• 환경영향평가
• /
• 제14권2호
• /
• pp.55-62
• /
• 2005

This study applied the Neural Network and Fuzzy theory to show water-purity control and preventive measure in water quality forecasting of the future river. This study picked out NAJU and HAMPYUNG as the subject of investigation and used monthly the water quality and the outflow data of KWANGJU2, NAJU, YOUNGSANNPO and HAMPYUNG from 1995 to 1999 to forecast BOD, COD, T-N, T-P water density. The datum from 1995 to 1999 are used for study and that of 2000 are used for verification. To develop model of water quality forecasting, firstly, this research formed Neural Network model and divided Neural Network model into two case - the case of considering lag and not considering. And this study selected optimal Neural Network model through changing the number of hidden layer based on input layer(n) from n to 3n. Through forecasting result, the case without considering lag showed more precise simulated result. Accordingly, this study intended to compare, analyse that Fuzzy model using the method without considering lag with Neural Network model. As a result, this study found that the model without considering lag in Neural Network Network shows the most excellent outcome. Thus this study examined a forecasting accuracy, analyzed result and verified propriety through appling the method of water quality forecasting using Neural Network and Fuzzy Algorithms to the actual case.

• 대한치과기공학회지
• /
• 제40권3호
• /
• pp.151-162
• /
• 2018

Purpose: The main purpose of this study is to develop assessment measures for the quality of service for dental labs. Methods: In order to construct the measure of service quality assessment for dental labs, relevant modifications were extracted around theoretical studies, and the survey was conducted on dental technician workers through internet survey. final scale questions were extracted through exploratory factor analysis and confirmed factor analysis of measurement variables, the demographic characteristics of the subjects and the perceptual difference of dental labs were analyzed for the extracted variables. Results: The final five variants of the interactive factor analysis that include the ability to change employee growth, reliability, responsiveness, materiality, interoperability, confirmatory factor analysis excludes variations in employee growth wages, welfare benefits, by changing its name to network capabilities, the quality of service factors for the final dental labs consisted of five variations: network competence, reliability, responsiveness, materiality and interoperability. Conclusion : The service quality of the dental labs showed that the reliability of the product related to the dental materials and the product production responsiveness related to the production order, the Materiality of the materials and equipment of the dental labs, the Interoperability responsiveness related to dental orders, And the importance of network capability to form a mutual network.

• 한국기계가공학회지
• /
• 제21권6호
• /
• pp.89-97
• /
• 2022

Ultrasonic metal welding has been widely used for joining lithium-ion battery tabs. Weld quality monitoring has been an important issue in lithium-ion battery manufacturing. This study focuses on the weld quality monitoring in ultrasonic metal welding with the longitudinal-torsional vibration mode horn developed newly. As the quality of ultrasonic welding depends on welding parameters like pressure, time, and amplitude, the suitable values of these parameters were selected for experimentation. The welds were tested via tensile testing machine and weld strengths were investigated. The dataset collected for performance test was used to train the multi-layer perceptron neural network. The three layer neural network was used for the study and the optimum number of neurons in the first and second hidden layers were selected based on performances of each models. The best models were selected for the horn and then tested to see their performances on an unseen dataset. The neural network models for the longitudinal-torsional mode horn attained test accuracy of 90%. This result implies that proposed models has potential for the weld quality monitoring.

• 경영과학
• /
• 제33권3호
• /
• pp.19-30
• /
• 2016

This study provides a framework to assess network design under the regime of QoE (Quality of Experience). Our approach is expected to reveal the necessity of developing the QoE measures and applying this notion to network design, particularly in the mobile environment. Furthermore, our model shows the ample potential that both users and network providers are able to attain a win-win case by shifting the focus on network design and service operations from QoS (Quality of Service) to QoE. Since the former considers only relevant technological specifications, it may fail in capturing critical factors surrounding users, such as a context where the corresponding user is working on. For example, according to one study [13], the bit-rate, a widely employed QoS measure, shows inferior performance in provisioning network resources to the MOS (Mean Opinion Score), a representative QoE measure. Our framework develops the idea and construct a prototype to systematically assess network design and operations in terms of QoE. The proposed prototype aims at achieving a higher level of efficiency without severely deteriorating users' satisfaction level. We also provide some simulation results which support our idea. That is, reducing the chance of over-provisioning on the basis of the QoE paradigm results in a great flexibility. It may give price cut for users or postponement of network investment for providers or both. Our simulation results also seem robust irrespective of the forms of the QoS-QoE relationship.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제23권5호
• /
• pp.310-315
• /
• 2017

