Enhanced PMF Model to Predict User Interest for Web API Recommendation

Many methods focus solely on the relationship between the API and the user and fail to capture their contextual value. Because of this, they could not get better accuracy. The accuracy of the API recommendation can be improved by considering the effect of API contextual information on their latent attribute and the effect of the user time factor on the latent attribute of the user through the deep learning-based matrix factorization method (DL-PMF). In this chapter, a CNN (convolutional neural network) with an attention mechanism for the hidden features of web API elements and an LSTM (long-term and short-term memory) network is introduced to find the hidden features of service users. Finally, the authors combined PMF (probabilistic matrix factorization) to estimate the value of the recommended results. Experimental results obtained by the DL-PMF method show better than the experimental results obtained by the PMF and the ConvMF (convolutional matrix factorization) method in the recommended accuracy.

Measurement report: High contributions of halocarbon and aromatic compounds to atmospheric volatile organic compounds in an industrial area

Volatile organic compounds (VOCs) are key components of tropospheric chemistry. We investigated ambient VOCs in an industrial area in Nanjing, China, between July 2018 and May 2020. The sum of the suite of measured total VOC (TVOC) concentrations was 59.8 ± 28.6 ppbv (part per billion by volume) during the investigation period. About twice the TVOC concentrations were observed in the autumn (83 ± 20 ppbv) and winter (77.5 ± 16.8 ppbv) seasons compared to those in spring (39.6 ± 13.1 ppbv) and summer (38.8 ± 10.2 ppbv). In previous studies in Nanjing, oxygenated VOCs (OVOCs) and halocarbons were not measured, and the current TVOC concentration without halocarbons and OVOCs was similar to the previous investigation in the same study area. However, it was twofold higher than the one reported in the nonindustrial suburban area of Nanjing. Due to the industrial influence, the halocarbons VOC group (14.3 ± 7.3 ppbv, 24 %) was the second-largest contributor to the TVOCs after alkanes (21 ± 7 ppbv, 35 %), which is in contrast with the previous studies in Nanjing and also in almost all other regions in China. Relatively high proportions of halocarbons and aromatics were observed in autumn (25.7 % and 19.3 %, respectively) and winter (25.8 % and 17.6 %, respectively) compared to those in summer (20.4 % and 11.8 %, respectively) and spring (20.3 % and 13.6 %, respectively). According to the potential source contribution function (PSCF), short-distance transport from the surrounding industrial areas and cities was the main reason for the high VOC concentrations in the study area. According to positive matrix factorization (PMF) model results, vehicle-related emissions (33 %–48 %) contributed to the major portion of the ambient VOC concentrations. Aromatics, followed by alkenes, were the top contributors to the loss rate of OH radicals (LOH; 37 % and 32 %, respectively). According to the empirical kinetic modelling approach (EKMA) and relative incremental reactivity (RIR) analysis, the study area was in the VOC-sensitive regime for ozone (O3) formation during all measurement seasons. Therefore, alkenes and aromatics emissions from automobiles need to be decreased to reduce secondary air pollution formation in the study area.

Effects of Human Activities on the Spatial Distribution, Ecological Risk and Sources of PTEs in Coastal Sediments

Potentially toxic elements (PTEs) have attracted substantial attention because of their widespread sources, long residue time and easy accumulation. PTEs in the surface sediments of inshore waters are strongly affected by human activities because these waters are a zone of interaction between the ocean and land. In the present study, to explore the environmental geochemical behaviour and source of PTEs in the surface sediments of coastal waters, the contents and spatial distributions of copper (Cu), lead (Pb), zinc (Zn), cadmium (Cd), chromium (Cr), mercury (Hg) and arsenic (As) in different regions of Xiamen Bay were investigated. The data were processed by multivariate statistical methods, and the distribution characteristics of PTEs in the surface sediments of Xiamen Bay were analysed. In addition, the pollution load index (PLI), geo-accumulation index (Igeo) and potential ecological index(RI) were used to evaluate the pollution degree and potential risk in the surface sediments of Xiamen Bay, and the positive matrix factorisation (PMF) model was used to analyse the source. The results show that Zn had the highest mean concentration, followed by Pb, Cr, Cu, As, Cd and Hg, among the seven PTEs. The mean contents of Pb, Zn, Cd, Cu and Hg, and especially Hg and Cd, were higher than the corresponding environmental background values. The average PLI value indicated that the Xiamen Bay sediment was moderately contaminated by PTEs. The Igeo results showed that Xiamen Bay was moderately to strongly polluted by Cd and Hg. The proportions of samples with low, medium and strong risk levels were 11.63%, 74.42%, and 13.95% in surface sediments, respectively. PMF models showed that the input of chemical fertilizer and medication, anthropogenic atmospheric components and terrestrial detritus were the main sources of PTEs in the surface sediment of Xiamen Bay.

