The concentration of PM2.5 is an important index to measure the degree of air pollution. When it exceeds the standard value, it is considered to cause pollution and lower the air quality, which is harmful to human health and can cause a variety of diseases, i.e., asthma, chronic bronchitis, etc. Therefore, the prediction of PM2.5 concentration is helpful to reduce its harm. In this paper, a hybrid model called CNN-BiLSTM-Attention is proposed to predict the PM2.5 concentration over the next two days. First, we select the PM2.5 concentration data in hours from January 2013 to February 2017 of Shunyi District, Beijing. The auxiliary data includes air quality data and meteorological data. We use the sliding window method for preprocessing and dividing the corresponding data into a training set, a validation set, and a test set. Second, CNN-BiLSTM-Attention is composed of the convolutional neural network, bidirectional long short-term memory neural network, and attention mechanism. The parameters of this network structure are determined by the minimum error in the training process, including the size of the convolution kernel, activation function, batch size, dropout rate, learning rate, etc. We determine the feature size of the input and output by evaluating the performance of the model, finding out the best output for the next 48 h. Third, in the experimental part, we use the test set to check the performance of the proposed CNN-BiLSTM-Attention on PM2.5 prediction, which is compared by other comparison models, i.e., lasso regression, ridge regression, XGBOOST, SVR, CNN-LSTM, and CNN-BiLSTM. We conduct short-term prediction (48 h) and long-term prediction (72 h, 96 h, 120 h, 144 h), respectively. The results demonstrate that even the predictions of the next 144 h with CNN-BiLSTM-Attention is better than the predictions of the next 48 h with the comparison models in terms of mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R²).

The rapid growth in the number of motor vehicles has exacerbated traffic congestion. The occurrence of congestion not only poses significant challenges for traffic management authorities but also severely impacts residents’ travel and daily routines. Against this backdrop, predicting traffic flow can provide crucial insights for anticipating changing traffic patterns. Therefore, this paper proposes a novel hybrid deep learning architecture (CNN-LSTM-GRU) for highway traffic flow prediction that integrates spatiotemporal and meteorological dimensions. Our approach constructs a multidimensional feature matrix encompassing temporal sequences, spatial correlations, and weather conditions. Convolutional Neural Networks (CNN) are employed to capture spatial patterns, while Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks jointly model temporal dependencies. Through systematic hyperparameter tuning and step-length optimization, we validate the model using real-world traffic data from a provincial highway network. The experimental evaluation analyzes the following two critical dimensions: (1) holiday vs. non-holiday traffic patterns, and (2) the impact of weather data integration. Comparative analysis reveals that our hybrid model demonstrates superior prediction accuracy over standalone LSTM, GRU, and their CNN-based counterparts (CNN-LSTM, CNN-GRU).

How to explore the interaction between an individual researcher and others in scientific research, find out the degree of association among individual researchers, and evaluate the contribution of researchers to the whole according to the mechanism and law of interaction, is of great significance to grasp the overall trend of the field. Scholars mostly use bibliometrics to solve these problems and analyze the citation and cooperation among academic achievements from the dimension of “quantity”. However, there is still no mature method for scholars to explore the evolution of knowledge and the relationship between authors; this paper tries to fill this gap. We narrow down the scope of research and focus the research content on the literature in biology and chemistry, collect all the papers from PubMed system (a very comprehensive authoritative database of biomedical papers) during 2014–2018, and take year as a specific analysis unit so as to improve the accuracy of the analysis. Then, we construct the author cooperation networks. Finally, through the above methods and steps, we identify the core authors of each year, analyze the recent cooperative relationships among authors, and predict some changes in the cooperative relationship among the authors based on the networks’ analytical data, evaluating and estimating the role that authors play in the overall field. Therefore, we expect that the cooperative authorship networks supported by the complex network theory can better explain the author’s cooperative relationship.

It is now generally accepted that an article written by influential authors often deserves a higher ranking in information retrieval. However, it is a challenging task to determine an author’s relative influence since information about the author is, much of the time, inaccessible. Actually, in scientific publications, the author is an important metadata item, which has been widely used in previous studies. In this paper, we bring an optimized AuthorRank, which is a topic-sensitive algorithm calculated by citation context, into citation analysis for testing whether and how topical AuthorRank can replace or enhance classical PageRank for publication ranking. For this purpose, we first propose a PageRank with Priors (PRP) algorithm to rank publications and authors. PRP is an optimized PageRank algorithm supervised by the Labeled Latent Dirichlet Allocation (Labeled-LDA) topic model with full-text information extraction. We then compared four methods of generating an AuthorRank score, looking, respectively, at the first author, the last author, the most famous author, and the “average” author (of a publication). Additionally, two combination methods (Linear and Cobb–Douglas) of AuthorRank and PRP were compared with several baselines. Finally, as shown in our evaluation results, the performance of AuthorRank combined with PRP is better (p < 0.001) than other baselines for publication ranking.

Scientific papers published in journals or conferences, also considered academic publications, are the manifestation of scientific research achievements. Lots of scientific papers published in digital form bring new challenges for academic evaluation and information retrieval. Therefore, research on the ranking method of scientific papers is significant for the management and evaluation of academic resources. In this paper, we first identify internal and external factors for evaluating scientific papers and propose a publication ranking method based on an analysis of a heterogeneous academic network. We use four types of metadata (i.e., author, venue (journal or conference), topic, and title) as vertexes for creating the network; in there, the topics are trained by the SentenceLDA algorithm with the metadata of the We then use the Gibbs sampling method to create a heterogeneous academic network and apply the ConNetClus algorithm to calculate the probability value of publication ranking. To evaluate the significance of the method proposed in this paper, we compare the ranking results with BM25, PageRank, etc., and homogeneous networks in MAP and NDCG. As shown in our evaluation results, the performance of the method we propose in this paper is better than other baselines for ranking publications.