Dalarna University's logo and link to the university's website

du.sePublications
Change search
Link to record
Permanent link

Direct link
Publications (10 of 25) Show all publications
Saeed, N., Nyberg, R. G., Alam, M., Dougherty, M., Jomaa, D. & Rebreyend, P. (2021). Classification of the Acoustics of Loose Gravel. Sensors, 21(14), Article ID 4944.
Open this publication in new window or tab >>Classification of the Acoustics of Loose Gravel
Show others...
2021 (English)In: Sensors, E-ISSN 1424-8220, Vol. 21, no 14, article id 4944Article in journal (Refereed) Published
Abstract [en]

Road condition evaluation is a critical part of gravel road maintenance. One of the assessed parameters is the amount of loose gravel, as this determines the driving quality and safety. Loose gravel can cause tires to slip and the driver to lose control. An expert assesses the road conditions subjectively by looking at images and notes. This method is labor-intensive and subject to error in judgment; therefore, its reliability is questionable. Road management agencies look for automated and objective measurement systems. In this study, acoustic data on gravel hitting the bottom of a car was used. The connection between the acoustics and the condition of loose gravel on gravel roads was assessed. Traditional supervised learning algorithms and convolution neural network (CNN) were applied, and their performances are compared for the classification of loose gravel acoustics. The advantage of using a pre-trained CNN is that it selects relevant features for training. In addition, pre-trained networks offer the advantage of not requiring days of training or colossal training data. In supervised learning, the accuracy of the ensemble bagged tree algorithm for gravel and non-gravel sound classification was found to be 97.5%, whereas, in the case of deep learning, pre-trained network GoogLeNet accuracy was 97.91% for classifying spectrogram images of the gravel sounds.

Place, publisher, year, edition, pages
Switzerland: MDPI, 2021
Keywords
gravel roads; loose gravel; ensemble bagged trees; sound analysis; road maintenance; GoogLeNet
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:du-37811 (URN)10.3390/s21144944 (DOI)000677020000001 ()34300684 (PubMedID)2-s2.0-85110519300 (Scopus ID)
Available from: 2021-08-02 Created: 2021-08-02 Last updated: 2024-01-30Bibliographically approved
Saeed, N., Dougherty, M., Nyberg, R. G., Rebreyend, P. & Jomaa, D. (2020). A Review of Intelligent Methods for Unpaved Roads Condition Assessment. In: 2020 15th IEEE Conference on Industrial Electronics and Applications (ICIEA): . Paper presented at 2020 15th IEEE Conference on Industrial Electronics and Applications (ICIEA) (pp. 79-84).
Open this publication in new window or tab >>A Review of Intelligent Methods for Unpaved Roads Condition Assessment
Show others...
2020 (English)In: 2020 15th IEEE Conference on Industrial Electronics and Applications (ICIEA), 2020, p. 79-84Conference paper, Published paper (Refereed)
Abstract [en]

Conventional road condition evaluation is an expensive and time-consuming task. Therefore data collection from indirect economical methods is desired by road monitoring agencies. Recently intelligent road condition monitoring has become popular. More studies have focused on automated paved road condition monitoring, and minimal research is available to date on automating gravel road condition assessment. Road roughness information gives an overall picture of the road but does not help in identifying the type of defect; therefore, it cannot be helpful in the more specific road maintenance plan. Road monitoring can be automated using data from conventional sensors, vehicles' onboard devices, and audio and video streams from cost-effective devices. This paper reviews classical and intelligent methods for road condition evaluation in general and, more specifically, reviews studies proposing automated solutions targeting gravel or unpaved roads.

Keywords
unpaved roads, machine learning, road condition monitoring, data quality, sensors
National Category
Computer and Information Sciences
Research subject
Research Profiles 2009-2020, Complex Systems – Microdata Analysis
Identifiers
urn:nbn:se:du-35459 (URN)10.1109/ICIEA48937.2020.9248317 (DOI)000646627000014 ()2-s2.0-85097521958 (Scopus ID)
Conference
2020 15th IEEE Conference on Industrial Electronics and Applications (ICIEA)
Available from: 2020-11-23 Created: 2020-11-23 Last updated: 2024-01-30Bibliographically approved
Saeed, N., Alam, M., Nyberg, R. G., Dougherty, M., Rebreyend, P. & Jomaa, D. (2020). Comparison of Pattern Recognition Techniques for Classification of the Acoustics of Loose Gravel. In: 2020 7th International Conference on Soft Computing and Machine Intelligence, ISCMI 2020: . Paper presented at 7th International Conference on Soft Computing and Machine Intelligence, ISCMI 2020; Virtual, Stockholm; Sweden; 14 November 2020 through 15 November 2020 (pp. 237-243). , Article ID 9311569.
Open this publication in new window or tab >>Comparison of Pattern Recognition Techniques for Classification of the Acoustics of Loose Gravel
Show others...
2020 (English)In: 2020 7th International Conference on Soft Computing and Machine Intelligence, ISCMI 2020, 2020, p. 237-243, article id 9311569Conference paper, Published paper (Refereed)
Abstract [en]

Road condition evaluation is a critical part of gravel road maintenance. One of the parameters that are assessed is loose Gravel. An expert does this evaluation by subjectively looking at images taken and written text for deciding on the road condition. This method is labor-intensive and subjected to an error of judgment; therefore, it is not reliable. Road management agencies are looking for more efficient and automated objective measurement methods. In this study, acoustic data of gravel hitting the bottom of the car is used, and the relation between these acoustics and the condition of loose gravel on gravel roads is seen. A novel acoustic classification method based on Ensemble bagged tree (EBT) algorithm is proposed in this study for the classification of loose gravel sounds. The accuracy of the EBT algorithm for Gravel and Non-gravel sound classification is found to be 97.5. The detection of the negative classes, i.e., non-gravel detection, is preeminent, which is considerably higher than Boosted Trees, RUSBoosted Tree, Support vector machines (SVM), and decision trees.

Keywords
Supervised learning, Sound analysis, Fast Fourier Transform, FFT, Gravel roads, Pattern recognition
National Category
Engineering and Technology Computer Systems
Research subject
Research Profiles 2009-2020, Complex Systems – Microdata Analysis
Identifiers
urn:nbn:se:du-35796 (URN)10.1109/ISCMI51676.2020.9311569 (DOI)000750622300045 ()2-s2.0-85100349048 (Scopus ID)9781728175591 (ISBN)
Conference
7th International Conference on Soft Computing and Machine Intelligence, ISCMI 2020; Virtual, Stockholm; Sweden; 14 November 2020 through 15 November 2020
Projects
Automated gravel road condition assessment
Available from: 2021-01-14 Created: 2021-01-14 Last updated: 2022-05-12Bibliographically approved
Meng, X., Carling, K., Håkansson, J. & Rebreyend, P. (2018). How do administrative borders affect accessibility to hospitals? The case of Sweden. International Journal of Health Planning and Management, 33(3)
Open this publication in new window or tab >>How do administrative borders affect accessibility to hospitals? The case of Sweden
2018 (English)In: International Journal of Health Planning and Management, ISSN 0749-6753, E-ISSN 1099-1751, Vol. 33, no 3Article in journal (Refereed) Published
Abstract [en]

An administrative border might hinder the optimal allocation of a given set of resources by restricting the flow of goods, services, and people. In this paper, we address the question: Do administrative borders lead to poor accessibility to public service? In answering the question, we have examined the case of Sweden and its regional administrative borders and hospital accessibility. We have used detailed data on the Swedish road network, its hospitals, and its geo-coded population. We have assessed the population's spatial accessibility to Swedish hospitals by computing the inhabitants' distance to the nearest hospital. We have also elaborated several scenarios ranging from strongly confining regional borders to no confinements of borders and recomputed the accessibility. Our findings imply that administrative borders are only marginally worsening the accessibility.

Keywords
administrative barriers, optimal location, population dynamics, public service, travel time
National Category
Probability Theory and Statistics
Research subject
Research Profiles 2009-2020, Complex Systems – Microdata Analysis
Identifiers
urn:nbn:se:du-27519 (URN)10.1002/hpm.2520 (DOI)000442224700014 ()29667273 (PubMedID)2-s2.0-85045844366 (Scopus ID)
Available from: 2018-04-24 Created: 2018-04-24 Last updated: 2021-11-12Bibliographically approved
Lemarchand, L., Massé, D., Rebreyend, P. & Håkansson, J. (2018). Multiobjective Optimization for Multimode Transportation Problems. Advances in Operations Research, Article ID 8720643.
Open this publication in new window or tab >>Multiobjective Optimization for Multimode Transportation Problems
2018 (English)In: Advances in Operations Research, ISSN 1687-9147, E-ISSN 1687-9155, article id 8720643Article in journal (Refereed) Published
Abstract [en]

We propose modelling for a facilities localization problem in the context of multimode transportation. The applicative goal is to locate service facilities such as schools or hospitals while optimizing the different transportation modes to these facilities. We formalize the School Problem and solve it first exactly using an adapted -constraint multiobjective method. Because of the size of the instances considered, we have also explored the use of heuristic methods based on evolutionary multiobjective frameworks, namely, NSGA2 and a modified version of PAES. Those methods are mixed with an original local search technique to provide better results. Numerical comparisons of solutions sets quality are made using the hypervolume metric. Based on the results for test-cases that can be solved exactly, efficient implementation for PAES and NSGA2 allows execution times comparison for large instances. Results show good performances for the heuristic approaches as compared to the exact algorithm for small test-cases. Approximate methods present a scalable behavior on largest problem instances. A master/slave parallelization scheme also helps to reduce execution times significantly for the modified PAES approach.

National Category
Computer Systems Computer Systems
Research subject
Research Profiles 2009-2020, Complex Systems – Microdata Analysis
Identifiers
urn:nbn:se:du-27779 (URN)10.1155/2018/8720643 (DOI)000446981000001 ()2-s2.0-85049169081 (Scopus ID)
Note

Open Access APC beslut 30/2017

Available from: 2018-06-08 Created: 2018-06-08 Last updated: 2021-11-12Bibliographically approved
Meng, X. & Rebreyend, P. (2016). On transforming a road network database to a graph for localization purpose. International Journal of Web Services Research, 13(2), 46-55
Open this publication in new window or tab >>On transforming a road network database to a graph for localization purpose
2016 (English)In: International Journal of Web Services Research, ISSN 1545-7362, E-ISSN 1546-5004, Vol. 13, no 2, p. 46-55Article in journal (Refereed) Published
Abstract [en]

The problems of finding best facility locations require complete and accurate road networks with the corresponding population data in a specific area. However the data obtained from road network databases usually do not fit in this usage. In this paper we propose a procedure of converting the road network database to a road graph which could be used for localization problems. Several challenging problems exist in the transformation process which are commonly met also in other data bases. The procedure of dealing with those challenges are proposed. The data come from the National road data base in Sweden. The graph derived is cleaned, and reduced to a suitable level for localization problems. The residential points are also processed in ordered to match the graph. The reduction of the graph is done maintaining the accuracy of distance measures in the network.