Chemical Characterization, Source, and SOA Production of Intermediate Volatile Organic Compounds during Haze Episodes in North China

The growth of secondary organic aerosols (SOA) is a vital cause of the outbreaks of winter haze in North China. Intermediate volatile organic compounds (IVOCs) are important precursors of SOA. Therefore, the chemical characteristics, source, and SOA production of IVOCs during haze episodes have attracted much attention. Hourly time resolution IVOC samples during two haze episodes collected in Hebei Province in North China were analyzed in this study. Results showed that: (1) the concentration of IVOCs measured was within the range of 11.3~85.1 μg·cm−3 during haze episodes, with normal alkanes (n-alkanes), polycyclic aromatic hydrocarbons (PAHs), branched alkanes (b-alkanes), and the residue unresolved complex mixture (R-UCM) accounting for 8.6 ± 2.3%, 6.8 ± 2.2%, 24.1 ± 3.8%, and 60.5 ± 6.5% of IVOCs, respectively. NC12-nC15 in n-alkanes, naphthalene and its alkyl substitutes in PAHs, b-alkanes in B12-B16 bins, and R-UCM in B12-B16 bins are the main components, accounting for 87.0 ± 0.2%, 87.6 ± 2.9%, 85.9 ± 5.4%, 74.0 ± 8.3%, respectively. (2) Based on the component characteristics of IVOCs and the ratios of n-alkanes/b-alkanes in emission sources and the hourly variation of IVOCs during haze episodes, coal combustion (CC), biomass burning (BB), gasoline vehicles (GV), and diesel vehicles (DV)were identified as important emission sources of IVOCs in Hebei Province. (3) During haze episodes, temporal variation of the estimated SOA production based on different methods (such as IVOCs concentration, OC/ECmin tracer, and the PMF model) were similar; however, the absolute values were different. This difference may be due to the transformation of IVOCs to SOA affected by various factors such as SOA production from different IVOC components, meteorological conditions, atmospheric oxidation, etc.

Research and Application of Film and Television Literature Recommendation Based on Secure Internet of Things and Machine Learning

Film and television literature recommendation is an AI algorithm that recommends related content according to user preferences and records. The wide application in various APPs and websites provides users with great convenience. This article aims to study the Internet of Things and machine learning technology, combining deep learning, reinforcement learning, and recommendation algorithms, to achieve accurate recommendation of film and television literature. This paper proposes to use the ConvMF-KNN recommendation model to verify and analyze the four models of PMF, ConvM, ConvMF-word2vec, and ConvMF-KNN, respectively, on public datasets. Using the path information between vertices in bipartite graph and considering the degree of vertices, the similarity between items is calculated, and the neighbor item set of items is obtained. The experimental results show that the ConvMF-KNN model combined with the KNN idea effectively improves the recommendation accuracy. Compared with the accuracy of the PMF model on the MovieLens 100 k, MovieLens 1 M, and AIV datasets, the accuracy of the ConvMF model on the above three datasets is 5.26%, 6.31%, and 26.71%, respectively, an increase of 2.26%, 1.22%, and 7.96%. This model is of great significance.

Insights into Elemental Composition and Sources of Fine and Coarse Particulate Matter in Dense Traffic Areas in Toronto and Vancouver, Canada

Traffic is a significant pollution source in cities and has caused various health and environmental concerns worldwide. Therefore, an improved understanding of traffic impacts on particle concentrations and their components could help mitigate air pollution. In this study, the characteristics and sources of trace elements in PM2.5 (fine), and PM10-2.5 (coarse), were investigated in dense traffic areas in Toronto and Vancouver, Canada, from 2015–2017. At nearby urban background sites, 24-h integrated PM samples were also concurrently collected. The PM2.5 and PM10-2.5 masses, and a number of elements (i.e., Fe, Ba, Cu, Sb, Zn, Cr), showed clear increases at each near-road site, related to the traffic emissions resulting from resuspension and/or abrasion sources. The trace elements showed a clear partitioning trend between PM2.5 and PM10-2.5, thus reflecting the origin of some of these elements. The application of positive matrix factorization (PMF) to the combined fine and coarse metal data (86 total), with 24 observations at each site, was used to determine the contribution of different sources to the total metal concentrations in fine and coarse PM. Four major sources were identified by the PMF model, including two traffic non-exhaust (crustal/road dust, brake/tire wear) sources, along with regional and local industrial sources. Source apportionment indicated that the resuspended crustal/road dust factor was the dominant contributor to the total coarse-bound trace element (i.e., Fe, Ti, Ba, Cu, Zn, Sb, Cr) concentrations produced by vehicular exhaust and non-exhaust traffic-related processes that have been deposited onto the surface. The second non-exhaust factor related to brake/tire wear abrasion accounted for a considerable portion of the fine and coarse elemental (i.e., Ba, Fe, Cu, Zn, Sb) mass at both near-road sites. Regional and local industry contributed mostly to the fine elemental (i.e., S, As, Se, Cd, Pb) concentrations. Overall, the results show that non-exhaust traffic-related processes were major contributors to the various redox-active metal species (i.e., Fe, Cu) in both PM fractions. In addition, a substantial proportion of these metals in PM2.5 was water-soluble, which is an important contributor to the formation of reactive oxygen species and, thus, may lead to oxidative damage to cells in the human body. It appears that controlling traffic non-exhaust-related metals emissions, in the absence of significant point sources in the area, could have a pronounced effect on the redox activity of PM, with broad implications for the protection of public health.

Magnetic Particles Weight as an Indicator for Heavy Metals Concentration

Due to the ever-increasing population growth, urbanization and industrial activity are essential for meeting the basic needs of households. Together with the resulting traffic load and ineffective waste disposal, these factors are the most important sources of environmental pollution in this century. Therefore, the concentration of contaminants should be regularly monitored to protect ecological and human health. The common analytical methods are time-consuming, expensive, and account for a potential source of contamination. In this study, Spearman correlation coefficient, cluster analysis, PMF model, and spatial analysis indicated that anthropogenic magnetic particle weight (MPW) indicates the heavy metal load originated from anthropogenic activity. Hence, it is introduced as a simple, rapid, and cost-effective method for monitoring heavy metal contamination in soil, dust together with bed and suspended sediment. Whenever limited background knowledge prevents planning a comprehensive environmental investigation, this method can be used as the first step for gaining a general insight towards the present status and organize ranked set sampling design.