Software-Defined Network의 등장은 하드웨어적인 네트워크 기능들을 소프트웨어적인 형태의 모듈로 Controller에 보다 유연하게 적용시키도록 함으로써 전통적인 네트워크의 구조를 변화시키고 있다. 이러한 환경 속에서 최근 네트워크 트래픽에 대한 Quality of Service 및 자원관리와 같은 다양한 관점에서의 네트워크 관리정책에 대한 연구개발이 진행되고 있고, 이러한 관리정책을 뒷받침 할 수 있는 네트워크 모니터링에 대한 기법들 또한 제시되어 왔다. 이에 본 논문에서는 기계 학습 기법인 Naive Bayesian Classification을 통하여 Flow를 분류한 후, 전송 지연 측정 모듈을 통하여 효율적인 전송경로를 선정하는 기법을 제안한다. 이는 다양한 대역폭을 갖는 여러 경로들로 이루어진 네트워크상에서 효율적인 경로 분배 역할을 할 수 있고, 부하를 분산시킴으로써 보다 원활한 네트워크 환경 및 서비스 품질을 제공할 수 있다.

• Journal of Information Processing Systems
• /
• 제8권1호
• /
• pp.1-20
• /
• 2012

The most important criterion for achieving the maximum performance in a wireless mesh network (WMN) is to limit the interference within the network. For this purpose, especially in a multi-radio network, the best option is to use non-overlapping channels among different radios within the same interference range. Previous works that have considered non-overlapping channels in IEEE 802.11a as the basis for performance optimization, have considered the link quality across all channels to be uniform. In this paper, we present a measurement-based study of link quality across all channels in an IEEE 802.11a-based indoor WMN test bed. Our results show that the generalized assumption of uniform performance across all channels does not hold good in practice for an indoor environment and signal quality depends on the geometry around the mesh routers.

• The Korean Journal of Ecology
• /
• 제21권5_3호
• /
• pp.723-733
• /
• 1998

Restoration to improve the ecological quality of Mt. Nam was explored in a viewpoint of restoration in both landscape and ecosystem levels. A restoration plan in landscape level was based on the result on the land-use pattern in Mt. Nam including its surrounding area and that in ecosystem level on the ecological quality of each landscape element. A plant to construct the green network, which extending from Mt. Nam to the Han river through the Yongsan family park and through the Eungbong urban park was prepared as a restoration project in landscape level to improve the ecological quality of Mt. Nam as an ecological park. On the other hand, a plan for restoration and creation of biotop as a restoration project in ecosystem level was also prepared to improve the ecological quality of each green area consisting green network. Green areas composing green network include keystone green area (Mt. Nam), green stations (Yongsan family park, Eungbong urban park, and the han river citizen's park), and green pathway (or ecological corridor) connecting those green areas.

• Journal of Welding and Joining
• /
• 제18권3호
• /
• pp.114-121
• /
• 2000

Since resistance spot welding has become one of the most popular sheet metal fabrication processes, a strong emphasis is being put on the quality of the welds. Throughout the years many quality estimation systems have been developed by many researchers to ensure weld quality. In this study, the process variables, which were monitored in the primary circuit of the welding machine, are used to estimate the weld quality with Hopfield neural network. The primary dynamic resistance is vectorized and stored as five patterns in the network. As the welding is done, the dynamic resistance patterns are recognized and the quality is estimated with the proposed method. Due to the primary process variables, it is possible to utilize this algorithms as an in-process real time quality monitoring system.

• 한국품질경영학회:학술대회논문집
• /
• 한국품질경영학회 2004년도 품질경영모델을 통한 가치 창출
• /
• pp.376-381
• /
• 2004

The goal of this article is to stress the importance of good quality in telecommunication services and to introduce two basic concepts on the service quality in the telecommunication industry: QoS(Quality of Service) and NP(Network Performance) Based on these notions, presented is an integrated scheme for quality improvement in telecommunication services. Tn particular , proposed with this framework Is an efficient and effective establishment of a balanced set of parameters for continuous monitoring and correct ions of service performance.

• 상하수도학회지
• /
• 제19권6호
• /
• pp.738-748
• /
• 2005

Considering pollution source is transferred by discharge, it is very important to analyze the correlation between discharge and water quality. And temperature also influent to the water quality. In this paper, it is used water quality data that was measured DO (Dissolved Oxygen), TOC (Total Organic Carbon), TN (Total Nitrogen), TP (Total Phosphorus) at Dalchun real time monitoring stations in Namhan river. These characteristics were analyzed with the water quality of rainy and nonrainy periods. Input data of the water quality forecasting models that they were constructed by neural network and neuro-fuzzy was chosen as the reasonable data, and water quality forecasting models were applied. LMNN (Levenberg-Marquardt Neural Network), MDNN (MoDular Neural Network), and ANFIS (Adaptive Neuro-Fuzzy Inference System) models have achieved the highest overall accuracy of TOC data. LMNN and MDNN model which are applied for DO, TN, TP forecasting shows better results than ANFIS. MDNN model shows the lowest estimation error when using daily time, which is qualitative data trained with quantitative data. If some data has periodical properties, it seems effective using qualitative data to forecast.