General

Welcome to Higher Research Seminar with Italo Masiello on November 17th

Friday, October 27th, 2023

Welcome to the last Higher Research Seminar of the year!

  • When? November 17th 14-15
  • Where? In B1006, Växjö or online

Title: Technology integration is about trust

Abstract:

We started our research project with a baggage of expectations about what we could do with data in compulsory education. Even greater expectation was reflected by the school principals we were working with. “Can we see this? And can we see that?”: asked the principals.

Two years after we started the project, we are standing on the finish line but have not crossed it yet. This means that we have not been able to “really” analyze (any which way) the data to create useful visualization dashboards. But we have learned a hack of a lot!
1. No data standards on site!
2. Digital inheritance is enormous!
3. Everyone develops as they please!
4. Competences are not at the top!
5. GDPR scares the “#€% out of everyone!
6. Local IT infrastructure is not in place!
7. OMG how many hours of dialog it took to get where we are today!
8. It is not about technology. It is about trust!

I will show you what we can do with the data, at this point in time only theoretically. I will also show you the technical infrastructure that Artemis, my doctoral student working with the data, has setup for integrating multiple datasets coming from different companies and schools. If you have experience of working with educational data from the primary school sector, I would also like to hear from you about ideas for future direction.

Welcome to our October PhD-seminar

Friday, September 15th, 2023

When? Friday October 6th 14-16
Where? Onsite: D1140 at Linnaeus University in Växjö and online
Registration: Please sign up for the PhD-seminar via this link https://forms.gle/dQLHkqx9ctt2ws82A by October 3rd (especially important if you plan on attending onsite so we have fika for everyone)

Agenda
14.00-14.10 Welcome and practical information from Welf Löwe
14.10-14.55 Presentation and discussion: Bridging the Gap: A Hybrid Recommendation System for E-Commerce Cold Start Challenges – Kailash Chowdary Bodduluri, Industry PhD-student HL Design
14.55 – 15.05 Coffee break
15.05 – 15.50 Presentation and discussion – Continuous Performance Management of Business Processes via Digital Twin and Model-Driven Architecture – Samuele Giussani, PhD student at LNU
15.50 -16.00 Sum up and plan for our next seminar on November 3rd

Bridging the Gap: A Hybrid Recommendation System for E-Commerce Cold Start Challenges Kailash Chowdary Bodduluri, Industry PhD-student HL Design

Abstract: In the dynamic landscape of e-commerce, effective recommendation systems play a pivotal role in enhancing user experiences and boosting sales. However, the ubiquitous cold start problem has long been a challenge in implementing recommendation systems, particularly for businesses like HL Design that provide smart webshops to e-commerce customers. To address this challenge, extensive research was conducted through a systematic literature review on hybrid recommendation systems in the e-commerce domain. This review aimed to identify existing algorithms in the literature and uncover potential areas for adaptation. The literature review revealed some existing research gaps in the context of dealing with cold start issues. To bridge these gaps, a novel hybrid recommendation system was developed. This system leverages product images and descriptions, identifies similar products based on user sessions, and incorporates historical sales data. By combining these diverse data sources, the developed system offers innovative solutions to tackle the persistent cold start challenges in recommendation systems. This seminar will delve into the journey of identifying these research gaps, developing the hybrid recommendation system, and exploring its effectiveness in addressing cold start issues. It promises to be an enlightening discussion for those navigating the complex realm of recommendation systems in e-commerce.”

Continuous Performance Management of Business Processes via Digital Twin and Model-Driven ArchitectureSamuele Giussani, PhD student at LNU

Business Process Management (BPM) deals with administrating the chains of events, activities, and decisions that add value to an organization. It is of particular interest to assess the business process performance in a continuous way, in order to gather as much information as possible to allow informed decisions in the value chain.

However, organizations are often complex and driven by several business-critical processes, that should be continuously monitored, evaluated, and managed to deliver value-added products and services to customers. To this end, we employ a Digital Twin of the Organization (DTO), which is a virtual representation of the organization that includes all the actors and activities implementing the business processes, to estimate and analyze the relevant Key Performance Indicators (KPIs).

The notation commonly adopted in BPM is distant from what a DTO can use to produce its results, so we introduce Biz2Sim, a model transformer tool that leverages the Model-Driven Architecture (MDA) approach to obtain simulation models from the Business Process Model and Notation (BPMN). By incorporating both Biz2Sim and the DTO in the traditional BPM lifecycle, performance assessment can be performed with real-time data and with an increased degree of automation.

