Obstacle detection is a fundamental capability of an autonomous maritime surface vessel (AMSV). State-of-the-art obstacle detection algorithms are based on convolutional neural networks (CNNs). While CNNs provide higher detection accuracy and fast detection speed, they require enormous amounts of data for their training. In particular, the availability of domain-specific datasets is a challenge for obstacle detection. The difficulty in conducting onsite experiments limits the collection of maritime datasets. Owing to the logistic cost of conducting on-site operations, simulation tools provide a safe and cost-efficient alternative for data collection. In this work, we introduce SimuShips, a publicly available simulation-based dataset for maritime environments. Our dataset consists of 9471 high-resolution (1920x1080) images which include a wide range of obstacle types, atmospheric and illumination conditions along with occlusion, scale and visible proportion variations. We provide annotations in the form of bounding boxes. In addition, we conduct experiments with YOLOv5 to test the viability of simulation data. Our experiments indicate that the combination of real and simulated images improves the recall for all classes by 2.9%. @en

The use of digital twins for the development of Autonomous Maritime Surface Vessels (AMSVs) has enormous potential to resolve the increasing need for water-based navigation and safety at the sea. Aiming at the problem of lack of broad and integrated digital twin implementations with live data along with the absence of a digital twin-driven framework for AMSV design and development, an application framework for the development of a fully autonomous vessel using an integrated digital twin in a 3D simulation environment has been presented. Our framework has 4 layers which ensure that simulation and real-world vessel and the environment are as close as possible. Åboat, an in-house, experimental research platform for maritime automation and autonomous surface vessel applications, equipped with two trolling electric motors, cameras, LiDARs, IMU and GPS has been used as the case study to provide a proof of concept. Åboat, its sensors, and the environment have been replicated in a commercial, 3D simulation environment, AILiveSim. Using the proposed application framework, we develop obstacle detection and path planning systems based on machine learning which leverage live data from a 3D simulation environment to mirror the complex dynamics of the real world. Exploiting the proposed application framework, the rewards across training episodes of a Deep Reinforcement Learning model are evaluated for live simulated data in AILiveSim.@en

Objective: To assess the effects of neurally adjusted ventilatory assist (NAVA) ventilation on oxygenation and respiratory parameters in preterm infants. Study Design: An observational crossover study with a convenience sample of 19 infants born before 30 gestational weeks. Study parameters were recorded during 3-h periods of both NAVA and conventional ventilation. The proportion of time peripheral oxygen saturation (SpO2) and cerebral regional oxygen saturation (cRSO2) were within their target ranges, plus the number and severity of desaturation episodes were analyzed. In addition, electrical activity of the diaphragm (Edi), neural respiratory rates, and peak inspiratory pressures (PIPs) were recorded. Results: Infants were born at a median age of 264/7 gestational weeks (range: 230/7–293/7); the study was performed at a median age of 20 days (range: 1–82). The proportion of time SpO2 was within the target range, the number of peripheral desaturations or cRSO2 did not differ between the modes. However, the desaturation severity index was lower (131 vs. 152; p =.03) and fewer manual supplemental oxygen adjustments (1.3 vs. 2.2/h; p =.006) were needed during the period of NAVA ventilation following conventional ventilation. The mean Edi (8.1 vs. 11.4 µV; p <.006) and PIP values (14.9 vs. 19.1; p <.001) were lower during the NAVA mode. Conclusions: Although NAVA ventilation did not increase the proportion of time with optimal saturation, it was associated with decreased diaphragmatic activity, lower PIPs, less severe hypoxemic events, and fewer manual oxygen adjustments in very preterm infants.@en

We present the EVONANO platform for the evolution of nanomedicines with application to anti-cancer treatments. Our work aims to decrease both the time and cost required to develop nanoparticle designs. EVONANO includes a simulator to grow tumours, extract representative scenarios, and simulate nanoparticle transport through these scenarios in order to predict nanoparticle distribution. The nanoparticle designs are optimised using machine learning to efficiently find the most effective anti-cancer treatments. We demonstrate EVONANO with two examples optimising the properties of nanoparticles and treatment to selectively kill cancer cells over a range of tumour environments. Our platform shows how in silico models that capture both tumour and tissue-scale dynamics can be combined with machine learning to optimise nanomedicine.@en

The birth of massive open online courses (MOOCs) has had an undeniable effect on how teaching is being delivered. It seems that traditional in class teaching is becoming less popular with the young generation, the generation that wants to choose when, where and at what pace they are learning. As such, many universities are moving towards taking their courses, at least partially, online. However, online courses, although very appealing to the younger generation of learners, come at a cost. For example, the dropout rate of such courses is higher than that of more traditional ones, and the reduced in person interaction with the teachers results in less timely guidance and intervention from the educators. Machine learning (ML) based approaches have shown phenomenal successes in other domains. The existing stigma that applying ML based techniques requires a large amount of data seems to be a bottleneck when dealing with small scale courses with limited amounts of produced data. In this study, we show not only that the data collected from an online learning management system could be well utilized in order to predict students overall performance but also that it could be used to propose timely intervention strategies to boost the students performance level. The results of this study indicate that effective intervention strategies could be suggested as early as the middle of the course to change the course of students progress for the better. We also present an assistive pedagogical tool based on the outcome of this study, to assist in identifying challenging students and in suggesting early intervention strategies.@en

In this article we present the state of the art in the field of autonomous surface ship navigation using machine learning. We discuss the main challenges towards the development of fully autonomous navigation systems with the International Regulations for Preventing Collisions at Sea (COLREGs). Finally, we propose two alternative approaches that are based on machine learning. Existing COLREGs-based navigation and collision avoidance algorithms are based on traditional search-based planning and optimization algorithms. We consider that these approaches are suitable when the problem space is defined completely and rigorously. However, experts believe that is not the case for COLREGs since it leaves many aspects open to the interpretation of the captain. For example, COLREGs expects that any collision avoidance action shall be taken with due regard to the observance of good seamanship, a concept not defined in the convention. Furthermore, many rules are defined using undefined concepts like safe distance, or keywords like early, or substantial, without giving any definition. COLREGs even allow for the rules to be broken to avoid an accident. Due to this, traditional planning approaches may not be able to handle complex scenarios that are underspecified according to COLREGs. An alternative is the use of machine learning (ML), reinforcement learning (RL) and imitation learning (IL) at the core of autonomous navigation systems. Machine learning is known to succeed and outperform traditional approaches specially in vaguely defined problem domains, where it is difficult, if not impossible, to create a full formal specification of the phenomenon under study. We consider this to be the case for COLREGs-based navigation and we conjecture that a ML-based navigation approach can outperform existing search-based and optimization algorithms.@en

We propose a method for scenario-based testing of maritime collision avoidance systems. The goal is to test an autonomous agent in scenarios that can lead to an unacceptable risk of collision or may clearly not comply with the International Regulations for Preventing Collisions at Sea (COLREGs).Our method is based on the use of a discriminating artificial neural network that is trained online while performing the testing of the agents. Our experimental results show that the proposed algorithm generates test suits composed mostly of challenging scenarios. This allows us to validate quickly if the agent under test can perform the collision avoidance maneuvers safely while abiding the COLREGs. @en

This paper explores the state of the art on to methods to verify and validate navigation algorithms for autonomous surface ships. We perform a systematic mapping study to find research works published in the last 10 years proposing new algorithms for autonomous navigation and collision avoidance and we have extracted what verification and validation approaches have been applied on these algorithms. We observe that most research works use simulations to validate their algorithms. However, these simulations often involve just a few scenarios designed manually. This raises the question if the algorithms have been validated properly. To remedy this, we propose the use of a systematic scenario-based testing approach to validate navigation algorithms extensively.@en

We introduce WEBRSIM, the first web-based simulator for reaction systems. The simulator has an easy-to-use interface where the input is a reaction system and four functionalities: the computation of the interactive process driven by a given context sequence, the behaviour graph of the reaction system, its conservation dependency graph, and all its conserved sets. WEBRSIM comes with a browser-based friendly interface and offers a fast software to support computational modeling with reaction systems.@en

Reaction systems, a mathematical formalism inspired by the mechanisms within a biological cell, focuses on an abstract set-based representation of chemical reactions via facilitation and inhibition. The simple yet elegant nature of reaction systems makes them ideal tools for analysing qualitatively the phenomena which typically are dealt with quantitatively. Steady states are one of the well studied and important subjects across various fields of science ranging from biology, to chemistry, to engineering and economics. Finding all steady states of an arbitrary reaction system has been shown to be an NP-complete problem. We study reaction systems with a small number of reactants and inhibitors and we propose an algorithm to list all steady states of such reaction systems. We also show that the complexity of such an algorithm is polynomial. This reduction in complexity opens a door to transform modelling with reaction systems from an abstract concept to a tool that can be used on real-life case studies.@en

Quantitative models may exhibit sophisticated behaviour that includes having multiple steady states, bistability, limit cycles, and period-doubling bifurcation. Such behaviour is typically driven by the numerical dynamics of the model, where the values of various numerical parameters play the crucial role. We introduce in this paper natural correspondents of these concepts to reaction systems modelling, a framework based on elementary set theoretical, forbidding/enforcing-based mechanisms. We construct several reaction systems models exhibiting these properties.@en

Quantitative model refinement is an essential step in the model development cycle. Starting with a high level, abstract representation of a biological system, one often needs to add details to this representation to reflect changes in its constituent elements. Any such refinement step has two aspects: One structural and one quantitative. The structural aspect of the refinement defines an increase in the resolution of its representation, while the quantitative one specifies a numerical setup for the model that ensures its fit preservation at every refinement step. We discuss in this paper the implementation of quantitative model refinement in four extensively used biomodeling frameworks: ODE-based models,@en

There has been much progress in recent years towards building larger and larger computational models for biochemical networks, driven by advances both in high throughput data techniques, and in computational modeling and simulation. Such models are often given as unstructured lists of species and interactions between them, making it very difficult to understand the logicome of the network, i.e. the logical connections describing the activation of its key nodes. The problem we are addressing here is to predict whether these key nodes will get activated at any point during a fixed time interval (even transiently), depending on their initial activation status. We solve the problem in terms of a Boolean network over the key nodes, that we call the logicome of the biochemical network. The main advantage of the logicome is that it allows the modeler to focus on a well-chosen small set of key nodes, while abstracting away from the rest of the model, seen as biochemical implementation details of the model. We validate our results by showing that the interpretation of the obtained logicome is in line with literature-based knowledge of the EGFR signalling pathway.@en

Reaction systems are a new mathematical formalism inspired by the living cell and driven by only two basic mechanisms: facilitation and inhibition. As a modeling framework, they differ from the traditional approaches based on ODEs and CTMCs in two fundamental aspects: their qualitative character and the non-permanency of resources. In this article we introduce to reaction systems several notions of central interest in biomodeling: mass conservation, invariants, steady states, stationary processes, elementary fluxes, and periodicity. We prove that the decision problems related to these properties span a number of complexity classes from P to NP- and coNP-complete to PSPACE-complete.@en

Reaction systems is a new mathematical formalism inspired by the biological cell, which focuses on an abstract set-based representation of chemical reactions via facilitation and inhibition. In this article we focus on the property of mass conservation for reaction systems. We show that conservation of sets gives rise to a relation between the species, which we capture in the concept of the conservation dependency graph. We then describe an application of this relation to the problem of listing all conserved sets. We further give a sufficient negative polynomial criterion which can be used for proving that a set is not conserved. Finally, we present a simulator of reaction systems, which also includes an implementation of the algorithm for listing the conserved sets of a given reaction system.@en

There is growing interest in creating large-scale computational models for biological process. One of the challenges in such a project is to fit and validate larger and larger models, a process that requires more high-quality experimental data and more computational effort as the size of the model grows. Quantitative model refinement is a recently proposed model construction technique addressing this challenge. It proposes to create a model in an iterative fashion by adding details to its species, and to fix the numerical setup in a way that guarantees to preserve the fit and validation of the model. In this survey we make an excursion through quantitative model refinement – this includes introducing the concept of quantitative model refinement for reaction based models, for rule-based models, for Petri nets and for guarded command language models, and to illustrate it on three case studies (the heat shock response, the ErbB signaling pathway, and the self-assembly of intermediate filaments).@en

The iterative process of adding details to a model while preserving its numerical behavior is called quantitative model refinement, and it has been previously discussed for ODE-based models and for kappa-based models. In this paper, we investigate and compare this approach in three different modeling frameworks: rule-based modeling, Petri nets and guarded command languages. As case study we use a model for the eukaryotic heat shock response that we refine to include the acetylation of the heat shock factor. We discuss how to perform the refinement in each of these frameworks in order to avoid the combinatorial state explosion of the refined model. We conclude that Bionetgen (and rule-based modeling in general) is well-suited for a compact representation of the refined model, Petri nets offer a good solution through the use of colors, while the PRISM refined model may be much larger than the basic model.@en

Reaction systems are a formal framework for modeling processes driven by biochemical reactions. They are based on the mechanisms of facilitation and inhibition. A main assumption is that if a resource is available, then it is present in sufficient amounts and as such, several reactions using the same resource will not compete concurrently against each other; this makes reaction systems very different as a modeling framework than traditional frameworks such as ODEs or continuous time Markov chains. We demonstrate in this paper that reaction systems are rich enough to capture the essential characteristics of ODE-based models. We construct a reaction system model for the heat shock response in such a way that its qualitative behavior correlates well with the quantitative behavior of the corresponding ODE model. We construct our reaction system model based on a novel concept of dominance graph that captures the competition on resources in the ODE model. We conclude with a discussion on the expressivity of reaction systems as compared to that of ODE-based models.@en

The simple intramolecular model for gene assembly in ciliates consists of three molecular operations, simple ld, simple hi and simple dlad. Mathematical models in terms of signed permutations and signed strings proved limited in capturing some of the combinatorial details of the simple gene assembly process. Brijder and Hoogeboom introduced a new model in terms of overlap-inclusion graphs which could describe two of the three operations of the model and their combinatorial properties. To capture the third operation, we extended their framework to directed overlap-inclusion (DOI) graphs in Azimi et al. (2011) [1]. In this paper we introduce DOI graph-based rewriting rules that capture all three operations of the simple gene assembly model and prove that they are equivalent to the string-based formalization of the model.@en

The simple intramolecular model for gene assembly in ciliates consists of three molecular operations based on local DNA manipulations. It was shown to predict correctly the assembly of all currently known ciliate gene patterns. Mathematical models in terms of signed permutations and signed strings proved limited in capturing some of the combinatorial details of the simple gene assembly process. A different formalization in terms of overlap-inclusion graphs, recently introduced by Brijder and Hoogeboom, proved well-suited to describe two of the three operations of the model and their combinatorial properties. We introduce in this paper an extension of the framework of Brijder and Hoogeboom in terms of directed overlap-inclusion graphs where more of the linear structure of the ciliate genes is described. We investigate a number of combinatorial properties of these graphs, including a necessary property in terms of forbidden induced subgraphs.@en