Agenda

Date and TimeTitle
Jan 10, 2020
1:00pm - 2:00pm (Pacific)
Sample Session Two

Sessions can be used to serve on-demand or live webcast and webinars to your attendees. Select the time of your event, and then specify whether you will be hosting a live or on-demand event. Turn on the desired sections of your Interaction Panel to encourage conversation among attendees.

Jun 16, 2020
11:00am - 11:30am (Tallinn)
Conference Opening
Jun 16, 2020
11:30am - 12:30pm (Helsinki)
Information Retrieval in the Neural Age

Speaker: Claudia Hauff

Information Retrieval in the Neural Age

 

ABSTRACT

In recent years, neural technologies have had a large impact on the field of information retrieval (IR): long-standing research problems (such as ad-hoc retrieval or passage retrieval) have seen large jumps in retrieval effectiveness and novel problems (such as conversational search) are tackled by default with neural approaches. IR though is not just the application of techniques developed in the NLP and ML communities. IR has unique research problems and approaches to research that distinguish it from other communities. In this talk, I aim to give insights into what some of the core problems of IR are, how they have been tackled in the past and how we curently view them in this neural age. In the process, I will highlight some of the research activities our group at TU Delft has explored in this area (such as axiomatic IR, curriculum learning for IR, search as learning).

 

SHORT BIO:

Claudia Hauff is an Associate Professor at the Web Information Systems group, Delft University of Technology (TU Delft) and a computer scientist by training. She received her PhD in 2010 from the University of Twente. In the past, she has worked on a variety of topics in the fields of information retrieval & data science, including query performance prediction, social search, learning to search and information retrieval for specific user groups. Together with a number of PhD students she currently focuses on the areas of collaborative search, complex search, and conversational search.

Jun 16, 2020
12:00pm - 12:11pm (Helsinki)
Analysis of legacy monolithic software decomposition into microservices

Authors: Justas Kazanavičius and Dalius Mažeika

Analysis of legacy monolithic software decomposition into microservices

 

ABSTRACT

Microservice architecture is becoming a standard by default in most of the enterprises because many projects have been implemented using this architecture in the last few years and results have been very positive. Extracting microservices from legacy monolithic software is an extremely complicated task. Each enterprise application is unique. This paper aims to investigate the existing methodologies of monolith decomposition into microservices. The same enterprise application was decomposed into microservices using 3 different methods. Evaluation criteria were proposed that were used to analyze advantages and disadvantages of each.

 

SHORT BIO:

Justas Kazanavicius is a first year informatic engineering doctoral student in Vilnius Gediminas Technical University. He has electronic engineering bachelor, informatic technology master degrees and more than 10 years experience as a software developer. One publication has been published: MIGRATING LEGACY SOFTWARE TO MICROSERVICES ARCHITECTURE at international conference eStream 2019, Vilnius.

Jun 16, 2020
12:12pm - 12:24pm (Helsinki)
Do We Really Know How to Measure Software Quality

Authors: Vineta Arnicane, Juris Borzovs and Anete Nesaule-Erina

Do We Really Know How to Measure Software Quality

 

ABSTRACT

Particular return to McCall’s et al. seminal work has been done in recent international standards ISO/IEC 25022:2016 and ISO/IEC 25023:2016. 122 lower level measures (metrics in McCall’s et al. terminology) were introduced. Authors of standards themselves classify quality measures as Highly Recommended, Recommended, Used at user’s Discretion and Generic, Specific. In this paper, quality measures are additionally classified also from the point of view of objectivity of measurement and of usage in industry.

 

SHORT BIO:

Anete Nesaule-Eriņa is a master program “Computer Science” student at Faculty of Computing, University of Latvia.

Jun 16, 2020
12:25pm - 12:37pm (Helsinki)
Floor Selection Proposal for Automated Travel with Smart Elevator

Authors: Uljana Reinsalu, Tarmo Robal and Mairo Leier

Floor Selection Proposal for Automated Travel with Smart Elevator

 

ABSTRACT

Elevators have been used for centuries to convey material and people, with a history going back to 19th century. Modern elevators as we use them today became widely used some 150 years ago, and regardless of many improvements and technological advancements, the general concept has remained the same. The typical elevator still needs traveller’s input to take the passenger from one floor to another. In this paper we explore the possibility to predict elevator passenger destination floor. For this task we use passenger profiles established through deep learning, and elaborate on the passenger’s trip history to predict the floor the passenger desires to travel. The study is based on a smart elevator system set up in a typical office building. The aim is to provide personalised elevator service in the context of a smart elevator.

 

SHORT BIO:

 

Jun 16, 2020
12:38pm - 12:50pm (Helsinki)
Change Discovery in Heterogeneous Data Sources of a Data Warehouse

Authors: Darja Solodovnikova and Laila Niedrite

Change Discovery in Heterogeneous Data Sources of a Data Warehouse

 

ABSTRACT

Data warehouses have been used to analyze data stored in relational databases for several decades. However, over time, data that are employed in the decision-making process have become so enormous and heterogeneous that traditional data warehousing solutions have become unusable. Therefore, new big data technologies have emerged to deal with large volumes of data. The problem of structural evolution of integrated heterogeneous data sources has become extremely topical due to dynamic and diverse nature of big data. In this paper, we propose an approach to change discovery in data sources of a data warehouse utilized to analyze big data. Our solution incorporates an architecture that allows to perform OLAP operations and other kinds of analysis on integrated big data and is able to detect changes in schemata and other characteristics of structured, semi-structured and unstructured data sources. We discuss the algorithm for change discovery and metadata necessary for its operation.

 

SHORT BIO:

Darja Solodovnikova is an associate professor and a researcher at the Faculty of Computing of the University of Latvia. She received her PhD in computer science in 2011 from the University of Latvia. The doctoral thesis covered the topics of evolution in data warehouses. Darja has also been involved in research on data warehouse business requirements, conceptual modelling and OLAP personalization. Her current research interests are in the field of data warehousing, OLAP and big data evolution.

Jun 16, 2020
12:51pm - 1:03pm (Helsinki)
Review of Non-English Corpora Annotated for Emotion Classification in Text

Authors: Viktorija Leonova

Review of Non-English Corpora Annotated for Emotion Classification in Text

 

ABSTRACT

In this paper we try to systematize the information about the available corpora for emotion classification in text for languages other than English with the goal to find what approaches could be used for low-resource languages with close to no existing works in the field. We analyze the corresponding volume, emotion classification schema, language of each corresponding corpus and methods employed for data preparation and annotation automation. We’ve systematized twenty-four papers representing the corpora and found that corpora were mostly for the most spoken world languages: Hindi, Chinese, Turkish, Arabic, Japanese etc. A typical corpus contained several thousand of manually-annotated entries, collected from a social network, annotated by three annotators each and was processed by a few machine learning methods, such as linear SVM and Naïve Bayes and (more recent ones) a couple of neural networks methods, such as CNN.

 

SHORT BIO:

Viktorija Leonova, born in Riga, Latvia. Has acquired bachelor’s degree in the University of Latvia (1999—2003). Has moved Cyprus in 2007, where she was living until 2015. She has enrolled in the Open University of Cyprus and graduated with master’s grade in Computer Science with specialization in Intelligent Systems (2012—2015). She returned to Latvia in 2015 where she is currently studying in PhD program in the University of Latvia on the faculty of Computer Science.

Jun 16, 2020
1:04pm - 1:16pm (Helsinki)
Using Machine Learning for Automated Assessment of Misclassification of Goods for Fraud Detection

Authors: Margarita Spichakova and Hele-Mai Haav

Using Machine Learning for Automated Assessment of Misclassification of Goods for Fraud Detection

 

ABSTRACT

The paper is devoted to providing automated solutions to an actual problem of misclassification of goods in cross-border trade. In this paper, we introduce a hybrid approach to Harmonized System (HS) code assessment that combines the knowledge derived from textual descriptions of products, assigned to them HS codes and taxonomy of HS codes nomenclature. We use machine learning for providing HS code's predictions and recommendations on the basis of a model learned from the textual descriptions of the products. In order to perform an assessment of misclassification of goods we present a novel combined similarity measure based on cosine similarity of texts and semantic similarity of HS codes based on HS code taxonomy (ontology). The method is evaluated on the real open source data set of Bill of Lading Summary 2017 [1] using Gensim Python library [4].

 

SHORT BIO:

Margarita Spitšakova is a software developer at the Department of Software Science of Tallinn University of Technology, Estonia. She received her Ph.D. in 2017. The research topics include heuristic optimization methods and their application to the inference of the system models. Furthermore, she has experience in developing novel methods for creating software based on AI technologies, for example, the resource planning software, or electricity consumption prediction models.

Jun 16, 2020
1:17pm - 1:29pm (Helsinki)
Mobile Phone Usage Data for Credit Scoring

Authors: Henri Ots, Innar Liiv and Diana Tur

Mobile Phone Usage Data for Credit Scoring

 

ABSTRACT

The aim of this study is to demostrate that mobile phone usage data can be used to make predictions and find the best classification method for credit scoring even if the dataset is small (2,503 customers). We use different classification algorithms to split customers into paying and non-paying ones using mobile data, and then compare the predicted results with actual results. There are several related works publicly accessible in which mobile data has been used for credit scoring, but they are all based on a large dataset. Small companies are unable to use datasets as large as those used by these related papers, therefore these studies are of little use for them. In this paper we try to argue that there is value in mobile phone usage data for credit scoring even if the dataset is small. We found that with a dataset that consists of mobile data based only on 2,503 customers, we can predict credit risk. The best classification method gave us the result 0.62 AUC (area under the curve).

 

SHORT BIO:

Innar Liiv is Associate Professor of Data Science at Tallinn University of Technology and Research Associate at Oxford University's Centre for Technology and Global Affairs. He was previously a Cyber Studies Visiting Research Fellow at the University of Oxford (2016-2017) and a Visiting Scholar at Stanford University (2015). His research interests include data science and big data technology transfer to industrial and governmental applications.

Jun 16, 2020
1:30pm - 1:42pm (Helsinki)
Text Extraction from Scrolling News Tickers

Authors: Ingus Janis Pretkalnins, Arturs Sprogis, and Guntis Barzdins

Text Extraction from Scrolling News Tickers

 

ABSTRACT

While a lot of work exists on text or keyword extraction from videos, not a lot can be found on the exact problem of extracting continuous text from scrolling tickers. In this work a novel Tesseract OCR based pipeline is proposed for location and continuous text extraction from scrolling tickers in videos. The solution worked faster than real time, and achieved a character accuracy of 97.3% on 45 minutes of manually transcribed 360p videos of popular Latvian news shows.

 

SHORT BIO:

Ingus Jānis Pretkalninš is an undergraduate mathematics student at the University of Latvia. He works at the Institute of Mathematics and Computer Science, University of Latvia, and is interested in epistemology and machine learning.

Jun 16, 2020
1:43pm - 1:55pm (Helsinki)
Specialized image descriptors for signboard photographs classification

Authors: Aleksei Samarin, Valentin Malykh and Sergey Muravyov

Specialized image descriptors for signboard photographs classification

 

ABSTRACT

We propose several types of advertising sign photo descriptors that are useful for images classi cation. We also collected a dataset of commercial building facade photographs grouped by a type of provided services in order to perform comparison between di erent classi cation methods. Finally we performed comparison between methods based on the proposed descriptor usage and combined advertising sign classi er and obtained better performance using our system.

 

SHORT BIO:

My name is Sergey Muravyov. I am 26 years old and I am a postdoctoral researcher in ITMO University, Saint-Petersburg, Russia. I entered ITMO University in 2010. I defended my PhD thesis “Automatic evaluation and tuning system for clustering algorithms” in 2019. Although my research domain is mostly AutoML, it was very interesting to take part into new team with challenging task of computer vision that is signboard classification.

Jun 16, 2020
1:56pm - 2:08pm (Helsinki)
Application Development for Hand Gestures Recognition with Using a Depth Camera

Authors: Dina Satybaldina, Gulziya Kalymova and Natalya Glazyrina

Application Development for Hand Gestures Recognition with Using a Depth Camera

 

ABSTRACT

The aim of the work is to develop an application for hand gestures identification based on a convolutional neural network using the TensorFlow & Keras deep learning frameworks. The gesture recognition system consists of a gesture presentation, a gesture capture device (sensor), the preprocessing and image segmentation algorithms, the features extraction algorithm, and gestures classification. As a sensor, Intel® Real Sense™ depth camera D435 with USB 3.0 support for connecting to a computer was used. For video processing and extraction both RGB images and depth information from the input data, functions from the Intel Real Sense library are applied. For pre-processing and image segmentation algorithms computer vision methods from the OpenCV library are implemented. The subsystem for the features extracting and gestures classification is based on the modified VGG-16, with weights previously trained on the ImageNet database. Performance of the gesture recognition system is evaluated using a custom dataset. Experimental results show that the proposed model, trained on a database of 2000 images, provides high recognition accuracy (99.4%).

