nodes. 10 non-metastatic lymph nodes). The neural network system was trained with training files and the output level (metastatic index) of testing files were acquired. Diagnosis was decided according to 4 different standard metastatic index-68. 78. 88. 98 respectively and positive predictive values. negative predictive values and accuracy of each standard metastatic index were calculated. Results: In the diagnosis of using single MR imaging criteria. the rim enhancement criteria had highest positive predictive value (0.95) and the size criteria had highest negative predictive value (0.77). In the diagnosis of using single MR imaging criteria. the highest accurate criteria was heterogeneity (accuracy: 0.81) and the lowest one was central necrosis (accuracy: 0.59). In the diagnosis of using neural network systems. the highest accurate standard metastatic index was 78. and that time. the accuracy was 0.90. Neural network system was more accurate than any other single MR imaging criteria in evaluating cervical lymph node metastasis. Conclusion: Neural network system has been shown to be more useful than any other single MR imaging criteria. In future. Neural network system will be powerful aiding tool in evaluating cervical node metastasis.

• International Journal of Control, Automation, and Systems
• /
• 제2권4호
• /
• pp.423-434
• /
• 2004

In this paper, we introduce a new topology of Self-Organizing Polynomial Neural Networks (SOPNN) based on genetically optimized Multi-Layer Perceptron (MLP) and discuss its comprehensive design methodology involving mechanisms of genetic optimization. Let us recall that the design of the 'conventional' SOPNN uses the extended Group Method of Data Handling (GMDH) technique to exploit polynomials as well as to consider a fixed number of input nodes at polynomial neurons (or nodes) located in each layer. However, this design process does not guarantee that the conventional SOPNN generated through learning results in optimal network architecture. The design procedure applied in the construction of each layer of the SOPNN deals with its structural optimization involving the selection of preferred nodes (or PNs) with specific local characteristics (such as the number of input variables, the order of the polynomials, and input variables) and addresses specific aspects of parametric optimization. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between the approximation and generalization (predictive) abilities of the model. To evaluate the performance of the GA-based SOPNN, the model is experimented using pH neutralization process data as well as sewage treatment process data. A comparative analysis indicates that the proposed SOPNN is the model having higher accuracy as well as more superb predictive capability than other intelligent models presented previously.reviously.

• 한국지능시스템학회논문지
• /
• 제18권1호
• /
• pp.41-47
• /
• 2008

클러스터 기반 퍼지 모델트리에서 훈련 데이터의 과잉 적응은 검중 데이터의 성능을 저하시키는 문제점을 가지고 있다. 이러한 문제점을 해결하기 위한 방법으로 본 논문에서는 상호 노드간의 정보를 고려하는 방법을 제안하고자 한다. 제안된 방법은 우선 입력과 출력변수의 속성을 고려한 퍼지 클러스터링에 의해 중심벡터를 계산한 후, 중심벡터들과 입력 속성간의 소속도를 이용하여 구간 분할된 영역별로 각각의 선형모델을 구축한다. 예측 단계에서는 입력된 데이터가 잎노드에 도달하기까지 경유하게 되는 노드들의 중심벡터들과 입력 데이터간의 거리값에 따른 소속도를 계산한 후 최종적으로 각 노드의 선형모델들과 계산된 소속도를 이용하여 출력값을 예측하게 된다. 제안된 방법의 우수성을 보이기 위해 다양한 벤치마크 데이터를 대상을 실험한 결과, 기존의 클러스터 기반 퍼지 모델트리보다 향상된 성능을 보임을 알 수 있었다.

• 한국정보처리학회논문지
• /
• 제3권7호
• /
• pp.1773-1780
• /
• 1996

인공지능의 기호적 방법과 수치적 방법을 결합한 지식기반신경망은 다른 기계 학 습모델보다 우수한 성능을 나타내고 있다. 그러나 지식기반신경망은 신경망으로 형성 된 후 동적으로 그 구조를 변경할 수 없어서 영역이론정련화 기능을 갖추지 못하였다. 지식기반신경망의 이러한 단점을 보완하기 위하여 TopGen 알고리즘이 제안되었으나 삽입된 은닉노드를 모두 입력 노드에 연결한 점, 빔탐색을 이용한 등의 문제를 안고 있다. 본 논문에서는 TopGen의 문제점을 해소하기 위하여 은닉 노드를 다음 하위계층 의 노드에 링크 시켰으며, 역추적을 허용한 언덕 오르기를 이용하는 알고리즘을 설계 하였다.

