Umeå University's logo

umu.sePublikasjoner
Endre søk
Begrens søket
1234567 1 - 50 of 1739
RefereraExporteraLink til resultatlisten
Permanent link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Treff pr side
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sortering
  • Standard (Relevans)
  • Forfatter A-Ø
  • Forfatter Ø-A
  • Tittel A-Ø
  • Tittel Ø-A
  • Type publikasjon A-Ø
  • Type publikasjon Ø-A
  • Eldste først
  • Nyeste først
  • Skapad (Eldste først)
  • Skapad (Nyeste først)
  • Senast uppdaterad (Eldste først)
  • Senast uppdaterad (Nyeste først)
  • Disputationsdatum (tidligste først)
  • Disputationsdatum (siste først)
  • Standard (Relevans)
  • Forfatter A-Ø
  • Forfatter Ø-A
  • Tittel A-Ø
  • Tittel Ø-A
  • Type publikasjon A-Ø
  • Type publikasjon Ø-A
  • Eldste først
  • Nyeste først
  • Skapad (Eldste først)
  • Skapad (Nyeste først)
  • Senast uppdaterad (Eldste først)
  • Senast uppdaterad (Nyeste først)
  • Disputationsdatum (tidligste først)
  • Disputationsdatum (siste først)
Merk
Maxantalet träffar du kan exportera från sökgränssnittet är 250. Vid större uttag använd dig av utsökningar.
  • 1.
    Abdelraouf, Hussein
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    LARGE LANGUAGE MODELS ADAPTED TO SWEDISH OF THE 1920S2023Independent thesis Advanced level (degree of Master (Two Years)), 20 poäng / 30 hpOppgave
    Abstract [en]

    Large Language Models typically perform best when there is a lot of data to train on. An interesting question is how such models perform in less dominant languages (e.g., Swedish) and over domains of historical interest where less modern words and phrasings are used. Specifically, how can existing language models for current usage be adapted to get the best question-answering results when applied over such historical domains? In this Master's thesis, we will use domain adaption on three different pre-trained Swedish NLP language models: BERT base Swedish Cased SQuAD Experimental, GPT-SW3, and IBM Watson. We will fine-tune these models on the specific domain of Vasaloppet's 100-year-old articles to evaluate if the models will have difficulties predicting results from a Swedish source that is a century old. We will evaluate how well these models perform on question answering and report results and lessons learned. 

  • 2.
    Abedan Kondori, Farid
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.
    Yousefi, Shahrouz
    KTH Royal Institute of Technology, Department of Media Technology and Interaction Design.
    Liu, Li
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.
    Li, Haibo
    KTH Royal Institute of Technology, Department of Media Technology and Interaction Design.
    Head operated electric wheelchair2014Inngår i: IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI 2014), IEEE , 2014, s. 53-56Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Currently, the most common way to control an electric wheelchair is to use joystick. However, there are some individuals unable to operate joystick-driven electric wheelchairs due to sever physical disabilities, like quadriplegia patients. This paper proposes a novel head pose estimation method to assist such patients. Head motion parameters are employed to control and drive an electric wheelchair. We introduce a direct method for estimating user head motion, based on a sequence of range images captured by Kinect. In this work, we derive new version of the optical flow constraint equation for range images. We show how the new equation can be used to estimate head motion directly. Experimental results reveal that the proposed system works with high accuracy in real-time. We also show simulation results for navigating the electric wheelchair by recovering user head motion.

  • 3.
    Abedin, Md Reaz Ashraful
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Bensch, Suna
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Hellström, Thomas
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Self-supervised language grounding by active sensing combined with Internet acquired images and text2017Inngår i: Proceedings of the Fourth International Workshop on Recognition and Action for Scene Understanding (REACTS2017) / [ed] Jorge Dias George Azzopardi, Rebeca Marf, Málaga: REACTS , 2017, s. 71-83Konferansepaper (Fagfellevurdert)
    Abstract [en]

    For natural and efficient verbal communication between a robot and humans, the robot should be able to learn names and appearances of new objects it encounters. In this paper we present a solution combining active sensing of images with text based and image based search on the Internet. The approach allows the robot to learn both object name and how to recognise similar objects in the future, all self-supervised without human assistance. One part of the solution is a novel iterative method to determine the object name using image classi- fication, acquisition of images from additional viewpoints, and Internet search. In this paper, the algorithmic part of the proposed solution is presented together with evaluations using manually acquired camera images, while Internet data was acquired through direct and reverse image search with Google, Bing, and Yandex. Classification with multi-classSVM and with five different features settings were evaluated. With five object classes, the best performing classifier used a combination of Pyramid of Histogram of Visual Words (PHOW) and Pyramid of Histogram of Oriented Gradient (PHOG) features, and reached a precision of 80% and a recall of 78%.

    Fulltekst (pdf)
    fulltext
  • 4.
    Adewole, Kayode S.
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Department of Computer Science, University of Ilorin, Ilorin, Nigeria.
    Torra, Vicenç
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    DFTMicroagg: a dual-level anonymization algorithm for smart grid data2022Inngår i: International Journal of Information Security, ISSN 1615-5262, E-ISSN 1615-5270, Vol. 21, s. 1299-1321Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    The introduction of advanced metering infrastructure (AMI) smart meters has given rise to fine-grained electricity usage data at different levels of time granularity. AMI collects high-frequency daily energy consumption data that enables utility companies and data aggregators to perform a rich set of grid operations such as demand response, grid monitoring, load forecasting and many more. However, the privacy concerns associated with daily energy consumption data has been raised. Existing studies on data anonymization for smart grid data focused on the direct application of perturbation algorithms, such as microaggregation, to protect the privacy of consumers. In this paper, we empirically show that reliance on microaggregation alone is not sufficient to protect smart grid data. Therefore, we propose DFTMicroagg algorithm that provides a dual level of perturbation to improve privacy. The algorithm leverages the benefits of discrete Fourier transform (DFT) and microaggregation to provide additional layer of protection. We evaluated our algorithm on two publicly available smart grid datasets with millions of smart meters readings. Experimental results based on clustering analysis using k-Means, classification via k-nearest neighbor (kNN) algorithm and mean hourly energy consumption forecast using Seasonal Auto-Regressive Integrated Moving Average with eXogenous (SARIMAX) factors model further proved the applicability of the proposed method. Our approach provides utility companies with more flexibility to control the level of protection for their published energy data.

    Fulltekst (pdf)
    fulltext
  • 5.
    Adewole, Kayode S.
    et al.
    Department of Computer Science and Media Technology, Malmö University, Sweden; Department of Computer Science, University of Ilorin, Ilorin, Nigeria.
    Torra, Vicenç
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Energy disaggregation risk resilience through microaggregation and discrete Fourier transform2024Inngår i: Information Sciences, ISSN 0020-0255, E-ISSN 1872-6291, Vol. 662, artikkel-id 120211Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    Progress in the field of Non-Intrusive Load Monitoring (NILM) has been attributed to the rise in the application of artificial intelligence. Nevertheless, the ability of energy disaggregation algorithms to disaggregate different appliance signatures from aggregated smart grid data poses some privacy issues. This paper introduces a new notion of disclosure risk termed energy disaggregation risk. The performance of Sequence-to-Sequence (Seq2Seq) NILM deep learning algorithm along with three activation extraction methods are studied using two publicly available datasets. To understand the extent of disclosure, we study three inference attacks on aggregated data. The results show that Variance Sensitive Thresholding (VST) event detection method outperformed the other two methods in revealing households' lifestyles based on the signature of the appliances. To reduce energy disaggregation risk, we investigate the performance of two privacy-preserving mechanisms based on microaggregation and Discrete Fourier Transform (DFT). Empirically, for the first scenario of inference attack on UK-DALE, VST produces disaggregation risks of 99%, 100%, 89% and 99% for fridge, dish washer, microwave, and kettle respectively. For washing machine, Activation Time Extraction (ATE) method produces a disaggregation risk of 87%. We obtain similar results for other inference attack scenarios and the risk reduces using the two privacy-protection mechanisms.

