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

Made available in DSpace on 2016-03-15T19:44:09Z (GMT). No. of bitstreams: 1 Hania Cecilia Pilan.pdf: 15559422 bytes, checksum: eae834aa2a5d0daddc074ad470e524e8 (MD5) Previous issue date: 2012-08-17 / Fundo Mackenzie de Pesquisa / The subject of this thesis is the analysis of the everyday life narratives of Sao Paulo's sidewalk residents and its (Re) meanings that enter the field of aesthetic needs. The human being is complex and at the same time transparent, desiring to be someone significant, uses mechanisms to survive as an individual among the society. And, when excluded from the group to which he belongs, he necessarily must (Re) mean, in order to join a new group. In the case of sidewalk residents, this action is exacerbated, becoming more evident the necessity of expression and the use of archetypes in the battle against invisibility within their social group and if possible, achieving to stand out among his peers. The narratives, conducted through interviews, allowed penetrate into a parallel world where neither time has the same value and setting as we were used to. In order to understand the narratives of this (Re) meaning world daily and achieve the proposed objectives, it was used as a theoretical study of social representations, with the cultural-historical psychology foundations, depth psychology and art contexts and concepts. Supported by these bibliographical sources, documentary, and especially in the participatory field research, it was possible to articulate a discussion of the aesthetic needs of the sidewalk's residents in their socio-historical context and their need to (re) signification. Among the various analyzed, we have chosen four main characters for their sensible aesthetic productions, which demonstrate the social segment in which they belong, to be analysis objects of their (RE) meanings. Among them, we were able to find heroes, faithful man, poets, painters, performers, bricoleurs, who have art as their mainspring of their social development, presenting archetypes to (Re) mean their world. / O objeto de estudo desta tese consiste na análise de narrativas do cotidiano dos moradores de calçada da cidade de São Paulo quanto as suas (Re) significações que adentram o campo das necessidades estéticas. O ser humano, complexo e ao mesmo tempo transparente, no afã de ser alguém significante, usa de mecanismos para sobreviver como indivíduo dentro da sociedade. E, quando excluído do grupo ao qual pertence, tem necessariamente que se (Re) significar, para inserir-se em um novo grupo. No caso dos moradores de calçada, essa ação é exacerbada tornando mais evidente a necessidade de expressão e o uso de arquétipos na batalha contra a invisibilidade dentro de seu grupo social e se possível, conseguindo se destacar entre seus pares. As narrativas, realizadas por meio de entrevistas, possibilitaram adentrar em um mundo paralelo, onde nem o tempo tem a mesma valia e marcação como fomos aculturados. Para compreender as narrativas deste mundo (Re) significado diariamente e atingir os objetivos propostos foi usado como referencial teórico o estudo de representações sociais, com os fundamentos da psicologia histórico-cultural, a psicologia profunda e os contextos e conceitos da arte. Apoiada nessas fontes bibliográficas, documentais, e principalmente na pesquisa participante de campo, foi possível articular uma discussão sobre as necessidades estéticas dos moradores de calçada no seu contexto sócio-histórico e sua necessidade de (Re) significação. Dentre os inúmeros analisados, escolhemos quatro protagonistas pelas suas produções estético sensíveis, que exemplificam o segmento social ao qual pertencem, para serem objeto de análise de suas (Re) significações. Entre eles pudemos encontrar heróis, homens de fé, poetas, pintores, performáticos, bricoleurs, que fazem da arte a mola propulsora da sua projeção social, arquétipos que se apresentam para (Re) significar seu mundo.

Os mapas conceituais (MCs) são úteis para representar o conhecimento dos alunos e promover a aprendizagem significativa. A análise detalhada de mapas conceituais pode revelar informações latentes que não são percebidas a partir da mera leitura do seu conjunto de proposições. O presente trabalho tem como objetivo propor a análise de vizinhança (AViz) como uma forma inovadora de analisar os MCs obtidos em sala de aula. A seleção de um conceito obrigatório (CO) permite verificar como os alunos o relaciona com outros conceitos, que são denominados conceitos vizinhos (CVs). MCs (n=69) sobre as mudanças climáticas formam o primeiro conjunto de dados empíricos que ratifica o potencial da AViz. O CO selecionado foi dispersão, a fim de analisar se os alunos conseguem relacioná-lo com o caráter global desse problema ambiental. Os padrões identificados a partir da AViz sugerem que, apesar de serem submetidos a uma mesma sequência didática, nem todos os alunos conseguiram utilizar o CO de forma adequada. Isso pode ser explicado a partir da Teoria da Aprendizagem Significativa de David Ausubel, que destaca o papel fundamental dos conhecimentos prévios no processo de assimilação de novas informações. / Concept maps (CMs) are useful to represent students\' knowledge and to promote meaningful learning. The deep analysis of concept maps may reveal latent information that is not perceived from the simple reading of its propositional network. This work proposes the Neighborhood Analysis (NeAn) as an innovative way to analyze the CMs obtained in classrooms. The selection of a compulsory concept (CC) allows teachers to evaluate how the students relate it to other concepts, named neighbors (NCs). CMs (n=69) on climate change are the first set of empirical data that confirms the potential of NeAn. Dispersion was selected as CC in order to check whether students can relate it with the global perspective of this environmental problem. The patterns found from the NeAn suggest that, despite being exposed to the same didactic activities, some students could not use the CC properly. This may be explained from David Ausubel\'s learning theory, which stresses the critical role of prior knowledge in the assimilation process of new information.

A k nearest neighbor query q retrieves k objects that lie closest to the query point q among a given set of objects P. With the availability of inexpensive location aware mobile devices, the continuous monitoring of such queries has gained lot of attention and many methods have been proposed for continuously monitoring the kNNs in highly dynamic environment. Multiple continuous queries require real-time results and both the objects and queries issue frequent location updates. Most popular spatial index, R-tree, is not suitable for continuous monitoring of these queries due to its inefficiency in handling frequent updates. Recently, the interest of database community has been shifting towards using grid-based index for continuous queries due to its simplicity and efficient update handling. For kNN queries, the order in which cells of the grid are accessed is very important. In this research, we present two efficient and effective grid access methods, CircularTrip and ArcTrip, that ensure that the number of cells visited for any continuous kNN query is minimum. Our extensive experimental study demonstrates that CircularTrip-based continuous kNN algorithm outperforms existing approaches in terms of both efficiency and space requirement. Moreover, we show that CircularTrip and ArcTrip can be used for many other variants of nearest neighbor queries like constrained nearest neighbor queries, farthest neighbor queries and (k + m)-NN queries. All the algorithms presented for these queries preserve the properties that they visit minimum number of cells for each query and the space requirement is low. Our proposed techniques are flexible and efficient and can be used to answer any query that is hybrid of above mentioned queries. For example, our algorithms can easily be used to efficiently monitor a (k + m) farthest neighbor query in a constrained region with the flexibility that the spatial conditions that constrain the region can be changed by the user at any time.

Cette thèse présente de nouvelles méthodes de synthèse de texture basées sur l'exemple pour les problèmes de prédiction d'images (c'est à dire, codage prédictif) et d'inpainting d'images. Les principales contributions de cette étude peuvent aussi être vues comme des extensions du template matching. Cependant, le problème de synthèse de texture tel que nous le définissons ici se situe plutôt dans un contexte d'optimisation formalisée sous différentes contraintes. Le problème de prédiction d'images est d'abord situé dans un contexte de représentations parcimonieuses par l'approximation du template sous contraintes de parcimonie. La méthode de prédiction proposée avec les dictionnaires adaptés localement montrent de meilleures performances par rapport aux dictionnaires classiques (tels que la transformée en cosinus discrète (TCD)), et à la méthode du template matching. Le problème de prédiction d'images est ensuite placé dans un cadre d'apprentissage de dictionnaires en adaptant les méthodes traditionnelles d'apprentissage pour la prédiction de l'image. Les observations expérimentales montrent une meilleure performance comparativement à des méthodes de prédiction parcimonieuse et des prédictions intra de type H.264/AVC. Enfin un cadre neighbor embedding est proposé pour la prédiction de l'image en utilisant deux méthodes de réduction de dimensionnalité: la factorisation de matrice non négative (FMN) et le locally linear embedding (LLE). Ce cadre est ensuite étendu au problème d'inpainting d'images. Les évaluations expérimentales démontrent l'efficacité des idées sous-jacentes pour la compression via la prédiction d'images et l'inpainting d'images.

Nondestructive testing is used extensively throughout the industry for quality assessment and detection of defects in engineering materials. The range and variety of anomalies is enormous and critical assessment of their location and size is often complicated. Depending upon final operational considerations, some of these anomalies may be critical and their detection and classification is therefore of importance. Despite the several advantages of using Nondestructive testing for flaw detection, the conventional NDT techniques based on the heuristic experience-based pattern identification methods have many drawbacks in terms of cost, length and result in erratic analysis and thus lead to discrepancies in results. The use of several statistical and soft computing techniques in the evaluation and classification operations result in the development of an automatic decision support system for defect characterization that offers the possibility of an impartial standardized performance. The present work evaluates the application of both supervised and unsupervised classification techniques for flaw detection and classification in a semi-infinite half space. Finite element models to simulate the MASW test in the presence and absence of voids were developed using the commercial package LS-DYNA. To simulate anomalies, voids of different sizes were inserted on elastic medium. Features for the discrimination of received responses were extracted in time and frequency domains by applying suitable transformations. The compact feature vector is then classified by different techniques: supervised classification (backpropagation neural network, adaptive neuro-fuzzy inference system, k-nearest neighbor classifier, linear discriminate classifier) and unsupervised classification (fuzzy c-means clustering). The classification results show that the performance of k-nearest Neighbor Classifier proved superior when compared with the other techniques with an overall accuracy of 94% in detection of presence of voids and an accuracy of 81% in determining the size of the void in the medium. The assessment of the various classifiers’ performance proved to be valuable in comparing the different techniques and establishing the applicability of simplified classification methods such as k-NN in defect characterization. The obtained classification accuracies for the detection and classification of voids are very encouraging, showing the suitability of the proposed approach to the development of a decision support system for non-destructive testing of materials for defect characterization.

Top-k and Skyline queries are a long study topic in database and information retrieval communities and they are two popular operations for preference retrieval. Top-k query returns a subset of the most relevant answers instead of all answers. Efficient top-k processing retrieves the k objects that have the highest overall score. In this paper, some algorithms that are used as a technique for efficient top-k processing for different scenarios have been represented. A framework based on existing algorithms with considering based cost optimization that works for these scenarios has been presented. This framework will be used when the user can determine the user ranking function. A real life scenario has been applied on this framework step by step. Skyline query returns a set of points that are not dominated (a record x dominates another record y if x is as good as y in all attributes and strictly better in at least one attribute) by other points in the given datasets. In this paper, some algorithms that are used for evaluating the skyline query have been introduced. One of the problems in the skyline query which is called curse of dimensionality has been presented. A new strategy that based on the skyline existing algorithms, skyline frequency and the binary tree strategy which gives a good solution for this problem has been presented. This new strategy will be used when the user cannot determine the user ranking function. A real life scenario is presented which apply this strategy step by step. Finally, the advantages of the top-k query have been applied on the skyline query in order to have a quickly and efficient retrieving results.

Nondestructive testing is used extensively throughout the industry for quality assessment and detection of defects in engineering materials. The range and variety of anomalies is enormous and critical assessment of their location and size is often complicated. Depending upon final operational considerations, some of these anomalies may be critical and their detection and classification is therefore of importance. Despite the several advantages of using Nondestructive testing for flaw detection, the conventional NDT techniques based on the heuristic experience-based pattern identification methods have many drawbacks in terms of cost, length and result in erratic analysis and thus lead to discrepancies in results. The use of several statistical and soft computing techniques in the evaluation and classification operations result in the development of an automatic decision support system for defect characterization that offers the possibility of an impartial standardized performance. The present work evaluates the application of both supervised and unsupervised classification techniques for flaw detection and classification in a semi-infinite half space. Finite element models to simulate the MASW test in the presence and absence of voids were developed using the commercial package LS-DYNA. To simulate anomalies, voids of different sizes were inserted on elastic medium. Features for the discrimination of received responses were extracted in time and frequency domains by applying suitable transformations. The compact feature vector is then classified by different techniques: supervised classification (backpropagation neural network, adaptive neuro-fuzzy inference system, k-nearest neighbor classifier, linear discriminate classifier) and unsupervised classification (fuzzy c-means clustering). The classification results show that the performance of k-nearest Neighbor Classifier proved superior when compared with the other techniques with an overall accuracy of 94% in detection of presence of voids and an accuracy of 81% in determining the size of the void in the medium. The assessment of the various classifiers’ performance proved to be valuable in comparing the different techniques and establishing the applicability of simplified classification methods such as k-NN in defect characterization. The obtained classification accuracies for the detection and classification of voids are very encouraging, showing the suitability of the proposed approach to the development of a decision support system for non-destructive testing of materials for defect characterization.

In this thesis, improving the performance of the automatic recognition of the Doppler radar targets is studied. The radar used in this study is a ground-surveillance doppler radar. Target types are car, truck, bus, tank, helicopter, moving man and running man. The input of this thesis is the output of the real doppler radar signals which are normalized and preprocessed (TRP vectors: Target Recognition Pattern vectors) in the doctorate thesis by Erdogan (2002). TRP vectors are normalized and homogenized doppler radar target signals with respect to target speed, target aspect angle and target range. Some target classes have repetitions in time in their TRPs. By the use of these repetitions, improvement of the target type classification performance is studied. K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) algorithms are used for doppler radar target classification and the results are evaluated. Before classification PCA (Principal Component Analysis), LDA (Linear Discriminant Analysis), NMF (Nonnegative Matrix Factorization) and ICA (Independent Component Analysis) are implemented and applied to normalized doppler radar signals for feature extraction and dimension reduction in an efficient way. These techniques transform the input vectors, which are the normalized doppler radar signals, to another space. The effects of the implementation of these feature extraction algoritms and the use of the repetitions in doppler radar target signals on the doppler radar target classification performance are studied.

國外法學資訊系統已研究多年，嘗試利用科技幫助提昇司法審判的效率。重要的議題包括輔助判決，法律文件分類，或是相似案件搜尋等。本研究將針對中文裁判書的分類做進一步談討。 在文件特徵表示方面，我們以有序詞組來表達中文裁判書，我們嘗試比較採用不同的詞彙來源對於分類效果的影響。實驗中我們分別採用一般通用的電子詞典建立一般詞組；以及以演算法取出法學專業詞彙集建立專業詞組。並依tf-idf(term frequency – inverse document frequency)的概念，設計兩種詞組權重tpf-idf(term pair frequency – inverse document frequency)以及tpf-icf(term pair frequency – inverse category frequency)，來計算特徵詞組權重。 在文件分類演算法方面，我們實作以相似度為基礎的k最近鄰居法作為系統分類機制，藉由裁判書的案由欄位，將案例分為七種類別，分別為竊盜、搶奪、強盜、贓物、傷害、恐嚇以及賭博。並藉由觀察案例資料庫的相似度分佈，以找出恰當的參數，進一步得到較佳的分類正確率與較低的拒絕率。 我們並依照自省式學習法的精神，建立權重調整的機制。企圖藉由自省式學習法提昇分類效果，以及找出對分類有影響的詞組。而我們以案例資料庫的相似度差異值以及距離差異值，分析調整前後案例資料庫的變化，藉以觀察自省式學習法的效果。 / Legal information systems for non-Chinese languages have been studied intensively in the past many years. There are several topics under discussion, such as judgment assistance, legal document classification, and similar case search, and so on. This thesis studies the classification of Chinese judgment documents. I use phrases as the indices for documents. I attempt to compare the influences of different lexical sources for segmenting Chinese text. One of the lexical sources is a general machine-readable dictionary, Hownet, and the other is the set of terms algorithmically extracted from legal documents. Based on the concept of tf-idf, I design two kinds of phrase weights: tpf-idf and tpf-icf. In the experiments, I use the k-nearest neighbor method to classify Chinese judgment documents into seven categories based on their prosecution reasons: larceny(竊盜), robbery (搶奪), robbery by threatening or disabling the victims (強盜), receiving stolen property (贓物), causing bodily harm (傷害), intimidation (恐嚇), and gambling(賭博). To achieve high accuracy with low rejection rates, I observe and discuss the distribution of similarity of the training documents to select appropriate parameters. In addition, I also conduct a set of analogous experiments for classifying documents based on the cited legal articles for gambling cases. To improve the classification effects, I apply the introspective learning technique to adjust the weights of phrases. I observe the intra-cluster similarity and inter-cluster similarity in evaluating the effects of weight adjustment on experiments for classifying documents based on their prosecution reasons and cited articles.