31 |
Mapping Stockholm's Bike-share Future : A GIS-based Analysis of Bicycle-sharing Stations in Stockholm / Kartläggning av Stockholms lånecykelsystem : En GIS-analys av lånecykelstationer i StockholmHagwall, Rut January 2023 (has links)
In cities all over the globe, bicycle-sharing systems are being implemented as a way of promoting bicycling as the primary mode of transportation. Cities encourage the residents to bicycle as a way of improving local environments and reducing traffic congestion. A step in this direction is providing a bicycle-sharing system, which increases the accessibility and mobility in a city. For the availability of a bicycle-sharing system to be maximized, the locations of the docking stations must be carefully selected and analyzed. Several studies have been conducted where the availability of bicycle-sharing systems have been evaluated, using different approaches. However, no studies have been conducted in Stockholm on the newly established Stockholm eBikes bicycle-sharing system. Thus, this thesis aims to evaluate the location of bicycle-sharing stations and determine the most suitable locations of those in Stockholm. This is done through a GIS-based MCDM method which applies an Analytical Hierarchy Process to weigh the criteria that must be considered. The analysis is done in QGIS, an open-source GIS-software, with data from OpenStreetMap and local data sources. The results indicate that the suitability of the current bicycle-sharing stations in Stockholm is high considering the analyzed criteria. Further, a suggestion is given for locations where the suitability for bicycle-sharing stations is high. This suggestion proposes new locations in Stockholm where a bicycle- sharing station could increase the availability of the bicycle-sharing system as well as the mobility in the city.
|
32 |
Artificiell Intelligence och Beslutstödssystem : Hur kan AI påverka verksamhetsstyrning / Artificial Intelligence and Decision Support Systems : How can organizational governance be impacted by AILundström, Anton, Aldijana, Sisic January 2023 (has links)
Dagens samhälle genomsyras av olika teknologier som påverkar människan, ekonomin och samhället. Numera besitter verksamheter stora datamängder som behöver registreras och struktureras och detta kan göras med hjälp av ett beslutstödsystem som ger underlag till beslutsfattare. I och med den stora och fortsatt ökade datamängden som behöver registreras och analyseras begränsas människans kognitiva förmåga till att hantera all denna data på egen hand. Som en lösning till denna problematik kan Artificial Intelligence (AI) användas. Syftet med denna forskningsstudie är att undersöka hur AI kan påverka beslutstödsystem inom verksamhetsstyrning. Fokuset grundar sig inom tre aspekter- planering, analys och uppföljning. För att besvara forskningsmålet har en djupare analys genomförts i form av en kvalitativ ansats, där sex deltagare intervjuats. Dessa intervjuer var semistrukturerade och enbart personer med välinsatta kunskaper inom beslutsstödsystem och AI har deltagit. Litteraturstudien, som baseras på tidigare forskning om AI och beslutsstödsystem och hur dessa två fungerar tillsammans, gav en grund för analysering, förklaring och diskussion tillsammans med den empiriska insamlade datan. Med hjälp av den insamlade datan kunde sedan intervjuerna analyseras tematiskt. Resultatet visade att AI:ns förmågor medför fördelar hos verksamheter genom ökadprestanda, effektivisering av strukturerad och ostrukturerad data samt frigör tid hosbeslutsfattare. Baserat på resultatet belystes det att beslutstödsystem kan enbart göra relativt enkla analyser på strukturerad data medan den är begränsad på ostruktureraddata. I samband med detta framhäver resultatet att verksamheter behöver även bearbeta extern information såsom omvärldsbevakningen. På så sätt ger teknologin användarna bästa möjliga beslutsunderlag samt då ett bredare beslutsunderlag tas fram och vidare förbättra planering, analys och uppföljning genom att AI kan analysera och samla in data från olika datakällor. Däremot behöver människan alltid vara närvarande i beslutsfattandet då AI besitter också begränsningar vilket kankompletteras med människan. / In today's society there are various technologies which affect people, the economy and society. Nowadays, businesses have large amounts of data that need to be registered and structured and this can be done with the help of a decision support system that provides information to decision makers. With the large amount of data being established even today, the human cognitive ability is limited to handling allthis data on their own. As a solution to this problem, AI can be used. The purpose of this research study is to investigate how AI can affect decision support systems in operations management. The focus is based on three aspects -planning, analysis and follow-up. In order to answer the research aim, a qualitative approach has been used where six participants were interviewed. These interviews were semi-structured and only people with well-versed knowledge in decision support systems and AI have participated. The literature study, which is based on previous research on AI and decision support systems and how the two work together, provided a basis for analysis, explanation and discussion along with the empirical data collected. As a result of the collected data, the interviews were analyzed thematically. The result showed that AI's capabilities bring benefits to businesses through increased performance, efficiency of structured and unstructured data and frees uptime for decision makers. Based on the results, it was highlighted that decision support systems can only perform relatively simple analyzes on structured data while it is limited on unstructured data. In connection with this, the result highlights that businesses also need to process external information such as monitoring of the environment. In this way, the technology provides users with the best possible basis for decision-making. This is because a broader basis for decision-making is produced and therefore improves planning, analysis and follow-up as AI can analyze and collect data from different data sources. However, the human always needs to be present in the decision-making as AI also has limitations which can be supplemented with the human.
