DISA

Don’t miss the opportunity to come and listen to our invited lecture from Memorial University of Newfoundland – Dr. Vinicius Prado da Fonseca
Please sign up via this form by February 21st. https://forms.gle/wZ9YmV8Fu4AwbaQu5

Title: “Using ML/RL to develop visual and tactile sensing for the next generation of assistant devices and smart prosthesis”

Abstract:
The next generation of autonomous robotic assistants and semi-autonomous prostheses will focus on making object manipulation more predictable and reliable. Achieving these goals requires novel manipulation methods while obtaining and processing accurate object information. This presentation delves into recent investigations leveraging Machine Learning models and Reinforcement Learning methodologies to extract hand and object characteristics from visual and tactile data. Our ongoing research spans various domains, including robotic perception, human grasp analysis, and intention recognition. Specifically, we will showcase progress in haptic feedback integration, enhancing robot hand grasp stability, automatic texture recognition, precise surface reconstruction, and optimizing robotic disassembly tasks. Through these endeavors, we aim to illuminate pioneering approaches in employing machine learning models to analyze visual-tactile data, offering promising applications in automated hand control and biomedical engineering.

Bio:
Dr. Vinicius Prado da Fonseca , Ph.D., is an Assistant Professor in the Department of Computer Science at Memorial University of Newfoundland. In 2014, Dr. Prado was awarded the Science without Borders Ph.D. scholarship, and later, in 2020, obtained his Ph.D. degree in Electrical and Computer Engineering from the University of Ottawa, Canada. Dr. Prado’s area of expertise is robotic manipulation and visual and tactile robotic feedback, where he focuses on building the next generation of tactile sensing and perception combined with artificial intelligence, fuzzy logic controllers, and applied reinforcement/machine learning. In recent years, he has published over 30 peer-reviewed articles in leading conferences and journals such as IEEE ICRA, Springer Intelligent Robotics, and IEEE Transactions.
https://www.cs.mun.ca/~vpradodafons/

When? Friday March 15th 14-16
Where? Onsite: D2272 at Linnaeus University in Växjö and online
Registration: Please sign up for the PhD-seminar via this link https://forms.gle/ycGkmasndKvofBCE6 by March 13th (especially important if you plan on attending onsite so we have fika for everyone)

14.00-14.10 Welcome and practical information from Welf Löwe
14.10-14.55 Presentation and discussion: Advancements in IoT and AI Integration: Insights from Kalmar’s IoT Lab – Fredrik Ahlgren
14.55 – 15.05 Coffee break
15.05 – 15.50 Presentation and discussion – Data and sustainability – Jorge Zapizo
15.50 -16.00 Sum up and plan for our next seminar on April 19th

Abstracts

Advancements in IoT and AI Integration: Insights from Kalmar’s IoT Lab – Fredrik Ahlgren
In this seminar, Dr. Fredrik Ahlgren, Senior Lecturer at Linnaeus University, will outline the transformative journey of establishing the IoT Lab in Kalmar, showcasing its evolution from an initial concept to a thriving research hub. The presentation will highlight the lab’s innovative projects, such as connected beehives and the M/S Dessi connected ship initiative, alongside collaborative efforts with over 15 industry partners through pilot cases. Dr. Ahlgren will delve into the integration of AI for data analysis, including the use of ChatGPT for enhancing research outputs. The seminar will reference specific publications, such as the application of machine learning for fuel consumption prediction in maritime engineering and the use of reinforcement learning in IoT environments, underscoring the lab’s contribution to applied research in IoT and AI. Attendees will gain insights into the lab’s strategic approach to leveraging IoT and AI for addressing real-world challenges, highlighting the impact of these technologies on industry and education.

Data and sustainability – Jorge Zapico
Data can make sustainability issues visible and actionable: carbon emissions, biodiversity, energy, resource consumption, waste. These issues are complex, long term, systemic, and we have problems grasping them without support. Technology provides new ways to measure the current state, simulate future scenarios and options, and to get feedback about ongoing changes and interventions. Dr. Jorge Zapico, Senior Lecturer at Linnaeus University will present lesson learnt from developing prototypes and services for sustainability during the last 15 years, what he sees as the main contributions, risks and pitfalls, and which future innovation spaces lay ahead.

When? Friday March 1st 14-16
Where? Onsite: B1009 at Linnaeus University in Växjö and online
Registration: Please sign up for the PhD-seminar via this link https://forms.gle/1KCLvBZQph4Vs1cR7 by February 28th (especially important if you plan on attending onsite so we have fika for everyone)

14.00-14.10 Welcome and practical information from Welf Löwe
14.10-14.55 Presentation and discussion: Leveraging machine learning and large language models to map source code as natural language to architectural modules. – Nils Johansson, Industry PhD-student at Volvo CE
14.55 – 15.05 Coffee break
15.05 – 15.50 Presentation and discussion – Towards a Probabilistic Interactive Video Training Tool for Emergency Medical Services – Romain Herault, PhD-student at LNU
15.50 -16.00 Sum up and plan for our next seminar on April 5th

Abstracts

The 8th International Workshop on Formal Approaches for Advanced Computing Systems (FAACS 2024), co-located with the 21st IEEE International Conference on Software Architecture (ICSA 2024), will be held in IIIT Hyderabad, India June 4-8, 2024.

Important Dates:
– Submission Deadline: February 18, 2024
– Notification of Papers: March 17, 2024
– Camera Ready: March 31, 2024
– Workshop Date: June 4 – 5, 2024

Motivation and Scope
Cutting-edge technologies, infrastructures, and computational paradigms such as digital twin, cloud, fog, edge computing, IoT, digitalization, Industry 5.0, and cyber-physical systems are changing how data and services are delivered and used. Such systems have a significant and elaborate societal impact, making it paramount to guarantee essential qualities of the delivered product, such as dependability, reliability, safety, and availability. As new paradigms become pervasive in our everyday lives, new challenges also emerge in dealing with uncertainty, untrustworthiness, and information loss, affecting the software life cycle in different phases. Ensuring critical qualities requires a joint effort in devising advanced software architecture designs by the software architecture community and formal modeling and verification approaches by the formal methods community.

The main goal of the workshop is to foster integration between formal methods and software architecture promoting new connections and synergies between the two communities to address the challenges of the upcoming generation of computing systems. Aligned with the theme of the ICSA 2024, we welcome contributions on the potential and risks of generative AI in developing advanced software architectures and ensuring qualities like dependability, reliability, safety, and availability through formal modeling and verification.

Topics of Interest include (but are not limited to) the following:

When? Friday February 16th 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/FUV4yzLXLTwiSvQe9 by February 14th (especially important if you plan on attending onsite so we have fika for everyone)

14.00-14.10 Welcome and practical information from Welf Löwe
14.10-14.55 Presentation and discussion: Using Virtual Reality to gain insights – Aris Alissandrakis
14.55 – 15.05 Coffee break
15.05 – 15.50 Presentation and discussion – Cloud and HPC – Morgan Ericsson
15.50 -16.00 Sum up and plan for our next seminar on March 15th

Abstracts
Using Virtual Reality to gain insights – Aris Alissandrakis

This seminar will give a brief overview of recent work (2017-now) conducted by the VRxAR Labs research group.

The evolution of our immersive analytics system that went from “simple” data exploration to supporting hybrid asymmetric collaboration will be presented.
The focus will be on the motivations and decisions that informed the direction of this research, and the methodological approaches used to make sure that the system both a) did what it was supposed to and b) was perceived favorably by its users.

Given that VR is better experienced and understood by seen in motion, anyone interested in this is encouraged to check out our video demonstrations on [https://vimeo.com/vrxar].

Cloud and HPC – Morgan Ericsson

We’ll start by discussing what HPC, Cloud computing and related terms mean. We’ll then discuss how and when you should use a cloud environment, such as CSCloud, for HPC. The talk will illustrate the important concepts using CSCloud and discuss, e.g., virtual machines and networks, containers, orchestration, etc.

When? Friday February 2th 14-16
Where? Onsite: D2272 at Linnaeus University in Växjö and online
Registration: Please sign up for the PhD-seminar via this link https://forms.gle/H9oqD7duf23ibLfv7 by January 31st (especially important if you plan on attending onsite so we have fika for everyone)

14.00-14.10 Welcome and practical information from Welf Löwe
14.10-14.55 Presentation and discussion: Object Identification in Land Parcels using a Machine Learning Approach – Niels Gundermann, Industry PhD student at Data Experts
14.55 – 15.05 Coffee break
15.05 – 15.50 Presentation and discussion – Development of Visual Learning Analytic Tools to Explore Performance and Engagement of Students in Both Primary/Secondary and Higher Education – Zeynab Mohseni, PhD-student
15.50 -16.00 Sum up and plan for our next seminar on February 2nd

Abstracts

When? Friday January 19th 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/e5GiPpZpyc7UBznv8 by January 17^th (especially important if you plan on attending onsite so we have fika for everyone)

14.00-14.10 Welcome and practical information from Welf Löwe
14.10-14.55 Presentation and discussion: Virtual Ecosystems for Smart Sustainable City-districts – an architecture perspective – Jesper Andersson
14.55 – 15.05 Coffee break
15.05 – 15.50 Presentation and discussion – Self-adaptation: basic principles and industrial usage – Danny Weyns
15.50 -16.00 Sum up and plan for our next seminar on February 16th

Abstracts

Virtual Ecosystems for Smart Sustainable City-districts – an architecture perspective – Jesper Andersson

This talk will discuss architectural issues concerning establishing and operating a digital ecosystem. Digital ecosystems are becoming a foundation for value streams in multiple businesses and domains. The case we study is a smart-district platform, which shares challenges with the Smart-city.

This talk focuses on two concerns, the ecosystem’s platform architecture and architecture barriers to establishing and operating an ecosystem. We characterize sustainable product and service ecosystems in a smart-district ecosystem and discuss specific design alternatives. In a design process, certain architectural barriers impede ecosystem establishment and operation. We describe some categories with concrete examples from the case. In connection to the barriers, we describe specific architectural governance challenges and discuss some possible solutions. We discuss several avenues for future platform architecture and governance research.

Self-adaptation: basic principles and industrial usage – Danny Weyns
 
Self-adaptation enables a software system to reason about itself at runtime and adapt itself to realise a set of quality goals. Self-adaptation has been widely used in the software industry, but not necessarily known under the term self-adaptation. In this talk, I motivate the use of self-adaptation, outline the basic principles of self-adaptation, and report the results of a large-scale survey with practitioners on the use of self-adaptation in industry. 

When? Friday January 12th 14-16
Where? Onsite: B1006 at Linnaeus University in Växjö and online
Registration: Please sign up for the PhD-seminar via this link https://forms.gle/YsyLzBd7K6tL1hmX6 by January 10th (especially important if you plan on attending onsite so we have fika for everyone)

14.00-14.10 Welcome and practical information from Welf Löwe
14.10-14.55 Presentation and discussion: Senadin Alisic, PhD student Combitech
14.55 – 15.05 Coffee break
15.05 – 15.50 Presentation and discussion – Improving access to digital archives pertaining to the Sámi with HTR and automatic subject indexing, Johannes Widegren, PhD in Computer and Information Science at the Department of Cultural Sciences
15.50 -16.00 Sum up and plan for our next seminar on February 2nd

Abstracts

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.

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 Architecture – Samuele 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.