 

SHORT BIO:

Gulzia Kalymova is currently a PhD student in the Department of Information Technologies at L.N.Gumilyov Eurasian National University, Nur-Sultan, Kazakhstan. She received her Bachelor and Master degrees in Mathematics in Kazakh National University after Al-Farabi, Almaty, Kazakhstan. Her current research interests include Human-Computer Interactions, Machine Learning, Gesture Recognition, Computer Vision and Image Processing. She has published around 10 research papers in different international and national journals and conferences.

Jun 16, 2020
2:09pm - 2:21pm (Helsinki)
Simultaneous Road Edge and Road Surface Markings Detection Using Convolutional Neural Networks

Authors: René Pihlak and Andri Riid

Simultaneous Road Edge and Road Surface Markings Detection Using Convolutional Neural Networks

 

ABSTRACT

Accurate road surface markings and road edges detection is a crucial task for operating self-driving cars and for advanced driver assistance systems deployment (e.g. lane detection) in general. This research proposes an original neural network based method that combines structural components of autoencoders, residual neural networks and densely connected neural networks. The resulting neural network is able to concurrently detect and segment accurate road edges and road surface markings from RGB images of road surfaces.

 

SHORT BIO:

Rene Pihlak is a researcher (Msc) and doctoral student of Information and Communication Technology at Tallinn University of Technology. He graduated Computer and Systems Engineering with cum laude at Tallinn University of Technology in 2019, having previously studied mechatronics (2013-2017), Law & Economics (1997–1998 M.A., University of Hamburg, Germany), and Finance (1992-1997, B.Sc., University of Tartu).

Jun 16, 2020
2:22pm - 2:34pm (Helsinki)
Features and Methods for Automatic Posting Account Classification

Authors: Zigmunds Beļskis, Marita Zirne and Mārcis Pinnis

Features and Methods for Automatic Posting Account Classification

 

ABSTRACT

Manual processes in accounting can introduce errors that affect business decisions. Automation (or at least partial automation of accounting processes) can help to minimise human errors. In this paper, we investigate methods for the automation of one of the processes involved in invoice posting – the assignment of account codes to posting entries – using various classification methods. We show that machine learning-based methods can reach a precision of up to 93% for debit account code classification and even up to 98% for credit account code classification.

 

SHORT BIO:

My name is Zigmunds Beļskis. I am 28 years old and I am a software developer in Tilde LLC located in Riga, Latvia. I have a college degree in software engineering from University of Latvia. I mainly develop and maintain enterprise resource planning system named “Tildes Jumis” which is mainly focused on accounting.

Jun 16, 2020
4:00pm - 4:45pm (Tallinn)
Doctoral Consortium Opening and Keynote
Jun 16, 2020
4:45pm - 5:00pm (Helsinki)
Aspect-Oriented Analytics of Big Data

Authors: No'aman M. Ali

Aspect-Oriented Analytics of Big Data

 

ABSTRACT

Social media platforms are one of the most significant contributors to big data; it enables consumers to provide their views or opinions about products and services. These abundant reviews contain substantial and valuable knowledge and have become a significant resource for both consumers and firms. Therefore, enterprises seek realtime insights and relevant information on how the market responds to products and services. The proposed framework employs the sentiment analysis and aspect-based sentiment analysis in parallel to customer reviews to support decision-makers regarding Marketing and Manufacturing domains. Our proposal presents a multilayer classifier for consumers’ reviews. The first layer is used to categorize reviews into the aspect and non-aspect classes. The second layer is used to break every review involved in the aspect-based category into opinion units based on the product aspects. Next, we plan to measure the polarity of the reviews and opinion units. Finally, we plan to visualize the results in the form of domain-oriented reports. Also, we present a description of the testing and evaluation criteria.

 

SHORT BIO:

No'aman Muhammad Ali – received his M.Sc. degree from the department of computer science, Cairo University, in 2016. Currently, No'aman is an assistant lecturer at the Information Technology & Systems Department, Port Said University, Egypt, since 2016. No'aman is a Ph.D. student at the Department of Computer Science, Saint Petersburg State University. His research interests involve Big data analytics, pattern recognition, recommender systems, natural language processing.

Jun 16, 2020
5:00pm - 5:11pm (Helsinki)
Importance of the use of Analytics in Requirements Engineering

Authors: Marina Pincuka

Importance of the use of Analytics in Requirements Engineering

 

ABSTRACT

Requirements Engineering is regarded as one of the most important functions in software development process. Inadequate/ incorrect engineering of requirements may lead to expensive errors in software development or even to project failure. Even though there are a different methods and approaches that are proposed in literatures, many of these approaches have not been used in the industry or have been proved to be ineffective. The main goal of this work is to investigate the Requirements Engineering weak points and see which of these weak points can be strengthened by the use of analytics.

 

SHORT BIO:

Marina Pinčuka is a Riga Technical University, 1st year PhD student in the study program “Computer Systems”. Marina Pinčuka is a Riga Technical University, 1st year PhD student. In 2019. graduated with a master degree from Riga Technical University. Since 2017 works at Riga Technical University as a scientific assistant, in 2019 got promoted to the researcher. Parallel in 2018 started working as a system analyst in the IT company, in 2020 got promoted to the project manager.

Jun 16, 2020
5:15pm - 5:26pm (Helsinki)
Business capabilities utilization enhancement using Archimate for EAS projects delivery in an agile environment

Authors: Karolis Noreika

Business capabilities utilization enhancement using Archimate for EAS projects delivery in an agile environment

 

ABSTRACT

Businesses of all sizes are constantly seeking to improve their daily business pro-cesses to stay competitive in the modern-day economy. Enterprises take for granted that they are utilizing their business capabilities in the best way possible. The purpose of this paper is to present a manual method to minimize the gap of misalignment between business and IT when delivering enterprise application software (EAS) projects in an agile environment. The research is based on litera-ture review and empirical data from 3 EAS projects over a one-year time. By in-troducing a regular reference check to minimize the gap of misalignment between business and IT or deficit, during EAS project delivery between the requirements and strategical organizational goals described using enterprise architecture frameworks, specifically Archimate, it was observed that cost of projects and overall enterprise effort towards its goals decreased and provided significant cost savings. A more automated approach than previously available is required.

