To see the other types of publications on this topic, follow the link: Human activity.
Dissertations / Theses on the topic 'Human activity'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Human activity.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Albinali, Fahd. "Activity-Aware Computing: Modeling of Human Activity and Behavior." Diss., The University of Arizona, 2008. http://hdl.handle.net/10150/195382.
Full textAbstract:
With our society becoming increasingly mobile and devices that are small, inexpensive and wireless, we are transitioning from an age of desktop computing to an age where computers are used in all aspects of life and leisure. Ubiquitous Computing is largely concerned with the progression of computers from stationary desktop environments to environments where computers and sensors are integrated with objects and every aspect of our daily life, often in an invisible way.This dissertation investigates an important problem in Ubiquitous Computing: detecting domestic activities using ubiquitously deployed sensors from data sets of limited size. The dissertation assumes that home environments in the next 20 years will support a wide range of sensing technologies that are built in smart appliances and the surrounding environment (e.g. RFID tags and readers, accelerometers, temperature sensors etc.). The dissertation also assumes that there will be an abundance of embedded CPU power in the environment that will enable fast and efficient spectral analysis and feature extraction from sensor signals. Using efficient wireless technologies such as the new Bluetooth Wibree protocol, these devices will be able to communicate their sensed data in an efficient way.Two approaches are presented for domestic activity recognition from wireless sensors. The first approach is rule-based and logical in nature and is suitable when sensor data is not present for training. Importantly, fuzzy distributions model the uncertainty and variability in expert knowledge. The second approach is probabilistic in nature and learns by observation without human intervention. This approach uses Bayesian Learning and is optimized to deal with sparse data sets (with hundreds of sensor readings and few instances of activities). Further, a case study is presented in which activity recognition optimizes energy consumption for wireless PC cards that results in significant energy savings.This dissertation concludes by highlighting major and minor results. A summary of the author's future and current research efforts is presented including the application of activity recognition in medical interventions and resource allocation problems.
2
Reyes, Ortiz Jorge Luis. "Smartphone-based human activity recognition." Doctoral thesis, Universitat Politècnica de Catalunya, 2014. http://hdl.handle.net/10803/284725.
Full textAbstract:
Human Activity Recognition (HAR) is a multidisciplinary research field that aims to gather data regarding people's behavior and their interaction with the environment in order to deliver valuable context-aware information. It has nowadays contributed to develop human-centered areas of study such as Ambient Intelligence and Ambient Assisted Living, which concentrate on the improvement of people's Quality of Life.
The first stage to accomplish HAR requires to make observations from ambient or wearable sensor technologies. However, in the second case, the search for pervasive, unobtrusive, low-powered, and low-cost devices for achieving this challenging task still has not been fully addressed. In this thesis, we explore the use of smartphones as an alternative approach for performing the identification of physical activities. These self-contained devices, which are widely available in the market, are provided with embedded sensors, powerful computing capabilities and wireless communication technologies that make them highly suitable for this application. This work presents a series of contributions regarding the development of HAR systems with smartphones. In the first place we propose a fully operational system that recognizes in real-time six physical activities while also takes into account the effects of postural transitions that may occur between them. For achieving this, we cover some research topics from signal processing and feature selection of inertial data, to Machine Learning approaches for classification. We employ two sensors (the accelerometer and the gyroscope) for collecting inertial data. Their raw signals are the input of the system and are conditioned through filtering in order to reduce noise and allow the extraction of informative activity features. We also emphasize on the study of Support Vector Machines (SVMs), which are one of the state-of-the-art Machine Learning techniques for classification, and reformulate various of the standard multiclass linear and non-linear methods to find the best trade off between recognition performance, computational costs and energy requirements, which are essential aspects in battery-operated devices such as smartphones. In particular, we propose two multiclass SVMs for activity classification:one linear algorithm which allows to control over dimensionality reduction and system accuracy; and also a non-linear hardware-friendly algorithm that only uses fixed-point arithmetic in the prediction phase and enables a model complexity reduction while maintaining the system performance. The efficiency of the proposed system is verified through extensive experimentation over a HAR dataset which we have generated and made publicly available. It is composed of inertial data collected from a group of 30 participants which performed a set of common daily activities while carrying a smartphone as a wearable device. The results achieved in this research show that it is possible to perform HAR in real-time with a precision near 97\% with
smartphones. In this way, we can employ the proposed methodology in several higher-level applications that require HAR such as ambulatory monitoring of the disabled and the elderly during periods above five days without the need of a battery recharge. Moreover, the proposed algorithms can be adapted to other commercial wearable devices recently introduced in the market (e.g. smartwatches, phablets, and glasses). This will open up new opportunities for developing practical and innovative HAR applications.<br>El Reconocimiento de Actividades Humanas (RAH) es un campo de investigación multidisciplinario que busca recopilar información sobre el comportamiento de las personas y su interacción con el entorno con el propósito de ofrecer información contextual de alta significancia sobre las acciones que ellas realizan. Recientemente, el RAH ha contribuido en el desarrollo de áreas de estudio enfocadas a la mejora de la calidad de vida del hombre tales como: la inteligència ambiental (Ambient Intelligence) y la vida cotidiana asistida por el entorno para personas dependientes (Ambient Assisted Living). El primer paso para conseguir el RAH consiste en realizar observaciones mediante el uso de sensores fijos localizados en el ambiente, o bien portátiles incorporados de forma vestible en el cuerpo humano. Sin embargo, para el segundo caso, aún se dificulta encontrar dispositivos poco invasivos, de bajo consumo energético, que permitan ser llevados a cualquier lugar, y de bajo costo. En esta tesis, nosotros exploramos el uso de teléfonos móviles inteligentes (Smartphones) como una alternativa para el RAH. Estos dispositivos, de uso cotidiano y fácilmente asequibles en el mercado, están dotados de sensores embebidos, potentes capacidades de cómputo y diversas tecnologías de comunicación inalámbrica que los hacen apropiados para esta aplicación. Nuestro trabajo presenta una serie de contribuciones en relación al desarrollo de sistemas para el RAH con Smartphones. En primera instancia proponemos un sistema que permite la detección de seis actividades físicas en tiempo real y que, además, tiene en cuenta las transiciones posturales que puedan ocurrir entre ellas. Con este fin, hemos contribuido en distintos ámbitos que van desde el procesamiento de señales y la selección de características, hasta algoritmos de Aprendizaje Automático (AA). Nosotros utilizamos dos sensores inerciales (el acelerómetro y el giroscopio) para la captura de las señales de movimiento de los usuarios. Estas han de ser procesadas a través de técnicas de filtrado para la reducción de ruido, segmentación y obtención de características relevantes en la detección de actividad. También hacemos énfasis en el estudio de Máquinas de soporte vectorial (MSV) que son uno de los algoritmos de AA más usados en la actualidad. Para ello reformulamos varios de sus métodos estándar (lineales y no lineales) con el propósito de encontrar la mejor combinación de variables que garanticen un buen desempeño del sistema en cuanto a precisión, coste computacional y requerimientos de energía, los cuales son aspectos esenciales en dispositivos portátiles con suministro de energía mediante baterías. En concreto, proponemos dos MSV multiclase para la clasificación de actividad: un algoritmo lineal que permite el balance entre la reducción de la dimensionalidad y la precisión del sistema; y asimismo presentamos un algoritmo no lineal conveniente para dispositivos con limitaciones de hardware que solo utiliza aritmética de punto fijo en la fase de predicción y que permite reducir la complejidad del modelo de aprendizaje mientras mantiene el rendimiento del sistema. La eficacia del sistema propuesto es verificada a través de una experimentación extensiva sobre la base de datos RAH que hemos generado y hecho pública en la red. Esta contiene la información inercial obtenida de un grupo de 30 participantes que realizaron una serie de actividades de la vida cotidiana en un ambiente controlado mientras tenían sujeto a su cintura un smartphone que capturaba su movimiento. Los resultados obtenidos en esta investigación demuestran que es posible realizar el RAH en tiempo real con una precisión cercana al 97%. De esta manera, podemos emplear la metodología propuesta en aplicaciones de alto nivel que requieran el RAH tales como monitorizaciones ambulatorias para personas dependientes (ej. ancianos o discapacitados) durante periodos mayores a cinco días sin la necesidad de recarga de baterías.
3
Outten, Alan Gerard. "Analysis of human muscle activity." Thesis, Imperial College London, 1997. http://hdl.handle.net/10044/1/7958.
Full text
4
TOKALA, SAI SUJIT, and RANADEEP ROKALA. "HUMAN ACTIVITY MONITORING USING SMARTPHONE." Thesis, Blekinge Tekniska Högskola, Institutionen för tillämpad signalbehandling, 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-2566.
Full textAbstract:
The main aim of the project is to develop an algorithm which will classify the activity performed by a human who is carrying a smart phone. The day to day life made humans very busy at work and during daily activities, mostly elderly people who are at home have an important need to monitor their activity by others when they are alone, if they are inactive for a long time without movement, or in some situations like if they have fallen down, became unconscious for sometime or seized with a cardiac arrest etc… will help the observer to know the state of activity of person being monitored. In this project we develop an algorithm to know the activity of a person using accelerometer available in Smartphone. We have extracted the Smartphone accelerometer data using an application called accelerometer data logger version 1.0 available in Smartphone market and have processed the data in Matlab for classifying the different activities of human being into static and dynamic activity, if the activity is dynamic then further classification into walking or running is performed with the algorithm. We implemented smoothening filters for data analysis and statistical techniques like standard deviation, mean and signal magnitude analysis for activity classification. This classification algorithm will let us know the type of activity either static or dynamic and then classify the position of the user, such as walking, running or ideal, which can provide useful information for the observer who is monitoring the activities of wearer, and which will help the wearer for his daily living. To bring out the extensive use of algorithm and to provide valuable feedback for wearer regarding his activities, energy spent by user during the activities was calculated at a given time using regression methods and was implemented in the algorithm. The developed model was able to estimate the energy spent by the user, the observations recorded were almost similar to the treadmill data which is taken as a standard for our model and the mean error is not more than ±2 for 30 observations. The final results when compared with the standard model was proved to be 93 % accurate on average of 30 subjects data which is used for verifying the algorithm developed. With these set of results we have come to a conclusion that algorithm can be easily implemented in a real time Smartphone application with low false predictions and can be implemented with low computational cost and fast real-time response. In future our classification algorithm can also be used in military applications where one can know what the soldier is doing without actually seeing him and additionally it can be proved as a support system in athlete’s health monitoring and training.<br>I denna modell har vi utvecklat en algoritm för aktivitetsklassificeringoch energiförbrukning uppskattning , vilket hjälper oss i övervakningen daglig mänsklig aktivitet med större noggrannhet . Resultaten valideras med standard energiförbrukning teknik och aktivitetsklassificeringsvideoobservationer. Vi vill att denna modell ska integreras i smarta mobiltelefoner för att ge slutanvändaren en vänlig atmosfär utan att lägga några komplicerade funktioner för hantering av utrustningen . Denna modell är mycket användbart i klinisk uppföljning av patienterna , kommer det att hjälpa oss att övervaka gamla , sjuka och utvecklingsstörda personens aktivitetsidentifiering och hjälper oss i nära övervakning av patienterna men fysiskt att vara borta från dem . Våra bärbara MEMS baserade treaxlig accelerometer system baserat smartphone kompatibel algoritm tillsammans med andra fysiologiska övervakningsparametrarkommer att ge korrekt övervakning rörelse och energiförbrukning uppskattning för klinisk analys . Denna modell är användbar för analys och övervakning av grupp -och enskilda individer , vilket kommer att leda till att spåra deras rörelser och en framgångsrik räddningsaktion för att rädda dem från dödliga sjukdomar och förebygga risker när de är skadade . Framtida arbete kommer att vara kontinuerlig övervakning av ämnen enskild aktivitet tillsammans med gruppaktivitet . Identifiera hållning övergång av olika aktiviteter i en kort tid som att springa till sittande , sittande till stående , står att krypa etc.<br>0091-7660885577
5
Ameri-Daragheh, Alireza. "Wearable human activity recognition systems." Thesis, California State University, Long Beach, 2015. http://pqdtopen.proquest.com/#viewpdf?dispub=1595755.
Full textAbstract:
<p> In this thesis, we focused on designing wearable human activity recognition (WHAR) systems. As the first step, we conducted a thorough research over the publications during the recent ten years in this area. Then, we proposed an all-purpose architecture for designing the software of WHAR systems. Afterwards, among various applications of these wearable systems, we decided to work on wearable virtual fitness coach device which can recognize various types and intensities of warm-up exercises that an athlete performs. We first proposed a basic hardware platform for implementing the WHAR software. Afterwards, the software design was done in two phases. In the first phase, we focused on four simple activities to be recognized by the wearable device. We used Weka machine learning tool to build a mathematical model which could recognize the four activities with the accuracy of 99.32%. Moreover, we proposed an algorithm to measure the intensity of the activities with the accuracy of 93%. In the second phase, we focused on eight complex warm-up exercises. After building the mathematical model, the WHAR system could recognize the eight activities with the accuracy of 95.60%.</p>
6
Kepenekci, Burcu. "Human Activity Recognition By Gait Analysis." Phd thesis, METU, 2011. http://etd.lib.metu.edu.tr/upload/12613089/index.pdf.
Full textAbstract:
This thesis analyzes the human action recognition problem. Human actions are modeled as a time evolving temporal texture. Gabor filters, which are proved to be a robust 2D texture representation tool by detecting spatial points with high variation, is extended to 3D domain to capture motion texture features. A well known filtering algorithm and a recent unsupervised clustering algorithm, the Genetic Chromodynamics, are combined to select salient spatio-temporal features of the temporal texture and to segment the activity sequence into temporal texture primitives. Each activity sequence is represented as a composition of temporal texture primitives with its salient spatio-temporal features, which are also the symbols of our codebook. To overcome temporal variation between different performances of the same action, a Profile Hidden Markov Model is applied with Viterbi Path Counting (ensemble training). Not only parameters and structure but also codebook is learned during training.
7
Akpinar, Kutalmis. "Human Activity Classification Using Spatio-temporal." Master's thesis, METU, 2012. http://etd.lib.metu.edu.tr/upload/12614587/index.pdf.
Full textAbstract:
This thesis compares the state of the art methods and proposes solutions for human activity classification from video data. Human activity classification is finding the meaning of human activities, which are captured by the video. Classification of human activity is needed in order to improve surveillance video analysis and summarization, video data mining and robot intelligence. This thesis focuses on the classification of low level human activities which are used as an important information source to determine high level activities.
In this study, the feature relation histogram based activity description proposed by Ryoo et al. (2009) is implemented and extended. The feature histogram is widely used in feature based approaches<br>however, the feature relation histogram has the ability to represent the locational information of the features. Our extension defines a new set of relations between the features, which makes the method more effective for action description. Classifications are performed and results are compared using feature histogram, Ryoo&rsquo<br>s feature relation histogram and our feature relation histogram using the same datasets and the feature type. Our experiments show that feature relation histogram performs slightly better than the feature histogram, our feature relation histogram is even better than both of the two. Although the difference is not clearly observable in the datasets containing periodic actions, a 12% improvement is observed for the non-periodic action datasets. Our work shows that the spatio-temporal relation represented by our new set of relations is a better way to represent the activity for classification.
8
Qi, Lin. "Autonomous Identification of Human Activity Regions." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-212052.
Full textAbstract:
Human activity regions (HARs) are human-centric semantic partitions where observing and/or interacting with humans is likely in indoor environments. HARs are useful for achieving successful human-robot interaction, such as in safe navigation around a building or to know where to be able to assist humans in their activities. In this thesis, a system is designed for generating HARs automatically based on data recorded by robots. This approach to generating HARs is to cluster the areas that are commonly associated with frequent human presence. In order to detect human positions, we employ state-of-the-art perception techniques. The environment that the robot patrols is assumed to be an indoor environment such as an office. We show how we can generate HARs in correct regions by clustering human position data. The experimental evaluations show that we can do so in different indoor environments, with data acquired from different sensors and that the system can handle noise.<br>Mänskliga aktivitetsregioner, HARs (Human Activity Regions) är människocentreraderegioner som ger en semantisk partitionering av inomhusmiljöer. HARs är användbara för att uppnå väl fungerande människarobot- interaktioner. I denna avhandling utformas ett system för att generera HARs automatiskt baserat på data från robotar. Detta görs genom att klustra observationer av människor för att på så vis få fram de områden som är associerade med frekvent mänsklig närvaro. Experiment visar att systemet kan hantera data som registrerats av olika sensorer i olika inomhusmiljöer och att det är robust. Framförallt genererar systemet en pålitlig partitionering av miljön.
9
Lakins, Johnathon N. "Structure and activity of human clusterin." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1999. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape7/PQDD_0021/NQ45178.pdf.
Full text
10
Devaraj, Revathy. "Validation of the Human Activity Profile." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2000. http://www.collectionscanada.ca/obj/s4/f2/dsk2/ftp01/MQ52893.pdf.
Full text
11
Pham, Cuong Van. "Human activity recognition for pervasive interaction." Thesis, University of Newcastle Upon Tyne, 2012. http://hdl.handle.net/10443/1684.
Full textAbstract:
This thesis addresses the challenge of computing food preparation context in the kitchen. The automatic recognition of fine-grained human activities and food ingredients is realized through pervasive sensing which we achieve by instrumenting kitchen objects such as knives, spoons, and chopping boards with sensors. Context recognition in the kitchen lies at the heart of a broad range of real-world applications. In particular, activity and food ingredient recognition in the kitchen is an essential component for situated services such as automatic prompting services for cognitively impaired kitchen users and digital situated support for healthier eating interventions. Previous works, however, have addressed the activity recognition problem by exploring high-level-human activities using wearable sensing (i.e. worn sensors on human body) or using technologies that raise privacy concerns (i.e. computer vision). Although such approaches have yielded significant results for a number of activity recognition problems, they are not applicable to our domain of investigation, for which we argue that the technology itself must be genuinely “invisible”, thereby allowing users to perform their activities in a completely natural manner. In this thesis we describe the development of pervasive sensing technologies and algorithms for finegrained human activity and food ingredient recognition in the kitchen. After reviewing previous work on food and activity recognition we present three systems that constitute increasingly sophisticated approaches to the challenge of kitchen context recognition. Two of these systems, Slice&Dice and Classbased Threshold Dynamic Time Warping (CBT-DTW), recognize fine-grained food preparation activities. Slice&Dice is a proof-of-concept application, whereas CBT-DTW is a real-time application that also addresses the problem of recognising unknown activities. The final system, KitchenSense is a real-time context recognition framework that deals with the recognition of a more complex set of activities, and includes the recognition of food ingredients and events in the kitchen. For each system, we describe the prototyping of pervasive sensing technologies, algorithms, as well as real-world experiments and empirical evaluations that validate the proposed solutions.
12
Blanke, Ulf Mario [Verfasser]. "Recognizing Complex Human Activity Based on Activity Spotting / Ulf Mario Blanke." München : Verlag Dr. Hut, 2011. http://d-nb.info/1017353484/34.
Full text
13
Bryan, Donna Sarah. "Regulation of interleukin-6 activity in human keratinocytes by human papillomavirus." Thesis, Queen Mary, University of London, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.286270.
Full text
14
Zagnoli, Andrea. "Human Activity Recognition con telecamere di profondità." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2017. http://amslaurea.unibo.it/12946/.
Full textAbstract:
Lo studio presentato in questa Tesi si propone di elaborare, implementare e testare un algoritmo di Human Activity Recognition (HAR) basato su telecamere di profondità. Per HAR si intende quel settore del machine learning che mira a studiare tecniche che, tramite l’acquisizione di informazioni da sorgenti di diverso tipo, permettano ad una macchina di apprendere in modo autonomo un metodo di classificazione delle attività umane. In particolare l’algoritmo proposto sfrutta la tecnologia delle telecamere di profondità (il sensore utilizzato è il Microsoft Kinect) che a differenza delle tradizionali telecamere a colori proiettano un campo di luce infrarossa e, in base a come questa viene riflessa dagli oggetti nella stanza, è in grado di calcolare la distanza tra il sensore e l’oggetto. L’algoritmo implementato in ambiente .NET, è stato testato su due dataset raccolti dal Computer Science Department, Cornell University e su un nuovo dataset raccolto contestualmente a questo studio. I risultati sperimentali confermano l’efficacia dell’algoritmo su tutte le azioni raccolte nei diversi dataset.
15
Tadesse, Girmaw Abebe. "Human activity recognition using a wearable camera." Doctoral thesis, Universitat Politècnica de Catalunya, 2018. http://hdl.handle.net/10803/668914.
Full textAbstract:
Advances in wearable technologies are facilitating the understanding of human activities using first-person vision (FPV) for a wide range of assistive applications. In this thesis, we propose robust multiple motion features for human activity recognition from first person videos. The proposed features encode discriminant characteristics form magnitude, direction and dynamics of motion estimated using optical flow. M:>reover, we design novel virtual-inertial features from video, without using the actual inertial sensor, from the movement of intensity centroid across frames. Results on multiple datasets demonstrate that centroid-based inertial features improve the recognition performance of grid-based features.
Moreover, we propose a multi-layer modelling framework that encodes hierarchical and temporal relationships among activities. The first layer operates on groups of features that effectively encode motion dynamics and temporal variaitons of intra-frame appearance descriptors of activities with a hierarchical topology. The second layer exploits the temporal context by weighting the outputs of the hierarchy during modelling. In addition, a post-decoding smoothing technique utilises decisions on past samples based on the confidence of the current sample. We validate the proposed framework with several classi fiers, and the temporal modelling is shown to improve recognition performance.
We also investigate the use of deep networks to simplify the feature engineering from first-person videos. We propose a stacking of spectrograms to represent short-term global motions that contains a frequency-time representation of multiplemotion components. This enables us to apply 2D convolutions to extract/learn motion features. We employ long short-term memory recurrent network to encode long-term temporal dependency among activiites. Furthermore, we apply cross-domain knowledge transfer between inertial based and vision-based approaches for egocentric activity recognition. We propose sparsity weightedcombination of information from different motion modalities and/or streams . Results show that the proposed approach performs competitively with existing deep frameworks, moreover, with reduced complexity.<br>Los avances en tecnologías wearables facilitan la comprensión de actividades humanas utilizando cuando se usan videos grabados en primera persona para una amplia gama de aplicaciones. En esta tesis, proponemos características robustas de movimiento para el reconocimiento de actividades humana a partir de videos en primera persona. Las características propuestas codifican características discriminativas estimadas a partir de optical flow como magnitud, dirección y dinámica de movimiento. Además, diseñamos nuevas características de inercia virtual a partir de video, sin usar sensores inerciales, utilizando el movimiento del centroide de intensidad a través de los fotogramas. Los resultados obtenidos en múltiples bases de datos demuestran que las características inerciales basadas en centroides mejoran el rendimiento de reconocimiento en comparación con grid-based características. Además, proponemos un algoritmo multicapa que codifica las relaciones jerárquicas y temporales entre actividades. La primera capa opera en grupos de características que codifican eficazmente las dinámicas del movimiento y las variaciones temporales de características de apariencia entre múltiples fotogramas utilizando una jerarquía. La segunda capa aprovecha el contexto temporal ponderando las salidas de la jerarquía durante el modelado. Además, diseñamos una técnica de postprocesado para filtrar las decisiones utilizando estimaciones pasadas y la confianza de la estimación actual. Validamos el algoritmo propuesto utilizando varios clasificadores. El modelado temporal muestra una mejora del rendimiento en el reconocimiento de actividades. También investigamos el uso de redes profundas (deep networks) para simplificar el diseño manual de características a partir de videos en primera persona. Proponemos apilar espectrogramas para representar movimientos globales a corto plazo. Estos espectrogramas contienen una representación espaciotemporal de múltiples componentes de movimiento. Esto nos permite aplicar convoluciones bidimensionales para aprender funciones de movimiento. Empleamos long short-term memory recurrent networks para codificar la dependencia temporal a largo plazo entre las actividades. Además, aplicamos transferencia de conocimiento entre diferentes dominios (cross-domain knowledge) entre enfoques inerciales y basados en la visión para el reconocimiento de la actividad en primera persona. Proponemos una combinación ponderada de información de diferentes modalidades de movimiento y/o secuencias. Los resultados muestran que el algoritmo propuesto obtiene resultados competitivos en comparación con existentes algoritmos basados en deep learning, a la vez que se reduce la complejidad.
16
Kruusvall, I︠U︡. "Environmental and social influence on human activity." Tartu, Estonia : Dept. of Psychology, University of Tartu, 1994. http://catalog.hathitrust.org/api/volumes/oclc/35034030.html.
Full text
17
Westholm, Erik. "A Simulator Tool for Human Activity Recognition." Thesis, Örebro University, School of Science and Technology, 2010. http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-10322.
Full textAbstract:
<p>The goal of this project was to create a simulator that was to produce data for research in the field of activity recognition. The simulator was to simulate a human entity moving around in, and interacting with, a PEIS environment. This simulator ended up being based on The Sims 3, and how this was done is described. The reader is expected to have some experience with programming.</p>
18
Meijer, Gerwin Alexander Leo. "Physical activity implications for human energy metabolism /." [Maastricht : Maastricht : Rijksuniversiteit Limburg] ; University Library, Maastricht University [Host], 1990. http://arno.unimaas.nl/show.cgi?fid=5563.
Full text
19
Li, Xiaoyu. "Studies of antiviral activity of human APOBEC3G." Thesis, McGill University, 2011. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=97017.
Full textAbstract:
The HIV-1 accessory protein Vif (virion infectivity factor) is required for HIV-1 to replicate in certain "non-permissive" cell types, which include major targets of HIV-1, such as primary T lymphocytes and macrophages, as well as T-cell lines such as H9. Vif is not required for viral replication in other "permissive" cell types such as SupT1, Jurkat, 293, HeLa, and CEM-SS lines. Recent studies demonstrate that non-permissive cells contain a protein called human APOBEC3G (apolipoprotein B mRNA-editing enzyme catalytic polypeptide-like 3G), which prevents HIV-1 replication in the absence of Vif. The human APOBEC3G (hA3G) is incorporated into HIV-1 during viral assembly, and inhibits HIV-1 replication in newly-infected cells. Vif is able to bind to hA3G in the cytoplasm, and induces degradation of hA3G through proteasome-dependent pathway. This prevents the incorporation of hA3G into HIV-1, thereby abolishing the anti-HIV activity of hA3G. Our project mainly focuses on the antiviral mechanism of hA3G. It has been shown that the presence of hA3G in HIV-1 strongly inhibits the ability of the virus to produce new viral DNA upon infection. Our new observation is that the reduction in late DNA synthesis is due to the hA3G induced inhibition of strand transfer steps in reverse transcription. Analysis of viral cDNA intermediates in vivo reveals that hA3G causes an inhibition of the minus and plus strand transfers, without having a significant impact on DNA elongation. Using an in vitro system to measure minus strand transfer similarly shows a dose-dependent reduction of strand transfer by hA3G. This inhibition of strand transfer occurs independently the editing activity of hA3G and is correlated with its ability to prevent RNaseH degradation of the template RNA. As hA3G expresses in human cells hosting HIV-1, inhibition of Vif-mediated hA3G degradation clearly represents a new anti-HIV-1 strategy for drug discovery. We have established a screening system to discover inhibitors that protect hA3G from Vif-mediated degradation. Through screening, compounds IMB-26 and IMB-35 were identified to be specific inhibitors for the degradation of hA3G by Vif. The inhibitors suppressed HIV-1 replication in hA3G-containing cells but not in those without hA3G. The anti-HIV effect correlated with the endogenous hA3G level. HIV-1 particles from hA3G-expressing cells treated with IMB-26/35 contained a hA3G level higher than that from those without IMB-26/35 treatment, and showed decreased infectivity. IMB-26/35 blocked Vif/hA3G interaction, and therefore protected hA3G from Vif-mediated degradation. The compounds were safe with an anti-HIV therapeutic index >200 in vitro. LD50 of IMB-26 in mice was >1000 mg/kg (intraperitoneally).<br>La protéine virale du VIH-1 Vif (virion infectivity factor) est nécessaire pour la réplication du VIH dans certains types de cellules dites non permissibles. Ces types de cellules incluent les cellules souches des lymphocytes T et des macrophages, ainsi que les lignées cellulaires des lymphocytes T, comme la lignée H9. Parmi ce groupe de lignées cellulaires, certaines sont les cibles naturelles du virus. Vif n'est pas nécessaire pour la réplication du VIH dans d'autres types de cellules dites permissibles, comme les lignées SupT1, Jurkat, 293, HeLa, et CEM-SS. Des études récentes ont démontré que les lignées non permissibles contiennent la protéine APOBEC3G (Apolipoprotein B mRNA-editing enzyme catalytic polypeptide-like 3G). La protéine humaine APOBEC3G (h3AG) est incorporée dans la particule virale durant l'assemblage du VIH et bloque la réplication du virus suite à l'infection de nouvelles cellules. Vif lie la protéine h3AG dans le cytoplasme et induit sa dégradation par le proteasome, ce qui rends les cellules non permissibles susceptibles à l'infection par le VIH.Notre projet consiste à étudier le mécanisme antiviral du h3AG. Il a déjà été montré que le hA3G inhibe la production d'ADN suite à une nouvelle infection. Nous avons remarqué que la réduction de la synthèse d'ADN est le résultat de l'inhibition de changement de brin pendant la transcription reverse. L'analyse des intermédiaires d'ADNc durant la réplication in vivo révèle que le hA3G inhibe les transferts des brins positifs et négatifs sans affecter l'étape d'élongation durant la synthèse d'ADN. Des tests menés in vitro montrent une réduction du transfert bu brin négatif dépendante de la dose du hA3G. Cette inhibition est indépendante de l'activité d'édition du hA3G, mais elle dépend de la capacité du h3AG à inhiber la dégradation de la matrice d'ARN, une étape accomplie par la RNase H. Puisque la hA3G est produite dans les cellules humaines infectées par le VIH, l'inhibition de sa dégradation par Vif constitue une cible potentielle dans un traitement éventuel contre la VIH. Alors, nous avons mis au point un système de criblage pour découvrir des inhibiteurs qui empêcheraient la dégradation de la hA3G par Vif. Nous avons identifié deux composés, IMB-26 et IMB-35, qui inhibent spécifiquement cette dégradation. Ces inhibiteurs ont bloqué la réplication du VIH dans des cellules qui contiennent la hA3G mais n'ont pas montré d'effets sur des cellules qui ne contiennent pas la hA3G. Nous avons observé une corrélation entre le niveau du hA3G et l'effet antivirale. Le traitement des cellules avec les composés IMB-26/35 augmente le niveau du hA3G et diminue la capacité du virus d'infecter de nouvelles cellules. En culture cellulaire, les index thérapeutique de ces composés est >200. Ce qui prévoit qu'ils seront sécuritaires. Chez les souris, la LD50 du IMB-26 est >1000 mg/kg (intra péritonéale). En conclusion, notre projet a permis l'identification de deux nouveaux composés antiviraux qui agissent en stabilisant la hA3G.
20
Kaelin, A. C. "A characterization of human placental monooxygenase activity." Thesis, Brunel University, 1986. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.374837.
Full text
21
Kilner, James Morvan. "Oscillatory activity in the human motor system." Thesis, University College London (University of London), 2001. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.369225.
Full text
22
Hendriks-Jansen, Horst. "Situated activity, interactive emergence, and human thought." Thesis, University of Sussex, 1994. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.386443.
Full text
23
Kroese, Karolin. "Generating biomarkers of human Nek8 kinase activity." Thesis, University of Leicester, 2018. http://hdl.handle.net/2381/42233.
Full textAbstract:
Nek8 is a member of the human NIMA-related serine/threonine protein kinase family that has roles in cell cycle progression, primary cilia function and the DNA damage response. Mutations in the human nek8 gene cause Nephronophthisis (NPHP), an autosomal recessive polycystic kidney disease in which defects in primary cilia lead to a broad range of often severe symptoms that affect many organs of the body. In the kidneys, NPHP causes the development of cortico-medullary cysts that impair kidney function and ultimately lead to kidney failure. Nek8 localises to the primary cilium where it interacts with Inversin and PC-2, products of genes that are also mutated in inherited cystic kidney diseases. Nek8 also plays a role in the intra-S phase DNA damage checkpoint where it contributes to cell cycle arrest by inhibiting CDK2 activity to allow time for repair of stalled replication forks. The purpose of this study was to generate novel biomarkers of Nek8 kinase activity that could be used to shed light on its role at the primary cilium and in the replication stress response. Our aim was therefore to identify phosphosites of Nek8 in its potential substrate proteins, Inversin and PC-2, and to generate phospho-specific antibodies against these sites. We chose three sites in the Inversin N-terminus for phospho-specific antibody generation and showed that these were capable of detecting purified, phosphorylated Inversin upon incubation with Nek8. Second, we characterised a phospho-Nek8 antibody that recognises a phosphorylation site in the activation loop of the kinase. This antibody was capable of detecting autophosphorylated Nek8 by Western blot and immunofluorescence microscopy as confirmed using two, newly identified chemical inhibitors of Nek8. Localisation studies with this antibody revealed novel data on the presence of active Nek8 at centrosomes, cilia and sites of DNA damage. Finally, we found that Nek8 inhibition was associated with generation of enlarged multinucleated cells and accumulation of DNA damage foci. Together, these data support a role for Nek8 in linking ciliary signalling pathways and the DNA damage response, while the phospho-specific antibodies represent a new set of tools that can be used to explore Nek8 function in normal and pathological states.
24
Machado, Inês Prata. "Human activity data discovery based on accelerometry." Master's thesis, Faculdade de Ciências e Tecnologia, 2013. http://hdl.handle.net/10362/10992.
Full text
25
Ziaeefard, Maryam. "Time-slice analysis of dyadic human activity." Doctoral thesis, Université Laval, 2017. http://hdl.handle.net/20.500.11794/27920.
Full textAbstract:
La reconnaissance d’activités humaines à partir de données vidéo est utilisée pour la surveillance ainsi que pour des applications d’interaction homme-machine. Le principal objectif est de classer les vidéos dans l’une des k classes d’actions à partir de vidéos entièrement observées. Cependant, de tout temps, les systèmes intelligents sont améliorés afin de prendre des décisions basées sur des incertitudes et ou des informations incomplètes. Ce besoin nous motive à introduire le problème de l’analyse de l’incertitude associée aux activités humaines et de pouvoir passer à un nouveau niveau de généralité lié aux problèmes d’analyse d’actions. Nous allons également présenter le problème de reconnaissance d’activités par intervalle de temps, qui vise à explorer l’activité humaine dans un intervalle de temps court. Il a été démontré que l’analyse par intervalle de temps est utile pour la caractérisation des mouvements et en général pour l’analyse de contenus vidéo. Ces études nous encouragent à utiliser ces intervalles de temps afin d’analyser l’incertitude associée aux activités humaines. Nous allons détailler à quel degré de certitude chaque activité se produit au cours de la vidéo. Dans cette thèse, l’analyse par intervalle de temps d’activités humaines avec incertitudes sera structurée en 3 parties. i) Nous présentons une nouvelle famille de descripteurs spatiotemporels optimisés pour la prédiction précoce avec annotations d’intervalle de temps. Notre représentation prédictive du point d’intérêt spatiotemporel (Predict-STIP) est basée sur l’idée de la contingence entre intervalles de temps. ii) Nous exploitons des techniques de pointe pour extraire des points d’intérêts afin de représenter ces intervalles de temps. iii) Nous utilisons des relations (uniformes et par paires) basées sur les réseaux neuronaux convolutionnels entre les différentes parties du corps de l’individu dans chaque intervalle de temps. Les relations uniformes enregistrent l’apparence locale de la partie du corps tandis que les relations par paires captent les relations contextuelles locales entre les parties du corps. Nous extrayons les spécificités de chaque image dans l’intervalle de temps et examinons différentes façons de les agréger temporellement afin de générer un descripteur pour tout l’intervalle de temps. En outre, nous créons une nouvelle base de données qui est annotée à de multiples intervalles de temps courts, permettant la modélisation de l’incertitude inhérente à la reconnaissance d’activités par intervalle de temps. Les résultats expérimentaux montrent l’efficience de notre stratégie dans l’analyse des mouvements humains avec incertitude.<br>Recognizing human activities from video data is routinely leveraged for surveillance and human-computer interaction applications. The main focus has been classifying videos into one of k action classes from fully observed videos. However, intelligent systems must to make decisions under uncertainty, and based on incomplete information. This need motivates us to introduce the problem of analysing the uncertainty associated with human activities and move to a new level of generality in the action analysis problem. We also present the problem of time-slice activity recognition which aims to explore human activity at a small temporal granularity. Time-slice recognition is able to infer human behaviours from a short temporal window. It has been shown that temporal slice analysis is helpful for motion characterization and for video content representation in general. These studies motivate us to consider timeslices for analysing the uncertainty associated with human activities. We report to what degree of certainty each activity is occurring throughout the video from definitely not occurring to definitely occurring. In this research, we propose three frameworks for time-slice analysis of dyadic human activity under uncertainty. i) We present a new family of spatio-temporal descriptors which are optimized for early prediction with time-slice action annotations. Our predictive spatiotemporal interest point (Predict-STIP) representation is based on the intuition of temporal contingency between time-slices. ii) we exploit state-of-the art techniques to extract interest points in order to represent time-slices. We also present an accumulative uncertainty to depict the uncertainty associated with partially observed videos for the task of early activity recognition. iii) we use Convolutional Neural Networks-based unary and pairwise relations between human body joints in each time-slice. The unary term captures the local appearance of the joints while the pairwise term captures the local contextual relations between the parts. We extract these features from each frame in a time-slice and examine different temporal aggregations to generate a descriptor for the whole time-slice. Furthermore, we create a novel dataset which is annotated at multiple short temporal windows, allowing the modelling of the inherent uncertainty in time-slice activity recognition. All the three methods have been evaluated on TAP dataset. Experimental results demonstrate the effectiveness of our framework in the analysis of dyadic activities under uncertainty
26
Albert, Florea George, and Filip Weilid. "Deep Learning Models for Human Activity Recognition." Thesis, Malmö universitet, Fakulteten för teknik och samhälle (TS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-20201.
Full textAbstract:
AMI Meeting Corpus (AMI) -databasen används för att undersöka igenkännande av gruppaktivitet. AMI Meeting Corpus (AMI) -databasen ger forskare fjärrstyrda möten och naturliga möten i en kontorsmiljö; mötescenario i ett fyra personers stort kontorsrum. För attuppnågruppaktivitetsigenkänninganvändesbildsekvenserfrånvideosoch2-dimensionella audiospektrogram från AMI-databasen. Bildsekvenserna är RGB-färgade bilder och ljudspektrogram har en färgkanal. Bildsekvenserna producerades i batcher så att temporala funktioner kunde utvärderas tillsammans med ljudspektrogrammen. Det har visats att inkludering av temporala funktioner både under modellträning och sedan förutsäga beteende hos en aktivitet ökar valideringsnoggrannheten jämfört med modeller som endast använder rumsfunktioner[1]. Deep learning arkitekturer har implementerats för att känna igen olika mänskliga aktiviteter i AMI-kontorsmiljön med hjälp av extraherade data från the AMI-databas.Neurala nätverks modellerna byggdes med hjälp av KerasAPI tillsammans med TensorFlow biblioteket. Det finns olika typer av neurala nätverksarkitekturer. Arkitekturerna som undersöktes i detta projektet var Residual Neural Network, Visual GeometryGroup 16, Inception V3 och RCNN (LSTM). ImageNet-vikter har använts för att initialisera vikterna för Neurala nätverk basmodeller. ImageNet-vikterna tillhandahålls av Keras API och är optimerade för varje basmodell [2]. Basmodellerna använder ImageNet-vikter när de extraherar funktioner från inmatningsdata. Funktionsextraktionen med hjälp av ImageNet-vikter eller slumpmässiga vikter tillsammans med basmodellerna visade lovande resultat. Både Deep Learning användningen av täta skikt och LSTM spatio-temporala sekvens predikering implementerades framgångsrikt.<br>The Augmented Multi-party Interaction(AMI) Meeting Corpus database is used to investigate group activity recognition in an office environment. The AMI Meeting Corpus database provides researchers with remote controlled meetings and natural meetings in an office environment; meeting scenario in a four person sized office room. To achieve the group activity recognition video frames and 2-dimensional audio spectrograms were extracted from the AMI database. The video frames were RGB colored images and audio spectrograms had one color channel. The video frames were produced in batches so that temporal features could be evaluated together with the audio spectrogrames. It has been shown that including temporal features both during model training and then predicting the behavior of an activity increases the validation accuracy compared to models that only use spatial features [1]. Deep learning architectures have been implemented to recognize different human activities in the AMI office environment using the extracted data from the AMI database.The Neural Network models were built using the Keras API together with TensorFlow library. There are different types of Neural Network architectures. The architecture types that were investigated in this project were Residual Neural Network, Visual Geometry Group 16, Inception V3 and RCNN(Recurrent Neural Network). ImageNet weights have been used to initialize the weights for the Neural Network base models. ImageNet weights were provided by Keras API and was optimized for each base model[2]. The base models uses ImageNet weights when extracting features from the input data.The feature extraction using ImageNet weights or random weights together with the base models showed promising results. Both the Deep Learning using dense layers and the LSTM spatio-temporal sequence prediction were implemented successfully.
27
Sathe, Pushkar Sunil. "Tracking, Recognizing and Analyzing Human Exercise Activity." University of Akron / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=akron1574250900963207.
Full text
28
Boeheim, Jamie Lynn. "Human activity recognition using limb component extraction /." Online version of thesis, 2008. http://hdl.handle.net/1850/7764.
Full text
29
O'Malley, Patrick D. "Human activity tracking for wide-area surveillance." [Gainesville, Fla.] : University of Florida, 2002. http://purl.fcla.edu/fcla/etd/UFE1000150.
Full textAbstract:
Thesis (M.S.)--University of Florida, 2002.<br>Title from title page of source document. Document formatted into pages; contains vi, 46 p.; also contains graphics. Includes vita. Includes bibliographical references.
30
Böhme, Martin [Verfasser]. "Tracking gaze and human activity / Martin Böhme." Lübeck : Zentrale Hochschulbibliothek Lübeck, 2010. http://d-nb.info/1004772181/34.
Full text
31
Pang, Jinyong. "Human Activity Recognition Based on Transfer Learning." Scholar Commons, 2018. https://scholarcommons.usf.edu/etd/7558.
Full textAbstract:
Human activity recognition (HAR) based on time series data is the problem of classifying various patterns. Its widely applications in health care owns huge commercial benefit. With the increasing spread of smart devices, people have strong desires of customizing services or product adaptive to their features. Deep learning models could handle HAR tasks with a satisfied result. However, training a deep learning model has to consume lots of time and computation resource. Consequently, developing a HAR system effectively becomes a challenging task. In this study, we develop a solid HAR system using Convolutional Neural Network based on transfer learning, which can eliminate those barriers.
32
Dreher, Heinz. "Empowering Human Cognitive Activity through Hypertext Technology." Thesis, Curtin University, 1997. http://hdl.handle.net/20.500.11937/813.
Full textAbstract:
This research explores how computers may be used by individual researchers engaged in cognitive activity and creating original outputs, specifically, how one of the emerging information technologies, hypertext, is able to provide suggestions for the understanding to support and empower human cognitive activity.The study investigates the possibility of a new model within which to approach that part of research that seeks to make connections to what has been done previously, and to stimulate new thoughts.Imagine swimming in a vast sea of potentially useful information. How can one possibly begin to make sense of it? Engage in a phenomenological experience in which the data is permitted to speak to you. Immerse yourself, navigate around with the ability to backtrack, search, explore trails of associative thought, all with a prepared mind. The mind is prepared, or sensitised, due to the previous research and learning ? the culture to which one belongs. The process will gradually cause an uncluttering of the sea of information resulting eventually in what in this thesis is termed Generative Conceptualisation. The tools and techniques used to do this (for it is impossible to work unaided with large amounts of data) will have provided the empowerment to generate and create. The tyranny of linear order has been replaced by the dynamically varying structure of selected, sometimes hierarchical and othertimes herterarchic or network views of the data, forming or exposing (primarily through juxtaposition) insights, new ideas, and new knowledge. These are some characteristics of working in a hypertext paradigm.Generative Conceptualisation is introduced to describe the intermingling of human mind and computer hypertext, which, it is argued, results in a greater degree of original output by researchers. A hypertext paradigm, the definition of which emerges in the thesis, is suggested as being an environment for Generative Conceptualisation. A theory (substantive) of knowledge creation is offered in the concluding chapter, in the light of which existing formal theories of knowledge creation may be reviewed or elaborated.
33
Dreher, Heinz. "Empowering Human Cognitive Activity through Hypertext Technology." Curtin University of Technology, School of Information Systems, 1997. http://espace.library.curtin.edu.au:80/R/?func=dbin-jump-full&object_id=9393.
Full textAbstract:
This research explores how computers may be used by individual researchers engaged in cognitive activity and creating original outputs, specifically, how one of the emerging information technologies, hypertext, is able to provide suggestions for the understanding to support and empower human cognitive activity.The study investigates the possibility of a new model within which to approach that part of research that seeks to make connections to what has been done previously, and to stimulate new thoughts.Imagine swimming in a vast sea of potentially useful information. How can one possibly begin to make sense of it? Engage in a phenomenological experience in which the data is permitted to speak to you. Immerse yourself, navigate around with the ability to backtrack, search, explore trails of associative thought, all with a prepared mind. The mind is prepared, or sensitised, due to the previous research and learning ? the culture to which one belongs. The process will gradually cause an uncluttering of the sea of information resulting eventually in what in this thesis is termed Generative Conceptualisation. The tools and techniques used to do this (for it is impossible to work unaided with large amounts of data) will have provided the empowerment to generate and create. The tyranny of linear order has been replaced by the dynamically varying structure of selected, sometimes hierarchical and othertimes herterarchic or network views of the data, forming or exposing (primarily through juxtaposition) insights, new ideas, and new knowledge. These are some characteristics of working in a hypertext paradigm.Generative Conceptualisation is introduced to describe the intermingling of human mind and computer hypertext, which, it is argued, results in a greater degree of original output by researchers. A hypertext paradigm, the definition of which emerges in the thesis, is ++<br>suggested as being an environment for Generative Conceptualisation. A theory (substantive) of knowledge creation is offered in the concluding chapter, in the light of which existing formal theories of knowledge creation may be reviewed or elaborated.
34
Najder-Stefaniak, K. "Ethical dimension of management of human activity and of human work results." Thesis, Сумський державний університет, 2014. http://essuir.sumdu.edu.ua/handle/123456789/34304.
Full textAbstract:
The contemporary human being realizes that their activity influences the surrounding world and themselves. At the same time, the occurrences that have taken place in the 20th and 21st century make them recognize the fact of the existence of the multidimensional cultural crisis and that they have reached the “turning point.” These happenings inspire to reflection on the creative activity of the human being; they make us realize that it is really important, in relation to that activity, to exercise the virtue of wisdom, i.e. the constant predisposition to create the good.
When you are citing the document, use the following link http://essuir.sumdu.edu.ua/handle/123456789/34304
35
Karpatschof, Benny. "Human activity : contributions to the anthropological sciences from a perspective of activity theory /." Copenhagen : Dansk psykologisk forlag, 2000. http://catalogue.bnf.fr/ark:/12148/cb37716657t.
Full text
36
Porter, Joanna Catherine Mary. "Control of leukocyte integrin activity on T lymphocytes." Thesis, University College London (University of London), 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.312850.
Full text
37
Griffin, B. D. "Studies of human factor VIII." Thesis, Open University, 1986. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.482878.
Full textAbstract:
Factor VIII is a complex of two proteins, the von Willebrand factor (or factor VIII related antigen) and the procoagulant protein. Both are essential for normal haemostasis. Problems exist in the purification of factor VIII as it is present in only low concentrations in plasma, and its procoagulant activity is unstable. As a result, therapeutic factor VIII concentrates prepared by the Blood Transfusion Service (for the treatment of heamophilia and von Willebrand's disease) are relatively impure, and the yield from existing purification processes is low. The studies presented in this thesis are aimed towards increasing the quality and yield of therapeutic concentrates. Attention has been focussed on improving methods for the purification and assay of factor VIII. Novel affinity purifications reagents for factor VIII have been studied, and methods for removing the major impurity (fibrinogen) from conventional factor VIII concentrates have been investigated. The factor VIII related antigen (FVIIIR:Ag) and the procoagulant antigen (FVIII:CAg) have been purified, and used as immunogens for the production of specific antibodies. A large volume of polyclonal antibody to FVIIIR:Ag has been produced in sheep. This was subsequently used to develop an immunopurification method for FVIII:CAg. Immunisation of mice with purified FVIII:CAg gave a valuable panel of ten monoclonal antibodies to procoagulant factor VIII. These have important applications in the assay, purification and biochemical study of this protein. Sensitive radiometric assays for FVIIIR:Ag and FVIII:CAg have been established. This work involved the development of methods for the preparation of ¹²⁵I-FVIIIR:Ag, and for the purification and labelling of human anti-FVIII:CAg Fab' fragments from inhibitor plasma. An artificial factor VIII-deficient substrate has been prepared on a large scale for the one-stage bioassay of procoagulant activity (FVIII:C).
38
Niu, Feng. "Human Activity Recognition and Pathological Gait Pattern Identification." Scholarly Repository, 2007. http://scholarlyrepository.miami.edu/oa_dissertations/247.
Full textAbstract:
Human activity analysis has attracted great interest from computer vision researchers due to its promising applications in many areas such as automated visual surveillance, computer-human interactions, and motion-based identification and diagnosis. This dissertation presents work in two areas: general human activity recognition from video, and human activity analysis for the purpose of identifying pathological gait from both 3D captured data and from video. Even though the research in human activity recognition has been going on for many years, still there are many issues that need more research. This includes the effective representation and modeling of human activities and the segmentation of sequences of continuous activities. In this thesis we present an algorithm that combines shape and motion features to represent human activities. In order to handle the activity recognition from any viewing angle we quantize the viewing direction and build a set of Hidden Markov Models (HMMs), where each model represents the activity from a given view. Finally, a voting based algorithm is used to segment and recognize a sequence of human activities from video. Our method of representing activities has good attributes and is suitable for both low resolution and high resolution video. The voting based algorithm performs the segmentation and recognition simultaneously. Experiments on two sets of video clips of different activities show that our method is effective. Our work on identifying pathological gait is based on the assumption of gait symmetry. Previous work on gait analysis measures the symmetry of gait based on Ground Reaction Force data, stance time, swing time or step length. Since the trajectories of the body parts contain information about the whole body movement, we measure the symmetry of the gait based on the trajectories of the body parts. Two algorithms, which can work with different data sources, are presented. The first algorithm works on 3D motion-captured data and the second works on video data. Both algorithms use support vector machine (SVM) for classification. Each of the two methods has three steps: the first step is data preparation, i.e., obtaining the trajectories of the body parts; the second step is gait representation based on a measure of gait symmetry; and the last step is SVM based classification. For 3D motion-captured data, a set of features based on Discrete Fourier Transform (DFT) is used to represent the gait. We demonstrate the accuracy of the classification by a set of experiments that shows that the method for 3D motion-captured data is highly effective. For video data, a model based tracking algorithm for human body parts is developed for preparing the data. Then, a symmetry measure that works on the sequence of 2D data, i.e. sequence of video frames, is derived to represent the gait. We performed experiments on both 2D projected data and real video data to examine this algorithm. The experimental results on 2D projected data showed that the presented algorithm is promising for identifying pathological gait from video. The experimental results on the real video data are not good as the results on 2D projected data. We believe that better results could be obtained if the accuracy of the tracking algorithm is improved.
39
Pouke, M. (Matti). "Augmented virtuality:transforming real human activity into virtual environments." Doctoral thesis, Oulun yliopisto, 2015. http://urn.fi/urn:isbn:9789526208343.
Full textAbstract:
Abstract The topic of this work is the transformation of real-world human activity into virtual environments. More specifically, the topic is the process of identifying various aspects of visible human activity with sensor networks and studying the different ways how the identified activity can be visualized in a virtual environment. The transformation of human activities into virtual environments is a rather new research area. While there is existing research on sensing and visualizing human activity in virtual environments, the focus of the research is carried out usually within a specific type of human activity, such as basic actions and locomotion. However, different types of sensors can provide very different human activity data, as well as lend itself to very different use-cases. This work is among the first to study the transformation of human activities on a larger scale, comparing various types of transformations from multiple theoretical viewpoints. This work utilizes constructs built for use-cases that require the transformation of human activity for various purposes. Each construct is a mixed reality application that utilizes a different type of source data and visualizes human activity in a different way. The constructs are evaluated from practical as well as theoretical viewpoints. The results imply that different types of activity transformations have significantly different characteristics. The most distinct theoretical finding is that there is a relationship between the level of detail of the transformed activity, specificity of the sensors involved and the extent of world knowledge required to transform the activity. The results also provide novel insights into using human activity transformations for various practical purposes. Transformations are evaluated as control devices for virtual environments, as well as in the context of visualization and simulation tools in elderly home care and urban studies<br>Tiivistelmä Tämän väitöskirjatyön aiheena on ihmistoiminnan muuntaminen todellisesta maailmasta virtuaalitodellisuuteen. Työssä käsitellään kuinka näkyvästä ihmistoiminnasta tunnistetaan sensoriverkkojen avulla erilaisia ominaisuuksia ja kuinka nämä ominaisuudet voidaan esittää eri tavoin virtuaaliympäristöissä. Ihmistoiminnan muuntaminen virtuaaliympäristöihin on kohtalaisen uusi tutkimusalue. Olemassa oleva tutkimus keskittyy yleensä kerrallaan vain tietyntyyppisen ihmistoiminnan, kuten perustoimintojen tai liikkumisen, tunnistamiseen ja visualisointiin. Erilaiset anturit ja muut datalähteet pystyvät kuitenkin tuottamaan hyvin erityyppistä dataa ja siten soveltuvat hyvin erilaisiin käyttötapauksiin. Tämä työ tutkii ensimmäisten joukossa ihmistoiminnan tunnistamista ja visualisointia virtuaaliympäristössä laajemmassa mittakaavassa ja useista teoreettisista näkökulmista tarkasteltuna. Työssä hyödynnetään konstrukteja jotka on kehitetty eri käyttötapauksia varten. Konstruktit ovat sekoitetun todellisuuden sovelluksia joissa hyödynnetään erityyppistä lähdedataa ja visualisoidaan ihmistoimintaa eri tavoin. Konstrukteja arvioidaan sekä niiden käytännön sovellusalueen, että erilaisten teoreettisten viitekehysten kannalta. Tulokset viittaavat siihen, että erilaisilla muunnoksilla on selkeästi erityyppiset ominaisuudet. Selkein teoreettinen löydös on, että mitä yksityiskohtaisemmasta toiminnasta on kyse, sitä vähemmän tunnistuksessa voidaan hyödyntää kontekstuaalista tietoa tai tavanomaisia datalähteitä. Tuloksissa tuodaan myös uusia näkökulmia ihmistoiminnan visualisoinnin hyödyntämisestä erilaisissa käytännön sovelluskohteissa. Sovelluskohteina toimivat ihmiskehon käyttäminen ohjauslaitteena sekä ihmistoiminnan visualisointi ja simulointi kotihoidon ja kaupunkisuunnittelun sovellusalueilla
40
Matilainen, M. (Matti). "Embedded computer vision methods for human activity recognition." Doctoral thesis, Oulun yliopisto, 2017. http://urn.fi/urn:isbn:9789526216256.
Full textAbstract:
Abstract The way how people interact with machines will change in the future. Long have been the traditional ways – mouse and keyboard – the primary interface between man and computer. Recently, the voice and gesture controlled interfaces have been introduced in many devices but they have not yet become very popular. One possible direction where human-computer interfaces can go is to be able to completely hide the interface from the user and allow him or her to interact with the machines in a way that is more natural to human. This thesis introduces a smart living space concept that is a small step towards that direction. The interfacing is assumed to be done unnoticeably to the user via a wireless sensor network that is monitoring the user and analysing his or her behaviour and also using a hand held mobile device which can be used to control the system. A system for human body part segmentation is presented. The system is applied in various applications related to person identification from one’s gait and unusual activity detection. The system is designed to work robustly when the data streams provided by the sensor network are noisy. This increases the usefulness of the system in home environments where the person using the interface is either occluded by the static objects in the room or is interacting with any movable objects. The second part of the proposed smart living space concept is the mobile device carried by the user. Two methods that can be used in a hand gesture-based UI are proposed. A database for training such methods is proposed<br>Tiivistelmä Tapa jolla ihmiset käyttävät tietokonetta on muuttumassa. Hiiri ja näppäimistö ovat olleet jo pitkään yleisimmät tavat, joilla tietokoneita on ohjattu. Uusia tapoja ohjata tietokonetta on kehitetty, mutta ne eivät ole vielä syrjäyttäneet perinteisiä menetelmiä täysin. Yksi todennäköinen muutos tulevaisuudessa on se, että käyttöliittymät sulautetaan ympäristöön ja sen myötä tehdään käyttökokemuksesta luonnollisempi ihmiselle. Tässä väitöskirjassa esitellään järjestelmä, joka muuttaa ihmisen elinympäristön älykkääksi. Langaton kameraverkko analysoi automaattisesti huoneen tapahtumia ja käyttäjä kontrolloi järjestelmää eleohjatulla mobiililaitteella. Väitöskirjassa esitellään menetelmä ihmisen ruumiinosien tunnistukseen, jota sovelletaan myös ihmisen tunnistukseen kävelytyylistä ja epänormaalien aktiviteettien tunnistukseen. Menetelmää suunnitellessa on painotettu sitä, että se toimisi myös silloin, kun käytettävissä on vain huonolaatuista ja kohinaista videodataa. Kohinaa aiheuttaa kotiympäristöissä erityisesti huonekalut, jotka osittain peittävät näkymää ja tavarat, joita huoneessa oleskeleva ihminen saattaa siirrellä. Toinen osa väitöskirjaa käsittelee mobiililaitteen ohjausta käsielein ja esittelee kaksi menetelmää, joilla tällainen käyttöliittymä on mahdollista toteuttaa. Toisen menetelmän opetuksessa käytetty käsitietokanta ja tietokannan vertailutulokset julkaistaan
41
Costa, Bento Diana Filipa. "Immune activity during progression of human colorectal cancer." Thesis, Cardiff University, 2016. http://orca.cf.ac.uk/96996/.
Full textAbstract:
Colorectal cancer (CRC) patients survive and stay free of disease for longer after surgery if their primary tumours were infiltrated with an increased density of T cells. Studies of breast tumours and melanoma have also shown that the presence of specialised blood vessels named high endothelial venules (HEVs), within tumours are associated with a high density of infiltrating T cells and a positive prognosis. It is therefore possible, that presence of HEVs within CRC is associated with a high density of infiltrating T cells and a good patient outcome. To test this hypothesis, primary tumours, resected from sixty-two CRC patients were analysed for the presence of HEVs. These were studied with respect to the numbers and distribution of intra-tumoural T cells as well as tumour stage and patient survival. The results showed that HEV developed in response to CRC but were found within the extra-tumoural area and not the tumour mass. HEVs were also always present within a concentration of T and B cells, namely lymphoid aggregates which resemble ectopic lymphoid structures (ELS). These ELS were associated with more advanced disease and hence did not necessarily identify patients with a better prognosis. Recent studies have suggested that the type of T cells infiltrating the tumours is a determinant for patient outcome indicating that not all T cells confer benefit. IL-17A producing T cells are thought to drive CRC development. Moreover, our laboratory has previously shown that detection of a CEA (Carcinoembryonic antigen)-specific T cell response by in vitro secretion of IFN-γ is associated with tumour recurrence whereas the opposite is true for the 5T4 tumour antigen. This study therefore set out to determine whether IL-17A producing T cells are present at higher frequencies in CRC compared to normal bowel and whether IL-17Aproducing T cells are CEA-specific. The experiments revealed that IL-17A-producing T cells are present at a higher frequency within CRCs, but the prevalence of Th17 responses specific for 5T4 was slightly higher than for CEA, implying that IL-17A secretion by CEA-specific T cells was not responsible for the tumour recurrence. Tumours from CEA-responsive patients were less immunogenic than those from CEA non-responsive patients reflecting the aggressiveness of the tumour.
42
Sauma, Lilian. "Transcriptional activity of PPARγ in primary human adipocytes". Doctoral thesis, Linköpings universitet, Internmedicin, 2009. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-19169.
Full textAbstract:
The prevalence of obesity is increasing in most parts of the world and is a strong risk factor for the development of insulin resistance, type 2 diabetes and hypertension. Adipose tissue is mainly composed of adipocytes which store energy in the form of triglycerides and release it as free fatty acids. Adipose tissue is one of the major regulators of energy homeostasis in the body. Adipose tissue in different regions of the body has different characteristics and adipocytes in intra-abdominal fat depots are more associated with insulin resistance than adipocytes from subcutaneous fat depots. Research performed during the past several years has led to an explosion in the understanding of adipose tissue and the active role that it plays in aspects of physiology and pathophysiology. One important discovery has been identification of the nuclear hormone receptor called peroxisome proliferator-activated receptor γ (PPARγ). Peroxisome proliferator-activated receptor γ (PPARγ) is a transcription factor, which is highly expressed in adipocytes. PPARγ has been shown to affect several genes of importance for lipid metabolism, differentiation of fat cells and insulin sensitivity. The PPARγ receptor can be activated by thiazolidinediones (TZD), a class of insulinsensitising drugs, which promote fatty acid storage in fat depots and decrease glucose levels in plasma, thus, demonstrating the importance of PPARγ activity in insulin resistance and metabolic syndrome. This thesis has investigated the transcriptional activity of PPARγ in a clinically relevant cell type for insulin resistance and type 2 diabetes; the primary human adipocyte. For this purpose, a method for transfection of primary human adipocytes by electroporation and for measurement of the activity of PPARγ has been developed and optimised. This method has been used to study the effect of saturated and unsaturated fatty acids on the transcriptional activity of PPARγ. Interestingly, it was been found that saturated fatty acids can activate PPARγ, thus promoting a protection against diabetes. The strongest activator was the monounsaturated palmitoleic acid. The transcriptional activity of PPARγ in primary human adipocytes from intra-abdominal and subcutaneous adipose tissues was also examined. It was found that PPARγ activity is considerably lower in adipocytes from visceral compared with subcutaneous fat from the same subject. Another reason for using human tissue to reach clinical relevance shown here was that the same difference in PPARγ activity could not be found between intra-abdominal and subcutaneous fat tissues in mice. This finding may serve as the basis of why excess intraabdominal fat tissue is associated with high risk for development of type 2 diabetes and cardiovascular diseases. The blood pressure regulating renin-angiotensin system (RAS) in human adipose tissue and in isolated adipocytes was examined and related to PPARγ. It was found that the production of angiotensin II, which is an important hormone for increasing the blood pressure, can be produced by isolated adipocytes and that the production is higher in adipocytes coming from omental than subcutaneous fat tissue. Further, it was shown that angiotensin II inhibits PPARγ activity in omental adipocytes, thus reducing the insulin sensitivity. Therefore, this study connects two of the major risk factors in obesity; diabetes and hypertension, and may also explain how drugs, which inhibit the RAS, can also be protective against diabetes. In conclusion, the findings in this thesis give new knowledge about regulating mechanisms of fat cells and its importance in diabetes and cardiovascular disease.<br>Prevalensen av fetma ökar drastiskt i stora delar av världen och utgör en stor riskfaktor för att utveckla insulinresistens, typ 2 diabetes och hypertoni. Fett kan lagras i olika fettdepåer i kroppen. Fettet som inlagras inuti kroppen, intraabdominellt fett, skiljer sig från fettväven som lagras direkt under huden (subkutant fett). Nyare rön visar att en stor mängd intra-abdominell fettvävnad är en särskilt stark riskfaktor för att utveckla insulinresistens och typ 2 diabetes, samt att avlägsnande av subkutant fett knappast alls påverkar riskfaktorer för kardiovaskulär sjukdom. Under de senaste åren har forskningen lett till en djupare förståelse av fettvävnaden och dess aktiva roll i fysiologin och patofysiologin av insulinresistens. En viktig upptäckt har varit identifieringen av en nukleär receptor som kallas för PPARγ (peroxisome proliferator-activated receptor gamma). PPARγ receptorn uttrycks huvudsakligen i fettceller och är viktig för fettcelldifferentieringen och fettcellsfunktionen. Receptorn aktiveras av vissa läkemedel för behandling av insulinresistens och hyperglykemi, de så kallade tiazolidindionerna (avandia och actos finns på den svenska marknaden), som sänker blodsockret och även påverkar blodtrycket samt blodfetterna i gynnsam riktning. Detta utgör ett tydligt bevis för betydelsen av PPARγ aktiviteten vid insulinresistens och det metabola syndromet. Den här avhandlingen studerar transkriptionsaktiviteten av PPARγ i en klinisk relevant celltyp för insulinresistens och typ 2 diabetes, den mänskliga fettcellen. För detta ändamål har en metod för transfektion av primära humana fettceller utvecklats. Metoden användes för att studera insulinsignaleringen i detalj och också för att mäta aktiviteten hos transkriptionsfaktorer. Aktiviteten av PPARγ i primära humana fettceller påverkades olika av olika mättade och omättade fettsyror, som alltså kan verka som hormoner. Intressant nog visades att mättat fett, som av många anses vara särskilt ”onyttigt”, i form av stearinsyra kan aktivera PPARγ och därmed tänkas medföra ett skydd mot diabetes. Den starkaste aktivatorn var enkelomättad palmoljesyra. Aktiviteten hos PPARγ i fettceller från de två olika fettdepåerna, intra-abdominella och subkutana fettvävnaden, studerades. Aktiviteten av PPARγ i isolerade fettceller från intra-abdominellt fett befanns vara betydligt lägre än i subkutant fett från samma person. Som en ytterligare anledning att använda mänsklig vävnad för att nå klinisk relevans visades också av att möss inte har samma skillnad i PPARγ aktivitet mellan subkutant och intra-abdominellt. Fynden ger underlag till varför stor mängd intraabdominellt fett är förknippat med hög risk för diabetes och därmed kopplad ökad kardiovaskulär risk. Det blodtrycksreglerande renin-angiotensin systemet (RAS) i human fettvävnad och i isolerade fettceller och relationen till PPARγ studerades. Produktionen av angiotensin II, som är ett viktigt blodtryckshöjande hormon, producerades av isolerade human fettceller och produktionen var högre från fettceller som kommer från mänskligt omentfett än från subkutant fett. Vidare visades att tillsatt angiotensin II hämmade PPARγ aktiviteten i fettceller från omentfettet. Detta fynd kopplar alltså samman två av de stora riskfaktorerna vid fetma; diabetes och högt blodtyck. Det ger också nya intressanta infallsvinklar i hur blodtrycksläkemedel som hämmar reninsystemet kan tänkas skydda mot diabetesuppkomst. Sammanfattningsvis visar denna avhandling att man kan transfektera primära humana fettceller och studera PPARγ aktivitet i denna celltyp, och att PPARγ aktiviteten kan styras av fettsyror, vilket alltså innebär att matkomponenter (fettsyror) har direkt hormonella effekter i kroppen. Omentfett visades ha särskilt låg PPARγ aktivitet. Slutligen befanns att fettväven och isolerade fettceller kan producera olika komponenter i RAS. Det är tydligt att dessa fynd tillsammans har givit upphov till viktig ny kunskap om fettcellens reglermekanismer och dess betydelse för diabetes och kardiovaskulär sjukdom.
43
Masato, Daniele. "Incremental activity and plan recognition for human teams." Thesis, University of Aberdeen, 2012. http://digitool.abdn.ac.uk:80/webclient/DeliveryManager?pid=186768.
Full textAbstract:
Anticipating human subjects' intentions and information needs is considered one of the ultimate goals of Artificial Intelligence. Activity and plan recognition contribute to this goal by studying how low-level observations about subjects and the environment in which they act can be linked to a high-level plan representation. This task is challenging in a dynamic and uncertain environment; the environment may change while the subjects are reasoning about it, and the effects of the subjects' interactions cannot be predicted with certainty. Humans generally struggle to enact plans and maintain situation awareness in such circumstances, even when they work in teams towards a common objective. Intelligent software assistants can support human teams by monitoring their activities and plan progress, thus relieving them from some of the cognitive burden they experience. The assistants' design needs to keep into account that teams can form and disband quickly in response to environmental changes, and that the course of action may change during plan execution. It is also crucial to efficiently and incrementally process a stream of observations in order to enable online prediction of those intentions and information needs. In this thesis we propose an incremental approach for team composition and activity recognition based on probabilistic graphical models. We show that this model can successfully learn team formations and behaviours in highly dynamic domains, and that classification can be performed in polynomial time. We evaluate our model within a simulated scenario provided by an open-source computer game. In addition, we discuss an incremental approach to plan recognition that exploits the results yielded by activity recognition to assess a team's course of action. We show how this model can account for incomplete or inconsistent knowledge about recognised activities, and how it can be integrated into an existing mechanism for plan recognition.
44
Fitzsimons, E. J. "5-aminolaevulinic acid synthase activity in human erythroblasts." Thesis, Bucks New University, 1986. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.381462.
Full text
45
Fisher, Rebecca Jane. "Inhibition and oscillatory activity in human motor cortex." Thesis, University College London (University of London), 2002. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.272397.
Full text
46
Stephens, Kyle. "Human and group activity recognition from video sequences." Thesis, University of York, 2016. http://etheses.whiterose.ac.uk/18347/.
Full textAbstract:
A good solution to human activity recognition enables the creation of a wide variety of useful applications such as applications in visual surveillance, vision-based Human-Computer-Interaction (HCI) and gesture recognition. In this thesis, a graph based approach to human activity recognition is proposed which models spatio-temporal features as contextual space-time graphs. In this method, spatio-temporal gradient cuboids were extracted at significant regions of activity, and feature graphs (gradient, space-time, local neighbours, immediate neighbours) are constructed using the similarity matrix. The Laplacian representation of the graph is utilised to reduce the computational complexity and to allow the use of traditional statistical classifiers. A second methodology is proposed to detect and localise abnormal activities in crowded scenes. This approach has two stages: training and identification. During the training stage, specific human activities are identified and characterised by employing modelling of medium-term movement flow through streaklines. Each streakline is formed by multiple optical flow vectors that represent and track locally the movement in the scene. A dictionary of activities is recorded for a given scene during the training stage. During the testing stage, the consistency of each observed activity with those from the dictionary is verified using the Kullback-Leibler (KL) divergence. The anomaly detection of the proposed methodology is compared to state of the art, producing state of the art results for localising anomalous activities. Finally, we propose an automatic group activity recognition approach by modelling the interdependencies of group activity features over time. We propose to model the group interdependences in both motion and location spaces. These spaces are extended to time-space and time-movement spaces and modelled using Kernel Density Estimation (KDE). The recognition performance of the proposed methodology shows an improvement in recognition performance over state of the art results on group activity datasets.
47
Duckworth, Paul. "Unsupervised human activity analysis for intelligent mobile robots." Thesis, University of Leeds, 2017. http://etheses.whiterose.ac.uk/18850/.
Full textAbstract:
The success of intelligent mobile robots in daily living environments depends on their ability to understand human movements and behaviours. One goal of recent research is to understand human activities performed in real human environments from long term observation. We consider a human activity to be a temporally dynamic configuration of a person interacting with key objects within the environment that provide some functionality. This can be a motion trajectory made of a sequence of 2-dimensional points representing a person’s position, as well as more detailed sequences of high-dimensional body poses, a collection of 3-dimensional points representing body joints positions, as estimated from the point of view of the robot. The limited field of view of the robot, restricted by the limitations of its sensory modalities, poses the challenge of understanding human activities from obscured, incomplete and noisy observations. As an embedded system it also has perceptual limitations which restrict the resolution of the human activity representations it can hope to achieve. In this thesis an approach for unsupervised learning of activities implemented on an autonomous mobile robot is presented. This research makes the following novel contributions: 1) A qualitative spatial-temporal vector space encoding of human activities as observed by an autonomous mobile robot. 2) Methods for learning a low dimensional representation of common and repeated patterns from multiple encoded visual observations. In order to handle the perceptual challenges, multiple abstractions are applied to the robot’s perception data. The human observations are first encoded using a leg-detector, an upper-body image classifier, and a convolutional neural network for pose estimation, while objects within the environment are automatically segmented from a 3-dimensional point cloud representation. Central to the success of the presented framework is mapping these encodings into an abstract qualitative space in order to generalise patterns invariant to exact quantitative positions within the real world. This is performed using a number of qualitative spatial-temporal representations which capture different aspects of the relations between the human subject and the objects in the environment. The framework auto-generates a vocabulary of discrete spatial-temporal descriptors extracted from the video sequences and each observation is represented as a vector over this vocabulary. Analogously to information retrieval on text corpora we use generative probabilistic techniques to recover latent, semantically meaningful, concepts in the encoded observations in an unsupervised manner. The relatively small number of concepts discovered are defined as multinomial distributions over the vocabulary and considered as human activity classes, granting the robot a high-level understanding of visually observed complex scenes. We validate the framework using, 1) A dataset collected from a physical robot autonomously patrolling and performing tasks in an office environment during a six week deployment, and 2) a high-dimensional “full body pose” dataset captured over multiple days by a mobile robot observing a kitchen area of an office environment from multiple view points. We show that the emergent categories from our framework align well with how humans interpret behaviours andsimple activities. Our presented framework models each extended observation as a probabilistic mixture over the learned activities, meaning it can learn human activity models even when embedded in continuous video sequences without the need for manual temporal segmentation, which can be time consuming and costly. Finally, we present methods for learning such human activity models in an incremental and continuous setting using variational inference methods to update the activity distribution online. This allows the mobile robot to efficiently learn and update its models of human activity over time, discarding the raw data, allowing for life-long learning.
48
Santos, Diliana Maria Barradas Rebelo dos. "Human activity recognition for an intelligent knee orthosis." Master's thesis, Faculdade de Ciências e Tecnologia, 2012. http://hdl.handle.net/10362/8493.
Full textAbstract:
Dissertação para obtenção do Grau de Mestre em
Engenharia Biomédica<br>Activity recognition with body-worn sensors is a large and growing field of research.
In this thesis we evaluate the possibility to recognize human activities based on data from
biosignal sensors solely placed on or under an existing passive knee orthosis, which will
produce the needed information to integrate sensors into the orthosis in the future.
The development of active orthotic knee devices will allow population to ambulate
in a more natural, efficient and less painful manner than they might with a traditional
orthosis. Thus, the term ’active orthosis’ refers to a device intended to increase the ambulatory
ability of a person suffering from a knee pathology by applying forces to correct
the position only when necessary and thereby make usable over longer periods of time.
The contribution of this work is the evaluation of the ability to recognize activities
with these restrictions on sensor placement as well as providing a proof-of-concept for
the development of an activity recognition system for an intelligent orthosis.
We use accelerometers and a goniometer placed on the orthosis and Electromyography
(EMG) sensors placed on the skin under the orthosis to measure motion and muscle activity
respectively. We segment signals in motion primitives semi-automatically and apply
Hidden-Markov-Models (HMM) to classify the isolated motion primitives. We discriminate
between seven activities like for example walking stairs up and ascend a hill. In
a user study with six participants, we evaluate the systems performance for each of the
different biosignal modalities alone as well as the combinations of them. For the best
performing combination, we reach an average person-dependent accuracy of 98% and a
person-independent accuracy of 79%.
49
Arvidsson, Dan. "Cross-Platform Modelling for Human Activity Recognition System." Thesis, Umeå universitet, Statistik, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-149731.
Full textAbstract:
Human activity recognition (HAR) systems have a large set of potential applications in healthcare, e.g. fall detection and tracking physical activities. HAR systems based on wearable sensors have gained the most attraction, due to smartphones having these sensors embedded in them. This makes them a great candidate for collecting human activity sensor data. By utilizing the smartphone sensors, no other sensors need to be supplied and instead only a mobile application needs to be supplied. However, this comes with a trade-off, sensors embedded in smartphones display specific heterogeneity and biases, depending on platform and price range. Normally in such a scenario, multiple HAR systems have to be built and trained for each device. This is both a time consuming effort and gives no guarantees that the different systems will have similar activity recognition accuracy. Therefore, in this thesis, a HAR system is constructed, where classification methods and filtering techniques are explored and evaluated, in an effort to give some guidelines for how to construct a HAR system, that can be embedded in multiple platforms. This study shows that when considering a few common activities, this HAR system performs well even when sensor data is collected from multiple sources. Ensemble method AdaBoost, in combination with decision trees, gives the overall best performance. Filtering techniques, such as Butterworth and Chebyshev performs better than constant- and linear detrending. This is primarily due to their ability to distinguish between low frequency activities, such as standing and sitting. The best result in this study was given when combining Chebyshev filtering and AdaBoosted decision trees, with a F-score of 0.9877.
50
Garcia-Rangel, Carlos-Enrique. "Anti-Candida activity of the human gut metabolome." Master's thesis, Université Laval, 2018. http://hdl.handle.net/20.500.11794/29994.
Full textAbstract:
L’intestin humain contient une variété de microbes commensaux qui sont représentés par divers organismes appartenant aux trois domaines de la vie où les Eukarya sont essentiellement représentés par le règne des champignons. La levure commensale et opportuniste Candida albicans a été identifiée comme étant le champignon le plus commun dans l’intestin des humains sains. Des études récentes soutiennent que malgré leur faible abondance les levures du genre Candida peuvent altérer l'équilibre du microbiote et conduire à des dysbioses ou des pathologies récurrentes comme la maladie de Crohn et les colites ulcéreuses. Il a été démontré que le microbiote commensal joue un rôle essentiel dans la protection de l’intestin contre la colonisation par des bactéries pathogènes et des pathobiontes. Cependant, jusqu'à présent, on ignore si la prolifération ou la pathogénicité de C. albicans peuvent être contrôlées par d'autres microbiotes fécaux. Dans cette étude, nous avons démontré que le métabolome microbien de l'intestin humain exerce une activité antifongique contre C. albicans et d’autres levures qui résident au niveau intestinal. Ces métabolites inhibent plusieurs traits de virulence de C. albicans incluant la filamentation et l'invasion des cellules humaines. De plus, un crible génétique chez C. albicans a suggéré que TOR est la cible moléculaire de la ou des molécules antifongiques du métabolome microbien de l'intestin humain.<br>The human gut contains a variety of commensal microbes which are composed of diverse organisms that belong to all three domains of life with Eukarya primarily represented by fungi. The commensal / opportunistic yeast Candida albicans has been reported as the most common fungus in the gut of healthy humans. Recent evidences support that, this small fraction can alter the microbiota equilibrium leading to dysbiosis and diseases like inflammatory bowel diseases. It has been demonstrated that commensal microbiota plays a critical role in the protection of the gut against colonization by other bacterial pathogens and pathobionts. However, so far, whether C. albicans overgrowth or pathogenicity are controlled by other fecal microbiota is not known. In this study, we showed that the human microbial gut metabolome (GM) exerts an antifungal activity against different intestinal-resident yeasts including hyphal growth and the invasion of human enterocytes of C. albicans. Furthermore, a genetic screen in C. albicans suggested that TOR is the molecular target of the antifungal molecule(s) of the GM.