Building a model-based personalised recommendation approach for tourist attractions from geotagged social media data

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.     

Particle trajectories of nonlinear gravity waves in deep water

The paper presents a numerical method for calculating the particle trajectories of nonlinear gravity waves in deep water. Particle trajectories, mass-transport velocity and Lagrangian wave period can be accurately determined by the proposed method. The high success rate of the proposed method is examined by comparing the present results with those of (a) Longuet-Higgins, M.S., 1986, 1987. Eulerian and Lagrangian aspects of surface waves. Journal of Fluid Mechanics 173, 683-707 and (b) Lagrangian moments and mass transport in Stokes waves. Journal of Fluid Mechanics 179, 547-555. It is shown that the dimensionless mass-transport velocity can exceed 10% for large waves, and the Lagrangian wave period is much larger than the Eulerian wave period for large waves.     

矢量数据栅格化的一种有效方法——环绕数法

矢量数据栅格化是GIS数据处理的一项重要任务。目前,已存在多种栅格化方法,但是每种方法都有各自的局限性。本文首次提出了环绕数法,它基于计算几何转角理论,通过计算跨越数来确定环绕数,是一种简单、高效、易于实现的栅格化方法。应用环绕数法,不但可以完成简单多边形的栅格化,而且可以完成自交多边形的栅格化。     

Verification of significant wave representation method

The significant wave representation method is the simplest method for computing the transformation of significant wave height across-shore. However, many engineers are reluctant to use this method because many researchers have pointed out that the method possibly contains a large estimation error. Nevertheless, Rattanapitikon et al. [Rattanapitikon, W., Karunchintadit, R., Shibayama, T., 2003. Irregular wave height transformation using representative wave approach. Coastal Engineering Journal, JSCE 45(3), 489–510.] showed that the wave representation method could be used to compute the transformation of root mean square wave heights. It may also be possible to use it for computing the significant wave height transformation. Therefore, this study was carried out to examine the possibility of simulating significant wave height transformation across-shore by using the significant wave representation method. Laboratory data from small- and large-scale wave flumes were used to calibrate and examine the models. Six regular wave models were applied directly to irregular waves by using the significant wave height and spectral peak period. The examination showed that three regular wave models (with new coefficients) could be used to compute the significant wave height transformation with very good accuracy. On the strength of both accuracy and simplicity of the three models, a suitable model is recommended for computing the significant wave height transformation. The suitable model was also modified for better predictions. The modified model (with different coefficients) can be used to compute either regular wave height or significant wave height transformation across-shore.     

Introduction: Interaction between environment and fisheries—The role of stakeholder participation

This paper is an introduction to the special issue on a role of participation in dealing with the interactions between environment and fisheries. In this introduction, we explore the recent discussion on the ecosystem-based approach to fisheries management (EBAFM) and extract important points for implementation of EBAFM from the social science literature on participation and participatory processes in environmental management. The introduction finishes by describing the analytical framework for studying participatory processes.     

A protocol for classifying ecologically relevant marine zones,a statistical approach

Mapping ecologically relevant zones in the marine environment has become increasingly important. Biological data are however often scarce and alternatives are being sought in optimal classifications of abiotic variables. The concept of ‘marine landscapes’ is based on a hierarchical classification of geological, hydrographic and other physical data. This approach is however subject to many assumptions and subjective decisions.     

Arctic sea-ice motion and its relation to pressure field

Daily Arctic sea-ice motion maps during the winter seasons (December–March) from December 1988 to March 2003 derived from NSCAT, QuikSCAT, SSM/I, and AMSRE data by a wavelet analysis method have been merged with those derived from buoy data. These merged sea-ice motion data have been used to study the circulation regimes and winter-to-winter variability of Arctic sea-ice motion. The relation between sea-ice motion and the pressure field in the Arctic Ocean was also studied by applying Principal Component Analysis (PCA) to the monthly merged sea-ice motion data and the monthly pressure field data from IABP. The mean Arctic sea-ice motion map of the 15 winter seasons has two distinct features: the Beaufort Gyre and a cyclonic circulation system in the Eurasian Basin, which moves ice from the Laptev Sea to Fram Strait. The strengths and sizes of the two features change from one winter season to another. Seasons with a strong or normal Beaufort Gyre alternate with seasons with a weak or no Beaufort Gyre every one to three seasons. The principal components of the first two modes of PCA of the monthly sea-ice motion are closely correlated with their counterparts of the monthly pressure field in the Arctic Ocean. The mode-one components of these two anomalies alternate between anticyclonic and cyclonic circulation systems. The correlation between Arctic Oscillation indexes and the principal components of the first mode of PCA of the monthly Arctic sea-ice motion is low but statistically significant.     

基于神经-模糊方法的单料烟感官质量评价专家系统

作者通过对单料烟评吸的结果与理化测定的指标参数进行分析 ,结合专家经验并采用神经 -模糊方法 ,提出一种基于单料烟的理化指标对各感官参数进行分类、分级 ,建造单料烟感官质量评价专家系统的方法。实验表明 ,该系统具有学习与知识提取能力 ,在卷烟产品质量管理新产品开发中具有指导意义     

极端波浪条件下黏土质斜坡海床稳定性解析

海洋资源开发引起海底软黏土的结构性破坏,导致土体强度弱化,在百年一遇的极端波浪作用时极易发生斜坡海床的局部失稳甚至大范围海底滑坡,给海洋工程建设和正常运营带来严重影响。目前,主要采用极限平衡法评价这类海底斜坡,但该法只能给出近似解。基于极限分析上限方法,推导了极端波浪诱发的波压力对斜坡海床的做功功率,建立了外力功与内能耗散率平衡方程;利用最优化方法,结合数值积分和强度折减技术,求解了不同时刻的斜坡海床稳定性系数,并针对扰动后的斜坡海床开展了有限元解的对比验证。在此基础上,深入探讨了不同波浪参数(波长、波高和水深)和坡长小于一个波长等极端条件下的海底斜坡稳定性。     

冲绳海槽热液柱动力过程的数值模拟

本文以冲绳海槽伊平屋北部热液区(126o53.80′,27o45.50′)的现场水文数据作为背景条件,使用k-ε湍流模型模拟热液柱的动力过程。模拟计算得到的羽流速度、温度和湍流耗散率等基本物理量展现了热液柱的时空演化过程。模拟结果显示,羽流最大上升高度及中性浮力面高度与海底的距离分别为83.62m和68.97m,和2014年先导专项在此附近热液区所观测的温度异常和盐度异常的深度位置(离海底约66—86m)接近。羽流的上升速度满足高斯分布,其半径b与距喷口高度z-H成正比:b=0.0985(z-H),其中z为距海底高度,H为热液烟囱体的高度。羽流的最大体积通量比喷口的初始值增加了878倍,达1.034m~3/s;在中性浮力面位置附近,动量通量达到最大值,为0.156m~4/s~2,比初始值增加了882倍;浮力通量在中性浮力面以下和BM2000(Bloomfield et al,2000)理论模型符合良好,在中性浮力面以上则呈现随高度先增加后减小的特征。本文计算得到的平均卷挟率为α≈0.0807,与背景流较弱的热液区的声学现场观测结果相符。