To Örebro University

oru.seÖrebro University Publications
Change search
Link to record
Permanent link

Direct link
Publications (10 of 32) Show all publications
Aregbede, V., Abraham, S. S., Persson, A., Längkvist, M. & Loutfi, A. (2024). Affordance-Based Goal Imagination for Embodied AI Agents. In: 2024 IEEE International Conference on Development and Learning (ICDL): . Paper presented at IEEE International Conference on Development and Learning (ICDL 2024), Austin, Texas, USA, May 20-23, 2024 (pp. 1-6). IEEE
Open this publication in new window or tab >>Affordance-Based Goal Imagination for Embodied AI Agents
Show others...
2024 (English)In: 2024 IEEE International Conference on Development and Learning (ICDL), IEEE, 2024, p. 1-6Conference paper, Published paper (Refereed)
Abstract [en]

Goal imagination in robotics is an emerging concept and involves the capability to automatically generate realistic goals, which, in turn, requires the assessment of the feasibility of transitioning from the current conditions of an initial scene to thedesired goal state. Existing research has explored the utilization of diverse image-generative models to create images depicting potential goal states based on the current state and instructions. In this paper, we illustrate the limitations of current state-of-the-art image generative models in accurately assessing the feasibility of specific actions in particular situations. Consequently, we present how integrating large language models, which possess profound knowledge of real-world objects and affordances, can enhance the performance of image-generative models in discerning plausible from implausible actions and simulating the outcomes of actions in a given context. This will be a step towards achieving the pragmatic goal of imagination in robotics.

Place, publisher, year, edition, pages
IEEE, 2024
Keywords
Embodiment, Affordance
National Category
Computer graphics and computer vision
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-118193 (URN)10.1109/ICDL61372.2024.10644764 (DOI)001338553000023 ()2-s2.0-85203835311 (Scopus ID)9798350348552 (ISBN)9798350348569 (ISBN)
Conference
IEEE International Conference on Development and Learning (ICDL 2024), Austin, Texas, USA, May 20-23, 2024
Funder
Swedish Research Council, 2021-05229
Available from: 2025-01-09 Created: 2025-01-09 Last updated: 2025-02-07Bibliographically approved
Rahaman, G. M., Längkvist, M. & Loutfi, A. (2024). Deep learning based automated estimation of urban green space index from satellite image: A case study. Urban Forestry & Urban Greening, 97, Article ID 128373.
Open this publication in new window or tab >>Deep learning based automated estimation of urban green space index from satellite image: A case study
2024 (English)In: Urban Forestry & Urban Greening, ISSN 1618-8667, E-ISSN 1610-8167, Vol. 97, article id 128373Article in journal (Refereed) Published
Abstract [en]

The green area factor model is a crucial tool for conserving and creating urban greenery and ecosystem services within neighborhood land. This model serves as a valuable index, streamlining the planning, assessment, and comparison of local-scale green infrastructures. However, conventional on-site measurements of the green area factor are resource intensive. In response, this study pioneers a computational approach that integrates ecological and social dimensions to estimate the green area factor. Employing satellite remote sensing and advanced deep learning techniques, the methodology utilizes satellite orthophotos of urban areas subjected to semantic segmentation, identifying and categorizing diverse green elements. Ground truths are established through on-site measurements of green area factors and satellite orthophotos from benchmarking sites in <spacing diaeresis>Orebro, Sweden. Results reveal an 82.0% average F1-score for semantic segmentations, signifying a favourable correlation between computationally estimated and measured green area factors. The proposed methodology is potential for adapting to various urban settings. In essence, this research introduces a promising, cost-effective solution for assessing urban greenness, particularly beneficial for urban administrators and planners aiming for insightful and comprehensive green strategies in city planning.

Place, publisher, year, edition, pages
Elsevier, 2024
Keywords
Deep convolutional neural networks (CNN), Green infrastructure, Green index, Semantic segmentation, Urban greenery, Urban planning
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:oru:diva-114996 (URN)10.1016/j.ufug.2024.128373 (DOI)001247062200001 ()2-s2.0-85194227352 (Scopus ID)
Funder
Region Örebro County, 20294202
Available from: 2024-07-25 Created: 2024-07-25 Last updated: 2024-07-25Bibliographically approved
Neelakantan, S., Hansson, A., Norell, J., Schött, J., Längkvist, M. & Loutfi, A. (2024). Machine Learning for Lithology Analysis using a Multi-Modal Approach of Integrating XRF and XCT data. In: 14th Scandinavian Conference on Artificial Intelligence SCAI 2024, June 10-11, 2024, Jönköping, Sweden: . Paper presented at 14th Scandinavian Conference on Artificial Intelligence (SCAI 2024), Jönköping, Sweden, June 10-11, 2024.
Open this publication in new window or tab >>Machine Learning for Lithology Analysis using a Multi-Modal Approach of Integrating XRF and XCT data
Show others...
2024 (English)In: 14th Scandinavian Conference on Artificial Intelligence SCAI 2024, June 10-11, 2024, Jönköping, Sweden, 2024Conference paper, Published paper (Refereed)
Abstract [en]

We explore the use of various machine learning (ML) models for classifying lithologies utilizing data from X-ray fluorescence (XRF) and X-ray computed tomography (XCT). Typically, lithologies are identified over several meters, which restricts the use of ML models due to limited training data. To address this issue, we augment the original interval dataset, where lithologies are marked over extensive sections, into finer segments of 10cm, to produce a high resolution dataset with vastly increased sample size. Additionally, we examine the impact of adjacent lithologies on building a more generalized ML model. We also demonstrate that combining XRF and XCT data leads to an improved classification accuracy compared to using only XRF data, which is the common practice in current studies, or solely relying on XCT data.

National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-115219 (URN)10.3384/ecp208021 (DOI)
Conference
14th Scandinavian Conference on Artificial Intelligence (SCAI 2024), Jönköping, Sweden, June 10-11, 2024
Funder
Knowledge Foundation, Dnr:20190128
Available from: 2024-08-06 Created: 2024-08-06 Last updated: 2024-08-12Bibliographically approved
Neelakantan, S., Norell, J., Hansson, A., Längkvist, M. & Loutfi, A. (2024). Neural network approach for shape-based euhedral pyrite identification in X-ray CT data with adversarial unsupervised domain adaptation. Applied Computing and Geosciences, 21, Article ID 100153.
Open this publication in new window or tab >>Neural network approach for shape-based euhedral pyrite identification in X-ray CT data with adversarial unsupervised domain adaptation
Show others...
2024 (English)In: Applied Computing and Geosciences, E-ISSN 2590-1974, Vol. 21, article id 100153Article in journal (Refereed) Published
Abstract [en]

We explore an attenuation and shape-based identification of euhedral pyrites in high-resolution X-ray Computed Tomography (XCT) data using deep neural networks. To deal with the scarcity of annotated data we generate a complementary training set of synthetic images. To investigate and address the domain gap between the synthetic and XCT data, several deep learning models, with and without domain adaption, are trained and compared. We find that a model trained on a small set of human annotations, while displaying over-fitting, can rival the human annotators. The unsupervised domain adaptation approaches are successful in bridging the domain gap, which significantly improves their performance. A domain-adapted model, trained on a dataset that fuses synthetic and real data, is the overall best-performing model. This highlights the possibility of using synthetic datasets for the application of deep learning in mineralogy.

Place, publisher, year, edition, pages
Elsevier, 2024
Keywords
Mineral identification, Unsupervised domain adaptation, Deep convolutional neural network, Semantic segmentation, Euhedral pyrites
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:oru:diva-111189 (URN)10.1016/j.acags.2023.100153 (DOI)001155327400001 ()2-s2.0-85182272087 (Scopus ID)
Funder
Knowledge Foundation, 20190128
Note

This work has been supported by the Industrial Graduate School Collaborative AI and Robotics funded by the Swedish Knowledge Foundation Dnr:20190128 and in collaboration with the industrial partner Orexplore Technologies.

Available from: 2024-01-29 Created: 2024-01-29 Last updated: 2024-02-14Bibliographically approved
Landin, C., Zhao, X., Längkvist, M. & Loutfi, A. (2023). An Intelligent Monitoring Algorithm to Detect Dependencies between Test Cases in the Manual Integration Process. In: 2023 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW): . Paper presented at 16th IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW 2023), Dublin, Ireland, April 16-20, 2023 (pp. 353-360). IEEE
Open this publication in new window or tab >>An Intelligent Monitoring Algorithm to Detect Dependencies between Test Cases in the Manual Integration Process
2023 (English)In: 2023 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW), IEEE, 2023, p. 353-360Conference paper, Published paper (Refereed)
Abstract [en]

