Enhancing collaborative filtering by user interest expansion via personalized ranking

Recommender systems suggest a few items from many possible choices to the users by understanding their past behaviors. In these systems, the user behaviors are influenced by the hidden interests of the users. Learning to leverage the information about user interests is often critical for making better recommendations. However, existing collaborative-filtering-based recommender systems are usually focused on exploiting the information about the user's interaction with the systems; the information about latent user interests is largely underexplored. To that end, inspired by the topic models, in this paper, we propose a novel collaborative-filtering-based recommender system by user interest expansion via personalized ranking, named iExpand. The goal is to build an item-oriented model-based collaborative-filtering framework. The iExpand method introduces a three-layer, user-interests-item, representation scheme, which leads to more accurate ranking recommendation results with less computation cost and helps the understanding of the interactions among users, items, and user interests. Moreover, iExpand strategically deals with many issues that exist in traditional collaborative-filtering approaches, such as the overspecialization problem and the cold-start problem. Finally, we evaluate iExpand on three benchmark data sets, and experimental results show that iExpand can lead to better ranking performance than state-of-the-art methods with a significant margin.     

A low distortion image enhancement scheme based on multi-resolutions analysis in next generation network

With the advent of Next Generation Network (NGN), services that are currently provided by multiple specific network-centric architectures. NGN provides AAA (Anytime, Anywhere and Always on) access to users from different service providers with consistent and ubiquitous provision of services as necessary. This special issue of NGN includes pervasive, grid, and peer-to-peer computing to provide computing and communication services at anytime and anywhere. In fact, the application of NGN includes digital image processing, multimedia systems/services, and so on. Here we focus on the digital image processing technology in NGN environments. Low-contrast structure and heavy noise in NGN environments can be found in many kinds of digital images, which makes the images vague and uncertainly, especially in x-ray images. As result, some useful tiny characteristic are weakened—which are difficult to distinguish even by naked eyes. Based on the combination of no-linear grad-contrast operator and multi-resolution wavelet analysis, a kind of image enhancement processing algorithm for useful tiny characters is presented. The algorithm can enhance the tiny characters while confine amplifying noise. The analysis of the results shows that local regions of the image are enhanced by using the concept of the grad contrast to make image clearer adaptively. Experiments were conducted on real pictures, and the results show that the algorithm is flexible and convenient.     

Mining blackhole and volcano patterns in directed graphs: a general approach

Given a directed graph, the problem of blackhole mining is to identify groups of nodes, called blackhole patterns, in a way such that the average in-weight of this group is significantly larger than the average out-weight of the same group. The problem of finding volcano patterns is a dual problem of mining blackhole patterns. Therefore, we focus on discovering the blackhole patterns. Indeed, in this article, we develop a generalized blackhole mining framework. Specifically, we first design two pruning schemes for reducing the computational cost by reducing both the number of candidate patterns and the average computation cost for each candidate pattern. The first pruning scheme is to exploit the concept of combination dominance to reduce the exponential growth search space. Based on this pruning approach, we develop the gBlackhole algorithm. Instead, the second pruning scheme is an approximate approach, named approxBlackhole, which can strike a balance between the efficiency and the completeness of blackhole mining. Finally, experimental results on real-world data show that the performance of approxBlackhole can be several orders of magnitude faster than gBlackhole, and both of them have huge computational advantages over the brute-force approach. Also, we show that the blackhole mining algorithm can be used to capture some suspicious financial fraud patterns.     

Enhanced Photoelectrochemical Performance of Hematite Photoanode by Decorating NiCoP Nanoparticles Through a Facile Spin Coating Method

Catalysis Letters - Hematite (α-Fe2O3) is a potential photoanode material for photoelectrochemical (PEC) water splitting, but its short hole diffusion length and low water oxidation kinetics...     

旅游管理专业研究生《地理信息系统》课程教学改革探讨

在智慧旅游时代,掌握GIS基础理论知识和技术技能对于旅游专业学生来说非常重要.本文从旅游管理研究生GIS课程目标发出,结合实践教学经验,分析了该课程在教学过程中存在的一些问题,从教学内容、教学方法和考核方式三个方面提出切实可行的GIS课程教学改革建议,以提升课程教学质量和研究生的科研素质.     