    Fulltekst (pdf)
    fulltext
  • 6.
    Adewole, Kayode Sakariyah
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Department of Computer Science, University of Ilorin, Ilorin, Nigeria.
    Torra, Vicenç
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Privacy issues in smart grid data: from energy disaggregation to disclosure risk2022Inngår i: Database and expert systems applications: 33rd international conference, DEXA 2022, Vienna, Austria, August 22–24, 2022, proceedings, part I / [ed] Christine Strauss; Alfredo Cuzzocrea; Gabriele Kotsis; A Min Tjoa; Ismail Khalil, Springer, 2022, s. 71-84Konferansepaper (Fagfellevurdert)
    Abstract [en]

    The advancement in artificial intelligence (AI) techniques has given rise to the success rate recorded in the field of Non-Intrusive Load Monitoring (NILM). The development of robust AI and machine learning algorithms based on deep learning architecture has enabled accurate extraction of individual appliance load signature from aggregated energy data. However, the success rate of NILM algorithm in disaggregating individual appliance load signature in smart grid data violates the privacy of the individual household lifestyle. This paper investigates the performance of Sequence-to-Sequence (Seq2Seq) deep learning NILM algorithm in predicting the load signature of appliances. Furthermore, we define a new notion of disclosure risk to understand the risk associated with individual appliances in aggregated signals. Two publicly available energy disaggregation datasets have been considered. We simulate three inference attack scenarios to better ascertain the risk of publishing raw energy data. In addition, we investigate three activation extraction methods for appliance event detection. The results show that the disclosure risk associated with releasing smart grid data in their original form is on the high side. Therefore, future privacy protection mechanisms should devise efficient methods to reduce this risk.

  • 7.
    Adewole, Kayode Sakariyah
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Department of Computer Science and Media Technology, Malmö University, Malmö, Sweden; Department of Computer Science, University of Ilorin, Ilorin, Nigeria.
    Torra, Vicenç
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Department of Computer Science and Media Technology, Malmö University, Malmö, Sweden.
    Privacy protection of synthetic smart grid data simulated via generative adversarial networks2023Inngår i: Proceedings of the 20th international conference on security and cryptography, SECRYPT 2023 / [ed] DiVimercati, SD; Samarati, P, SciTePress, 2023, s. 279-286Konferansepaper (Fagfellevurdert)
    Abstract [en]

    The development in smart meter technology has made grid operations more efficient based on fine-grained electricity usage data generated at different levels of time granularity. Consequently, machine learning algorithms have benefited from these data to produce useful models for important grid operations. Although machine learning algorithms need historical data to improve predictive performance, these data are not readily available for public utilization due to privacy issues. The existing smart grid data simulation frameworks generate grid data with implicit privacy concerns since the data are simulated from a few real energy consumptions that are publicly available. This paper addresses two issues in smart grid. First, it assesses the level of privacy violation with the individual household appliances based on synthetic household aggregate loads consumption. Second, based on the findings, it proposes two privacy-preserving mechanisms to reduce this risk. Three inference attacks are simulated and the results obtained confirm the efficacy of the proposed privacy-preserving mechanisms.

    Fulltekst (pdf)
    fulltext
  • 8.
    Adlerborn, Björn
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    Parallel Algorithms and Library Software for the Generalized Eigenvalue Problem on Distributed Memory Computer Systems2016Licentiatavhandling, med artikler (Annet vitenskapelig)
    Abstract [en]

    We present and discuss algorithms and library software for solving the generalized non-symmetric eigenvalue problem (GNEP) on high performance computing (HPC) platforms with distributed memory. Such problems occur frequently in computational science and engineering, and our contributions make it possible to solve GNEPs fast and accurate in parallel using state-of-the-art HPC systems. A generalized eigenvalue problem corresponds to finding scalars y and vectors x such that Ax = yBx, where A and B are real square matrices. A nonzero x that satisfies the GNEP equation is called an eigenvector of the ordered pair (A,B), and the scalar y is the associated eigenvalue. Our contributions include parallel algorithms for transforming a matrix pair (A,B) to a generalized Schur form (S,T), where S is quasi upper triangular and T is upper triangular. The eigenvalues are revealed from the diagonals of S and T. Moreover, for a specified set of eigenvalues an associated pair of deflating subspaces can be computed, which typically is requested in various applications. In the first stage the matrix pair (A,B) is reduced to a Hessenberg-triangular form (H,T), where H is upper triangular with one nonzero subdiagonal and T is upper triangular, in a finite number of steps. The second stage reduces the matrix pair further to generalized Schur form (S,T) using an iterative QZ-based method. Outgoing from a one-stage method for the reduction from (A,B) to (H,T), a novel parallel algorithm is developed. In brief, a delayed update technique is applied to several partial steps, involving low level operations, before associated accumulated transformations are applied in a blocked fashion which together with a wave-front task scheduler makes the algorithm scale when running in a parallel setting. The potential presence of infinite eigenvalues makes a generalized eigenvalue problem ill-conditioned. Therefore the parallel algorithm for the second stage, reduction to (S,T) form, continuously scan for and robustly deflate infinite eigenvalues. This will reduce the impact so that they do not interfere with other real eigenvalues or are misinterpreted as real eigenvalues. In addition, our parallel iterative QZ-based algorithm makes use of multiple implicit shifts and an aggressive early deflation (AED) technique, which radically speeds up the convergence. The multi-shift strategy is based on independent chains of so called coupled bulges and computational windows which is an important source of making the algorithm scalable. The parallel algorithms have been implemented in state-of-the-art library software. The performance is demonstrated and evaluated using up to 1600 CPU cores for problems with matrices as large as 100000 x 100000. Our library software is described in a User Guide. The software is, optionally, tunable via a set of parameters for various thresholds and buffer sizes etc. These parameters are discussed, and recommended values are specified which should result in reasonable performance on HPC systems similar to the ones we have been running on.

    Fulltekst (pdf)
    fulltext
  • 9.
    Adlerborn, Björn
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    Kjelgaard Mikkelsen, Carl Christian
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    Karlsson, Lars
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    Kågström, Bo
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    Towards Highly Parallel and Compute-Bound Computation of Eigenvectors of Matrices in Schur Form2017Rapport (Annet vitenskapelig)
    Abstract [en]

    In this paper we discuss the problem of computing eigenvectors for matrices in Schur form using parallel computing. We develop a new parallel algorithm and report on the performance of our MPI based implementation. We have also implemented a new parallel algorithm for scaling during the backsubstitution phase. We have increased the arithmetic intensity by interleaving the compution of several eigenvectors and by merging the backward substitution and the back-transformation of the eigenvector computation.

    Fulltekst (pdf)
    fulltext
  • 10.
    Adlerborn, Björn
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    Kågström, Bo
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Högpresterande beräkningscentrum norr (HPC2N).
    Kressner, Daniel
    A parallel QZ algorithm for distributed memory HPC systems2014Inngår i: SIAM Journal on Scientific Computing, ISSN 1064-8275, E-ISSN 1095-7197, Vol. 36, nr 5, s. C480-C503Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    Appearing frequently in applications, generalized eigenvalue problems represent one of the core problems in numerical linear algebra. The QZ algorithm of Moler and Stewart is the most widely used algorithm for addressing such problems. Despite its importance, little attention has been paid to the parallelization of the QZ algorithm. The purpose of this work is to fill this gap. We propose a parallelization of the QZ algorithm that incorporates all modern ingredients of dense eigensolvers, such as multishift and aggressive early deflation techniques. To deal with (possibly many) infinite eigenvalues, a new parallel deflation strategy is developed. Numerical experiments for several random and application examples demonstrate the effectiveness of our algorithm on two different distributed memory HPC systems.

  • 11.
    af Geijerstam, Klas
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Online graph based latency estimation of microservice applications in a FAAS environment2021Independent thesis Advanced level (degree of Master (Two Years)), 20 poäng / 30 hpOppgave
    Abstract [en]

    Function-as-a-Service (FaaS) is an increasingly common platform for many kinds of applications and services, replacing the need to maintain and setup hardware or virtual machines to host functionality in the cloud. The billing model for FaaS is commonly based on actual usage, which makes the ability to estimate the performance and latency of an application before invoking it valuable. This thesis evaluates if previously defined algorithms for offline latency estimation, can be adapted to work with online data. Performing online estimation of latency potentially enables cheaper estimations, as no extra executions are neccessary, and latency estimation of applications and functions that can not be executed spu- riously. The experiments show that for a set of test applications, the previously defined algorithms can achieve greater than 95% accuracy, and that a non-graph based estimation using exponential moving average can achieve greater than 98% accuracy. 

    Fulltekst (pdf)
    fulltext
  • 12.
    Ahlman Bohm, Jacob
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Minimizing initial margin requirements using computational optimization2023Independent thesis Advanced level (degree of Master (Two Years)), 20 poäng / 30 hpOppgave
    Abstract [en]

    Trading contracts with future commitments requires posting a collateral, called initial margin requirement, to cover associated risks. Differences in estimating those risks and varying risk appetites can however lead to identical contracts having different initial margin requirements at different market places. This creates a potential for minimizing those requirements by reallocating contracts.

