Contribución a las arquitecturas flexibles para la multiconferencia web adaptable a la demanda

Los sistemas de videoconferencia y colaboración en tiempo real para múltiples usuarios permiten a sus usuarios comunicarse por medio de vídeo, audio y datos. Históricamente estos han sido sistemas caros de obtener y de mantener. El paso de las décadas ha limado estos problemas acercado el mundo de comunicación en tiempo real a un grupo mucho más amplio, llegando a usarse en diversos ámbitos como la educación o la medicina. En este sentido, el último gran salto evolutivo al que hemos asistido ha sido la transición de este tipo de aplicaciones hacia la Web. Varias tecnologías han permitido este viaje hacia el navegador. Las Aplicaciones Ricas de Internet (RIAs), que permiten crear aplicaciones Web interactivas huyendo del clásico esquema de petición y respuesta y llevando funcionalidades propias de las aplicaciones nativas a la Web. Por otro lado, la computación en la nube o Cloud Computing, con su modelo de pago por uso de recursos virtualizados, ha llevado a la creación de servicios que se adaptan mejor a la demanda, han habilitado este viaje hacia el navegador. No obstante, como cada cambio, este salto presenta una serie de retos para los sistemas de videoconferencia establecidos. Esta tesis doctoral propone un conjunto de arquitecturas, mecanismos y algoritmos para adaptar los sistemas de multiconferencia al entorno Web, teniendo en cuenta que este es accedido desde dispositivos diferentes y mediante redes de acceso variadas. Para ello se comienza por el estudio de los requisitos que debe cumplir un sistema de videoconferencia en la Web. Como resultado se diseña, implementa y desarrolla un servicio de videoconferencia que permite la colaboración avanzada entre múltiples usuarios mediante vídeo, audio y compartición de escritorio. Posteriormente, se plantea un sistema de comunicación entre una aplicación nativa y Web, proponiendo técnicas de adaptación entre los dos entornos que permiten la conversación de manera transparente para los usuarios. Estos sistemas permiten facilitar la transición hacia tecnologías Web. Como siguiente paso, se identificaron los principales problemas que existen para la comunicación multiusuario en dispositivos de tamaño reducido (teléfonos inteligentes) utilizando redes de acceso heterogéneas. Se propone un mecanismo, combinación de transcodificación y algoritmos de adaptación de calidad para superar estas limitaciones y permitir a los usuarios de este tipo de dispositivos participar en igualdad de condiciones. La aparición de WebRTC como tecnología disruptiva en este entorno, permitiendo nuevas posibilidades de comunicación en navegadores, motiva la segunda iteración de esta tesis. Aquí se presenta un nuevo esquema de adaptación a la demanda para servidores de videoconferencia diseñado para las necesidades del entorno Web y para aprovechar las características de Cloud Computing. Finalmente, esta tesis repasa las conclusiones obtenidas como fruto del trabajo llevado a cabo, reflejando la evolución de la videoconferencia Web desde sus inicios hasta nuestros días. ABSTRACT Multiuser Videoconferencing and real-time collaboration systems allow users to communicate using video, audio and data streams. These systems have been historically expensive to obtain and maintain. Over the last few decades, technological breakthroughs have mitigated those costs and popularized real time video communication, allowing its use in environments such as education or health. The last big evolutionary leap forward has been the transition of these types of applications towards theWeb. Several technologies have allowed this journey to theWeb browser. Firstly, Rich Internet Applications (RIAs) enable the creation of dynamic Web pages that defy the classical request-response interaction and provide an experience similar to their native counterparts. On the other hand, Cloud Computing brings the leasing of virtualized hardware resources in a pay-peruse model and, with it, better scalability in resource-demanding services. However, as with every change, this evolution imposes a set of challenges on existing videoconferencing solutions. This dissertation proposes a set of architectures, mechanisms and algorithms that aim to adapt multi-conferencing systems to the Web platform, taking into account the variety of devices and access networks that come with it. To this end, this thesis starts with a study concerning the requirements that must be met by new Web videoconferencing systems. The result of this study is the design, development and implementation of a new videoconferencing services that provides advanced collaboration to its user by providing video and audio communication as well as desktop sharing. After this, a new communication system between Web and native applications is presented. This system proposes adaptation mechanisms to bridge the two worlds providing a seamless integration transparent to users who can now access the powerful native application via an easy Web interface. The next step is to identify the main challenges posed by multi-conferencing on small devices (smartphones) with heterogeneous access networks. This dissertation proposes a mechanism that combines transcoding and adaptive quality algorithms to overcome those limitations. A second iteration in this dissertation is motivated by WebRTC. WebRTC appears as a disrupting technology by enabling new real-time communication possibilities in browsers. A new mechanism for flexible videoconferencing server scalability is presented. This mechanism aims to address the strong scalability requirements in the Web environment by taking advantage of Cloud Computing. Finally, the dissertation discusses the results obtained throughout the study, capturing the evolution of Web videoconferencing systems.

