• Journal of Korean Dental Science
• /
• 제16권1호
• /
• pp.47-62
• /
• 2023

Purpose: We aimed to investigate the objective cutoff values of unstimulated flow rates (UFR) and stimulated salivary flow rates (SFR) in patients with xerostomia and to present an optimal machine learning model with a classification and regression tree (CART) for all ages. Materials and Methods: A total of 829 patients with oral diseases were enrolled (591 females; mean age, 59.29±16.40 years; 8~95 years old), 199 patients with xerostomia and 630 patients without xerostomia. Salivary and clinical characteristics were collected and analyzed. Result: Patients with xerostomia had significantly lower levels of UFR (0.29±0.22 vs. 0.41±0.24 ml/min) and SFR (1.12±0.55 vs. 1.39±0.94 ml/min) (P<0.001), respectively, compared to those with non-xerostomia. The presence of xerostomia had a significantly negative correlation with UFR (r=-0.603, P=0.002) and SFR (r=-0.301, P=0.017). In the diagnosis of xerostomia based on the CART algorithm, the presence of stomatitis, candidiasis, halitosis, psychiatric disorder, and hyperlipidemia were significant predictors for xerostomia, and the cutoff ranges for xerostomia for UFR and SFR were 0.03~0.18 ml/min and 0.85~1.6 ml/min, respectively. Conclusion: Xerostomia was correlated with decreases in UFR and SFR, and their cutoff values varied depending on the patient's underlying oral and systemic conditions.

• 제어로봇시스템학회논문지
• /
• 제6권3호
• /
• pp.273-283
• /
• 2000

In this paper we suggest an optimal design method of Fuzzy-Neural Networks(FNN) model for complex and nonlinear systems. The FNNs use the simplified inference as fuzzy inference method and Error Back Propagation Algorithm as learning rule. And we use a HCM(Hard C-Means) Clustering Algorithm to find initial parameters of the membership function. The parameters such as parameters of membership functions learning rates and momentum weighted value is proposed to achieve a sound balance between approximation and generalization abilities of the model. According to selection and adjustment of a weighting factor of an aggregate objective function which depends on the number of data and a certain degree of nonlinearity (distribution of I/O data we show that it is available and effective to design and optimal FNN model structure with a mutual balance and dependency between approximation and generalization abilities. This methodology sheds light on the role and impact of different parameters of the model on its performance (especially the mapping and predicting capabilities of the rule based computing). To evaluate the performance of the proposed model we use the time series data for gas furnace the data of sewage treatment process and traffic route choice process.

• 한국통신학회논문지
• /
• 제37A권9호
• /
• pp.780-785
• /
• 2012

본 논문은 차량 번호판 중앙부 위치값을 기반으로 한 신경망을 이용하여 차량의 번호판 영역을 추출하는 방법을 제안하고자 한다. 임의의 숫자들로 정의된 번호판영역에 대한 학습패턴과 넓은 범위를 수용할 수 있도록 한 신경망의 학습패턴을 이용하여 보다 효율적인 방법을 제시하였다. 학습패턴으로 차량 번호판 인식의 최적화을 이루었고 차량번호 및 헤드라이트 부분의 은닉효과와, 학습패턴의 확대 및 감소에 대하여 연구하였다. 위의 과정을 통하여 지하주차장에서 595여대의 자동차에 대하여 번호판 영역을 추출한 결과 98.5%의 인식율을 보여주었다.

• 한국정보전자통신기술학회논문지
• /
• 제1권3호
• /
• pp.105-109
• /
• 2008

본 논문은 차량 번호판 중앙부 위치값을 기반으로한 신경망을 이용하여 차량의 번호판 영역을 추출하는 방법을 제안하고자 한다. 임의의 숫자들로 정의된 표시영역에 대한 학습패턴과 넓은 범위를 수용할 수 있도록 한 신경망의 학습패턴을 이용하여 보다 효율적인 방법을 제시하였다. 학습패턴으로 차량 번호판 인식의 최적화을 이루었고 차량번호 및 헤드라이트 부분의 은닉효과와, 학습패턴의 확대 및 감소에 대하여 연구하였다. 위의 과정을 통하여 지하주차장에서 595여대의 자동차에 대하여 번호판 영역을 추출한 결과 98.5%의 인식율을 보여주었다.

