Pekka Pääkkönen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Pekka Pääkkönen has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Daniel Pakkala
VTT Technical Research Centre of Finland, Oulu, Finland
4 shared publications Antti Heikkinen
VTT Technical Research Centre of Finland, Kaitoväylä 1, 90570 Oulu, Finland
1 shared publication- C. Bento1 shared publication
Cornelia Kappler
Siemens Communications, Berlin, Germany
1 shared publication- Cs. Simon1 shared publication
D. Pakkala
VTT Technical Research Centre of Finland, Käitoväylä 1, 90570, Oulu, Finland
1 shared publication
Latest Publications
- Open Access
- 28 May 2024
- Published by Elsevier in Internet of Things
- Vol. 26
Reference architecture design and evaluation for digitalization of underground mining
- 28 May 2024
- Published by Elsevier in Internet of Things
- Vol. 26
Open AccessReference architecture design and evaluation for digitalization of underground mining
- Open Access
- 28 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 92735-92751
Evaluation of Human Pose Recognition and Object Detection Technologies and Architecture for Situation-Aware Robotics Applications in Edge Computing Environment
Realization of situation-awareness for autonomous robotics applications in edge computing environment is challenging. First, computing capabilities of edge devices are limited, which must be considered in the execution of machine learning (ML)-based solutions. Second, many technologies are available for realizing situation-aware capabilities, but comparison and integration of solutions creates additional challenges. Third, existing ML-based models are often not directly applicable for realizing custom applications, and model(s) may need to be re-trained with new data. The contribution of this paper is efficiency and feasibility evaluation of human pose recognition and object detection technologies in edge computing environment. Several lessons learnt covering constraints are presented regarding feasibility of the experimented technologies and data sets. The efficiency evaluation results indicated that simultaneous human pose recognition (Google’s Movenet) and object detection (Yolov5) on Jetson AGX Xavier achieved ~13-16 FPS, while GPU and CPU utilization remained at a medium level, and most of the memory remained unused (< 44 %). Object concept and human pose concept activation algorithms may be considered as an additional contribution. Realized architecture design of the prototyped system in multiple computing environments can be considered as a partial evaluation of a ML-based big data reference architecture.
- 28 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 92735-92751
Open AccessEvaluation of Human Pose Recognition and Object Detection Technologies and Architecture for Situation-Aware Robotics Applications in Edge Computing Environment
Realization of situation-awareness for autonomous robotics applications in edge computing environment is challenging. First, computing capabilities of edge devices are limited, which must be considered in the execution of machine learning (ML)-based solutions. Second, many technologies are available for realizing situation-aware capabilities, but comparison and integration of solutions creates additional challenges. Third, existing ML-based models are often not directly applicable for realizing custom applications, and model(s) may need to be re-trained with new data. The contribution of this paper is efficiency and feasibility evaluation of human pose recognition and object detection technologies in edge computing environment. Several lessons learnt covering constraints are presented regarding feasibility of the experimented technologies and data sets. The efficiency evaluation results indicated that simultaneous human pose recognition (Google’s Movenet) and object detection (Yolov5) on Jetson AGX Xavier achieved ~13-16 FPS, while GPU and CPU utilization remained at a medium level, and most of the memory remained unused (< 44 %). Object concept and human pose concept activation algorithms may be considered as an additional contribution. Realized architecture design of the prototyped system in multiple computing environments can be considered as a partial evaluation of a ML-based big data reference architecture.
- Open Access
- 21 October 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (20) , 10679
Concept and Architecture for Applying Continuous Machine Learning in Multi-Access Routing at Underground Mining Vehicles
Autonomous moving vehicles facilitate mining of ore in underground mines. The vehicles are usually equipped with many sensor-based devices (e.g., Lidar, video camera, proximity sensor, etc.), which enable environmental monitoring, and remote control of the vehicles at the control center. Transfer of sensor-based data from the vehicles towards the control center is challenging due to limited connectivity enabled by the multi-access technologies of the communication infrastructure (e.g., 5G, Wi-Fi) within the underground mine, and the mobility of the vehicles. This paper presents design, development, and evaluation of a concept and architecture enabling continuous machine learning (ML) for optimizing route selection of real-time streaming data in a real and emulated underground mining environment. Continuous ML refers to training and inference based on the most recently available data. Experiments in the emulator indicated that utilization of a ML-based model (based on the RandomForestRegressor) in decision making achieved ~5–13% lower one-way delay in streaming data transfers, when compared to a simpler heuristic model.
