TY - JOUR ID - 10.1016/j.jes.2021.03.035 TI - Fish forewarning of comprehensive toxicity in water environment based on Bayesian sequential method AU - Kaifeng Rao AU - Li Tang AU - Xin Zhang AU - Heyu Xiang AU - Liang Tang AU - Yong Liu AU - Wei Wang AU - Jie Jiang AU - Mei Ma AU - Yiping Xu AU - Zijian Wang VL - 33 IS - 12 PB - SP - 150 EP - 159 PY - JF - Journal of Environmental Sciences JA - J. Environ. Sci. UR - http://www.jesc.ac.cn/jesc_en/ch/reader/view_abstract.aspx?file_no=S1001074221001200&flag=1 KW - Corresponding authors.;Bayesian sequential method;Fish electrical signal;Outlier detection;Anomaly probability;Time series forecasting AB - Environmental impact of pollutants can be analyzed effectively by acquiring fish behavioral signals in water with biological behavior sensors. However, a variety of factors, such as the complexity of biological organisms themselves, the device error and the environmental noise, may compromise the accuracy and timeliness of model predictions. The current methods lack prior knowledge about the fish behavioral signals corresponding to characteristic pollutants, and in the event of a pollutant invasion, the fish behavioral signals are poorly discriminated. Therefore, we propose a novel method based on Bayesian sequential, which utilizes multi-channel prior knowledge to calculate the outlier sequence based on wavelet feature followed by calculating the anomaly probability of observed values. Furthermore, the relationship between the anomaly probability and toxicity is analyzed in order to achieve forewarning effectively. At last, our algorithm for fish toxicity detection is verified by integrating the data on laboratory acceptance of characteristic pollutants. The results show that only one false positive occurred in the six experiments, the present algorithm is effective in suppressing false positives and negatives, which increases the reliability of toxicity detections, and thereby has certain applicability and universality in engineering applications. ER -