• 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 1996년도 추계학술대회 학술발표 논문집
• /
• pp.302-305
• /
• 1996

In this paper, an optimal identification method using fuzzy-neural networks is proposed for modeling of nonlinear complex systems. The proposed fuzzy-neural modeling implements system structure and parameter identification using the intelligent schemes together with optimization theory, linguistic fuzzy implication rules, and neural networks(NNs) from input and output data of processes. Inference type for this fuzzy-neural modeling is presented as simplified inference. To obtain optimal model, the learning rates and momentum coefficients of fuzz-neural networks(FNNs) and parameters of membership function are tuned using genetic algorithm(GAs). For the purpose of its application to nonlinear processes, data for route choice of traffic problems and those for activated sludge process of sewage treatment system are used for the purpose of evaluating the performance of the proposed fuzzy-neural network modeling. The show that the proposed method can produce the intelligence model w th higher accuracy than other works achieved previously.

• 전자공학회논문지C
• /
• 제36C권6호
• /
• pp.44-51
• /
• 1999

HMM-Net은 은닉 마르코프 모델(HMM)의 계산과정을 신경망 구조로 구현한 것으로, HMM이 갖고 있는 시계열 모델링 능력과 신경망이 갖고 있는 우수한 변별력을 결합한 것이다. HMM-Net 분류기를 학습하는 방법으로는 HMM의 학습에 이용되는 最尤法(ML)과 신경망 학습의 最小二乘誤差法(MMSE)를 적용할 수 있다. 이들 중 ML이 MMSE보다 안정된 학습을 보장하는 반면 초기 학습조건을 적절하게 설정하였을 경우에는 MMSE가 ML보다 우수하다고 알려져 있다[3]. 따라서 이 논문에서는 먼저 ML을 이용하여 초기학습을 수행한 다음 보다 학습성능이 우수한 MMSE로 바꾸어 최적 또는 준최적으로 학습하는 하이브리드 학습법(ML/MMSE)을 제안한다. 실험용 시계열 패턴으로 /0/부터 /9/까지의 고립 숫자음을 이용하여 실험한 결과, 제안한 방법이 학습특성 및 인식률면에서 ML이나 MMSE만을 이용하는 기존의 방법보다 우수하였음을 확인하였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2003년도 추계종합학술대회
• /
• pp.797-800
• /
• 2003

본 논문은 차량 번호판 중앙부 위치값을 기반으로한 신경망을 이용하여 차량의 번호판 영역을 추출하는 방법을 제안하고자 한다. 임의의 숫자들로 정의된 표시영역에 대한 학습패턴과 넓은 범위를 수용할 수 있도록 한 신경망의 학습패턴을 이용하여 보다 효율적인 방법을 제시하였다. 학습패턴으로 차량 번호판 인식의 최적화을 이루었고 차량번호 및 헤드라이트 부분의 은닉효과와, 학습패턴의 확대 및 감소에 대하여 연구하였단. 위의 과정을 통하여 지하주차장에서 595여대의 자동차에 대하여 번호판 영역을 추출한 결과 98.5%의 인식율을 보여주었다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.1181-1186
• /
• 1993

In the paper, a new design method of rule-based fuzzy modeling is proposed for model identification of nonlinear systems. The structure indentification is carried out, utilizing fuzzy c-means clustering. Fuzzy-neural networks composed back-propagation algorithm and linear fuzzy inference method, are used to identify parameters of the premise and consequence parts. To obtain optimal linguistic fuzzy implication rules, the learning rates and momentum coefficients are tuned automatically using a modified complex method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권10호
• /
• pp.3394-3408
• /
• 2014

Conventional mobile state (MS) and base station (BS) association based on average signal strength often results in imbalance of cell load which may require more powerful processor at BSs and degrades the perceived transmission rate of MSs. To deal with this problem, a Markov decision process (MDP) for load balancing in a multi-cell system with multi-carriers is formulated. To solve the problem, exploiting Sarsa algorithm of on-line learning type [12], ${\alpha}$-controllable load balancing algorithm is proposed. It is designed to control tradeoff between the cell load deviation of BSs and the perceived transmission rates of MSs. We also propose an ${\varepsilon}$-differential soft greedy policy for on-line learning which is proven to be asymptotically convergent to the optimal greedy policy under some condition. Simulation results verify that the ${\alpha}$-controllable load balancing algorithm controls the behavior of the algorithm depending on the choice of ${\alpha}$. It is shown to be very efficient in balancing cell loads of BSs with low ${\alpha}$.