玻纤增强复合材料及其复合绝缘横担覆冰特性研究

为了指导复合材料横担在重冰区的应用,本文开展了玻纤增强复合材料及复合材料绝缘横担的覆冰特性研究.结果表明:空白样品在垂直悬挂方式下的覆冰量和冰闪络电压均优于水平悬挂样品,且覆冰量均少于对应的亲水性的纯铝棒和Q345钢棒;涂覆PRTV涂料的复合材料样品覆冰量比空白样品少,对应的闪络电压大幅提升,且对应样品的冰面粘附力值最小,为纯铝棒冰面粘附力值的19％,而空白样品的冰面粘附力值为纯铝棒的78％.硅橡胶复合绝缘横担的覆冰特性正好和复合材料试样相反,水平悬挂方式下复合绝缘横担覆冰量相比垂直悬挂的同规格复合绝缘子减少了30％,闪络电压提高了51％.     

模具敏捷制造系统研究

针对模具设计制造过程复杂、条件苛刻和单件或小批量生产的特点 ,论述了模具产业发展敏捷制造技术的必要性。提出了模具敏捷制造系统框架和基于STEP与特征技术实现信息集成与过程集成的运行机制。阐述了基于Internet/Intranet的开放式可视化协同工作平台的模具敏捷制造实施方案。     

Effect of supports on the redox performance of pyrite cinder in chemical looping combustion

Chemical looping combustion (CLC) is a clean and efficient flame-free combustion technology,which combust the fuels by lattice oxygen from a solid oxygen carrier with inherent CO2 capture.The develop-ment of oxygen carriers with low cost and high redox performance is crucial to the whole efficiency of CLC process.As the solid by-product from the sulfuric acid production,pyrite cinder presented excellent redox performance as an oxygen carrier in CLC process.The main components in pyrite cinder are Fe2O3,CaSO4,Al2O3 and SiO2 in which Fe2O3 is the active component to provide lattice oxygen.In order to sys-tematic investigate the functions of supports (CaSO4,Al2O3 and SiO2) in pyrite cinder,three oxygen car-riers (Fe2O3-CaSO4,Fe2O3-Al2O3 and Fe2O3-SiO2) were prepared and evaluated in this study.The results showed that Fe2O3-CaSO4 displayed high redox activity and cycling stability in the multiple redox cycles.However,both Fe2O3-Al2O3 and Fe2O3-SiO2 experienced serious deactivation during redox reactions.It indicated that the inert Fe-Si solid solution (Fe2SiO4) was formed in the spent Fe2O3-SiO2 sample,which decreased the oxygen carrying capacity of this sample.The XPS results showed that the oxygen species on the surface of Fe2O3-CaSO4 could be fully recovered after the 20 redox cycles.It can be concluded that CaSO4 is the key to the high redox activity and cycling stability of pyrite cinder.     

PAN/FPU Composite Nanofiber Membrane with Superhydrophobic and Superoleophobic Surface as a Filter Element for High-Efficiency Protective Masks

Recently, because of the outbreak of COVID-19, the demand for various types of filter elements in protective materials has increased globally. Furthermore, new requirements for the filtration performance of PM2.5 liquid (oil) particles have been put forward. In this work, Superhydrophobic and superoleophobic composite nanofibers with excellent filtration capacity for oil and salt particles are developed through the modification of polyacrylonitrile (PAN) by fluoro-polyurethane (FPU) doping. The results show that the PAN/FPU composite nanofibers doped with 9 wt% FPU has a uniform fiber morphology with a diameter of 240 ± 30 nm. Compared to the pure PAN nanofibers, the water-based contact angle of PAN/FPU increases from 90 ± 5° to 151 ± 5°, and the oil-based contact angle increases from 58 ± 2° to 152 ± 3°. Importantly, at a high flow rate of 95 L min⁻¹, the filtration efficiency of the PAN/FPU nanofiber membrane for 0.3 µm oil particles increases from 92 ± 1% to 99.2 ± 0.1%. After cyclic loading, the filtration efficiency of 0.3 µm oil particles remains above 98%. Meanwhile, the filtration efficiency for 0.3 µm salt particles remains at 98.23 ± 0.1%. The PAN/FPU nanofiber membrane developed in this work is effective in applications and has good market prospects as a protective filtration material.