MATRIX – Machine learning based decision support for train traffic disturbance management: An experimental study

In railways, it is often not possible to avoid real-time disturbances altogether. A disturbed train may easily spread its delay to other trains, resulting in reduced train punctuality and substantial socio-economic costs. During disturbances, it is important to effectively prioritize trains, resolve the potential conflicts in the train timetable and quickly arrive at a rescheduled timetable as per the infrastructure manager’s (IM’s) goals. Currently, this task is handled manually by traffic controllers. The train timetable rescheduling problem is typically hard to solve, even for modern computers. Solving it requires exploring many alternative rescheduling decisions and quickly finding a good- enough solution based on the IM’s goals in real-time. Two main solution approaches in computer science to solve real-world problems are traditional and machine learning (ML) approaches. In a traditional approach, a computer is programmed to do various computations on input data to solve the problem and generate the solution as output. In an ML approach, a computer uses input data and expected outputs to learn how to solve the problem at hand without being explicitly programmed. The learning process results in an ML model/program, which helps to make data-driven decisions in the future using its learned experience. ML approaches have received remarkable attention in recent years. They have been shown to work well in transportation and many other problem domains, independently or in combination with traditional approaches, to tackle complex scheduling problems and get better solutions. This project aims to improve decision support for effective conflict resolution during disturbances by devising an ML model. The developed ML model will be able to assist traffic controllers in resolving a conflict during disturbances by suggesting the train to be prioritized (along with a confidence score). The model will be used in combination with a rescheduling algorithm developed at BTH (2016–2021) to speed it up and make data-driven decisions. We will assess the devised model, using various disturbances on a Swedish railway network, by evaluating the quality of the rescheduled timetables obtained by following the model’s suggestions.

Read more about the project

AgileSec – Agile Development of Security Critical Software

Today, the software industry is moving to agile development processes. One of the main ideas is that an agile team has sufficient skills to get the job done and does not have to rely on external experts. In traditional software development, security issues are handled by experts. However, in agile development, security issues should be handled by the team. The agile process must, therefore, be extended with security related quality control and support. Rigorous quality control may, however, reduce productivity. The level of security expertise may differ significantly from one agile team to another, and it is, therefore, important to adapt security related quality control to the security maturity level of the team. In this application, we argue that an accurate estimate of a team’s security maturity would be helpful in many ways.

Read more about the project

Blixten II

The need for and potential of using computational decision-support system for real-time railway traffic management has become more apparent the last years. In the research project TRANSFORM, effective methods to parallelize a sequential scheduling algorithm have been developed and analyzed. The parallelization has contributed to substantial speed-ups as well as increased stability and flexibility, allowing for distributed computations and multiple objectives to be incorporated. The intention is to develop and evaluate these algorithms further within this project BLIXTEN II, with a focus on mainly three different aspects:

Read more about the project

TRANS-FORM – Smart transfers through unraveling urban form and travel flow dynamics

Smart cities and communities rely on efficient, reliable and robust transport systems. Managing urban public transport systems is becoming increasingly challenging with a pronounced shift towards multiply actors operating in a multi-modal multi-level networks. This calls for the development of an integrated passenger-focused management approach which takes advantage of multiple data sources and state-of-the-art scheduling support.

TRANS-FORM, a cooperation between universities, industrial partners, public authorities and private operators, will develop, implement and test a data driven decision making tool that will support smart planning and proactive and adaptive operations. The tool will integrate new concepts and methods of behavioural modelling, passenger flow forecasting and network state predictions into real-time operations.

Read more about the project

Symphony

The Symphony project aims at investigating and solving the problem of exposing services by a marketplace in Cloudnative and federated environments, addressing the security, confidentiality, privacy and provenance needs for future applications of digital societies. By considering the use-case of data services for managing Renewable Energy Source (RES), the Symphony project seeks to develop solutions for securing, monitoring and accounting of service chains using blockchain-based techniques. In addition, the Symphony project applies a requirements-driven engineering approach that analyses the security needs of Cloudnative systems and of the RES use-ease as considered by the user. The project will implement a prototype for service exposure model using a service chain for RES on TRL 4/5 (“Technology validated in lab /relevant environment (industrially relevant environment in the case of key enabling technologies”).

Read more about the project

Bonseyes

The Bonseyes project aims to develop a platform consisting of a Data Marketplace, Deep Learning Toolbox, and Developer Reference Platforms for organizations wanting to adopt Artificial Intelligence in low power IoT devices (“edge computing”), embedded computing systems, or data center servers (“cloud computing”). It will bring about orders of magnitude improvements in efficiency, performance, reliability, security, and productivity in the design and programming of Systems of Artificial Intelligence that incorporate Smart Cyber Physical Systems while solving a chicken-egg problem for organizations who lack access to Data and Models. It’s open software architecture will facilitate adoption of the whole concept on a wider scale.

Read more about the project

FLOAT: Real-time decision support for railway traffic management

This project is financed by Trafikverket and is a continuation of the previous research projects OAT+ and EOT (both financed by Trafikverket). Researchers working in the project are currently Ph D student Sai Prashanth Josyula, Post-Doc Omid Gholami and Associate Professor Johanna Törnquist Krasemann, BTH.

Read more about the project

CONVINcE

CONVINcE addresses the challenge of reducing the power consumption in IPbased video networks with an end-to-end approach, from the Head End where contents are encoded and streamed to the terminals where they are consumed, embracing the Content Delivery Networks (CDN) and the core and access networks. Energy saving is a key challenge for the European Union and the CONVINcE project contributes to win this challenge. CONVINcE helps the European industry to develop new solutions and products reducing the energy footprint of video delivery networks. The double effect gained is to reduce the energy consumption in Europe and to boost the competiveness of the European industry in the area addressed by the CONVINcE project.

Read more about the project

CCC – Center for Computational Criminology

Within the Center for Computational Criminology (CCC) at Blekinge Tekniska Högskola (BTH), research and collaboration have been conducted with law enforcement agencies, mainly the police since 2012. The work was funded by the Swedish Agency for Growth between 2012-2014, by Blekinge Region in 2015 and by Vinnova in 2016 . The purpose of the work of the CCC is to investigate, develop and evaluate automated methods to simplify criminal investigations within law enforcement agencies.

Read more about the project