Enhanced levels of singlet oxygen ( 1 O 2 ) in chloroplasts trigger programmed cell death. The impact of 1 O 2 production in chloroplasts was monitored first in the conditional fluorescent (flu) mutant of Arabidopsis thaliana that accumulates 1 O 2 upon a dark/light shift. The onset of 1 O 2 production is rapidly followed by a loss of chloroplast integrity that precedes the rupture of the central vacuole and the final collapse of the cell. Inactivation of the two plastid proteins EXECUTER (EX1) and EX2 in the flu mutant abrogates these responses, indicating that disintegration of chloroplasts is due to EX-dependent signaling rather than 1 O 2 directly. In flu seedlings, 1 O 2 -mediated cell death signaling operates as a default pathway that results in seedlings committing suicide. By contrast, EX-dependent signaling in the wild type induces the formation of microlesions without decreasing the viability of seedlings. 1 O 2 -mediated and EX-dependent loss of plastid integrity and cell death in these plants occurs only in cells containing fully developed chloroplasts. Our findings support an as yet unreported signaling role of 1 O 2 in the wild type exposed to mild light stress that invokes photoinhibition of photosystem II without causing photooxidative damage of the plant.

The traffic flow prediction is becoming increasingly crucial in Intelligent Transportation Systems. Accurate prediction result is the precondition of traffic guidance, management, and control. To improve the prediction accuracy, a spatiotemporal traffic flow prediction method is proposed combined with k-nearest neighbor (KNN) and long short-term memory network (LSTM), which is called KNN-LSTM model in this paper. KNN is used to select mostly related neighboring stations with the test station and capture spatial features of traffic flow. LSTM is utilized to mine temporal variability of traffic flow, and a two-layer LSTM network is applied to predict traffic flow respectively in selected stations. The final prediction results are obtained by result-level fusion with rank-exponent weighting method. The prediction performance is evaluated with real-time traffic flow data provided by the Transportation Research Data Lab (TDRL) at the University of Minnesota Duluth (UMD) Data Center. Experimental results indicate that the proposed model can achieve a better performance compared with well-known prediction models including autoregressive integrated moving average (ARIMA), support vector regression (SVR), wavelet neural network (WNN), deep belief networks combined with support vector regression (DBN-SVR), and LSTM models, and the proposed model can achieve on average 12.59% accuracy improvement.

No abstract