Keywords
road network, graph, population, GIS
National Category
Economic Geography
Research subject
Research Profiles 2009-2020, Complex Systems – Microdata Analysis
Identifiers
urn:nbn:se:du-17361 (URN)10.4018/IJWSR.2016040103 (DOI)000384810100004 ()2-s2.0-84969766630 (Scopus ID)
Available from: 2015-05-07 Created: 2015-05-07 Last updated: 2021-11-12Bibliographically approved
Rebreyend, P., Lemarchand, L. & Euler, R. (2015). A computational comparison of different algorithms for very large p-median problems. In: Gabriela Ochoa, Francisco Chicano (Ed.), Evolutionary Computation in Combinatorial Optimization: 15th European Conference, EvoCOP 2015, Copenhagen, Denmark, April 8-10, 2015, Proceedings. Paper presented at 15th European Conference, EvoCOP 2015, Copenhagen, Denmark, April 8-10, 2015 (pp. 13-24). Springer, 9026
Open this publication in new window or tab >>A computational comparison of different algorithms for very large p-median problems
2015 (English)In: Evolutionary Computation in Combinatorial Optimization: 15th European Conference, EvoCOP 2015, Copenhagen, Denmark, April 8-10, 2015, Proceedings / [ed] Gabriela Ochoa, Francisco Chicano, Springer, 2015, Vol. 9026, p. 13-24Conference paper, Published paper (Refereed)
Abstract [en]

In this paper, we propose a new method for solving large scale p-median problem instances based on real data. We compare different approaches in terms of runtime, memory footprint and quality of solutions obtained. In order to test the different methods on real data, we introduce a new benchmark for the p-median problem based on real Swedish data. Because of the size of the problem addressed, up to 1938 candidate nodes, a number of algorithms, both exact and heuristic, are considered. We also propose an improved hybrid version of a genetic algorithm called impGA. Experiments show that impGA behaves as well as other methods for the standard set of medium-size problems taken from Beasley’s benchmark, but produces comparatively good results in terms of quality, runtime and memory footprint on our specific benchmark based on real Swedish data.

Place, publisher, year, edition, pages
Springer, 2015
Series
Lecture Notes in Computer Science, ISSN 0302-9743 ; 9026
National Category
Computer Sciences
Research subject
Research Profiles 2009-2020, Complex Systems – Microdata Analysis
Identifiers
urn:nbn:se:du-19289 (URN)10.1007/978-3-319-16468-7_2 (DOI)000361701400002 ()2-s2.0-84925061348 (Scopus ID)978-3-319-16468-7 (ISBN)978-3-319-16467-0 (ISBN)
Conference
15th European Conference, EvoCOP 2015, Copenhagen, Denmark, April 8-10, 2015
Available from: 2015-09-11 Created: 2015-09-11 Last updated: 2021-11-12Bibliographically approved
Carling, K., Han, M., Håkansson, J. & Rebreyend, P. (2015). Distance measure and the p-median problem in rural areas. Annals of Operations Research, 226(1), 89-99
Open this publication in new window or tab >>Distance measure and the p-median problem in rural areas
2015 (English)In: Annals of Operations Research, ISSN 0254-5330, E-ISSN 1572-9338, Vol. 226, no 1, p. 89-99Article in journal (Refereed) Published
Abstract [en]

The p-median model is used to locate P facilities to serve a geographically distributed population. Conventionally, it is assumed that the population patronize the nearest facility and that the distance between the resident and the facility may be measured by the Euclidean distance. Carling, Han, and Håkansson (2012) compared two network distances with the Euclidean in a rural region with a sparse, heterogeneous network and a non-symmetric distribution of the population. For a coarse network and P small, they found, in contrast to the literature, the Euclidean distance to be problematic. In this paper we extend their work by use of a refined network and study systematically the case when P is of varying size (1-100 facilities). We find that the network distance give as good a solution as the travel-time network. The Euclidean distance gives solutions some 4-10 per cent worse than the network distances, and the solutions tend to deteriorate with increasing P. Our conclusions extend to intra-urban location problems.

Place, publisher, year, edition, pages
Springer, 2015
Keywords
dense network, location model, optimal location, simulated annealing, travel-time, urban areas
National Category
Transport Systems and Logistics
Research subject
Complex Systems – Microdata Analysis, General Microdata Analysis - methods; Complex Systems – Microdata Analysis, General Microdata Analysis - transports
Identifiers
urn:nbn:se:du-14682 (URN)10.1007/s10479-014-1677-4 (DOI)000349852400005 ()2-s2.0-84922967961 (Scopus ID)
Available from: 2014-07-18 Created: 2014-07-18 Last updated: 2021-11-12Bibliographically approved
Zhao, X., Rebreyend, P. & Håkansson, J. (2015). Does road network density matter in optimally locating facilities?.
Open this publication in new window or tab >>Does road network density matter in optimally locating facilities?
2015 (English)Report (Other (popular science, discussion, etc.))
Abstract [en]

Optimal location on the transport infrastructure is the preferable requirement for many decision making processes. Most studies have focused on evaluating performances of optimally locate p facilities by minimizing their distances to a geographically distributed demand (n) when p and n vary. The optimal locations are also sensitive to geographical context such as road network, especially when they are asymmetrically distributed in the plane. The influence of alternating road network density is however not a very well-studied problem especially when it is applied in a real world context. This paper aims to investigate how the density level of the road network affects finding optimal location by solving the specific case of p-median location problem. A denser network is found needed when a higher number of facilities are to locate. The best solution will not always be obtained in the most detailed network but in a middle density level. The solutions do not further improve or improve insignificantly as the density exceeds 12,000 nodes, some solutions even deteriorate. The hierarchy of the different densities of network can be used according to location and transportation purposes and increase the efficiency of heuristic methods. The method in this study can be applied to other location-allocation problem in transportation analysis where the road network density can be differentiated. 

Publisher
p. 14
Series
Working papers in transport, tourism, information technology and microdata analysis, ISSN 1650-5581 ; 2015:10
Keywords
Road network; Density; p – median model; CPLEX; Heuristics
National Category
Computer and Information Sciences Human Geography
Research subject
Research Profiles 2009-2020, Complex Systems – Microdata Analysis
Identifiers
urn:nbn:se:du-19079 (URN)
Available from: 2015-08-21 Created: 2015-08-21 Last updated: 2021-11-12Bibliographically approved
Zhao, X., Rebreyend, P. & Håkansson, J. (2015). How does the complexity of a road network affect optimal facility locations?. Borlänge: Högskolan Dalarna
Open this publication in new window or tab >>How does the complexity of a road network affect optimal facility locations?
2015 (English)Report (Other academic)
Abstract [en]

The road network is a necessary component in transportation. It facilitiesspatial movements of people and goods, and it also influences the optimal locations of facilities that usually serve as destinations of the movements. To fulfill the transportation needs and to adapt to the facility development, the road network is often organized hierarchically and asymmetrically with various road levels and spatial structures. The complexity of the road network increases along with the increase of road levels and spatial structures. However, location models locate facilities on a given road network, usually the most complex one, and the influence from the complexity of road network in finding optimal locations is not well-studied. This paper aims to investigate how the complexity of a road network affects the optimal facility locations by applying the widely-applied p-median model. The main result indicates that an increase in road network complexity, up to a certain level, can obviously improve the solution, and the complexity beyond that level does not always lead to better solutions. Furthermore, the result is not sensitive to the choice of algorithms. In a specific case study, a detailed sensitivity analysis of algorithm and facility number further provides insight into computation complexity and location problems from intra-urban to inter-urban.

Place, publisher, year, edition, pages
Borlänge: Högskolan Dalarna, 2015. p. 19
Series
Working papers in transport, tourism, information technology and microdata analysis, ISSN 1650-5581 ; 2015:10
Keywords
Transportation system; Spatial optimization; Location models; Heuristics
National Category
Social Sciences Computer Sciences
Research subject
Complex Systems – Microdata Analysis, General Microdata Analysis - transports
Identifiers
urn:nbn:se:du-24682 (URN)
Note

New updated version of paper.

Available from: 2017-04-04 Created: 2017-04-04 Last updated: 2021-11-12Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-1015-8015

Search in DiVA

Show all publications