Strong Connectivity in Directed Hypergraphs and its Application to the Atomic Decomposition of Ontologies

Los hipergrafos dirigidos se han empleado en problemas relacionados con lógica proposicional, bases de datos relacionales, linguística computacional y aprendizaje automático. Los hipergrafos dirigidos han sido también utilizados como alternativa a los grafos (bipartitos) dirigidos para facilitar el estudio de las interacciones entre componentes de sistemas complejos que no pueden ser fácilmente modelados usando exclusivamente relaciones binarias. En este contexto, este tipo de representación es conocida como hiper-redes. Un hipergrafo dirigido es una generalización de un grafo dirigido especialmente adecuado para la representación de relaciones de muchos a muchos. Mientras que una arista en un grafo dirigido define una relación entre dos de sus nodos, una hiperarista en un hipergrafo dirigido define una relación entre dos conjuntos de sus nodos. La conexión fuerte es una relación de equivalencia que divide el conjunto de nodos de un hipergrafo dirigido en particiones y cada partición define una clase de equivalencia conocida como componente fuertemente conexo. El estudio de los componentes fuertemente conexos de un hipergrafo dirigido puede ayudar a conseguir una mejor comprensión de la estructura de este tipo de hipergrafos cuando su tamaño es considerable. En el caso de grafo dirigidos, existen algoritmos muy eficientes para el cálculo de los componentes fuertemente conexos en grafos de gran tamaño. Gracias a estos algoritmos, se ha podido averiguar que la estructura de la WWW tiene forma de “pajarita”, donde más del 70% del los nodos están distribuidos en tres grandes conjuntos y uno de ellos es un componente fuertemente conexo. Este tipo de estructura ha sido también observada en redes complejas en otras áreas como la biología. Estudios de naturaleza similar no han podido ser realizados en hipergrafos dirigidos porque no existe algoritmos capaces de calcular los componentes fuertemente conexos de este tipo de hipergrafos. En esta tesis doctoral, hemos investigado como calcular los componentes fuertemente conexos de un hipergrafo dirigido. En concreto, hemos desarrollado dos algoritmos para este problema y hemos determinado que son correctos y cuál es su complejidad computacional. Ambos algoritmos han sido evaluados empíricamente para comparar sus tiempos de ejecución. Para la evaluación, hemos producido una selección de hipergrafos dirigidos generados de forma aleatoria inspirados en modelos muy conocidos de grafos aleatorios como Erdos-Renyi, Newman-Watts-Strogatz and Barabasi-Albert. Varias optimizaciones para ambos algoritmos han sido implementadas y analizadas en la tesis. En concreto, colapsar los componentes fuertemente conexos del grafo dirigido que se puede construir eliminando ciertas hiperaristas complejas del hipergrafo dirigido original, mejora notablemente los tiempos de ejecucion de los algoritmos para varios de los hipergrafos utilizados en la evaluación. Aparte de los ejemplos de aplicación mencionados anteriormente, los hipergrafos dirigidos han sido también empleados en el área de representación de conocimiento. En concreto, este tipo de hipergrafos se han usado para el cálculo de módulos de ontologías. Una ontología puede ser definida como un conjunto de axiomas que especifican formalmente un conjunto de símbolos y sus relaciones, mientras que un modulo puede ser entendido como un subconjunto de axiomas de la ontología que recoge todo el conocimiento que almacena la ontología sobre un conjunto especifico de símbolos y sus relaciones. En la tesis nos hemos centrado solamente en módulos que han sido calculados usando la técnica de localidad sintáctica. Debido a que las ontologías pueden ser muy grandes, el cálculo de módulos puede facilitar las tareas de re-utilización y mantenimiento de dichas ontologías. Sin embargo, analizar todos los posibles módulos de una ontología es, en general, muy costoso porque el numero de módulos crece de forma exponencial con respecto al número de símbolos y de axiomas de la ontología. Afortunadamente, los axiomas de una ontología pueden ser divididos en particiones conocidas como átomos. Cada átomo representa un conjunto máximo de axiomas que siempre aparecen juntos en un modulo. La decomposición atómica de una ontología es definida como un grafo dirigido de tal forma que cada nodo del grafo corresponde con un átomo y cada arista define una dependencia entre una pareja de átomos. En esta tesis introducimos el concepto de“axiom dependency hypergraph” que generaliza el concepto de descomposición atómica de una ontología. Un modulo en una ontología correspondería con un componente conexo en este tipo de hipergrafos y un átomo de una ontología con un componente fuertemente conexo. Hemos adaptado la implementación de nuestros algoritmos para que funcionen también con axiom dependency hypergraphs y poder de esa forma calcular los átomos de una ontología. Para demostrar la viabilidad de esta idea, hemos incorporado nuestros algoritmos en una aplicación que hemos desarrollado para la extracción de módulos y la descomposición atómica de ontologías. A la aplicación la hemos llamado