• Proceedings of the KIEE Conference
• /
• 1999.07g
• /
• pp.2929-2931
• /
• 1999

In this paper, an adaptive fuzzy inference and HCM(Hard C-Means) clustering method are used for on-line fuzzy modeling of nonlinear and complex system. Here HCM clustering method is utilized for determining the initial parameter of membership function of fuzzy premise rules and also avoiding overflow phenomenon during the identification of consequence parameters. To obtain the on-line model structure of fuzzy systems. we use the recursive least square method for the consequent parameter identification. And the proposed on-line identification algorithm is carried out and is evaluated for sewage treatment process system.

• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.3
• /
• 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.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• v.13 no.3
• /
• pp.278-290
• /
• 1991

Prediction of the sop tissue changes following hard tissue movements is very important in the preoperative analysis of surgical changes of the patient who have orthognathic surgery. This study examined post operative changes of the mid-facial sop tissues in Koreans depending upon two major positional changes of the maxilla following Le Fort - I type osteotomy for orthognathic purposes. Sixty patients(41 males and 19 females) of Koreans were selected and divided into two groups according to directional change of movement of anterior bony structures of the Maxilla as follows : Group I (44 patients) was mooed anteriorly and/or inferiorly, and Group II (16 patients) was mooed posteriorly and/or superioly. Postoperative changes of the sop tissue measurements following hard tissue changes were examined on pre - and post - operative cephalometrics by means of computerized digitation methods and the ratios of changes were analysed. The results were obtained as follows : 1. In Group I, all of the sop tissue measures except the Pn was closely followed by the changes of the hard tissue measures in the horizontal plane, but the Sn and the Cm were only correlated to the vertical changes(p<0.001). In group II, all of the sop tissue measures excluding of the N' and the Pn were significantly correlated to the hard tissue measures in horizontal plane(p<0.001), but the Ls and Stm were only correlated relatively to the vertical changes of the ANS(p<0.01). 2. Predictable ratio of the Sn was 66% of the ANS or 56% of the A in the horizontal plane and 89% of the A in the vertical plane in Group I. In Group II, the Sn was predictable as 85% of the ANS or 70% of the A in the horizontal plane but was not predictable in vertical plane. 3. Predictable ratio of the Cm was 28% of the ANS or 50% of the A in the horizontal plane and 56% of the ANS or 36% of the A in the vertical plane in Group I. In Group II, the Cm was predictable horizontally as 74% of the A. Predictable ratio of the Pn was 30% of the ANS or 38% of the A in horizontal plane in Group I, but it was not predictable both horizontally and vertically in Group II. 4. Predictable ratio of the Ls was 52% of the Pr in Group I and 77% in Group II in the horizontal plane. The Stm was predictable as 34% of the pr or 22% of the I in the horizontal plane in Group I, and was also predictable as 55% of the pr or 68% of the I horizontally and 21% of the pr or 65% of the I vertically in Group II. 5. All ratios of change in the thickness. length and area of the upper lip following maxillary movement were statiscally correlated, however, mangitudes of them were meaningful clinically.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.27 no.4
• /
• pp.558-563
• /
• 2000

The lasers have been used in dentistry for more than 30 years and the application of lasers for drilling dental hard tissue has been investigated since the early developement of lasers. Recently, the Er:YAG laser was invented for hard tissue ablation. The Er:YAG laser, having a wavelength of 2.94um, is highly absorbed in both water and hydroxiapatite, leading to a very effective material for hard tissue removal by bursting off the solid tissue component that is, enamel and dentin are removed by the Er :YAG laser by water vaporization and microexplosion, without any melting of inorganic tissues. Therefore, the Er:YAG laser produced round craters with well defined margins and the surrounding tissues had no cracks and no charring. When used for cavity preparation, pulpal damage should not occur if hear buildup is minimized by careful selection of exposure parameters and by use of a water spray. The present study demonstrated that the Er:YAG laser cut the tooth substance adequately for composite resin restoration, without having undesirable side effects such as harmful effects on the pulp, discoloration or cracking etc. Also, the child patients were well cooperative during laser treatment mainly because of little noise, lesser vibration and minimal pain compared to conventional means of cavity preparation.

• Proceedings of the KIEE Conference
• /
• 2001.11c
• /
• pp.420-423
• /
• 2001

In this paper, the Multi-FNNs(Fuzzy-Neural Networks) architecture is identified and optimized using HCM(Hard C-Means) clustering method and genetic algorithms. The proposed Multi-FNNs architecture uses simplified inference and linear inference as fuzzy inference method and error back propagation algorithm as learning rules. Here, HCM clustering method, which is carried out for the process data preprocessing of system modeling, is utilized to determine the structure of Multi-FNNs according to the divisions of input-output space using I/O process data. Also, the parameters of Multi-FNNs model such as apexes of membership function, learning rates and momentum coefficients are adjusted using genetic algorithms. An aggregate performance index with a weighting factor is used to achieve a sound balance between approximation and generalization abilities of the model. To evaluate the performance of the proposed model we use the time series data for gas furnace and the NOx emission process data of gas turbine power plant.

