Transportation system has time-varying, coupling and nonlinear dynamic characteristics. Traffic flow forecast
is one of the key technologies of traffic guidance. It is very difficult to accurately forecast them effectively. This paper has
analyzed the complexity and the evaluation index of urban transportation network and has proposed the forecasting model
of the hybrid algorithm based on chaos immune knowledge. First of all, the chaos knowledge is introduced into the topology
structure of immune network, so as to obtain the matching predictive values and knowledge base. Secondly, this algorithm
can dynamically control and adjusted the regional search speed and can fuse the information obtained by the chaos
and immune algorithm, in order to realize the short-term traffic flow forecast. Finally, the simulation experiment shows
that the traffic flow forecasting error obtained by the method is small, feasible and effective and can better meet the needs
of the traffic guidance system.
Serious feature heterogeneity and semantic gaps exist between multi-source heterogeneous data, and existing cross-modal retrieval methods cannot effectively extract common semantic and complementary information between multi-source heterogeneous data. In this regard, an adversarial cross-modal retrieval method that fuses collaborative attention networks is proposed. The method addresses two major challenges in the cross-modal retrieval process, firstly, an information extraction algorithm based on the cooperative attention mechanism is designed, and secondly, the cooperative attention network is combined with the adversarial subspace learning algorithm to enhance the complementary capability of information in the feature subspace. The experimental results show that the proposed method has better retrieval results than similar cross-modal retrieval methods in terms of MAP metrics.
Recently, digital image inpainting technique based on variational and partial differential equation has been researched widely. In this paper, image inpainting is applied to image encoding and a novel scheme of encoding is proposed. In the encoding, applying an edge detector to detect the edge. In addition, the four boundaries of the image also belong to the edge collection; next, generating small neighborhoods of the edge collection to get an edge-extended image, then encoding the addresses of the edge-extended image and using high bit rate to accurately code the gray values of it. So, a high compression rate is achieved. Unlike the traditional decoding, here the decoding is realized by a harmonic inpainting model to achieve a good quality of reconstructed image. At the end, a lot of images are simulated. These simulated results show that with this scheme proposed, one can get a good quality of reconstructed image in a high compression rate.
Keywords-image encodingt;image decoding; image inpaintingI.
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.