Human Motion Analysis Based on Sequential Modeling of Radar Signal and Stereo Image Features

Falls are one of the greatest threats to elderly health in their daily living routines and activities. Therefore, it is very important to detect falls of an elderly in a timely and accurate manner, so that immediate response and proper care can be provided, by sending fall alarms to caregivers. Radar is an effective non-intrusive sensing modality which is well suited for this purpose, which can detect human motions in all types of environments, penetrate walls and fabrics, preserve privacy, and is insensitive to lighting conditions. Micro-Doppler features are utilized in radar signal corresponding to human body motions and gait to detect falls using a narrowband pulse-Doppler radar. Human motions cause time-varying Doppler signatures, which are analyzed using time-frequency representations and matching pursuit decomposition (MPD) for feature extraction and fall detection. The extracted features include MPD features and the principal components of the time-frequency signal representations. To analyze the sequential characteristics of typical falls, the extracted features are used for training and testing hidden Markov models (HMM) in different falling scenarios. Experimental results demonstrate that the proposed algorithm and method achieve fast and accurate fall detections. The risk of falls increases sharply when the elderly or patients try to exit beds. Thus, if a bed exit can be detected at an early stage of this motion, the related injuries can be prevented with a high probability. To detect bed exit for fall prevention, the trajectory of head movements is used for recognize such human motion. A head detector is trained using the histogram of oriented gradient (HOG) features of the head and shoulder areas from recorded bed exit images. A data association algorithm is applied on the head detection results to eliminate head detection false alarms. Then the three dimensional (3D) head trajectories are constructed by matching scale-invariant feature transform (SIFT) keypoints in the detected head areas from both the left and right stereo images. The extracted 3D head trajectories are used for training and testing an HMM based classifier for recognizing bed exit activities. The results of the classifier are presented and discussed in the thesis, which demonstrates the effectiveness of the proposed stereo vision based bed exit detection approach.

Bayesian Emulation for Sequential Modeling, Inference and Decision Analysis

The advances in three related areas of state-space modeling, sequential Bayesian learning, and decision analysis are addressed, with the statistical challenges of scalability and associated dynamic sparsity. The key theme that ties the three areas is Bayesian model emulation: solving challenging analysis/computational problems using creative model emulators. This idea defines theoretical and applied advances in non-linear, non-Gaussian state-space modeling, dynamic sparsity, decision analysis and statistical computation, across linked contexts of multivariate time series and dynamic networks studies. Examples and applications in financial time series and portfolio analysis, macroeconomics and internet studies from computational advertising demonstrate the utility of the core methodological innovations.

Chapter 1 summarizes the three areas/problems and the key idea of emulating in those areas. Chapter 2 discusses the sequential analysis of latent threshold models with use of emulating models that allows for analytical filtering to enhance the efficiency of posterior sampling. Chapter 3 examines the emulator model in decision analysis, or the synthetic model, that is equivalent to the loss function in the original minimization problem, and shows its performance in the context of sequential portfolio optimization. Chapter 4 describes the method for modeling the steaming data of counts observed on a large network that relies on emulating the whole, dependent network model by independent, conjugate sub-models customized to each set of flow. Chapter 5 reviews those advances and makes the concluding remarks.

AN INVESTIGATION OF VARIABLE VALVE TIMING EFFECTS ON HCCI ENGINE PERFORMANCE

The Homogeneous Charge Compression Ignition (HCCI) engine is a promising combustion concept for reducing NOx and particulate matter (PM) emissions and providing a high thermal efficiency in internal combustion engines. This concept though has limitations in the areas of combustion control and achieving stable combustion at high loads. For HCCI to be a viable option for on-road vehicles, further understanding of its combustion phenomenon and its control are essential. Thus, this thesis has a focus on both the experimental setup of an HCCI engine at Michigan Technological University (MTU) and also developing a physical numerical simulation model called the Sequential Model for Residual Affected HCCI (SMRH) to investigate performance of HCCI engines. The primary focus is on understanding the effects of intake and exhaust valve timings on HCCI combustion. For the experimental studies, this thesis provided the contributions for development of HCCI setup at MTU. In particular, this thesis made contributions in the areas of measurement of valve profiles, measurement of piston to valve contact clearance for procuring new pistons for further studies of high geometric compression ratio HCCI engines. It also consists of developing and testing a supercharging station and the setup of an electrical air heater to extend the HCCI operating region. The HCCI engine setup is based on a GM 2.0 L LHU Gen 1 engine which is a direct injected engine with variable valve timing (VVT) capabilities. For the simulation studies, a computationally efficient modeling platform has been developed and validated against experimental data from a single cylinder HCCI engine. In-cylinder pressure trace, combustion phasing (CA10, CA50, BD) and performance metrics IMEP, thermal efficiency, and CO emission are found to be in good agreement with experimental data for different operating conditions. Effects of phasing intake and exhaust valves are analyzed using SMRH. In addition, a novel index called Fuel Efficiency and Emissions (FEE) index is defined and is used to determine the optimal valve timings for engine operation through the use of FEE contour maps.

Post-processing of sequential indicator simulation realizations for modeling geologic bodies

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Sequential fusion of decisions from adaptive and random samples for controlled verification of errors

Fusion techniques have received considerable attention for achieving performance improvement with biometrics. While a multi-sample fusion architecture reduces false rejects, it also increases false accepts. This impact on performance also depends on the nature of subsequent attempts, i.e., random or adaptive. Expressions for error rates are presented and experimentally evaluated in this work by considering the multi-sample fusion architecture for text-dependent speaker verification using HMM based digit dependent speaker models. Analysis incorporating correlation modeling demonstrates that the use of adaptive samples improves overall fusion performance compared to randomly repeated samples. For a text dependent speaker verification system using digit strings, sequential decision fusion of seven instances with three random samples is shown to reduce the overall error of the verification system by 26% which can be further reduced by 6% for adaptive samples. This analysis novel in its treatment of random and adaptive multiple presentations within a sequential fused decision architecture, is also applicable to other biometric modalities such as finger prints and handwriting samples.

Structural and functional characterization of the human CCR5 receptor in complex with HIV gp120 envelope glycoprotein and CD4 receptor by molecular modeling studies

The entry of human immunodeficiency virus (HIV) into cells depends on a sequential interaction of the gp120 envelope glycoprotein with the cellular receptors CD4 and members of the chemokine receptor family. The CC chemokine receptor CCR5 is such a receptor for several chemokines and a major coreceptor for the entry of R5 HIV type-1 (HIV-1) into cells. Although many studies focus on the interaction of CCR5 with HIV-1, the corresponding interaction sites in CCR5 and gp120 have not been matched. Here we used an approach combining protein structure modeling, docking and molecular dynamics simulation to build a series of structural models of the CCR5 in complexes with gp120 and CD4. Interactions such as hydrogen bonds, salt bridges and van der Waals contacts between CCR5 and gp120 were investigated. Three snapshots of CCR5-gp120-CD4 models revealed that the initial interactions of CCR5 with gp120 are involved in the negatively charged N-terminus (Nt) region of CCR5 and positively charged bridging sheet region of gp120. Further interactions occurred between extracellular loop2 (ECL2) of CCR5 and the base of V3 loop regions of gp120. These interactions may induce the conformational changes in gp120 and lead to the final entry of HIV into the cell. These results not only strongly support the two-step gp120-CCR5 binding mechanism, but also rationalize extensive biological data about the role of CCR5 in HIV-1 gp120 binding and entry, and may guide efforts to design novel inhibitors.

Learning and Production of Movement Sequences: Behavioral, Neurophysiological, and Modeling Perspectives

A growing wave of behavioral studies, using a wide variety of paradigms that were introduced or greatly refined in recent years, has generated a new wealth of parametric observations about serial order behavior. What was a mere trickle of neurophysiological studies has grown to a more steady stream of probes of neural sites and mechanisms underlying sequential behavior. Moreover, simulation models of serial behavior generation have begun to open a channel to link cellular dynamics with cognitive and behavioral dynamics. Here we summarize the major results from prominent sequence learning and performance tasks, namely immediate serial recall, typing, 2XN, discrete sequence production, and serial reaction time. These populate a continuum from higher to lower degrees of internal control of sequential organization. The main movement classes covered are speech and keypressing, both involving small amplitude movements that are very amenable to parametric study. A brief synopsis of classes of serial order models, vis-à-vis the detailing of major effects found in the behavioral data, leads to a focus on competitive queuing (CQ) models. Recently, the many behavioral predictive successes of CQ models have been joined by successful prediction of distinctively patterend electrophysiological recordings in prefrontal cortex, wherein parallel activation dynamics of multiple neural ensembles strikingly matches the parallel dynamics predicted by CQ theory. An extended CQ simulation model-the N-STREAMS neural network model-is then examined to highlight issues in ongoing attemptes to accomodate a broader range of behavioral and neurophysiological data within a CQ-consistent theory. Important contemporary issues such as the nature of working memory representations for sequential behavior, and the development and role of chunks in hierarchial control are prominent throughout.

Handling Sequential Observations in Intelligent Surveillance

Demand for intelligent surveillance in public transport systems is growing due to the increased threats of terrorist attack, vandalism and litigation. The aim of intelligent surveillance is in-time reaction to information received from various monitoring devices, especially CCTV systems. However, video analytic algorithms can only provide static assertions, whilst in reality, many related events happen in sequence and hence should be modeled sequentially. Moreover, analytic algorithms are error-prone, hence how to correct the sequential analytic results based on new evidence (external information or later sensing discovery) becomes an interesting issue. In this paper, we introduce a high-level sequential observation modeling framework which can support revision and update on new evidence. This framework adapts the situation calculus to deal with uncertainty from analytic results. The output of the framework can serve as a foundation for event composition. We demonstrate the significance and usefulness of our framework with a case study of a bus surveillance project.

A Continuous Time Markov Chain Based Sequential Analytical Approach for Composite Power System Reliability Assessment

This paper proposes a continuous time Markov chain (CTMC) based sequential analytical approach for composite generation and transmission systems reliability assessment. The basic idea is to construct a CTMC model for the composite system. Based on this model, sequential analyses are performed. Various kinds of reliability indices can be obtained, including expectation, variance, frequency, duration and probability distribution. In order to reduce the dimension of the state space, traditional CTMC modeling approach is modified by merging all high order contingencies into a single state, which can be calculated by Monte Carlo simulation (MCS). Then a state mergence technique is developed to integrate all normal states to further reduce the dimension of the CTMC model. Moreover, a time discretization method is presented for the CTMC model calculation. Case studies are performed on the RBTS and a modified IEEE 300-bus test system. The results indicate that sequential reliability assessment can be performed by the proposed approach. Comparing with the traditional sequential Monte Carlo simulation method, the proposed method is more efficient, especially in small scale or very reliable power systems.

A dynamic sequential route choice model for micro-simulation

Dans les études sur le transport, les modèles de choix de route décrivent la sélection par un utilisateur d’un chemin, depuis son origine jusqu’à sa destination. Plus précisément, il s’agit de trouver dans un réseau composé d’arcs et de sommets la suite d’arcs reliant deux sommets, suivant des critères donnés. Nous considérons dans le présent travail l’application de la programmation dynamique pour représenter le processus de choix, en considérant le choix d’un chemin comme une séquence de choix d’arcs. De plus, nous mettons en œuvre les techniques d’approximation en programmation dynamique afin de représenter la connaissance imparfaite de l’état réseau, en particulier pour les arcs éloignés du point actuel. Plus précisément, à chaque fois qu’un utilisateur atteint une intersection, il considère l’utilité d’un certain nombre d’arcs futurs, puis une estimation est faite pour le restant du chemin jusqu’à la destination. Le modèle de choix de route est implanté dans le cadre d’un modèle de simulation de trafic par événements discrets. Le modèle ainsi construit est testé sur un modèle de réseau routier réel afin d’étudier sa performance.

Modeling High-Dimensional Audio Sequences with Recurrent Neural Networks

Cette thèse étudie des modèles de séquences de haute dimension basés sur des réseaux de neurones récurrents (RNN) et leur application à la musique et à la parole. Bien qu'en principe les RNN puissent représenter les dépendances à long terme et la dynamique temporelle complexe propres aux séquences d'intérêt comme la vidéo, l'audio et la langue naturelle, ceux-ci n'ont pas été utilisés à leur plein potentiel depuis leur introduction par Rumelhart et al. (1986a) en raison de la difficulté de les entraîner efficacement par descente de gradient. Récemment, l'application fructueuse de l'optimisation Hessian-free et d'autres techniques d'entraînement avancées ont entraîné la recrudescence de leur utilisation dans plusieurs systèmes de l'état de l'art. Le travail de cette thèse prend part à ce développement. L'idée centrale consiste à exploiter la flexibilité des RNN pour apprendre une description probabiliste de séquences de symboles, c'est-à-dire une information de haut niveau associée aux signaux observés, qui en retour pourra servir d'à priori pour améliorer la précision de la recherche d'information. Par exemple, en modélisant l'évolution de groupes de notes dans la musique polyphonique, d'accords dans une progression harmonique, de phonèmes dans un énoncé oral ou encore de sources individuelles dans un mélange audio, nous pouvons améliorer significativement les méthodes de transcription polyphonique, de reconnaissance d'accords, de reconnaissance de la parole et de séparation de sources audio respectivement. L'application pratique de nos modèles à ces tâches est détaillée dans les quatre derniers articles présentés dans cette thèse. Dans le premier article, nous remplaçons la couche de sortie d'un RNN par des machines de Boltzmann restreintes conditionnelles pour décrire des distributions de sortie multimodales beaucoup plus riches. Dans le deuxième article, nous évaluons et proposons des méthodes avancées pour entraîner les RNN. Dans les quatre derniers articles, nous examinons différentes façons de combiner nos modèles symboliques à des réseaux profonds et à la factorisation matricielle non-négative, notamment par des produits d'experts, des architectures entrée/sortie et des cadres génératifs généralisant les modèles de Markov cachés. Nous proposons et analysons également des méthodes d'inférence efficaces pour ces modèles, telles la recherche vorace chronologique, la recherche en faisceau à haute dimension, la recherche en faisceau élagué et la descente de gradient. Finalement, nous abordons les questions de l'étiquette biaisée, du maître imposant, du lissage temporel, de la régularisation et du pré-entraînement.

Efficient 3D scene modeling and mosaicing

El modelat d'escenes és clau en un gran ventall d'aplicacions que van des de la generació mapes fins a la realitat augmentada. Aquesta tesis presenta una solució completa per a la creació de models 3D amb textura. En primer lloc es presenta un mètode de Structure from Motion seqüencial, a on el model 3D de l'entorn s'actualitza a mesura que s'adquireix nova informació visual. La proposta és més precisa i robusta que l'estat de l'art. També s'ha desenvolupat un mètode online, basat en visual bag-of-words, per a la detecció eficient de llaços. Essent una tècnica completament seqüencial i automàtica, permet la reducció de deriva, millorant la navegació i construcció de mapes. Per tal de construir mapes en àrees extenses, es proposa un algorisme de simplificació de models 3D, orientat a aplicacions online. L'eficiència de les propostes s'ha comparat amb altres mètodes utilitzant diversos conjunts de dades submarines i terrestres.

Radial Plasma Dynamic in Sequential Pinches

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

cDNA sequence and molecular modeling of a nerve growth factor from Bothrops jararacussu venomous gland

The complete nucleotide sequence of a nerve growth factor precursor from Bothrops jararacussu snake (Bj-NGF) was determined by DNA sequencing of a clone from cDNA library prepared from the poly(A) + RNA of the venom gland of B.jararacussu. cDNA encoding Bj-NGF precursor contained 723 bp in length, which encoded a prepro-NGF molecule with 241 amino acid residues. The mature Bj-NGF molecule was composed of I 18 amino acid residues with theoretical pI and molecular weight of 8.31 and 13,537, respectively. Its amino acid sequence showed 97%, 96%, 93%, 86%, 78%, 74%, 76%, 76% and 55% sequential similarities with NGFs from Crotalus durissus terrificus, Agkistrodon halys pallas, Daboia (Vipera) russelli russelli, Bungarus multicinctus, Naja sp., mouse, human, bovine and cat, respectively. Phylogenetic analyses based on the amino acid sequences of 15 NGFs separate the Elapidae family (Naja and Bungarus) from those Crotalidae snakes (Bothrops, Crotalus and Agkistrodon). The three-dimensional structure of mature Bj-NGF was modeled based on the crystal structure of the human NGF. The model reveals that the core of NGF, formed by a pair of P-sheets, is highly conserved and the major mutations are both at the three beta-hairpin loops and at the reverse turn. (C) 2002 Societe francaise de biochimie et biologic moleculaire/Editions scientifiques et medicales Elsevier SAS. All rights reserved.

Optimization Strategies Based on Sequential Quadratic Programming Applied for a Fermentation Process for Butanol Production

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)