• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.2
• /
• pp.154-162
• /
• 2003

In this paper, Associative Memory with Cellular Neural Networks classifies and recognizes image patterns as an operator applied to image process. CNN processes nonlinear data in real-time like neural networks, and made by cell which communicates with each other directly through its neighbor cells as the Cellular Automata does. It is applied to the optimization problem, associative memory, pattern recognition, and computer vision. Image processing with CNN is appropriate to 2-D images, because each cell which corresponds to each pixel in the image is simultaneously processed in parallel. This paper shows the method for designing the structure of associative memory based on CNN and getting output image by choosing the most appropriate weight pattern among the whole learned weight pattern memories. Each template represents weight values between cells and updates them by learning. Hebbian rule is used for learning template weights and LMS algorithm is used for classification.

• International Journal of Oral Biology
• /
• v.35 no.4
• /
• pp.209-214
• /
• 2010

Cells that have endogenous multipotent properties can be used as a starting source for the generation of induced pluripotent cells (iPSC). In addition, small molecules associated with epigenetic reprogramming are also widely used to enhance the multi- or pluripotency of such cells. Skinderived precursor cells (SKPs) are multipotent, sphereforming and embryonic neural crest-related precursor cells. These cells can be isolated from a juvenile or adult mammalian dermis. SKPs are also an efficient starting cell source for reprogramming and the generation of iPSCs because of the high expression levels of Sox2 and Klf4 in these cells as well as their endogenous multipotency. In this study, valproic acid (VPA), a histone deacetylase (HDAC) inhibitor, was tested in the generation of iPSCs as a potential enhancer of the reprogramming potential of SKPs. SKPs were isolated from the back skins of 5-6 week old C57BL/6 X DBA/2 F1 mice. After passage 3, the SKPs was treated with 2 mM of VPA and the quantitative real time RT-PCR was performed to quantify the expression of Oct4 and Klf4 (pluripotency specific genes), and Snai2 and Ngfr (neural crest specific genes). The results show that Oct4 and Klf4 expression was decreased by VPA treatment. However, there were no significant changes in neural crest specific gene expression following VPA treatment. Hence, although VPA is one of the most potent of the HDAC inhibitors, it does not enhance the reprogramming of multipotent skin precursor cells in mice.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.11
• /
• pp.2075-2082
• /
• 2006

This paper presents modeling and optimization techniques for hish efficiency solar cell process on single-crystalline float zone (FZ) wafers. Among a sequence of multiple steps of fabrication, the followings are the most sensitive steps for the contact formation: 1) Emitter formation by diffusion; 2) Anti-reflection-coating (ARC) with silicon nitride using plasma-enhanced chemical vapor deposition (PECVD); 3) Screen-printing for front and back metalization; and 4) Contact formation by firing. In order to increase the performance of solar cells in terms of efficiency, the contact formation process is modeled and optimized using neural networks and genetic algorithms, respectively. This paper utilizes the design of experiments (DOE) in contact formation to reduce process time and fabrication costs. The experiments were designed by using central composite design which consists of 24 factorial design augmented by 8 axial points with three center points. After contact formation process, the efficiency of the fabricated solar cell is modeled using neural networks. Established efficiency model is then used for the analysis of the process characteristics and process optimization for more efficient solar cell fabrication.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.31 no.1
• /
• pp.67-72
• /
• 2003

In this paper, solar cell array of KOMPSAT 1 was modeled and analyzed. The modeling results of solar array were achieved by neural algorithm, which is a powerful nonlinear system modeling tool. Using solar cell array modeling, the solar cell array was analyzed and verified by simulation considering solar cell data of KOMPSAT 1. The characteristics curves and power generation of the solar array are analyzed by using the modeling.

