DISA

Centre for Data Intensive Sciences and Applications

New PhD-seminar series in Computer Science

2022-10-01

In Computer Science at Linnaeus University we have different types of PhD-students. Our regular PhD-students, DISA-PhD-students and DIA-PhD-students and will hopefully be approved of getting a second intake for DIA starting next semester. Our PhD-students do not regularly meet these days and we want to change this. This will be an opportunity for PhD-students, supervisors from the university and industry to meet and discuss and provide a structured knowledge exchange.

We are working to increase the quality and formal processes for all of our PhD-students and as a first step we will introduce monthly PhD-seminars starting beginning of November 2022.

We will meet first Friday of each month between 14-16 preferably onsite but if it’s not possible we will provide the possibility to connect online too. During each seminar 2 PhD-students will get the chance to present their research and status for 30 min followed by a Q& A for 20-25 min with a coffee break in between.

Keep your eyes open for more information

/Diana

DISA Seminar May 9th

2022-05-06

Welcome to our DISA seminar with invited guest Themis Palpanas from The Data Intelligence Institute of Paris (diiP).

  • When? Monday May 9th 12-13
  • Where? Via Zoom – link will be sent to those who sign up
  • Registration: https://forms.gle/nE4nsNTKfy2FJ4pm7

Data Intelligence Institute of Paris: Creating a diiP Connection to DISA and Linnaeus University
The Data Intelligence Institute of Paris (diiP) is an interdisciplinary initiative of Université Paris Cité (France). It is a laboratory that fosters and supports the emergence of interdisciplinary practices around data science and data intelligence. It gathers researchers from formal sciences, physical sciences, life sciences and social sciences. In this talk, we will describe the goals of diiP and its operation, and try to draw parallels with DISA. We hope that this seminar will initiate discussions and eventually collaborations between the two institutes and universities.

Themis Palpanas is Senior Member of the French University Institute (IUF), a distinction that recognizes excellence across all academic disciplines, and professor of computer science at the University of Paris (France), where he is director of the Data Intelligence Institute of Paris (diiP), and director of the data management group, diNo. He received the BS degree from the National Technical
University of Athens, Greece, and the MSc and PhD degrees from the University of Toronto, Canada. He has previously held positions at the University of California at Riverside, University of Trento, and at
IBM T.J. Watson Research Center, and visited Microsoft Research, and the IBM Almaden Research Center.

His interests include problems related to data science (big dataanalytics and machine learning applications). He is the author of 9 US patents (3 of which have been implemented in world-leading commercial data management products), and 2 French patents. He is the recipient of 3 Best Paper awards, and the IBM Shared University Research (SUR) Award. He is currently serving on the VLDB Endowment Board of Trustees, as an Associate Editor in the TKDE, and IDA journals, as well as on the
Editorial Advisory Board of the IS journal, and the Editorial Board of the TLDKS Journal. He has served as Editor in Chief for the BDR Journal (that he drove to an impact factor of 3.578 and cite score of
8.6), as General Chair for VLDB 2013, Associate Editor for VLDB 2022, 2019 and 2017, and Research PC Vice Chair for ICDE 2020.

DISA Seminar April 4th Marie Skłodowska Curie postdoctoral fellowships (MSCA-PF)

2022-03-10

  • When? April 4th, 2022 12-13
  • Where? Online, you will get a link to the event when you have registered
  • Registration: https://forms.gle/M88bznTfa8CYDjjY7

DISA welcomes you to an information seminar focused on information and advice on how to develop a competitive proposal in the upcoming call for Marie Skłodowska Curie postdoctoral fellowships (MSCA-PF). The seminar will include presentations illustrating four relevant perspectives – key information, evaluation of proposals, hosting an MSCA-PF fellow and being an MSCA-PF fellow. As a fellow you apply for the fellowship with a PI, and as a PI you apply for the fellowship with an identified fellow. The seminar will provide researchers interested in becoming a supervisor for a MSCA PF with information on the fellowship programme, the requirements of a supervisor, practical information, and insights on how to write a competitive proposal from the supervisor’s perspective.

The MSCA PF tool is an outstanding prospect to expand your research group by an extremely skilled and funded postdoctoral researcher for two years while adding complementary skills and competencies to your group.

Speakers:

From the programme:

  • What is MSCA Postdoctoral Fellowships?
  • Proposal writing process
  • What is required from you as a Supervisor? The MSCA Guidelines on Supervision.
  • LNU as a host institution
  • Yes, I want to be a MSCA supervisor. What do I do now?
  • Experiences from a LNU MSCA PF Supervisor
  • Q&A

About MSCA PF

The objective of the Horizon Europe MSCA-PFs is to support researchers’ careers and foster excellence in research. The Postdoctoral Fellowship’s action targets researchers holding a PhD who wish to carry out their research activities abroad, acquire new skills and develop their careers. PF grants help researchers gain experience in other countries, disciplines and non-academic sectors. The grant usually covers two years’ salary, a mobility allowance, research costs and overheads for the host institution. Applications should be co-written by the researcher and the host organization. MSCA PF is open to all scientific disciplines.

Visit the European Commission’s website for additional information.

 

Webinar on Linked Open Data in Cultural Heritage

2022-02-15

Welcome to the webinar titled: Semantic metadata enrichment and data augmentation of small museum collections following the FAIR principles

Abstract: The lecture will present the benefits and challenges of making the cultural heritage data of small regional museums findable, accessible, interoperable and reusable (FAIR). Using the Archaeological Museum of Tripoli, Greece, as a case study, it demonstrates how the employment of semantic methods, such as semantic enrichment and linking to Linked Data resources, and semantic technologies, such as the CIDOC-Conceptual Reference Model (CRM) and other standard ontologies, can help alleviate some of these challenges and help small museums make their data FAIR. It also discusses how a semantics-based approach can facilitate collaboration between Digital Humanities and Information Studies researchers, and cultural heritage institutions, by providing a common means of communication that means cultural heritage data can be reused, repurposed, and redeployed efficiently.

Welcome!

 

KvarkenSat Innovation Challenge 2022 on Sustainable Forestry

2022-02-10

The DISA forestry group invites you to KvarkenSat Innovation Challenge 2022 on Sustainable Forestry that will start in next week with a pre-hackathon followed by the hackathon using space-based data helping to combat climate change!

Acceptance based on submission, the best submissions may be approved early.

The challenges

Climate change brings about major changes affecting us all. Extreme weather events become more frequent and especially the amount of rainfall increases in Northern Europe, one contributor being the warmer winters. New species of both vegetation and animals enter new areas while the existing species might have even major changes in their habitats. These lead to new challenges in the forestry industry. We are looking for ideas and solutions combining existing knowledge and datasets with space-based data and datasets based on satellite measurements, in four particular themes including soil moisture, spruce bark beetles, forest ground damage and the forest value chain.

Who can apply?

The hackathon is open to students, teachers, researchers and start-ups in teams of 3-5 persons. Relevant expertise to participate include: space and satellite data, machine learning and neural networks, computer science, positioning systems, automation, image processing/recognition, engineering, logistics, business/communications and forestry.

Awards

The three best proposals across all of the themes will be awarded a cash prize (over 100 000SEK) and possible continuation/acceleration within start-ups and innovation programs.

Pre-Hack Webinar

To get familiar with the hackathon, meet the mentors and partners, and participate in Q&A-session join our webinar on 15 February at 13.00 (14.00 Finnish time).

Link to the join the webinar: https://bit.ly/KvarkenSatWebinar

More information about the hackathon: https://ultrahack.org/kvarkensat-innovation-challenge-2022

Baltic-Adriatic Summer School on Digital Humanities

2022-01-25

  • When: 13 – 17 June 2022
  • Where: Zadar, Croatia
  • Language: English
  • Duration: 5 days

We are happy to announce the BAL-ADRIA Summer School on Digital Humanities 2022!

BAL-ADRIA is a collaboration between countries surrounding the Baltic Sea, and countries surrounding the Adriatic Sea, thus connecting Northern and Southern Europe. In a supportive academic environment, we are offering good-sized classes ideal for learning, discussing and getting feedbacks on your ideas and thoughts. This year’s Programme is taught by an international team of researchers and practitioners of digital humanities and social sciences and is delivered in a form of lectures, seminars and practical workshops. Two topics will be covered, equalling together:

  • Digital humanities research tools
  • Fundamentals of programming for digital humanities

For more information and to register, please visit http://baladria.unizd.hr/.