    The task of minimizing the requirement is identified as a black-box optimization problem with constraints. The aim of this project was to investigate that optimization problem, how it can best be tackled, and comparing different techniques for doing so. Based on the results and obstacles encountered along the way, some guidelines are then outlined to provide assistance for whomever is interested in solving this or similar problems.

    The project consisted both of a literature study to examine existing knowledge within the subject of optimization, and an implementation phase to empirically test how well that knowledge can be put to use in this case. During the latter various algorithms were tested in a number of different scenarios. Focus was put on practical aspects that could be important in a real situation, such as how much they could decrease the initial margin requirement, execution time, and ease of implementation.

    As part of the literature study, three algorithms were found which were evaluated further: simulated annealing, differential evolution, and particle swarm optimization. They all work without prior knowledge of the function to be optimized, and are thus suitable for black-box optimization.

    Results from the implementation part showed largely similar performance between all three algorithms, indicating that other aspects such as ease of implementation or parallelization potential can be more important to consider when choosing which one to use. They were all well able to optimize different portfolios in a number of different cases. However, in more complex situations they required much more time to do so, showing a potential need to speed up the process.

    Fulltekst (pdf)
    fulltext
  • 13.
    Ahlskog, Johanna
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Human-Multi-Drone Interaction in Search and Rescue Systems under High Cognitive Workload2024Independent thesis Advanced level (degree of Master (Two Years)), 20 poäng / 30 hpOppgave
    Abstract [en]

    Unmanned Aerial Vehicles (UAV), often referred to as drones, have seen increased use in search and rescue (SAR) missions. Traditionally, these missions involve manual control of each drone for aerial surveillance. As UAV autonomy progresses, the next phase in drone technology consists of a shift to autonomous collaborative multi-drone operations, where drones function collectively in swarms. A significant challenge lies in designing user interfaces that can effectively support UAV pilots in their mission without an overload of information from each drone and of their surroundings.

    This thesis evaluates important human factors, such as situational awareness (SA) and cognitive workload, within complex search and rescue scenarios, with the goal of increasing trust in multi-drone systems through the design and testing of various components. Conducting these user studies aims to generate insights for the future design of multi-drone systems.

    Two prototypes were developed with a multi-drone user interface, and simulated a stressful search and rescue mission with high cognitive workload. In the second prototype, a heatmap guided UAV pilots based on the lost person model. The prototypes were tested in a conducted user study with experienced UAV pilots in different SAR organizations across Sweden.

    The results showed variability in SA while monitoring drone swarms, depending on user interface components and SA levels. The prototypes caused significant cognitive workload, slightly reduced in the heatmap-equipped prototype. Furthermore, there was a marginal increase in trust observed in the prototype with the heatmap. Notably, a lack of manual control raised challenges for the majority of participants and many desired features were suggested by participants. These early expert insights can serve as a starting point for future development of multi-drone systems.

    Fulltekst (pdf)
    fulltext
  • 14.
    Ahmad, Farooq
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Lindgren, Helena
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Selection of foundational ontology for collaborative knowledge modeling in healthcare domain2010Inngår i: Artificial intelligence: methodology, systems, and applications / [ed] Dicheva, Darina; Dochev, Danail, Springer Berlin/Heidelberg, 2010, s. 261-262Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Ontology design is an important process for structuring knowledge to be reused in different projects in the health domain. In this paper, we describe an ontology design for the collaborative knowledge building system ACKTUS to be used for developing personalized knowledge applications for different domains. Different foundational ontologies were compared with respect to selected criteria considered vital for the project, such as modularity and descriptiveness.

  • 15.
    Ahmad, Sabtain
    et al.
    Vienna University of Technology, Vienna, Austria.
    Aral, Atakan
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. University of Vienna, Vienna, Austria.
    Hierarchical federated transfer learning: a multi-cluster approach on the computing continuum2023Inngår i: 2023 international conference on machine learning and applications (ICMLA), IEEE, 2023, s. 1163-1168Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Federated Learning (FL) involves training models over a set of geographically distributed users. We address the problem where a single global model is not enough to meet the needs of geographically distributed heterogeneous clients. This setup captures settings where different groups of users have their own objectives however, users based on geographical location or task similarity, can be grouped together and by inter-cluster knowledge they can leverage the strength in numbers and better generalization in order to perform more efficient FL. We introduce a Hierarchical Multi-Cluster Computing Continuum for Federated Learning Personalization (HC3FL) to cluster similar clients and train one edge model per cluster. HC3FL incorporates federated transfer learning to enhance the performance of edge models by leveraging a global model that captures collective knowledge from all edge models. Furthermore, we introduce dynamic clustering based on task similarity to handle client drift and to dynamically recluster mobile (non-stationary) clients. We evaluate the HC3FL approach through extensive experiments on real-world datasets. The results demonstrate that our approach effectively improves the performance of edge models compared to traditional FL approaches.

  • 16.
    Ahmad, Sabtain
    et al.
    Institute of Information Systems Engineering, Vienna University of Technology, Vienna, Austria.
    Uyanık, Halit
    Department of Computer Engineering, Istanbul Technical University, Istanbul, Turkey.
    Ovatman, Tolga
    Department of Computer Engineering, Istanbul Technical University, Istanbul, Turkey.
    Sandıkkaya, Mehmet Tahir
    Department of Computer Engineering, Istanbul Technical University, Istanbul, Turkey.
    De Maio, Vincenzo
    Institute of Information Systems Engineering, Vienna University of Technology, Vienna, Austria.
    Brandić, Ivona
    Institute of Information Systems Engineering, Vienna University of Technology, Vienna, Austria.
    Aral, Atakan
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Sustainable environmental monitoring via energy and information efficient multi-node placement2023Inngår i: IEEE Internet of Things Journal, ISSN 2327-4662, Vol. 10, nr 24, s. 22065-22079Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    The Internet of Things is gaining traction for sensing and monitoring outdoor environments such as water bodies, forests, or agricultural lands. Sustainable deployment of sensors for environmental sampling is a challenging task because of the spatial and temporal variation of the environmental attributes to be monitored, the lack of the infrastructure to power the sensors for uninterrupted monitoring, and the large continuous target environment despite the sparse and limited sampling locations. In this paper, we present an environment monitoring framework that deploys a network of sensors and gateways connected through low-power, long-range networking to perform reliable data collection. The three objectives correspond to the optimization of information quality, communication capacity, and sustainability. Therefore, the proposed environment monitoring framework consists of three main components: (i) to maximize the information collected, we propose an optimal sensor placement method based on QR decomposition that deploys sensors at information- and communication-critical locations; (ii) to facilitate the transfer of big streaming data and alleviate the network bottleneck caused by low bandwidth, we develop a gateway configuration method with the aim to reduce the deployment and communication costs; and (iii) to allow sustainable environmental monitoring, an energy-aware optimization component is introduced. We validate our method by presenting a case study for monitoring the water quality of the Ergene River in Turkey. Detailed experiments subject to real-world data show that the proposed method is both accurate and efficient in monitoring a large environment and catching up with dynamic changes.

    Fulltekst (pdf)
    fulltext
  • 17.
    Ahmetaj, Shqiponja
    et al.
    TU Wien, Vienna, Austria; WU Wien, Vienna, Austria.
    David, Robert
    WU Wien, Vienna, Austria; Semantic Web Company, Vienna, Austria.
    Polleres, Axel
    WU Wien, Vienna, Austria; Complexity Science Hub Vienna, Vienna, Austria.
    Šimkus, Mantas
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. TU Wien, Vienna, Austria.
    Repairing SHACL constraint violations using answer set programming2022Inngår i: The Semantic Web –ISWC 2022: 21st International Semantic Web Conference, Virtual Event, October 23–27, 2022 : Proceedings / [ed] Ulrike Sattler; Aidan Hogan; Maria Keet; Valentina Presutti; João Paulo A. Almeida; Hideaki Takeda; Pierre Monnin; Giuseppe Pirrò; Claudia d’Amato, Springer, 2022, s. 375-391Konferansepaper (Fagfellevurdert)
    Abstract [en]

    The Shapes Constraint Language (SHACL) is a recent W3C recommendation for validating RDF graphs against shape constraints to be checked on target nodes of the data graph. The standard also describes the notion of validation reports for data graphs that violate given constraints, which aims to provide feedback on how the data graph can be fixed to satisfy the constraints. Since the specification left it open to SHACL processors to define such explanations, a recent work proposed the use of explanations in the style of database repairs, where a repair is a set of additions to or deletions from the data graph so that the resulting graph validates against the constraints. In this paper, we study such repairs for non-recursive SHACL, the largest fragment of SHACL that is fully defined in the specification. We propose an algorithm to compute repairs by encoding the explanation problem – using Answer Set Programming (ASP) – into a logic program, the answer sets of which correspond to (minimal) repairs. We then study a scenario where it is not possible to simultaneously repair all the targets, which may be often the case due to overall unsatisfiability or conflicting constraints. We introduce a relaxed notion of validation, which allows to validate a (maximal) subset of the targets and adapt the ASP translation to take into account this relaxation. Our implementation in Clingo is – to the best of our knowledge – the first implementation of a repair generator for SHACL.

  • 18.
    Ahmetaj, Shqiponja
    et al.
    TU Wien, Austria.
    Löhnert, Bianca
    TU Wien, Austria.
    Ortiz, Magdalena
    TU Wien, Austria.
    Šimkus, Mantas
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. TU Wien, Austria.
    Magic Shapes for SHACL Validation2022Inngår i: Proceedings of the VLDB Endowment, E-ISSN 2150-8097, Vol. 15, nr 10, s. 2284-2296Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    A key prerequisite for the successful adoption of the Shapes Constraint Language (SHACL)—the W3C standardized constraint language for RDF graphs—is the availability of automated tools that efficiently validate targeted constraints (known as shapes graphs) over possibly very large RDF graphs. There are already significant efforts to produce optimized engines for SHACL validation, but they focus on restricted fragments of SHACL. For unrestricted SHACL, that is SHACL with unrestricted recursion and negation, there is no validator beyond a proof-of-concept prototype, and existing techniques are inherently incompatible with the goal-driven approaches being pursued by existing validators. Instead they require a global computation on the entire data graph that is not only computationally very costly, but also brittle, and can easily result in validation failures due to conflicts that are irrelevant to the validation targets. To address these challenges, we present a ‘magic’ transformation— based on Magic Sets as known from Logic Programming—that transforms a SHACL shapes graph S into a new shapes graph S′ whose validation considers only the relevant neighbourhood of the targeted nodes. The new S′ is equivalent to S whenever there are no conflicts between the constraints and the data, and in case the validation of S fails due to conflicts that are irrelevant to the target, S′ may still admit a lazy, target-oriented validation. We implement the algorithm and run preliminary experiments, showing our approach can be a stepping stone towards validators for full SHACL, and that it can significantly improve the performance of the only prototype validator that currently supports full recursion and negation.

    Fulltekst (pdf)
    fulltext
  • 19.
    Ahmetaj, Shqiponja
    et al.
    Technical University of Vienna, Wien, Austria.
    Ortiz, Magdalena
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Oudshoorn, Anouk M.
    Technical University of Vienna, Wien, Austria.
    Šimkus, Mantas
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Reconciling SHACL and ontologies: semantics and validation via rewriting2023Inngår i: Proceedings of the 36th international workshop on Description Logics (DL 2023) / [ed] Oliver Kutz; Carsten Lutz; Ana Ozaki, CEUR-WS , 2023Konferansepaper (Fagfellevurdert)
    Abstract [en]

    This extended abstract summarizes our recent work [1] on SHACL validation in the presence of OWL 2 QL ontologies. To overcome the challenge posed by the non-monotonic behavior of SHACL constraints, we propose a new intuitive validation semantics and a rewriting algorithm that embeds the effects of the ontological axioms into the SHACL constraints. We analyze the complexity of validation in this setting.

    Fulltekst (pdf)
    fulltext
  • 20.
    Ahmetaj, Shqiponja
    et al.
    Tu Wien, Austria.
    Ortiz, Magdalena
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Oudshoorn, Anouk
    Tu Wien, Austria.
    Šimkus, Mantas
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Reconciling SHACL and ontologies: semantics and validation via rewriting2023Inngår i: ECAI 2023 / [ed] Kobi Gal; Ann Nowé; Grzegorz J. Nalepa; Roy Fairstein; Roxana Rădulescu, IOS Press, 2023, s. 27-35Konferansepaper (Fagfellevurdert)
    Abstract [en]

    OWL and SHACL are two prominent W3C standards for managing RDF graphs, the data model of the Web. They are used for different purposes and make different assumptions about the completeness of data: SHACL is used for expressing integrity constraints on complete data, while OWL allows inferring implicit facts from incomplete data; SHACL reasoners perform validation, while OWL reasoners do logical inference. Integrating these two tasks into one uniform approach is a relevant but challenging problem. The SHACL standard envisions graph validation in combination with OWL entailment, but it does not provide technical guidance on how to realize this. To address this problem, we propose a new intuitive semantics for validating SHACL constraints with OWL 2 QL ontologies based on a suitable notion of the chase. We propose an algorithm that rewrites a set of recursive SHACL constraints (with stratified negation) and an OWL 2 QL ontology into a stand-alone set of SHACL constraints that preserves validation for every input graph, which can in turn be evaluated using an off-the-shelf SHACL validator. We show that validation in this setting is EXPTIME-complete in combined complexity, but only PTIME-complete in data complexity, i.e., if the constraints and the ontology are fixed.

    Fulltekst (pdf)
    fulltext
  • 21. Aichroth, Patrick
    et al.
    Weigel, Christian
    Kurz, Thomas
    Stadler, Horst
    Drewes, Frank
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Björklund, Johanna
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Schlegel, Kai
    Berndl, Emanuel
    Perez, Antonio
    Bowyer, Alex
    Volpini, Andrea
    MICO - MEDIA IN CONTEXT2015Inngår i: 2015 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), 2015Konferansepaper (Fagfellevurdert)
    Abstract [en]

    The abundance of digital content requires cost-effective technologies to extract the hidden meaning from media objects. However, current approaches fail to deal with the challenges related to cross-media analysis, metadata publishing, querying and recommendation that are necessary to overcome this challenge. In this paper, we describe the EU project MICO (Media in Context) which aims to provide the necessary technologies based on open-source software (OSS) core components.

  • 22.
    Ait-Mlouk, Addi
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Jiang, Lili
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    KBot: a Knowledge graph based chatBot for natural language understanding over linked data2020Inngår i: IEEE Access, E-ISSN 2169-3536, Vol. 8, s. 149220-149230Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    With the rapid progress of the semantic web, a huge amount of structured data has become available on the web in the form of knowledge bases (KBs). Making these data accessible and useful for end-users is one of the main objectives of chatbots over linked data. Building a chatbot over linked data raises different challenges, including user queries understanding, multiple knowledge base support, and multilingual aspect. To address these challenges, we first design and develop an architecture to provide an interactive user interface. Secondly, we propose a machine learning approach based on intent classification and natural language understanding to understand user intents and generate SPARQL queries. We especially process a new social network dataset (i.e., myPersonality) and add it to the existing knowledge bases to extend the chatbot capabilities by understanding analytical queries. The system can be extended with a new domain on-demand, flexible, multiple knowledge base, multilingual, and allows intuitive creation and execution of different tasks for an extensive range of topics. Furthermore, evaluation and application cases in the chatbot are provided to show how it facilitates interactive semantic data towards different real application scenarios and showcase the proposed approach for a knowledge graph and data-driven chatbot.

    Fulltekst (pdf)
    fulltext
  • 23.
    Ait-Mlouk, Addi
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Vu, Xuan-Son
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Jiang, Lili
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    WINFRA: A Web-Based Platform for Semantic Data Retrieval and Data Analytics2020Inngår i: Mathematics, E-ISSN 2227-7390, Vol. 8, nr 11, artikkel-id 2090Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    Given the huge amount of heterogeneous data stored in different locations, it needs to be federated and semantically interconnected for further use. This paper introduces WINFRA, a comprehensive open-access platform for semantic web data and advanced analytics based on natural language processing (NLP) and data mining techniques (e.g., association rules, clustering, classification based on associations). The system is designed to facilitate federated data analysis, knowledge discovery, information retrieval, and new techniques to deal with semantic web and knowledge graph representation. The processing step integrates data from multiple sources virtually by creating virtual databases. Afterwards, the developed RDF Generator is built to generate RDF files for different data sources, together with SPARQL queries, to support semantic data search and knowledge graph representation. Furthermore, some application cases are provided to demonstrate how it facilitates advanced data analytics over semantic data and showcase our proposed approach toward semantic association rules.

    Fulltekst (pdf)
    fulltext
  • 24.
    Alaqra, Alaa
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Cell-phone Travel Planner GUI for SpaceTime2010Independent thesis Basic level (degree of Bachelor), 10 poäng / 15 hpOppgave
    Abstract [en]

    Global positioning systems have been having an increasing interest recently and been integrated and used in many applications to service positioning, navigation and travel planning. This project has set to design and test an interface of a travel planner for cell phones. A pre-study was made to investigate other travel planners to help the design of this application that has targeted a user friendly interface that people can use regardless of their background. A special feature, carpooling, has been introduced to ease the environmental, economical, and social aspects of navigation. The test was done as walk-through mockup images case scenarios. The test subjects were pleased with the interface’s friendliness, invoked carpooling issues, presented contradictory opinions regarding the interface's design, and offered future integration with other applications suggestions all of which were discussed. Overall, the test results were positive and few problems with the overall design were identified. A future study with more participants and a deeper analysis of the interface would be one way to further investigate the proposed interface.

    Fulltekst (pdf)
    FULLTEXT01
  • 25.
    Aldahir, Abdulsalam
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    EVALUATION OF THE PERFORMANCE OF WEBGPU IN A CLUSTER OF WEB-BROWSERS FOR SCIENTIFIC COMPUTING2022Independent thesis Basic level (degree of Bachelor), 10 poäng / 15 hpOppgave
    Abstract [en]

    The development and wide spread of Internet browsers and technologies make them a tool that can be used for many scientific problems. This raises the question of whether Internet browsers, together with WebGPU and WebRTC, can be used to do scalable computing in a distributed cluster. This thesis answers the question by implementing a peer-to-peer cluster and testing it with two problems, Matrix multiplication and Mandelbrot sets generation. The experimental results show that computing embarrassingly parallel problems are scalable with more than 75% efficiency.

    Fulltekst (pdf)
    fulltext
  • 26.
    Aler Tubella, Andrea
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Barsotti, Flavia
    Strategy Office, ING Analytics, ING Bank, Amsterdam, Netherlands; Institute for Advanced Study (IAS), University of Amsterdam, Amsterdam, Netherlands.
    Koçer, Rüya Gökhan
    Strategy Office, ING Analytics, ING Bank, Amsterdam, Netherlands.
    Mendez, Julian Alfredo
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Ethical implications of fairness interventions: what might be hidden behind engineering choices?2022Inngår i: Ethics and Information Technology, ISSN 1388-1957, E-ISSN 1572-8439, Vol. 24, nr 1, artikkel-id 12Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    The importance of fairness in machine learning models is widely acknowledged, and ongoing academic debate revolves around how to determine the appropriate fairness definition, and how to tackle the trade-off between fairness and model performance. In this paper we argue that besides these concerns, there can be ethical implications behind seemingly purely technical choices in fairness interventions in a typical model development pipeline. As an example we show that the technical choice between in-processing and post-processing is not necessarily value-free and may have serious implications in terms of who will be affected by the specific fairness intervention. The paper reveals how assessing the technical choices in terms of their ethical consequences can contribute to the design of fair models and to the related societal discussions.

    Fulltekst (pdf)
    fulltext
  • 27.
    Aler Tubella, Andrea
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Dignum, Virginia
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    The Glass Box Approach: Verifying Contextual Adherence to Values2019Inngår i: AISafety 2019: Proceedings of the Workshop on Artificial Intelligence Safety 2019co-located with the 28th International Joint Conference on Artificial Intelligence (IJCAI-19) / [ed] Huáscar Espinoza, Han Yu, Xiaowei Huang, Freddy Lecue, Cynthia Chen, José Hernández-Orallo, Seán Ó hÉigeartaigh, Richard Mallah, CEUR-WS , 2019Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Artificial Intelligence (AI) applications are beingused to predict and assess behaviour in multiple domains, such as criminal justice and consumer finance, which directly affect human well-being. However, if AI is to be deployed safely, then people need to understand how the system is interpreting and whether it is adhering to the relevant moral values. Even though transparency is often seen as the requirement in this case, realistically it might notalways be possible or desirable, whereas the needto ensure that the system operates within set moral bounds remains.

    In this paper, we present an approach to evaluate the moral bounds of an AI system based on the monitoring of its inputs and outputs. We place a ‘Glass Box’ around the system by mapping moral values into contextual verifiable norms that constrain inputs and outputs, in such a way that if these remain within the box we can guarantee that the system adheres to the value(s) in a specific context. The focus on inputs and outputs allows for the verification and comparison of vastly different intelligent systems–from deep neural networks to agent-based systems–whereas by making the context explicit we exposethe different perspectives and frameworks that are taken into account when subsuming moral values into specific norms and functionalities. We present a modal logic formalisation of the Glass Box approach which is domain-agnostic, implementable, and expandable.

    Fulltekst (pdf)
    fulltext
  • 28.
    Aler Tubella, Andrea
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Mora-Cantallops, Marçal
    Dpto. Ciencias de la Computación, Universidad de Alcalá, Madrid, Alcalá de Henares, Spain.
    Nieves, Juan Carlos
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    How to teach responsible AI in Higher Education: challenges and opportunities2024Inngår i: Ethics and Information Technology, ISSN 1388-1957, E-ISSN 1572-8439, Vol. 26, nr 1, artikkel-id 3Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    In recent years, the European Union has advanced towards responsible and sustainable Artificial Intelligence (AI) research, development and innovation. While the Ethics Guidelines for Trustworthy AI released in 2019 and the AI Act in 2021 set the starting point for a European Ethical AI, there are still several challenges to translate such advances into the public debate, education and practical learning. This paper contributes towards closing this gap by reviewing the approaches that can be found in the existing literature and by interviewing 11 experts across five countries to help define educational strategies, competencies and resources needed for the successful implementation of Trustworthy AI in Higher Education (HE) and to reach students from all disciplines. The findings are presented in the form of recommendations both for educators and policy incentives, translating the guidelines into HE teaching and practice, so that the next generation of young people can contribute to an ethical, safe and cutting-edge AI made in Europe.

    Fulltekst (pdf)
    fulltext
  • 29.
    Aler Tubella, Andrea
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Theodorou, Andreas
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Dignum, Frank
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Dignum, Virginia
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Governance by glass-box: implementing transparent moral bounds for AI behaviour2019Inngår i: Proceedings of the 28th International Joint Conference on Artificial Intelligence, 2019, s. 5787-5793Konferansepaper (Annet vitenskapelig)
    Abstract [en]

    Artificial Intelligence (AI) applications are being used to predict and assess behaviour in multiple domains which directly affect human well-being. However, if AI is to improve people’s lives, then people must be able to trust it, by being able to understand what the system is doing and why. Although transparency is often seen as the requirementin this case, realistically it might not always be possible, whereas the need to ensure that the system operates within set moral bounds remains.

    In this paper, we present an approach to evaluate the moral bounds of an AI system based on the monitoring of its inputs and outputs. We place a ‘Glass-Box’ around the system by mapping moral values into explicit verifiable norms that constrain inputs and outputs, in such a way that if these remain within the box we can guarantee that the system adheres to the value. The focus on inputs and outputs allows for the verification and comparison of vastly different intelligent systems; from deep neural networks to agent-based systems.

    The explicit transformation of abstract moral values into concrete norms brings great benefits interms of explainability; stakeholders know exactly how the system is interpreting and employing relevant abstract moral human values and calibrate their trust accordingly. Moreover, by operating at a higher level we can check the compliance of the system with different interpretations of the same value.

  • 30.
    Aler Tubella, Andrea
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Theodorou, Andreas
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Dignum, Virginia
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Michael, Loizos
    Contestable Black Boxes2020Inngår i: Rules and Reasoning. RuleML+RR 2020. / [ed] V. Gutiérrez-Basulto, T. Kliegr, A. Soylu, M. Giese, D. Roman, Springer, 2020, s. 159-167Konferansepaper (Fagfellevurdert)
    Abstract [en]

    The right to contest a decision with consequences on individuals or the society is a well-established democratic right. Despite this right also being explicitly included in GDPR in reference to automated decision-making, its study seems to have received much less attention in the AI literature compared, for example, to the right for explanation. This paper investigates the type of assurances that are needed in the contesting process when algorithmic black boxes are involved, opening new questions about the interplay of contestability and explainability. We argue that specialised complementary methodologies to evaluate automated decision-making in the case of a particular decision being contested need to be developed. Further, we propose a combination of well-established software engineering and rule-based approaches as a possible socio-technical solution to the issue of contestability, one of the new democratic challenges posed by the automation of decision making.

  • 31.
    Aler Tubella, Andrea
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Theodorou, Andreas
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Nieves, Juan Carlos
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Interrogating the black box: Transparency through information-seeking dialogues2021Inngår i: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS) , 2021, s. 106-114Konferansepaper (Fagfellevurdert)
    Abstract [en]

    This paper is preoccupied with the following question: given a (possibly opaque) learning system, how can we understand whether its behaviour adheres to governance constraints? The answer can be quite simple: we just need to “ask” the system about it. We propose to construct an investigator agent to query a learning agent- the suspect agent- to investigate its adherence to a given ethical policy in the context of an information-seeking dialogue, modeled in formal argumentation settings. This formal dialogue framework is the main contribution of this paper. Through it, we break down compliance checking mechanisms into three modular components, each of which can be tailored to various needs in a vast amount of ways: an investigator agent, a suspect agent, and an acceptance protocol determining whether the responses of the suspect agent comply with the policy. This acceptance protocol presents a fundamentally different approach to aggregation: rather than using quantitative methods to deal with the non-determinism of a learning system, we leverage the use of argumentation semantics to investigate the notion of properties holding consistently. Overall, we argue that the introduced formal dialogue framework opens many avenues both in the area of compliance checking and in the analysis of properties of opaque systems.

  • 32.
    Ali, Hazrat
    et al.
    College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar.
    Shah, Zubair
    College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar.
    Alam, Tanvir
    College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar.
    Wijayatunga, Priyantha
    Umeå universitet, Samhällsvetenskapliga fakulteten, Handelshögskolan vid Umeå universitet, Statistik.
    Elyan, Eyad
    School of Computing Science and Digital Media, Robert Gordon University, Aberdeen, United Kingdom.
    Editorial: recent advances in multimodal artificial intelligence for disease diagnosis, prognosis, and prevention2024Inngår i: Frontiers in Radiology, ISSN 2673-8740, Vol. 3, artikkel-id 1349830Artikkel i tidsskrift (Annet vitenskapelig)
    Fulltekst (pdf)
    fulltext
  • 33.
    Ali, Irfan
    et al.
    Department of Computer System Engineering, Institute of Business Administration Sukkar, Sukkur, Pakistan.
    Shehzad, Muhammad Naeem
    Department of Electrical and Computer Engineering, COMSATS University Islamabad, Lahore Campus, Lahore, Pakistan.
    Bashir, Qaisar
    Intel Corporation, TX, Austin, United States.
    Elahi, Haroon
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Awais, Muhammad Naeem
    Department of Electrical and Computer Engineering, COMSATS University Islamabad, Lahore Campus, Lahore, Pakistan.
    Geman, Oana
    Department of Computers, Electronics and Automation, Stefan Cel Mare University of Suceava, Suceava, Romania.
    Liu, Pin
    School of Computer Science and Engineering, Central South University, Changsha, China.
    A thermal-aware scheduling algorithm for reducing thermal risks in DAG-based applications in cyber-physical systems2023Inngår i: Ubiquitous security: second international conference, Ubisec 2022, Zhangjiajie, China, December 28–31, 2022, revised selected papers / [ed] Guojun Wang; Kim-Kwang Raymond Choo; Jie Wu; Ernesto Damiani, Singapore: Springer, 2023, s. 497-508Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Directed Acyclic Graph (DAG)-based scheduling applications are critical to resource allocation in the Cloud, Edge, and Fog layers of cyber-physical systems (CPS). However, thermal anomalies in DVFS-enabled homogeneous multiprocessor systems (HMSS) may be exploited by malicious applications posing risks to the availability of the underlying CPS. This can negatively affect the trustworthiness of CPS. This paper proposes an algorithm to address the thermal risks in DVFS-enabled HMSS for periodic DAG-based applications. It also improves the current list scheduling-based Depth-First and Breadth-First techniques without violating the timing constraints of the system. We test the algorithm using standard benchmarks and synthetic applications in a simulation setup. The results show a reduction in the temperature peaks by up to 30%, average temperature by up to 22%, temperature variations up to 3 times, and temperature spatial gradients by up to 4 times as compared to the conventional Depth-First Scheduling algorithms.

  • 34.
    Aliahmadipour, L.
    et al.
    Department of Computer Science, Faculty of Mathematics and Computer, Shahid Bahonar University of Kerman, Kerman, Iran.
    Eftekhari, M.
    Department of Computer Engineering, Shahid Bahonar University of Kerman, Kerman, Iran.
    Torra, Vicenç
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    HFC: data clustering based on hesitant fuzzy decision making2022Inngår i: Iranian Journal of Fuzzy Systems, ISSN 1735-0654, Vol. 19, nr 5, s. 167-181Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    In a clustering task, choosing a proper clustering algorithm and obtaining qualified clusters are crucial issues. Sometimes, a clustering algorithm is chosen based on the data distribution, but data distributions are not known beforehand in real world problems. In this case, we hesitate which clustering algorithm to choose. In this paper, this hesitation is modeled by a hesitant fuzzy multi criteria decision making problem (HFMCDM) in which some clustering algorithms play the role of experts. Here, we consider fuzzy C-means (FCM) and agglomerative clustering algorithms as representative of two popular categories of clustering algorithms partitioning and hierarchical clustering methods, respectively.

    Then, we propose a new clustering procedure based on hesitant fuzzy decision making approaches (HFC) to decide which of the FCM family or hierarchical clustering algorithms is suitable for our data. This procedure ascertains a good clustering algorithm using neutrosophic FCM (NFCM) through a two phases process. The HFC procedure not only makes a true decision about applying partitioning clustering algorithms, but also improves the performance of FCM and evolutionary kernel intuitionistic fuzzy c-means clustering algorithm (EKIFCM) with construction hesitant fuzzy partition (HFP) conveniently. Experimental results show that the clustering procedure is applicable and practical. According to HFC procedure, it should be mentioned that it is possible to replace the other clustering algorithms that belong to any partitioning and hierarchical clustering methods. Also, we can consider other categories of clustering algorithms.

  • 35.
    Ali-Eldin, Ahmed
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Kihl, Maria
    Dept. of Electrical and Information Technology, Lund University, Lund, Sweden.
    Tordsson, Johan
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Elmroth, Erik
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Efficient provisioning of bursty scientific workloads on the cloud using adaptive elasticity control2012Inngår i: Proceedings of the 3rd workshop on Scientific Cloud Computing Date, Association for Computing Machinery (ACM), 2012, s. 31-40Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Elasticity is the ability of a cloud infrastructure to dynamically change theamount of resources allocated to a running service as load changes. We build anautonomous elasticity controller that changes the number of virtual machinesallocated to a service based on both monitored load changes and predictions offuture load. The cloud infrastructure is modeled as a G/G/N queue. This modelis used to construct a hybrid reactive-adaptive controller that quickly reactsto sudden load changes, prevents premature release of resources, takes intoaccount the heterogeneity of the workload, and avoids oscillations. Using simulations with Web and cluster workload traces, we show that our proposed controller lowers the number of delayed requests by a factor of 70 for the Web traces and 3 for the cluster traces when compared to a reactive controller. Ourcontroller also decreases the average number of queued requests by a factor of 3 for both traces, and reduces oscillations by a factor of 7 for the Web traces and 3 for the cluster traces. This comes at the expense of between 20% and 30% over-provisioning, as compared to a few percent for the reactive controller.

  • 36.
    Alin, Lars
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Object Tracking withIphone 3Gs2010Independent thesis Advanced level (degree of Master (One Year)), 30 poäng / 45 hpOppgave
    Abstract [en]

    In June of 2007 Apple Inc. released the smartphone Iphone. It was a groundbreaking success that set a new standard for what a smartphone should be able to do. Apple has improved the Iphone every year since then and the 3Gs is the newest Iphone model. As the phones have improved, both when looking at hardware and software, the applications have improved as well. The Iphone 3Gs provides the possibility to use the camera as an application background and with that the possibility to analyze the surroundings, making it possible to track objects that the phone is pointed towards.This thesis examines how object tracking can be implemented in applications for Iphone 3Gs as well as providing a survey of four different areas of use that have been implemented in Xcode: an augmented reality car game, a letter tracking application, a face recognition application and an object recognition application.

    Fulltekst (pdf)
    FULLTEXT01
  • 37.
    Alisade, Hubert
    et al.
    Department of American Studies, University of Innsbruck, Austria.
    Calvanese, Diego
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. Faculty of Engineering, Free University of Bozen-Bolzano, Italy.
    Klarer, Mario
    Department of American Studies, University of Innsbruck, Austria.
    Mosca, Alessandro
    Faculty of Engineering, Free University of Bozen-Bolzano, Italy.
    Ndefo, Nonyelum
    Faculty of Engineering, Free University of Bozen-Bolzano, Italy.
    Rangger, Bernadette
    Department of American Studies, University of Innsbruck, Austria.
    Tratter, Aaron
    Department of American Studies, University of Innsbruck, Austria.
    Exploration of medieval manuscripts through keyword spotting in the MENS project2023Inngår i: Proceedings of the AIxIA 2023 discussion papers (AIxIA 2023 DP), Rome, Italy, November 6-9, 2023 / [ed] Roberto Basili; Domenico Lembo; Carla Limongelli; AndreA Orlandini, CEUR-WS , 2023, s. 67-74Konferansepaper (Fagfellevurdert)
    Abstract [en]

    In-depth searching for specific content in medieval manuscripts requires labor-intensive, hence time-consuming manual manuscript screening. Using existing IT tools to carry out this task has not been possible, since state-of-the-art keyword spotting lacks the necessary metaknowledge or larger ontology that scholars intuitively apply in their investigations. This problem is being addressed in the “Research Südtirol/Alto Adige” 2019 project “MENS – Medieval Explorations in Neuro-Science (1050–1450): Ontology-Based Keyword Spotting in Manuscript Scans,” whose goal is to build a paradigmatic case study for compiling and subsequent screening of large collections of manuscript scans by using AI techniques for natural language processing and data management based on formal ontologies. We report here on the ongoing work and the results achieved so far in the MENS project.

    Fulltekst (pdf)
    fulltext
  • 38.
    Almeida, Teresa
    et al.
    Umeå universitet, Samhällsvetenskapliga fakulteten, Institutionen för informatik. IT University of Copenhagen.
    Balaam, Madeline
    Bardzell, Shaowen
    Hansen, Lone Koefoed
    Introduction to the Special Issue on HCI and the Body: ReimaginingWomen's Health2020Inngår i: ACM Transactions on Computer-Human Interaction, ISSN 1073-0516, E-ISSN 1557-7325, Vol. 27, nr 4, artikkel-id 20Artikkel i tidsskrift (Annet vitenskapelig)
  • 39.
    Almström, Filip
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    A dynamic approach to sorting with respect to big data2023Independent thesis Advanced level (degree of Master (Two Years)), 20 poäng / 30 hpOppgave
    Abstract [en]

    This study introduces a dynamic approach to sorting, making use of predictions and data gathered during run-time to optimize the sorting of the current data set. This approach is used to develop a sorting algorithm called DynamicSort which partitions data and calculates a partial standard deviation for each partition to determine which of two sorting algorithms should be used to sort the partition. The algorithm is tested against Quicksort and radix sort on data sets of different sizes and standard deviation with the intent of finding advantages of the approach. In order to adapt to modern applications, the algorithm is tested in an environment utilizing parallel processing on multiple machines on data sets generated to mimic the characteristic size of big data. To accommodate this the data is divided at start and merged together after sorting using a k-way merge sort. While the tests conducted do not show any concrete gain in performance there are several factors that could be further optimized and evaluated. We find that it is not enough to simply consider the standard deviation in this approach. While no real instance of big data was used the algorithm was adapted for limited cache sizes and multiple hosts working in parallel.

    Fulltekst (pdf)
    fulltext
  • 40.
    Al-Naser, Mohammad
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.
    Söderström, Ulrik
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för tillämpad fysik och elektronik.
    Reconstruction of occluded facial images using asymmetrical Principal Component Analysis2012Inngår i: Integrated Computer-Aided Engineering, ISSN 1069-2509, E-ISSN 1875-8835, Vol. 19, nr 3, s. 273-283Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    When only non-occluded image parts are available for facial images it is difficult or impossible to correctly recognize the person in the image. The problem addressed in this work is reconstruction of the occluded parts in facial images; e. g. eyes covered with sunglasses. Asymmetrical Principal Component Analysis (aPCA) allows estimation of occluded facial parts based on the content of the facial parts which are visible. aPCA is used to estimate full non-occluded faces from 3 kinds of occlusion with 2 different reconstruction methods in this work and we present the results with both objective and subjective evaluation. The subjective evaluation shows that clear and sharp image regions are preferred even if this results in visible edges in the images. The method also performs well when a different facial expression than the one in the database is used to calculate the reconstruction parameters.

  • 41.
    Amaral, Cleber Jorge
    et al.
    Federal Institute of Santa Catarina.
    Babireski Furio, Vitor Luis
    Federal University of Santa Catarina.
    Zagre Junior, Robson
    Federal University of Santa Catarina.
    Kampik, Timotheus
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    de Brito, Maiquel
    Federal University of Santa Catarina.
    Zatelli, Maicon R.
    Federal University of Santa Catarina.
    Schmitz, Tiago L.
    Santa Catarina State University.
    Hübner, Jomi F.
    Federal University of Santa Catarina.
    Ferrandin, Mauri
    Federal University of Santa Catarina.
    JaCaMo Builders: Team Description for the Multi-agent Programming Contest 2020/212021Inngår i: The Multi-Agent Programming Contest 2021: One-and-a-Half Decades of Exploring Multi-Agent Systems / [ed] Tobias Ahlbrecht; Jürgen Dix; Niklas Fiekas; Tabajara Krausburg, Cham: Springer Nature, 2021, s. 134-157Konferansepaper (Fagfellevurdert)
    Abstract [en]

    This paper describes the JaCaMo Builders team and its participation in the Multi-Agent Programming Contest 2020/21 based on the Agents Assemble II scenario. The paper presents the analysis of the scenario and design of the solution; the software architecture, including the tools used during the development of the team; the main strategies; and the results achieved by the team, with challenges and directions for future editions of the contest.

  • 42.
    Amaral, Cleber Jorge
    et al.
    Federal Institute of Santa Catarina.
    Hübner, Jomi F.
    Federal University of Santa Catarina.
    Kampik, Timotheus
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Towards Jacamo-rest: A Resource-Oriented Abstraction for Managing Multi-Agent Systems2020Inngår i: Proceedings of the 14th Workshop-School on Agents, Environments, and Applications (WESAAC 2020) / [ed] Vaz Alves, Gleifer and Guiménez Lug, Gustavo and Pinz Borgeso, André and Pantoja, Carlos Eduardo, Ponta Grossa: Universidade Tecknologica Federal do parana (UTFPR) , 2020, s. 140-151Konferansepaper (Fagfellevurdert)
    Abstract [en]

    The Multi-Agent Oriented Programming (MAOP) paradigm provides abstractions to model and implements entities of agents, as well as of their organisations and environments.In recent years, researchers have started to explore the integration of MAOP and the resource-oriented web architecture (REST).This paper further advances this line of research by presenting an ongoing work on jacamo-rest, a resource-oriented web-based abstraction for the multi-agent programming platform JaCaMo.Jacamo-rest takes Multi-Agent System (MAS) interoperability to a new level, enabling MAS to not only interact with services or applications of the World Wide Web but also to be managed and updated in their specifications by other applications.To add a developer interface to JaCaMo that is suitable for the Web, we provide a novel conceptual perspective on the management of MAOP specification entities as web resources.We tested jacamo-rest using it as a middleware of a programming interface application that provides modern software engineering facilities such as continuous deployments and iterative software development for MAS.

    Fulltekst (pdf)
    fulltext
  • 43.
    Amaral, Cleber Jorge
    et al.
    Federal Institute of Santa Catarina, São José, Brazil.
    Hübner, Jomi Fred
    Federal University of Santa Catarina, Florianópolis, Brazil.
    Kampik, Timotheus
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. SAP Signavio, Umeå, Sweden.
    TDD for AOP: test-driven development for agent-oriented programming2023Inngår i: AAMAS '23: Proceedings of the 2023 international conference on autonomous agents and multiagent systems, Association for Computing Machinery (ACM), 2023, s. 3038-3040Konferansepaper (Fagfellevurdert)
    Abstract [en]

    This demonstration paper introduces native test-driven development capabilities that have been implemented in an agent-oriented programming language, in particular as extensions of AgentSpeak. We showcase how these capabilities can facilitate the testing and continuous integration of agents in JaCaMo multi-agent systems.

  • 44.
    Amaral, Cleber Jorge
    et al.
    Federal Institute of Santa Catarina, São José, SC, Brazil.
    Kampik, Timotheus
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Cranefield, Stephen
    University of Otago, Dunedin, New Zealand.
    A Framework for Collaborative and Interactive Agent-oriented Developer Operations2020Inngår i: AAMAS Proceedings 2020: Demonstration Track, ACM Digital Library, 2020, s. 2092-2094Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Considering the increasing prevalence of autonomous systems in today's society, one could expect that agent-oriented programming (AOP) is gaining traction among mainstream software engineering practitioners. However, the tools and frameworks that are used and developed in the academic multi-agent systems engineering community struggle to keep up with recent developments in the software industry in regards to how complex information systems are developed and maintained. An important aspect of recent changes in software engineering practices is the application of technologies that support the increasingly fast iteration of a programming-testing-deployment cycle. Such approaches require intense collaboration that crosses boundaries between traditionally separated roles like software development, quality assurance, and operations; these approaches are often referred to as DevOps.

  • 45.
    Andersson, Eric
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
    Generating corpora of semantic graphs based on graph extension grammar2023Independent thesis Basic level (degree of Bachelor), 10 poäng / 15 hpOppgave
    Abstract [en]

    This thesis introduces the tool Lovelace which is used to generate corpora of semantic graphs to investigate which functionalities and design- as well as implementation aspects are important in a corpus generator. Lovelace uses the graph grammar formalism graph extension grammar (GEG) to generate these corpora. A GEG consists of two parts, regular tree grammar (RTG) and graph operations. A tree generated by an RTG is used as an instruction on how the graph operations are applied to create a semantic graph. Since Lovelace can express variables as word classes the combination of semantic graphs and well-formed word classes means that the corpus generated by Lovelace is well-formed. In addition, Lovelace enables the user to configure parameters to specify the corpus generated. These corpora could be used as a tool to translate and process natural language. The thesis ends with a discussion about which parts are missing and what could be improved in the corpus generator, along with new insights into which functionalities are important for a user of a corpus generator.  

    Fulltekst (pdf)
    fulltext
  • 46.
    Andersson, Jennifer
    et al.
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik. Umeå universitet.
    Bodin, Kenneth
    Algoryx Simulation AB, Umeå, Sweden.
    Lindmark, Daniel
    Algoryx Simulation AB, Umeå, Sweden.
    Servin, Martin
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik. Algoryx Simulation AB, Umeå, Sweden.
    Wallin, Erik
    Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för fysik.
    Reinforcement Learning Control of a Forestry Crane Manipulator2021Inngår i: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021): Proceedings, Prague: IEEE Robotics and Automation Society, 2021, s. 2121-2126Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Forestry machines are heavy vehicles performing complex manipulation tasks in unstructured production forest environments. Together with the complex dynamics of the on-board hydraulically actuated cranes, the rough forest terrains have posed a particular challenge in forestry automation. In this study, the feasibility of applying reinforcement learning control to forestry crane manipulators is investigated in a simulated environment. Our results show that it is possible to learn successful actuator-space control policies for energy efficient log grasping by invoking a simple curriculum in a deep reinforcement learning setup. Given the pose of the selected logs, our best control policy reaches a grasping success rate of 97%. Including an energy-optimization goal in the reward function, the energy consumption is significantly reduced compared to control policies learned without incentive for energy optimization, while the increase in cycle time is marginal. The energy-optimization effects can be observed in the overall smoother motion and acceleration profiles during crane manipulation. 

    Fulltekst (pdf)
    fulltext
  • 47.
    Andersson, Jennifer
    et al.
    Department of Information Technology, Uppsala University, Uppsala, Sweden.
    Moya, Jose Alonso
    Schwickerath, Ulrich
    Anomaly Detection for the Centralised Elasticsearch Service at CERN2021Inngår i: Frontiers in Big Data, ISSN 2624-909X, Vol. 4, artikkel-id 718879Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    For several years CERN has been offering a centralised service for Elasticsearch, a popular distributed system for search and analytics of user provided data. The service offered by CERN IT is better described as a service of services, delivering centrally managed and maintained Elasticsearch instances to CERN users who have a justified need for it. This dynamic infrastructure currently consists of about 30 distinct and independent Elasticsearch installations, in the following referred to as Elasticsearch clusters, some of which are shared between different user communities. The service is used by several hundred users mainly for logs and service analytics. Due to its size and complexity, the installation produces a huge amount of internal monitoring data which can be difficult to process in real time with limited available person power. Early on, an idea was therefore born to process this data automatically, aiming to extract anomalies and possible issues building up in real time, allowing the experts to address them before they start to cause an issue for the users of the service. Both deep learning and traditional methods have been applied to analyse the data in order to achieve this goal. This resulted in the current deployment of an anomaly detection system based on a one layer multi dimensional LSTM neural network, coupled with applying a simple moving average to the data to validate the results. This paper will describe which methods were investigated and give an overview of the current system, including data retrieval, data pre-processing and analysis. In addition, reports on experiences gained when applying the system to actual data will be provided. Finally, weaknesses of the current system will be briefly discussed, and ideas for future system improvements will be sketched out.

    Fulltekst (pdf)
    fulltext
  • 48.
    Andersson, Jonas
    et al.
    Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper, Radiofysik.
    Nyholm, Tufve
    Umeå universitet, Medicinska fakulteten, Institutionen för strålningsvetenskaper, Radiofysik.
    Ceberg, Crister
    Almén, Anja
    Bernhardt, Peter
    Fransson, Annette
    Olsson, Lars E.
    Artificial intelligence and the medical physics profession - A Swedish perspective2021Inngår i: Physica medica (Testo stampato), ISSN 1120-1797, E-ISSN 1724-191X, Vol. 88, s. 218-225Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    Background: There is a continuous and dynamic discussion on artificial intelligence (AI) in present-day society. AI is expected to impact on healthcare processes and could contribute to a more sustainable use of resources allocated to healthcare in the future. The aim for this work was to establish a foundation for a Swedish perspective on the potential effect of AI on the medical physics profession.

    Materials and methods: We designed a survey to gauge viewpoints regarding AI in the Swedish medical physics community. Based on the survey results and present-day situation in Sweden, a SWOT analysis was performed on the implications of AI for the medical physics profession.

    Results: Out of 411 survey recipients, 163 responded (40%). The Swedish medical physicists with a professional license believed (90%) that AI would change the practice of medical physics but did not foresee (81%) that AI would pose a risk to their practice and career. The respondents were largely positive to the inclusion of AI in educational programmes. According to self-assessment, the respondents’ knowledge of and workplace preparedness for AI was generally low.

    Conclusions: From the survey and SWOT analysis we conclude that AI will change the medical physics profession and that there are opportunities for the profession associated with the adoption of AI in healthcare. To overcome the weakness of limited AI knowledge, potentially threatening the role of medical physicists, and build upon the strong position in Swedish healthcare, medical physics education and training should include learning objectives on AI.

    Fulltekst (pdf)
    fulltext
  • 49.
    Andersson, Marcus
    Umeå universitet, Samhällsvetenskapliga fakulteten, Institutionen för psykologi.
    Complexity and problem solving: A tale of two systems2018Independent thesis Basic level (degree of Bachelor), 10 poäng / 15 hpOppgave
    Abstract [en]

    The purpose of this thesis is to investigate if increasing complexity for a problem makes a difference for a learning system with dual parts. The dual parts of the learning system are modelled after the Actor and Critic parts from the Actor-Critic algorithm, using the reinforcement learning framework. The results conclude that not any difference can be found in the relative performance in the Actor and Critic parts when increasing the complexity of a problem. These results could depend on technical difficulties in comparing the environments and the algorithms. The difference in complexity would then be non-uniform in an unknowable way and uncertain to use as comparison. If on the other hand the change of complexity is uniform, this could point to the fact that there is an actual difference in how each of the actor and critic handles different types of complexity. Further studies with a controlled increase in complexity are needed to establish which of the scenarios is most likely to be true. In the discussion an idea is presented of using the Actor-Critic framework as a model to understand the success rate of psychological treatments better.

    Fulltekst (pdf)
    Andersson_Kogvet_Kand_15hp.pdf
  • 50.
    Andersson, Ola
    Umeå universitet, Teknisk-naturvetenskaplig fakultet, Institutionen för datavetenskap.
    Threat, risk, and vulnerabilityanalyses during the developmentof IT systems in the SwedishArmed Forces2010Independent thesis Advanced level (degree of Master (Two Years)), 20 poäng / 30 hpOppgave
    Abstract [en]

    This master’s thesis describes how two models from the Swedish Armed Forces; the risk management model and the IT lifecycle model can be combined. An example is then presented for how the risk management model can be extended for threats, risks, and vulnerabilities related to information technology. The combination and extension of the models are based on a literature study that lists and compares models and methods for threat, risk, andvulnerability analyses, as well as an analysis of threats related to information technology. From the combined and extended model, a design proposal for how to implement the identified functionality was identified. Based on an evaluation that showed that the program NTE and the plugin EASTER were suitable as the foundation for this implementation, the program NTE and the plugin EASTER were extended with further functionality and resulted in the implementation of the plugin ASCENSION. This was evaluated and resulted in ideas for a possible re-design and examples of the future potential of ASCENSION.

    Fulltekst (pdf)
    FULLTEXT01
1234567 1 - 50 of 1739
RefereraExporteraLink til resultatlisten
Permanent link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf