Papers by Keyword: Kohonen Neural Network

Abstract: The paper proposes a Kohonen neural network to the MOA fault diagnosis. The data from MOA monitoring was trained by a Kohonen neural network in Matlab. By this way, the best weight matrix could be obtained. The trained Kohonen neural network is adopted to diagnose the sample, and the MOA fault type could be effectively identified.

Abstract: Based directly on the neural network weights from testing and evaluating the coatings on real vehicle equipment, by inputting the values of the EIS characteristic parameter received from the real vehicle testing, memorizing the neural network weights under guideless training, it provides a quick and convenient method to evaluate the protective performance of vehicle equipment coatings, and thus the quick testing of the corrosion severity of vehicle equipment can be achieved.

Abstract: This paper presents a new distance calculation circuit (DCC) that in artificial neural networks is used to calculate distances between vectors of signals. The proposed circuit is a digital, fully parallel and asynchronous solution. The complexity of the circuit strongly depends on the type of the distance measure. Considering two popular measures i.e. the Euclidean (L2) and the Manhattan (L1) one, it is shown that in the L2 case the number of transistors is even ten times larger than in the L1 case. Investigations carried out on the system level show that the L1 measure is a good estimate of the L2 one. For the L1 measure, for an example case of 4 inputs, for 10 bits of resolution of the signals, the number of transistors is equal to c. 2500. As transistors of minimum sizes can be used, the chip area of a single DCC, if realized in the CMOS 180 nm technology, is less than 0.015 mm².

Abstract: Sensory analysis has an important impact on food production since its results can help the understanding of consumers’ perceptions about the products. Thus, many methods have been proposed and applied to quantify sensory attributes of food products. In this paper we proposed a methodology, using Kohonen's Self-Organizing Maps and K-means algorithm, to classify food samples through the responses, provided by human evaluators, for their attributes such as aroma, flavor, appearance and texture. Conducted experiments in sensory analysis to determine the acceptance of new gelatins produced from chicken feet and new wines produced from spares of Açaí and Cajá confirm that proposed methodology is suitable for the investigated purpose.

Abstract: Sensorial qualities of fruit wines were compared by clustering due artificial neural networks. A Kohonen network has been used as a software tool in order to increase the human skills in this kind of application. Seven wine samples were used in this work, which the five samples were of Barbados cherry wine, one sample of peach wine and one sample of grape wine. 50 consumers chosen to perhaps had been used to obtain the sensorial data using a hedonic scale of 1-9 times. Sensorial values of flavor, aroma and appearance obtained of the hedonic dating were compared. Results showed that Kohonen network classified the Barbados cherry wines in distinct group, for frequency among yours sensorial responses. Kohonen network results were similar or better than statistical classification, this shows that the use of Kohonen algorithm in the sensorial analysis of wines is valid. Kohonen algorithm is very good in clustering of Barbados cherry wine samples and it uses in sensorial analyses of wines is promises.

Abstract: Photolithography is usually the bottleneck process with the most expensive equipment in a semiconductor wafer fabrication system. To improve the performances of the photolithography area with dynamic combination rules, a method of Kohonen neural network (KNN)–based performance improvements is proposed. First, a dynamic scheduling framework based on a KNN model and scheduling rules is proposed. A KNN-based sample learning algorithm for improving the performances is presented. Finally, to demonstrate the validity and feasibility of the proposed method, data from a real wafer fabrication system are used to simulate the proposed method. Results of simulation experiments indicate that the proposed method can be used to improve a complex wafer photolithography performance.