 

SHORT BIO:

Karolis Noreika has more than 12 years’ experience working in IT industry and is currently working as a Scrum master in Danske bank implementing business process automation solutions on enterprise level. Karolis is studying in his first year as doctoral student at Vilnius University Institute of Data Science and Digital Technologies under supervision of professor Saulius Gudas. Karolis is interested in enterprise application software development methodologies, enterprise architecture frameworks.

Jun 16, 2020
5:45pm - 5:57pm (Helsinki)
A Hybrid Method for Textual Data Classification Based on Support Vector Machine with Particle Swarm Optimization Metaheuristic and k-Means Clustering

Authors: Konstantinas Korovkinas

A Hybrid Method for Textual Data Classification Based on Support Vector Machine with Particle Swarm Optimization Metaheuristic and k-Means Clustering

 

ABSTRACT

This paper introduces a hybrid method for textual data classification. The goal of this paper is to improve classification accuracy of method presented in our previous work by integrating to it k-Means method for decreasing training dataset and particle swarm optimization metaheuristic for a linear support vector machine parameter tuning. The paper reports that the introduced method is characterized by higher improvements in all effectiveness metrics than the methods presented in our previous works.

 

SHORT BIO:

Konstantinas Korovkinas received professional bachelor's degree in computer programming at Vilnius college (2003). In 2007 graduated from Vilnius Gediminas Technical University and received bachelor's degree in Informatics. In 2014 successfully completed Business Informatics studies at Vilnius University Kaunas faculty and received master degree in Information systems (Magna Cum Laude). From 2015 is a doctoral student at Vilnius University Kaunas faculty (Natural Sciences, Informatics). From 2018 is a junior assistant at Vilnius University Kaunas faculty, teaches "Computer architecture" and "Python" programming.

Jun 16, 2020
6:00pm - 6:12pm (Helsinki)
Fault Tolerant Distributed Join Algorithms in RDBMS

Authors: Arsen Nasibullin

Fault Tolerant Distributed Join Algorithms in RDBMS

 

ABSTRACT

 

 

SHORT BIO:

I'm Arsen Nasibullin. I'm from Russia, Ufa. Last 10 years I've been living in Saint-Petersburg. I graduated from Saint-Petersburg State university, and now I'm a post-graduate student in this university at Mathematical and Mechanics department. My scientific interests are around data management and databases. I'm a software engineer with more than 6 years experinece. Last 3 years I've been working on EPAM.

Jun 16, 2020
6:15pm - 6:25pm (Helsinki)
Towards Transforming Natural Language Queries into SPARQL Queries

Authors: Majid Askar

Towards Transforming Natural Language Queries into SPARQL Queries

 

ABSTRACT

Ontology Based Data Access (OBDA) improves knowledge sharing and reuse and grants a set of options to enhance the power of knowledge management. In OBDA systems, user queries can be expressed in SPARQL. This prevents ordinary users from formulating their own queries. For such lay users, it should be possible to express queries in their own languages and terms instead of being forced to learn SPARQL. To enable this, a transformation from a natural language to SPARQL is needed. To cope with such translation, several challenges, such as natural language processing, ontology handling, string matching, and SPARQL query building should be addressed. In this PhD study, we will use natural language processing techniques and investigate the role of user involvement in the query translation process. Also, string-matching algorithms will be used. We will start with the processing of the natural query. Then the mapping between the query entities and corresponding entities in the datasets. The user interaction validating and confirming this mapping should take place. Finally, building the SPARQL query. The proposed approach will be evaluated based on a bench mark by means of query efficiency and accuracy.

 

SHORT BIO:

Majid Ahmed JadElrab Askar Lecturer assistant at the faculty of computers & information - Assiut University - Egypt Member of the BioDialog project. In Assiut University member of: The Quality Assurance & Accreditation unit. The Online Teaching project. The E-learning Centre. The Upgrading and Development of Meat Hygiene and Technology Education in Egypt project.

Jun 16, 2020
6:30pm - 6:44pm (Helsinki)
A Linguistic Analysis Of Startups In The Context Of The Air Transport Industry Management

Authors: Olga Zervina

A Linguistic Analysis Of Startups In The Context Of The Air Transport Industry Management

 

ABSTRACT

Much research has studied how a company can maximize its profit. Relatively small number of them focused on Value Proposition, though the number of authors proved that companies that deliver multiple values experience better business performance. This article describes a current research on linguistic analysis of startups in the context of the air transport industry. Analyzing startups manually is a very time consuming task, so the automation of the process would be beneficial. The author takes corpus linguistic approach, created an experiment protocol and is on the stage of conducting an experiment. Under this experiment air transportation startups’ landing pages were collected in the number of 800. 100 annotators first were preliminary surveyed and then trained to annotate startups. Post-annotation training will be conducted to understand the difference in expertise level. The annotation results will be further analyzed and linguistic features and patterns will be identified. As a result of the research, an author will develop a methodology for analysis of values based on a model of automatic identification of values in the text of a startup’s landing page in the air transportation industry.

 

SHORT BIO:

Olga is a Director of postgraduate Aviation Management program. She has linguistic and economical background and now she is also a PhD student. With her current PhD studies in the field of linguistic data science, she expands her knowledge of NLP techniques and turns her focus towards the wide-scale applications in transportation management. The topic of her thesis is “A Linguistic Analysis of Innovation Project Proposals in the Context of the Air Transport Industry Management”. Olga works closely with aviation industry to be able to analyze the latest trends and needs so to satisfy as an Aviation Management program director the modern requirements of the market. Also, Olga is a lecturer of Digital Marketing, she focuses on IT linguistic tools for landing pages texts.

Jun 16, 2020
6:45pm - 7:15pm (Tallinn)
Doctoral Consortium Closing
Jun 17, 2020
11:00am - 12:00pm (Helsinki)
Continuous Requirements Engineering in the Context of Socio-Cyber-Physical Systems

Speaker: Marite Kirikova

Continuous Requirements Engineering in the Context of Socio-Cyber-Physical Systems

 

ABSTRACT

Continuously changing business situations and technologies have produced a need for continuous requirements engineering. The challenges in continuous requirements engineering are determined by the scope of solutions and development methods, for instance, multiproject environments. Quite often, requirements engineering is based on specific models, for instance, enterprise models; and can utilize the power of enterprise architecture tools. While there are many well established approaches to enterprise architecture development for “ordinary”enterprises, in the socio-cyber-physical context there are fewer methods, tools, and architecture frameworks. Thus, in respect of both research and practice, we shall meet a double challenge: the challenge of the continuity of requirements engineering and the challenge of requirements engineering for socio-cyber physical systems. One of the toolsets to meet this double challenge will be demonstrated by combining architecture frameworks for socio-cyber-physical systems with the FREEDOM framework for continuous systems engineering.

 

SHORT BIO:

Dr.sc.ing. Mārīte Kirikova is a Professor in Information Systems Design at the Department of Artificial Intelligence and Systems Engineering, Faculty of Computer Science and Information Technology, Riga Technical University, Latvia. She has more than 200 publications on the topics of requirements engineering, business process modelling, knowledge management, systems development and educational informatics. She is also a co-editor of several scientific proceedings in the area of databases, information systems, information systems engineering, enterprise modelling, systems and business, and business informatics. Marite Kirikova has participated in university research and teaching teams in Sweden, Denmark, Austria, and USA. In her research she currently focuses on continuous information systems engineering.

Jun 17, 2020
12:00pm - 12:11pm (Helsinki)
A Mobility Data Model for Web-Based Tourists Tracking

Authors: Thouraya Sakouhi, Jamal Malki and Jalel Akaichi

A Mobility Data Model for Web-Based Tourists Tracking

 

ABSTRACT

Tracking tourists activities at different levels of their journeys provides an overview on their mobility and a comprehension of their behavior and preferences. Most information related to tourism services and tourists are collected and stored through web platforms. In fact, selfdrive tourists access touristic information available on the web to plan for their trips. Accordingly, tourism professionals track their requirements in touristic information and then their mobility. Yet, since touristic information is managed at a territorial level, tracking tourists’ movement by tourism professionals, out of their territory, is not a straightforward task. Accordingly, the latters do not have a complete overview of tourists movements. Throughout this paper authors will start by discussing mobility data capture through the web and the related challenges. Then, they’ll introduce an integrated mobility data model for tracking tourists.

 

SHORT BIO:

Thouraya Sakouhi is a PhD student at the BESTMOD lab, Institut Supérieur de Gestion, Université de Tunis. She has MSc in Business Intelligence and BSc in Computer science from the same institute.

Jun 17, 2020
12:12pm - 12:24pm (Helsinki)
Complexity Issues in Data-Driven Fuzzy Inference Systems: Systematic Literature Review

Authors: Jolanta Miliauskaitė and Diana Kalibatiene

Complexity Issues in Data-Driven Fuzzy Inference Systems: Systematic Literature Review

 

ABSTRACT

The development of a data-driven fuzzy inference system (FIS) involves the automatic generation of membership functions and fuzzy if-then rules and choosing a particular defuzzification approach. The literature presents different techniques for automatic FIS development and highlights different challenges and issues of its automatic development because of its complexity. However, those complexity issues are not investigated sufficiently in a comprehensive way. Therefore, in this paper, we present a systematic literature review (SLR) of journal and conference papers on the topic of FIS complexity issues. We review 1 340 papers published between 1991 and 2019, systematize and classify them into categories according to the complexity issues. The results show that FIS complexity issues are classified as follows: computational complexity, fuzzy rules complexity, membership functions complexity, input data complexity, complexity of fuzzy rules interpretability, knowledge inferencing complexity and representation complexity, accuracy and interpretability complexity. The results of this study can help researchers and practitioners become familiar with existing FIS complexity issues, the extent of a particular complexity issue and to decide for future development.

 

SHORT BIO:

Jolanta Miliauskaitė works at Vilnius University (Lithuania) Institute of Data Science and Digital Technologies Department of Cyber-Social Systems Engineering Group. She defended a PhD in Technological Sciences, Informatics Engineering at Vilnius University (2015) on the topic ‘‘A Fuzzy Inference-Based Approach to Planning Quality of Enterprise Business Services’’. Her research interests include enterprise business services, service-oriented enterprise systems, web service composition, quality of service modelling and evaluation in service-oriented enterprise systems. She is a co-author of research papers in the field of Computer Sciences. She is a lector at Vilnius University Faculty of Mathematics and Informatics and Vilnius Gediminas Technical University (Lithuania) Faculty of Fundamental Sciences Department of Information Systems. She participated in the project of EU Structural Funds ‘‘Theoretical and Engineering Aspects of E-Service Technology Development and Application in High-Performance Computing Platforms’’. She is a member of organising committee of the International Baltic Conference on Databases and Information Systems (Baltic DB&IS 2018). She is a member of Lithuanian Computer Society (LIKS).

Jun 17, 2020
12:25pm - 12:37pm (Helsinki)
Towards DSL for DL Lifecycle Data Management

Authors: Edgars Celms, Janis Barzdins, Audris Kalnins, Arturs Sprogis, Mikus Grasmanis, Sergejs Rikacovs and Paulis Barzdins

Towards DSL for DL Lifecycle Data Management

 

ABSTRACT

A new method based on Domain Specific Language (DSL) approach to Deep Learning (DL) lifecycle data management tool support is presented: a very simple DL lifecycle data management tool, which however is usable in practice (it will be called Core tool) and a very advanced extension mechanism which in fact con-verts the Core tool into domain specific tool (DSL tool) building framework for DL lifecycle data management tasks. The extension mechanism will be based on the metamodel specialization approach to DSL modeling tools introduced by au-thors. The main idea of metamodel specialization is that we, at first, define the Universal Metamodel (UMM) for a domain and then for each use case define a Specialized Metamodel. But for use in our new domain the specialization concept will be extended: we add a functional specialization where invoking an additional custom program at appropriate points of Core tool is supported.

 

SHORT BIO:

Paulis F. Barzdins is a student at the University of Edinburgh pursuing a BSc in Artificial Intelligence, and a part-time Research Assistant at the Institute of Mathematics and Comuter Science, University of Latvia. Through work and studies his scientific interests include Deep Learning, with a focus on Image Captioning and Natural Language Processing. Other interests include creating music and analogue photography.

Jun 17, 2020
12:38pm - 12:50pm (Helsinki)
A Little Bird Told Me: Discovering KPIs from Twitter Data

Authors: Janis Zemnickis, Laila Niedrite and Natalija Kozmina

A Little Bird Told Me: Discovering KPIs from Twitter Data

 

ABSTRACT

The goal of our research and experiments is to find the definitions and values of key performance indicators (KPIs) in unstructured text. The direct access to opinions of customers served as a motivating factor for us to choose Twitter data for our experiments. For our case study, we have chosen the restaurant business domain. As in the other business domains, KPIs often serve as a solution for identification of current problems. Therefore, it is essential to learn which criteria are important to restaurant guests. The mission of our Proof-of-Concept KPI discovery tool presented in this paper is to facilitate the explorative analysis taking Twitter user posts as a data source. After processing tweets with Stanford CoreNLP toolkit, aggregated values are computed and presented as visual graphs. We see our tool as an instrument for data discovery applicable, for example, to define new qualitative and quantitative KPIs based on the values found in the graph. The graph represents a complete view of aggregated data that corresponds to the search results according to the user-defined keywords, and gives easy access to detailed data (tweets) that, in its turn, leads to better understanding of the post context and its emotional coloring.

 

SHORT BIO:

Speaker of research is Janis Zemnickis. He started his career as a C++ developer working in one of the biggest Nordic financial software development companies. Currently he is doctoral student of University of Latvia, Faculty of Computing. Currently his work is related to data warehouse in financial sector. He is also interested in big data technologies and has experience in WEB development.

Jun 17, 2020
12:51pm - 1:03pm (Helsinki)
Development of Ontology Based Competence Management Process Model for Non-Formal Education

Authors: Uldis Zandbergs and Jānis Grundspeņķis

Development of Ontology Based Competence Management Process Model for Non-Formal Education

 

ABSTRACT

The demand for constantly higher competences of employees nowadays is growing permanently. One of the main challenges of implementation of competence management processes is that, as a rule, they are based on the experts’ implicit knowledge that practically limits possibilities to transform the already existing knowledge about competences from one organization to another. The paper describes the ontology based competence management process model that is useful for non-formal education service providers in their efforts to use different competence management frameworks together instead of forcing organizations to change their routine competence management processes. The proposed model is based on the previously developed ontology based competence management model which defines more accurately the concept of competence. The competence management process is divided into three main steps – competence identification, competence assessment and competence development. The description of the first step is extended by including the concepts of goal and task to be achieved and performed correspondingly, as well as by adding the concept of creation of competence profile. The conceptual architecture of competence management system based on the prototype with a limited functionality for supporting competence management processes is presented.

 

SHORT BIO:

Uldis Zandbergs is Bachelor of Science degree from University of Latvia in 1998, and Master of Business Administration from Riga Business School at Riga Technical University, Latvia in 2003. He has been a doctoral student at Information Technology Faculty at Latvia University of Agriculture, Latvia. Since 2013 he is a researcher at Baltic Computer Academy. His research interests include competence modelling, competence assessment tools, automatization of competence management process.

Jun 17, 2020
1:04pm - 1:16pm (Helsinki)
A Method of Comparative Spatial Analysis of a Digitized (LiDAR) Point Cloud and the Corresponding GIS Database

Authors: Riina Maigre, Hele-Mai Haav, Rauni Lillemets, Kalev Julge and Gaspar Anton

A Method of Comparative Spatial Analysis of a Digitized (LiDAR) Point Cloud and the Corresponding GIS Database

 

ABSTRACT

Creation of a consistent 3D model of a city requires accurate data. Usually, accuracy assurance problems of data are solved by time consuming and expensive process of collecting and aligning with ground control points (GCP). Therefore, alternative methods become important. Using existing Geographic Information Systems (GIS) databases may decrease the time and cost of creating a reference dataset by reducing the number of GCPs required for producing high quality 3D data or GIS databases can serve as reference data. For this purpose, new spatial data analysis methods are needed to assure that GIS databases are of high-quality. In this paper, we propose a novel methodology and its sample development for comparative spatial analysis of digitized point cloud and the corresponding GIS database in order to statistically assess opportunities to align Mobile Mapping Systems (MMS) data with existing GIS databases or to improve involved datasets. The method is evaluated using LiDAR data provided by Estonian company Reach-U Ltd. and GIS database layers from different Estonian open and closed databases.

 

SHORT BIO:

Riina Maigre is a researcher at the Department of Software Science of Tallinn University of Technology. Her research interests include spatial data analysis, open data and semantic web technologies. In the past, she has also worked on web service composition and with e-government services.

Jun 17, 2020
1:17pm - 1:29pm (Helsinki)
Automating Detection of Occurrences of PostgreSQL Database Design Problems

Authors: Erki Eessaar

Automating Detection of Occurrences of PostgreSQL Database Design Problems

 

ABSTRACT

SQL is a very resilient and widely used software language. In case of building a SQL database, one has to design schemas of the database so that the database management system (DBMS) can enforce these. The result of designing a database schema is a technical artifact, which may have technical debt. The debt makes it more difficult to understand, maintain, extend, and reuse the artifact. Smells are the signs of technical debt. Many database design smells manifest the same problems as code smells. It could also be that a database schema makes incorrect statements about the domain of the database or lacks necessary elements, i.e., is incomplete. Thus, database schemas can have numerous problems and finding these is a prerequisite of improving the schemas. The paper introduces a catalog of open source SQL queries that have been designed for finding the occurrences of design problems in PostgreSQL databases (https://github.com/erki77/database-design-queries). Most of the queries help us to detect the occurrences of database design smells. The queries are for a specific although popular DBMS. However, most of the problems that occurrences these help us to find can appear in any SQL database, regardless of the used DBMS.

 

SHORT BIO:

Erki Eessaar, dr., is a full-time Associate Professor at the Department of Software Science in Tallinn University of Technology. He teaches courses about database design and development. He is the author or a co-author of more than 40 research papers and the author of one book in the field of databases and information systems development. Research interests: data models, automation of the software development as well as model- and pattern-driven development and evolution of information systems.

