Thesis (M.Phil.)--Hong Kong University of Science and Technology, 2006. / Includes bibliographical references (leaves 59-66). Also available in electronic version.

This thesis investigates translation tools and technologies in the Welsh language context and provides translators working in the Welsh-English language pair with a method of evaluation of Translation Memory (TM).

Sentiment analysis is the automatic classification of a text, trying to determine the attitude of the writer with respect to a specific topic. The attitude may be either their judgment or evaluation, their feelings or the intended emotional communication. The recent increase in the use of review sites and blogs, has made a great amount of subjective data available. Nowadays, it is nearly impossible to manually process all the relevant data available, and as a consequence, the importance given to the automatic classification of unformatted data, has increased. Up to date, all of the research carried on sentiment analysis was focused on English language. In this thesis, two Turkish datasets tagged with sentiment information is introduced and existing methods for English are applied on these datasets. This thesis also suggests new methods for Turkish sentiment analysis.

In recent years, many machine learning algorithms have been developed and widely applied in various applications. However, most of them have considered the data distributions of the training and test datasets to be similar. This thesis concerns on the decrease of generalization ability in a test dataset when the data distribution is different from that of the training dataset. As labels may be unavailable in the test dataset in practical applications, we follow the effective approach of unsupervised domain adaptation and propose distribution alignment methods to improve the generalization ability of models learned from the training dataset in the test dataset. To solve the problem of joint distribution alignment without target labels, we propose a new criterion of domain-shared group sparsity that is an equivalent condition for equal conditional distribution. A domain-shared group-sparse dictionary learning model is built with the proposed criterion, and a cross-domain label propagation method is developed to learn a target-domain classifier using the domain-shared group-sparse representations and the target-specific information from the target data. Experimental results show that the proposed method achieves good performance on cross-domain face and object recognition. Moreover, most distribution alignment methods have not considered the difference in distribution structures, which results in insufficient alignment across domains. Therefore, a novel graph alignment method is proposed, which aligns both data representations and distribution structural information across the source and target domains. An adversarial network is developed for graph alignment by mapping both source and target data to a feature space where the data are distributed with unified structure criteria. Promising results have been obtained in the experiments on cross-dataset digit and object recognition. Problem of dataset bias also exists in human pose estimation across datasets with different image qualities. Thus, this thesis proposes to synthesize target body parts for cross-domain distribution alignment, to address the problem of cross-quality pose estimation. A translative dictionary is learned to associate the source and target domains, and a cross-quality adaptation model is developed to refine the source pose estimator using the synthesized target body parts. We perform cross-quality experiments on three datasets with different image quality using two state-of-the-art pose estimators, and compare the proposed method with five unsupervised domain adaptation methods. Our experimental results show that the proposed method outperforms not only the source pose estimators, but also other unsupervised domain adaptation methods.

In der Lehrveranstaltung Bewegungstechnik & Bewegungsdesign für Verarbeitungsmaschinen werden die Studenten in die Lage versetzt, Systeme zur Bewegung von Arbeitsorganen in Verarbeitungs- und Textilmaschinen konstruktiv zu entwerfen und zu dimensionieren. Im Blickpunkt stehen zyklische Bewegungen, zu deren Realisierung auch der Einsatz von Mechanismen sinnvoll ist. Die interdisziplinäre Betrachtung der Bewegungstechnik dient als Einführung in die Problematik und als Grundlage für nachfolgende Optimierungen.

In der Lehrveranstaltung Bewegungstechnik & Bewegungsdesign für Verarbeitungsmaschinen werden die Studenten in die Lage versetzt, Systeme zur Bewegung von Arbeitsorganen in Verarbeitungs- und Textilmaschinen konstruktiv zu entwerfen und zu dimensionieren. Im Blickpunkt stehen zyklische Bewegungen, zu deren Realisierung auch der Einsatz von Mechanismen sinnvoll ist. Die interdisziplinäre Betrachtung der Bewegungstechnik dient als Einführung in die Problematik und als Grundlage für nachfolgende Optimierungen. Diese sind Gegenstand des Teils 2.

Acoustical characteristics are used to classify the structural and operational conditions in underground pipes with advanced signal classification methods.

In der Lehrveranstaltung Bewegungstechnik & Bewegungsdesign für Verarbeitungsmaschinen werden die Studenten in die Lage versetzt, Systeme zur Bewegung von Arbeitsorganen in Verarbeitungs- und Textilmaschinen konstruktiv zu entwerfen und zu dimensionieren. Im Blickpunkt stehen zyklische Bewegungen, zu deren Realisierung auch der Einsatz von Mechanismen sinnvoll ist. Die interdisziplinäre Betrachtung der Bewegungstechnik dient als Einführung in die Problematik und als Grundlage für nachfolgende Optimierungen.

In der Lehrveranstaltung Bewegungstechnik & Bewegungsdesign für Verarbeitungsmaschinen werden die Studenten in die Lage versetzt, Systeme zur Bewegung von Arbeitsorganen in Verarbeitungs- und Textilmaschinen konstruktiv zu entwerfen und zu dimensionieren. Im Blickpunkt stehen zyklische Bewegungen, zu deren Realisierung auch der Einsatz von Mechanismen sinnvoll ist. Die interdisziplinäre Betrachtung der Bewegungstechnik dient als Einführung in die Problematik und als Grundlage für nachfolgende Optimierungen. Diese sind Gegenstand des Teils 2.:1 Bewegungsaufgaben in Verarbeitungsmaschinen 2 Struktur des Antriebssystems 3 Bewegungsdesign Basics 4 Vorgaben für schnelle Bewegungen linearer Systeme 5 Motor-G-Getriebe-Konfiguration 6 Motor-U-Getriebe-Konfiguration

This thesis is concerned with the development and study of a pattern recognition system for siphon and sewer condition/defect analysis based on acoustic characteristics. Pattern recognition has been studied and used widely in many fields including: identification and authentication; medical diagnosis and musical modelling. Audio based classification and research has been mainly focusing on speech recognition and music retrieval, but few applications have attempted to use acoustic characteristics for underground pipe condition classification. Traditional CCTV inspection methods are relatively expensive and subjective so remote techniques have been developed to overcome this concern and increase the inspection efficiency. The acoustic environment provides a rich source of information about the internal conditions of a pipe. This thesis reports on a classification system based on measuring the direct and reflected acoustic signals and describing the energy spectrum for each condition/pipe defect. A K-nearest neighbour classifier (KNN) and Support vector machines (SVMs) classifier have been adopted to train the classification system to identify sediment and pipe surface defects by comparing the measured acoustic signals with a database containing a range of typical conditions. Laboratory generated data and field collected data were used to train the proposed system and evaluate its ability. The overall accuracy of the system recognizing blockage and structural aspects in each of the series of experiments varies between 70% and 95%.