Till Örebro universitet

oru.seÖrebro universitets publikationer
Ändra sökning
Avgränsa sökresultatet
1 - 29 av 29
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Träffar per sida
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sortering
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
Markera
Maxantalet träffar du kan exportera från sökgränssnittet är 250. Vid större uttag använd dig av utsökningar.
  • 1.
    Alirezaie, Marjan
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Kiselev, Andrey
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Klügl, Franziska
    Örebro universitet, Institutionen för naturvetenskap och teknik. Örebro universitet, Institutionen för juridik, psykologi och socialt arbete.
    Längkvist, Martin
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Exploiting Context and Semantics for UAV Path-finding in an Urban Setting2017Ingår i: Proceedings of the 1st International Workshop on Application of Semantic Web technologies in Robotics (AnSWeR 2017), Portoroz, Slovenia, May 29th, 2017 / [ed] Emanuele Bastianelli, Mathieu d'Aquin, Daniele Nardi, Technical University Aachen , 2017, s. 11-20Konferensbidrag (Refereegranskat)
    Abstract [en]

    In this paper we propose an ontology pattern that represents paths in a geo-representation model to be used in an aerial path planning processes. This pattern provides semantics related to constraints (i.e., ight forbidden zones) in a path planning problem in order to generate collision free paths. Our proposed approach has been applied on an ontology containing geo-regions extracted from satellite imagery data from a large urban city as an illustrative example.

    Ladda ner fulltext (pdf)
    Exploiting Context and Semantics for UAV Path-finding in an Urban Setting
  • 2.
    Alirezaie, Marjan
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Kiselev, Andrey
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Längkvist, Martin
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Klügl, Franziska
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    An Ontology-Based Reasoning Framework for Querying Satellite Images for Disaster Monitoring2017Ingår i: Sensors, E-ISSN 1424-8220, Vol. 17, nr 11, artikel-id 2545Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    This paper presents a framework in which satellite images are classified and augmented with additional semantic information to enable queries about what can be found on the map at a particular location, but also about paths that can be taken. This is achieved by a reasoning framework based on qualitative spatial reasoning that is able to find answers to high level queries that may vary on the current situation. This framework called SemCityMap, provides the full pipeline from enriching the raw image data with rudimentary labels to the integration of a knowledge representation and reasoning methods to user interfaces for high level querying. To illustrate the utility of SemCityMap in a disaster scenario, we use an urban environment—central Stockholm—in combination with a flood simulation. We show that the system provides useful answers to high-level queries also with respect to the current flood status. Examples of such queries concern path planning for vehicles or retrieval of safe regions such as “find all regions close to schools and far from the flooded area”. The particular advantage of our approach lies in the fact that ontological information and reasoning is explicitly integrated so that queries can be formulated in a natural way using concepts on appropriate level of abstraction, including additional constraints.

    Ladda ner fulltext (pdf)
    fulltext
  • 3.
    Alirezaie, Marjan
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Längkvist, Martin
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Kiselev, Andrey
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Open GeoSpatial Data as a Source of Ground Truth for Automated Labelling of Satellite Images2016Ingår i: SDW 2016: Spatial Data on the Web, Proceedings / [ed] Krzysztof Janowicz et al., CEUR Workshop Proceedings , 2016, s. 5-8Konferensbidrag (Refereegranskat)
  • 4.
    Alirezaie, Marjan
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Längkvist, Martin
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Knowledge Representation and Reasoning Methods to Explain Errors in Machine Learning2020Ingår i: Knowledge Graphs for eXplainable Artificial Intelligence: Foundations, Applications and Challenges / [ed] Ilaria Tiddi, Freddy Lécué, Pascal Hitzler, IOS Press, 2020Kapitel i bok, del av antologi (Refereegranskat)
    Abstract [en]

    In this chapter we focus the use of knowledge representation and reasoning (KRR) methods as a guide to machine learning algorithms whereby relevant contextual knowledge can be leveraged upon. In this way, the learning methods improve performance by taking into account causal relationships behind errors. Performance improvement can be obtained by focusing the learning task on aspects that are particularly challenging (or prone to error), and then using added knowledge inferred by the reasoner as a means to provide further input to learning algorithms. Said differently, the KRR algorithms guide the learning algorithms, feeding it labels and data in order to iteratively reduce the errors calculated by a given cost function. This closed loop system comes with the added benefit that errors are also made more understandable to the human, as it is the task of the KRR system to contextualize the errors from the ML algorithm in accordance with its knowledge model. This represents a type of explainable AI that is focused on interpretability. This chapter will discuss the benefits of using KRR methods with ML methods in this way, and demonstrate an approach applied to satellite data for the purpose of improving classification and segmentation task.