Welcome to the Higher Research Seminar in Computer Science on September 22nd

Wednesday, September 6th, 2023

Professor Mauro Caporuscio will give a seminar on September 22nd 14-15 about Green Software by Design. It is possible to attend the seminar either onsite or online. If you are interested in joining please send an email to diana.unander@lnu.se.

Abstract
Despite the media interest in sustainability, the public is still unaware that software, including digital assistants, cryptocurrencies, audio/video streaming services, finances, and games, are predicted to account for as much as 14% of the total worldwide carbon footprint in the next decade. Indeed, all software consumes electricity. In general, people think electricity is clean. Still, since most electricity is produced through burning fossil fuels (e.g., coal, oil, and natural gas), in practice, electricity is the single most significant cause of carbon emissions worldwide. Further, all the devices we use for running software (from our smartphones/computers to network appliances, and to cloud infrastructures) produce carbon when manufactured and disposed of (once they reach the end of life). The two most effective ways to reduce the carbon emissions of software are through Energy efficiency, and Hardware longevity. Unfortunately, current software development projects usually treat these concerns as an afterthought: a desirable quality to be considered if and only if other stakeholder- and economy-centered requirements (e.g., performance, business needs) have been successfully addressed. To face this unsustainable trend, we need a paradigm shift in the way we engineer and operate software systems. Indeed, the software shall be designed from the foundation to be green.

The aim of this talk is to bring these aspects to your attention and to hint at future research directions toward the reconciliation of three different and typically conflicting aspects: (1) efficiency: the ability to limit energy consumption, (2) longevity: the ability to live long and prevent hardware obsolescence, and (3) efficacy: the ability to meet the users’ expectations.

Welcome to our September PhD seminar!

Wednesday, August 23rd, 2023
  • When? Friday September 1st 14-16
  • Where? Onsite: D1172 at Linnaeus University in Växjö and online
  • Registration: Please sign up for the PhD-seminar via this link https://forms.gle/PENhmNcQVBRx8ipR9 by August 30th (especially important if you plan on attending onsite so we have fika for everyone)

Agenda
14.00-14.10 Welcome and practical information from Welf Löwe
14.10-14.55 Presentation and discussion: Digitalization of Work Instructions Gaurav Garg, Industry PhD-student Virtual Manufacturing
14.55 – 15.05 Coffee break
15.05 – 15.50 Presentation and discussion – Towards Smarter Organization; Digital Twin of the Organization Approach – Farid Edrisi, PhD student at LNU
15.50 -16.00 Sum up and plan for our next seminar on October 6th

(more…)

Welcome to our June PhD-seminar in 2023

Friday, May 5th, 2023
  • When? June 2nd 14.00 – 16.00
  • Where? D1172 – Växjö (link will provided for those who wants to attend online)
  • Registration: We would like to know how many that will attend onsite/online in order to get some fika for those onsite. So please register by May 30th  https://forms.gle/QHnUTeGkyYdb8dDe9 

Agenda

14.00-14.10     Welcome and practical information from Welf Löwe

14.10-14.55     Presentation and discussion: Title: Towards Better Product Quality: Identifying Legitimate Quality Issues through NLP & Machine Learning Techniques – Rakshanda Jabeen, Industry PhD-student at Electrolux Professional

14.55 – 15.05  Coffee break

15.05 – 15.50  Presentation and discussion – Title: Clustering and Modeling Large Social Networks – Masoud Fatemi, DISA PhD-student from Digital Humanities

15.50 -16.00    Sum up and plan for our next seminar on September 1st

(more…)

First publication from our Industry PhD-students at Volvo CE is published!

Wednesday, March 8th, 2023

Volvo CE is a major player in the construction business and leads the development of machines and technologies for sustainability, autonomy, and connectivity. An enabler for this technology transformation is smart usage and integration of machine operation data and computer simulations. To increase the knowledge in Volvo CE, a cooperation with the Linnaeus University started and Manoranjan Kumar and Joel Cramsky became two of the first industry PhD-students in DIA.

Something that most developers in industry do not do in their daily work is to share their knowledge in publications, but it’s an important part during the PhD-studies. One part of these studies has led to a paper within Data Science, “A prediction model for exhaust gas regeneration(EGR) clogging using offline and online machine learning” and it was recently published as a part of the Conference Proceedings of the 7th International Commercial Vehicle Technology Symposium.

For more information about the publication see: https://link.springer.com/chapter/10.1007/978-3-658-40783-4_13 

Welcome to our first PhD-seminar in 2023

Monday, December 19th, 2022

When? January 13th, 14-16
Where? D1140 – Växjö (link will provided for those who wants to attend online)
Registration: We would like to know how many that will attend onsite/online in order to get some fika for those onsite. So please register by January 11th https://forms.gle/mxHmRtdEydUWGoa79

Agenda
14.00-14.10 Welcome and practical information from Welf Löwe
14.10-14.55 Presentation and discussion: Exploiting Automatic Change Detection in Software Process Evolution for Organizational Learning – Sebastian Hönel
14.55 – 15.05 Coffee break
15.05 – 15.50 Presentation and discussion – Design and implementation of factory-integrated machine learning models and case studies of ongoing data-driven projects – Felix Viberg
15.50 -16.00 Sum up and plan for our next seminar on February 13th

Abstracts

(more…)

Invitation: Research Seminar 9/12 11-12

Tuesday, November 15th, 2022

Title: “Roadmaps for AI Integration in the Rail Sector: Current Project Results and Overview of Case-Studies”

Abstract: Artificial Intelligence (AI) is increasingly affirming as a game-changer technology in several sectors, including rail transport. The overall objective of the H2020 Shift2Rail project RAILS (Roadmaps for AI Integration in the raiL Sector) is to investigate the potential of AI in the rail sector and to contribute to the definition of roadmaps for future research in the context of railway maintenance and inspection, autonomous train driving, and traffic planning and management. This seminar will provide a high-level overview of the RAILS project, presenting the main topics, objectives, ongoing research activities, and preliminary results achieved. Particular attention will be given to the current investigations towards the application of Deep Learning approaches to improve the maintainability of railway assets and the safety of autonomous trains. To be specific, two main case studies will be discussed, and recent advancements presented, concerning smart maintenance at level crossings and vision-based obstacle detection on rail tracks.

Speaker: Lorenzo De Donato (Visiting PhD at LNU) he is a Ph.D. Student in Information Technology and Electrical Engineering. When Lorenzo is not in Sweden visiting us he can be found at the Department of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, Italy

Contact information: lorenzo.dedonato@unina.it

 

Welcome to our first PhD-seminar November 4th

Saturday, October 15th, 2022
  • When? November 4th 14-16
  • Where? D1140 – Växjö (link will provided for those who wants to attend online)
  • Registration: We would like to know how many that will attend onsite/online in order to get some fika for those onsite. So please register by November 2nd https://forms.gle/ZwwgoQ4JK4e41BBR6

 Agenda

14.00-14.10     Welcome and practical information from Welf Löwe

14.10-14.55     Presentation and discussion: Visual Analytics for Explainable Machine Learning in a Nutshell – Angelos Chatzimparmpas

14.55 – 15.05  Coffee break

15.05 – 15.50  Presentation and discussion: Getting the most out of health data, combing the best of two worlds – Olle Björneld

15.50 -16.00    Sum up and plan for our next seminar on January 13th

Abstracts

Visual Analytics for Explainable Machine Learning in a Nutshell – Angelos Chatzimparmpas

Machine learning (ML) research has recently gained much attention, with various models proposed to understand and predict patterns and trends in data originating from various domains. Unfortunately, users find it harder to evaluate and trust the results of these models as they become more complex because most of their internal workings are kept in secret black boxes.

One possible solution to this problem is the explanation of ML models with visual analytics (VA) since it enables human experts to analyze large and complex information spaces such as data and model spaces. By doing so, evidence has shown an improvement in predictions and an increase in the reliability of the results.

This talk aims to provide an overview of the state-of-the-art in explainable and trustworthy ML with the use of visualizations, as well as the development of VA systems for each stage of a typical ML pipeline. Furthermore, we will briefly introduce some of these tools and discuss how such VA techniques can help us not only understand ML models but also do this in a human-centered and steerable way.

Getting the most out of health data, combing the best of two worlds – Olle Björneld

Machine learning driven knowledge discovery on real world data based on domain knowledge. Real world data does not comply with machine learning models very well and prediction models perform suboptimal if pre-processing of data is deficient.

Based on experience from medical registry studies using electronic health data (EHR) performed in collaboration with domain experts, data analyst and statistician an automatic feature engineering framework and method have been developed. The framework is called automatic Knowledge Driven Feature Engineering (aKDFE) and have been evaluated by machine learning pipeline.

Experiment shows that prediction models performs better if aKDFE is used without losing explainability, but more experiments need to be performed in other domains to fully quantify the results. The key aspect is how to concentrate and mine inherent knowledge in transaction data to optimal machine learning driven prediction models.

A warm welcome,

Welf & Diana

New PhD-seminar series in Computer Science

Saturday, October 1st, 2022

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