- 21 October 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (20) , 10679
Open AccessConcept and Architecture for Applying Continuous Machine Learning in Multi-Access Routing at Underground Mining Vehicles
Autonomous moving vehicles facilitate mining of ore in underground mines. The vehicles are usually equipped with many sensor-based devices (e.g., Lidar, video camera, proximity sensor, etc.), which enable environmental monitoring, and remote control of the vehicles at the control center. Transfer of sensor-based data from the vehicles towards the control center is challenging due to limited connectivity enabled by the multi-access technologies of the communication infrastructure (e.g., 5G, Wi-Fi) within the underground mine, and the mobility of the vehicles. This paper presents design, development, and evaluation of a concept and architecture enabling continuous machine learning (ML) for optimizing route selection of real-time streaming data in a real and emulated underground mining environment. Continuous ML refers to training and inference based on the most recently available data. Experiments in the emulator indicated that utilization of a ML-based model (based on the RandomForestRegressor) in decision making achieved ~5–13% lower one-way delay in streaming data transfers, when compared to a simpler heuristic model.
- Open Access
- 29 December 2020
- Published by MDPI AG in Future Internet
- Vol. 13 (1) , 5
Architecture for Enabling Edge Inference via Model Transfer from Cloud Domain in a Kubernetes Environment
The current approaches for energy consumption optimisation in buildings are mainly reactive or focus on scheduling of daily/weekly operation modes in heating. Machine Learning (ML)-based advanced control methods have been demonstrated to improve energy efficiency when compared to these traditional methods. However, placing of ML-based models close to the buildings is not straightforward. Firstly, edge-devices typically have lower capabilities in terms of processing power, memory, and storage, which may limit execution of ML-based inference at the edge. Secondly, associated building information should be kept private. Thirdly, network access may be limited for serving a large number of edge devices. The contribution of this paper is an architecture, which enables training of ML-based models for energy consumption prediction in private cloud domain, and transfer of the models to edge nodes for prediction in Kubernetes environment. Additionally, predictors at the edge nodes can be automatically updated without interrupting operation. Performance results with sensor-based devices (Raspberry Pi 4 and Jetson Nano) indicated that a satisfactory prediction latency (~7–9 s) can be achieved within the research context. However, model switching led to an increase in prediction latency (~9–13 s). Partial evaluation of a Reference Architecture for edge computing systems, which was used as a starting point for architecture design, may be considered as an additional contribution of the paper.
- 29 December 2020
- Published by MDPI AG in Future Internet
- Vol. 13 (1) , 5
Open AccessArchitecture for Enabling Edge Inference via Model Transfer from Cloud Domain in a Kubernetes Environment
The current approaches for energy consumption optimisation in buildings are mainly reactive or focus on scheduling of daily/weekly operation modes in heating. Machine Learning (ML)-based advanced control methods have been demonstrated to improve energy efficiency when compared to these traditional methods. However, placing of ML-based models close to the buildings is not straightforward. Firstly, edge-devices typically have lower capabilities in terms of processing power, memory, and storage, which may limit execution of ML-based inference at the edge. Secondly, associated building information should be kept private. Thirdly, network access may be limited for serving a large number of edge devices. The contribution of this paper is an architecture, which enables training of ML-based models for energy consumption prediction in private cloud domain, and transfer of the models to edge nodes for prediction in Kubernetes environment. Additionally, predictors at the edge nodes can be automatically updated without interrupting operation. Performance results with sensor-based devices (Raspberry Pi 4 and Jetson Nano) indicated that a satisfactory prediction latency (~7–9 s) can be achieved within the research context. However, model switching led to an increase in prediction latency (~9–13 s). Partial evaluation of a Reference Architecture for edge computing systems, which was used as a starting point for architecture design, may be considered as an additional contribution of the paper.
- Open Access
- 6 April 2020
- Published by Springer Nature in Journal of Big Data
- Vol. 7 (1) , 1-29
Extending reference architecture of big data systems towards machine learning in edge computing environments
Background: Augmented reality, computer vision and other (e.g. network functions, Internet-of-Things (IoT)) use cases can be realised in edge computing environments with machine learning (ML) techniques. For realisation of the use cases, it has to be understood how data is collected, stored, processed, analysed, and visualised in big data systems. In order to provide services with low latency for end users, often utilisation of ML techniques has to be optimized. Also, software/service developers have to understand, how to develop and deploy ML models in edge computing environments. Therefore, architecture design of big data systems to edge computing environments may be challenging.Findings: The contribution of this paper is reference architecture (RA) design of a big data system utilising ML techniques in edge computing environments. An earlier version of the RA has been extended based on 16 realised implementation architectures, which have been developed to edge/distributed computing environments. Also, deployment of architectural elements in different environments is described. Finally, a system view is provided of the software engineering aspects of ML model development and deployment.Conclusions: The presented RA may facilitate concrete architecture design of use cases in edge computing environments. The value of RAs is reduction of development and maintenance costs of systems, reduction of risks, and facilitation of communication between different stakeholders.
- 6 April 2020
- Published by Springer Nature in Journal of Big Data
- Vol. 7 (1) , 1-29
Open AccessExtending reference architecture of big data systems towards machine learning in edge computing environments
Background: Augmented reality, computer vision and other (e.g. network functions, Internet-of-Things (IoT)) use cases can be realised in edge computing environments with machine learning (ML) techniques. For realisation of the use cases, it has to be understood how data is collected, stored, processed, analysed, and visualised in big data systems. In order to provide services with low latency for end users, often utilisation of ML techniques has to be optimized. Also, software/service developers have to understand, how to develop and deploy ML models in edge computing environments. Therefore, architecture design of big data systems to edge computing environments may be challenging.Findings: The contribution of this paper is reference architecture (RA) design of a big data system utilising ML techniques in edge computing environments. An earlier version of the RA has been extended based on 16 realised implementation architectures, which have been developed to edge/distributed computing environments. Also, deployment of architectural elements in different environments is described. Finally, a system view is provided of the software engineering aspects of ML model development and deployment.Conclusions: The presented RA may facilitate concrete architecture design of use cases in edge computing environments. The value of RAs is reduction of development and maintenance costs of systems, reduction of risks, and facilitation of communication between different stakeholders.
- Open Access
- 9 July 2019
- Published by Springer Nature in Journal of Cloud Computing
- Vol. 8 (1) , 9
Online architecture for predicting live video transcoding resources
- 9 July 2019
- Published by Springer Nature in Journal of Cloud Computing
- Vol. 8 (1) , 9
Open AccessOnline architecture for predicting live video transcoding resources
- Open Access
- 23 March 2017
- Published by Springer Nature in Journal of Big Data
- Vol. 4 (1) , 6
Quality management architecture for social media data
- 23 March 2017
- Published by Springer Nature in Journal of Big Data
- Vol. 4 (1) , 6
Open AccessQuality management architecture for social media data
- Open Access
- 8 April 2016
- Published by Springer Nature in Journal of Big Data
- Vol. 3 (1) , 1
Feasibility analysis of AsterixDB and Spark streaming with Cassandra for stream-based processing
- 8 April 2016
- Published by Springer Nature in Journal of Big Data
- Vol. 3 (1) , 1
Open AccessFeasibility analysis of AsterixDB and Spark streaming with Cassandra for stream-based processing
- Open Access
- 21 June 2014
- Published by Springer Nature in Service Oriented Computing and Applications
- Vol. 9 (2) , 193-209
Mechanism and architecture for the migration of service implementation during traffic peaks
- 21 June 2014
- Published by Springer Nature in Service Oriented Computing and Applications
- Vol. 9 (2) , 193-209
Open AccessMechanism and architecture for the migration of service implementation during traffic peaks
- 1 July 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21671753,p. 1-5
Ambient Networks Integrated Prototype Design and Implementation
This paper presents the design and realization process of the ambient networks integrated prototype. The approach of developing a prototype that integrates various components developed by different teams working in parallel is a cornerstone of the project's validation strategy. We offer other projects a case study that helps speed up their design and development process for complex research prototypes. We present the top-to-bottom approach starting from usage scenarios and leading to the list of software modules to be developed. The structure of the prototype is explained, with focus on registration, lookup, naming and security framework. By this we provide an insight into the internal structure of a future global fixed-mobile converged (FMC) network.
- 1 July 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21671753,p. 1-5
Ambient Networks Integrated Prototype Design and Implementation
This paper presents the design and realization process of the ambient networks integrated prototype. The approach of developing a prototype that integrates various components developed by different teams working in parallel is a cornerstone of the project's validation strategy. We offer other projects a case study that helps speed up their design and development process for complex research prototypes. We present the top-to-bottom approach starting from usage scenarios and leading to the list of software modules to be developed. The structure of the prototype is explained, with focus on registration, lookup, naming and security framework. By this we provide an insight into the internal structure of a future global fixed-mobile converged (FMC) network.