Risto Ritala
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Risto Ritala has a total of 99 co-authors. Here are the top co-authors by number of shared publications:
- Mikko Lauri
University of Hamburg
8 shared publications - Aino Ropponen
Tampere University of Technology, Department of Automation Science and Engineering, P.O. Box 692, FI-33101 Tampere, Finland
7 shared publications - Lari Melander
Automation Technology and Mechanical Engineering, Tampere University, Tampere, Finland
4 shared publications Miika Rajala
Department of Automation Science and Engineering, Tampere University of Technology, Tampere, Finland
4 shared publications- Jukka-Pekka Raunio
Tampere University of Technology, FI-33101 Tampere , Finland
3 shared publications Petteri Pulkkinen
3 shared publications
Latest Publications
- Open Access
- 8 November 2021
- Published by Walter de Gruyter GmbH in Open Engineering
- Vol. 11 (1) , 1048-1058
Prediction of future paths of mobile objects using path library
In situational awareness, the ability to make predictions about the near future situation in the area under surveillance is often as essential as being aware of the current situation. We introduce a privacy-preser-ving instance-based prediction method, where a path library is collected by learning earlier paths of mobile objects in the area of surveillance. The input to the pre-diction is the most recent coordinates of the objects in the scene. Based on similarity to short segments of currently tracked paths, a relative weight is associated with each path in the library. Future paths are predicted by computing the weighted average of the library paths. We demonstrate the operation of a situational awareness system where privacy-preserving data are extracted from an inexpensive computer vision which consists of a camera-equipped Raspberry PI -based edge device. The system runs a deep neural network-based object detection algorithm on the camera feed and stores the coordinates, object class labels, and timestamps of the detected objects. We used probabilistic reasoning based on joint probabilistic data association, Hungarian algorithm, and Kalman filter to infer which detections from different time instances came from the same object.
- 8 November 2021
- Published by Walter de Gruyter GmbH in Open Engineering
- Vol. 11 (1) , 1048-1058
Open AccessPrediction of future paths of mobile objects using path library
In situational awareness, the ability to make predictions about the near future situation in the area under surveillance is often as essential as being aware of the current situation. We introduce a privacy-preser-ving instance-based prediction method, where a path library is collected by learning earlier paths of mobile objects in the area of surveillance. The input to the pre-diction is the most recent coordinates of the objects in the scene. Based on similarity to short segments of currently tracked paths, a relative weight is associated with each path in the library. Future paths are predicted by computing the weighted average of the library paths. We demonstrate the operation of a situational awareness system where privacy-preserving data are extracted from an inexpensive computer vision which consists of a camera-equipped Raspberry PI -based edge device. The system runs a deep neural network-based object detection algorithm on the camera feed and stores the coordinates, object class labels, and timestamps of the detected objects. We used probabilistic reasoning based on joint probabilistic data association, Hungarian algorithm, and Kalman filter to infer which detections from different time instances came from the same object.
- Open Access
- 4 July 2020
- Published by Springer Nature in European Journal of Forest Research
- Vol. 139 (6) , 1029-1043
Separating the impact of work environment and machine operation on harvester performance
In mechanized logging operations, interactions between the forest machines and their operators, forest resources and environmental conditions are multifold and not easily detected. However, increased computational resources and sensing capabilities of the forest machines together with extensive forest inventory data enable modeling of such relationships, leading eventually to better planning of the operations, better assistance for the forest machine operators, and increased efficiency of timber harvesting. In this study, both forest machine fieldbus data and forest inventory data were acquired extensively. The forest inventory data, acquired nationwide, was clustered to categorize general tree and soil types in Finland. The found forest categories were applied when the harvester fieldbus data, collected from the forest operations in the North Karelia region with two similar harvesters, was analyzed. When the performance of the machine and the operator, namely the fuel consumption and log production, is studied individually for each forest cluster, the impact of working environment no longer masks the causes based on the machine or the operator, thus making the observations from separate forest locations comparable. The study observed statistically significant differences in fuel consumption between the most general tree and soil clusters as well as between the harvester-operator units. The modeling approach applied, based on multivariate linear regression, finds such reasons for the differences that have clear interpretation from machine setup or operator working style perspective, and thus offers a feasible method for assisting the operators in improving their working practices and thus the overall performance specifically at forest of given type.
