Lauri LovénUniversity of Oulu · Center for Ubiquitous Computing
Lauri Lovén
Doctor of Science (Tech.)
About
52
Publications
46,553
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
886
Citations
Citations since 2017
Introduction
I currently work as postdoctoral researcher at the Center for Ubiquitous Computing, University of Oulu. My research interests include distributed AI (especially distr. learning, inference and decision making), edge computing, EdgeAI, spatiotemporal models, and advanced data analytics in general.Twitter: https://twitter.com/LauriLoven
Additional affiliations
January 2018 - present
Position
- PhD Student
Description
- I'm working at the center as a researcher, writing my doctoral thesis on the topic of distributed AI methods in the context of Edge Analytics.
June 2016 - December 2017
University of Oulu
Position
- Analyst
Description
- I worked as the head of the Analytics+ business and research ecosystem (http://www.analytics.plus/).
August 2015 - May 2016
Position
- Research Assistant
Description
- I worked on my master's thesis on road friction prediction. I built statistical learning models, based on mixed effects models and Gaussian Markov random fields, for predicting the tyre--road friction coefficient in an urban, arctic environment.
Education
June 2015 - May 2016
August 2013 - May 2015
Publications
Publications (52)
Spatiotemporal interpolation provides estimates of observations in unobserved locations and time slots. In smart cities, interpolation helps to provide a fine-grained contextual and situational understanding of the urban environment, in terms of both short-term (e.g., weather, air quality, traffic) or long term (e.g., crime, demographics) spatio-te...
Capacitated spatial clustering, a type of unsupervised machine learning method, is often used to tackle problems in compressing, classifying, logistic optimization and infrastructure optimization. Depending on the application at hand, a wide set of extensions may be necessary in clustering.
In this article we propose a number of novel extensions...
Efficient service placement and workload allocation methods are necessary enablers for the actively studied topic of edge computing. In this paper, we show that under certain circumstances, the number of superfluous workload reallocations from one edge server to another may grow to a significant proportion of all user tasks – a phenomenon we presen...
Future AI applications require performance, reliability and privacy that the existing, cloud-dependant system architectures cannot provide. In this article, we study orchestration in the device-edge-cloud continuum, and focus on AI for edge, that is, the AI methods used in resource orchestration. We claim that to support the constantly growing requ...
Efficient resource usage in edge computing requires clever allocation of the workload of application components. In this paper, we show that under certain circumstances, the number of superfluous workload reallocations from one edge server to another may grow to a significant proportion of all user tasks—a phenomenon we present as a reallocation st...
This article contributes a research vision for using edge computing to deliver the computing infrastructure for emerging smart megacities, with use cases, key requirements, and reflections on the state of the art. We also address edge server placements, a key challenge for edge computing adoption.
italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Edge Intelligence
(EI) is an emerging computing and communication paradigm that enables Artificial Intelligence (AI) functionality at the network edge. In this article, we highlight EI as an emerging and important field of research, discuss the state o...
Edge computing augments cloud computing. While cloud computing is based on far away computing centres, edge computing acknowledges the computing resources in the continuum between local devices and the cloud. The computing resources in edge computing are often heterogeneous, with varying capacity, intermittent connectivity, and opportunistic availa...
Location-allocation and partitional spatial clustering both deal with spatial data, seemingly from different viewpoints. Partitional clustering analyses data points by partitioning them into separate groups, while location-allocation places facilities in locations that best meet the needs of demand points. However, both partitional clustering and l...
The deployment of edge computing infrastructure requires a careful placement of the edge servers, with an aim to improve application latencies and reduce data transfer load in opportunistic Internet of Things systems. In the edge server placement, it is important to consider computing capacity, available deployment budget, and hardware requirements...
The fifth generation (5G) wireless networks are on the way to be deployed around the world. The 5G technologies target to support diverse vertical applications by connecting heterogeneous devices and machines with drastic improvements in terms of high quality of service, increased network capacity and enhanced system throughput. However, 5G systems...
The growing network density and unprecedented increase in network traffic, caused by the massively expanding number of connected devices and online services, require intelligent network operations. Machine Learning (ML) has been applied in this regard in different types of networks and networking technologies to meet the requirements of future comm...
![Experiment phasing. (Table adapted from one by Halkola et al. [12].)](profile/Lauri-Loven/publication/343335845/figure/tbl1/AS:919285677432832@1596186193576/Experiment-phasing-Table-adapted-from-one-by-Halkola-et-al-12_Q320.jpg)
Well-being in smart environments refers to the mental, physiological and emotional states of people passing through environments where sensors, actuators and computers are intertwined with everyday tasks. In that context, well-being must be measurable and, to some extent, susceptible to external influence within the short time-spans that people spe...
