Maritime monitoring requirements have been beyond human operators capabilities due to the broadness of the coverage area and the variety of monitoring activities, e.g. illegal migration, or security threats by foreign warships. Abnormal vessel movement can be defined as an unreasonable movement deviation from the usual trajectory, speed, or other traffic parameters. Detection of the abnormal vessel movement requires the operators not only to pay short-term attention but also to have long-term trajectory trace ability. Recent advances in deep learning have shown the potential of deep learning techniques to discover hidden and more complex relations that often lie in low dimensional latent spaces. In this paper, we propose a deep autoencoder-based clustering model for automatic detection of vessel movement anomaly to assist monitoring operators to take actions on the vessel for more investigation.

Activated non-graphitizable hard carbon using orange peel with mesoporous structure has been prepared by pyrolyzation at 700, 800, 900 °C using chemical activation method. The activated orange peel-derived hard carbon has been characterized for its mesoporous and disordered structure. TG-DSC gives the information for the changes about sample composition and thermal stability of the materials. Increasing the carbonization temperature for orange peel precursor using NaOH as activating agent, elevates the pore diameter, which thereby facilitating the insertion of Na+. Raman and X-ray diffraction confirms the presence of disordered carbon. The surface morphology of the material was analyzed by scanning eletron microsope and nitrogen ( N2) adsorption and desorption analysis give the morphology, mesopore size (3.374, 3.39 and 4 nm) and surace area (60.164, 58.99 and 54.327 m2/g) of the orange peel-derived hard carbon. Hence, this work strongly evidences that the biomass-derived hard carbon with good porosity and paves way of superior electrochemical performance for emerging sodium ion batteries.