• Proceedings of the KIEE Conference
• /
• 2003.07a
• /
• pp.552-554
• /
• 2003

The second harmonic component is commonly used for blocking differential relay in power transformers. However, it is difficult to distinguish between inrush and internal winding fault with differential current protective relaying. This paper proposed a new method using Nuro-Fuzzy System based on HCM(Hard C-Means). The proposed system is more objective and systematic than existing model. The data used in input are 3-phase primary voltage and fundamental harmonic of differential current. Various states of transformer are simulated using BCTRAN and HYSDAT of EMTP. As a result of the application of algorithm in various cases, the exact discrimination between internal winding fault and inrush is performed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.894-897
• /
• 2014

The speed of processes and the extremely large amount of data to be used in Intelligence Transportations System (ITS) cannot be handling by humans without considerable automation. However, it is difficult to develop software with conventional fixed algorithms (hard-wired logic on decision making level) for effectively manipulate dynamically evolving real time transportation environment. This situation can be resolved by applying methods of artificial intelligence and data mining that provide flexibility and learning capability. This paper presents a brief introduction of data mining and artificial intelligence (AI) applications in Intelligence Transportation System (ITS), analyzing the prospects of enhancing the capabilities by means of knowledge discovery and accumulating intelligence to support in decision making.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.11
• /
• pp.5379-5388
• /
• 2012

In fuzzy modeling for nonlinear process, the fuzzy rules are typically formed by selection of the input variables, the number of space division and membership functions. The Generation of fuzzy rules for nonlinear processes have the problem that the number of fuzzy rules exponentially increases. To solve this problem, complex nonlinear process can be modeled by generating the fuzzy rules by means of fuzzy division of input space. Therefore, in this paper, rules of non-fuzzy inference systems are generated by partitioning the input space in the scatter form using HCM clustering algorithm. The premise parameters of the rules are determined by membership matrix by means of HCM clustering algorithm. The consequence part of the rules is represented in the form of polynomial functions and the consequence parameters of each rule are identified by the standard least-squares method. And lastly, we evaluate the performance and the nonlinear characteristics using the data widely used in nonlinear process. Through this experiment, we showed that high-dimensional nonlinear systems can be modeled by a very small number of rules.

• Composites Research
• /
• v.37 no.1
• /
• pp.46-52
• /
• 2024

The development of transportation methods has improved human transportation convenience and made it possible to expand the travel radius of people with disabilities who have difficulty moving. However, in the case of WAV (wheelchair Accessible Vehicle), the safety that may occur in a vehicle accident is still lower than that of regular passenger seats. In particular, in the case of a rear-end collision that may occur in a defenseless situation, it can cause fatal neck injuries to disabled passengers. Therefore, a more detailed design plan must be reflected in the headrest to be applied to WAV. In this study, a multi-cell headrest was proposed to implement local compression characteristic distribution of the headrest during rear-end collision of WAV. Afterwards, a correlation analysis was performed between the passenger's NIC (Neck Injury Criterion) and impact energy absorption using the data set construction through analysis and the clustering results using k-means clustering. As a result of clustering, it was confirmed that data clusters with similar characteristics were formed, and a correlation analysis between NIC and impact energy absorption through the characteristics of each cluster was performed. As a result of the analysis, it was confirmed that the softer the cell compression characteristics in Mid3 and Mid6, the more impact energy absorption increases, and the harder the cell compression characteristics in Front2, Mid3, and Mid6, the more effective it is in reducing NIC.

• The Journal of Korean Academy of Prosthodontics
• /
• v.34 no.3
• /
• pp.539-573
• /
• 1996

This investigation was designed to determine the effectiveness of the posterior occlusal schemes on masticatory activity during mastication in complete denture. Twelve edentulous subjects were selected for this study. All subjects had no past history and no functional abnormality on masticatory system and TMjoint. And, they had residual ridge of favorable morphology, firm mucosa and Class I skeletal jaw relationship, Twelve experimental denture with interchangeable occlusions(0-degree teeth, 30-degree teeth, Levin teeth and S-A teeth) were constructed for this study. The masticatory performance was analyzed by means of standard sieve(10, 16, 20, 30sieve), and the electrical activity from selected muscles(Temporalis and Masseter muscle) was recorded simultaneously with electromyography(Bio-Pak system) as the subject masticated test foods (rice, peanut and gum) with four different occlusal schemes. Mandibular movement was, also, measured with Sirognathography(Bio-Pak system). These recordings were performed in immediately, after 1 week and after 2 weeks of insertion of complete denture. The results were as follows; 1. The average masticatory performance of 0-degree artificial teeth was higher than any other artificial teeth. 2. Masticatory performance in denture wearer was affected preferentially by food and artificial occlusal schemes. 3. During chewing, there was a statistical difference of EMG activity between masseter and temporal muscle(p<0.01). Especially, EMG activity of working masticatory muscle was highly affected by food rather than by artificial occlusal schemes. 4. In denture wearer, the velocity of opening was not affected by food, whereas, the velocity of closing was faster in soft food chewing than in hard food chewing, and the amount of vertical displacement was grater in chewing of soft and large bolus than in chewing of hard and small bolus. However, the amount of lateral displacement showed conversely (p<0.05). 5. It was considered that masticatory performance in denture wearer is not affected by the condition of residual ridge, the history of denture wear, the preference, the adaptation to artificial teeth and the total mesiodistal length of artificial posterior teeth.