- 4 July 2020
- Published by Springer Nature in European Journal of Forest Research
- Vol. 139 (6) , 1029-1043
Open AccessSeparating the impact of work environment and machine operation on harvester performance
In mechanized logging operations, interactions between the forest machines and their operators, forest resources and environmental conditions are multifold and not easily detected. However, increased computational resources and sensing capabilities of the forest machines together with extensive forest inventory data enable modeling of such relationships, leading eventually to better planning of the operations, better assistance for the forest machine operators, and increased efficiency of timber harvesting. In this study, both forest machine fieldbus data and forest inventory data were acquired extensively. The forest inventory data, acquired nationwide, was clustered to categorize general tree and soil types in Finland. The found forest categories were applied when the harvester fieldbus data, collected from the forest operations in the North Karelia region with two similar harvesters, was analyzed. When the performance of the machine and the operator, namely the fuel consumption and log production, is studied individually for each forest cluster, the impact of working environment no longer masks the causes based on the machine or the operator, thus making the observations from separate forest locations comparable. The study observed statistically significant differences in fuel consumption between the most general tree and soil clusters as well as between the harvester-operator units. The modeling approach applied, based on multivariate linear regression, finds such reasons for the differences that have clear interpretation from machine setup or operator working style perspective, and thus offers a feasible method for assisting the operators in improving their working practices and thus the overall performance specifically at forest of given type.
- Open Access
- 21 October 2019
- Published by Springer Nature in European Journal of Forest Research
- Vol. 139 (2) , 213-227
Fusion of open forest data and machine fieldbus data for performance analysis of forest machines
Forest resource data is important in targeting the forestry operations, and it is in the hearth of the precision forestry concept. The forest resource data can be produced with many techniques, and the number of existing forest data sources has increased during the years. In addition to the forest resource data, other data describing the circumstances of the forest site, such as trafficability and weather conditions, are available. In Finland, a forest data platform gathers the data sources under a single service for easier implementation of the precision forestry applications. This data is useful in operations planning, but it also describes the conditions that prevail when the forest machine arrives to the forest site. This study proposes data fusion between fieldbus time series of the forest machine and the forest data. The fused dataset enables explorative statistical analysis for examining the relationship between the machine performance and the forest attributes and provides data for building predictive models between the two. The presented methods are applied into a dataset generated from a field test data. The results show that some fieldbus time series features are predictable from forest attributes with $$R^{2}$$ value over 0.80, and clustering methods help in interpreting the machine behavior in different environments. In addition, an idea for generating a new forest data source to the forest data platform based on the fusion is discussed.- 21 October 2019
- Published by Springer Nature in European Journal of Forest Research
- Vol. 139 (2) , 213-227
Open AccessFusion of open forest data and machine fieldbus data for performance analysis of forest machines
Forest resource data is important in targeting the forestry operations, and it is in the hearth of the precision forestry concept. The forest resource data can be produced with many techniques, and the number of existing forest data sources has increased during the years. In addition to the forest resource data, other data describing the circumstances of the forest site, such as trafficability and weather conditions, are available. In Finland, a forest data platform gathers the data sources under a single service for easier implementation of the precision forestry applications. This data is useful in operations planning, but it also describes the conditions that prevail when the forest machine arrives to the forest site. This study proposes data fusion between fieldbus time series of the forest machine and the forest data. The fused dataset enables explorative statistical analysis for examining the relationship between the machine performance and the forest attributes and provides data for building predictive models between the two. The presented methods are applied into a dataset generated from a field test data. The results show that some fieldbus time series features are predictable from forest attributes with $$R^{2}$$ value over 0.80, and clustering methods help in interpreting the machine behavior in different environments. In addition, an idea for generating a new forest data source to the forest data platform based on the fusion is discussed. - Open Access
- 1 January 2019
- Published by Finnish Society of Forest Science in Silva Fennica
- Vol. 53 (2)
Classifying soil stoniness based on the excavator boom vibration data in mounding operations
The stoniness index of forest soil describes the stone content in the upper soil layer at depths of 20–30 centimeters. This index is not available in any existing map databases, and traditional measurements for the stoniness of the soil have always necessitated laborious soil-penetration methods. Knowledge of the stone content of a forest site could be of use in a variety of forestry operations. This paper presents a novel approach to obtaining automatic measurements of soil stoniness during an excavator-based mounding operation. The excavator was equipped with only a low-cost inertial measurement unit and a satellite navigation receiver. Using the data from these sensors and manually conducted soil stoniness measurements, supervised machine learning methods were utilized to build a model that is capable of predicting the stoniness class of a given mounding location. This study compares different classifiers and feature selection methods to find the most promising solution for this learning problem. The discussion includes a proposition for a meaningful measurement resolution of the soil’s stoniness, and a practical method for evaluating the variability of the stone content of the soil. The results indicate that it is possible to predict the soil stoniness class with 70% accuracy using only the inertial and location measurements.