DISA-DH researchers granted external infrastructure funding

2021-12-15

Professor Mikko Laitinen from DISA is one the principal investigators of a national consortium for digital humanities that was awarded research funding for building and upgrading of national and international research infrastructures in Finland.

Academy of Finland last week granted nearly 36 million euros between 15 research infrastructures. Laitinen is a member of FIN-CLARIAH, which is a national research infrastructure for digital and computational social sciences and the humanities, comprising two components: the first supports research based on various language resources, and the other one develops digital infrastructure tools and solutions for large and heterogeneous datasets for the humanities and social sciences. Laitinen points out that the connections and especially the interdisciplinary research on social media that was carried out in the first DISA period were integral in becoming part of this national consortium.

For more information, please contact mikko.laitinen@lnu.se

DISA Lunch seminar – Industry – Novotek

2021-11-30

Welcome to a DISA Industry Seminar with Novotek. There is a genuine interest to find research collaboration related to water and wastewater management together with them and Kalmar Vatten.

  • When? December 9th 12-13
  • Where? Online – you will get a link when you register
  • Registration? https://forms.gle/FUtjyV4H7kYRcegB6

During the seminar you will meet Thomas Lundqvist

In Swedish water and wastewater management, there are great opportunities to create large savings and environmental benefits by starting to work systematically with advanced data analysis, which is often called “analytics” or “machine learning”. Examples of areas where this methodology has great potential are:

  • Leak detection and leak detection in water and sewage systems.
  • Reduction of chemical consumption in the water purification process
  • Improving water quality
  • Reduction of energy consumption
  • Improved control of flue gas production which leads to increased process yield. Simply more biogas from the same amount of feedstock.

Although the analysis technique has been known for a long time, there are some challenges when starting to work with this in, for example, a municipal treatment plant. It requires a certain type of competence that is usually not available in a simple way. Advanced software is also required for this purpose. Once you have acquired the skills and tools, you come to the problem that is usually even more difficult to solve. There is a lack of sufficient data. This may be because:

  • You do not have enough sensors that measure relevant things.
  • The sensors are not connected and the data is not stored.
  • If sensor values ​​are stored, the measurements are usually truncated incorrectly to save storage space and cost.
  • Large amounts of redundant information are often stored completely unnecessarily.

If you were to solve all this, you still have a big challenge as you lack other similar facilities to compare your analyzes with. There is a great potential to be able to share data between several municipalities and waterworks to learn from others and to simply get a much larger data base for their analyzes.
Novotek, together with Linnaeus University and Kalmar Vatten, wants to start a collaboration with the aim of finding a long-term solution together to the challenges that all waterworks and treatment plants face when society places increased demands on water treatment and water production, now and in the future!

Come and discuss with us and see how we can solve these challenges together!

DISA Seminar December 6th: Machine Learning for Astroparticle Physics

2021-11-22

Astroparticle physics is a sub-branch of Physics dealing with the detection of gamma-rays, neutrinos, gravitational waves and cosmic rays from the Universe. In this seminar, we will focus on the field of extragalactic gamma-ray astronomy.

The two main types of datasets in the field are those produced via simulations and those acquired via detector equipments (“real”), leading to a large amount of data to be calibrated, prepared, filtered, reconstructed and analysed. Simulations are especially needed in order to understand the sensitivity of the given equipment to a given searched physics “signal” and to prepare the data analysis procedure before looking at the real data. Decades of experience in data analysis in the field lead to the ability to publish solid results.

In this context, machine learning is giving a big boost in speeding up the data analysis procedures. The first successful applications of supervised Machine Learning in the field date back to the years 2010-2013 and concern classification and regression methods. Nowadays, there is a huge effort to exploit Deep Learning methods to achieve faster simulations and to improve the current data analysis methods, where physicists cannot “see” or “predict” any significant features describing the datasets.

I will present the current activities and future challenges of my research groups at Linnaeus University and at the University of Paris and, more generally, the challenges of the field.

Keywords: gamma-ray astronomy, supervised machine learning, event classification, feature regression

Papers:

  1. Y. Becherini et al., 2011 (Astrop. Phys., Vol 34, 12, 2011, 858-870)
  2. Y. Becherini et al., 2012 (Gamma 2012)
  3. Y. Becherini et al., 2012 (arXiv:1211.5997) 
  4. M. Senniappan et al
  5. T. Bylund et al.,