Finding a balance between meeting test coverage and minimizing the testing resources is always a challenging task both in software (SW) and hardware (HW) testing. Therefore, employing machine learning (ML) techniques for test optimization purposes has received a great deal of attention. However, utilizing machine learning techniques frequently requires large volumes of valuable data to be trained. Although, the data gathering is hard and also expensive, manual data analysis takes most of the time in order to locate the source of failure once they have been produced in the so-called fault localization. Moreover, by applying ML techniques to historical production test data, relevant and irrelevant features can be found using strength association, such as correlation- and mutual information-based methods. In this paper, we use production data records of 100 units of a 5G radio product containing more than 7000 test results. The obtained results show that insightful information can be found after clustering the test results by their strength association, most linear and monotonic, which would otherwise be challenging to identify by traditional manual data analysis methods.

Place, publisher, year, edition, pages
IEEE, 2023
Series
IEEE International Conference on Software Testing Verification and Validation Workshop, ICSTW, ISSN 2159-4848
Keywords
Terms Test Optimization, Machine Learning, Fault Localization, Dependence Analysis, Mutual Information
National Category
Computer Sciences
Identifiers
urn:nbn:se:oru:diva-107727 (URN)10.1109/ICSTW58534.2023.00066 (DOI)001009223100052 ()2-s2.0-85163076493 (Scopus ID)9798350333350 (ISBN)9798350333367 (ISBN)
Conference
16th IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW 2023), Dublin, Ireland, April 16-20, 2023
Funder
Knowledge FoundationVinnova
Available from: 2023-08-28 Created: 2023-08-28 Last updated: 2023-10-05Bibliographically approved
Paylar, B., Längkvist, M., Jass, J. & Olsson, P.-E. (2023). Utilization of Computer Classification Methods for Exposure Prediction and Gene Selection in Daphnia magna Toxicogenomics. Biology, 12(5), Article ID 692.
Open this publication in new window or tab >>Utilization of Computer Classification Methods for Exposure Prediction and Gene Selection in Daphnia magna Toxicogenomics
2023 (English)In: Biology, E-ISSN 2079-7737, Vol. 12, no 5, article id 692Article in journal (Refereed) Published
Abstract [en]

Zinc (Zn) is an essential element that influences many cellular functions. Depending on bioavailability, Zn can cause both deficiency and toxicity. Zn bioavailability is influenced by water hardness. Therefore, water quality analysis for health-risk assessment should consider both Zn concentration and water hardness. However, exposure media selection for traditional toxicology tests are set to defined hardness levels and do not represent the diverse water chemistry compositions observed in nature. Moreover, these tests commonly use whole organism endpoints, such as survival and reproduction, which require high numbers of test animals and are labor intensive. Gene expression stands out as a promising alternative to provide insight into molecular events that can be used for risk assessment. In this work, we apply machine learning techniques to classify the Zn concentrations and water hardness from Daphnia magna gene expression by using quantitative PCR. A method for gene ranking was explored using techniques from game theory, namely, Shapley values. The results show that standard machine learning classifiers can classify both Zn concentration and water hardness simultaneously, and that Shapley values are a versatile and useful alternative for gene ranking that can provide insight about the importance of individual genes.

Place, publisher, year, edition, pages
MDPI, 2023
Keywords
Zn, bioavailability, biomarker, machine learning, water hardness
National Category
Water Engineering
Identifiers
urn:nbn:se:oru:diva-106096 (URN)10.3390/biology12050692 (DOI)000995573200001 ()37237504 (PubMedID)2-s2.0-85160308477 (Scopus ID)
Funder
Knowledge Foundation, 20180027Örebro University, 1214-NT3060
Available from: 2023-05-29 Created: 2023-05-29 Last updated: 2024-01-02Bibliographically approved
Rahaman, G. M., Längkvist, M. & Loutfi, A. (2022). Deep Learning based Aerial Image Segmentation for Computing Green Area Factor. In: 2022 10th European Workshop on Visual Information Processing (EUVIP): . Paper presented at 10th European Workshop on Visual Information Processing (EUVIP), Lisbon, Portugal, September 11-14, 2022. IEEE
Open this publication in new window or tab >>Deep Learning based Aerial Image Segmentation for Computing Green Area Factor
2022 (English)In: 2022 10th European Workshop on Visual Information Processing (EUVIP), IEEE, 2022Conference paper, Published paper (Refereed)
Abstract [en]

The Green Area Factor(GYF) is an aggregate norm used as an index to quantify how much eco-efficient surface exists in a given area. Although the GYF is a single number, it expresses several different contributions of natural objects to the ecosystem. It is used as a planning tool to create and manage attractive urban environments ensuring the existence of required green/blue elements. Currently, the GYF model is gaining rapid attraction by different communities. However, calculating the GYF value is challenging as significant amount of manual effort is needed. In this study, we present a novel approach for automatic extraction of the GYF value from aerial imagery using semantic segmentation results. For model training and validation a set of RGB images captured by Drone imaging system is used. Each image is annotated into trees, grass, soil/open surface, building, and road. A modified U-net deep learning architecture is used for the segmentation of various objects by classifying each pixel into one of the semantic classes. From the segmented image we calculate the class-wise fractional area coverages that are used as input into the simplified GYF model called Sundbyberg for calculating the GYF value. Experimental results yield that the deep learning method provides about 92% mean IoU for test image segmentation and corresponding GYF value is 0.34.

Place, publisher, year, edition, pages
IEEE, 2022
Series
European Workshop on Visual Information Processing, ISSN 2471-8963, E-ISSN 2164-974X
Keywords
green Area index, deep learning, CNN, image, segmentation, urban planning, semantic classification
National Category
Computer graphics and computer vision
Research subject
Computerized Image Analysis
Identifiers
urn:nbn:se:oru:diva-102544 (URN)10.1109/EUVIP53989.2022.9922743 (DOI)000886233300019 ()2-s2.0-85141101986 (Scopus ID)9781665466233 (ISBN)9781665466240 (ISBN)
Conference
10th European Workshop on Visual Information Processing (EUVIP), Lisbon, Portugal, September 11-14, 2022
Available from: 2022-12-05 Created: 2022-12-05 Last updated: 2025-02-07Bibliographically approved
Blad, S., Längkvist, M., Klügl, F. & Loutfi, A. (2022). Empirical analysis of the convergence of Double DQN in relation to reward sparsity. In: Wani, MA; Kantardzic, M; Palade, V; Neagu, D; Yang, L; Chan, KY (Ed.), 21st IEEE International Conference on Machine Learning and Applications. ICMLA 2022: Proceedings. Paper presented at 21st IEEE International Conference on Machine Learning and Applications (IEEE ICMLA), Nassau, Bahamas, December 12-14, 2022 (pp. 591-596). IEEE
Open this publication in new window or tab >>Empirical analysis of the convergence of Double DQN in relation to reward sparsity
2022 (English)In: 21st IEEE International Conference on Machine Learning and Applications. ICMLA 2022: Proceedings / [ed] Wani, MA; Kantardzic, M; Palade, V; Neagu, D; Yang, L; Chan, KY, IEEE, 2022, p. 591-596Conference paper, Published paper (Refereed)
Abstract [en]

Q-Networks are used in Reinforcement Learning to model the expected return from every action at a given state. When training Q-Networks, external reward signals are propagated to the previously performed actions leading up to each reward. If many actions are required before experiencing a reward, the reward signal is distributed across all those actions, where some actions may have greater impact on the reward than others. As the number of significant actions between rewards increases, the relative importance of each action decreases. If actions have too small importance, their impact might be over-shadowed by noise in a deep neural network model, potentially causing convergence issues. In this work, we empirically test the limits of increasing the number of actions leading up to a reward in a simple grid-world environment. We show in our experiments that even though the training error surpasses the reward signal attributed to each action, the model is still able to learn a smooth enough value representation.

Place, publisher, year, edition, pages
IEEE, 2022
Keywords
reinforcement learning, deep q-learning, reward sparsity
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:oru:diva-102850 (URN)10.1109/ICMLA55696.2022.00102 (DOI)000980994900087 ()2-s2.0-85152213586 (Scopus ID)9781665462839 (ISBN)9781665462846 (ISBN)
Conference
21st IEEE International Conference on Machine Learning and Applications (IEEE ICMLA), Nassau, Bahamas, December 12-14, 2022
Funder
Wallenberg AI, Autonomous Systems and Software Program (WASP)Knowledge Foundation, 20190128Knut and Alice Wallenberg Foundation
Available from: 2022-12-22 Created: 2022-12-22 Last updated: 2023-08-21Bibliographically approved
Sjöqvist, H., Längkvist, M. & Javed, F. (2020). An Analysis of Fast Learning Methods for Classifying Forest Cover Types. Applied Artificial Intelligence, 34(10), 691-709
Open this publication in new window or tab >>An Analysis of Fast Learning Methods for Classifying Forest Cover Types
2020 (English)In: Applied Artificial Intelligence, ISSN 0883-9514, E-ISSN 1087-6545, Vol. 34, no 10, p. 691-709Article in journal (Refereed) Published
Abstract [en]

Proper mapping and classification of Forest cover types are integral in understanding the processes governing the interaction mechanism of the surface with the atmosphere. In the presence of massive satellite and aerial measurements, a proper manual categorization has become a tedious job. In this study, we implement three different modest machine learning classifiers along with three statistical feature selectors to classify different cover types from cartographic variables. Our results showed that, among the chosen classifiers, the standard Random Forest Classifier together with Principal Components performs exceptionally well, not only in overall assessment but across all seven categories. Our results are found to be significantly better than existing studies involving more complex Deep Learning models.

Place, publisher, year, edition, pages
Taylor & Francis Group, 2020
National Category
Other Natural Sciences Probability Theory and Statistics
Research subject
Statistics
Identifiers
urn:nbn:se:oru:diva-83354 (URN)10.1080/08839514.2020.1771523 (DOI)000550104300001 ()2-s2.0-85086860115 (Scopus ID)
Funder
The Jan Wallander and Tom Hedelius Foundation, P18-0201
Available from: 2020-06-18 Created: 2020-06-18 Last updated: 2020-08-19Bibliographically approved
Landin, C., Tahvili, S., Haggren, H., Längkvist, M., Muhammad, A. & Loutfi, A. (2020). Cluster-Based Parallel Testing Using Semantic Analysis. In: 2020 IEEE International Conference On Artificial Intelligence Testing (AITest): . Paper presented at 2nd IEEE International Conference on Artificial Intelligence Testing (AITest 2020), Oxford, United Kingdom, August 3-6, 2020 (pp. 99-106). IEEE
Open this publication in new window or tab >>Cluster-Based Parallel Testing Using Semantic Analysis
Show others...
2020 (English)In: 2020 IEEE International Conference On Artificial Intelligence Testing (AITest), IEEE, 2020, p. 99-106Conference paper, Published paper (Refereed)
Abstract [en]

Finding a balance between testing goals and testing resources can be considered as a most challenging issue, therefore test optimization plays a vital role in the area of software testing. Several parameters such as the objectives of the tests, test cases similarities and dependencies between test cases need to be considered, before attempting any optimization approach. However, analyzing corresponding testing artifacts (e.g. requirement specification, test cases) for capturing the mentioned parameters is a complicated task especially in a manual testing procedure, where the test cases are documented as a natural text written by a human. Thus, utilizing artificial intelligence techniques in the process of analyzing complex and sometimes ambiguous test data, is considered to be working in different industries. Test scheduling is one of the most popular and practical ways to optimize the testing process. Having a group of test cases which are required the same system setup, installation or testing the same functionality can lead to a more efficient testing process. In this paper, we propose, apply and evaluate a natural language processing-based approach that derives test cases' similarities directly from their test specification. The proposed approach utilizes the Levenshtein distance and converts each test case into a string. Test cases are then grouped into several clusters based on their similarities. Finally, a set of cluster-based parallel test scheduling strategies are proposed for execution. The feasibility of the proposed approach is studied by an empirical evaluation that has been performed on a Telecom use-case at Ericsson in Sweden and indicates promising results.

Place, publisher, year, edition, pages
IEEE, 2020
Series
IEEE International Conference on Artificial Intelligence Testing (AITest)
Keywords
Software Testing, Natural Language Processing, Test Optimization, Semantic Similarity, Clustering
National Category
Computer Sciences
Identifiers
urn:nbn:se:oru:diva-88654 (URN)10.1109/AITEST49225.2020.00022 (DOI)000583824000015 ()2-s2.0-85092313008 (Scopus ID)978-1-7281-6984-2 (ISBN)
Conference
2nd IEEE International Conference on Artificial Intelligence Testing (AITest 2020), Oxford, United Kingdom, August 3-6, 2020
Funder
Knowledge FoundationVinnova
Available from: 2021-01-19 Created: 2021-01-19 Last updated: 2023-10-05Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-0579-7181

Search in DiVA

Show all publications