scholarly journals Assessing autonomous ship navigation using bridge simulators enhanced by cycle-consistent adversarial networks

2021 ◽  
pp. 1748006X2110210
Author(s):  
Andreas Brandsæter ◽  
Ottar L Osen
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Decision Support ◽  
Object Detection ◽  
Autonomous Navigation ◽  
Adversarial Networks ◽  
Maritime Navigation ◽  
Ship Navigation ◽  
Autonomous Ship ◽  
Ship Operation

The advent of artificial intelligence and deep learning has provided sophisticated functionality for sensor fusion and object detection and classification which have accelerated the development of highly automated and autonomous ships as well as decision support systems for maritime navigation. It is, however, challenging to assess how the implementation of these systems affects the safety of ship operation. We propose to utilize marine training simulators to conduct controlled, repeated experiments allowing us to compare and assess how functionality for autonomous navigation and decision support affects navigation performance and safety. However, although marine training simulators are realistic to human navigators, it cannot be assumed that the simulators are sufficiently realistic for testing the object detection and classification functionality, and hence this functionality cannot be directly implemented in the simulators. We propose to overcome this challenge by utilizing Cycle-Consistent Adversarial Networks (Cycle-GANs) to transform the simulator data before object detection and classification is performed. Once object detection and classification are completed, the result is transferred back to the simulator environment. Based on this result, decision support functionality with realistic accuracy and robustness can be presented and autonomous ships can make decisions and navigate in the simulator environment.

scholarly journals Autonomous Ship Navigation Methods: A Review

2019 ◽  
Author(s):  
A Noel ◽  
K Shreyanka ◽  
K G S Kumar ◽  
B M Shameem ◽  
B Akshar
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Autonomous Navigation ◽  
Cyber Attacks ◽  
Machine Learning Algorithms ◽  
Learning Approach ◽  
Major Advance ◽  
Maritime Industry ◽  
Ship Navigation ◽  
Autonomous Ship

Autonomous navigation is achieved by training or programming the ship with the stored data about the vessel behavior in various sailing environment. The autonomous behaviour relies on intelligent analytics based on machine learning algorithms. As a major advance in machine learning, the deep learning approach is becoming a powerful technique for autonomy. The deep learning methodologies are applied in various fields in the maritime industry such as detecting anomalies, ship classification, collision avoidance, risk detection of cyber attacks, navigation in ports and so on. The present paper reviews on various methods available in the literature for vessel autonomy and their applications in ship navigation. The focus of the work is to illustrate the advantages of deep learning approach over the machine learning and other traditional methods.

scholarly journals Survey on Deep Learning-Based Marine Object Detection

2021 ◽  
Vol 2021 ◽  
pp. 1-18
Author(s):  
Ruolan Zhang ◽  
Shaoxi Li ◽  
Guanfeng Ji ◽  
Xiuping Zhao ◽  
Jing Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Object Detection ◽  
Large Scale ◽  
Intelligent Transportation System ◽  
High Efficiency ◽  
Maritime Transportation ◽  
Perception System ◽  
Ship Navigation ◽  
Autonomous Ship

We present a survey on marine object detection based on deep neural network approaches, which are state-of-the-art approaches for the development of autonomous ship navigation, maritime surveillance, shipping management, and other intelligent transportation system applications in the future. The fundamental task of maritime transportation surveillance and autonomous ship navigation is to construct a reachable visual perception system that requires high efficiency and high accuracy of marine object detection. Therefore, high-performance deep learning-based algorithms and high-quality marine-related datasets need to be summarized. This survey focuses on summarizing the methods and application scenarios of maritime object detection, analyzes the characteristics of different marine-related datasets, highlights the marine detection application of the YOLO series model, and also discusses the current limitations of object detection based on deep learning and possible breakthrough directions. The large-scale, multiscenario industrialized neural network training is an indispensable link to solve the practical application of marine object detection. A widely accepted and standardized large-scale marine object verification dataset should be proposed.

scholarly journals Learning to See the Hidden Part of the Vehicle in the Autopilot Scene

Electronics ◽  
2019 ◽  
Vol 8 (3) ◽  
pp. 331 ◽  
Author(s):  
Yifeng Xu ◽  
Huigang Wang ◽  
Xing Liu ◽  
Henry He ◽  
Qingyue Gu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Object Detection ◽  
Vision System ◽  
Image Inpainting ◽  
Semantic Segmentation ◽  
Fatal Crash ◽  
White Side ◽  
Original Size ◽  
High Level

Recent advances in deep learning have shown exciting promise in low-level artificial intelligence tasks such as image classification, speech recognition, object detection, and semantic segmentation, etc. Artificial intelligence has made an important contribution to autopilot, which is a complex high-level intelligence task. However, the real autopilot scene is quite complicated. The first accident of autopilot occurred in 2016. It resulted in a fatal crash where the white side of a vehicle appeared similar to a brightly lit sky. The root of the problem is that the autopilot vision system cannot identify the part of a vehicle when the part is similar to the background. A method called DIDA was first proposed based on the deep learning network to see the hidden part. DIDA cascades the following steps: object detection, scaling, image inpainting assuming a hidden part beside the car, object re-detection from inpainted image, zooming back to the original size, and setting an alarm region by comparing two detected regions. DIDA was tested in a similar scene and achieved exciting results. This method solves the aforementioned problem only by using optical signals. Additionally, the vehicle dataset captured in Xi’an, China can be used in subsequent research.

