Abstract Recent advances in artificial intelligence (AI) have laid the foundation for developing a sophisticated collision avoidance system use maritime autonomous surface ships, potentially enhancing safety and decreasing navigator’s workload. Understanding reasoning behind an AI is inherently difficult. To help human operator understand what doing its reasoning, we employed human-centered design approach to develop transparency layers that visualize different aspects of operation by...

Sensor data from marine engine systems can be used to detect changes in performance near real time which may indicative of an impending failure. Thus sensor-based condition monitoring important for the reliability ship machinery and improve maritime safety. However, there is a need efficient robust algorithms such streams. In this paper, sensor diesel on ocean-going are anomaly detection. The focus unsupervised methods based clustering idea identify clusters normal operating conditions...

Abstract This paper proposes and demonstrates a simulator-based approach for testing assessing human operators’ ability performance in supervising autonomous ships. In the autonomy concept studied here, it is assumed that navigation system capable of detecting notifying operator prior to entering challenging situation. The will attempt resolve situation with proposed evasive maneuver, but may occasionally make errors or select sub-optimal solutions. When notified about situation, should...

We propose novel modifications to an anomaly detection methodology based on multivariate signal reconstruction followed by residuals analysis. The reconstructions are made using Auto Associative Kernel Regression (AAKR), where the query observations compared historical called memory vectors, representing normal operation. When data set with grows large, naive approach all used as vectors will lead unacceptable large computational loads, hence a reduced of should be intelligently selected....

Abstract The prospect of a future where the maritime shipping industry is dominated by autonomous vessels appealing and gaining global interest from majors, research institutions, academia. Potential advantages include increased operational safety, reduced costs, lower environmental footprint. However, transition will not happen overnight without challenges. For example, algorithms for navigation must take into consideration safety concerns own ship, its crew passengers, other surrounding...

In this paper we present an application of sensor-based anomaly detection in maritime transport. The study is based on real sensor data streamed from a ship to shore, where the analysed through big analytics platform. novelty work originates use sensors covering different aspects operation, exemplified here by propulsion power, speed over ground and motion four degrees freedom. developed method employs Auto Associative Kernel Regression (AAKR) for signal reconstruction, Sequential...

Maritime Autonomous Surface Ships (MASS) are quickly emerging as a game-changing technology in various parts of the world. They can be used for wide range applications, including cargo transportation, oceanographic research and military operations. One main challenges associated with MASS is need to build trust confidence systems among end-users. While use AI algorithms lead more efficient effective decision-making, humans often reticent rely on that they do not fully understand. The lack...

The advent of artificial intelligence and deep learning has provided sophisticated functionality for sensor fusion object detection classification which have accelerated the development highly automated autonomous ships as well decision support systems maritime navigation. It is, however, challenging to assess how implementation these affects safety ship operation. We propose utilize marine training simulators conduct controlled, repeated experiments allowing us compare navigation...

Abstract This paper proposes a novel approach to explain the predictions made by data-driven methods. Since such rely heavily on data used for training, explanations that convey information about how training affects are useful. The quantify different data-clusters of affect prediction. quantification is based Shapley values, concept which originates from coalitional game theory, developed fairly distribute payout among set cooperating players. A player’s value measure contribution. values...

This article presents a data interface for maritime simulators to facilitate the development of ship Automatic Navigational Systems (ANS) at different autonomy levels. The core architecture this consists simulator, Sim-PC, and downstream clients. Two transmission channels are established between simulator SimPC using UDP Modbus TCP/IP protocols, while interaction Sim-PC clients is achieved through websockets. provides technical details each channel demonstrates their application relevant...

Sfard og Leron (1996) observerte at studentar arbeider flittigare oftare lukkast når dei programmerer enn gjer med analytisk matematikk, sjølv om programmeringsoppgåva løyser det same matematiske problemet i ein meir generell form. Her går me gjennom relevant litteratur teori for å drøfta kvifor kan vera slik. Dette reiser interessante spørsmål både korleis bruka programmering styrka matematikkforståinga best lærer programmering.

This paper proposes a novel approach to explain the predictions made by data-driven methods. Since such rely heavily on data used for training, explanations that convey information about how training affects are useful. The quantify different data-clusters of affect prediction. quantification is based Shapley values, concept which originates from coalitional game theory, developed fairly distribute payout among set cooperating players. A player's value measure contribution. values often...

In this paper we present an application of sensorbased anomaly detection in maritime transport. The study is based on real sensor data streamed from a ship to shore, where the analysed through big analytics platform. novelty work originates use sensors covering different aspects operation, exemplified here by propulsion power, speed over ground and motion four degrees freedom. developed method employs Auto Associative Kernel Regression (AAKR) for signal reconstruction, Sequential Probability...

The interest in programming schools has the last decade increased, and many countries have introduced as part of school curriculum. Teaching to students primary secondary is often focused on computer sciences aspect programming. current study a recently initiated research project “Programming for understanding mathematics” which different emphasis; investigates how mathematical competence are affected by actively using mathematics lessons. In this paper, recognized analytical framework...