All the modern surveillance systems take advantage of the Automatic Identification System (AIS), a compulsory tracking system for many types of vessels. Ships that carry AIS transponders on board transmit their position and status in order to alert nearby vessels and ground stations, but this information can well be used to identify events of interest and support decision making. The detection of anomalies (i.e. unexpected sailing behavior) in vessels’ trajectories is such an event, which is of utmost importance. Approaches for detecting such anomalies vary from extracting normality models to searching for individual cases, such as AIS switch-off or collision avoidance maneuvers. The current research work follows the former method; it employs sparse historic AIS data and polynomial interpolation in order to extract shipping lanes. It modifies the DB-Scan clustering algorithm in order to achieve more coherent trajectory clusters, which are then composed to create the shipping lanes. The proposed approach implements distributed processing on Apache Spark in order to improve processing speed and scalability and is evaluated using real-world AIS data collected from terrestrial AIS receivers. The evaluation shows that the biggest part (i.e. more than 90%) of any future vessel trajectory falls within the extracted shipping lanes.

Due to the vast amount of available tracking sensors in recent years, high-frequency and high-volume streams of data are generated every day. The maritime domain is no different as all larger vessels are obliged to be equipped with a vessel tracking system that transmits their location periodically. Consequently, automated methodologies able to extract meaningful information from high-frequency, large volumes of vessel tracking data need to be developed. The automatic identification of vessel mobility patterns from such data in real time is of utmost importance since it can reveal abnormal or illegal vessel activities in due time. Therefore, in this work, we present a novel approach that transforms streaming vessel trajectory patterns into images and employs deep learning algorithms to accurately classify vessel activities in near real time tackling the Big Data challenges of volume and velocity. Two real-world data sets collected from terrestrial, vessel-tracking receivers were used to evaluate the proposed methodology in terms of both classification and streaming execution performance. Experimental results demonstrated that the vessel activity classification performance can reach an accuracy of over $96\%$ while achieving sub-second latencies in streaming execution performance.

A bstract: The COVID-19 pandemic in 2020 has highlighted the need to pull all available resources towards the mitigation of the devastating effects of such “Black Swan” events. Towards that end, we investigated the option to employ technology in order to assist the diagnosis of patients infected by the virus. As such, several state-of-the-art pre-trained convolutional neural networks were evaluated as of their ability to detect infected patients from chest X-Ray images. A dataset was created as a mix of publicly available X-ray images from patients with confirmed COVID-19 disease, common bacterial pneumonia and healthy individuals. To mitigate the small number of samples, we employed transfer learning, which transfers knowledge extracted by pre-trained models to the model to be trained. The experimental results demonstrate that the classification performance can reach an accuracy of 95% for the best two models.

Edge computing constitutes a promising paradigm of managing and processing the massive amounts of data generated by Internet of Things (IoT) devices. Data and computation are moved closer to the client, thus enabling latency- and bandwidth-sensitive applications. However, the distributed and heterogeneous nature of the edge as well as its limited resource capabilities pose several challenges in implementing or choosing an efficient edge-enabled storage system. Therefore, it is imperative for the research community to contribute to the clarification of the purposes and highlight the advantages and disadvantages of various edge-enabled storage systems. This work aspires to contribute toward this direction by presenting a performance analysis of three different storage systems, namely MinIO, BigchainDB, and the IPFS. We selected these three systems as they have been proven to be valid candidates for edge computing infrastructures. In addition, as the three evaluated systems belong to different types of storage, we evaluated a wide range of storage systems, increasing the variability of the results. The performance evaluation is performed using a set of resource utilization and Quality of Service (QoS) metrics. Each storage system is deployed and installed on a Raspberry Pi (small single-board computers), which serves as an edge device, able to optimize the overall efficiency with minimum power and minimum cost. The experimental results revealed that MinIO has the best overall performance regarding query response times, RAM consumption, disk IO time, and transaction rate. The results presented in this paper are intended for researchers in the field of edge computing and database systems.

Nowadays, the increasing number of moving objects tracking sensors, results in the continuous flow of high-frequency and high-volume data streams. This phenomenon can especially be observed in the maritime domain since most of the vessels worldwide are now transmitting their positions periodically. Therefore, there is a strong necessity to extract meaningful information and identify mobility patterns from such tracking data in an automated fashion, eliminating the need for experts’ input. To this end, a novel approach is presented in this paper, which fuses the research fields of computer vision and trajectory classification, in order to deliver a high-precision classification of mobility patterns. The experimental results demonstrate that the classification performance of the proposed approach can reach an f1-score of over 95%.