• Journal of Biosystems Engineering
• /
• v.28 no.2
• /
• pp.117-126
• /
• 2003

This study was conducted to develop precision control system fur cold storage facility that could offer safe storage environment for green grocery. For that reason of neuro-fuzzy control system with learning ability algorithm and single chip neuro-fuzzy micro controller was developed for cold storage facility. Dynamic characteristics and hunting of neuro-fuzzy control system were far superior to on-off and fuzzy control system. Dynamic characteristics of temperature were faster than on-off control system by 1,555 seconds(123% faster) and fuzzy control system by 460 seconds(36.4% faster). When system was arrived at steady state. hunting was ${\pm}$0.5$^{\circ}C$ in on-off control system, ${\pm}$0.4$^{\circ}C$ in fuzzy control system, and ${\pm}$0.3$^{\circ}C$ in neuro-fuzzy control system. Hunting of humidity and wind velocity was also controlled precisely by 70 to 72.5% and 1m/s For storage experiment with onion, characteristics of neuro-fuzzy control system were tested. Dynamic characteristics of neuro-fuzzy control system made cold storage facility conducted precooling ability and minimized hunting.

• BMB Reports
• /
• v.55 no.9
• /
• pp.447-452
• /
• 2022

Neurogenic differentiation 1 (NeuroD1) is an essential transcription factor for neuronal differentiation, maturation, and survival, and is associated with inflammation in lipopolysaccharide (LPS)-induced glial cells; however, the concrete mechanisms are still ambiguous. Therefore, we investigated whether NeuroD1-targeting miRNAs affect inflammation and neuronal apoptosis, as well as the underlying mechanism. First, we confirmed that miR-30a-5p and miR-153-3p, which target NeuroD1, reduced NeuroD1 expression in microglia and astrocytes. In LPS-induced microglia, miR-30a-5p and miR-153-3p suppressed pro-inflammatory cytokines, reactive oxygen species, the phosphorylation of c-Jun N-terminal kinase, extracellular-signal-regulated kinase (ERK), and p38, and the expression of cyclooxygenase and inducible nitric oxide synthase (iNOS) via the NF-κB pathway. Moreover, miR-30a-5p and miR-153-3p inhibited the expression of NOD-like receptor pyrin domain containing 3 (NLRP3) inflammasomes, NLRP3, cleaved caspase-1, and IL-1β, which are involved in the innate immune response. In LPS-induced astrocytes, miR-30a-5p and miR-153-3p reduced ERK phosphorylation and iNOS expression via the STAT-3 pathway. Notably, miR-30a-5p exerted greater anti-inflammatory effects than miR-153-3p. Together, these results indicate that miR-30a-5p and miR-153-3p inhibit MAPK/NF-κB pathway in microglia as well as ERK/STAT-3 pathway in astrocytes to reduce LPS-induced neuronal apoptosis. This study highlights the importance of NeuroD1 in microglia and astrocytes neuroinflammation and suggests that it can be regulated by miR-30a-5p and miR-153-3p.

• The KIPS Transactions:PartD
• /
• v.9D no.5
• /
• pp.939-944
• /
• 2002

In this paper, we propose and apply new classification method to the remotely sensed image acquired from airborne multi-spectral scanner. This is a neuro-fuzzy image classifier derived from the generic model of a 3-layer fuzzy perceptron. We implement a classification software system with the proposed method for land cover image classification. Comparisons with the proposed and maximum-likelihood classifiers are also presented. The results show that the neuro-fuzzy classification method classifies more accurately than the maximum likelihood method. In comparing the maximum-likelihood classification map with the neuro-fuzzy classification map, it is apparent that there is more different as amount as 7.96% in the overall accuracy. Most of the differences are in the "Building" and "Pine tree", for which the neuro-fuzzy classifier was considerably more accurate. However, the "Bare soil" is classified more correctly with the maximum-likelihood classifier rather than the neuro-fuzzy classifier.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.855-858
• /
• 1995

A neural network has very simple construction (input, output and connection weight) and then it can be robusted against some disturbance. In this paper, we proposed a neuro-controller using a Multi-Layered neural network which is combined with PD controller. The proposed neuro-controller is learned by backpropagation learning rule with momentum and neuro-controller adjusts connection weight in neural network to make approximate dynamic model of DC Servo motor. Computer Simulation results show that the proposed neuro-controller's performance is better than that of origianl PD controller.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.55 no.4
• /
• pp.158-160
• /
• 2006

In this paper, a neuro-fuzzy observer system is designed using neuro-fuzzy system for speed control of AC servo motor. This neuro-fuzzy observer is proposed to with the problems occur in the Luenberger observer and sliding observer. The problems of Luenberger and sliding observer are to have to know the dynamics and internal parameters of the system. Performance of the neuro-fuzzy observer system has verified through the experiment with dynamometer load. It is shown that feasibility of the neuro-fuzzy observer is verified.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.7
• /
• pp.536-543
• /
• 2004

In this paper, we proposed a new method of modeling a neuro-fuzzy system using a hybrid clustering algorithm. The initial parameters and the number of clusters of the proposed system are optimally chosen simultaneously with respect to the process of regression, which is a unique characteristics of the proposed system. The proposed algorithm presented in this work improves the overall performance of the proposed a neuro-fuzzy system by choosing a proper number of clusters adaptively according the characteristics of given data. The process of clustering is performed by deciding on the number of classes, which yields the property of convergence of the system. In experiments, the superiority of the proposed neuro-fuzzy system is demonstrated, especially the process of optimizing parameters and clustering of learning speed.

• Journal of Genetic Medicine
• /
• v.1 no.1
• /
• pp.57-59
• /
• 1997

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.2
• /
• pp.48-54
• /
• 2002

In this study, a neuro-fuzzy controller which has the characteristic of fuzzy control and artificial neural network is designed. A fuzzy rule to be applied is automatically selected by the allocated neurons. The neurons correspond to fuzzy rules are created by an expert. To adapt the more precise model is implemented by error back-propagation learning algorithm to adjust the link-weight of fuzzy membership function in the neuro-fuzzy controller. The more classified fuzzy rule is used to include the property of dual mode method. In order to verify the effectiveness of the proposed algorithm designed above, an operating characteristic of a DC servo motor with variable load is investigated.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.6
• /
• pp.252-257
• /
• 2002

We designed a neuro-fuzzy controller to improve some problems that are happened when the DC servo motor is controlled by a PID controller or a fuzzy logic controller. Our model proposed in this paper has the stable and accurate responses, and shortened settling time. To prove the capability of the neuro-fuzzy controller designed in this paper, the proposed controller is applied to the speed control of DC servo motor. The results showed that the proposed controller did not produce the overshoot, which happens when PID controller is used, and also it did not produce the steady state error when FLC is used. And also, it reduced the settling time about 10%. In addition, we could by aware that our model was only about 60% of the value of current peak of PID controller.

• Bulletin of the Korean Chemical Society
• /
• v.33 no.11
• /
• pp.3887-3888
• /
• 2012