1 - 20 of 20
rss atomLink 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
  • Westphal, Florian
    et al.
    Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science.
    Grahn, Håkan
    Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science.
    Lavesson, Niklas
    Jönköpings universitet.
    Representative Image Selection for Data Efficient Word Spotting2020In: 14th IAPR International Workshop on Document Analysis Systems (DAS), Springer, 2020Conference paper (Refereed)
    Abstract [en]

    This paper compares three different word image representations as base for label free sample selection for word spotting in historical handwritten documents. These representations are a temporal pyramid representation based on pixel counts, a graph based representation, and a pyramidal histogram of characters (PHOC) representation predicted by a PHOCNet trained on synthetic data. We show that the PHOC representation can help to reduce the amount of required training samples by up to 69% depending on the dataset, if it is learned iteratively in an active learning like fashion. While this works for larger datasets containing about 1 700 images, for smaller datasets with 100 images, we find that the temporal pyramid and the graph representation perform better.

    Download full text (pdf)
    fulltext
  • Josyula, Sai Prashanth
    Blekinge Institute of Technology, Faculty of Computing.
    Investigating ethical issues in research concerned with data sources involving sensitive personal data2017Report (Other academic)
    Download full text (pdf)
    fulltext
  • Högström, Ebba
    et al.
    Blekinge Institute of Technology, Faculty of Engineering, Department of Spatial Planning. School of Geogrpahy and Earth Sciences, University of Glasgow, Glasgow, UK.
    Philo, Chris
    School of Geography and Earth Sciences, University of Glasgow, Glasgow, UK.
    Space out of time, spaces full of times and shaking the kaleidoscope of memory: Investigating the temporalities of an urban mental health campus2019Conference paper (Refereed)
    Download full text (pdf)
    AHRA 2019 Book of abstracts
  • Engström, Carl-Johan
    et al.
    Kungliga tekniska högskolan, Institutionen Samhällsplanering och miljö.
    Högström, Ebba
    Kungliga tekniska högskolan, Institutionen Samhällsplanering och miljö.
    Rostvik, Maja
    Kungliga tekniska högskolan, Institutionen Samhällsplanering och miljö.
    Synergier mellan investeringar.: Åtta fallstudier.2013Report (Other academic)
    Abstract [sv]

    Denna rapport är framtagen för att få en ökad förståelse för hur olika investeringar i Stockholmsregionen påverkar varandra och genom att för-stå det, på sikt få ett mer kraftfullt och samordnat genomförande. Frågor som ställs i studien är bland annat dessa: Vilka synergier finns det mellan olika investeringar och hur kan man utnyttja dem? Kan man stöd-ja privata investeringar genom offent-liga investeringar? Kan man påvisa att offentliga investeringar som gjorts har gett upphov till privata investe-ringar som annars inte skulle ha genomförts? Vad är det som påverkar om en investering ger följdeffekter eller inte?

    Download full text (pdf)
    fulltext
  • Högström, Ebba
    et al.
    Blekinge Institute of Technology, Faculty of Engineering, Department of Spatial Planning.
    Jörgensen, Rasmus
    Architecture as an agent of change: The case of school 53 in St Petersburg2013In: Contemporary design in the social sector.: New ideas for school environments / [ed] Veits, Maria, St Petersburg: Design Platform, TOK Curators , 2013, p. 50-61Chapter in book (Other (popular science, discussion, etc.))
    Abstract [en]

    Conducting a thorough organisational analysis is crucial for coming up with sustainable design interventions and architec- tural alteration. Architecture has the power to influence or constrain spatial practices. Therefore in order to be successful every proposal has to be based on knowledge about the organisation, their everyday activities and goals

    Download full text (pdf)
    Contemporary Design in the Social Sector. Yes ideas for School Environments.
  • Högström, Ebba
    Tillfälliga förbindelser.: Reflektioner på färd längs periferin1998In: Nordisk arkitekturforskning, ISSN 1102-5824, Vol. 11, no 3, p. 95-105Article in journal (Other (popular science, discussion, etc.))
    Abstract [sv]

    Kartan och planen. An kartlägga eller konstruera. En motsatsställning mellan det skapade och det upptäckta. Mellan det byggda och det funna. Var skapas det upptäckta och var upptäckts det skapade? Är kartläggandet en avbild eller är det en skapad och konstruerad plan? Och är då pla­nen är en sorts karta? 

    Download full text (pdf)
    Högström (1998) Tillfälliga förbindelser
  • Gradolewski, Dawid
    et al.
    Blekinge Institute of Technology, Faculty of Engineering, Department of Mathematics and Natural Sciences.
    Maslowski, Dawid
    Intema Sp Zoo, POL.
    Dziak, Damian
    Blekinge Institute of Technology, Faculty of Engineering, Department of Mathematics and Natural Sciences.
    Jachimczyk, Bartosz
    Blekinge Institute of Technology, Faculty of Engineering, Department of Mathematics and Natural Sciences.
    Mundlamuri, Siva Teja
    Blekinge Institute of Technology, Faculty of Engineering, Department of Mathematics and Natural Sciences. Intema Sp Zoo, Siennicka 25a, POL.
    Prakash, Chandran G.
    Blekinge Institute of Technology, Faculty of Engineering, Department of Mathematics and Natural Sciences. Intema Sp Zoo, Siennicka 25a, POL.
    Kulesza, Wlodek
    Blekinge Institute of Technology, Faculty of Engineering, Department of Mathematics and Natural Sciences.
    A Distributed Computing Real-Time Safety System of Collaborative Robot2020In: ELEKTRONIKA IR ELEKTROTECHNIKA, ISSN 1392-1215, Vol. 26, no 2, p. 4-14Article in journal (Refereed)
    Abstract [en]

    Robotization has become common in modern factories due to its efficiency and cost-effectiveness. Lots of robots and manipulators share their workspaces with humans what could lead to hazardous situations causing health damage or even death. This article presents a real-time safety system applying the distributed computing paradigm for a collaborative robot. The system consists of detection/sensing modules connected with a server working as decision-making system. Each configurable sensing module pre-processes vision information and then sends to the server the images cropped to new objects extracted from a background. After identifying persons from the images, the decision-making system sends a request to the robot to perform pre-defined action. In the proposed solution, there are indicated three safety zones defined by three different actions on a robot motion. As identification method, state-of-the-art of Machine Learning algorithms, the Histogram of Oriented Gradients (HOG), Viola-Jones, and You Only Look Once (YOLO), have been examined and presented. The industrial environment tests indicated that YOLOv3 algorithm outperformed other solutions in terms of identification capabilities, false positive rate and maximum latency.

    Download full text (pdf)
    A Distributed Computing Real-Time Safety System of Collaborative Robot
  • Shahmardani, Mahdieh
    et al.
    Blekinge Institute of Technology, Faculty of Engineering, Department of Mechanical Engineering.
    Ståhle, Per
    Lund University, SWE.
    Islam, Md Shafiqul
    Blekinge Institute of Technology, Faculty of Engineering, Department of Mechanical Engineering.
    Kao-Walter, Sharon
    Blekinge Institute of Technology, Faculty of Engineering, Department of Mechanical Engineering.
    Numerical simulation of buckling and post-buckling behavior of a central notched thin aluminum foil with nonlinearity in consideration2020In: Metals, ISSN 2075-4701, Vol. 10, no 5, article id 582Article in journal (Refereed)
    Abstract [en]

    In thin notched sheets under tensile loading, wrinkling appears on the sheet surface, specifically around the cracked area. This is due to local buckling and compression stresses near the crack surfaces. This study aims to numerically study the buckling behavior of a thin sheet with a central crack under tension. A numerical model of a notched sheet under tensile loading is developed using the finite element method, which considers both material and geometrical nonlinearity. To overcome the convergence problem caused by the small thickness-to-length/width ratio and to stimulate the buckling, an imperfection is defined as a small perturbation in the numerical model. Both elastic and elasto-plastic behavior are applied, and the influence of them is studied on the critical buckling stress and the post-buckling behavior of the notched sheet. Numerical results for both elastic and elasto-plastic behavior reflect that very small perturbations need more energy for the activation of buckling mode, and a higher buckling mode is predominant. The influences of different parameters, including Poisson’s ratio, yield limit, crack length-to-sheet-width ratio, and the sheet aspect ratio are also evaluated with a focus on the critical buckling stress and the buckling mode shape. With increase in Poisson’s ratio. First, the critical buckling stress reduces and then remains constant. A higher yield limit results in increases in the critical buckling stress, and no change in the buckling mode shape while adopting various crack length-to-sheet-width ratios, and the sheet aspect ratio changes the buckling mode shape.

    Download full text (pdf)
    Numerical simulation of buckling and post-buckling behavior of a central notched thin aluminum foil with nonlinearity in consideration
  • Peixoto, Mariana
    et al.
    Universidade Federal de Pernambuco, BRA.
    Ferreira, Dayse
    Universidade Federal de Pernambuco, BRA.
    Cavalcanti, Mateus
    Universidade Federal de Pernambuco, BRA.
    Silva, Cléber Costa
    Universidade Federal de Pernambuco, BRA.
    Vilela, Jéssyka
    Universidade Federal de Pernambuco, BRA.
    Araújo, João
    Universidade Nova de Lisboa, PRT.
    Gorschek, Tony
    Blekinge Institute of Technology, Faculty of Computing, Department of Software Engineering.
    On Understanding How Developers Perceive and Interpret Privacy Requirements Research Preview2020In: Lecture Notes in Computer Science / [ed] Madhavji N.,Pasquale L., Springer , 2020, Vol. 12045, p. 116-123Conference paper (Refereed)
    Abstract [en]

    [Context and motivation] Ensuring privacy of users’ data has become a top concern in software development, either to satisfy users’ needs or to comply with privacy laws. The problem may increase by the time a new law is in the vacancy period, and companies are working to understand how to comply with it. In addition, research has shown that many developers do not have sufficient knowledge about how to develop privacy-sensitive software. [Question/problem] Motivated by this scenario, this research investigates the personal factors affecting the developers’ understanding of privacy requirements during the vacancy period of a data protection law. [Principal ideas/results] We conducted thirteen interviews in six different private companies. As a result, we found nine personal factors affecting how software developers perceive and interpret privacy requirements. [Contribution] The identification of the personal factors contributes to the elaboration of effective methods for promoting proper privacy-sensitive software development. © 2020, Springer Nature Switzerland AG.

    Download full text (pdf)
    On Understanding How Developers Perceive and Interpret Privacy Requirements Research Preview
  • Romare, Charlotte
    et al.
    Blekinge Institute of Technology, Faculty of Engineering, Department of Health. Region Blekinge, SWE.
    Skär, Lisa
    Blekinge Institute of Technology, Faculty of Engineering, Department of Health.
    Smart glasses for caring situations in complex care environments: Scoping review2020In: JMIR mhealth and uhealth, E-ISSN 2291-5222, Vol. 8, no 4, article id e16055Article, review/survey (Refereed)
    Abstract [en]

    Background: Anesthesia departments and intensive care units represent two advanced, high-tech, and complex care environments. Health care in those environments involves different types of technology to provide safe, high-quality care. Smart glasses have previously been used in different health care settings and have been suggested to assist health care professionals in numerous areas. However, smart glasses in the complex contexts of anesthesia care and intensive care are new and innovative. An overview of existing research related to these contexts is needed before implementing smart glasses into complex care environments. Objective: The aim of this study was to highlight potential benefits and limitations with health care professionals' use of smart glasses in situations occurring in complex care environments. Methods: A scoping review with six steps was conducted to fulfill the objective. Database searches were conducted in PubMed and Scopus; original articles about health care professionals’ use of smart glasses in complex care environments and/or situations occurring in those environments were included. The searches yielded a total of 20 articles that were included in the review. Results: Three categories were created during the qualitative content analysis: (1) smart glasses as a versatile tool that offers opportunities and challenges, (2) smart glasses entail positive and negative impacts on health care professionals, and (3) smart glasses' quality of use provides facilities and leaves room for improvement. Smart glasses were found to be both a helpful tool and a hindrance in caring situations that might occur in complex care environments. This review provides an increased understanding about different situations where smart glasses might be used by health care professionals in clinical practice in anesthesia care and intensive care; however, research about smart glasses in clinical complex care environments is limited. Conclusions: Thoughtful implementation and improved hardware are needed to meet health care professionals’ needs. New technology brings challenges; more research is required to elucidate how smart glasses affect patient safety, health care professionals, and quality of care in complex care environments. ©Charlotte Romare, Lisa Skär.

    Download full text (pdf)
    Smart Glasses for Caring Situations in Complex Care Environments: Scoping Review
  • Christiansen, Line
    et al.
    Blekinge Institute of Technology, Faculty of Engineering, Department of Health.
    Lindberg, Catharina
    Blekinge Institute of Technology, Faculty of Engineering, Department of Health.
    Sanmartin Berglund, Johan
    Blekinge Institute of Technology, Faculty of Engineering, Department of Health.
    Anderberg, Peter
    Blekinge Institute of Technology, Faculty of Engineering, Department of Health.
    Skär, Lisa
    Blekinge Institute of Technology, Faculty of Engineering, Department of Health.
    Using Mobile Health and the Impact on Health-Related Quality of Life: Perceptions of Older Adults with Cognitive Impairment2020In: International Journal of Environmental Research and Public Health, ISSN 1661-7827, E-ISSN 1660-4601, Vol. 17, no 8Article in journal (Refereed)
    Abstract [en]

    Digital health technologies such as mobile health (mHealth) are considered to have the potential to support the needs of older adults with cognitive impairment. However, the evidence for improving health with the use of mHealth applications is of limited quality. Few studies have reported on the consequences of technology use concerning the older adults' quality of life. The purpose of this study was to describe perceptions of mHealth and its impact on health-related quality of life (HRQoL) among older adults with cognitive impairment. The study was conducted using a qualitative design with a phenomenographic approach. A total of 18 older participants with cognitive impairment were interviewed. The interviews were analyzed in order to apply phenomenography in a home-care context. The results showed variations in the older adults' perceptions that were comprised within three categories of description; Require technology literacy, Maintain social interaction, and Facilitate independent living. In conclusion, the development and design of mHealth technologies need to be tailored based on older adults´ needs in order to be understood and perceived as useful in a home-care context. For mHealth to support HRQoL, healthcare should be provided in a way that encourages various forms of communication and interaction.

    Download full text (pdf)
    Using Mobile Health and the Impact on Health-Related Quality of Life: Perceptions of Older Adults with Cognitive Impairment
  • Javadi, Mohammad Saleh
    et al.
    Blekinge Institute of Technology, Faculty of Engineering, Department of Mathematics and Natural Sciences.
    Dahl, Mattias
    Blekinge Institute of Technology, Faculty of Engineering, Department of Mathematics and Natural Sciences.
    Pettersson, Mats
    Blekinge Institute of Technology, Faculty of Engineering, Department of Mathematics and Natural Sciences.
    Change Detection in Aerial Images Using Three-Dimensional Feature Maps2020In: Remote Sensing, ISSN 2072-4292, E-ISSN 2072-4292, Vol. 12, no 9, article id 1404Article in journal (Refereed)
    Abstract [en]

     Interest in aerial image analysis has increased owing to recent developments in and availabilityofaerialimagingtechnologies,likeunmannedaerialvehicles(UAVs),aswellasagrowing need for autonomous surveillance systems. Variant illumination, intensity noise, and different viewpointsareamongthemainchallengestoovercomeinordertodeterminechangesinaerialimages. In this paper, we present a robust method for change detection in aerial images. To accomplish this, the method extracts three-dimensional (3D) features for segmentation of objects above a defined reference surface at each instant. The acquired 3D feature maps, with two measurements, are then used to determine changes in a scene over time. In addition, the important parameters that affect measurement, such as the camera’s sampling rate, image resolution, the height of the drone, and the pixel’sheightinformation,areinvestigatedthroughamathematicalmodel. Toexhibititsapplicability, the proposed method has been evaluated on aerial images of various real-world locations and the results are promising. The performance indicates the robustness of the method in addressing the problems of conventional change detection methods, such as intensity differences and shadows.

    Download full text (pdf)
    fulltext
  • Abualhaija, Sallam
    et al.
    University of Luxembourg, LUX.
    Fucci, Davide
    Blekinge Institute of Technology, Faculty of Computing, Department of Software Engineering.
    Dalpiaz, Fabiano
    Utrecht University, NLD.
    Franch, Xavier
    Universitat Politècnica de Catalunya, ESP.
    3rd workshop on natural language processing for requirements engineering (NLP4RE'20)2020In: CEUR Workshop Proceedings / [ed] Sabetzadeh M.,Vogelsang A.,Abualhaija S.,Borg M.,Dalpiaz F.,Daneva M.,Fernandez N.C.,Franch X.,Fucci D.,Gervasi V.,Groen E.,Guizzardi R.,Herrmann A.,Horkoff J.,Mich L.,Perini A.,Susi A., CEUR-WS , 2020, Vol. 2584Conference paper (Refereed)
    Download full text (pdf)
    3rd workshop on natural language processing for requirements engineering (NLP4RE'20)
  • Lenarduzzi, Valentina
    et al.
    Lut University, FIN.
    Fucci, Davide
    Blekinge Institute of Technology, Faculty of Computing, Department of Software Engineering.
    Mendez, Daniel
    Blekinge Institute of Technology, Faculty of Computing, Department of Software Engineering.
    On the perceived harmfulness of requirement smells: An empirical study2020In: CEUR Workshop Proceedings / [ed] Sabetzadeh M.,Vogelsang A.,Abualhaija S.,Borg M.,Dalpiaz F.,Daneva M.,Fernandez N.C.,Franch X.,Fucci D.,Gervasi V.,Groen E.,Guizzardi R.,Herrmann A.,Horkoff J.,Mich L.,Perini A.,Susi A., CEUR-WS , 2020, Vol. 2584Conference paper (Refereed)
    Abstract [en]

    Technical debt is considered to have negative effects to the long term success of software projects. However, how the debt metaphor applies to requirements engineering is yet not significantly explored. Previ- ously, we proposed a framework to identify Requirements Debt (ReD) in three stages of the software development lifecycle. One of these stages is the formalization of stakeholder needs into natural language requirement specifications. In this work, we propose a live study aiming at surveying requirements engineering experts to gain further insights on the issues taking place at this stage and how they fit in our definition of ReD. Copyright © 2020 for this paper by its authors.

    Download full text (pdf)
    On the perceived harmfulness of requirement smells: An empirical study
  • Fotrousi, Farnaz
    Blekinge Institute of Technology, Faculty of Computing, Department of Software Engineering.
    Combining User Feedback and Monitoring Data to Support Evidence-based Software Evolution2020Doctoral thesis, comprehensive summary (Other academic)
    Download full text (pdf)
    fulltext
  • Javadi, Mohammad Saleh
    et al.
    Blekinge Institute of Technology, Faculty of Engineering, Department of Mathematics and Natural Sciences.
    Dahl, Mattias
    Blekinge Institute of Technology, Faculty of Engineering, Department of Mathematics and Natural Sciences.
    Pettersson, Mats
    Blekinge Institute of Technology, Faculty of Engineering, Department of Mathematics and Natural Sciences.
    Adjustable Contrast Enhancement Using Fast Piecewise Linear Histogram Equalization2020In: ACM International Conference Proceeding Series, Association for Computing Machinery , 2020, p. 57-61Conference paper (Refereed)
    Abstract [en]

    Histogram equalization is a technique to enhance the contrast of the image by redistributing the histogram. In this paper, a fast piecewise linear histogram equalization method is introduced based on an adjustable degree of enhancement and piecewise continuous transformation functions using frequencies of different grey-levels. This method aims to address and maximize the contrast enhancement of the image by stretching the entire spectrum. For this purpose, particular nodes (bins) on the histogram are simultaneously detected that in comparison with recursive methods, it requires less computational time. Then, the particular nodes are stretched using transformation functions to align with the reference nodes. The experimental results indicate that the performance of the proposed method is promising in terms of contrast enhancement. Moreover, this method preserves the texture of various regions in the image very well through the equalization process by using the degree of enhancement. © 2020 Owner/Author.

    Download full text (pdf)
    Adjustable Contrast Enhancement Using Fast Piecewise Linear Histogram Equalization
  • G Palm, Bruna
    et al.
    Universidade Federal de Pernambuco, BRA.
    Alves, Dimas
    Universidade Federal do Pampa, BRA; .
    Pettersson, Mats
    Blekinge Institute of Technology, Faculty of Engineering, Department of Mathematics and Natural Sciences.
    Vu, Viet Thuy
    Blekinge Institute of Technology, Faculty of Engineering, Department of Mathematics and Natural Sciences.
    Machado, Renato
    Aeronautics Institute of Technology (ITA), BRA.
    J Cintra, Renato
    University of Calgary, CAN.
    M Bayer, Fabio
    Universidade Federal de Santa Maria, BRA.
    Dämmert, Patrik B. G.
    Saab Electronic Defence Systems, SWE.
    Hellsten, Hans
    Saab Electronic Defence Systems, SWE.
    Wavelength-Resolution SAR Ground Scene Prediction Based on Image Stack2020In: Sensors, ISSN 1424-8220, E-ISSN 1424-8220, Vol. 20, no 7Article in journal (Refereed)
    Abstract [en]

    This paper presents five different statistical methods for ground scene prediction (GSP) in wavelength-resolution synthetic aperture radar (SAR) images. The GSP image can be used as a reference image in a change detection algorithm yielding a high probability of detection and low false alarm rate. The predictions are based on image stacks, which are composed of images from the same scene acquired at different instants with the same flight geometry. The considered methods for obtaining the ground scene prediction include (i) autoregressive models; (ii) trimmed mean; (iii) median; (iv) intensity mean; and (v) mean. It is expected that the predicted image presents the true ground scene without change and preserves the ground backscattering pattern. The study indicates that the the median method provided the most accurate representation of the true ground. To show the applicability of the GSP, a change detection algorithm was considered using the median ground scene as a reference image. As a result, the median method displayed the probability of detection of 97 % and a false alarm rate of 0 . 11 / km 2 , when considering military vehicles concealed in a forest.

    Download full text (pdf)
    Wavelength-Resolution SAR Ground Scene Prediction Based on Image Stack
  • Andersson, Martin
    et al.
    Blekinge Institute of Technology, Faculty of Engineering, Department of Industrial Economics.
    Larsson, Johan P
    Geography and Entrepreneurship2020In: Handbook of Regional Science: Live, Springer , 2020Chapter in book (Refereed)
    Abstract [en]

    We take selective stock of the literature on the geography of entrepreneurship. This literature has been focused on rates of new firm formation, whereas studies of the geography of “high-impact” entrepreneurship are still scant. Entrepreneurship may be described as a “regional event” by the fact that entrepreneurs derive necessary resources from local markets, but also from regional spillovers, social networks, and engrained factors of the local industrial geography. We point to a few fields of analysis where causal or more detailed analyses are warranted.

    Download full text (pdf)
    fulltext
  • Rameez, Muhammad
    Blekinge Institute of Technology, Faculty of Engineering, Department of Mathematics and Natural Sciences.
    Interference Mitigation Techniques in FMCW Automotive Radars2020Licentiate thesis, comprehensive summary (Other academic)
    Abstract [en]

    Radar has emerged as an important sensor for scenario perception in automated driving and surveillance systems. The exponential increase of radar units in traffic and their operating frequency limitations have given rise to the problem of mutual interference. Radar's performance degrades in the presence of interference, which can result in false alarms and missed detections. In the case of safety-oriented systems (such as automatic emergency braking, blind-spot detection and obstacle detection at level crossings), radar's degraded performance can result in accidents. Therefore, it is important to mitigate the effect of mutual interference to make modern radar applications safe and reliable. The goal of this work is to develop signal processing techniques for interference mitigation in frequency modulated continuous wave (FMCW) radars operating at 77-81 GHz.

    The thesis investigates radar interference suppression in the spatial domain, using antenna arrays. The interference is suppressed by placing notches in the antenna radiation pattern in the direction of the interference source by employing digital beamforming.

    The array aperture (size) determines the beam-width and notch resolution of the receiving antenna. Narrow notches are desirable since they lead to a smaller suppressed region in the radar's field of view. It is demonstrated that an extended virtual aperture in a multiple-input-multiple-output (MIMO) FMCW radar does not offer an improved notch resolution for interference suppression due to a non-coherent interference signal in the virtual aperture. Moreover, it is shown that the calibration mismatches of the receiving array completely change the final antenna beam-pattern compared to the theoretical one.

    Additionally, an adaptive beamforming approach of interference suppression based on the least mean squares (LMS) algorithm is presented, which is evaluated using outdoor measurements from a 77GHz FMCW radar. The results demonstrate that the proposed technique suppresses interference successfully, resulting in a signal to interference plus noise ratio (SINR) improvement. It is also shown that complex-baseband (IQ) receivers achieve better interference suppression compared to real-baseband receivers when spatial domain methods are employed.

    The final research publication deals with interference mitigation in the time-domain intermediate frequency signal. The disturbed samples in the received signal are detected, removed, and reconstructed based on an estimated autoregressive (AR) signal model. The baseband signal coherence in both fast- and slow-time makes it possible to perform signal reconstruction in both dimensions. With the help of outdoor measurements covering selected scenarios, it is demonstrated that by carefully selecting the signal reconstruction dimension, a better SINR and side-lobe suppression can be achieved.

    Download full text (pdf)
    fulltext
  • Krantz, Amandus
    et al.
    Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science.
    Westphal, Florian
    Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science.
    Cluster-based Sample Selection for Document Image Binarization2019In: 2019 INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION WORKSHOPS (ICDARW), VOL 5, IEEE , 2019, p. 47-52Conference paper (Refereed)
    Abstract [en]

    The current state-of-the-art, in terms of performance, for solving document image binarization is training artificial neural networks on pre-labelled ground truth data. As such, it faces the same issues as other, more conventional, classification problems; requiring a large amount of training data. However, unlike those conventional classification problems, document image binarization involves having to either manually craft or estimate the binarized ground truth data, which can be error-prone and time-consuming. This is where sample selection, the act of selecting training samples based on some method or metric, might help. By reducing the size of the training dataset in such a way that the binarization performance is not impacted, the required time spent creating the ground truth is also reduced. This paper proposes a cluster-based sample selection method that uses image similarity metrics and the relative neighbourhood graph to reduce the underlying redundancy of the dataset. The method, implemented with affinity propagation and the structural similarity index, reduces the training dataset on average by 49.57% while reducing the binarization performance only by 0.55%.

    Download full text (pdf)
    fulltext