Rapid detection of carmine in black tea with spectrophotometry coupled predictive modelling.

Carmine is an artificial colorant commonly used by fraudulent food business participants in black tea adulteration, for purpose of gaining illegal profits. This study combined spectrophotometry with machine learning for rapid detection of carmine in black tea based on the spectral characteristics of tea infusion. The qualitative model demonstrated an accuracy rate of 100% for successful identification of the presence/absence of carmine in black tea. For quantitative analysis, the R2 between carmine concentrations generated according to spectral characteristics and those determined with HPLC was 0.988 and 0.972, respectively, for black tea samples involved in the test subset and an independent dataset II. Paired t-test indicated that the difference was statistically insignificant (P values of 0.26 and 0.44, respectively). The method established in this study was rapid and reliable for detecting carmine in black tea, and thus could be used as a useful tool to identify black tea adulteration in market.

Automated traffic incident detection with a smaller dataset based on generative adversarial networks.

An imbalanced and small training sample can cause an incident detection model to have a low detection rate and a high false alarm rate. To solve the scarcity of incident samples, a novel incident detection framework is proposed based on generative adversarial networks (GANs). First, spatial and temporal rules are presented to extract variables from traffic data, which is followed by the random forest algorithm to rank the importance of variables. Then, some new incident samples are generated using GANs. Finally, the support vector machine algorithm is applied as the incident detection model. Real traffic data, which were collected from a 69.5-mile section of the I-80 highway, are used to validate the proposed approach. A total of 140 detectors are installed on the section enabling traffic flow to be measured every 30s. During 14 days, 139 incident samples and 946 nonincident samples were extracted from the raw data. Five categories of experiments are designed to evaluate whether the proposed framework can solve the small sample size problem, imbalanced sample problem, and timeliness problem in the current incident detection system. The experimental results show that our proposed framework can considerably improve the detection rate and reduce the false alarm rate of traffic incident detection. The balance of the dataset can improve the detection rate from 87.48% to 90.68% and reduce the false alarm rate from 12.76% to 7.11%. This paper lends support to further studies on combining GANs with the machine learning model to address the imbalance and small sample size problems related to intelligent transportation systems.

A highway crash risk assessment method based on traffic safety state division.

In order to quantitatively analyze the influence of different traffic conditions on highway crash risk, a method of crash risk assessment based on traffic safety state division is proposed in this paper. Firstly, the highway crash data and corresponding traffic data of upstream and downstream are extracted and processed by using the matched case-control method to exclude the influence of other factors on the model. Secondly, considering the weight of traffic volume, speed and occupancy, a multi-parameter fusion cluster method is applied to divide traffic safety state. In addition, the quantitative relationship between different traffic states and highway crash risk is analyzed by using Bayesian conditional logistic regression model. Finally, the results of case study show that different traffic safety conditions are in different crash risk levels. The highway traffic management department can improve the safety risk management level by focusing on the prevention and control of high-risk traffic safety conditions.

Comparison of two mathematical prediction models in assessing the toxicity of heavy metal mixtures to the feeding of the nematode Caenorhabditis elegans.

The combined toxicity of four heavy metals (copper, zinc, cadmium and chromium) to the nematode Caenorhabditis elegans was determined by using feeding as an endpoint. Six equivalent-effect concentration ratio (EECR) mixtures and six uniform design concentration ratio (UDCR) mixtures were designed to fully explore the combined toxicities of these heavy metals. Observed toxicities were compared with predictions calculated by two basic models, concentration addition (CA) and independent action (IA). All the concentration-response relationships of the mixtures can be well characterized and described by the Weibull function. CA provided a relatively better prediction for the mix-toxicity of the four heavy metals, which share a similar mode of action on the feeding of C. elegans, although the prediction calculated by IA was also reliable, from the viewpoint of model prediction.