Umeå University's logo

umu.sePublications
Change search
Refine search result
1 - 6 of 6
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1.
    Fouladgar, Nazanin
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Alirezaie, Marjan
    Centre for Applied Autonomous Sensor Systems (AASS), Örebro University, Örebro, Sweden.
    Främling, Kary
    Umeå University, Faculty of Science and Technology, Department of Computing Science. School of Science and Technology, Aalto University, Espoo, Finland.
    CN-waterfall: a deep convolutional neural network for multimodal physiological affect detection2022In: Neural Computing & Applications, ISSN 0941-0643, E-ISSN 1433-3058, Vol. 34, no 3, p. 2157-2176Article in journal (Refereed)
    Abstract [en]

    Affective computing solutions, in the literature, mainly rely on machine learning methods designed to accurately detect human affective states. Nevertheless, many of the proposed methods are based on handcrafted features, requiring sufficient expert knowledge in the realm of signal processing. With the advent of deep learning methods, attention has turned toward reduced feature engineering and more end-to-end machine learning. However, most of the proposed models rely on late fusion in a multimodal context. Meanwhile, addressing interrelations between modalities for intermediate-level data representation has been largely neglected. In this paper, we propose a novel deep convolutional neural network, called CN-Waterfall, consisting of two modules: Base and General. While the Base module focuses on the low-level representation of data from each single modality, the General module provides further information, indicating relations between modalities in the intermediate- and high-level data representations. The latter module has been designed based on theoretically grounded concepts in the Explainable AI (XAI) domain, consisting of four different fusions. These fusions are mainly tailored to correlation- and non-correlation-based modalities. To validate our model, we conduct an exhaustive experiment on WESAD and MAHNOB-HCI, two publicly and academically available datasets in the context of multimodal affective computing. We demonstrate that our proposed model significantly improves the performance of physiological-based multimodal affect detection.

    Download full text (pdf)
    fulltext
  • 2.
    Gabi, Danlami
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science. Department of Computer Science, Kebbi State University of Science and Technology, Aliero, Nigeria.
    Dankolo, Nasiru Muhammad
    Department of Computer Science, Kebbi State University of Science and Technology, Aliero, Nigeria.
    Muslim, Abubakar Atiku
    Department of Computer Science, Kebbi State University of Science and Technology, Aliero, Nigeria.
    Abraham, Ajith
    Machine Intelligence Research Labs, Scientific Network for Innovation and Research Excellence, WA, Auburn, United States.
    Joda, Muhammad Usman
    Department of Mathematical Sciences, Bauchi State University Gadau, Bauchi, Nigeria.
    Zainal, Anazida
    Faculty of Engineering, School of Computing, Universiti Teknologi Malaysia, Johor Bahru, Malaysia.
    Zakaria, Zalmiyah
    Faculty of Engineering, School of Computing, Universiti Teknologi Malaysia, Johor Bahru, Malaysia.
    Dynamic scheduling of heterogeneous resources across mobile edge-cloud continuum using fruit fly-based simulated annealing optimization scheme2022In: Neural Computing & Applications, ISSN 0941-0643, E-ISSN 1433-3058, Vol. 34, p. 14085-14105Article in journal (Refereed)
    Abstract [en]

    Achieving sustainable profit advantage, cost reduction and resource utilization are always a bottleneck for resource providers, especially when trying to meet the computing needs of resource hungry applications in mobile edge-cloud (MEC) continuum. Recent research uses metaheuristic techniques to allocate resources to large-scale applications in MECs. However, some challenges attributed to the metaheuristic techniques include entrapment at the local optima caused by premature convergence and imbalance between the local and global searches. These may affect resource allocation in MECs if continually implemented. To address these concerns and ensure efficient resource allocation in MECs, we propose a fruit fly-based simulated annealing optimization scheme (FSAOS) to serve as a potential solution. In the proposed scheme, the simulated annealing is incorporated to balance between the global and local search and to overcome its premature convergence. We also introduce a trade-off factor to allow application owners to select the best service quality that will minimize their execution cost. Implementation of the FSAOS is carried out on EdgeCloudSim Simulator tool. Simulation results show that the FSAOS can schedule resources effectively based on tasks requirement by returning minimum makespan and execution costs, and achieve better resource utilization compared to the conventional fruit fly optimization algorithm and particle swarm optimization. To further unveil how efficient the FSAOSs, a statistical analysis based on 95% confidential interval is carried out. Numerical results show that FSAOS outperforms the benchmark schemes by achieving higher confidence level. This is an indication that the proposed FSAOS can provide efficient resource allocation in MECs while meeting customers’ aspirations as well as that of the resource providers.

