This master thesis project is carried out by one student at the Royal Institute of Technology in collaboration with Cybercom Group. The aim was to evaluate and compare system design strategies for fruit recognition in harvesting robots and the performance of supervised machine learning classification methods when applied to this specific task. The thesis covers the basics of these systems; to which parameters, constraints, requirements, and design decisions have been investigated. The framework is used as a foundation for the implementation of both sensing system, and processing and classification algorithms. A plastic tomato plant with fruit of varying maturity was used as a basis for training and testing, and a Kinect v2 for Windows including sensors for high resolution color-, depth, and IR data was used for image acquisition. The obtained data were processed and features of objects of interest extracted using MATLAB and a SDK for Kinect provided by Microsoft. Multiple views of the plant were acquired by having the plant rotate on a platform controlled by a stepper motor and an Ardunio Uno. The algorithms tested were binary classifiers, including Support Vector Machine, Decision Tree, and k-Nearest Neighbor. The models were trained and validated using a five fold cross validation in MATLABs Classification Learner application. Peformance metrics such as precision, recall, and the F1-score, used for accuracy comparison, were calculated. The statistical models k-NN and SVM achieved the best scores. The method considered most promising for fruit recognition purposes was the SVM. / Det här masterexamensarbetet har utförts av en student från Kungliga Tekniska Högskolan i samarbete med Cybercom Group. Målet var att utvärdera och jämföra designstrategier för igenkänning av frukt i en skörderobot och prestandan av klassificerande maskininlärningsalgoritmer när de appliceras på det specifika problemet. Arbetet omfattar grunderna av dessa system; till vilket parametrar, begränsningar, krav och designbeslut har undersökts. Ramverket användes sedan som grund för implementationen av sensorsystemet, processerings- och klassifikationsalgoritmerna. En tomatplanta i pplast med frukter av varierande mognasgrad användes som bas för träning och validering av systemet, och en Kinect för Windows v2 utrustad med sensorer för högupplöst färg, djup, och infraröd data anvöndes för att erhålla bilder. Datan processerades i MATLAB med hjälp av mjukvaruutvecklingskit för Kinect tillhandahållandet av Windows, i syfte att extrahera egenskaper ifrån objekt på bilderna. Multipla vyer erhölls genom att låta tomatplantan rotera på en plattform, driven av en stegmotor Arduino Uno. De binära klassifikationsalgoritmer som testades var Support Vector MAchine, Decision Tree och k-Nearest Neighbor. Modellerna tränades och valideras med hjälp av en five fold cross validation i MATLABs Classification Learner applikation. Prestationsindikatorer som precision, återkallelse och F1- poäng beräknades för de olika modellerna. Resultatet visade bland annat att statiska modeller som k-NN och SVM presterade bättre för det givna problemet, och att den sistnömnda är mest lovande för framtida applikationer.

In the hope to increase the detection rate of faults in combined heat and power plant boilers thus lowering unplanned maintenance three machine learning models are constructed and evaluated. The algorithms; k-Nearest Neighbor, One-Class Support Vector Machine, and Auto-encoder have a proven track record in research for anomaly detection, but are relatively unexplored for industrial applications such as this one due to the difficulty in collecting non-artificial labeled data in the field.The baseline versions of the k-Nearest Neighbor and Auto-encoder performed very similarly. Nevertheless, the Auto-encoder was slightly better and reached an area under the precision-recall curve (AUPRC) of 0.966 and 0.615 on the trainingand test period, respectively. However, no sufficiently good results were reached with the One-Class Support Vector Machine. The Auto-encoder was made more sophisticated to see how much performance could be increased. It was found that the AUPRC could be increased to 0.987 and 0.801 on the trainingand test period, respectively. Additionally, the model was able to detect and generate one alarm for each incident period that occurred under the test period.The conclusion is that ML can successfully be utilized to detect faults at an earlier stage and potentially circumvent otherwise costly unplanned maintenance. Nevertheless, there is still a lot of room for improvements in the model and the collection of the data. / I hopp om att öka identifieringsgraden av störningar i kraftvärmepannor och därigenom minska oplanerat underhåll konstrueras och evalueras tre maskininlärningsmodeller.Algoritmerna; k-Nearest Neighbor, One-Class Support Vector Machine, och Autoencoder har bevisad framgång inom forskning av anomalidetektion, men är relativt outforskade för industriella applikationer som denna på grund av svårigheten att samla in icke-artificiell uppmärkt data inom området.Grundversionerna av k-Nearest Neighbor och Auto-encoder presterade nästan likvärdigt. Dock var Auto-encoder-modellen lite bättre och nådde ett AUPRC-värde av 0.966 respektive 0.615 på träningsoch testperioden. Inget tillräckligt bra resultat nåddes med One-Class Support Vector Machine. Auto-encoder-modellen gjordes mer sofistikerad för att se hur mycket prestandan kunde ökas. Det visade sig att AUPRC-värdet kunde ökas till 0.987 respektive 0.801 under träningsoch testperioden. Dessutom lyckades modellen identifiera och generera ett larm vardera för alla incidenter under testperioden. Slutsatsen är att ML framgångsrikt kan användas för att identifiera störningar iett tidigare skede och därigenom potentiellt kringgå i annat fall dyra oplanerade underhåll. Emellertid finns det fortfarande mycket utrymme för förbättringar av modellen samt inom insamlingen av data.

Ein zunehmend wichtiges Thema in der Informatik ist der Umgang mit Ähnlichkeit in einer großen Anzahl unterschiedlicher Domänen. Derzeit existiert keine universell verwendbare Infrastruktur für die Ähnlichkeitssuche in allgemeinen metrischen Räumen. Ziel der Arbeit ist es, die Grundlage für eine derartige Infrastruktur zu legen, die in klassische Datenbankmanagementsysteme integriert werden könnte. Im Rahmen einer Analyse des State of the Art wird der M-Baum als am besten geeignete Basisstruktur identifiziert. Dieser wird anschließend zum EM-Baum erweitert, wobei strukturelle Kompatibilität mit dem M-Baum erhalten wird. Die Abfragealgorithmen werden im Hinblick auf eine Minimierung notwendiger Distanzberechnungen optimiert. Aufbauend auf einer mathematischen Analyse der Beziehung zwischen Baumstruktur und Abfrageaufwand werden Freiheitsgrade in Baumänderungsalgorithmen genutzt, um Bäume so zu konstruieren, dass Ähnlichkeitsanfragen mit einer minimalen Anzahl an Anfrageoperationen beantwortet werden können. / A topic of growing importance in computer science is the handling of similarity in multiple heterogenous domains. Currently there is no common infrastructure to support this for the general metric space. The goal of this work is lay the foundation for such an infrastructure, which could be integrated into classical data base management systems. After some analysis of the state of the art the M-Tree is identified as most suitable base and enhanced in multiple ways to the EM-Tree retaining structural compatibility. The query algorithms are optimized to reduce the number of necessary distance calculations. On the basis of a mathematical analysis of the relation between the tree structure and the query performance degrees of freedom in the tree edit algorithms are used to build trees optimized for answering similarity queries using a minimal number of distance calculations.

"Many current and future medical devices are wearable, using the human body as a conduit for wireless communication, which implies that human body serves as a crucial part of the transmission medium in body area networks (BANs). Implantable medical devices such as Pacemaker and Cardiac Defibrillators are designed to provide patients with timely monitoring and treatment. Endoscopy capsules, pH Monitors and blood pressure sensors are used as clinical diagnostic tools to detect physiological abnormalities and replace traditional wired medical devices. Body-mounted sensors need to be investigated for use in providing a ubiquitous monitoring environment. In order to better design these medical devices, it is important to understand the propagation characteristics of channels for in-body and on- body wireless communication in BANs. The IEEE 802.15.6 Task Group 6 is officially working on the standardization of Body Area Network, including the channel modeling and communication protocol design. This thesis is focused on the propagation characteristics of human body movements. Specifically, standing, walking and jogging motions are measured, evaluated and analyzed using an empirical approach. Using a network analyzer, probabilistic models are derived for the communication links in the medical implant communication service band (MICS), the industrial scientific medical band (ISM) and the ultra- wideband (UWB) band. Statistical distributions of the received signal strength and second order statistics are presented to evaluate the link quality and outage performance for on-body to on- body communications at different antenna separations. The Normal distribution, Gamma distribution, Rayleigh distribution, Weibull distribution, Nakagami-m distribution, and Lognormal distribution are considered as potential models to describe the observed variation of received signal strength. Doppler spread in the frequency domain and coherence time in the time domain from temporal variations is analyzed to characterize the stability of the channels induced by human body movements. The shape of the Doppler spread spectrum is also investigated to describe the relationship of the power and frequency in the frequency domain. All these channel characteristics could be used in the design of communication protocols in BANs, as well as providing features to classify different human body activities. Realistic data extracted from built-in sensors in smart devices were used to assist in modeling and classification of human body movements along with the RF sensors. Variance, energy and frequency domain entropy of the data collected from accelerometer and orientation sensors are pre- processed as features to be used in machine learning algorithms. Activity classifiers with Backpropagation Network, Probabilistic Neural Network, k-Nearest Neighbor algorithm and Support Vector Machine are discussed and evaluated as means to discriminate human body motions. The detection accuracy can be improved with both RF and inertial sensors."

With the advent of computers and the information age, vast amounts of data generated in a great deal of science and industry fields require the statisticians to explore further. In particular, statistical and computational problems in biology and medicine have created a new field of bioinformatics, which is attracting more and more statisticians, computer scientists, and biologists. Several procedures have been developed for tracing the source of fecal pollution in water resources based on certain characteristics of certain microorganisms. Use of this collection of techniques has been termed microbial source tracking (MST). Most of the current methods for MST are based on patterns of either phenotypic or genotypic variation in indicator organisms. Studies also suggested that patterns of genotypic variation might be more reliable due to their less association with environmental factors than those of phenotypic variation. Among the genotypic methods for source tracking, fingerprinting via rep-PCR is most common. Thus, identifying the specific pollution sources in contaminated waters based on rep-PCR fingerprinting techniques, viewed as a classification problem, has become an increasingly popular research topic in bioinformatics. In the project, several statistical methods for classification were studied, including linear discriminant analysis, quadratic discriminant analysis, logistic regression, and $k$-nearest-neighbor rules, neural networks and support vector machine. This project report summaries each of these methods and relevant statistical theory. In addition, an application of these methods to a particular set of MST data is presented and comparisons are made.

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

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.

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.