- 1 January 2019
- Published by Finnish Society of Forest Science in Silva Fennica
- Vol. 53 (2)
Open AccessClassifying soil stoniness based on the excavator boom vibration data in mounding operations
The stoniness index of forest soil describes the stone content in the upper soil layer at depths of 20–30 centimeters. This index is not available in any existing map databases, and traditional measurements for the stoniness of the soil have always necessitated laborious soil-penetration methods. Knowledge of the stone content of a forest site could be of use in a variety of forestry operations. This paper presents a novel approach to obtaining automatic measurements of soil stoniness during an excavator-based mounding operation. The excavator was equipped with only a low-cost inertial measurement unit and a satellite navigation receiver. Using the data from these sensors and manually conducted soil stoniness measurements, supervised machine learning methods were utilized to build a model that is capable of predicting the stoniness class of a given mounding location. This study compares different classifiers and feature selection methods to find the most promising solution for this learning problem. The discussion includes a proposition for a meaningful measurement resolution of the soil’s stoniness, and a practical method for evaluating the variability of the stone content of the soil. The results indicate that it is possible to predict the soil stoniness class with 70% accuracy using only the inertial and location measurements.
- 1 December 2018
- Published by Elsevier in Journal of Process Control
- Vol. 72, 74-90
Active scanner control on paper machines
- 1 December 2018
- Published by Elsevier in Journal of Process Control
- Vol. 72, 74-90
Active scanner control on paper machines
- 1 May 2018
- Published by Walter de Gruyter GmbH in Nordic Pulp & Paper Research Journal
- Vol. 33 (1) , 133-141
Online quality evaluation of tissue paper structure on new generation tissue machines
At present, the tissue paper manufacturing is mostly based on the dry crepe technology. During the last decade, the manufacturers have introduced new tissue machines concepts that increase the softness, bulk, and absorption capacity. Such machines produce a strong regular three-dimensional (3D) structure to the sheet before the Yankee cylinder. At present, the quality of the 3D structure is not evaluated, or it is evaluated only subjectively at the mill. This is mostly because of the difficulties to separate reliably the regular 3D pattern from other variations. This paper introduces a frequency analysis based method which separates the surface profile variances in tissue paper to the creping, to the regular 3D pattern and to the residual variation. The 3D surface profiles and their variances were determined online with the photometric stereo method. We show that the introduced analysis method evaluates the variance portions reliably and the results are consistent with the visual perception of the 3D surfaces. In one particular product, the regular 3D pattern explains 74% of total surface variance; the creping explains 10% and residual variations 16%. Furthermore, the creping and residual variances are quite stable over time whereas the variance of the regular 3D pattern fluctuates significantly.
- 1 May 2018
- Published by Walter de Gruyter GmbH in Nordic Pulp & Paper Research Journal
- Vol. 33 (1) , 133-141
Online quality evaluation of tissue paper structure on new generation tissue machines
At present, the tissue paper manufacturing is mostly based on the dry crepe technology. During the last decade, the manufacturers have introduced new tissue machines concepts that increase the softness, bulk, and absorption capacity. Such machines produce a strong regular three-dimensional (3D) structure to the sheet before the Yankee cylinder. At present, the quality of the 3D structure is not evaluated, or it is evaluated only subjectively at the mill. This is mostly because of the difficulties to separate reliably the regular 3D pattern from other variations. This paper introduces a frequency analysis based method which separates the surface profile variances in tissue paper to the creping, to the regular 3D pattern and to the residual variation. The 3D surface profiles and their variances were determined online with the photometric stereo method. We show that the introduced analysis method evaluates the variance portions reliably and the results are consistent with the visual perception of the 3D surfaces. In one particular product, the regular 3D pattern explains 74% of total surface variance; the creping explains 10% and residual variations 16%. Furthermore, the creping and residual variances are quite stable over time whereas the variance of the regular 3D pattern fluctuates significantly.
