Search

Accurate estimation of traffic emissions and analysis of spatio-temporal distribution on urban roads play a crucial role in the development of low-carbon transportation system. Traditionally, a region's emission characteristics have been studied using numerous emission models with GPS-based spatio-temporal data. Due to the heavy data processing needs of GPS-based data, emission characteristics for a large region have been studied by dividing the region into a limited number of smaller areas or units. Additionally, GPS data are based on a few vehicles in the traffic which does not fully reflect road conditions. This paper proposed an approach that can be used to study and calculate the spatio-temporal emission pattern of a region at a roadway section level by using Baidu's online traffic data and COPERT model. The proposed method can be used to estimate road-level emission patterns while avoiding the impact of redundant data in large datasets, making the dataset more reliable, applicable, and scalable. The proposed approach has been demonstrated through a study of spatio-temporal emission patterns in the Qiaoxi district within city of Shijiazhuang, China. Online data crawling technology was used to obtain data on urban road traffic speed and driving distance. The linear reference technology was used to construct a two-layer road network model to conduct the coupling and matching of traffic data with the road network data. The COPERT model was implemented to calculate the average traffic emissions on each road in the road network, and a traffic emission intensity index was proposed to quantify the CO, VOC, NOx and CO2 emissions on urban roads in the study area. The analysis results show that the traffic emission intensity of the expressway, trunk road, secondary road, and branch road is high during the morning peak (7 AM-9 AM) and evening peak (5 PM—7 PM). The sections with higher traffic emission intensity are mainly concentrated on the main roads and secondary roads such as Jiefang South Street, Shitong Road and Xinhua Road. Nearly one-third of 2nd Ring and 3rd Ring roads also have relatively high emission intensity. The research results provide new ideas for estimating traffic emissions in urban road networks and analyzing the spatio-temporal distribution of traffic emissions. The research results can also provide a decision-making basis for traffic management departments to formulate energy-saving and emission-reduction measures and promote the development of urban green and low-carbon transportation. [ABSTRACT FROM AUTHOR]

Microblog has become the "first scenario" under which the public learn about the epidemic situation and express their opinions. Public sentiment mining based on microblog data can provide a reference for the government's information disclosure, public sentiment guidance and formulation of epidemic prevention and control policy. In this paper, about 200,000 pieces of text data were collected from Jan. 1 to Feb. 26, 2020 from Sina Weibo, which is the most popular microblog website in China. And a public sentiment analysis framework suitable for Chinese-language scenarios was proposed. In this framework, a sentiment dictionary suitable for Chinese-language scenarios was constructed, and Baidu's Sentiment Analysis API was used to calculate the public sentiment indexes. Then, an analysis on the correlation between the public sentiment indexes and the COVID-19 case indicators was made. It was discovered that there is a high correlation between public sentiments and incidence trends, in which negative sentiment is of statistical significance for the prediction of epidemic development. To further explore the source of public negative sentiment, the topics of the public negative sentiment on Weibo was analyzed, and 20 topics in five categories were got. It is found that there is a strong linkage between the hot spots of public concern and the epidemic prevention and control policies. If the policies cover the hot spots of public concern in a timely and effective manner, the public negative sentiment will be effectively alleviated. The analytical framework proposed in this paper also applies to the public sentiment analysis and policy making for other major public events. [ABSTRACT FROM AUTHOR]

Background: The prediction and prevention of influenza is a public health issue of great concern, and the study of timely acquisition of influenza transmission trend has become an important research topic. For achieving more quicker and accurate detection and prediction, the data recorded on the Internet, especially on the search engine from Google or Baidu are widely introduced into this field. Moreover, with the development of intelligent technology and machine learning algorithm, many updated and advanced trend tracking and forecasting methods are also being used in this research problem. Methods: In this paper, a new recurrent neural network architecture, attention-based long short-term memory model is proposed for influenza surveillance. This is a kind of deep learning model which is trained by processing from Baidu Index series so as to fit the real influenza survey time series. Previous studies on influenza surveillance by Baidu Index mostly used traditional autoregressive moving average model or classical machine learning models such as logarithmic linear regression, support vector regression or multi-layer perception model to fit influenza like illness data, which less considered the deep learning structure. Meanwhile, some new model that considered the deep learning structure did not take into account the application of Baidu index data. This study considers introducing the recurrent neural network with long short-term memory combined with attention mechanism into the influenza surveillance research model, which not only fits the research problems well in model structure, but also provides research methods based on Baidu index. Results: The actual survey data and Baidu Index data are used to train and test the proposed attention-based long short-term memory model and the other comparison models, so as to iterate the value of the model parameters, and to describe and predict the influenza epidemic situation. The experimental results show that our proposed model has better performance in the mean absolute error, mean absolute percentage error, index of agreement and other indicators than the other comparison models. Conclusion: Our proposed attention-based long short-term memory model vividly verifies the ability of this attention-based long short-term memory structure for better surveillance and prediction the trend of influenza. In comparison with some of the latest models and methods in this research field, the model we proposed is also excellent in effect, even more lightweight and robust. Future research direction can consider fusing multimodal data based on this model and developing more application scenarios. [ABSTRACT FROM AUTHOR]

Objectives: To investigate the consistency of adverse events (AEs) and adverse drug reactions (ADRs) reported in the literature, monitoring and social media data. Methods: Using one Chinese patent medicine-Cordyceps sinensis extracts (CSE) as an example, we obtained safety data from the national monitoring system (July 2002 to February 2016), literature (up to November 2016) and social media (May 2019). For literature data, we searched the Chinese National Knowledge Infrastructure Database (CNKI), WanFang database, Chinese Science and Technology Periodical Database (VIP), Chinese Biomedical Literature Database (SinoMed), PubMed, Embase and the Cochrane Library. Social media data was from the Baidu post bar and Sina micro-blog. Two authors independently screened the literature and extracted data by PRISMA Harms checklist was followed. AEs and ADRs were coded using the World Health Organization Adverse Reaction Terminology (WHO-ART). AEs and ADRs were grouped into thirty-one organ-system classes for comparisons. Frequencies, relative frequencies and rank were used as metrics. Radar chart was used to manifest the features of the distributions and proportions. Results: 610 AEs reported in CFDA monitoring data were associated with CSE, of which 537 (88.03%) were suspected ADRs (10.49% certain). 5568 AEs were identified from 172 papers (63% RCTs, 37% other types of studies including case series, case reports, ADR monitoring reports and reviews), in which 86 (1.54%) were ADRs (1.54% certain). 15 AEs (0 certain ADR) were identified from social media. AEs, ADRs and their affected system-organ classes, looked largely similar, but different in every aspect when looking at details. Data from RCTs demonstrated the most disparity. Conclusions: In our study, the most prevalent AEs and ADRs, mainly gastro-intestinal system disorders including nausea, diarrhea and vomiting, in monitoring system were largely similar with those in literature and social media. But data from different sources varied if looked at details. Multiple data sources (the monitoring system, literature and social media) should be integrated to collect safety information of interventions. The distributions of AEs and ADRs from RCTs were least similar with the data from other sources. Our empirical proof is consistent with other similar studies. [ABSTRACT FROM AUTHOR]

The urban spatial structure in this study refers to the combination of different categories of land use, and the purpose of the study is to reveal the intrinsic correlation characteristics between urban land use structural combination forms and urban functions. Through the integration of land and population maps and other multi-source data, with the help of exploratory spatial data analysis and other models, this research deals with the land use spatial structure characteristics of Changchun city and its coordination relationship with urban functions. Main conclusions of the study are as follows. The overall density of the land use in the central urban area of Changchun shows patterns of the core being higher than the periphery, the large-scale agglomeration being significant and the small-scale relatively scattered, and the pattern of the mixed land use function index has obvious differentiation characteristics. The study shows that, in the context of the spatial pattern, the overall coupling coordination degree of the land use structure index and the urban function index shows a trend of a gradual decrease, from the core to the periphery. In the context of category differences, the coupling coordination of the land use structure with the population distribution and the Baidu thermal distribution is relatively high, and the coupling coordination with various service facilities is relatively low. Finally, in the context of scale differences, all types of coupling coordination degrees have significant sensitivity to the spatial scales. A large scale significantly reflects the overall decrease in the coupling coordination degrees from the core to the periphery, while a small scale shows the polycentric pattern characteristics of the urban spatial structure. [ABSTRACT FROM AUTHOR]

Background: AIDS is a worrying public health issue in China and lacks timely and effective surveillance. With the diffusion and adoption of the Internet, the ‘big data’ aggregated from Internet search engines, which contain users’ information on the concern or reality of their health status, provide a new opportunity for AIDS surveillance. This paper uses search engine data to monitor and forecast AIDS in China. Methods: A machine learning method, artificial neural networks (ANNs), is used to forecast AIDS incidences and deaths. Search trend data related to AIDS from the largest Chinese search engine, Baidu.com, are collected and selected as the input variables of ANNs, and officially reported actual AIDS incidences and deaths are used as the output variable. Three criteria, the mean absolute percentage error, the root mean squared percentage error, and the index of agreement, are used to test the forecasting performance of the ANN method. Results: Based on the monthly time series data from January 2011 to June 2017, this article finds that, under the three criteria, the ANN method can lead to satisfactory forecasting of AIDS incidences and deaths, regardless of the change in the number of search queries. Conclusions: Despite the inability to self-detect HIV/AIDS through online searching, Internet-based data should be adopted as a timely, cost-effective complement to a traditional AIDS surveillance system. [ABSTRACT FROM AUTHOR]

New coronavirus cases and related deaths are continuing to occur worldwide. Early identification of the emergence of novel outbreaks of infectious diseases is critical to the generation of timely responses. We performed a comparative study to determine the feasibility of the early detection of the COVID-19 outbreak in China based on influenza surveillance data and the internet-based Baidu search index to evaluate the timelines of the alert signals compared with the traditional case reporting and response systems. An abnormal increase in the number of influenza-like illnesses (ILI) occurred at least one month earlier than the clinical reports of pneumonia with unknown causes and the conventional monitoring system. The peak of the search volume was 20 days earlier than the issuance of the massive official warning about the epidemic. The findings from this study suggest that monitoring abnormal surges of ILI and identifying peaks of online searches of key terms can provide early signals of novel disease outbreaks. We emphasize the importance of broadening the potential of syndromic surveillance, internet searches, and social media data together with the traditional disease surveillance system to enhance early detection and understanding of emerging infectious diseases. Synopsis: Early identification of the emergence of an outbreak of a novel infectious disease is critical to generating a timely response. The traditional monitoring system is adequate for detecting the outbreak of common diseases; however, it is insufficient for the discovery of novel infectious diseases. In this study, we used COVID-19 as an example to compare the delay time of different tools for identifying disease outbreaks. The results showed that both the abnormal spike in influenza-like illnesses and the peak of online searches of key terms could provide early signals. We emphasize the importance of testing these findings and discussing the broader potential to use syndromic surveillance, internet searches, and social media data together with traditional disease surveillance systems for early detection and understanding of novel emerging infectious diseases. [ABSTRACT FROM AUTHOR]

With the acceleration of global urbanization and climate change, dengue fever is spreading worldwide. Different levels of dengue fever have also occurred in China, especially in southern China, causing enormous economic losses. Unfortunately, there is no effective treatment for dengue, and the most popular dengue vaccine does not exhibit good curative effects. Therefore, we developed a Generalized Additive Mixed Model (GAMM) that gathered climate factors (mean temperature, relative humidity and precipitation) and Baidu search data during 2011–2015 in Guangzhou city to improve the accuracy of dengue fever prediction. Firstly, the time series dengue fever data were decomposed into seasonal, trend and remainder components by the seasonal-trend decomposition procedure based on loess (STL). Secondly, the time lag of variables was determined in cross-correlation analysis and the order of autocorrelation was estimated using autocorrelation (ACF) and partial autocorrelation functions (PACF). Finally, the GAMM was built and evaluated by comparing it with Generalized Additive Mode (GAM). Experimental results indicated that the GAMM (R2: 0.95 and RMSE: 34.1) has a superior prediction capability than GAM (R2: 0.86 and RMSE: 121.9). The study could help the government agencies and hospitals respond early to dengue fever outbreak. [ABSTRACT FROM AUTHOR]