HyS y hemos estudiado sus tiempos de ejecución usando una selección de ontologías muy conocidas del área biomédica, la mayoría disponibles en el portal de Internet NCBO. Los resultados de la evaluación muestran que los tiempos de ejecución de HyS son mucho mejores que las aplicaciones más rápidas conocidas. ABSTRACT Directed hypergraphs are an intuitive modelling formalism that have been used in problems related to propositional logic, relational databases, computational linguistic and machine learning. Directed hypergraphs are also presented as an alternative to directed (bipartite) graphs to facilitate the study of the interactions between components of complex systems that cannot naturally be modelled as binary relations. In this context, they are known as hyper-networks. A directed hypergraph is a generalization of a directed graph suitable for representing many-to-many relationships. While an edge in a directed graph defines a relation between two nodes of the graph, a hyperedge in a directed hypergraph defines a relation between two sets of nodes. Strong-connectivity is an equivalence relation that induces a partition of the set of nodes of a directed hypergraph into strongly-connected components. These components can be collapsed into single nodes. As result, the size of the original hypergraph can significantly be reduced if the strongly-connected components have many nodes. This approach might contribute to better understand how the nodes of a hypergraph are connected, in particular when the hypergraphs are large. In the case of directed graphs, there are efficient algorithms that can be used to compute the strongly-connected components of large graphs. For instance, it has been shown that the macroscopic structure of the World Wide Web can be represented as a “bow-tie” diagram where more than 70% of the nodes are distributed into three large sets and one of these sets is a large strongly-connected component. This particular structure has been also observed in complex networks in other fields such as, e.g., biology. Similar studies cannot be conducted in a directed hypergraph because there does not exist any algorithm for computing the strongly-connected components of the hypergraph. In this thesis, we investigate ways to compute the strongly-connected components of directed hypergraphs. We present two new algorithms and we show their correctness and computational complexity. One of these algorithms is inspired by Tarjan’s algorithm for directed graphs. The second algorithm follows a simple approach to compute the stronglyconnected components. This approach is based on the fact that two nodes of a graph that are strongly-connected can also reach the same nodes. In other words, the connected component of each node is the same. Both algorithms are empirically evaluated to compare their performances. To this end, we have produced a selection of random directed hypergraphs inspired by existent and well-known random graphs models like Erd˝os-Renyi and Newman-Watts-Strogatz. Besides the application examples that we mentioned earlier, directed hypergraphs have also been employed in the field of knowledge representation. In particular, they have been used to compute the modules of an ontology. An ontology is defined as a collection of axioms that provides a formal specification of a set of terms and their relationships; and a module is a subset of an ontology that completely captures the meaning of certain terms as defined in the ontology. In particular, we focus on the modules computed using the notion of syntactic locality. As ontologies can be very large, the computation of modules facilitates the reuse and maintenance of these ontologies. Analysing all modules of an ontology, however, is in general not feasible as the number of modules grows exponentially in the number of terms and axioms of the ontology. Nevertheless, the modules can succinctly be represented using the Atomic Decomposition of an ontology. Using this representation, an ontology can be partitioned into atoms, which are maximal sets of axioms that co-occur in every module. The Atomic Decomposition is then defined as a directed graph such that each node correspond to an atom and each edge represents a dependency relation between two atoms. In this thesis, we introduce the notion of an axiom dependency hypergraph which is a generalization of the atomic decomposition of an ontology. A module in the ontology corresponds to a connected component in the hypergraph, and the atoms of the ontology to the strongly-connected components. We apply our algorithms for directed hypergraphs to axiom dependency hypergraphs and in this manner, we compute the atoms of an ontology. To demonstrate the viability of this approach, we have implemented the algorithms in the application HyS which computes the modules of ontologies and calculate their atomic decomposition. In the thesis, we provide an experimental evaluation of HyS with a selection of large and prominent biomedical ontologies, most of which are available in the NCBO Bioportal. HyS outperforms state-of-the-art implementations in the tasks of extracting modules and computing the atomic decomposition of these ontologies.