- 18 April 2018
- Published by Taylor & Francis in International Journal of Forest Engineering
- Vol. 29 (2) , 63-73
Time-of-flight imaging for assessing soil deformations and improving forestry vehicle tracking accuracy
Automatically collected forest environment data is essential when developing more accurate and efficient forestry operations. Reliable position-based data enables efficient wood procurement operations and helps to avoid damage to the forest floor. A modern forestry vehicle with extensive sensing capabilities could measure environmental parameters, such as soil type, topography or weather conditions, while carrying out other wood procurement tasks. Furthermore, methods to improve positioning accuracy are also called for when the positioning is based on global satellite navigation systems (GNSS), whose signals are often blocked by the forest canopy. In this article, data is collected automatically with two of Microsoft’s Kinect v2 time-of-flight sensors during field tests in a forest environment in Southern Finland. The aim of the article is to propose methods which will improve positioning accuracy by enabling the movement of the forwarder to be detected and also to provide reliable measurements of any soil deformations caused by the vehicle in real time. The results show that Kinect v2 technology enables tracking of the vehicle’s movements over short distances with sub-meter accuracy, thus supporting the GNSS positioning during the short periods of unavailable satellite visibility. Kinect v2 technology has also been shown to be able to measure the depth of ruts as accurately as conventional manual measurements.
- 18 April 2018
- Published by Taylor & Francis in International Journal of Forest Engineering
- Vol. 29 (2) , 63-73
Time-of-flight imaging for assessing soil deformations and improving forestry vehicle tracking accuracy
Automatically collected forest environment data is essential when developing more accurate and efficient forestry operations. Reliable position-based data enables efficient wood procurement operations and helps to avoid damage to the forest floor. A modern forestry vehicle with extensive sensing capabilities could measure environmental parameters, such as soil type, topography or weather conditions, while carrying out other wood procurement tasks. Furthermore, methods to improve positioning accuracy are also called for when the positioning is based on global satellite navigation systems (GNSS), whose signals are often blocked by the forest canopy. In this article, data is collected automatically with two of Microsoft’s Kinect v2 time-of-flight sensors during field tests in a forest environment in Southern Finland. The aim of the article is to propose methods which will improve positioning accuracy by enabling the movement of the forwarder to be detected and also to provide reliable measurements of any soil deformations caused by the vehicle in real time. The results show that Kinect v2 technology enables tracking of the vehicle’s movements over short distances with sub-meter accuracy, thus supporting the GNSS positioning during the short periods of unavailable satellite visibility. Kinect v2 technology has also been shown to be able to measure the depth of ruts as accurately as conventional manual measurements.
- 1 March 2018
- Published by Walter de Gruyter GmbH in Nordic Pulp & Paper Research Journal
- Vol. 33 (01)
Online quality evaluation of tissue paper structure on new generation tissue machines
Människor för vem casinospel till slut blir ett allvarligt problem, och denna artikel (alt. checklista) har sammanställts för dig som misstänker att du eventuellt lider av det som vanligtvis kallas för problematiskt spel spelberoende
- 1 March 2018
- Published by Walter de Gruyter GmbH in Nordic Pulp & Paper Research Journal
- Vol. 33 (01)
Online quality evaluation of tissue paper structure on new generation tissue machines
Människor för vem casinospel till slut blir ett allvarligt problem, och denna artikel (alt. checklista) har sammanställts för dig som misstänker att du eventuellt lider av det som vanligtvis kallas för problematiskt spel spelberoende
- 7 February 2018
- Published by Springer Nature in Telecommunication Systems
- Vol. 68 (4) , 745-759
Topology estimation method for telecommunication networks
- 7 February 2018
- Published by Springer Nature in Telecommunication Systems
- Vol. 68 (4) , 745-759
Topology estimation method for telecommunication networks
- 28 September 2016
- Published by Springer Nature in Annals of Mathematics and Artificial Intelligence
- Vol. 79 (4) , 337-370
Meeting a deadline: shortest paths on stochastic directed acyclic graphs with information gathering
- 28 September 2016
- Published by Springer Nature in Annals of Mathematics and Artificial Intelligence
- Vol. 79 (4) , 337-370
Meeting a deadline: shortest paths on stochastic directed acyclic graphs with information gathering