| 1. |
- Bumann, Adrian, et al.
(författare)
-
Predicting the spread of invasive marine species with open data and machine learning: Process and Challenges
- 2021
-
Ingår i: International Conference on Marine Data and Information Systems (IMDIS) 2021.
-
Konferensbidrag (refereegranskat)abstract
- One of the world’s most complex marine challenges is the spread of invasive species. Invasive species cause severe harm to marine ecosystems and the people who depend on them, with economic impact alone amounting to several billion dollars annually. Recent advances in data science and artificial intelligence (AI) along with the increasing availability of free marine and other data online are improving the possibility to tackle these challenges. This paper presents the efforts by Ocean Data Factory Sweden (ODF Sweden), a data-driven innovation consortium in Gothenburg, to apply machine learning (ML) to one use case – the prediction of the spread of the Killer Shrimp, or Dikerogammarus Villosus, into the Baltic Sea (Figure 1). We discuss our process to address this use case as well as some reflections on the process and its challenges, in particular when taking into consideration the FAIR (findable, accessible, interoperable and reusable) principles in data science.
|
|
| 2. |
- Bumann, Adrian, et al.
(författare)
-
The Killer Shrimp Invasion Challenge on Kaggle: An online competition tackling the spread of invasive marine species through machine learning
- 2021
-
Ingår i: International Conference on Marine Data and Information Systems (IMDIS) 2021.
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- The world faces numerous complex marine challenges, such as overfishing, the spread of invasive species, and rising sea levels. These challenges are interconnected with the 17 UN Sustainable Development Goals, and in particular Goal #14 - Life below water. A paradox for any action related to the ocean is that while there is an enormous lack of ocean data, there is also an abundance of online marine and geo data that could be used to develop solutions through the application of artificial intelligence (AI). Open innovation and crowdsourcing could be a solution to such complex problems; however, applying data science to solve marine challenges through these open strategies is limited. Responding to the above, Ocean Data Factory Sweden (ODF Sweden), a data-driven innovation consortium in Gothenburg, developed an online competition, The Killer Shrimp Invasion Challenge (Figure 1). The competition was launched on the data science competition platform, Kaggle, in the spring of 2020 to address the spread of the invasive Killer Shrimp through applying machine learning (ML) to online data. This paper will describe the Killer Shrimp use case, the launch of the Kaggle competition, competition results and reflections on this form of tackling marine challenges.
|
|
| 3. |
- Burden, Håkan, et al.
(författare)
-
Accelerating Acquisition in an Open Innovation Ecosystem
- 2019
-
Ingår i: Proc of Twenty-fifth Americas Conference on Information Systems.
-
Konferensbidrag (refereegranskat)abstract
- Maritime transports are to be regarded as a self-organized ecosystem (Kay et al., 1999) characterized by sub-optimization where historically each actor to has optimized its own operations, often giving rise to inefficiencies as a whole. In recent years however, digital transformation has challenged this by providing means for enhanced transparency in data sharing and situational awareness, enabling better coordination and improved efficiency on the whole (Lind et al. 2018a). Digital transformation drives the possibilities of creating new value by enabling higher degrees of connectivity between actors, digitally twin physical objects, drawing patterns of behaviour based on extensive sets of historical data, as well as harmonizing data sharing through standardized interfaces and communication protocols (e.g. Almirall and Casadesus-Masanell 2010; Gassman et al. 2010; Lakhani et al. 2006). To break existing patterns of behaviour and to avoid the creation of proprietary solutions that feed sub-optimization, there is a need for new inspiration and perspectives that capitalize on the opportunities that digital transformation provides. From an open innovation point of view, this means that innovators both having experience from the sector as well as from other sectors would come together, come up with, and provide new applications not previously possible or never thought about before. A core capability that the ecosystem needs to develop and ensure is data streams made accessible for those that can provide new applications aimed for the single actor and/or clusters of actors, within or outside the maritime sector (Lind et al. 2018).This has also been one of the objectives for Port Collaborative Decision Making (PortCDM), which is a concept that provides guidelines and standards for the data exchange within and between ports, between ships and ports, and between ports and hinterland operators (Lind et al 2018). Such data exchange is necessary if enhanced efficiency during port call operations is to be achieved but also facilitates open innovation within the maritime sector. In order to realise that potential, a purposive transfer of knowledge between the established actors and potential new service providers has to be established (Chesbrough 2006). We therefore set out to explore How can open innovation intermediaries accelerate acquisition in an ecosystem through the management and throughput of knowledge transfer?We address the question through a longitudinal study by applying an action research approach involving actors from the local port and students from three bachelor programs. Before we describe the specifics of the research methodology, we outline our theoretical framework in terms of how knowledge transfer can be framed within an open innovation ecosystem. After the research methodology we detail the five iterations and then discuss the effect on knowledge transfer within the ecosystem. Finally, we conclude and give directions on future research.
|
|
| 4. |
- Jansson, Emmelie Å, et al.
(författare)
-
A mammalian functional nitrate reductase that regulates nitrite and nitric oxide homeostasis
- 2008
-
Ingår i: Nature Chemical Biology. - : Springer Science and Business Media LLC. - 1552-4450 .- 1552-4469. ; 4:7, s. 411-417
-
Tidskriftsartikel (refereegranskat)abstract
- Inorganic nitrite (NO(2)(-)) is emerging as a regulator of physiological functions and tissue responses to ischemia, whereas the more stable nitrate anion (NO(3)(-)) is generally considered to be biologically inert. Bacteria express nitrate reductases that produce nitrite, but mammals lack these specific enzymes. Here we report on nitrate reductase activity in rodent and human tissues that results in formation of nitrite and nitric oxide (NO) and is attenuated by the xanthine oxidoreductase inhibitor allopurinol. Nitrate administration to normoxic rats resulted in elevated levels of circulating nitrite that were again attenuated by allopurinol. Similar effects of nitrate were seen in endothelial NO synthase-deficient and germ-free mice, thereby excluding vascular NO synthase activation and bacteria as the source of nitrite. Nitrate pretreatment attenuated the increase in systemic blood pressure caused by NO synthase inhibition and enhanced blood flow during post-ischemic reperfusion. Our findings suggest a role for mammalian nitrate reduction in regulation of nitrite and NO homeostasis.
|
|