|
33 |
Integration of magnetic resonance spectroscopic imaging into the radiotherapy treatment planning / Intégration des cartes métaboliques d'imagerie spectroscopique à la planification de radiothérapieLaruelo Fernandez, Andrea 24 May 2016 (has links)
L'objectif de cette thèse est de proposer de nouveaux algorithmes pour surmonter les limitations actuelles et de relever les défis ouverts dans le traitement de l'imagerie spectroscopique par résonance magnétique (ISRM). L'ISRM est une modalité non invasive capable de fournir la distribution spatiale des composés biochimiques (métabolites) utilisés comme biomarqueurs de la maladie. Les informations fournies par l'ISRM peuvent être utilisées pour le diagnostic, le traitement et le suivi de plusieurs maladies telles que le cancer ou des troubles neurologiques. Cette modalité se montre utile en routine clinique notamment lorsqu'il est possible d'en extraire des informations précises et fiables. Malgré les nombreuses publications sur le sujet, l'interprétation des données d'ISRM est toujours un problème difficile en raison de différents facteurs tels que le faible rapport signal sur bruit des signaux, le chevauchement des raies spectrales ou la présence de signaux de nuisance. Cette thèse aborde le problème de l'interprétation des données d'ISRM et la caractérisation de la rechute des patients souffrant de tumeurs cérébrales. Ces objectifs sont abordés à travers une approche méthodologique intégrant des connaissances a priori sur les données d'ISRM avec une régularisation spatio-spectrale. Concernant le cadre applicatif, cette thèse contribue à l'intégration de l'ISRM dans le workflow de traitement en radiothérapie dans le cadre du projet européen SUMMER (Software for the Use of Multi-Modality images in External Radiotherapy) financé par la Commission européenne (FP7-PEOPLE-ITN). / The aim of this thesis is to propose new algorithms to overcome the current limitations and to address the open challenges in the processing of magnetic resonance spectroscopic imaging (MRSI) data. MRSI is a non-invasive modality able to provide the spatial distribution of relevant biochemical compounds (metabolites) commonly used as biomarkers of disease. Information provided by MRSI can be used as a valuable insight for the diagnosis, treatment and follow-up of several diseases such as cancer or neurological disorders. Obtaining accurate and reliable information from in vivo MRSI signals is a crucial requirement for the clinical utility of this technique. Despite the numerous publications on the topic, the interpretation of MRSI data is still a challenging problem due to different factors such as the low signal-to-noise ratio (SNR) of the signals, the overlap of spectral lines or the presence of nuisance components. This thesis addresses the problem of interpreting MRSI data and characterizing recurrence in tumor brain patients. These objectives are addressed through a methodological approach based on novel processing methods that incorporate prior knowledge on the MRSI data using a spatio-spectral regularization. As an application, the thesis addresses the integration of MRSI into the radiotherapy treatment workflow within the context of the European project SUMMER (Software for the Use of Multi-Modality images in External Radiotherapy) founded by the European Commission (FP7-PEOPLE-ITN framework).
|
34 |
Méthodes pour l'électroencéphalographie multi-sujet et application aux interfaces cerveau-ordinateur / Methods for multi-subject electroencephalography and application to brain-computer interfacesKorczowski, Louis 17 October 2018 (has links)
L'étude par neuro-imagerie de l'activité de plusieurs cerveaux en interaction (hyperscanning) permet d'étendre notre compréhension des neurosciences sociales. Nous proposons un cadre pour l'hyperscanning utilisant les interfaces cerveau-ordinateur multi-utilisateur qui inclut différents paradigmes sociaux tels que la coopération ou la compétition. Les travaux de cette thèse comportent trois contributions interdépendantes. Notre première contribution est le développement d'une plateforme expérimentale sous la forme d'un jeu vidéo multijoueur, nommé Brain Invaders 2, contrôlé par la classification de potentiels évoqués visuels enregistrés par électroencéphalographie (EEG). Cette plateforme est validée par deux protocoles expérimentaux comprenant dix-neuf et vingt-deux paires de sujets et utilise différentes approches de classification adaptative par géométrie riemannienne. Ces approches sont théoriquement et expérimentalement comparées et nous montrons la supériorité de la fusion des classifieurs indépendants sur la classification d'un hypercerveau durant la seconde contribution. L'analyse de coïncidence des signaux entre les individus est une approche classique pour l'hyperscanning, elle est pourtant difficile quand les signaux EEG concernés sont transitoires avec une grande variabilité (intra- et inter-sujet) spatio-temporelle et avec un faible rapport signal-à-bruit. En troisième contribution, nous proposons un nouveau modèle composite de séparation aveugle de sources physiologiquement plausibles permettant de compenser cette variabilité. Une solution par diagonalisation conjointe approchée est proposée avec une implémentation d'un algorithme de type Jacobi. A partir des données de Brain Invaders 2, nous montrons que cette solution permet d'extraire simultanément des sources d'artéfacts, des sources d'EEG évoquées et des sources d'EEG continues avec plus de robustesse et de précision que les modèles existants. / The study of several brains interacting (hyperscanning) with neuroimagery allows to extend our understanding of social neurosciences. We propose a framework for hyperscanning using multi-user Brain-Computer Interfaces (BCI) that includes several social paradigms such as cooperation or competition. This dissertation includes three interdependent contribution. The first contribution is the development of an experimental platform consisting of a multi-player video game, namely Brain Invaders 2, controlled by classification of visual event related potentials (ERP) recorded by electroencephalography (EEG). The plateform is validated through two experimental protocols including nineteen and twenty two pairs of subjects while using different adaptive classification approaches using Riemannian geometry. Those approaches are theoretically and experimentally compared during the second contribution ; we demonstrates the superiority in term of accuracy of merging independent classifications over the classification of the hyperbrain during the second contribution. Analysis of inter-brain synchronizations is a common approach for hyperscanning, however it is challenging for transient EEG waves with an great spatio-temporal variability (intra- and inter-subject) and with low signal-to-noise ratio such as ERP. Therefore, as third contribution, we propose a new blind source separation model, namely composite model, to extract simultaneously evoked EEG sources and ongoing EEG sources that allows to compensate this variability. A solution using approximate joint diagonalization is given and implemented with a fast Jacobi-like algorithm. We demonstrate on Brain Invaders 2 data that our solution extracts simultaneously evoked and ongoing EEG sources and performs better in term of accuracy and robustness compared to the existing models.
|
35 |
Méthodes de séparation aveugle de sources et application à l'imagerie hyperspectrale en astrophysique / Blind source separation methods and applications to astrophysical hyperspectral dataBoulais, Axel 15 December 2017 (has links)
Ces travaux de thèse concernent le développement de nouvelles méthodes de séparation aveugle de mélanges linéaires instantanés pour des applications à des données hyperspectrales en astrophysique. Nous avons proposé trois approches pour effectuer la séparation des données. Une première contribution est fondée sur l'hybridation de deux méthodes existantes de séparation aveugle de source (SAS) : la méthode SpaceCORR nécessitant une hypothèse de parcimonie et une méthode de factorisation en matrices non négatives (NMF). Nous montrons que l'utilisation des résultats de SpaceCORR pour initialiser la NMF permet d'améliorer les performances des méthodes utilisées seules. Nous avons ensuite proposé une première méthode originale permettant de relâcher la contrainte de parcimonie de SpaceCORR. La méthode MASS (pour \textit{Maximum Angle Source Separation}) est une méthode géométrique basée sur l'extraction de pixels mono-sources pour réaliser la séparation des données. Nous avons également étudié l'hybridation de MASS avec la NMF. Enfin, nous avons proposé une seconde approche permettant de relâcher la contrainte de parcimonie de SpaceCORR. La méthode originale SIBIS (pour \textit{Subspace-Intersection Blind Identification and Separation}) est une méthode géométrique basée sur l'identification de l'intersection de sous-espaces engendrés par des régions de l'image hyperspectrale. Ces intersections permettent, sous une hypothèse faible de parcimonie, de réaliser la séparation des données. L'ensemble des approches proposées dans ces travaux ont été validées par des tests sur données simulées puis appliquées sur données réelles. Les résultats obtenus sur ces données sont très encourageants et sont comparés à ceux obtenus par des méthodes de la littérature. / This thesis deals with the development of new blind separation methods for linear instantaneous mixtures applicable to astrophysical hyperspectral data sets. We propose three approaches to perform data separation. A first contribution is based on hybridization of two existing blind source separation (BSS) methods: the SpaceCORR method, requiring a sparsity assumption, and a non-negative matrix factorization (NMF) method. We show that using SpaceCORR results to initialize the NMF improves the performance of the methods used alone. We then proposed a first original method to relax the sparsity constraint of SpaceCORR. The method called MASS (Maximum Angle Source Separation) is a geometric method based on the extraction of single-source pixels to achieve the separation of data. We also studied the hybridization of MASS with the NMF. Finally, we proposed an approach to relax the sparsity constraint of SpaceCORR. The original method called SIBIS (Subspace-Intersection Blind Identification and Separation) is a geometric method based on the identification of intersections of subspaces generated by regions of the hyperspectral image. Under a sparsity assumption, these intersections allow one to achieve the separation of the data. The approaches proposed in this manuscript have been validated by experimentations on simulated data and then applied to real data. The results obtained on our data are very encouraging and are compared with those obtained by methods from the literature.
|
36 |
A Real-Time Classification approach of a Human Brain-Computer Interface based on Movement Related ElectroencephalogramMileros, Martin D. January 2004 (has links)
<p>A Real-Time Brain-Computer Interface is a technical system classifying increased or decreased brain activity in Real-Time between different body movements, actions performed by a person. Focus in this thesis will be on testing algorithms and settings, finding the initial time interval and how increased activity in the brain can be distinguished and satisfyingly classified. The objective is letting the system give an output somewhere within 250ms of a thought of an action, which will be faster than a persons reaction time. </p><p>Algorithms in the preprocessing were Blind Signal Separation and the Fast Fourier Transform. With different frequency and time interval settings the algorithms were tested on an offline Electroencephalographic data file based on the "Ten Twenty" Electrode Application System, classified using an Artificial Neural Network. </p><p>A satisfying time interval could be found between 125-250ms, but more research is needed to investigate that specific interval. A reduction in frequency resulted in a lack of samples in the sample window preventing the algorithms from working properly. A high frequency is therefore proposed to help keeping the sample window small in the time domain. Blind Signal Separation together with the Fast Fourier Transform had problems finding appropriate correlation using the Ten-Twenty Electrode Application System. Electrodes should be placed more selectively at the parietal lobe, in case of requiring motor responses.</p>
|
37 |
Modélisation gaussienne de rang plein des mélanges audio convolutifs appliquée à la séparation de sources.Duong, Quang-Khanh-Ngoc 15 November 2011 (has links) (PDF)
Nous considérons le problème de la séparation de mélanges audio réverbérants déterminés et sous-déterminés, c'est-à-dire l'extraction du signal de chaque source dans un mélange multicanal. Nous proposons un cadre général de modélisation gaussienne où la contribution de chaque source aux canaux du mélange dans le domaine temps-fréquence est modélisée par un vecteur aléatoire gaussien de moyenne nulle dont la covariance encode à la fois les caractéristiques spatiales et spectrales de la source. A n de mieux modéliser la réverbération, nous nous aff ranchissons de l'hypothèse classique de bande étroite menant à une covariance spatiale de rang 1 et nous calculons la borne théorique de performance atteignable avec une covariance spatiale de rang plein. Les ré- sultats expérimentaux indiquent une augmentation du rapport Signal-à-Distorsion (SDR) de 6 dB dans un environnement faiblement à très réverbérant, ce qui valide cette généralisation. Nous considérons aussi l'utilisation de représentations temps-fréquence quadratiques et de l'échelle fréquentielle auditive ERB (equivalent rectangular bandwidth) pour accroître la quantité d'information exploitable et décroître le recouvrement entre les sources dans la représentation temps-fréquence. Après cette validation théorique du cadre proposé, nous nous focalisons sur l'estimation des paramètres du modèle à partir d'un signal de mélange donné dans un scénario pratique de séparation aveugle de sources. Nous proposons une famille d'algorithmes Expectation-Maximization (EM) pour estimer les paramètres au sens du maximum de vraisemblance (ML) ou du maximum a posteriori (MAP). Nous proposons une famille d'a priori de position spatiale inspirée par la théorie de l'acoustique des salles ainsi qu'un a priori de continuité spatiale. Nous étudions aussi l'utilisation de deux a priori spectraux précédemment utilisés dans un contexte monocanal ou multicanal de rang 1: un a priori de continuité spatiale et un modèle de factorisation matricielle positive (NMF). Les résultats de séparation de sources obtenus par l'approche proposée sont comparés à plusieurs algorithmes de base et de l'état de l'art sur des mélanges simulés et sur des enregistrements réels dans des scénarios variés.
|
38 |
A Real-Time Classification approach of a Human Brain-Computer Interface based on Movement Related ElectroencephalogramMileros, Martin D. January 2004 (has links)
A Real-Time Brain-Computer Interface is a technical system classifying increased or decreased brain activity in Real-Time between different body movements, actions performed by a person. Focus in this thesis will be on testing algorithms and settings, finding the initial time interval and how increased activity in the brain can be distinguished and satisfyingly classified. The objective is letting the system give an output somewhere within 250ms of a thought of an action, which will be faster than a persons reaction time. Algorithms in the preprocessing were Blind Signal Separation and the Fast Fourier Transform. With different frequency and time interval settings the algorithms were tested on an offline Electroencephalographic data file based on the "Ten Twenty" Electrode Application System, classified using an Artificial Neural Network. A satisfying time interval could be found between 125-250ms, but more research is needed to investigate that specific interval. A reduction in frequency resulted in a lack of samples in the sample window preventing the algorithms from working properly. A high frequency is therefore proposed to help keeping the sample window small in the time domain. Blind Signal Separation together with the Fast Fourier Transform had problems finding appropriate correlation using the Ten-Twenty Electrode Application System. Electrodes should be placed more selectively at the parietal lobe, in case of requiring motor responses.
|
39 |
Blind source separation based on joint diagonalization of matrices with applications in biomedical signal processingZiehe, Andreas January 2005 (has links)
<p>This thesis is concerned with the solution of the blind source
separation problem (BSS). The BSS problem occurs frequently in various
scientific and technical applications. In essence, it consists in
separating meaningful underlying components out of a mixture of a
multitude of superimposed signals.</p>
<P>
In the recent research literature there are two related approaches to
the BSS problem: The first is known as Independent Component Analysis (ICA),
where the goal is to transform the data such that the components
become as independent as possible. The second is based on the notion
of diagonality of certain characteristic matrices derived from the
data. Here the goal is to transform the matrices such that they become
as diagonal as possible. In this thesis we study
the latter method of approximate joint diagonalization (AJD) to
achieve a solution of the BSS problem. After an introduction to the
general setting, the thesis provides an overview on particular choices
for the set of target matrices that can be used for BSS by joint
diagonalization.</p>
<P>
As the main contribution of the thesis, new algorithms for
approximate joint diagonalization of several matrices with
non-orthogonal transformations are developed.</p>
<P>
These newly developed algorithms will be tested on synthetic
benchmark datasets and compared to other previous diagonalization
algorithms.</p>
<P>
Applications of the BSS methods to biomedical signal processing are
discussed and exemplified with real-life data sets of multi-channel
biomagnetic recordings.</p> / <p>Diese Arbeit befasst sich mit der Lösung des Problems der blinden
Signalquellentrennung (BSS). Das BSS Problem tritt häufig in vielen
wissenschaftlichen und technischen Anwendungen auf. Im Kern besteht das
Problem darin, aus einem Gemisch von überlagerten Signalen die
zugrundeliegenden Quellsignale zu extrahieren.</p>
<P>
In wissenschaftlichen Publikationen zu diesem Thema werden
hauptsächlich zwei Lösungsansätze verfolgt:</p>
<P>
Ein Ansatz ist die sogenannte "Analyse der unabhängigen
Komponenten", die zum Ziel hat, eine lineare Transformation <B>V</B> der
Daten <B>X</B> zu finden, sodass die Komponenten U<sub>n</sub> der transformierten
Daten <B>U</B> = <B> V X</B> (die sogenannten "independent components") so
unabhängig wie möglich sind.
Ein anderer Ansatz beruht auf einer simultanen Diagonalisierung
mehrerer spezieller Matrizen, die aus den Daten gebildet werden.
Diese Möglichkeit der Lösung des Problems der blinden
Signalquellentrennung bildet den Schwerpunkt dieser Arbeit.</p>
<P>
Als Hauptbeitrag der vorliegenden Arbeit präsentieren wir neue
Algorithmen zur simultanen Diagonalisierung mehrerer Matrizen mit
Hilfe einer nicht-orthogonalen Transformation.</p>
<P>
Die neu entwickelten Algorithmen werden anhand von numerischen
Simulationen getestet und mit bereits bestehenden
Diagonalisierungsalgorithmen verglichen. Es zeigt sich, dass unser
neues Verfahren sehr effizient und leistungsfähig ist. Schließlich
werden Anwendungen der BSS Methoden auf Probleme der biomedizinischen
Signalverarbeitung erläutert und anhand von realistischen
biomagnetischen Messdaten wird die Nützlichkeit in der explorativen
Datenanalyse unter Beweis gestellt.</p>
|
40 |
Optimizing dense wireless networks of MIMO linksCortes-Pena, Luis Miguel 27 August 2014 (has links)
Wireless communication systems have exploded in popularity over the past few decades. Due to their popularity, the demand for higher data rates by the users, and the high cost of wireless spectrum, wireless providers are actively seeking ways to improve the spectral efficiency of their networks. One promising technique to improve spectral efficiency is to equip the wireless devices with multiple antennas. If both the transmitter and receiver of a link are equipped with multiple antennas, they form a multiple-input multiple-output (MIMO) link.
The multiple antennas at the nodes provide degrees-of-freedom that can be used for either sending multiple streams of data simultaneously (a technique known as spatial multiplexing), or for suppressing interference through linear combining, but not both. Due to this trade-off, careful allocation of how many streams each link should carry is important to ensure that each node has enough degrees-of-freedom available to suppress the interference and support its desired streams. How the streams are sent and received and how interference is suppressed is ultimately determined by the beamforming weights at the transmitters and the combining weights at the receivers. Determining these weights is, however, made difficult by their inherent interdependency.
Our focus is on unplanned and/or dense single-hop networks, such as WLANs and femtocells, where each single-hop network is composed of an access point serving several associated clients. The objective of this research is to design algorithms for maximizing the performance of dense single-hop wireless networks of MIMO links. We address the problems of determining which links to schedule together at each time slot, how many streams to allocate to each link (if any), and the beamforming and combining weights that support those streams.
This dissertation describes four key contributions as follows:
- We classify any interference suppression technique as either unilateral interference suppression or bilateral interference suppression. We show that a simple bilateral interference suppression approach outperforms all known unilateral interference suppression approaches, even after searching for the best unilateral solution.
- We propose an algorithm based on bilateral interference suppression whose goal is to maximize the sum rate of a set of interfering MIMO links by jointly optimizing which subset of transmitters should transmit, the number of streams for each transmitter (if any), and the beamforming and combining weights that support those streams.
- We propose a framework for optimizing dense single-hop wireless networks. The framework implements techniques to address several practical issues that arise when implementing interference suppression, such as the overhead of performing channel measurements and communicating channel state information, the overhead of computing the beamforming and combining weights, and the overhead of cooperation between the access points.
- We derive the optimal scheduler that maximizes the sum rate subject to proportional fairness.
Simulations in ns-3 show that the framework, using the optimal scheduler, increases the proportionally fair aggregate goodput by up to 165% as compared to the aggregate goodput of 802.11n for the case of four interfering single-hop wireless networks with two clients each.
|
Page generated in 0.0322 seconds