Traffic-data recovery plays an important role in traffic prediction, congestion judgment, road network planning and other fields. Complete and accurate traffic data help to find the laws contained in the data more efficiently and effectively. However, existing methods still have problems to cope with the case when large amounts of traffic data are missed. As a generalization of vector algebra, geometric algebra has more powerful representation and processing capability for high-dimensional data. In this article, we are thus inspired to propose the geometric-algebra-based generative adversarial network to repair the missing traffic data by learning the correlation of multidimensional traffic parameters. The generator of the proposed model consists of a geometric algebra convolution module, an attention module and a deconvolution module. Global and local data mean squared errors are simultaneously applied to form the loss function of the generator. The discriminator is composed of a multichannel convolutional neural network which can continuously optimize the adversarial training process. Real traffic data from two elevated highways are used for experimental verification. Experimental results demonstrate that our method can effectively repair missing traffic data in a robust way and has better performance when compared with the state-of-the-art methods.

No abstract

In consideration of the important influence of the season change on the temperature difference, the poor thermal inertia of non-thermal insulation walls and the inflammableness of organic thermal insulation walls, it is designed to prepare the phase-change material into the phase-change mortar applied to the exterior of the building walls so as to improve the thermal inertia of the wall in summer. The phase-change material, taking the lowest eutectic mixture mainly formed with lauric acid and myristic acid, hereinafter referred to as 'fatty acid', as the main of phase-change material, and the expanded perlite as the inorganic carrier, is prepared into a phase-change aggregate by way of absorption, through encapsulating the aggregate, the optimal process parameters are then determined. The phase-change mortar with the phase-change perlite aggregate is prepared, and simulation test on the thermal performance of the temperature control is conducted. Laboratory results indicate that, the expanded perlite absorbs 200% fatty acid by way of vacuum absorption method, and is encapsulated by 67% polyurethane resin, and then becomes a stable phase-change perlite aggregate. Phase-change perlite-based mortar can achieve better temperature control effect, additionally, the increasing of the dosage of the fatty acid, the decreasing of the effective caloric value will become faster, and the longer the temperature delaying time as well as the greater the temperature dropping amplitude, meaning that the effect of controlling the temperature becomes more outstanding. IntroductionThe improvement on thermal inertia of buildings is an important task in the fields of construction and energy. At present, most studies are based on thermal energy storage material. However, there also exist a series of problems, such as high costs of sensible heat of stone, large size and temperature fluctuations during heat accumulation. Prevalent organic insulation wallboards are flammable; therefore, PCMs have been applied in the research and development of Latent Thermal Energy Storage. 1-3 Phase-change material has optimum phase-transition temperature, large phase-change latent heat and stable physico-chemical properties. 4-6 Solid-liquid phase change material has owned comparatively mature technology but the defect of flowing as well; so, in order to eliminate leaks, it should be encapsulated before combining with base materials in practical use 7 .Researchers have conducted studies on the thermal analysis of phase-change mortar and phase-change aggregate. Neeper 8 investigated the optimal parameters of phrase-change wallboards using a one-dimensional model and evaluated the benefit from heating and cooling system of construction products. But the results from this numerical analysis are not completely reliable by themselves. Sari et al. 9 prepared a phrasechange aggregate with good thermal stability from expanded perlite which absorbed 150% lauric acid. But its stability in alkali surroundings has seldom been studied, with domestic test standards fo...