• 전자공학회논문지CI
• /
• 제48권5호
• /
• pp.64-73
• /
• 2011

유클리드 최소 신장 트리(EMST) 문제는 2차원 평면상에 존재하는 입력노드들을 최소 비용으로 연결하는 것이다. EMST와 같은 다항 시간문제에 대하여 연구된 알고리즘들은 수많은 입력들에 대하여 최적의 해를 얻기 위해 매우 많은 시간을 필요로 한다. 본 논문에서는 이 문제에 대한 해를 구하기 위해 분할과 병렬기법을 활용한 다항 시간 근사법(PTAS)을 제안하는데, 이 기법은 비교적 짧은 시간 내에 매우 큰 근사 EMST를 생성할 수 있다. 순수 PTAS는 비-다항 시간문제를 위해 개발되었지만, 다이내믹 프로그래밍을 활용하여 이것을 대형 EMST에 적용하였다. 제안된 방법에 의해 생성된 15,000개의 입력 단말노드와 16개의 분할 영역으로 구성된 근사 EMST의 생성 실험에서, 직렬 방식은 89%, 병렬 방식은 99%의 실행시간의 감축을 보였다. 따라서 본 논문에서 제안하는 방법은 평면상의 매우 많은 수의 입력 단말 노드에 대하여 근사 EMST를 신속히 구축해야 하는 응용에 잘 적용될 수 있다.

• 한국지능시스템학회논문지
• /
• 제11권4호
• /
• pp.325-330
• /
• 2001

최적화문제에 사용되는 신경회로망을 회로레벨에서 시뮬레이션을 해보면, 알고리즘레벨에서 시뮬레이션한 결과와 많이 다름을 체험한다. 즉, 이런 신경회로망의 출력값들은 시간이 흐름에 따라 점근적으로 수렴하나, 입력단의 값들은 입력단에 부수적으로 연결되어 있는 컨덕턴스의 값에 따라 수렴여부도 달라지고, 또한 시스템의 성능도 변함을 안다. 이 논문에서는 입력단에 시스템의 안정도를 위해 부수적으로 연결된 컨덕턴스의 값에 따라 시스템의 수렴여부를 입력단과 출력단에서 분석하였으며, 에너지함수의 수렴점들이 이들 컨덕턴스의 값에 따라 성분이 변함을 분석하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 추계학술대회 논문집 학회본부
• /
• pp.591-593
• /
• 1997

When input circumstance is changed abrubtly, many nodes of Competitive Learning Neural Networks far from new input vector may never win, and therefore never learn. Various techniques to prevent these phenomena have been reported. We proposed a new technique based on Self Creating and Organizing Neural Networks, and which is compared to Self Organizing Feature Map and Frequency Sensitive Neural Networks.

• ETRI Journal
• /
• 제16권1호
• /
• pp.35-43
• /
• 1994

In this paper, the robustness of the artificial neural networks to noise is demonstrated with a multilayer perceptron, and the reason of robustness is due to the statistical orthogonality among hidden nodes and its hierarchical information extraction capability. Also, the misclassification probability of a well-trained multilayer perceptron is derived without any linear approximations when the inputs are contaminated with random noises. The misclassification probability for a noisy pattern is shown to be a function of the input pattern, noise variances, the weight matrices, and the nonlinear transformations. The result is verified with a handwritten digit recognition problem, which shows better result than that using linear approximations.

• Journal of Multimedia Information System
• /
• 제3권4호
• /
• pp.141-148
• /
• 2016

This paper proposes a medium access control (MAC) protocol for multiple-input multiple-output (MIMO) ad-hoc networks. Multiple-packet receptions in MIMO systems have attracted as a key technique to achieve a high transmission rate. In the conventional protocols for multiple-packet receptions, timing offsets among multiple-frame transmissions cause frame collisions induced by hidden nodes, which degrades network performance. In the proposed protocol, transmission synchronization among hidden nodes can be achieved by applying pulse/tone exchanges. By applying the pulse/tone exchanges, multiple-packet receptions among hidden nodes can be achieved, which enhances network throughputs compared with the conventional protocol. Simulation results show effectiveness of the proposed protocol.