Cette thèse consiste à analyser conjointement des signaux de mouvement des yeux et d’électroencéphalogrammes (EEG) multicanaux acquis simultanément avec des participants effectuant une tâche de lecture de recueil d'informations afin de prendre une décision binaire - le texte est-il lié à un sujet ou non? La recherche d'informations textuelles n'est pas un processus homogène dans le temps - ni d'un point de vue cognitif, ni en termes de mouvement des yeux. Au contraire, ce processus implique plusieurs étapes ou phases, telles que la lecture normale, le balayage, la lecture attentive - en termes d'oculométrie - et la création et le rejet d'hypothèses, la confirmation et la décision - en termes cognitifs.Dans une première contribution, nous discutons d'une méthode d'analyse basée sur des chaînes semi-markoviennes cachées sur les signaux de mouvement des yeux afin de mettre en évidence quatre phases interprétables en termes de stratégie d'acquisition d'informations: lecture normale, lecture rapide, lecture attentive et prise de décision.Dans une deuxième contribution, nous lions ces phases aux changements caractéristiques des signaux EEG et des informations textuelles. En utilisant une représentation en ondelettes des EEG, cette analyse révèle des changements de variance et de corrélation des coefficients inter-canaux, en fonction des phases et de la largeur de bande. En utilisant des méthodes de plongement des mots, nous relions l’évolution de la similarité sémantique au sujet tout au long du texte avec les changements de stratégie.Dans une troisième contribution, nous présentons un nouveau modèle dans lequel les EEG sont directement intégrés en tant que variables de sortie afin de réduire l’incertitude des états. Cette nouvelle approche prend également en compte les aspects asynchrones et hétérogènes des données. / This PhD thesis consists in jointly analyzing eye-tracking signals and multi-channel electroencephalograms (EEGs) acquired concomitantly on participants doing an information collection reading task in order to take a binary decision - is the text related to some topic or not ? Textual information search is not a homogeneous process in time - neither on a cognitive point of view, nor in terms of eye-movement. On the contrary, this process involves several steps or phases, such as normal reading, scanning, careful reading - in terms of oculometry - and creation and rejection of hypotheses, confirmation and decision - in cognitive terms.In a first contribution, we discuss an analysis method based on hidden semi-Markov chains on the eye-tracking signals in order to highlight four interpretable phases in terms of information acquisition strategy: normal reading, fast reading, careful reading, and decision making.In a second contribution, we link these phases with characteristic changes of both EEGs signals and textual information. By using a wavelet representation of EEGs, this analysis reveals variance and correlation changes of the inter-channels coefficients, according to the phases and the bandwidth. And by using word embedding methods, we link the evolution of semantic similarity to the topic throughout the text with strategy changes.In a third contribution, we present a new model where EEGs are directly integrated as output variables in order to reduce the state uncertainty. This novel approach also takes into consideration the asynchronous and heterogeneous aspects of the data.

In this thesis two different problems in distributed sensor networks are considered. Part I involves optimal quantiser design for decentralised estimation of a two-state hidden Markov model with dual sensors. The notion of optimality for quantiser design is based on minimising the probability of error in estimating the hidden Markov state. Equations for the filter error are derived for the continuous (unquantised) sensor outputs (signals), which are used to benchmark the performance of the quantisers. Minimising the probability of filter error to obtain the quantiser breakpoints is a difficult problem therefore an alternative method is employed. The quantiser breakpoints are obtained by maximising the mutual information between the quantised signals and the hidden Markov state. This method is known to work well for the single sensor case. Cases with independent and correlated noise across the signals are considered. The method is then applied to Markov processes with Gaussian signal noise, and further investigated through simulation studies. Simulations involving both independent and correlated noise across the sensors are performed and a number of interesting new theoretical results are obtained, particularly in the case of correlated noise. In Part II, the focus shifts to the detection of faults in helicopter transmission systems. The aim of the investigation is to determine whether the acoustic signature can be used for fault detection and diagnosis. To investigate this, statistical change detection algorithms are applied to acoustic vibration data obtained from the main rotor gearbox of a Bell 206 helicopter, which is run at high load under test conditions.

<p>This study is based on three models, Markov model, Hidden Markov model and the Radial basis function neural network. A number of work has been done before about application of these three models to the stock market. Though, individual researchers have developed their own techniques to design and test the Radial basis function neural network. This paper aims to show the different ways and precision of applying these three models to predict price processes of the stock market. By comparing the same group of data, authors get different results. Based on Markov model, authors find a tendency of stock market in future and, the Hidden Markov model behaves better in the financial market. When the fluctuation of the stock price index is not drastic, the Radial basis function neural network has a nice prediction.</p>

This study is based on three models, Markov model, Hidden Markov model and the Radial basis function neural network. A number of work has been done before about application of these three models to the stock market. Though, individual researchers have developed their own techniques to design and test the Radial basis function neural network. This paper aims to show the different ways and precision of applying these three models to predict price processes of the stock market. By comparing the same group of data, authors get different results. Based on Markov model, authors find a tendency of stock market in future and, the Hidden Markov model behaves better in the financial market. When the fluctuation of the stock price index is not drastic, the Radial basis function neural network has a nice prediction.

Organohalide-respiring Bacteria (OHRB) play key roles in the reductive dehalogenation of natural organohalides and anthropogenic chlorinated contaminants. Reductive dehalogenases (RDases) catalyze the cleavage of carbon-halogen bonds, enabling respiratory energy conservation and growth. Large numbers of RDase genes, a majority lacking experimental characterization of function, are found on the genomes of OHRB. In silico genomics tools were employed to identify shared sequence features among RDase genes and proteins, predict RDase functionality, and elucidate RDase evolutionary history. These analyses showed that the RDase superfamily could be divided into proteins exported to the membrane and cytoplasmic proteins, indicating that not all RDases function in respiration. Further, Hidden Markov models (HMMs) and multiple sequence alignments (MSAs) based upon biochemically characterized RDases identified previously uncharacterized members of an RDase superfamily, delineated protein domains and amino acid motifs serving to distinguish RDases from unrelated iron-sulfur proteins. Such conserved and discriminatory features among RDases may facilitate monitoring of organohalide-degrading microbial communities or improve accuracy of genome annotation. Phylogenetic analyses of RDase superfamily sequences provided evidence of convergent evolution and horizontal gene transfer (HGT) across distinct OHRB genera. Yet, the low frequency of RDase transfer outside the genus level and the absence of RDase transfer between phyla indicate that RDases evolve primarily by vertical evolution or HGT is restricted among related OHRB strains. Polyphyletic evolutionary lineages within the RDase superfamily comprise distantly-related RDases, some exhibiting activities towards the same substrates, suggesting a longstanding history of OHRB adaptation to natural organohalides. Similar functional and phylogenetic analyses provided evidence that nitrous oxide (N₂O, a potent greenhouse gas) reductase (nosZ) genes from versatile OHRB members of the Anaeromyxobacter and Desulfomonile genera comprised a nosZ sub-family evolutionarily distinct from nosZ found in non-OHRB denitrifiers. Hence, elucidation of RDase and NosZ sequence diversity may enhance the mitigation of anthropogenic organohalides and greenhouse gases (i.e., N₂O), respectively. The tetrachloroethene-respiring bacterium Geobacter lovleyi strain SZ exhibited genomic features distinguishing it from non-organohalide-respiring members of the Geobacter genus, including a conjugative pilus transfer gene cluster, a chromosomal genomic island harboring two RDase genes, and a diminished set of c-type cytochrome genes. The G. lovleyi strain SZ genome also harbored a 77 kbp plasmid carrying 15 out of the 24 genes involved in biosynthesis of corrinoid, likely related to this strains ability to degrade PCE to cis-DCE in the absence of supplied corrinoid (i.e., vitamin B₁₂). Although corrinoids are essential cofactors to RDases, the strictly organohalide-respiring Dehalococcoides mccartyi strains are corrinoid auxotrophs and depend upon uptake of extracellular corrinoids via Archaeal and Bacterial salvage pathways. A key corrinoid salvage gene in D. mccartyi, cbiZ, occurs at duplicated loci adjacent to RDase genes and appears to have been horizontally-acquired from Archaea. These comparative genome analyses highlight RDase dependencies upon corrinoids and also suggest mobile genomic elements (e.g., plasmids) are associated with organohalide respiration and corrinoid acquisition among OHRB. In summary, analyses of OHRB genomes promise to enable more complete modeling of metabolic and evolutionary processes associated with the turnover of organohalides in anoxic environments. These efforts also expand knowledge of biomarkers for monitoring OHRB activity in anoxic environments, and will improve our understanding of the fate of chlorinated contaminants.

長久以來音樂於人們生活中扮演著極為重要角色，在大多數人的成長過程裡或多或少皆有令其印象深刻之旋律。然而這些旋律常由專業人士所創作，對於未接受過專業訓練的民眾而言，若欲創作自己專屬之音樂難度甚高，而此目標也變得遙不可及。 為解決上述問題，降低音樂自行創作門檻，本研究以行動裝置之使用環境不受限及直覺性觸控介面兩大特性為運行環境，設計Android系統上之音樂創作軟體，協助未受過音樂專業訓練的庶民透過音樂主旋律並搭配適合的和弦配樂達成自行創作音樂之目標。本創作音樂軟體利用行動裝置提供「繪畫旋律曲線」與「字詞輸入」兩種輸入方式，將使用者繪畫的旋律曲線轉換為一段音樂主旋律，進行調性判斷、修正主旋律組成音並利用音樂動機樣式變化加以使主旋律更為豐富，輔以隱藏式馬可夫模型產生適切之和弦序列。最後將主旋律聲波與其產生的和弦聲波以混音的結果呈現給予使用者。 為評估本創作軟體是否符合使用者需求，以實驗觀察法邀請38位受試者進行軟體操作與評估。分析結果顯示，近75%的受試者認為由音樂創作軟體所產生之主旋律與和弦彼此搭配良好且符合其音樂動機。在介面易用性評估方面，結果顯示有近90%受測者認為本研究所提出的音樂創作軟體具有簡單易用之特性且能夠協助其降低創作音樂之門檻。簡單且易用的音樂創作軟體在實務上之重要性不言可喻，不但可使非專業使用者達成自我創作音樂之夢想，更可讓其沉浸於音樂創作成就感之中。 / Music plays as an essential role in human life and it affects the listeners on a certain extent. However, a pleasing music is the production of musicians and is difficult to be created by novices without musical specialty. To lower the entry point of music creation, this thesis design and develop a music accompaniment system on Android with the characteristics of intuitive input and ubiquity for novices without professional music background. The developed system consists of the following modules, main melody preprocessing (key determination and melody modification), music similarity retrieval, main melody post processing (music motif variance), chord accompaniment (Hidden Markov Model and mixing main melody and chord melody) and text processing (tone determination and pitch finding) to automatically match the accordance between melodies and chords that are inputted by patting or word. Thirty-eight participants were invited for system evaluation using the observational experiment. Nearly 75% of participants perceived that the melody and chord matching fits their musical motivations, while 90% stated that they can rely on the system to easily produce desirable music. Our findings contribute to the essence of music creation that the system provides a simplified interface for novice being immersed in music accomplishments, similar to that of professional musicians.

Tracking and understanding human gait is an important step towards improving elderly mobility and safety. This thesis presents a vision-based tracking system that estimates the 3D pose of a wheeled walker user's lower limbs with cameras mounted on the moving walker. The tracker estimates 3D poses from images of the lower limbs in the coronal plane in a dynamic, uncontrolled environment. It employs a probabilistic approach based on particle filtering with three different camera setups: a monocular RGB camera, binocular RGB cameras, and a depth camera. For the RGB cameras, observation likelihoods are designed to compare the colors and gradients of each frame with initial templates that are manually extracted. Two strategies are also investigated for handling appearance change of tracking target: increasing number of templates and using different representations of colors. For the depth camera, two observation likelihoods are developed: the first one works directly in the 3D space, while the second one works in the projected image space. Experiments are conducted to evaluate the performance of the tracking system with different users for all three camera setups. It is demonstrated that the trackers with the RGB cameras produce results with higher error as compared to the depth camera, and the strategies for handling appearance change improve tracking accuracy in general. On the other hand, the tracker with the depth sensor successfully tracks the 3D poses of users over the entire video sequence and is robust against unfavorable conditions such as partial occlusion, missing observations, and deformable tracking target.

Speech recognition systems have been implemented using a wide range of signal processing techniques including neuromorphic/biological inspired and Digital Signal Processing techniques. Neuromorphic/biologically inspired techniques, such as silicon cochlea models, are based on fairly simple yet highly parallel computation and/or computational units. While the area of digital signal processing (DSP) is based on block transforms and statistical or error minimization methods. Essential to each of these techniques is the first stage of extracting meaningful information from the speech signal, which is known as feature extraction. This can be done using biologically inspired techniques such as silicon cochlea models, or techniques beginning with a model of speech production and then trying to separate the the vocal tract response from an excitation signal. Even within each of these approaches, there are multiple techniques including cepstrum filtering, which sits under the class of Homomorphic signal processing, or techniques using FFT based predictive approaches. The underlying reality is there are multiple techniques that have attacked the problem in speech recognition but the problem is still far from being solved. The techniques that have shown to have the best recognition rates involve Cepstrum Coefficients for the feature extraction and Hidden-Markov Models to perform the pattern recognition. The presented research develops an analog system based on programmable analog array technology that can perform the initial stages of auditory feature extraction and recognition before passing information to a digital signal processor. The goal being a low power system that can be fully contained on one or more integrated circuit chips. Results show that it is possible to realize advanced filtering techniques such as Cepstrum Filtering and Vector Quantization in analog circuitry. Prior to this work, previous applications of analog signal processing have focused on vision, cochlea models, anti-aliasing filters and other single component uses. Furthermore, classic designs have looked heavily at utilizing op-amps as a basic core building block for these designs. This research also shows a novel design for a Hidden Markov Model (HMM) decoder utilizing circuits that take advantage of the inherent properties of subthreshold transistors and floating-gate technology to create low-power computational blocks.

Speech recognition in Turkish Language is a challenging problem in several perspectives. Most of the challenges are related to the morphological structure of the language. Since Turkish is an agglutinative language, it is possible to generate many words from a single stem by using suffixes. This characteristic of the language increases the out-of-vocabulary (OOV) words, which degrade the performance of a speech recognizer dramatically. Also, Turkish language allows words to be ordered in a free manner, which makes it difficult to generate robust language models. In this thesis, the existing models and approaches which address the problem of Turkish LVCSR (Large Vocabulary Continuous Speech Recognition) are explored. Different recognition units (words, morphs, stem and endings) are used in generating the n-gram language models. 3-gram and 4-gram language models are generated with respect to the recognition unit. Since the solution domain of speech recognition is involved with machine learning, the performance of the recognizer depends on the sufficiency of the audio data used in acoustic model training. However, it is difficult to obtain rich audio corpora for the Turkish language. In this thesis, existing approaches are used to solve the problem of Turkish LVCSR by using a limited audio corpus. We also proposed several data selection approaches in order to improve the robustness of the acoustic model.

In the Internet era, more and more courses are taught through a course management system (CMS) or learning management system (LMS). In an asynchronous virtual learning environment, an instructor has the need to beware the progress of discussions in forums, and may intervene if ecessary in order to facilitate students¡¦ learning. This research proposes a discussion forum activity flow tracking system, called FAFT (Forum Activity Flow Tracer), to utomatically monitor the discussion activity flow of threaded forum postings in CMS/LMS. As CMS/LMS is getting popular in facilitating learning activities, the proposedFAFT can be used to facilitate instructors to identify students¡¦ interaction types in discussion forums. FAFT adopts modern data/text mining techniques to discover the patterns of forum discussion activity flows, which can be used for instructors to facilitate the online learning activities. FAFT consists of two subsystems: activity classification (AC) and activity flow discovery (AFD). A posting can be perceived as a type of announcement, questioning, clarification, interpretation, conflict, or assertion. AC adopts a cascade model to classify various activitytypes of posts in a discussion thread. The empirical evaluation of the classified types from a repository of postings in earth science on-line courses in a senior high school shows that AC can effectively facilitate the coding rocess, and the cascade model can deal with the imbalanced distribution nature of discussion postings. AFD adopts a hidden Markov model (HMM) to discover the activity flows. A discussion activity flow can be presented as a hidden Markov model (HMM) diagram that an instructor can adopt to predict which iscussion activity flow type of a discussion thread may be followed. The empirical results of the HMM from an online forum in earth science subject in a senior high school show that FAFT can effectively predict the type of a discussion activity flow. Thus, the proposed FAFT can be embedded in a course management system to automatically predict the activity flow type of a discussion thread, and in turn reduce the teachers¡¦ loads on managing online discussion forums.