scholarly journals De Novo Drug Design using Artificial Intelligence ASYNT-GAN

2020 ◽  
Author(s):  
Ivan Jacobs ◽  
Manolis Maragoudakis
Keyword(s):  
Molecular Structure ◽  
Artificial Intelligence ◽  
Deep Learning ◽  
De Novo ◽  
Protein Structures ◽  
Generative Adversarial Networks ◽  
Text Generation ◽  
De Novo Drug Design ◽  
3D Space ◽  
Adversarial Networks

In this paper we propose the generation of synthetic small and more sophisticated molecule structures that optimize the binding affinity to a target (ASYNT-GAN). To achieve this we leverage on three important achievements in A.I.: Attention, Deep Learning on Graphs and Generative Adversarial Networks. Similar to text generation based on parts of text we are able to generate a molecule architecture based on an existing target. By adopting this approach, we propose a novel way of searching for existing compounds that are suitable candidates. Similar to question and answer Natural Language solutions we are able to find drugs with highest relevance to a target. We are able to identify substructures of the molecular structure that are the most suitable for binding. In addition, we are proposing a novel way of generating the molecule in 3D space in such a way that the binding is optimized. We show that we are able to generate compound structures and protein structures that are optimised for binding to a target.

scholarly journals De Novo Drug Design using Artificial Intelligence ASYNT-GAN

2020 ◽  
Author(s):  
Ivan Jacobs ◽  
Manolis Maragoudakis
Keyword(s):  
Molecular Structure ◽  
Artificial Intelligence ◽  
Deep Learning ◽  
De Novo ◽  
Protein Structures ◽  
Generative Adversarial Networks ◽  
Text Generation ◽  
De Novo Drug Design ◽  
3D Space ◽  
Adversarial Networks

In this paper we propose the generation of synthetic small and more sophisticated molecule structures that optimize the binding affinity to a target (ASYNT-GAN). To achieve this we leverage on three important achievements in A.I.: Attention, Deep Learning on Graphs and Generative Adversarial Networks. Similar to text generation based on parts of text we are able to generate a molecule architecture based on an existing target. By adopting this approach, we propose a novel way of searching for existing compounds that are suitable candidates. Similar to question and answer Natural Language solutions we are able to find drugs with highest relevance to a target. We are able to identify substructures of the molecular structure that are the most suitable for binding. In addition, we are proposing a novel way of generating the molecule in 3D space in such a way that the binding is optimized. We show that we are able to generate compound structures and protein structures that are optimised for binding to a target.

Gastronomic Algorithms: Artistic and Sensory Exploration of Alain Passard's Michelin Plates in the Manner of Giuseppe Arcimboldo with GANs

Leonardo ◽  
2021 ◽  
pp. 1-11
Author(s):  
Emily L. Spratt
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Generative Adversarial Networks ◽  
Adversarial Networks ◽  
Artistic Collaboration ◽  
Recent Advances ◽  
Learning Techniques ◽  
Data Scientist ◽  
The Senses ◽  
Computer Programmer

Abstract Although recent advances in artificial intelligence to generate images with deep learning techniques, especially generative adversarial networks (GANs), have offered radically new opportunities for its creative applications, there has been little investigation into its use as a tool to explore the senses beyond vision alone. In an artistic collaboration that brought Chef Alain Passard, art historian and data scientist Emily Spratt, and computer programmer Thomas Fan together, photographs of the three-star Michelin plates from the Parisian restaurant Arpège were used as a springboard to explore the art of culinary presentation in the manner of the Renaissance painter Giuseppe Arcimboldo.

Using Deep Learning Artificial Intelligence Algorithms to Verify N-Nitroso-N-Methylurea and Urethane Positive Control Proliferative Changes in Tg-RasH2 Mouse Carcinogenicity Studies

2020 ◽  
pp. 019262332097398
Author(s):  
Daniel Rudmann ◽  
Jay Albretsen ◽  
Colin Doolan ◽  
Mark Gregson ◽  
Beth Dray ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Decision Support ◽  
Positive Control ◽  
Control Group ◽  
Control Groups ◽  
Test Study ◽  
Provide Decision Support ◽  
Proliferative Lesion ◽  
High Concordance

In Tg-rasH2 carcinogenicity mouse models, a positive control group is treated with a carcinogen such as urethane or N-nitroso-N-methylurea to test study validity based on the presence of the expected proliferative lesions in the transgenic mice. We hypothesized that artificial intelligence–based deep learning (DL) could provide decision support for the toxicologic pathologist by screening for the proliferative changes, verifying the expected pattern for the positive control groups. Whole slide images (WSIs) of the lungs, thymus, and stomach from positive control groups were used for supervised training of a convolutional neural network (CNN). A single pathologist annotated WSIs of normal and abnormal tissue regions for training the CNN-based supervised classifier using INHAND criteria. The algorithm was evaluated using a subset of tissue regions that were not used for training and then additional tissues were evaluated blindly by 2 independent pathologists. A binary output (proliferative classes present or not) from the pathologists was compared to that of the CNN classifier. The CNN model grouped proliferative lesion positive and negative animals at high concordance with the pathologists. This process simulated a workflow for review of these studies, whereby a DL algorithm could provide decision support for the pathologists in a nonclinical study.

Sign in / Sign up

Export Citation Format

Share Document