Mejoras y extensiones en el Front-End de un modelo de predicción de acciones de un estudiante en un laboratorio virtual 3D

Este documento presenta las mejoras y las extensiones introducidas en la herramienta de visualización del modelo predictivo del comportamiento del estudiante o Student Behavior Predictor Viewer (SBPV), implementada en un trabajo anterior. El modelo predictivo del comportamiento del estudiante es parte de un sistema inteligente de tutoría, y se construye a partir de los registros de actividad de los estudiantes en un laboratorio virtual 3D, como el Laboratorio Virtual de Biotecnología Agroforestal, implementado en un trabajo anterior, y cuyos registros de actividad de los estudiantes se han utilizado para validar este trabajo fin de grado. El SBPV es una herramienta para visualizar una representación gráfica 2D del grafo extendido asociado con cualquiera de los clusters del modelo predictivo del estudiante. Además de la visualización del grafo extendido, el SBPV controla la navegación a través del grafo por medio del navegador web. Más concretamente, el SBPV permite al usuario moverse a través del grafo, ampliar o reducir el zoom del gráfico o buscar un determinado estado. Además, el SBPV también permite al usuario modificar el diseño predeterminado del grafo en la pantalla al cambiar la posición de los estados con el ratón. Como parte de este trabajo fin de grado, se han corregido errores existentes en la versión anterior y se han introducido una serie de mejoras en el rendimiento y la usabilidad. En este sentido, se han implementado nuevas funcionalidades, tales como la visualización del modelo de comportamiento de cada estudiante individualmente o la posibilidad de elegir el método de clustering para crear el modelo predictivo del estudiante; así como ha sido necesario rediseñar la interfaz de usuario cambiando el tipo de estructuras gráficas con que se muestran los elementos del modelo y mejorando la visualización del grafo al interaccionar el usuario con él. Todas estas mejoras se explican detenidamente en el presente documento.---ABSTRACT---This document presents the improvements and extensions made to the visualization tool Student Behavior Predictor Viewer (SBPV), implemented in a previous job. The student behavior predictive model is part of an intelligent tutoring system, and is built from the records of students activity in a 3D virtual laboratory, like the “Virtual Laboratory of Agroforestry Biotechnology” implemented in a previous work, and whose records of students activity have been used to validate this final degree work. The SBPV is a tool for visualizing a 2D graphical representation of the extended graph associated with any of the clusters of the student predictive model. Apart from visualizing the extended graph, the SBPV supports the navigation across the graph by means of desktop devices. More precisely, the SBPV allows user to move through the graph, to zoom in/out the graphic or to locate a given state. In addition, the SBPV also allows user to modify the default layout of the graph on the screen by changing the position of the states by means of the mouse. As part of this work, some bugs of the previous version have been fixed and some enhancements have been implemented to improve the performance and the usability. In this sense, we have implemented new features, such as the display of the model behavior of only one student or the possibility of selecting the clustering method to create the student predictive model; as well as it was necessary to redesign the user interface changing the type of graphic structures that show model elements and improving the rendering of the graph when the user interacts with it. All these improvements are explained in detail in the next sections.

Quality of experience of adaptive video streaming: investigation in service parameters and subjective quality assessment methodology

The usage of HTTP adaptive streaming (HAS) has become widely spread in multimedia services. Because it allows the service providers to improve the network resource utilization and user׳s Quality of Experience (QoE). Using this technology, the video playback interruption is reduced since the network and server status in addition to capability of user device, all are taken into account by HAS client to adapt the quality to the current condition. Adaptation can be done using different strategies. In order to provide optimal QoE, the perceptual impact of adaptation strategies from point of view of the user should be studied. However, the time-varying video quality due to the adaptation which usually takes place in a long interval introduces a new type of impairment making the subjective evaluation of adaptive streaming system challenging. The contribution of this paper is two-fold: first, it investigates the testing methodology to evaluate HAS QoE by comparing the subjective experimental outcomes obtained from ACR standardized method and a semi-continuous method developed to evaluate the long sequences. In addition, influence of using audiovisual stimuli to evaluate the video-related impairment is inquired. Second, impact of some of the adaptation technical factors including the quality switching amplitude and chunk size in combination with high range of commercial content type is investigated. The results of this study provide a good insight toward achieving appropriate testing method to evaluate HAS QoE, in addition to designing switching strategies with optimal visual quality.

Janus: an FPGA-based system for high-performance scientific computing

This paper describes JANUS, a modular massively parallel and reconfigurable FPGA-based computing system. Each JANUS module has a computational core and a host. The computational core is a 4x4 array of FPGA-based processing elements with nearest-neighbor data links. Processors are also directly connected to an I/O node attached to the JANUS host, a conventional PC. JANUS is tailored for, but not limited to, the requirements of a class of hard scientific applications characterized by regular code structure, unconventional data manipulation instructions and not too large data-base size. We discuss the architecture of this configurable machine, and focus on its use on Monte Carlo simulations of statistical mechanics. On this class of application JANUS achieves impressive performances: in some cases one JANUS processing element outperfoms high-end PCs by a factor ≈1000. We also discuss the role of JANUS on other classes of scientific applications.

Avaliação da influência de emoções na tomada de decisão de sistemas computacionais.

Este trabalho avalia a influência das emoções humanas expressas pela mímica da face na tomada de decisão de sistemas computacionais, com o objetivo de melhorar a experiência do usuário. Para isso, foram desenvolvidos três módulos: o primeiro trata-se de um sistema de computação assistiva - uma prancha de comunicação alternativa e ampliada em versão digital. O segundo módulo, aqui denominado Módulo Afetivo, trata-se de um sistema de computação afetiva que, por meio de Visão Computacional, capta a mímica da face do usuário e classifica seu estado emocional. Este segundo módulo foi implementado em duas etapas, as duas inspiradas no Sistema de Codificação de Ações Faciais (FACS), que identifica expressões faciais com base no sistema cognitivo humano. Na primeira etapa, o Módulo Afetivo realiza a inferência dos estados emocionais básicos: felicidade, surpresa, raiva, medo, tristeza, aversão e, ainda, o estado neutro. Segundo a maioria dos pesquisadores da área, as emoções básicas são inatas e universais, o que torna o módulo afetivo generalizável a qualquer população. Os testes realizados com o modelo proposto apresentaram resultados 10,9% acima dos resultados que usam metodologias semelhantes. Também foram realizadas análises de emoções espontâneas, e os resultados computacionais aproximam-se da taxa de acerto dos seres humanos. Na segunda etapa do desenvolvimento do Módulo Afetivo, o objetivo foi identificar expressões faciais que refletem a insatisfação ou a dificuldade de uma pessoa durante o uso de sistemas computacionais. Assim, o primeiro modelo do Módulo Afetivo foi ajustado para este fim. Por fim, foi desenvolvido um Módulo de Tomada de Decisão que recebe informações do Módulo Afetivo e faz intervenções no Sistema Computacional. Parâmetros como tamanho do ícone, arraste convertido em clique e velocidade de varredura são alterados em tempo real pelo Módulo de Tomada de Decisão no sistema computacional assistivo, de acordo com as informações geradas pelo Módulo Afetivo. Como o Módulo Afetivo não possui uma etapa de treinamento para inferência do estado emocional, foi proposto um algoritmo de face neutra para resolver o problema da inicialização com faces contendo emoções. Também foi proposto, neste trabalho, a divisão dos sinais faciais rápidos entre sinais de linha base (tique e outros ruídos na movimentação da face que não se tratam de sinais emocionais) e sinais emocionais. Os resultados dos Estudos de Caso realizados com os alunos da APAE de Presidente Prudente demonstraram que é possível melhorar a experiência do usuário, configurando um sistema computacional com informações emocionais expressas pela mímica da face.