  • 5.
    Alirezaie, Marjan
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Längkvist, Martin
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Sioutis, Michael
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    A Symbolic Approach for Explaining Errors in Image Classification Tasks2018Konferensbidrag (Refereegranskat)
    Abstract [en]

    Machine learning algorithms, despite their increasing success in handling object recognition tasks, still seldom perform without error. Often the process of understanding why the algorithm has failed is the task of the human who, using domain knowledge and contextual information, can discover systematic shortcomings in either the data or the algorithm. This paper presents an approach where the process of reasoning about errors emerging from a machine learning framework is automated using symbolic techniques. By utilizing spatial and geometrical reasoning between objects in a scene, the system is able to describe misclassified regions in relation to its context. The system is demonstrated in the remote sensing domain where objects and entities are detected in satellite images.

  • 6.
    Alirezaie, Marjan
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Längkvist, Martin
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Sioutis, Michael
    Department of Computer Science, Aalto University, Espoo, Finland.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Semantic Referee: A Neural-Symbolic Framework for Enhancing Geospatial Semantic Segmentation2019Ingår i: Semantic Web, ISSN 1570-0844, E-ISSN 2210-4968, Vol. 10, nr 5, s. 863-880Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Understanding why machine learning algorithms may fail is usually the task of the human expert that uses domain knowledge and contextual information to discover systematic shortcomings in either the data or the algorithm. In this paper, we propose a semantic referee, which is able to extract qualitative features of the errors emerging from deep machine learning frameworks and suggest corrections. The semantic referee relies on ontological reasoning about spatial knowledge in order to characterize errors in terms of their spatial relations with the environment. Using semantics, the reasoner interacts with the learning algorithm as a supervisor. In this paper, the proposed method of the interaction between a neural network classifier and a semantic referee shows how to improve the performance of semantic segmentation for satellite imagery data.

  • 7.
    Blad, Samuel
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik. Nexer.
    Längkvist, Martin
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Klügl, Franziska
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Empirical analysis of the convergence of Double DQN in relation to reward sparsity2022Ingår i: 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, s. 591-596Konferensbidrag (Refereegranskat)
    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.

  • 8.
    Landin, Cristina
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik. Product Development Unit Radio, Production Test Development, Ericsson AB, Kumla, Sweden.
    Hatvani, Leo
    School of Innovation, Design and Engineering, Mälardalen University, Västerås, Sweden.
    Tahvili, Sahar
    Global Artificial Intelligence Accelerator (GAIA), Ericsson AB, Stockholm, Sweden; School of Innovation, Design and Engineering, Mälardalen University, Västerås, Sweden.
    Haggren, Hugo
    Global Artificial Intelligence Accelerator (GAIA), Ericsson AB, Stockholm, Sweden.
    Längkvist, Martin
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Håkansson, Anne
    School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden.
    Performance Comparison of Two Deep Learning Algorithms in Detecting Similarities Between Manual Integration Test Cases2020Ingår i: The Fifteenth International Conference on Software Engineering Advances, International Academy, Research and Industry Association (IARIA) , 2020, s. 90-97Konferensbidrag (Refereegranskat)
    Abstract [en]

    Software testing is still heavily dependent on human judgment since a large portion of testing artifacts, such as requirements and test cases are written in a natural text by experts. Identifying and classifying relevant test cases in large test suites is a challenging and also time-consuming task. Moreover, to optimize the testing process test cases should be distinguished based on their properties, such as their dependencies and similarities. Knowing the mentioned properties at an early stage of the testing process can be utilized for several test optimization purposes, such as test case selection, prioritization, scheduling,and also parallel test execution. In this paper, we apply, evaluate, and compare the performance of two deep learning algorithmsto detect the similarities between manual integration test cases. The feasibility of the mentioned algorithms is later examined in a Telecom domain by analyzing the test specifications of five different products in the product development unit at Ericsson AB in Sweden. The empirical evaluation indicates that utilizing deep learning algorithms for finding the similarities between manual integration test cases can lead to outstanding results.

    Ladda ner fulltext (pdf)
    Performance Comparison of Two Deep Learning Algorithms in Detecting Similarities Between Manual Integration Test Cases
  • 9.
    Landin, Cristina
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Tahvili, Sahar
    Global Artificial Intelligence Accelerator (GAIA), Ericsson AB, Stockholm, Sweden; School of Innovation, Design and Engineering, Mälardalen University, Västerås, Sweden.
    Haggren, Hugo
    Global Artificial Intelligence Accelerator (GAIA), Ericsson AB, Stockholm, Sweden.
    Längkvist, Martin
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Muhammad, Auwn
    Global Artificial Intelligence Accelerator (GAIA), Ericsson AB, Stockholm, Sweden.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Cluster-Based Parallel Testing Using Semantic Analysis2020Ingår i: 2020 IEEE International Conference On Artificial Intelligence Testing (AITest), IEEE, 2020, s. 99-106Konferensbidrag (Refereegranskat)
    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.

  • 10.
    Landin, Cristina
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik. Product Development Unit Radio, Production Test Development, Ericsson AB, Kumla, Sweden.
    Zhao, Xinrong
    Department of Mathematical Science, Chalmers University, Gothenburg, Sweden.
    Längkvist, Martin
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    An Intelligent Monitoring Algorithm to Detect Dependencies between Test Cases in the Manual Integration Process2023Ingår i: 2023 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW), IEEE, 2023, s. 353-360Konferensbidrag (Refereegranskat)
    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.

  • 11.
    Lidén, Mats
    et al.
    Örebro universitet, Institutionen för medicinska vetenskaper.
    Jendeberg, Johan
    Örebro universitet, Institutionen för medicinska vetenskaper.
    Längkvist, Martin
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Thunberg, Per
    Örebro universitet, Institutionen för medicinska vetenskaper.
    Discrimination between distal ureteral stones and pelvic phleboliths in CT using a deep neural network: more than local features needed2018Konferensbidrag (Refereegranskat)
    Abstract [en]

    Purpose: To develop a deep learning method for assisting radiologists in the discrimination between distal ureteral stones and pelvic phleboliths in thin slice CT images, and to evaluate whether this differentiation is possible using only local features.

    Methods and materials: A limited field-of-view image data bank was retrospectively created, consisting of 5x5x5 cm selections from 1 mm thick unenhanced CT images centered around 218 pelvis phleboliths and 267 distal ureteral stones in 336 patients. 50 stones and 50 phleboliths formed a validation cohort and the remainder a training cohort. Ground truth was established by a radiologist using the complete CT examination during inclusion.The limited field-of-view CT stacks were independently reviewed and classified as containing a distal ureteral stone or a phlebolith by seven radiologists. Each cropped stack consisted of 50 slices (5x5 cm field-of-view) and was displayed in a standard PACS reading environment. A convolutional neural network using three perpendicular images (2.5D-CNN) from the limited field-of-view CT stacks was trained for classification.

    Results: The 2.5D-CNN obtained 89% accuracy (95% confidence interval 81%-94%) for the classification in the unseen validation cohort while the accuracy of radiologists reviewing the same cohort was 86% (range 76%-91%). There was no statistically significant difference between 2.5D-CNN and radiologists.

    Conclusion: The 2.5D-CNN achieved radiologist level classification accuracy between distal ureteral stones and pelvic phleboliths when only using the local features. The mean accuracy of 86% for radiologists using limited field-of-view indicates that distant anatomical information that helps identifying the ureter’s course is needed.

  • 12.
    Längkvist, Martin
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Modeling time-series with deep networks2014Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
    Delarbeten
    1. A review of unsupervised feature learning and deep learning for time-series modeling
    Öppna denna publikation i ny flik eller fönster >>A review of unsupervised feature learning and deep learning for time-series modeling
    2014 (Engelska)Ingår i: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344, Vol. 42, nr 1, s. 11-24Artikel, forskningsöversikt (Refereegranskat) Published
    Abstract [en]

    This paper gives a review of the recent developments in deep learning and unsupervised feature learning for time-series problems. While these techniques have shown promise for modeling static data, such as computer vision, applying them to time-series data is gaining increasing attention. This paper overviews the particular challenges present in time-series data and provides a review of the works that have either applied time-series data to unsupervised feature learning algorithms or alternatively have contributed to modifications of feature learning algorithms to take into account the challenges present in time-series data.

    Ort, förlag, år, upplaga, sidor
    Elsevier, 2014
    Nyckelord
    Time-series, Unsupervised feature learning, Deep learning
    Nationell ämneskategori
    Datavetenskap (datalogi)
    Forskningsämne
    Datavetenskap
    Identifikatorer
    urn:nbn:se:oru:diva-34597 (URN)10.1016/j.patrec.2014.01.008 (DOI)000333451300002 ()2-s2.0-84894359867 (Scopus ID)
    Tillgänglig från: 2014-04-07 Skapad: 2014-04-07 Senast uppdaterad: 2018-01-11Bibliografiskt granskad
    2. Sleep stage classification using unsupervised feature learning
    Öppna denna publikation i ny flik eller fönster >>Sleep stage classification using unsupervised feature learning
    2012 (Engelska)Ingår i: Advances in Artificial Neural Systems, ISSN 1687-7594, E-ISSN 1687-7608, s. 107046-Artikel i tidskrift (Refereegranskat) Published
    Abstract [en]

    Most attempts at training computers for the difficult and time-consuming task of sleep stage classification involve a feature extraction step. Due to the complexity of multimodal sleep data, the size of the feature space can grow to the extent that it is also necessary to include a feature selection step. In this paper, we propose the use of an unsupervised feature learning architecture called deep belief nets (DBNs) and show how to apply it to sleep data in order to eliminate the use of handmade features. Using a postprocessing step of hidden Markov model (HMM) to accurately capture sleep stage switching, we compare our results to a feature-based approach. A study of anomaly detection with the application to home environment data collection is also presented. The results using raw data with a deep architecture, such as the DBN, were comparable to a feature-based approach when validated on clinical datasets.

    Ort, förlag, år, upplaga, sidor
    Hindawi Publishing Corporation, 2012
    Nationell ämneskategori
    Teknik och teknologier Datavetenskap (datalogi)
    Forskningsämne
    Datalogi
    Identifikatorer
    urn:nbn:se:oru:diva-24199 (URN)10.1155/2012/107046 (DOI)
    Tillgänglig från: 2012-08-02 Skapad: 2012-08-02 Senast uppdaterad: 2018-01-12Bibliografiskt granskad
    3. Fast Classification of Meat Spoilage Markers Using Nanostructured ZnO Thin Films and Unsupervised Feature Learning
    Öppna denna publikation i ny flik eller fönster >>Fast Classification of Meat Spoilage Markers Using Nanostructured ZnO Thin Films and Unsupervised Feature Learning
    2013 (Engelska)Ingår i: Sensors, E-ISSN 1424-8220, Vol. 13, nr 2, s. 1578-1592Artikel i tidskrift (Refereegranskat) Published
    Abstract [en]

    This paper investigates a rapid and accurate detection system for spoilage in meat. We use unsupervised feature learning techniques (stacked restricted Boltzmann machines and auto-encoders) that consider only the transient response from undoped zinc oxide, manganese-doped zinc oxide, and fluorine-doped zinc oxide in order to classify three categories: the type of thin film that is used, the type of gas, and the approximate ppm-level of the gas. These models mainly offer the advantage that features are learned from data instead of being hand-designed. We compare our results to a feature-based approach using samples with various ppm level of ethanol and trimethylamine (TMA) that are good markers for meat spoilage. The result is that deep networks give a better and faster classification than the feature-based approach, and we thus conclude that the fine-tuning of our deep models are more efficient for this kind of multi-label classification task.

    Nyckelord
    electronic nose, sensor material, representational learning, fast multi-label classification
    Nationell ämneskategori
    Datavetenskap (datalogi)
    Forskningsämne
    Datavetenskap
    Identifikatorer
    urn:nbn:se:oru:diva-34598 (URN)10.3390/s130201578 (DOI)000315403300012 ()2-s2.0-84873853951 (Scopus ID)
    Forskningsfinansiär
    VINNOVA, INT/SWD/VINN/P-04/2011
    Anmärkning

    Fuding agency: Department of Science & Technology, India 

    Tillgänglig från: 2014-04-07 Skapad: 2014-04-07 Senast uppdaterad: 2022-02-10Bibliografiskt granskad
    4. Learning feature representations with a cost-relevant sparse autoencoder
    Öppna denna publikation i ny flik eller fönster >>Learning feature representations with a cost-relevant sparse autoencoder
    2015 (Engelska)Ingår i: International Journal of Neural Systems, ISSN 0129-0657, E-ISSN 1793-6462, Vol. 25, nr 1, s. 1450034-Artikel i tidskrift (Refereegranskat) Published
    Abstract [en]

    There is an increasing interest in the machine learning community to automatically learn feature representations directly from the (unlabeled) data instead of using hand-designed features. The autoencoder is one method that can be used for this purpose. However, for data sets with a high degree of noise, a large amount of the representational capacity in the autoencoder is used to minimize the reconstruction error for these noisy inputs. This paper proposes a method that improves the feature learning process by focusing on the task relevant information in the data. This selective attention is achieved by weighting the reconstruction error and reducing the influence of noisy inputs during the learning process. The proposed model is trained on a number of publicly available image data sets and the test error rate is compared to a standard sparse autoencoder and other methods, such as the denoising autoencoder and contractive autoencoder.

    Nyckelord
    Sparse autoencoder; unsupervised feature learning; weighted cost function
    Nationell ämneskategori
    Annan teknik Datorteknik
    Forskningsämne
    Datavetenskap
    Identifikatorer
    urn:nbn:se:oru:diva-40063 (URN)10.1142/S0129065714500348 (DOI)000347965500005 ()25515941 (PubMedID)
    Tillgänglig från: 2014-12-29 Skapad: 2014-12-29 Senast uppdaterad: 2018-06-26Bibliografiskt granskad
    5. Selective attention auto-encoder for automatic sleep staging
    Öppna denna publikation i ny flik eller fönster >>Selective attention auto-encoder for automatic sleep staging
    2014 (Engelska)Manuskript (preprint) (Övrigt vetenskapligt)
    Nationell ämneskategori
    Datavetenskap (datalogi)
    Forskningsämne
    Datavetenskap
    Identifikatorer
    urn:nbn:se:oru:diva-42935 (URN)
    Tillgänglig från: 2015-02-25 Skapad: 2015-02-25 Senast uppdaterad: 2018-04-05Bibliografiskt granskad
    Ladda ner fulltext (pdf)
    Introductory chapter
    Ladda ner fulltext (pdf)
    Cover
    Ladda ner (pdf)
    Spikblad
  • 13.
    Längkvist, Martin
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Alirezaie, Marjan
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Kiselev, Andrey
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Interactive Learning with Convolutional Neural Networks for Image Labeling2016Ingår i: International Joint Conference on Artificial Intelligence (IJCAI), 2016Konferensbidrag (Refereegranskat)
    Abstract [en]

    Recently, deep learning models, such as Convolutional Neural Networks, have shown to give good performance for various computer vision tasks. A pre-requisite for such models is to have access to lots of labeled data since the most successful ones are trained with supervised learning. The process of labeling data is expensive, time-consuming, tedious, and sometimes subjective, which can result in falsely labeled data, which has a negative effect on both the training and the validation. In this work, we propose a human-in-the-loop intelligent system that allows the agent and the human to collabo- rate to simultaneously solve the problem of labeling data and at the same time perform scene labeling of an unlabeled image data set with minimal guidance by a human teacher. We evaluate the proposed in- teractive learning system by comparing the labeled data set from the system to the human-provided labels. The results show that the learning system is capable of almost completely label an entire image data set starting from a few labeled examples provided by the human teacher.

    Ladda ner fulltext (pdf)
    fulltext
  • 14.
    Längkvist, Martin
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Coradeschi, Silvia
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Rayappan, John Bosco Balaguru
    SASTRA University, Thanjavur, India.
    Fast Classification of Meat Spoilage Markers Using Nanostructured ZnO Thin Films and Unsupervised Feature Learning2013Ingår i: Sensors, E-ISSN 1424-8220, Vol. 13, nr 2, s. 1578-1592Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    This paper investigates a rapid and accurate detection system for spoilage in meat. We use unsupervised feature learning techniques (stacked restricted Boltzmann machines and auto-encoders) that consider only the transient response from undoped zinc oxide, manganese-doped zinc oxide, and fluorine-doped zinc oxide in order to classify three categories: the type of thin film that is used, the type of gas, and the approximate ppm-level of the gas. These models mainly offer the advantage that features are learned from data instead of being hand-designed. We compare our results to a feature-based approach using samples with various ppm level of ethanol and trimethylamine (TMA) that are good markers for meat spoilage. The result is that deep networks give a better and faster classification than the feature-based approach, and we thus conclude that the fine-tuning of our deep models are more efficient for this kind of multi-label classification task.

    Ladda ner fulltext (pdf)
    fastmeat
  • 15.
    Längkvist, Martin
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Jendeberg, Johan
    Örebro universitet, Institutionen för medicinska vetenskaper. Department of Radiology, Faculty of Health and Medical Sciences, Örebro University, Örebro, Sweden.
    Thunberg, Per
    Örebro universitet, Institutionen för medicinska vetenskaper. Department of Medical Physics, Faculty of Health and Medical Sciences, Örebro University, Örebro, Sweden.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Lidén, Mats
    Örebro universitet, Institutionen för medicinska vetenskaper. Department of Radiology, Faculty of Health and Medical Sciences, Örebro University, Örebro, Sweden.
    Computer aided detection of ureteral stones in thin slice computed tomography volumes using Convolutional Neural Networks2018Ingår i: Computers in Biology and Medicine, ISSN 0010-4825, E-ISSN 1879-0534, Vol. 97, s. 153-160Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Computed tomography (CT) is the method of choice for diagnosing ureteral stones - kidney stones that obstruct the ureter. The purpose of this study is to develop a computer aided detection (CAD) algorithm for identifying a ureteral stone in thin slice CT volumes. The challenge in CAD for urinary stones lies in the similarity in shape and intensity of stones with non-stone structures and how to efficiently deal with large high-resolution CT volumes. We address these challenges by using a Convolutional Neural Network (CNN) that works directly on the high resolution CT volumes. The method is evaluated on a large data base of 465 clinically acquired high-resolution CT volumes of the urinary tract with labeling of ureteral stones performed by a radiologist. The best model using 2.5D input data and anatomical information achieved a sensitivity of 100% and an average of 2.68 false-positives per patient on a test set of 88 scans.

  • 16.
    Längkvist, Martin
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Karlsson, Lars
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    A review of unsupervised feature learning and deep learning for time-series modeling2014Ingår i: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344, Vol. 42, nr 1, s. 11-24Artikel, forskningsöversikt (Refereegranskat)
    Abstract [en]

    This paper gives a review of the recent developments in deep learning and unsupervised feature learning for time-series problems. While these techniques have shown promise for modeling static data, such as computer vision, applying them to time-series data is gaining increasing attention. This paper overviews the particular challenges present in time-series data and provides a review of the works that have either applied time-series data to unsupervised feature learning algorithms or alternatively have contributed to modifications of feature learning algorithms to take into account the challenges present in time-series data.

    Ladda ner fulltext (pdf)
    DLreview
  • 17.
    Längkvist, Martin
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Karlsson, Lars
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Sleep stage classification using unsupervised feature learning2012Ingår i: Advances in Artificial Neural Systems, ISSN 1687-7594, E-ISSN 1687-7608, s. 107046-Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Most attempts at training computers for the difficult and time-consuming task of sleep stage classification involve a feature extraction step. Due to the complexity of multimodal sleep data, the size of the feature space can grow to the extent that it is also necessary to include a feature selection step. In this paper, we propose the use of an unsupervised feature learning architecture called deep belief nets (DBNs) and show how to apply it to sleep data in order to eliminate the use of handmade features. Using a postprocessing step of hidden Markov model (HMM) to accurately capture sleep stage switching, we compare our results to a feature-based approach. A study of anomaly detection with the application to home environment data collection is also presented. The results using raw data with a deep architecture, such as the DBN, were comparable to a feature-based approach when validated on clinical datasets.

  • 18.
    Längkvist, Martin
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Kiselev, Andrey
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Alirezaie, Marjan
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Classification and Segmentation of Satellite Orthoimagery Using Convolutional Neural Networks2016Ingår i: Remote Sensing, E-ISSN 2072-4292, Vol. 8, nr 4, artikel-id 329Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    The availability of high-resolution remote sensing (HRRS) data has opened up the possibility for new interesting applications, such as per-pixel classification of individual objects in greater detail. This paper shows how a convolutional neural network (CNN) can be applied to multispectral orthoimagery and a digital surface model (DSM) of a small city for a full, fast and accurate per-pixel classification. The predicted low-level pixel classes are then used to improve the high-level segmentation. Various design choices of the CNN architecture are evaluated and analyzed. The investigated land area is fully manually labeled into five categories (vegetation, ground, roads, buildings and water), and the classification accuracy is compared to other per-pixel classification works on other land areas that have a similar choice of categories. The results of the full classification and segmentation on selected segments of the map show that CNNs are a viable tool for solving both the segmentation and object recognition task for remote sensing data.

  • 19.
    Längkvist, Martin
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Learning feature representations with a cost-relevant sparse autoencoder2015Ingår i: International Journal of Neural Systems, ISSN 0129-0657, E-ISSN 1793-6462, Vol. 25, nr 1, s. 1450034-Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    There is an increasing interest in the machine learning community to automatically learn feature representations directly from the (unlabeled) data instead of using hand-designed features. The autoencoder is one method that can be used for this purpose. However, for data sets with a high degree of noise, a large amount of the representational capacity in the autoencoder is used to minimize the reconstruction error for these noisy inputs. This paper proposes a method that improves the feature learning process by focusing on the task relevant information in the data. This selective attention is achieved by weighting the reconstruction error and reducing the influence of noisy inputs during the learning process. The proposed model is trained on a number of publicly available image data sets and the test error rate is compared to a standard sparse autoencoder and other methods, such as the denoising autoencoder and contractive autoencoder.

  • 20.
    Längkvist, Martin
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Learning Representations with a Dynamic Objective Sparse Autoencoder2012Konferensbidrag (Refereegranskat)
    Abstract [en]

    The main objective of an auto-encoder is to reconstruct the input signals via a feature representation of latent variables. The number of latent variables defines the representational capacity limit of the model. For data sets where some or all signals contain noise there is an unnecessary amount of capacity spent on trying to reconstruct these signals. One solution is to increase the number of hidden units to increase the capacity so that there will be enough capacity to capture the valuable information. Another solution is to pre-process the signals or perform a manual signal selection. In this paper, we propose a method that will dynamically change the objective function depending on the current performance of the model. This is done by weighting the objective function individually for each input unit in order to guide the feature leaning and decrease the influence that problematic signals have on the learning of features. We evaluate our method on various multidimensional time-series data sets and handwritten digit recognition data sets and compare our results with a standard sparse auto-encoder.

    Ladda ner fulltext (pdf)
    dosae
  • 21.
    Längkvist, Martin
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Not all signals are created equal: Dynamic objective auto-encoder for multivariate data2012Konferensbidrag (Övrigt vetenskapligt)
    Ladda ner fulltext (pdf)
    Not all signals are created equal: Dynamic objective auto-encoder for multivariate data
  • 22.
    Längkvist, Martin
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Unsupervised feature learning for electronic nose data applied to Bacteria Identification in Blood2011Konferensbidrag (Refereegranskat)
    Abstract [en]

    Electronic nose (e-nose) data represents multivariate time-series from an array of chemical gas sensors exposed to a gas. This data is a new data set for usewith deep learning methods, and is highly suitable since e-nose data is complexand difficult to interpret for human experts. Furthermore, this data set presentsa number of interesting challenges for deep learning architectures per se. In this work we present a first study of e-nose data classification using deep learningwhen testing for the presence of bacteria in blood and agar solutions. We showin this study that deep learning outperforms hand-selected strategy based methods which has been previously tried with the same data set.

    Ladda ner fulltext (pdf)
    fulltext
  • 23.
    Längkvist, Martin
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Karlsson, Lars
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Selective attention auto-encoder for automatic sleep staging2014Manuskript (preprint) (Övrigt vetenskapligt)
  • 24.
    Längkvist, Martin
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Persson, Andreas
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Learning Generative Image Manipulations from Language Instructions2020Konferensbidrag (Refereegranskat)
    Abstract [en]

    This paper studies whether a perceptual visual system can simulate human-like cognitive capabilities by training a computational model to predict the output of an action using language instruction. The aim is to ground action words such that an AI is able to generate an output image that outputs the effect of a certain action on an given object. The output of the model is a synthetic generated image that demonstrates the effect that the action has on the scene. This work combines an image encoder, language encoder, relational network, and image generator to ground action words, and then visualize the effect an action would have on a simulated scene. The focus in this work is to learn meaningful shared image and text representations for relational learning and object manipulation.

    Ladda ner fulltext (pdf)
    Learning Generative Image Manipulations from Language Instructions
  • 25.
    Neelakantan, Suraj
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Norell, Jesper
    Orexplore AB, Kista, Stockholm, Sweden.
    Hansson, Alexander
    Orexplore AB, Kista, Stockholm, Sweden.
    Längkvist, Martin
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Neural network approach for shape-based euhedral pyrite identification in X-ray CT data with adversarial unsupervised domain adaptation2024Ingår i: Applied Computing and Geosciences, E-ISSN 2590-1974, Vol. 21, artikel-id 100153Artikel i tidskrift (Refereegranskat)
    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.

  • 26.
    Paylar, Berkay
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Längkvist, Martin
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Jass, Jana
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Olsson, Per-Erik
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Utilization of Computer Classification Methods for Exposure Prediction and Gene Selection in Daphnia magna Toxicogenomics2023Ingår i: Biology, E-ISSN 2079-7737, Vol. 12, nr 5, artikel-id 692Artikel i tidskrift (Refereegranskat)
    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.

  • 27.
    Persson, Andreas
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Längkvist, Martin
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Learning Actions to Improve the Perceptual Anchoring of Object2017Ingår i: Frontiers in Robotics and AI, E-ISSN 2296-9144, Vol. 3, nr 76Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    In this paper, we examine how to ground symbols referring to objects in perceptual data from a robot system by examining object entities and their changes over time. In particular, we approach the challenge by 1) tracking and maintaining object entities over time; and 2) utilizing an artificial neural network to learn the coupling between words referring to actions and movement patterns of tracked object entities. For this purpose, we propose a framework which relies on the notations presented in perceptual anchoring. We further present a practical extension of the notation such that our framework can track and maintain the history of detected object entities. Our approach is evaluated using everyday objects typically found in a home environment. Our object classification module has the possibility to detect and classify over several hundred object categories. We demonstrate how the framework creates and maintains, both in space and time, representations of objects such as 'spoon' and 'coffee mug'. These representations are later used for training of different sequential learning algorithms in order to learn movement actions such as 'pour' and 'stir'. We finally exemplify how learned movements actions, combined with common-sense knowledge, further can be used to improve the anchoring process per se.

  • 28.
    Rahaman, G M Atiqur
    et al.
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Längkvist, Martin
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Loutfi, Amy
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    Deep Learning based Aerial Image Segmentation for Computing Green Area Factor2022Ingår i: 2022 10th European Workshop on Visual Information Processing (EUVIP), IEEE, 2022Konferensbidrag (Refereegranskat)
    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.

  • 29.
    Sjöqvist, Hugo
    et al.
    Department of Global Public Health Sciences, Karolinska Institutet, Solna, Sweden; Department ofStatistics, Örebro University, Örebro, Sweden.
    Längkvist, Martin
    Örebro universitet, Institutionen för naturvetenskap och teknik. Department of Computer Science.
    Javed, Farrukh
    Örebro universitet, Handelshögskolan vid Örebro Universitet. Department of Statistics.
    An Analysis of Fast Learning Methods for Classifying Forest Cover Types2020Ingår i: Applied Artificial Intelligence, ISSN 0883-9514, E-ISSN 1087-6545, Vol. 34, nr 10, s. 691-709Artikel i tidskrift (Refereegranskat)
    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.

1 - 29 av 29
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf