Projects

• AnaRISE: Big Data Analytics for Visualization of RISE Business, Internal RISE Project, 2020 - 2021.

  Internal RISE digitalization project with a goal to make available, for employees and managers, a set of rich information and visualization tools for exploring the various activities, projects, people, and groups across RISE. The project is based on data driven analytics and NLP and uses automated ML pipelines to easily incorporate new data.}

• Streamline: Fast Reactive Analytics, EU funded ICT-16-2015 Big Bata research, 2015 - 2018.

  The goal of STREAMLINE is delivery of fast reactive analytics to be useful for a broad spectrum of problems including personalized recommendation, customer retention and of the targeted services. The approach to apply includes developing a high level declarative language for reducing the programming expertise of users and developing fast reactive machine learning technologies.

• ROSE: Roll Out Scenarios of Electric Roads, 2018 - 2019.

  The goal of the project is to identify road segments that are most suitable and economically viable to be converted to electric roads and to have a gradual roll out plan for electric roads on large Europe-scale network. In this project, we adopt a data driven approach to identify suitable road segments and propose roll out plan by analysing and fusing various traffic datasets to analyse driving pattern of individual vehicles. The vehicle positioning data available at Scania and Volvo provides information about driving pattern and fuel consumption and can thereby be analyzed to identify suitable stretches. The project is a collaboration between RISE, Scania, Volvo Trucks, Chalmers University, and the Swedish Transport Agency.

• BIDAF: Big Data Analytics Framework. Funded by KK-stiftelsen, 2015 - 2020.

  The goal of the BIDAF project is to create a strong distributed research environment for Big Data Analytics. The scientific objectives centre around realising the promise of advanced, near real-time analytics on uncertain data with high volume and velocity through machine learning techniques, with key challenges including i) development of a computational platform suitable for machine learning of massive streaming and distributed data; ii) development of machine learning algorithms suitable for handling both opportunities and challenges with massive data; and iii) to provide analytics methodology and high level functionality to make the value in massive data easier to access.

• BADA: FFI - Big Automotive Data Analytics. Funded by Vinnova, 2015 - 2017. The BADA project fuses big data analytics with the transport industry in Sweden. It is a collaboration between RISE SICS, Volvo cars, Volvo trucks, Scania, and the Swedish Transport Agency. It is financed by Vinnova, a state funding agency. In the BADA project, we investigate how big data analytics platforms and machine learning algorithms can impact the transport and automotive industries. The approach is centred on a number of industry driven use-cases and the development of prototype systems.

  • BADA overview presentation
  • BADA website

• MC-Data: Multi-Cloud Data Management. Funded by EIT Digital, 2013 - 2015.

• E2E Clouds: End-to-End Distributed Clouds. Funded by SSF: Swedish Foundation for Strategic Research (RIT10-0043), 2011-2016.

• RMAC: Resource Management Across Clouds. Funded by EIT Digital , 2012.

• CS2: Complex Service Systems: Elastic Cloud Storage (a focus project in SRA ICT TNG research programme, 2010-2012.

• Grid4All: Self-* Grid: Dynamic Virtual Organizations for schools, families, and all. FP6 EU project (034567), 2006 - 2009.

• Niche: a Distributed Component Management System which is used to develop, to deploy and to execute self-managing distributed component-based applications on a structured overlay network of computers.

Guides

• A Guide on how to use an External Kafka Client with HopsWorks
• Getting Started with Traffic Flow Analysis of sensor data from Motorway Control System using Spark

Open Source

• HDFS Contents Manager: A contents manager for Jupyter that used HDFS as a storage backend
• OnlineElastMan: A proactive and self-trained elasticity manager for Cloud services.
• SpanEdge: Stream processing on Edge Clouds!
• ElastMan: Elasticity Manager for Elastic Cloud-Based Services.

Master Thesis Supervision

• WinBro: A Window and Broadcast-based Parallel Streaming Graph Partitioning Framework for Apache Flink, by Adrian Ackva, 2019.
• An evaluation of deep neural network approaches for traffic speed prediction, by Cosar Ghandeharioon, 2018.
• Scalable System-Wide Traffic Flow Predictions Using Graph Partitioning and Recurrent Neural Networks, by Jon Reginbald Ivarsson, 2018.
• Road traffic congestion detection and tracking with Spark Streaming analytics, by Thorsteinn Thorri Sigurdsson, 2018.
• Detection and Classification of Anomalies in Road Traffic using Spark Streaming, by Nathan Adolfo Consuegra, 2018.
• Topology-Aware Placement of Stream Processing Components on Geographically Distributed Virtualized Environments, by Ken Danniswara, 2015.
• Self-trained Proactive Elasticity Manager for Cloud-based Storage Services, by David Daharewa Gureya, 2015.
• Automated Control of Elasticity for a Cloud-Based Key-Value Store, by Ala Arman, 2012.
• Self Tuning for Elastic Storage in Cloud Environment, by M. Amir Moulavi, 2011.
• Robust Fault-Tolerant Majority Based Key-Value Data Store Supporting Multiple Data Consistency, by Tareq Jamal Khan, 2011.
• Achieving Robust Self Management for Large Scale Distributed Applications using Management Elements, by Muhammad Asif Fayyaz, 2010.
• Distributed Control Loop Patterns for Managing Distributed Applications, by Mudassar Majeed, 2009.
• Evaluation of Approaches to Policy-Based Management in Self-Managing Distributed Systems, by Lin Bao, 2009.
• Multi-Binding and Component Mobility Support, by Rizwan Ahmed, 2009.

Teaching

Awards

Best Paper Award for the paper “State-Space Feedback Control for Elastic Distributed Storage in a Cloud Environment,” published in The Eighth International Conference on Autonomic and Autonomous Systems ICAS 2012, St. Maarten, Netherlands Antilles, March 2012, pp. 18-27.	First Prize Award for the presentation “Enabling and Achieving Self-Management for Large Scale Distributed Systems” at the Contrail Summer School, Hyeres, France, June 2011.

MeetUps

• Interactive Exploration and Visualisation of Traffic Accident Data, at OpenStack User Group Sweden MeetUp, July 3, 2017
• OpenStack in Docker Containers, at OpenStack User Group Sweden MeetUp, Apr 6, 2016.