Jun 17, 2020
1:30pm - 1:42pm (Helsinki)
On Case-based Reasoning for ETL Process Repairs: Making Cases Fine-grained

Authors: Artur Wojciechowski and Robert Wrembel

On Case-based Reasoning for ETL Process Repairs: Making Cases Fine-grained

 

ABSTRACT

Data sources (DSs) being integrated in a data warehouse frequently change their structures. As a consequence, in many cases, an already deployed ETL process stops its execution, generating errors. Since the number of deployed ETL processes may reach dozens of thousands and structural changes in DSs are frequent, being able to (semi-)automatically repair an ETL process after DS changes, would decrease ETL maintenance costs. In our approach, we developed the E-ETL framework, for ETL process repairs. In E-ETL, an ETL process is semi-automatically or automatically (depending on a case) repaired, so that it works with the changed DS. E-ETL supports two different repair methods: (1) user defined rules, (2) and Case-Based Reasoning (CBR). Having experimented with CBR, we learned that large cases do not frequently fit a given DS change, even though they include elements that could be applied to repair a given ETL process, and vice-versa - more complex DS changes cannot be handled by small cases. To solve this problem, in this paper, we contribute algorithms for decomposing detected structural changes in DSs. The purpose of the decomposition is to divide a set of detected structural DSs changes into smaller sets, to increase the probability of finding a suitable case by the CBR method.

 

SHORT BIO:

Artur Wojciechowski is a PhD student at Poznan University of Technology in Poland. In 2010, he received a PhD grant - Human Capital Operational Programme "Support for scholarships for postgraduates designated as strategic directions for the development of Wielkopolska, Sub-measure 8.2.2 Regional Innovation Strategies, Action 8.2, Priority VIII". He is a software developer In company mTab where he develops a tool for integrating, cleaning and managing data for market research analysis.

Jun 17, 2020
1:43pm - 1:55pm (Helsinki)
Rule Discovery for (Semi-)automatic Repairs of ETL Processes

Authors: Judith Awiti and Robert Wrembel

Rule Discovery for (Semi-)automatic Repairs of ETL Processes

 

ABSTRACT

A data source integration layer, commonly called extract-transform-load (ETL), is one of the core components of information systems. It is applicable to standard data warehouse (DW) architectures as well as to data lake (DL) architectures. The ETL layer runs processes that ingest, transform, integrate, and upload data into a DW or DL. The ETL layer is not static, since the data sources being integrated by this layer change their structures. As a consequence, an already deployed ETL process stops working and needs to be re-designed (repaired). Companies typically have deployed from thousands to hundreds of thousands of ETL processes. For this reason, a technique and software support for repairing semi-automatically a failed ETL processes is of vital practical importance. This problem has been only partially solved by technology or research, but the solutions still require an immense work of an ETL administrator. Our solution is based on a case-based-reasoning combined with repair rules. In this paper, we contribute a method for automatic discovery of repair rules from a stored history of repair cases.

 

SHORT BIO:

Judith Awiti received a B.Sc Computer Engineering degree from the Kwame Nkrumah University of Science and Technology (KNUST), Ghana, and an M.Sc Information Technology degree from Sikkim Manipal University, India. She was a Senior ICT Assistant at University of Energy and Natural Resources (UENR) from August 2013 to January 2018 and is now a researcher in the IT4BI-DC Erasmus Mundus programme. She has co-authored some scientific papers presented at major database conferences and her current research interests include data warehouses and ETL processes.

Jun 17, 2020
1:56pm - 2:08pm (Helsinki)
Testing of Execution of Concurrent Processes

Authors: Janis Bicevskis and Girts Karnitis

Testing of Execution of Concurrent Processes

 

ABSTRACT

Authors propose an algorithm for analysis of business processes to detect potentially incorrect results of concurrent processes execution. Our novel approach is to conclude necessary database isolation level from business process description. If traditional languages with loops and arithmetic operations (two-way counters) are used for business process descriptions, the problem of detecting incorrect execution of concurrent processes cannot be algorithmically solved. This paper introduces a simplified business processes description language CPL-1, a transaction mechanism and an algorithm that supports detection of incorrect results during the concurrent execution of business processes. Business processes are often run concurrently in real world tasks like billing systems, ticket distribution, hotel reservations, etc. Currently there are some popular solutions preventing incorrect execution of concurrent business processes by using built-in transaction mechanisms and/or resource reservations in database management systems (DBMS). The proposed solution is an alternative, which can be used when resource locking or DBMS transaction mechanisms cannot be applied.

 

SHORT BIO:

Girts Karnitis is a professor at Faculty of Computing, University of Latvia. He has more than 20 years experience in software development and has more than 30 scientific publications. His main principal areas of expertise are databases and information systems modelling, development and integration. Also, he is interested in process and data modeling and model-based system development where several scientific publications were prepared based on the projects he was working. His free time activities consist mostly of spending time with family, travelling, taking care of four cats and being a father of three teens who plan to study IT finding parents’ passion as a notable role model.

Jun 17, 2020
2:09pm - 2:21pm (Helsinki)
The Use of the Recommended Learning Path in the Personalized Adaptive E-learning System

Authors: Vija Vagale, Laila Niedrite and Svetlana Ignatjeva

The Use of the Recommended Learning Path in the Personalized Adaptive E-learning System

 

ABSTRACT

This paper promotes the idea of the learning process management in the e-learning system. A personalized adaptive e-learning system is used in this research that comprises three developed topic acquisition sequences: teacher, learner or optimal topic sequences. The learner has the ability to switch between the aforementioned topic sequences. The system stores data about the course acquisition process. The analysis of the stored data demonstrated that a bit more than half of the students used the teacher topic sequence; higher grades in topics got those students who chose the learner or optimal topic sequence; the grades of the half of the students who used the optimal and teacher topic sequences were in the same level. The obtained results were used as the justification for the improvement of the existing optimal topic sequence development method. As a result, an algorithm for the recommended learning path development is proposed in this paper. The topics of the course and links in between are described using a weighted directed graph. The weight of every edge and vertex of the graph is calculated based on the parameter values describing the topic. Afterwards, the recommended learning path is assumed to be the path with the lowest weight that is found in the weighted oriented graph using a search.

 

SHORT BIO:

Vija Vagale obtained her PhD degree of the computer science in subfield of Software and Systems Engineering from University of Latvia, Faculty of Computing in 2018. Currently she works as a researcher assistant in the University of Latvia, and as an assistant professor in the Daugavpils University. She is teaching courses about programming, databases and information technologies. Her research interests include e-learning systems, education, adaptation, personalization, and learner modelling.

Jun 17, 2020
4:15pm - 5:15pm (Tallinn)
LIVE Virtual excursion to Tartu with a guide

Join us LIVE on this virtual tour to Tartu.

Unfortunately, due to the evil virus named COVID-19, we were not able to take you on a physical tour throughout Tartu and its surroundings.