• Clinics in Shoulder and Elbow
• /
• v.15 no.2
• /
• pp.65-72
• /
• 2012

Purpose: To evaluate the differentiation potential of stem cells and their immunophenotype from 3 different sources. Methods: Our study involved three stem cell sources-subacromial bursal tissue, bone marrow, and umbilical cord blood. We obtained the subacromial bursal tissue and bone marrow from the patients undergoing shoulder surgery. After collecting the sample, we applied specific induction media for neurogenic, adipogenic and osteogenic differentiation. Also, flow-cytometry analysis was done to reveal the cell surface antigens. Results: We obtained 100% (8 cases) neural and adipogenic differentiation, but 62.5% (5 of 8 cases) osseous differentiation among the subacromial bursal tissue group. Bone marrow derived cells showed 100% neural (6 cases) and adipogenic (5 cases) differentiation, but 80% (4 of 5 cases) osseous differentiation. Umbilical cord blood derived cells revealed 97% (65 of 67 cases) neural, 53.7% (29 of 54 cases) adipogenic and 68.4% (39 of 57 cases) osseous differentiation. Immunophenotype analysis revealed that surface markers of bone marrow, subacromial bursal cell and umbilical cord blood derived mesenchymal stem cells are different from each other. Conclusions: Mesenchymal stem cells are potential agents in regenerative medicine and are characterized by expression of surface markers and by their differentiation potential. Our study with stem cells from subacromial bursal tissue, bone marrow and umbilical cord discovered that each stem cell has unique differentiation potential and function based on its origin. Various stem cells show multi-lineage differentiations in vitro which can be correlated to in vivo conditions.

• Journal of Korean Institute of Industrial Engineers
• /
• v.24 no.1
• /
• pp.23-35
• /
• 1998

This article presents a network flow analysis to form flexible machine cells with minimum intercellular part moves and a neural network model to form part families. The operational sequences and production quantity of the part, and the number of cells and the cell size are taken into considerations for a 0-1 quadratic programming formulation and a network flow based solution procedure is developed. After designing the machine cells, a neural network approach for the integration of part families and the automatic assignment of new parts to the existing cells is proposed. A multi-layer backpropagation network with one hidden layer is used. Experimental results with varying number of neurons in hidden layer to evaluate the role of hidden neurons in the network learning performance are also presented. The comprehensive methodology developed in this article is appropriate for solving large-scale industrial applications without building the knowledge-based expert rule for the cellular manufacturing environment.

• Journal of IKEEE
• /
• v.2 no.1 s.2
• /
• pp.134-138
• /
• 1998

Because of the statistical fluctuations and the high 'time-variability' nature of the traffic, managing the resources of the network require highly dynamic techniques with minimal Intervention and reaction times, and adaptive and learning capabilities. The neural networks normalizes the ATM cell arrival rate and queue length and has the adaptive learning algorithm, and experimentally investigated the method to prevent the congestion generated in ATM networks.

• Journal of the Korean Society for Precision Engineering
• /
• v.32 no.5
• /
• pp.463-470
• /
• 2015

Solar cell is typical representative of renewable green energy. Silicon wafer contributes about 66 percent to its cost structure. In its manufacturing, micro-cracks are often occurred due to manufacturing process such as wire sawing, grinding and cleaning. Their detection and classification are important to process feedback information. In this paper, a classification method of micro-cracks is proposed, based on the fusion of principal component analysis(PCA) and neural network. The proposed method shows that it gives higher results than single application of two methods, in terms of shape and size classification of micro-cracks.

• Proceedings of the KIPE Conference
• /
• 1998.10a
• /
• pp.966-971
• /
• 1998

The studies on the photovoltaic system are extensively exhaustible and broadly available resourse as a future energy supply. In this paper, a new maximum power point tracker(MPPT) using neural network theory is proposed to improve energy conversion efficiency. The boost converter and neural network controller(NNC) were employed so that the operating point of solar cell was located at the Maximum Power Point. And the back propagation algorithm with one input layer of two inputs(E, CE) and output layer(cnntrol value) was applied to train a neural network. Simulation and experimental results show that the performance of NNC in MPPT of photovoltaic array is better than that of controller based upon the Hill Climbing Method.

• Journal of Communications and Networks
• /
• v.10 no.1
• /
• pp.38-43
• /
• 2008

In this paper, adaptive channel borrowing approach fuzzy neural networks for load balancing (ACB-FNN) is presented to maximized the number of served calls and the depending on asymmetries traffic load problem. In a wireless network, the call's arrival rate, the call duration and the communication overhead between the base station and the mobile switch center are vague and uncertain. A new load balancing algorithm with cell involved negotiation is also presented in this paper. The ACB-FNN exhibits better learning abilities, optimization abilities, robustness, and fault-tolerant capability thus yielding better performance compared with other algorithms. It aims to efficiently satisfy their diverse quality-of-service (QoS) requirements. The results show that our algorithm has lower blocking rate, lower dropping rate, less update overhead, and shorter channel acquisition delay than previous methods.