Research Groups of Infotech Oulu Doctoral Program

 

Infotech Oulu research projects for 2018-2021:

Proactive and Context-Aware Networks under Reliability and Latency Constraints - NOOR

Project Investigator: Adjuct Professor Mehdi Bennis, Faculty of Information Technology and Electrical Engineering

The overarching goal of this project is to lay down the theoretical and algorithmic foundations of massive, low-latency, ultra-reliable and proactive wireless networks. Ensuring ultra-reliable and low-latency communication (URLLC) for 5G wireless networks and beyond mandates a departure from expected utility-based network design approaches, in which relying on average quantities (e.g., average throughput, average delay and average response time) is a necessity. Instead, a principled and scalable framework which takes into account delay, reliability, packet size, network architecture, and topology (across access, edge, and core) and decision making under uncertainty is sorely lacking. This constitutes one of the major objectives of this project with applications to several 5G verticals.

 

<--break->

Sparsity-Aware Online Signal Processing with Compressive Sensing - PROVING

Project Investigator: Adjuct Professor Marian CodreanuFaculty of Information Technology and Electrical Engineering

The emerging compressed sensing (CS) theory provides fundamentally new ways for acquisition, compression, transmission, processing, storage, and sharing of data. The goal of the project is to derive customized algorithms for two CS applications:

1) compressive wireless sensor networks for automatic process monitoring; the sensors convey wirelessly their compressive measurements to a central processor that has to detect (in real time) anomalies in the monitored process; we seek computationally efficient algorithms able to perform feature extraction and real time classification directly in the compressed domain  (without first reconstructing the signal of interest); and,

2) high resolution image & video signal reconstruction from block compressive measurements; here, the main challenge comes from the fact that the measurements vector corresponding to the entire image/video signal is too large to be processed all at once.

 

<--break->

Vision-based 3D perception for mixed reality applications

Project Investigator: Professor Janne HeikkiläFaculty of Information Technology and Electrical Engineering

Mixed reality (MR) refers to merging of real and virtual worlds using computer graphics. MR is implemented by overlaying virtual objects or scenes to the user’s field of view with optical or video see-through display systems, including wearable headsets and smartphones. A major challenge in MR is the alignment of the virtual objects with the visual information perceived from the real world. Accurate alignment is necessary to create realistic visualizations and immersive user experience, and it can only be achieved by exploiting the 3D structure of the environment. Another challenge is automatic analysis of the 3D scene that cannot be fully resolved by using 2D image recognition techniques. In this project, we focus on vision-based 3D perception that provides the basis for accurate alignment as well as for recognition. The aim is to develop novel methods for 3D sensing, modeling, and rendering, and build demonstrators to validate the performance of these methods in MR applications.

 

<--break->

IoT Localization Systems Using Shared Access in Radar Bands - IOTRAD

Project Investigator: Adjuct Professor Janne LehtomäkiFaculty of Information Technology and Electrical Engineering

New wireless systems require more and more spectrum. However, especially the desirable frequencies below 6 GHz have already been allocated. Spectrum sharing systems aim to solve this problem by sharing the spectrum between multiple users.
In this project, we consider sharing radar spectrum with internet of things (IoT) systems to enable accurate location tracking for IoT systems.
There will be in the future huge market for IoT devices and many of their applications require localization/location tracking. Since radar systems differ in frequencies, different kinds of IoT systems with different delay tolerances and communication distance requirements could be supported.

 

<--break->

Towards Reading Micro-expressions in the Real World

Project Investigator: Professor Guoying ZhaoFaculty of Information Technology and Electrical Engineering

This project aims to detect and recognize micro-expressions from both dynamic 2D and 3D analysis in order to develop camera-based methods and technologies for reading micro-expressions in real-world applications. The associations among micro-expressions and macro-expressions will be investigated for better understanding the emotions and improve the reliability for the multimodal system. As a case study, the application for learning assessment and support is planned to be explored with Learning and Educational Technology Research Unit (LET).

 

<--break->

Vision Sensing Technologies for Healthcare Diagnosis

Project Investigator: Associate Professor Adnenour Hadid,  Faculty of Information Technology and Electrical Engineering

Inspired by recent advances in computer vision together with medical evidences  indicating correlation between facial symptoms and some medical conditions, this project aims to devise computational models for detecting abnormalities reflective of diseases in person's facial structures and expressions based mainly on visual information. This would help designing futuristic unobtrusive technologies for health diagnosis and monitoring that people can effortlessly use in their daily lives without any contact. Imagine a "magic" mirror at home which unobtrusively monitors your physiological health measurements (e.g. heart rate and blood pressure), recognizes your affect states (e.g. stress and fatigue) and diagnoses possible diseases (e.g. imminent stroke or kidney infection) by only observing your face while you are in front of the mirror for activities such as shaving, brushing your teeth or washing your face. Such a "magic" medical mirror could, for instance, provide real-time feedback information about your health condition and even act as an assistive and therapeutic device by displaying a realistic 3D face avatar for engaging emotional interaction and preventive activities. As a second example, imagine a doctor wearing "smart" glasses which can unobtrusively estimate the pain of neonates and post-surgery patients that are incapable of articulating and expressing their pain experiences.

 

<--break->

Environment digitization and interactions by embedded self-sustainable systems - Entity

Project Investigator: Professor Heli Jantunen, Faculty of Information Technology and Electrical Engineering

Wireless hardware, including autonomous and wearable devices are responsible to collect and feed data for various networks thus creating the sensing elements of the Internet of Things. To manage power supply of independent devices, new energy technologies that combine harvesting and storage are necessary. While a number of promising enabling materials and structures exist today, their integration into real devices is the major challenge today, thus setting the topic and goal of our project.

 

<--break->

TWIsted LIGHT for digital tissue diagnosis - TWILIGHT

Project Investigator: Professor Igor Meglinski, Faculty of Information Technology and Electrical Engineering

The overall aim of the project is to validate the potential applicability of vector light beams (known as twisted light) for non-invasive tissue diagnosis (optical biopsy) and to develop an innovative proof-of-concept instrument – the orbital angular momentum (OAM)-scope – in order to improve the early detection of disease (cancer, inflammation, tissue degeneration, etc.) using OAM as a contrast enhancement factor. To achieve these targets the inter-disciplinary Consortium includes academic experts in polarization theory, numerical modeling, photonics and polarimetric instrumentation, phantoms tissue design and fabrication, as well as the industrial partner, will develop the low cost mobile imaging systems for the biomedical diagnosis.

 

<--break->

Personalization, Privacy and Quality Control for MaaS with Blockchain - TrustedMaaS

Project Investigator: Adjunct Professor Susanna Pirttikangas, Faculty of Information Technology and Electrical Engineering

Mobility as a service (MaaS) is a unifying platform for different transport services for a personalized journey with a single ticket. Blockchain is a distributed and immutable transaction ledger that provides trust between two actors without a need for a trusted third party. Blockchain is a clear candidate technology to solve some of the challenges presented in current MaaS platforms implementations. In this research we will explore how Blockchain technology can be integrated into existing MaaS platforms in order to mitigate some of the existing technological problems, speed up commercial transactions and maximize the revenues of different stakeholders. The project aims at more accurate and timely predictability of user behavior and the related costs in MaaS. We expect, that the integration of the service providers to the MaaS platform infrastructure should prove significantly easier with Blockchain than with the traditional middleware model and that the integration leads to more efficient platforms enabling MaaS. Furthermore, we expect to solve some of the critical problems that prevent national and international coverage such as more flexibility, privacy, security and a solution to the scalability problem. In the end, the results will be used in defining clearer business plans for different actors based on a decentralized solution and simplification of the operations among the different stakeholders. The project will be performed in close co-operation with industry and academia providing scientific breakthroughs as well as further disruption in both transport and financial sectors. Industrial collaboration is realized with MaaS Global, PayIQ and Chainfrog. This project is expected to extend the multidisciplinary collaboration with Oulu Business School, Center for Machine Vision and Signal Analysis and Center for Ubiquitous Computing.

 

<--break->

Bayesian Trusted Edge Analytics - B-TEA

Project Investigator: Professor Jukka Riekki, Faculty of Information Technology and Electrical Engineering

This project studies distributed data analysis in the Internet of Things. The research focuses on mobile agent based Bayesian machine learning and distributed Markov Chain Monte Carlo methods for resource usage optimization in edge computing. The developed methods will be evaluated in real-world applications. The project is funded by the Infotech Oulu, University of Oulu.

 

<--break->

Sensor Within: Harnessing Human Biology for Sensing Applications

Project Investigator: Professor Juha Röning, Faculty of Information Technology and Electrical Engineering

The overall aim of the project is to validate the potential applicability of vector light beams (known as twisted light) for non-invasive tissue diagnosis (optical biopsy) and to develop an innovative proof-of-concept instrument – the orbital angular momentum (OAM)-scope – in order to improve the early detection of disease (cancer, inflammation, tissue degeneration, etc.) using OAM as a contrast enhancement factor. To achieve these targets the inter-disciplinary Consortium includes academic experts in polarization theory, numerical modeling, photonics and polarimetric instrumentation, phantoms tissue design and fabrication, as well as the industrial partner, will develop the low cost mobile imaging systems for the biomedical diagnosis.

 

<--break->

Prediction and decision support systems for knee osteoarthritis

Project Investigator(s): Associate Professor Simo Saarakkala and Professor Miika NieminenFaculty of Medicine

Osteoarthritis (OA) is the most common joint disease in the world. Despite the extensive research, the etiology of OA is still poorly understood and its progression is highly difficult to predict clinically. However, large amount of accumulated clinical and research data exists, which enables new possibilities to understand OA progression when analysed with novel machine learning based methods. The ultimate objective is to produce a data-driven computational tool to support clinical decision making and to find major risk factors and determinants of OA and its progression. The research project will also have a strong focus on state-of-the-art machine learning approaches allowing to combine patients’ clinical background and imaging data.

Last updated: 23.1.2018