    Download full text (pdf)
    fulltext
  • 3.
    Gabi, Danlami
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science. Department of Computer Science, Faculty of Science, Kebbi State University of Science and Technology, Aliero, Kebbi State, Nigeria.
    Ismail, Abdul Samad
    Zainal, Anazida
    Zakaria, Zalmiyah
    Abraham, Ajith
    Dankolo, Nasiru Muhammed
    Cloud customers service selection scheme based on improved conventional cat swarm optimization2020In: Neural Computing & Applications, ISSN 0941-0643, E-ISSN 1433-3058, Vol. 32, p. 14817-14838Article in journal (Refereed)
    Abstract [en]

    With growing demand on resources situated at the cloud datacenters, the need for customers' resource selection techniques becomes paramount in dealing with the concerns of resource inefficiency. Techniques such as metaheuristics are promising than the heuristics, most especially when handling large scheduling request. However, addressing certain limitations attributed to the metaheuristic such as slow convergence speed and imbalance between its local and global search could enable it become even more promising for customers service selection. In this work, we propose a cloud customers service selection scheme called Dynamic Multi-Objective Orthogonal Taguchi-Cat (DMOOTC). In the proposed scheme, avoidance of local entrapment is achieved by not only increasing its convergence speed, but balancing between its local and global search through the incorporation of Taguchi orthogonal approach. To enable the scheme to meet customers' expectations, Pareto dominant strategy is incorporated providing better options for customers in selecting their service preferences. The implementation of our proposed scheme with that of the benchmarked schemes is carried out on CloudSim simulator tool. With two scheduling scenarios under consideration, simulation results show for the first scenario, our proposed DMOOTC scheme provides better service choices with minimum total execution time and cost (with up to 42.87%, 35.47%, 25.49% and 38.62%, 35.32%, 25.56% reduction) and achieves 21.64%, 18.97% and 13.19% improvement for the second scenario in terms of execution time compared to that of the benchmarked schemes. Similarly, statistical results based on 95% confidence interval for the whole scheduling scheme also show that our proposed scheme can be much more reliable than the benchmarked scheme. This is an indication that the proposed DMOOTC can meet customers' expectations while providing guaranteed performance of the whole cloud computing environment.

    Download full text (pdf)
    fulltext
  • 4.
    Mubashar, Mehreen
    et al.
    Department of Electrical and Computer Engineering, COMSATS University Islamabad, Abbottabad Campus, Abbottabad, Pakistan.
    Ali, Hazrat
    Umeå University, Faculty of Medicine, Department of Radiation Sciences, Radiation Physics. Department of Electrical and Computer Engineering, COMSATS University Islamabad, Abbottabad Campus, Abbottabad, Pakistan.
    Grönlund, Christer
    Umeå University, Faculty of Medicine, Department of Radiation Sciences, Radiation Physics.
    Azmat, Shoaib
    Department of Electrical and Computer Engineering, COMSATS University Islamabad, Abbottabad Campus, Abbottabad, Pakistan.
    R2U++: a multiscale recurrent residual U-Net with dense skip connections for medical image segmentation2022In: Neural Computing & Applications, ISSN 0941-0643, E-ISSN 1433-3058, Vol. 34, no 20, p. 17723-17739Article in journal (Refereed)
    Abstract [en]

