Time management and distance evaluation have long been a difficult task for workers and companies. This thesis studies 6712 pothole coordinates in Gävle municipality, and evaluates the minimal total road distance needed to visit each pothole once, and return to an initial pothole. Road distance is approximated using the flight distance and a simple random sample of 113 road distances from Google Maps. Thereafter, the data from the sample along with a Bayesian approach is used to find a distribution of the ratio between road distance and flight distance. Lastly, a solution to the shortest distance is devised using the Nearest Neighbor algorithm (NNA) and Simulated Annealing (SA). Computational work is performed with Markov Chain Monte Carlo (MCMC). The results provide a minimal road distance of 717 km. / Tidshantering och distansutvärdering är som regel en svår uppgift för arbetare och företag. Den här uppsatsen studerar 6712 potthål i Gävle kommun, och utvärderar den bilväg som på kortast sträcka besöker varje potthål och återgår till den ursprungliga startpunkten. Bilvägsavståndet mellan potthålen uppskattas med hjälp av flygavståndet, där ett obundet slumpmässigt urval av 113 bilvägsavstånd mellan potthålens koordinatpunkter dras. Bilvägsdistanser hittas med hjälp av Google Maps. Därefter används data från urvalet tillsammans med en bayesiansk modell för att hitta en fördelning för förhållandet mellan bilvägsavstånd och flygavstånd. Slutligen framförs en lösning på det kortaste bilvägsavståndet med hjälp av en Nearest Neighbour algoritm (NNA) samt Simulated Annealing (SA). Statistiskt beräkningsarbete utförs med Markov Chain Monte Carlo (MCMC). Resultaten ger en kortaste bilvägssträcka på 717 km.

Purpose – The purpose of the study is to expand the knowledge of how wheel motor currents can be combined with machine learning to be used in a collision detection system for autonomous robots, in order to decrease the number of external sensors and open new design opportunities and lowering production costs. Method – The study is conducted with design science research where two artefacts are developed in a cooperation with Globe Tools Group. The artefacts are evaluated in how they categorize data given by an autonomous robot in the two categories collision and non-collision. The artefacts are then tested by generated data to analyse their ability to categorize. Findings – Both artefacts showed a 100 % accuracy in detecting the collisions in the given data by the autonomous robot. In the second part of the experiment the artefacts show that they have different decision boundaries in how they categorize the data, which will make them useful in different applications. Implications – The study contributes to an expanding knowledge in how machine learning and wheel motor currents can be used in a collision detection system. The results can lead to lowering production costs and opening new design opportunities. Limitations – The data used in the study is gathered by an autonomous robot which only did frontal collisions on an artificial lawn. Keywords – Machine learning, K-Nearest Neighbour, Multilayer Perceptron, collision detection, autonomous robots, Collison detection based on current. / Syfte – Studiens syfte är att utöka kunskapen om hur hjulmotorstömmar kan kombineras med maskininlärning för att användas vid kollisionsdetektion hos autonoma robotar, detta för att kunna minska antalet krävda externa sensorer hos dessa robotar och på så sätt öppna upp design möjligheter samt minska produktionskostnader Metod – Studien genomfördes med design science research där två artefakter utvecklades i samarbete med Globe Tools Group. Artefakterna utvärderades sedan i hur de kategoriserade kollisioner utifrån en given datamängd som genererades från en autonom gräsklippare. Studiens experiment introducerade sedan in data som inte ingick i samma datamängd för att se hur metoderna kategoriserade detta. Resultat – Artefakterna klarade med 100% noggrannhet att detektera kollisioner i den giva datamängden som genererades. Dock har de två olika artefakterna olika beslutsregioner i hur de kategoriserar datamängderna till kollision samt icke-kollisioner, vilket kan ge dom olika användningsområden Implikationer – Examensarbetet bidrar till en ökad kunskap om hur maskininlärning och hjulmotorströmmar kan användas i ett kollisionsdetekteringssystem. Studiens resultat kan bidra till minskade kostnader i produktion samt nya design möjligheter Begränsningar – Datamängden som användes i studien samlades endast in av en autonom gräsklippare som gjorde frontalkrockar med underlaget konstgräs. Nyckelord – Maskininlärning, K-nearest neighbor, Multi-layer perceptron, kollisionsdetektion, autonoma robotar