 

Jun 17, 2020
5:15pm - 5:19pm (Tallinn)
Excursions & Dinners of Baltic DB&IS

Virtual tour of Excursions & Dinners of Baltic DB&IS 2004-2018. The duration of the show is 3.5 minutes.

Jun 17, 2020
5:30pm - 5:45pm (Tallinn)
History of the Baltic DB&IS conferences

Take a short trip back to history of the Baltic DB&IS conference series through memories of Albertas Caplinskas, Olegas Vasilecas, Hele-Mai Haav, and many others who have participated the confrerences throughout the years. The duration of the virtual trip is 10 minutes.

Jun 18, 2020
11:00am - 12:00pm (Helsinki)
Developing new encryption mechanisms for the Estonian eID infrastructure

Speaker: Jan Willemson

Developing new encryption mechanisms for the Estonian eID infrastructure

 

ABSTRACT

By looking at the aftermath of 2017 ROCA case for the Estonian ID-card, it became clear that out of the three main usage scenarios of ID-cards (signing, authentication, encryption), the one of encryption, in some sense, suffered the most. To date, there are still many vulnerable CDOC containers around. One of the main design flaws of this CDOC solution is relying on a single static long-term asymmetric key embedded into the ID-card as a decryption key. It is clear that a better solution is needed; however, it is not straightforward at all how this should look like. In fact, file level encryption is used in many different scenarios and the respective solutions should differ as well. In this talk we are going to cover some of these scenarios and initial ideas about how to approach them.

 

SHORT BIO:

Jan Willemson defended his PhD at Tartu University, Estonia, in 2002. Since 1998, he has been working at Cybernetica as a researcher, contributing to a number of e-government and information security projects. He has authored more than 60 research papers on digital time-stamping, secure computation, systems security, rational risk assessment, electronic voting, etc.

Jun 18, 2020
12:00pm - 12:11pm (Helsinki)
Impact of Information Security Training on Recognition of Phishing Attacks: A Case Study of Vilnius Gediminas Technical University

Authors: Justinas Rastenis, Simona Ramanauskaitė, Justinas Janulevičius and Antanas Čenys

Impact of Information Security Training on Recognition of Phishing Attacks: A Case Study of Vilnius Gediminas Technical University

 

ABSTRACT

Phishing attack is a type of social engineering attack and often used as the initial stage of a larger campaign. It is dangerous as users might inadvertently reveal to the attackers personal data or sensitive corporate information. Therefore, inability to recognize and properly react to phishing attacks must be treated as one of the main security risks in the enterprise. In this paper, we present a methodology for evaluating employees’ resistance to phishing attacks. We also analyze the changes to the situation after the employees participated in information security training. Experiments with employees of Vilnius Gediminas Technical University were carried out within a period of one year to gather information on how credulous they are to phishing attacks before and after security training. Results of the experiment reveal the benefit of security training, however there is still room for improvement and need to pay attention in the future.

 

SHORT BIO:

I‘m Justinas Rastenis, born in 13 of April, 1987 in Vilnius. In 2010 I got my bachelor's degree in informatics at Vilnius Gediminas technical university (VGTU), later in 2012 I got my master degree in engineering informatics at VGTU. Since 2007 I working in Information technology and system center at VGTU, since 2012 I working as a lector in Information system department. I’m interested in information technology, cyber security, deploy new infrastructure services.

Jun 18, 2020
12:12pm - 12:24pm (Helsinki)
Composition of Ensembles of Recurrent Neural Networks for Phishing Websites Detection

Authors: Paulius Vaitkevicius and Virginijus Marcinkevicius

Composition of Ensembles of Recurrent Neural Networks for Phishing Websites Detection

 

ABSTRACT

Phishing remains a continual security threat, causing global losses exceeding 3.5 billion USD in 2019, according to the FBI’s Internet Crime Complaint Center. The Anti-Phishing Working Group (APWG) reported as many as 2,172 unique phishing websites detected per day in 2019. Most of the methods to solve the phishing websites’ detection problem proposed by the scientific community are based on classical classification algorithms on phishing datasets with hand-extracted features. Although these methods demonstrate high accuracies, unfortunately, they are sensitive to changing environment: phishers can learn the most relevant URL features and adapt their attacks to overcome the security check. Therefore, in search of less sensitive methods, deep neural networks were started to employ, as they do not require manual feature extraction and can directly learn a representation from the URL’s sequence of characters. The purpose of this research is to propose a new method for phishing websites’ URL detection based on ensembles of Recurrent neural networks and other types of deep neural networks. The results of our approach are presented in this paper and compared with the performance of other Recurrent neural networks. These results are additionally compared with the performance of classical classification algorithms on the same dataset with 48 features extracted. Our method with no manually extracted feature gives a significant increase in classification accuracy, compared with single Recurrent neural networks, and matches the accuracy of classical classification ensembles with manually extracted features.

 

SHORT BIO:

P. Vaitkevicius is a doctoral student at Vilnius University, Institute of Data Science and Digital Technologies. His research interests include machine learning, artificial intelligence, cybersecurity, and natural language processing.

Jun 18, 2020
12:25pm - 12:37pm (Helsinki)
Managing Security Risks in Post-Trade Matching and Confirmation using CorDapp

Authors: Mubashar Iqbal and Raimundas Matulevičius

Managing Security Risks in Post-Trade Matching and Confirmation using CorDapp

 

ABSTRACT

Blockchain technology is ready to revolutionise the financial industry. The financial industry has various security challenges (e.g., tampering, repudiation, denial of service, etc). The Corda platform provides suitable technological infrastructure to build the blockchain-based application (CorDapp) in the financial industry to overcome these challenges. In this paper, we take a case of the capital market post-trade matching and confirmation process to perform security risk management. We compare the countermeasures of centralised application and CorDapp that mitigate the security risks. Furthermore, we explain what security risks appear within the CorDapp.

 

SHORT BIO:

Raimundas Matulevičius received his Ph.D. diploma from NTNU, Norway. Currently, he holds a Professor of Information Security position at the University of Tartu, Estonia. His research interests include information security and privacy, security risk management and model-driven security. His publication record includes more than 90 articles. Prof. Matulevičius is an author of a book on “Fundamentals of Secure System Modelling” (Springer, 2017).

Jun 19, 2020
2:00pm - 3:00pm (Tallinn)
Conference Closing

Closing of the 14th Baltic DB&IS conference.

Invitation to 15th Baltic DB&IS conference in Riga, Latvia (2022).