Real-time molecular characterization of air pollutants in a Hong Kong residence: Implication of indoor source emissions and heterogeneous chemistry

Due to the high health risks associated with indoor air pollutants and long-term exposure, indoor air quality has received increasing attention. In this study, we put emphasis on the molecular composition, source emissions, and chemical aging of air pollutants in a residence with designed activities mimicking ordinary Hong Kong homes. More than 150 air pollutants were detected at molecular level, 87 of which were quantified at a time resolution of not less than 1 hour. The indoor-to-outdoor ratios were higher than 1 for most of the primary air pollutants, due to emissions of indoor activities and indoor backgrounds (especially for aldehydes). In contrast, many secondary air pollutants exhibited higher concentrations in outdoor air. Painting ranked first in aldehyde emissions, which also caused great enhancement of aromatics. Incense burning had the highest emissions of particle-phase organics, with vanillic acid and syringic acid as markers. The other noteworthy fingerprints enabled by online measurements included linoleic acid, cholesterol, and oleic acid for cooking, 2,5-dimethylfuran, stigmasterol, iso-/anteiso-alkanes, and fructose isomers for smoking, C₂₈-C₃₄ even n-alkanes for candle burning, and monoterpenes for the use of air freshener, cleaning agents, and camphor oil. We showed clear evidence of chemical aging of cooking emissions, giving a hint of indoor heterogeneous chemistry. This study highlights the value of organic molecules measured at high time resolutions in enhancing our knowledge on indoor air quality.     

石英砂加载混凝工艺的DOM去除特征与混凝机理

为处理未纳入管网的市政污水,采用石英砂加载混凝工艺,考察石英砂的粒径及其投加量对处理效能的影响,分析了溶解性有机物(dissolved organic matters,DOM)的去除特征,并探讨了石英砂加载混凝机理。结果表明,与常规混凝相比,当石英砂的粒径和投加量分别为200目和 1.0 mg/L 时,石英砂加载混凝工艺对污水中浊度、COD的去除率分别为97.55%、59.2%,优于常规混凝;石英砂加载混凝工艺可明显去除芳香类、共轭双键、疏水性有机物,主要促进了腐殖质类物质的削减;石英砂通过架桥作用增加了絮体的密度,进而显著改善了絮体的沉降性能、强度;絮体的沉降性能、强度及再稳性能随着石英砂粒径的降低而升高。     

RAFNet: RGB-D attention feature fusion network for indoor semantic segmentation

Semantic segmentation based on the complementary information from RGB and depth images has recently gained great popularity, but due to the difference between RGB and depth maps, how to effectively use RGB-D information is still a problem. In this paper, we propose a novel RGB-D semantic segmentation network named RAFNet, which can selectively gather features from the RGB and depth information. Specifically, we construct an architecture with three parallel branches and propose several complementary attention modules. This structure enables a fusion branch and we add the Bi-directional Multi-step Propagation (BMP) strategy to it, which can not only retain the feature streams of the original RGB and depth branches but also fully utilize the feature flow of the fusion branch. There are three kinds of complementary attention modules that we have constructed. The RGB-D fusion module can effectively extract important features from the RGB and depth branch streams. The refinement module can reduce the loss of semantic information and the context aggregation module can help propagate and integrate information better. We train and evaluate our model on NYUDv2 and SUN-RGBD datasets, and prove that our model achieves state-of-the-art performances.     

碳质金矿中碳质物及其“劫金”机理研究进展

碳质金矿是重要的难处理金矿资源之一,碳质物“劫金”是金浸出率低下的主要原因。碳质物组分复杂,不同组分的碳质物的“劫金”能力和“劫金”行为存在差异,磨矿和浸出环节对碳质物的“劫金”能力也会产生影响,这些因素均能直接影响金的浸出率。通过系统总结碳质金矿中碳质物在组成特征、“劫金”机理及“劫金”能力的影响因素等方面的研究进展,对碳质物“劫金”机理现有研究工作的不足及未来研究方向进行了探讨,为碳质金矿碳质物劫金机理及预处理工艺的研究提供了重要参考。     

新型组合工艺对微污染原水中有机污染物和消毒副产物前体物的去除

本采用中试试验装置研究了生物陶粒过滤一微絮凝砂滤一活性炭吸附组合工艺，对微污染原水中有机污染物和消毒副产物前体物的去除效果。在原水UV254为0．047～0．065cm^-1，DOC为2．70～4．10mg／L，TOC为3．50～5．00mg／L的条件下，组合工艺对UV254，DOC、TOC平均去除率分别为98．4％、74．1％、69．2％。色-质联机分析结果表明，经组合工艺处理水中有机物由54种降至25种。组合工艺出水中三卤甲烷总含量不及常规工艺出水中该物质含量的五分之一。组合工艺能有效控制和消除水中有机物的污染，提供安全的优质饮用水。     

基于卷积块注意力模块的图像描述生成模型

图像描述生成模型是使用自然语言描述图片的内容及其属性之间关系的算法模型.对现有模型描述质量不高、图片重要部分特征提取不足和模型过于复杂的问题进行了研究,提出了一种基于卷积块注意力机制模块(CBAM)的图像描述生成模型.该模型采用编码器-解码器结构,在特征提取网络Inception-v4中加入CBAM,并作为编码器提取图片的重要特征信息,将其送入解码器长短期记忆网络(LSTM)中,生成对应图片的描述语句.采用MSCOCO2014数据集中训练集和验证集进行训练和测试,使用多个评价准则评估模型的准确性.实验结果表明,改进后模型的评价准则得分优于其他模型,其中Model2实验能够更好地提取到图像特征,生成更加准确的描述.     

A novel deep learning prediction model for concrete dam displacements using interpretable mixed attention mechanism

Dam displacements can effectively reflect its operational status, and thus establishing a reliable displacement prediction model is important for dam health monitoring. The majority of the existing data-driven models, however, focus on static regression relationships, which cannot capture the long-term temporal dependencies and adaptively select the most relevant influencing factors to perform predictions. Moreover, the emerging modeling tools such as machine learning (ML) and deep learning (DL) are mostly black-box models, which makes their physical interpretation challenging and greatly limits their practical engineering applications. To address these issues, this paper proposes an interpretable mixed attention mechanism long short-term memory (MAM-LSTM) model based on an encoder-decoder architecture, which is formulated in two stages. In the encoder stage, a factor attention mechanism is developed to adaptively select the highly influential factors at each time step by referring to the previous hidden state. In the decoder stage, a temporal attention mechanism is introduced to properly extract the key time segments by identifying the relevant hidden states across all the time steps. For interpretation purpose, our emphasis is placed on the quantification and visualization of factor and temporal attention weights. Finally, the effectiveness of the proposed model is verified using monitoring data collected from a real-world dam, where its accuracy is compared to a classical statistical model, conventional ML models, and homogeneous DL models. The comparison demonstrates that the MAM-LSTM model outperforms the other models in most cases. Furthermore, the interpretation of global attention weights confirms the physical rationality of our attention-based model. This work addresses the research gap in interpretable artificial intelligence for dam displacement prediction and delivers a model with both high-accuracy and interpretability.     

基于注意力的热点块和显著像素卷积神经网络的人脸防伪方法

人脸防伪用于验证被测试者是否为真实活体,是计算机视觉领域的一个研究热点。攻击手段的多样性以及人脸识别主要在嵌入式、移动式等不具备高计算能力的设备上应用,使得快速有效的人脸防伪计算成为具有挑战性的任务。针对该问题,文中提出了一种基于注意力的热点块和显著像素卷积神经网络的方法。其中,热点块机制以对5个热点块的判别来取代对整张人脸的判别,显著降低了计算量,迫使网络模型集中关注更具有鉴别信息的热点块,提高了网络模型的准确率;显著像素方法对输入的人脸图像进行显著像素预测,通过判断显著预测图是否符合人脸的深度特性来鉴别活体与攻击。该方法将热点块与显著像素的结果进行融合,充分发挥了局部特征和全局特征的作用,进一步提升了人脸防伪的效果。与现有方法相比,所提方法在CASIA-MFSD、Replay-Attack以及SiW数据集上都达到了很好的效果。