The establishment of maritime safety and security is an important concern. Ship position prediction for maritime situational awareness (MSA), as a critical aspect of maritime safety and security, requires a longer time interval than collision avoidance and maritime traffic monitoring. However, previous studies focused mainly on shorter time-interval predictions ranging from 30 min to 10 h. A longer time-interval ship position prediction is required not only for MSA, but also for efficient allocation of ships by shipping companies in accordance with global freight demand. This study used an end-to-end tracking method that inputs the previous position of a vessel to a trained deep learning model to predict its next position with an average 24-h interval. An AIS dataset with a long-time-interval distribution in a nine-year timespan for capesize bulk carriers worldwide was used. In the first experiment, a deep learning model of the Indian Ocean was examined. Subsequently, the model performance was compared for six different oceans and six primary maritime chokepoints to investigate the influence of each area. In the third experiment, a sample location within the Malacca Strait area was selected, and the number of ships was counted daily. The results indicate that the ship position can be predicted accurately with an average time interval of 24 h using deep learning systems with AIS data.
Perovskite solar cells based on series of inorganic cesium lead bromide and iodide mixture, CsPbBr3-xI x , where x varies between 0, 0.1, 0.2, and 0.3 molar ratio were synthesized by two step-sequential deposition at ambient condition to design the variations of wide band gap light absorbers. A device with high overall photoconversion efficiency of 3.98 % was obtained when small amount of iodide (CsPbBr2.9I0.1) was used as the perovskite and spiro-OMeTAD as the hole transport material (HTM). We investigated the origin of variation in open circuit voltage, Voc which was shown to be mainly dependent on two factors, which are the band gap of the perovskite and the work function of the HTM. An increment in Voc was observed for the device with larger perovskite band gap, while keeping the electron and hole extraction contacts the same. Besides, the usage of bilayer P3HT/MoO3 with deeper HOMO level as HTM instead of spiro-OMeTAD, thus increased the Voc from 1.16 V to 1.3 V for CsPbBr3 solar cell, although the photocurrent is lowered due to charge extraction issues. The stability studies confirmed that the addition of small amount of iodide into the CsPbBr3 is necessarily to stabilize the cell performance over time.
N-methyl-d-aspartate (NMDA) receptors are glutamate-activated ion channels that are widely distributed in the central nervous system and essential for brain development and function. Dysfunction of NMDA receptors has been associated with various neurodevelopmental disorders. Recently, a de novo recurrent GRIN2D missense variant was found in two unrelated patients with developmental and epileptic encephalopathy. In this study, we identified by whole exome sequencing novel heterozygous GRIN2D missense variants in three unrelated patients with severe developmental delay and intractable epilepsy. All altered residues were highly conserved across vertebrates and among the four GluN2 subunits. Structural consideration indicated that all three variants are probably to impair GluN2D function, either by affecting intersubunit interaction or altering channel gating activity. We assessed the clinical features of our three cases and compared them to those of the two previously reported GRIN2D variant cases, and found that they all show similar clinical features. This study provides further evidence of GRIN2D variants being causal for epilepsy. Genetic diagnosis for GluN2-related disorders may be clinically useful when considering drug therapy targeting NMDA receptors.