Advances in technology and data analysis provide rich opportunities for developing intelligent environments assisting their inhabitants, so-called smart environments or smart spaces. Enhanced with technology, sensors, user interfaces, and various applications, such smart spaces are capable of recognizing users and situations they are in, react acco...
In this white paper we provide a vision for 6G Edge Intelligence. Moving towards 5G and beyond the future 6G networks, intelligent solutions utilizing data-driven machine learning and artificial intelligence become crucial for several real-world applications including but not limited to, more efficient manufacturing, novel personal smart device env...
Executive Summary This white paper discusses the different business verticals that are expected to gain productivity enhancements with the introduction of B5G/6G wireless services. It is evident that wireless offers benefits when the use case exhibits mobility, requires nomadic behavior or flexibility and in some situation, cost may be favoring wir...
In this article, we study the scaling up of edge computing deployments. In edge computing, deployments are scaled up by adding more computational capacity atop the initial deployment, as deployment budgets allow. However, without careful consideration, adding new servers may not improve proximity to the mobile users, crucial for the Quality of Expe...
In the context of evolving communication technologies like 5G and the inevitable 6G, edge computing has a significant role to play. Cloud computing is inadequate at handling the real-time data processing and analysis requirements the above advancements will entail. However, edge computing has its own set of challenges, intensified further upon empl...
6G wireless networks improve on 5G by further increasing reliability, speeding up the networks and increasing the available bandwidth. These evolutionary enhancements, together with a number of revolutionary improvements such as high-precision 3D localization, ultra-high reliability and extreme mobility , introduce a new generation of 6G-native app...
In this paper, we describe how the microservices paradigm can be used to design and implement distributed edge services for Internet of Things applications. As a case study, traditionally monolithic user mobility analysis service is developed, with distributed and extendable microservices, for the standardized ETSI MEC system reference architecture...
This study discusses measurement of well-being in the context of smart environments. We propose an experimental design which induces variation in an individual's flow, stress, and affect for testing different measurement methods. Both qualitative and quantitative measuring methods are applied, with a variety of wearable sensors (EEG sensor, smart r...
As fifth generation (5G) research is maturing towards a global standard, the research community must
focus on the development of beyond-5G solutions and the 2030 era, i.e. 6G. It is not clear yet what 6G will
entail. It will include relevant technologies considered too immature for 5G or which are outside the defined
scope of 5G. This white pape...
As fifth generation (5G) research is maturing towards a global standard, the research community has started to focus on the development of beyond-5G solutions and the 2030 era, i.e. 6G. In the future, our society will be increasingly digitised, hyper-connected and globally data driven. Many widely anticipated future services will be critically depe...
Prevalent weather prediction methods are based on sensor data, collected by satellites and a sparse grid of stationary weather stations. Various initiatives improve the prediction models by including additional data sources such as mobile weather sensors, mobile phones, and micro weather stations of, for example, smart homes. The underlying computi...
Edge computing in the Internet of Things brings applications and content closer to the users by introducing an additional computational layer at the network infrastructure, between cloud and the resource-constrained data producing devices and user equipment. This way, the opportunistic nature of the operational environment is addressed by introduci...
Edge computing that leverages cloud resources to the proximity of user devices is seen as the future infrastructure for distributed applications. However, developing and deploying edge applications, that rely on cellular networks, is burdensome. Such network infrastructures are often based on proprietary components, each with unique programming abs...
Edge computing that leverages cloud resources to the proximity of user devices is seen as the future infrastructure for distributed applications. However, developing and deploying edge applications, that rely on cellular networks, is burdensome. Such network infrastructures are often based on proprietary components, each with unique programming abs...
Fifth Generation (5G) wireless systems are expected to fully integrate telecommunication technologies with the cloud computing and softwarized paradigms. Moreover, the realization of 5G will empower ultra reliability, low latency, massive scalability, and high capacity. 5G brings edge computing that offers customers more control of their data. Howe...
Edge and fog computing, prominent parts of the up-coming 5G mobile networks and future 6G technologies, promise to reduce applications' latencies, improve controls on privacy, and reduce network bandwidth usage. The promises are delivered by pulling computations from the remote cloud to close to the devices, where data is generated and applications...
Edge and Fog Computing platforms, together with soon-to-come 5G technologies and future 6G visions, enable local, low-latency computational resources. At the same time, rising awareness of novel artificial intelligence and other data-driven applications sets a demand of trustworthy computational power close to the client. Our research aims to bring...
Rising utilization of novel artificial intelligence and other data-driven applications sets a demand for privacy-preserving large-scale data management. In the current, cloud-centric model, trust is placed on third parties that collect, aggregate, link and analyse personally identifiable information (PII) with artificial intelligence (AI) and machi...
Edge computing, together with soon-to-come 5G technologies and future 6G vision, enable distributed computing platforms with computational and data resources in the close proximity to the users/clients with low-latency connections. Traditional data flow in the Internet of Things is vertical , spanning between the cloud, the network infrastructure c...
Edge computing, a key part of the upcoming 5G mobile networks and future 6G technologies, promises to distribute cloud applications while providing more bandwidth and reducing latencies [1]. The promises are delivered by moving application-specific computations between the cloud, the data producing devices, and the network infrastructure components...
The advances in communication technologies have made it possible to gather road condition information from moving vehicles in real time. However, data quality must be assessed and its effects to the road weather forecasts analyzed before using the new data as input in the forecasting systems. Road surface temperature forecasts assimilating mobile o...
In the next generation, 5G and beyond 5G, networks cyber-security solutions are increasingly incorporating Artificial Intelligence (AI) and Machine Learning (ML) techniques at the edge devices. We see the relationship of security and edge AI in two interesting viewpoints such as AI for edge security and security for edge AI. Throughout this article...
Mobile, vehicle-installed road weather sensors are becoming ubiquitous. While mobile sensors are often capable of making observations on a high frequency, their reliability and accuracy may vary. Large-scale road weather observation and forecasting are still mostly based on stationary road weather stations (RWS). Though expensive, sparsely located...
Residual plot of the inference model.
(TIF)
Q-Q plot of the mobile sensor calibration level random effect.
(TIF)
Q-Q plot of a sample of 100 residuals.
(TIF)
Q-Q plot of the RWS sensor calibration level random effect.
(TIF)
The Experience Sampling Method is widely used to collect human labelled data in the wild. Using this methodology, study participants repeatedly answer a set of questions, constructing a rich overview of the studied phenomena. One of the methodological decisions faced by researchers is deciding on the question scheduling. The literature defines thre...
Software agents have been exploited to handle the inherent dynamicity in the Internet of Things (IoT) systems, as agents are capable of autonomous, reactive and proactive operation in response to changes in their local environment. Agents, operating at the network edge, enable leveraging cloud resources into the proximity of the user devices. Howev...
Recent technological development offers new possibilities for taking into account peoples' personal wellness data in adjustment of environment conditions. For example, users' heartrate, facial expression, room temperature, and CO2 data could be used for adjustment of lighting, temperature, and air-condition to support people's wellbeing in smart en...
What does well-being mean in the context of smart environments? What restrictions are set, how can well-being be measured and predicted? Can smart environments control or influence individual well-being? We seek to answer these questions by aggregating existing research on well-being and identifying the concepts relevant for smart environments. As...
Target audience analysis (TAA) is an essential part of any psychological operation. In order to convey a change in behaviour, the overall population is systematically segmented into target audiences (TAs) according to their expected responsiveness to different types of influence and messages, as well as their expected ability to behave in a desired...
An information system including subscriber stations (MS), at least two service sources (2 to 5) providing a respective service to subscriber stations of the system, and an access point (1) arranged to analyze a service request in order to forward the service request to the service source (2) offering the service, the service sources (2 to 5) being...
The invention relates to an information system comprising: subscriber stations (MS), and a first service source (2) for providing the subscriber station (MS) with a requested service. In order to improve the user friendliness of the system, the system comprises an error correction device (6) arranged to correct a received service request and a sess...
Projects
Projects (6)
The EU-funded FRACTAL project is developing a computing node on which to base a cognitive fractal network capable of learning from and responding to its environment. It will support seamless, fast and reliable interaction between the physical world and the cloud for applications ranging from self-driving cars to remote medical procedures.
The objective of this research activity is to create a reliable computing node that will create a Cognitive Edge under industry standards. This computing node will be the building block of scalable Internet of Things (from Low Computing to High Computing Edge Nodes). The cognitive skill will be given by an internal and external architecture that allows to forecast its internal performance and the state of the surrounding world. Hence, this node will have the capability of learning how to improve its performance against the uncertainty of the environment.
As a result of the integration of these cognitive systems into a fractal network, there will be another intrinsic crucial advantage, emergency and adaptability, new functions will flourish through the created space of possibilities of our cognitive Systems. This complex network will transfer all those cognitive advantages to the Edge, a computing paradigm that lay down between the physical world and the cloud.
We aim to identify the challenges and detail the potential benefits of AI at the edge, building a coherent and overarching vision of what distributed artificial intelligence means in the context of edge computing. Further, we aim to find the methods realizing those benefits, testing hypotheses in a real-world setting on the edge platform atop the 5G test network (http://5gtn.fi). Our vision will be realized within the 8-year span of the Academy of Finland 6Genesis Flagship.
