In optical interferometers, fringe projection systems, and synthetic aperture radars, fringe patterns are common outcomes and usually degraded by unavoidable noises. The presence of noises makes the phase extraction and phase unwrapping challenging. Windowed Fourier transform (WFT) based algorithms have been proven to be effective for fringe pattern analysis to various applications. However, the WFT-based algorithms are computationally expensive, prohibiting them from real-time applications. In this paper, we propose a fast parallel WFT-based library using graphics processing units and computer unified device architecture. Real-time WFT-based algorithms are achieved with 4 frames per second in processing 256x256 fringe patterns. Up to 132x speedup is obtained for WFT-based algorithms using NVIDIA GTX295 graphics card than sequential C in quad-core 2.5GHz Intel(R)Xeon(R) CPU E5420.
Splice sites play a very important role for identification of coding regions from DNA sequences of eukaryotic genomes. This paper proposes, a novelty Machine Learning approach to the detection of splice site location in DNA sequences. The method is based on a hybrid of a Markov model and neural networks where parameters of the Markov model are learned by neural networks. Our proposed model is trained using a backpropagation algorithm. The experiments in the data set of Rogic show that this model performs well that 86% of acceptor sites and 89% of donor sites are correctly found. These results demonstrate the potential use of our approach.
Abstract.This paper describes a new algorithm for planing with incomplete information and conflicts. The given planing problem has two optimazation criteria: maximize the utility and minimize the conflicts of the plan. In order to achieve the first optimization goal by utility with incomplete data we build a clustering algorithm based on a fuzzy comparison method for intervals. To minimize the.conflicts while keeping a light utility, we apply genetic algorithm. The experiments show that a good balance is achieved by using a dual algorithm with a flexible order of maximizing utility and minimizing conflicts.
GI61 THI¥UBai toan l~p ke hoach 111. bai toan kinh di~n diro'c S\!' quan tam d~c bi~t b&i cac ling dung rgng rai cua no. Trong moi trirong ba:t dinh, bai toan l~p ke hoach cho so lo n cac heat dgng yeu diu phai xu: If t5i U'U vo i thOng tin khOng d'ay du, tr anh xung dgt giira cac heat dgng, dtng tho'i phai giai quyet va:n de bung n5 t5 ho'p. Day la muc tieu ra:t kho thuc hien, Bai nay dira ra each giai quyet bai toan l~p ke hoach cac heat di;mg khong ro ket qua. V&i nhirng tham s5 d'au vao d~c trtrng cho m6i hoat d9ng 111. t~p gia tri mer, t~p cac hoat di?ng xung d9t, chung toi sU' dung thu~t toan kep M tim nghiern t5i U'U, dtng thoi tranh xung d9t nh~m dern lai di? thuan lo'i cao nha:t cho ke hoach.Cac ke't qui thirc nghiern thu diro'c cho tha:y tho'i gian thirc hi~n cu a phirong ph ap ttro'ng d5i ngh va cha:t hrong cii a ke hoach kha tot.2. BAI ToAN L~P KE HO~eH eHO cAe HO~T DQNG KHONG RO KET QuA 2.1. P'hat bi~u ba! toan Tjr mi?t t~p cac heat di?ng ma m6i heat di?ng d~c trtrng b&i bOn yeu to: + Di? U1l tien ve tho'i gian xay ra.+ Dg Ich lei rieng ciia tirng hoat dgng.(Di? ich lqi rieng cua mi?t heat di?ng la chi 55 ich lo'i no mang cho toan b9 ke hoach, chira tinh den cac yeu t5 xung
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.