“…In this case increasing hidden layer can improve the prediction result. we make comparison with another paper which the prediction result is 64% [10]. In addition, in this paper we calculate the output of prediction for 7 types of secondary structure.…”
Section: Resultsmentioning
confidence: 99%
“…In addition, in this paper we calculate the output of prediction for 7 types of secondary structure. Meanwhile in another paper [3,9,10] use 3 types, there are Helix, Beta strand and Coil. Althought prediction of 7 types of secondary structure is more difficult, but the ANN still can predict for this problem.…”
Section: Resultsmentioning
confidence: 99%
“…In this problem, we use ANN as classification and recognition methods. Some calculation using ANN for Secondary structure prediction can be found in some papers [1,2,3,4,5,6,7,8,9,10,11].…”
Abstract. Some proteins in blue copper proteins have similar properties. In some cases it is not easy to distinguish the proteins each other. The study to recognize and classify in blue copper proteins has important roles to recognize the difference of similar properties, for examples, structures and residue sequences in blue copper proteins. There are many methods being developed to predict protein structure from many approachs, which one still not satisfactory yet. Therefore it is a challenge for scientists to develop or improve their methods. One of promising method is artificial neural networks (ANN). ANN is learning machine methods consisted of input, hidden and output layer. ANN is tested to recognize secondary structure in blue copper protein. It is found that ANN can distinguish for 7-type of secondary structure and recognize 72% secondary structure in blue copper protein.
“…In this case increasing hidden layer can improve the prediction result. we make comparison with another paper which the prediction result is 64% [10]. In addition, in this paper we calculate the output of prediction for 7 types of secondary structure.…”
Section: Resultsmentioning
confidence: 99%
“…In addition, in this paper we calculate the output of prediction for 7 types of secondary structure. Meanwhile in another paper [3,9,10] use 3 types, there are Helix, Beta strand and Coil. Althought prediction of 7 types of secondary structure is more difficult, but the ANN still can predict for this problem.…”
Section: Resultsmentioning
confidence: 99%
“…In this problem, we use ANN as classification and recognition methods. Some calculation using ANN for Secondary structure prediction can be found in some papers [1,2,3,4,5,6,7,8,9,10,11].…”
Abstract. Some proteins in blue copper proteins have similar properties. In some cases it is not easy to distinguish the proteins each other. The study to recognize and classify in blue copper proteins has important roles to recognize the difference of similar properties, for examples, structures and residue sequences in blue copper proteins. There are many methods being developed to predict protein structure from many approachs, which one still not satisfactory yet. Therefore it is a challenge for scientists to develop or improve their methods. One of promising method is artificial neural networks (ANN). ANN is learning machine methods consisted of input, hidden and output layer. ANN is tested to recognize secondary structure in blue copper protein. It is found that ANN can distinguish for 7-type of secondary structure and recognize 72% secondary structure in blue copper protein.
“…Analogy based approaches are referred to as the nearestneighbor algorithm (Levin et al, 1986;Nishikawa and Ooi, 1986;Salzberg and Cost, 1992;Zhang et al, 1992;Geourjon and Deleage, 1994;Yi and Lander, 1994;Salamov and Solovyev, 1995). The core of all these procedures is the definition of similarity, just as in the fold recognition methods.…”
“…This is a 3-class classification task which consists in assigning a conformation α-helix, β-strand or coil, to each residue of a sequence. The classifiers used are the neural architecture and statistical model in [4], with the nearest-neighbours algorithm of [10]. We have compared our optimal solution to other combiners: a single hidden layer neural network (MLP), a logistic regression model and an optimal convex combination.…”
Abstract. We consider the combination of the outputs of several classifiers trained independently for the same discrimination task. We introduce new results which provide optimal solutions in the case of linear combinations. We compare our solutions to existing ensemble methods and characterize situations where our approach should be preferred.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.