When travelling, people are accustomed to taking and uploading photos on social media websites, which has led to the accumulation of huge numbers of geotagged photos. Combined with multisource information (e.g. weather, transportation, or textual information), these geotagged photos could help us in constructing user preference profiles at a high level of detail. Therefore, using these geotagged photos, we built a personalised recommendation system to provide attraction recommendations that match a user's preferences. Specifically, we retrieved a geotagged photo collection from the public API for Flickr (Flickr.com) and fetched a large amount of other contextual information to rebuild a user's travel history. We then created a model-based recommendation method with a two-stage architecture that consists of candidate generation (the matching process) and candidate ranking. In the matching process, we used a support vector machine model that was modified for multiclass classification to generate the candidate list. In addition, we used a gradient boosting regression tree to score each candidate and rerank the list. Finally, we evaluated our recommendation results with respect to accuracy and ranking ability. Compared with widely used memory-based methods, our proposed method performs significantly better in the cold-start situation and when mining ‘long-tail’ data. 相似文献
Structural damage assessment under external loading, such as earthquake excitation, is an important issue in structural safety evaluation. In this regard, an appropriate data analysis and system identification technique is required to interpret the measured data and to identify the state of the structure. Generally, the recursive system identification algorithm is used. In this study, the recursive subspace identification (RSI) algorithm based on the matrix inversion lemma algorithm with oblique projection technique (RSI-Inversion-Oblique) is applied to investigate the time-varying dynamic characteristics. The user-defined parameters used in the RSI-Inversion-Oblique technique are carefully discussed, which include the size of the data Hankel matrix (i), model order to extract the physical modes, and forgetting factor (FF) to detect the time-varying system modal frequencies. Response data from the Northridge earthquake from the Sherman Oaks building (CSMIP) is used as an example to examine a systematic method to determine the suitable user-defined parameters in RSI. It is concluded that the number of rows in the data Hankel matrix significantly influences the identification of the time-varying fundamental modal frequency of the structure. An algorithmic model order selection method using the eigenvalue distribution of RSI-Inversion can detect the system modal frequencies at each appending data window without causing any abnormality. 相似文献
Aggregate disintegration is a critical process in soil splash erosion. However, the effect of soil organic carbon (SOC) and its fractions on soil aggregates disintegration is still not clear. In this study, five soils with similar clay contents and different contents of SOC have been used. The effects of slaking and mechanical striking on splash erosion were distinguished by using deionized water and 95% ethanol as raindrops. The simulated rainfall experiments were carried out in four heights (0.5, 1.0, 1.5 and 2.0 m). The result indicated that the soil aggregate stability increased with the increases of SOC and light fraction organic carbon (LFOC). The relative slaking and the mechanical striking index increased with the decreases of SOC and LFOC. The reduction of macroaggregates in eroded soil gradually decreased with the increase of SOC and LFOC, especially in alcohol test. The amount of macroaggregates (>0.25 mm) in deionized water tests were significantly less than that in alcohol tests under the same rainfall heights. The contribution of slaking to splash erosion increased with the decrease of heavy fractions organic carbon. The contribution of mechanical striking was dominant when the rainfall kinetic energy increased to a range of threshold between 9 J m−2 mm−1 and 12 m−2 mm−1. This study could provide the scientific basis for deeply understanding the mechanism of soil aggregates disintegration and splash erosion. 相似文献
The South China Sea continental margin in the Qiongdongnan Basin (QDNB) area has incrementally prograded since 10.5 Ma generating a margin sediment prism more than 4km-thick and 150–200 km wide above the well-dated T40 stratigraphic surface. Core and well log data, as well as clinoform morphology and growth patterns along 28 2D seismic reflection lines, illustrate the evolving architecture and margin morphology; through five main seismic-stratigraphic surfaces (T40, T30, T27, T20 and T0) frame 15 clinothems in the southwest that reduce over some 200 km to 8 clinoforms in the northeast. The overall margin geometry shows a remarkable change from sigmoidal, strongly progradational and aggradational in the west to weakly progradational in the east. Vertical sediment accumulation rate increased significantly across the entire margin after 2.4 Ma, with a marked increase in mud content in the succession. Furthermore, an estimate of sediment flux across successive clinoforms on each of the three selected seismic cross sections indicate an overall decrease in sediment discharge west to east, away from the Red River depocenter, as well as a decrease in the percentage of total discharge crossing the shelf break in this same direction. The QDNB Late Cenozoic continental margin growth, with its overall increased sediment flux, responded to the climate-induced, gradual cooling and falling global sea level during this icehouse period. 相似文献
In thermal-related engineering such as thermal energy structures and nuclear waste disposal, it is essential to well understand volume change and excess pore water pressure buildup of soils under thermal cycles. However, most existing thermo-mechanical models can merely simulate one heating–cooling cycle and fail in capturing accumulation phenomenon due to multiple thermal cycles. In this study, a two-surface elasto-plastic model considering thermal cyclic behavior is proposed. This model is based on the bounding surface plasticity and progressive plasticity by introducing two yield surfaces and two loading yield limits. A dependency law is proposed by linking two loading yield limits with a thermal accumulation parameter nc, allowing the thermal cyclic behavior to be taken into account. Parameter nc controls the evolution rate of the inner loading yield limit approaching the loading yield limit following a thermal loading path. By extending the thermo-hydro-mechanical equations into the elastic–plastic state, the excess pore water pressure buildup of soil due to thermal cycles is also accounted. Then, thermal cycle tests on four fine-grained soils (natural Boom clay, Geneva clay, Bonny silt, and reconstituted Pontida clay) under different OCRs and stresses are simulated and compared. The results show that the proposed model can well describe both strain accumulation phenomenon and excess pore water pressure buildup of fine-grained soils under the effect of thermal cycles.