Thesis (MSc)--Stellenbosch University, 2012. / ENGLISH ABSTRACT: This research considered the automated remote sensing-based classification of wetland extent within the Nuwejaars and Heuningnes River systems on the Agulhas Plain. The classification process was based on meaningful image objects created through image segmentation rather than on single pixels. An expert system classifier was compared to a nearest-neighbour supervised classifier, and one multispectral (SPOT 5) image (dry season) and two C-band, VV-polarisation synthetic aperture radar (SAR: ERS-2) images (dry and wet season) were used separately and in combination. Classifications were performed within two subset areas. Final classes identified were Permanent waterbody, Other wetland and Non-wetland. Statistical accuracy assessment was performed. Validation data was derived from a combination of high-resolution aerial photographs, the SPOT 5 image, high-resolution imagery on Google Earth and observations during a field visit. Wetland extent was defined as the total extent of wetland-specific vegetation, unvegetated seasonal pans and waterbodies. More detailed classes were originally envisaged, but available validation data was not considered adequate for assessing their accuracy with any confidence. The supervised classifier was found to be more accurate overall than the developed expert system. The difference between the two was however not always significant. The two SAR images alone did not contain sufficient information for the accurate classification of Agulhas wetlands’ extent, with recorded overall accuracies not exceeding 65% regardless of the classifier used. The SPOT image alone achieved accuracies higher than 80%; this was considered a good result. In comparison, combining the SAR and SPOT data did not improve the classification accuracy. The potential of the expert system to be applied with little modification to images acquired over other areas or over the same area in other years should be further investigated. However, several reservations are noted in this regard. Future research could potentially improve the results obtained from supervised classification by augmenting it with expert system rules to identify more complicated classes. KEYWORDS ERS-2, SPOT 5, SAR, wetlands, expert system classifier, nearest-neighbour supervised classifier / AFRIKAANSE OPSOMMING: Hierdie navorsing het die geoutomatiseerde afstandswaarneminggebaseerde klassifikasie van vleilandomvang binne die Nuwejaars- en Heuningnesrivier stelsels op die Agulhasvlakte ondersoek. Die klassifikasieproses was gebaseer op betekenisvolle beeldobjekte geskep deur middel van beeldsegmentasie eerder as op enkele beeldelemente. ‘n Deskundige stelsel klassifiseerder is vergelyk met ‘n naaste-naburige gerigte klassifiseerder. Een multispektrale (SPOT 5) beeld vir die droë seisoen, sowel as twee C-band, VV-polarisasie sintetiese diafragma radar (SAR, ERS2) beelde (vir die droë en nat seisoene) is afsonderlik en in kombinasie gebruik. Klassifikasies is uitgevoer binne twee sub-areas in die beelde. Finale klasse wat geïdentifiseer is was Permanente waterliggaam, Ander vleiland en Nie-vleiland. Statistiese akkuraatheidsassessering is uitgevoer. Verwysingsdata is geskep vanuit ‘n kombinasie van hoë- resolusie lugfoto’s, die SPOT 5 beeld, hoë-resolusie beelde op Google Earth en waarnemings tydens ‘n besoek aan die studiegebied. Vleiland omvang is gedefinieer as die totale omvang van vleiland-spesifieke plantegroei, onbegroeide seisoenale panne en waterliggame. Die gerigte klassifiseerder blyk om oor die algemeen meer akkuraat as die ontwikkelde deskundige stelsel te wees. Die verskil was egter nie altyd beduidend nie. Die twee SAR beelde alleen het nie genoegsame inligting bevat vir die akkurate klassifikasie van Agulhas-vleilande se omvang nie, met behaalde algehele akkuraatheidsvlakke wat nie 65% oorskry het nie, ongeag van die klassifiseerder. Die SPOT-beeld alleenlik het algehele akkuraathede van meer as 80% behaal; wat as ‘n goeie resultaat beskou kan word. In vergelyking hiermee kon die kombinering van SAR- en SPOT-data nie ‘n verbetering teweeg bring nie. Die potensiaal van die deskundige stelsel om met min aanpassing op beelde van ander gebiede of van dieselfde gebied in ander jare toegepas te word, verg verdere ondersoek. Verskeie voorbehoude word egter in hierdie verband gemeld. Toekomstige navorsing kan potensieel die resultate van gerigte klassifikasie verbeter deur dit aan te vul met deskundige stelsel reëls vir die klassifikasie van meer komplekse klasse. TREFWOORDE ERS-2, SPOT 5, SAR, vleilande, deskundige stelsel klassifiseerder, naaste-naburige gerigte klassifiseerder.

This thesis introduces readers various methods that are currently used for detection of network-based applications. Further part deals with selection of appropriate detection method and implementation of proof-of-concept script, including testing its reliability and accuracy. Chosen detection algorithm is based on statistics data from network flows of tested network communication. Due to its final solution does not depend on whether communication is encrypted or not. Next part contains several possible variants of how to integrate proposed solution in the current architecture of the existing product Kernun UTM --- which is firewall produced by Trusted Network Solutions a.s. company. Most suitable variant is chosen and described furthermore in more details. Finally there is also mentioned plan for further developement and possible ways how to improve final solution.

No description available.

The National Library of Sweden uses optical character recognition software to digitize their collections of historical newspapers. The purpose of such software is first to automatically segment text and images from scanned newspaper pages, and second to read the contents of the identified text regions. While the raw text is often digitized successfully, important contextual information regarding whether the text constitutes for example a header, a section title or the body text of an article is not captured. These characteristics are easy for a human to distinguish, yet they remain difficult for a machine to recognize. The main purpose of this thesis is to investigate how well section titles in the newspaper Svenska Dagbladet can be classified by using so called image embeddings as features. A secondary aim is to examine whether section titles become harder to classify in older newspaper data. Lastly, we explore if manual annotation work can be reduced using the predictions of a semi-supervised classifier to help in the labeling process.  Results indicate the use of image embeddings help quite substantially in classifying section titles. Datasets from three different time periods: 1990-1997, 2004-2013, and 2017 and onwards were sampled and annotated. The best performing model (Xgboost) achieved macro F1 scores of 0.886, 0.936 and 0.980 for the respective time periods. The results also showed classification became more difficult on older newspapers. Furthermore, a semi-supervised classifier managed an average precision of 83% with only single section title examples, showing promise as way to speed up manual annotation of data.

The threaded fastener is by far the most common method for securing components together and plays a significant role in determining the quality of a product. Atlas Copco offers industrial tools for tightening these fasteners, which are today suffering from errors in the applied torque. These errors have been found to behave in periodic patterns which indicate that the errors can be predicted and therefore compensated for. However, this is only possible by knowing the rotational position of the tool. Atlas Copco is interested in the possibility of acquiring this rotational position without installing sensors inside the tools. To address this challenge, the thesis explores the feasibility of estimating the rotational position by analysing the behaviour of the errors and finding periodicities in the data. The objective is to determine whether these periodicities can be used to accurately estimate the rotation of the torque errors of unknown data relative to errors of data where the rotational position is known. The tool analysed in this thesis exhibits a periodic pattern in the torque error with a period of 11 revolutions.  Two methods for estimating the rotational position were evaluated: a simple nearest neighbour method that uses mean squared error (MSE) as distance measure, and a more complex circular fully convolutional network (CFCN). The project involved data collection from a custom-built setup. However, the setup was not fully completed, and the models were therefore evaluated on a limited dataset. The results showed that the CFCN method was not able to identify the rotational position of the signal. The insufficient size of the data is discussed to be the cause for this. The nearest neighbour method, however, was able to estimate the rotational position correctly with 100% accuracy across 1000 iterations, even when looking at a fragment of a signal as small as 40%. Unfortunately, this method is computationally demanding and exhibits slow performance when applied to large datasets. Consequently, adjustments are required to enhance its practical applicability. In summary, the findings suggest that the nearest neighbour method is a promising approach for estimating the rotational position and could potentially contribute to improving the accuracy of tools. / Skruvförband är den vanligaste typen av förband för att sammanfoga komponenter och är avgörande för en produkts kvalitet. Atlas Copco tillverkar industriverktyg avsedda för sådana skruvförband, som dessvärre lider av små avvikelser i åtdragningsmomentet. Avvikelserna uppvisar ett konsekvent periodiskt mönster, vilket indikerar att de är förutsägbara och därför möjliga att kompenseras för. Det är dock endast möjligt genom att veta verktygets vinkelposition. Atlas Copco vill veta om det är möjligt att erhålla vinkelpositionen utan att installera sensorer i verktygen. Denna uppsats undersöker möjligheten att uppskatta vinkelpositionen genom att analysera beteendet hos avvikelserna i åtdragningsmomentet och identifiera periodiciteter i datan, samt undersöka om dessa periodiciteter kan utnyttjas för att uppskatta rotationen hos avvikelserna hos okänd data i förhållande till tidigare data. Det verktyget som används i detta projekt uppvisar en tydlig periodicitet med en period på 11 varv. Två metoder för att uppskatta vinkelpositionen utvärderades: en simpel nearest neighbour-metod som använder mean squared error (MSE) som mått för avstånd, och ett mer komplext circular fully convolutional network (CFCN). Projektet innefattade datainsamling från en egendesignad testrigg som tyvärr aldrig blev färdigställd, vilket medförde att utvärderingen av modellerna utfördes på ett begränsat dataset.  Resultatet indikerade att CFCN-metoden kräver en större datamängd för att kunna uppskatta rotationen hos den okända datan. Nearest neighbour-metoden lyckades uppskatta rotationen med 100% noggrannhet över 1000 iterationer, även när endast ett segment så litet som 40% av signalen utvärderades. Tyvärr lider denna metod av hög beräkningsbelastning och kräver förbättringar för att vara praktiskt tillämpbar. Sammantaget visade resultaten att nearest neighbour-metoden har potential att vara ett lovande tillvägagångssätt för att uppskatta vinkelpositionen och kan på så sätt bidra till förbättring av verktygens noggrannhet.

Several studies have been conducted within machine learning, and various variations have been applied to a wide spectrum of other fields. However, a thorough feasibility study within the payment processing industry using machine learning classifier algorithms is yet to be explored. Here, we construct a rule-based response vector and use that in combination with a magnitude of varying feature vectors across different machine learning classifier algorithms to try and determine whether individual transactions can be considered profitable from a business point of view. These algorithms include Naive-Bayes, AdaBoosting, Stochastic Gradient Descent, K-Nearest Neighbors, Decision Trees and Random Forests, all helped us build a model with a high performance that acts as a robust confirmation of both the benefits and a theoretical guide on the implementation of machine learning algorithms in the payment processing industry. The results as such are a firm confirmation on the benefits of data intensive models, even in complex industries similar to Swedbank Pay’s. These Implications help further boost innovation and revenue as they offer a better understanding of the current pricing mechanisms. / Många studier har utförts inom ämnet maskininlärning, och olika variationer har applicerats på ett brett spektrum av andra ämnen. Däremot, så har en ordentlig genomförbarhetsstudie inom betalningsleveransindustrin med hjälp av klassificeringsalgortimer har ännu ej utforskats. Här har vi konstruerat en regelbaserad responsvektor och använt den, tillsammans med en rad olika och varierande egenskapvektorer på olika maskininlärningsklassificeringsalgoritmer för att försöka avgöra ifall individuella transaktioner är lönsamma utifrån företagets perspektiv. Dessa algoritmer är Naive-Bayes, AdaBoosting, Stokastisk gradient medåkning, K- Närmaste grannar, beslutsträd och slumpmässiga beslutsskogar. Alla dessa har hjälpt oss bygga en teoretisk vägledning om implementering av maskininlärningsalgoritmer inom betalningsleveransindustrin. Dessa resultat är en robust bekräftelse på fördelarna av dataintensiva modeller även inom sådana komplexa industrier Swedbank Pay är verksamma inom. Implikationerna hjälper vidare att förstärka innovationen och öka intäkterna eftersom de erbjuder en bättre förståelse för deras nuvarande prissättningsmekanism.

La présente thèse s'intéresse à l'utilisation de méta-données textuelles pour l'analyse d'image. Nous cherchons à utiliser ces informations additionelles comme supervision faible pour l'apprentissage de modèles de reconnaissance visuelle. Nous avons observé un récent et grandissant intérêt pour les méthodes capables d'exploiter ce type de données car celles-ci peuvent potentiellement supprimer le besoin d'annotations manuelles, qui sont coûteuses en temps et en ressources. Nous concentrons nos efforts sur deux types de données visuelles associées à des informations textuelles. Tout d'abord, nous utilisons des images de dépêches qui sont accompagnées de légendes descriptives pour s'attaquer à plusieurs problèmes liés à la reconnaissance de visages. Parmi ces problèmes, la vérification de visages est la tâche consistant à décider si deux images représentent la même personne, et le nommage de visages cherche à associer les visages d'une base de données à leur noms corrects. Ensuite, nous explorons des modèles pour prédire automatiquement les labels pertinents pour des images, un problème connu sous le nom d'annotation automatique d'image. Ces modèles peuvent aussi être utilisés pour effectuer des recherches d'images à partir de mots-clés. Nous étudions enfin un scénario d'apprentissage multimodal semi-supervisé pour la catégorisation d'image. Dans ce cadre de travail, les labels sont supposés présents pour les données d'apprentissage, qu'elles soient manuellement annotées ou non, et absentes des données de test. Nos travaux se basent sur l'observation que la plupart de ces problèmes peuvent être résolus si des mesures de similarité parfaitement adaptées sont utilisées. Nous proposons donc de nouvelles approches qui combinent apprentissage de distance, modèles par plus proches voisins et méthodes par graphes pour apprendre, à partir de données visuelles et textuelles, des similarités visuelles spécifiques à chaque problème. Dans le cas des visages, nos similarités se concentrent sur l'identité des individus tandis que, pour les images, elles concernent des concepts sémantiques plus généraux. Expérimentalement, nos approches obtiennent des performances à l'état de l'art sur plusieurs bases de données complexes. Pour les deux types de données considérés, nous montrons clairement que l'apprentissage bénéficie de l'information textuelle supplémentaire résultant en l'amélioration de la performance des systèmes de reconnaissance visuelle.

Mit dem Begriff Wellenleiterquantenelektrodynamik (WQED) wird gemeinhin die Physik des quantisierten und in eindimensionalen Wellenleitern geführten Lichtes in Wechselwirkung mit einzelnen Emittern bezeichnet. In dieser Arbeit untersuche ich Effekte der WQED für einzelne Dreiniveausysteme (3NS) bzw. Paare von Zweiniveausystemen (2NS), die in den Wellenleiter eingebettet sind. Hierzu bediene ich mich hauptsächlich numerischer Methoden und betrachte die Modellsysteme im Rahmen der Drehwellennäherung. Ich untersuche die Dynamik der Streuung einzelner Photonen an einzelnen, in den Wellenleiter eingebetteten 3NS. Dabei analysiere ich den Einfluss dunkler bzw. nahezu dunkler Zustände der 3NS auf die Streuung und zeige, wie sich mit Hilfe stationärer elektrischer Treibfelder gezielt auf die Streuung einwirken lässt. Ich quantifiziere Verschränkung zwischen dem Lichtfeld im Wellenleiter und den Emittern mit Hilfe der Schmidt-Zerlegung und untersuche den Einfluss der Form der Einhüllenden eines Einzelphotonpulses auf die Ausbeute der Verschränkungserzeugung bei der Streuung des Photons an einem einzelnen Lambda-System im Wellenleiter. Hier zeigt sich, dass die Breite der Einhüllenden im k-Raum und die Emissionszeiten der beiden Übergänge des 3NS die maßgeblichen Parameter darstellen. Abschließend ergründe ich die Emissionsdynamik zweier im Abstand L in den Wellenleiter eingebetteter 2NS. Diese Dynamik wird insbesondere durch kavitätsartige und polaritonische Zustände des Systems aus Wellenleiter und Emitter ausschlaggebend beeinflusst. Bei der kollektiven Emission der 2NS treten - abhängig vom Abstand L - Sub- bzw. Superradianz auf. Dabei nimmt die Intensität dieser Effekte mit längerem Abstand L zu. Diese Eigenart lässt sich auf die Eindimensionalität des Wellenleiters zurückführen. / The field of waveguide quantum electrodynamics (WQED) deals with the physics of quantised light in one-dimensional (1D) waveguides coupled to single emitters. In this thesis, I investigate WQED effects for single three-level systems (3LS) and pairs of two-level systems (2LS), respectively, which are embedded in the waveguide. To this end, I utilise numerical techniques and consider all model systems within the rotating wave approximation. I investigate the dynamics of single-photon scattering by single, embedded 3LS. In doing so, I analyse the influence of dark and almost-dark states of the 3LS on the scattering dynamics. I also show, how stationary electrical driving fields can control the outcome of the scattering. I quantify entanglement between the waveguide''s light field and single emitters by utilising the Schmidt decomposition. I apply this formalism to a lambda-system embedded in a 1D waveguide and study the generation of entanglement by scattering single-photon pulses with different envelopes on the emitter. I show that this entanglement generation is mainly determined by the photon''s width in k-space and the 3LS''s emission times. Finally, I explore the emission dynamics of a pair of 2LS embedded by a distance L into the waveguide. These dynamics are primarily governed by bound states in the continuum and by polaritonic atom-photon bound-states. For collective emission processes of the two 2LS, sub- and superradiance appear and depend strongly on the 2LS''s distance: the effects increase for larger L. This is an exclusive property of the 1D nature of the waveguide.