    U-Net is a widely adopted neural network in the domain of medical image segmentation. Despite its quick embracement by the medical imaging community, its performance suffers on complicated datasets. The problem can be ascribed to its simple feature extracting blocks: encoder/decoder, and the semantic gap between encoder and decoder. Variants of U-Net (such as R2U-Net) have been proposed to address the problem of simple feature extracting blocks by making the network deeper, but it does not deal with the semantic gap problem. On the other hand, another variant UNET++ deals with the semantic gap problem by introducing dense skip connections but has simple feature extraction blocks. To overcome these issues, we propose a new U-Net based medical image segmentation architecture R2U++. In the proposed architecture, the adapted changes from vanilla U-Net are: (1) the plain convolutional backbone is replaced by a deeper recurrent residual convolution block. The increased field of view with these blocks aids in extracting crucial features for segmentation which is proven by improvement in the overall performance of the network. (2) The semantic gap between encoder and decoder is reduced by dense skip pathways. These pathways accumulate features coming from multiple scales and apply concatenation accordingly. The modified architecture has embedded multi-depth models, and an ensemble of outputs taken from varying depths improves the performance on foreground objects appearing at various scales in the images. The performance of R2U++ is evaluated on four distinct medical imaging modalities: electron microscopy, X-rays, fundus, and computed tomography. The average gain achieved in IoU score is 1.5 ± 0.37% and in dice score is 0.9 ± 0.33% over UNET++, whereas, 4.21 ± 2.72 in IoU and 3.47 ± 1.89 in dice score over R2U-Net across different medical imaging segmentation datasets.

    Download full text (pdf)
    fulltext
  • 5.
    Persiani, Michele
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Hellström, Thomas
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Policy regularization for legible behavior2023In: Neural Computing & Applications, ISSN 0941-0643, E-ISSN 1433-3058, Vol. 35, no 23, p. 16781-16790Article in journal (Refereed)
    Abstract [en]

    In this paper we propose a method to augment a Reinforcement Learning agent with legibility. This method is inspired by the literature in Explainable Planning and allows to regularize the agent’s policy after training, and without requiring to modify its learning algorithm. This is achieved by evaluating how the agent’s optimal policy may produce observations that would make an observer model to infer a wrong policy. In our formulation, the decision boundary introduced by legibility impacts the states in which the agent’s policy returns an action that is non-legible because having high likelihood also in other policies. In these cases, a trade-off between such action, and legible/sub-optimal action is made. We tested our method in a grid-world environment highlighting how legibility impacts the agent’s optimal policy, and gathered both quantitative and qualitative results. In addition, we discuss how the proposed regularization generalizes over methods functioning with goal-driven policies, because applicable to general policies of which goal-driven policies are a special case.

    Download full text (pdf)
    fulltext
  • 6.
    Tran, Khanh-Tung
    et al.
    AI Center, FPT Software Company Limited, Hanoi, Viet Nam.
    Vu, Xuan-Son
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Nguyen, Khuong
    AI Center, FPT Software Company Limited, Hanoi, Viet Nam.
    Nguyen, Hoang D.
    School of Computer Science and Information Technology, University College Cork, Cork, Ireland.
    NeuProNet: neural profiling networks for sound classification2024In: Neural Computing & Applications, ISSN 0941-0643, E-ISSN 1433-3058, Vol. 36, no 11, p. 5873-5887Article in journal (Refereed)
    Abstract [en]

    Real-world sound signals exhibit various aspects of grouping and profiling behaviors, such as being recorded from identical sources, having similar environmental settings, or encountering related background noises. In this work, we propose novel neural profiling networks (NeuProNet) capable of learning and extracting high-level unique profile representations from sounds. An end-to-end framework is developed so that any backbone architectures can be plugged in and trained, achieving better performance in any downstream sound classification tasks. We introduce an in-batch profile grouping mechanism based on profile awareness and attention pooling to produce reliable and robust features with contrastive learning. Furthermore, extensive experiments are conducted on multiple benchmark datasets and tasks to show that neural computing models under the guidance of our framework gain significant performance gaps across all evaluation tasks. Particularly, the integration of NeuProNet surpasses recent state-of-the-art (SoTA) approaches on UrbanSound8K and VocalSound datasets with statistically significant improvements in benchmarking metrics, up to 5.92% in accuracy compared to the previous SoTA method and up to 20.19% compared to baselines. Our work provides a strong foundation for utilizing neural profiling for machine learning tasks.

    Download full text (pdf)
    fulltext
1 - 6 of 6
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf