No description available.

En esta tesis se estudia el problema de la robustez en los sistemas de reconocimiento automático de texto manuscrito off-line. Los sistemas de reconocimiento automático de texto manuscrito estarán maduros para su uso generalizado, cuando sean capaces de ofrecer a cualquier usuario, sin ningún tipo de preparación o adiestramiento para su utilización, una productividad razonable. Se hace necesario pues, construir sistemas flexibles y robustos en cuanto a la entrada, de tal manera que no se requiera del escritor ningún esfuerzo extra, que no haría si escribiese para ser leído por un humano. La intención del preproceso de la señal es hacer el sistema invariante a fuentes de variabilidad que no ayuden a la clasificación. En la actualidad no hay definida una solución general para conseguir invariabilidad al estilo de escritura, y cada sistema desarrolla la suya ad-hoc. En esta tesis se explorarán diferentes métodos de normalización de la señal de entrada off-line. Para ello se hace un amplio estudio de algoritmos de preproceso, tanto a nivel de toda la imagen: umbralización, reducción del ruido y corrección del desencuadre; como a nivel de texto: slope, slant y normalización del tamaño de los caracteres. Los sistemas dependientes del escritor obtienen mejores tasas de acierto que los independientes del escritor. Por otra parte, los sistemas independientes del escritor tienen más facilidad para reunir muestras de entrenamiento. En esta tesis seestudiará la adaptación de sistemas independientes del escritor para su utilizaciónpor un único escritor, con la intención de que a partir de una pocas muestras producidas por este escritor se mejore la productividad del sistema (para este escritor), o lo que es lo mismo, que éste pueda escribir de manera más relajada sin que el sistema pierda productividad. Los sistemas de reconocimiento de texto manuscrito no están exentos de errores. No sólo interesa saber el número de errores que producirá / Pastor Gadea, M. (2007). Aportaciones al reconocimiento automático de texto manuscrito [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/1832 / Palancia

This thesis is focused on gesture recognition in video. The main purpose of this thesis was to create an algorithm and an application that can recognize selected gestures using a~video obtained through a~standard webcamera. The intention was to control an application program, such as video player. The approach used to achieve this goal was to exploit methods of feature extraction, tracking, and machine learning.

Gene detection in DNA sequences is one of the most difficult problems, which have been currently solved in bioinformatics. This thesis deals with gene detection in DNA sequences with methods using Hidden Markov Models. It contains a brief description of the fundamental principles of molecular biology, explains how genetic information is stored in DNA sequences, as well as the theoretical basis of the Hidden Markov Models. Further is described subsequent approach in the design of specific Hidden Markov Models for solving the problem of gene detection in DNA sequences. Is designed and implemented application, which uses previously designed Hidden Markov model for gene detection. This application is tested on the real data, results of these tests are discussed in the end of the thesis, as well as the possible extension and continuation of the project.

In this thesis, methods of implementing an online gesture recognition system for the novel Stylaero Board device are investigated. Two methods are evaluated - one based on LSTMs and one based on HMMs - on three kinds of gestures: Tap, circle, and flick motions. A method’s performance was measured in its accuracy in determining both whether any of the above listed gestures were performed and, if so, which gesture, in an online single-pass scenario. Insight was acquired regarding the technical challenges and possible solutions to the online aspect of the problem. Poor performance was, however, observed in both methods, with a likely culprit identified as low quality of training data, due to an arduous and complex gesture performance capturing process. Further research improving on the process of gathering data is suggested.

Philosophiae Doctor - PhD / This chapter outlines basic gene structure and how gene structure is related to promoter structure in both prokaryotes and eukaryotes and their transcription machinery. An in-depth discussion is given on variations types of the promoters among both prokaryotes and eukaryotes and as well as among three prokaryotic organisms namely, E.coli, B.subtilis and Mycobacteria with emphasis on Mituberculosis. The simplest definition that can be given for a promoter is: It is a segment of Deoxyribonucleic Acid (DNA) sequence located upstream of the 5' end of the gene where the RNA Polymerase enzyme binds prior to transcription (synthesis of RNA chain representative of one strand of the duplex DNA). However, promoters are more complex than defined above. For example, not all sequences upstream of genes can function as promoters even though they may have features similar to some known promoters (from section 1.2). Promoters are therefore specific sections of DNA sequences that are also recognized by specific proteins and therefore differ from other sections of DNA sequences that are transcribed or translated. The information for directing RNA polymerase to the promoter has to be in section of DNA sequence defining the promoter region. Transcription in prokaryotes is initiated when the enzyme RNA polymerase forms a complex with sigma factors at the promoter site. Before transcription, RNA polymerase must form a tight complex with the sigma/transcription factor(s) (figure 1.1). The 'tight complex' is then converted into an 'open complex' by melting of a short region of DNA within the sequence involved in the complex formation. The final step in transcription initiation involves joining of first two nucleotides in a phosphodiester linkage (nascent RNA) followed by the release of sigma/transcription factors. RNA polymerase then continues with the transcription by making a transition from initiation to elongation of the nascent transcript.

[EN] Wireless mobile ad ho networks, also known as MANETs, are omposed by independent mobile stations that ommuni ate without requiring any sort of infrastru ture for support. These networks are hara terized by variable bandwidth values and frequent path breaks, whi h are due to hannel noise, interferen e between stations and mobility. Su h fa tors require significant adaptation apabilites at different levels of the proto ol suites employed, enabling stations to qui kly respond to fast- hanging network onditions. Resear h on the most adequate proto- ols for the physi al, MAC and routing layers is still on-going, though some basi onsensus has already been rea hed and several testbeds have been setup around the world. To deploy real-time multimedia servi es, namely voi e and video, on top of su h an unreliable network environment is a very hallenging task. In this thesis we propose to a hieve that goal starting from urrently available Wi-Fi te hnology, and gradually finding the most adequate enhan ements to ea h proto ol layer of interest; we then ombine these enhan ements until we a hieve a omplete QoS framework for ad ho networks. By using urrently available te hnology we assure that the proposal of this thesis has an inherent high-level of appli ability on real life environments. Sin e our working field fo uses on video transmission over wireless ad ho networks, we will show how it is possible to support several QoS- onstrained video streams in MANET environments hara terized by moderate to high mobility levels, and by a significant amount of best efort traffic / [ES] Las redes inalámbricas ad hoc, también conocidas como redes MANET, están compuestas por un conjunto de estaciones móviles independientes capaces de omunicarse entre sí sin necesidad de ningún tipo de infraestructura común de comunicaciones. Estas redes se caracterizan por tener un ancho de banda variable y pérdidas frecuentes de ruta que se pueden atribuir al ruido del anal inalámbrico, a la interferencia entre las estaciones móviles o bien a la movilidad de las estaciones. Dichos factores requieren una gran capacidad de adaptación en las diferentes capas de la arquitectura de protocolos, permitiendo a una estación responder rápidamente a posibles cambios bruscos en las condiciones de la red. A pesar de que aún se están realizando trabajos de investigación en bus a de los protocolos más adecuados para las capas físicas, a eso al medio (MAC) y encaminamiento, ha sido posible llegar a un nivel básico de consenso, lo cual ha permitido el despliegue de plataformas y entornos aplicados que utilizan tecnología de red MANET. Ofrecer servicios multimedia, como voz y vídeo, en redes con tan poca habilidad es un desafío importante. En esta tesis nos proponemos alcanzar este objetivo partiendo de la tecnología Wi-Fi actualmente disponible, encontrando de forma paulatina las mejoras más importantes en las diferentes capas de la arquitectura de red, para llegar, finalmente, a una solución integrada capaz de ofrecer calidad de servicio (QoS) en las redes MANET. Al utilizar la tecnología que disponemos actualmente nos aseguramos que las propuestas de esta tesis tengan un alto grado de aplicabilidad en entornos reales. Ya que la línea de trabajo de la tesis está aplicada a la transmisión de vídeo en redes MANET, demostraremos que es posible ofrecer calidad de servicio a varios flujos de vídeo en una red MANET caracterizada por altos grados de movilidad en sus nodos y un nivel significativo de tráfico o de tipo best effort / Tavares De Araujo Cesariny Calafate, CM. (2006). Analysis and design of efficient techniques for video transmission in IEEE 802.11 wireless ad hoc networks [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/135282 / TESIS

Los incendios en recintos confinados son un tipo de emergencia que involucra a bomberos cuyas vidas a veces se ponen en peligro. En cualquier incendio confinado, el equipo de emergencia puede encontrar dos tipos de ambientes de combustión, ventilados o infra-ventilados. El comportamiento cambiante de este escenario depende de múltiples factores como el tamaño del recinto, la ventilación o el combustible involucrado, entre otros. Sin embargo, la dificultad de manejar este tipo de situaciones junto con el potencial error humano sigue siendo un desafío sin resolver para los bomberos en la actualidad. En ocasiones si se dan las condiciones adecuadas, pueden aparecer los fenómenos, extremadamente peligrosos, que son estudio de este trabajo (flashover y backdraft). Por lo tanto, existe una gran demanda de nuevas técnicas y tecnologías para abordar este tipo de emergencias que amenazan la vida y puede causar graves daños estructurales. A lo anterior hay que añadir que la incorporación de cámaras térmicas en los servicios de extinción de incendios y salvamentos, supone un gran avance que puede ayudar a prevenir estos tipos de fenómenos en tiempo real utilizando técnicas de inteligencia artificial.

Coronal Mass Ejections (CMEs) and solar flares are energetic events taking place at the Sun that can affect the space weather or the near-Earth environment by the release of vast quantities of electromagnetic radiation and charged particles. Solar active regions are the areas where most flares and CMEs originate. Studying the associations among sunspot groups, flares, filaments, and CMEs is helpful in understanding the possible cause and effect relationships between these events and features. Forecasting space weather in a timely manner is important for protecting technological systems and human life on earth and in space. The research presented in this thesis introduces novel, fully computerised, machine learning-based decision rules and models that can be used within a system design for automated space weather forecasting. The system design in this work consists of three stages: (1) designing computer tools to find the associations among sunspot groups, flares, filaments, and CMEs (2) applying machine learning algorithms to the associations¿ datasets and (3) studying the evolution patterns of sunspot groups using time-series methods. Machine learning algorithms are used to provide computerised learning rules and models that enable the system to provide automated prediction of CMEs, flares, and evolution patterns of sunspot groups. These numerical rules are extracted from the characteristics, associations, and time-series analysis of the available historical solar data. The training of machine learning algorithms is based on data sets created by investigating the associations among sunspots, filaments, flares, and CMEs. Evolution patterns of sunspot areas and McIntosh classifications are analysed using a statistical machine learning method, namely the Hidden Markov Model (HMM).

The subject of this graduation thesis is an application of speech recognition into ATC commands. The selection of methods and approaches to automatic recognition of ATC commands rises from detailed air traffic studies. By the reason that there is not any definite solution in such extensive field like speech recognition, this diploma work is focused just on speech recognizer based on comparison with templates (DTW). This recognizor is in this thesis realized and compared with freely accessible HTK system from Cambrige University based on statistic methods making use of Hidden Markov models. The usage propriety of both methods is verified by practical testing and results evaluation.