Search

Supplemental Material for Developing and validating a chronic obstructive pulmonary disease quick screening questionnaire using statistical learning models by Xiaoyue Wang, Hong He, Liang Xu, Cuicui Chen, Jieqing Zhang, Na Li, Xianxian Chen, Weipeng Jiang, Li Li, Linlin Wang, Yuanlin Song, Jing Xiao, Jun Zhang and Dongni Hou in Chronic Respiratory Disease

Background Early detection of influenza activity followed by timely response is a critical component of preparedness for seasonal influenza epidemic and influenza pandemic. However, most relevant studies were conducted at the regional or national level with regular seasonal influenza trends. There are few feasible strategies to forecast influenza activity at the local level with irregular trends. Methods Multi-source electronic data, including historical percentage of influenza-like illness (ILI%), weather data, Baidu search index and Sina Weibo data of Chongqing, China, were collected and integrated into an innovative Self-adaptive AI Model (SAAIM), which was constructed by integrating Seasonal Autoregressive Integrated Moving Average model and XGBoost model using a self-adaptive weight adjustment mechanism. SAAIM was applied to ILI% forecast in Chongqing from 2017 to 2018, of which the performance was compared with three previously available models on forecasting. Findings ILI% showed an irregular seasonal trend from 2012 to 2018 in Chongqing. Compared with three reference models, SAAIM achieved the best performance on forecasting ILI% of Chongqing with the mean absolute percentage error (MAPE) of 11·9%, 7·5%, and 11·9% during the periods of the year 2014–2016, 2017, and 2018 respectively. Among the three categories of source data, historical influenza activity contributed the most to the forecast accuracy by decreasing the MAPE by 19·6%, 43·1%, and 11·1%, followed by weather information (MAPE reduced by 3·3%, 17·1%, and 2·2%), and Internet-related public sentiment data (MAPE reduced by 1·1%, 0·9%, and 1·3%). Interpretation Accurate influenza forecast in areas with irregular seasonal influenza trends can be made by SAAIM with multi-source electronic data.

According to the currently equipment characteristics and process requirements of the refrigeration system of the energy station, we implement intelligent control energy-saving renovation project, which realized the automatic and intelligent control and operation of the refrigeration system related equipment. The system uses distributed control system, and provides systematic solutions for scientific decision-making, reasonable dispatch, energy management, energy efficiency analysis and energy-saving control. Simultaneously, to improve energy efficiency, this system can make full use of the electricity price policy, maximize the economic benefits of water storage, and operate in the lowest cost mode of energy supply.

Spin-glass theory has been widely introduced to describe the statistical behaviors in complex physical systems. By analogy between disorder photonics and other complex systems, the glassy behavior, especially the replica symmetry breaking (RSB) phenomenon, has been observed in random lasers. However, previous studies only analyzed the statistical properties of the random laser systems with single gain material. Here, the first experimental evidence of the glassy behavior in a random laser with complex energy level structure is reported. This novel random laser is demonstrated based on the electrospun polymer fibers with the assistance of Förster resonance energy transfer (FRET). The electrospinning technology employed in the experiment herein promises high-volume production of random laser devices with multiple energy levels, enabling the comprehensive investigation of lasing properties in multi-energy level random laser system. Clear paramagnetic phase and spin-glass phase are observed in the FRET-assisted random laser under different pump energies. The RSB phase transition is verified to occur at the laser threshold, which is robust among the random lasers with different donor–acceptor ratio. The finding of RSB in FRET-assisted random laser provides a new statistical analysis method toward the laser system with complex energy level, for example, quantum cascade laser.

Seasonal influenza epidemics which annually cause substantial diseases and deaths in high-risk population groups are a major public health concern around the world. Considering the hysteresis of traditional flu surveillance systems, this work aims to present a methodology capable of forecasting influenza activity of a city in China precisely 1 week ahead of the official publication. To that end, exogenous information collected from different sources were separately tested with historical influenza-like illness reports for the ability of detecting influenza activity, including climate surveillance, Internet users’ search activity, twitter and health inquiry on an online health consultation platform. Moreover, an ensemble model combining a time series analysis model and a tree boosting model based on those multisource data was applied to improve the accuracy and generalizability of influenza forecasting, in which a model fusion method based on the Kalman Filter was proposed. The validation experiments in this work were performed on the influenza-like illness reports collected from Chongqing city over 4 influenza seasons within 2014–2017. The results show that the proposed model outperformed other tested models by not only taking the periodic law of influenza into consideration but also incorporating information from diverse data sources. The mean absolute percentage error of the validation data set decreased to about 10%. This work provides a viable suggestion for improving the influenza activity forecasting of a city at its early stage.