Quantifying the Effects of Visual Road Information on Drivers' Speed Choices to Promote Self-Explaining Roads.

Roads should deliver appropriate information to drivers and thus induce safer driving behavior. This concept is also known as "self-explaining roads" (SERs). Previous studies have demonstrated that understanding how road characteristics affect drivers' speed choices is the key to SERs. Thus, in order to reduce traffic casualties via engineering methods, this study aimed to establish a speed decision model based on visual road information and to propose an innovative method of SER design. It was assumed that driving speed is determined by road geometry and modified by the environment. Lane fitting and image semantic segmentation techniques were used to extract road features. Field experiments were conducted in Tibet, China, and 1375 typical road scenarios were picked out. By controlling variables, the driving speed stimulated by each piece of information was evaluated. Prediction models for geometry-determined speed and environment-modified speed were built using the random forest algorithm and convolutional neural network. Results showed that the curvature of the right boundary in "near scene" and "middle scene", and the density of roadside greenery and residences play an important role in regulating driving speed. The findings of this research could provide qualitative and quantitative suggestions for the optimization of road design that would guide drivers to choose more reasonable driving speeds.

Domain-adversarial multi-task framework for novel therapeutic property prediction of compounds.

MOTIVATION: With the rapid development of high-throughput technologies, parallel acquisition of large-scale drug-informatics data provides significant opportunities to improve pharmaceutical research and development. One important application is the purpose prediction of small-molecule compounds with the objective of specifying the therapeutic properties of extensive purpose-unknown compounds and repurposing the novel therapeutic properties of FDA-approved drugs. Such a problem is extremely challenging because compound attributes include heterogeneous data with various feature patterns, such as drug fingerprints, drug physicochemical properties and drug perturbation gene expressions. Moreover, there is a complex non-linear dependency among heterogeneous data. In this study, we propose a novel domain-adversarial multi-task framework for integrating shared knowledge from multiple domains. The framework first uses an adversarial strategy to learn target representations and then models non-linear dependency among several domains. RESULTS: Experiments on two real-world datasets illustrate that our approach achieves an obvious improvement over competitive baselines. The novel therapeutic properties of purpose-unknown compounds that we predicted have been widely reported or brought to clinics. Furthermore, our framework can integrate various attributes beyond the three domains examined herein and can be applied in industry for screening significant numbers of small-molecule drug candidates. AVAILABILITY AND IMPLEMENTATION: The source code and datasets are available at https://github.com/JohnnyY8/DAMT-Model. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Simultaneous determination of NOGE-related and BADGE-related compounds in canned food by ultra-performance liquid chromatography-tandem mass spectrometry.

An improved analytical method enabling rapid and accurate determination and identification of bisphenol F diglycidyl ether (novolac glycidyl ether 2-ring), novolac glycidyl ether 3-ring, novolac glycidyl ether 4-ring, novolac glycidyl ether 5-ring, novolac glycidyl ether 6-ring, bisphenol A diglycidyl ether, bisphenol A (2,3-dihydroxypropyl) glycidyl ether, bisphenol A (3-chloro-2-hydroxypropyl) glycidyl ether, bisphenol A bis(3-chloro-2-hydroxypropyl) ether, and bisphenol A (3-chloro-2-hydroxypropyl) (2,3-dihydroxypropyl) ether in canned food and their contact packaging materials has been developed by using, for the first time, ultra-performance liquid chromatography coupled with tandem mass spectrometry. After comparison of electrospray ionization and atmospheric pressure chemical ionization in positive and negative-ion modes, tandem mass spectrometry with positive electrospray ionization was chosen to carry out selective multiple reaction monitoring analysis of novolac glycidyl ethers, bisphenol A diglycidyl ether, and its derivatives. The analysis time is only 5.5 min per run. Limits of detection varied from 0.01 to 0.20 ng g(-1) for the different target compounds on the basis of a signal-to-noise ratio (S/N) = 3; limits of quantitation were from 0.03 to 0.66 ng g(-1). The relative standard deviation for repeatability was <8.01%. Analytical recovery ranged from 87.60 to 108.93%. This method was successfully applied to twenty samples of canned food and their contact packaging materials for determination of migration of NOGE, BADGE, and their derivatives from can coatings into food.

[Research on calibration transfer of NIR filter spectrophotometer].

Calibration transfer is an important issue to building up universal and comparable performance of spectrometer data in near infrared spectral analysis technology. Methods of slope/bias correction, direct standardization (DS), and target factor analysis (TFA) were used for the calibration transfer among five NIR filter spectrophotometers using maize as the samples. The effects of three calibration transfer methods were compared. The DS method has the best performance. The average calibration transfer difference of DS is 7.01%. This study also relates to the dependence of calibration transfer on the number of standardization samples. It was proven by experiment that the results of calibration transfer will be better as the number of samples is increased and will be generally stable when there are twenty standardization samples. However, the effect of calibration transfer attained by DS is degraded sharply when the number of standardization samples decreases to be below twenty. Moreover, slope/bias and TFA are not sensitive to the number of standardization samples.