Open business intelligence: on the importance of data quality awareness in user-friendly data mining

Citizens demand more and more data for making decisions in their daily life. Therefore, mechanisms that allow citizens to understand and analyze linked open data (LOD) in a user-friendly manner are highly required. To this aim, the concept of Open Business Intelligence (OpenBI) is introduced in this position paper. OpenBI facilitates non-expert users to (i) analyze and visualize LOD, thus generating actionable information by means of reporting, OLAP analysis, dashboards or data mining; and to (ii) share the new acquired information as LOD to be reused by anyone. One of the most challenging issues of OpenBI is related to data mining, since non-experts (as citizens) need guidance during preprocessing and application of mining algorithms due to the complexity of the mining process and the low quality of the data sources. This is even worst when dealing with LOD, not only because of the different kind of links among data, but also because of its high dimensionality. As a consequence, in this position paper we advocate that data mining for OpenBI requires data quality-aware mechanisms for guiding non-expert users in obtaining and sharing the most reliable knowledge from the available LOD.

Granular computing as a basis of human–data interaction: a cognitive cities use case

The article proposes granular computing as a theoretical, formal and methodological basis for the newly emerging research field of human–data interaction (HDI). We argue that the ability to represent and reason with information granules is a prerequisite for data legibility. As such, it allows for extending the research agenda of HDI to encompass the topic of collective intelligence amplification, which is seen as an opportunity of today’s increasingly pervasive computing environments. As an example of collective intelligence amplification in HDI, we introduce a collaborative urban planning use case in a cognitive city environment and show how an iterative process of user input and human-oriented automated data processing can support collective decision making. As a basis for automated human-oriented data processing, we use the spatial granular calculus of granular geometry.

Edge caching with mobility prediction in virtualized LTE mobile networks

Abstract Mobile Edge Computing enables the deployment of services, applications, content storage and processing in close proximity to mobile end users. This highly distributed computing environment can be used to provide ultra-low latency, precise positional awareness and agile applications, which could significantly improve user experience. In order to achieve this, it is necessary to consider next-generation paradigms such as Information-Centric Networking and Cloud Computing, integrated with the upcoming 5th Generation networking access. A cohesive end-to-end architecture is proposed, fully exploiting Information-Centric Networking together with the Mobile Follow-Me Cloud approach, for enhancing the migration of content-caches located at the edge of cloudified mobile networks. The chosen content-relocation algorithm attains content-availability improvements of up to 500 when a mobile user performs a request and compared against other existing solutions. The performed evaluation considers a realistic core-network, with functional and non-functional measurements, including the deployment of the entire system, computation and allocation/migration of resources. The achieved results reveal that the proposed architecture is beneficial not only from the users’ perspective but also from the providers point-of-view, which may be able to optimize their resources and reach significant bandwidth savings.

Measurement of interactive computing : methodology and application /

Thesis--George Washington University.

Field and depot maintenance manual : magneto, ignition, assembly, 2920-529-8247, 2920-740-3411, 2920-737-2995, and 2920-753-9854 (Bendix-Scintilla types S4LN-32 and S6LN-32), end item application, engine, gasoline, 4-cylinder, continental model AOI-268-3A and -3B (TM 9-7605-1) ....

"June 1960."

Field maintenance manual : engine assembly (2804-678-1820) and clutch, end item application, truck utility, 1/4-ton, 4x4, M151 (TM9-2320-218-10).

"January 1963."

Field and depot maintenance : magnetos, ignition, assemblies, 2920-593-6456 and 2920-640-7743 (American Bosch types MRE6A43 and MRE6A41), end item application, engine, gasoline, 6-cylinder, continental models AOI-402-5 ... 12-cylinder, continental models AV-1790-5B ....

"April 1959."

Field and depot maintenance manual : engine, gasoline, "V" type, air cooled, 12-cylinder, fuel injected, supercharged, -2805-695-6237, (Continental model AVSI-1790-6) and fuel injected, (unsupercharged), -2805-293-9662, (Continental model AVI-1790-8) : end item application, tank, combat, full tracked, 90-mm, M48A2, (TM 9-2350-208) ....

Includes index.

Field and depot maintenance manual : engine, gasoline, fuel injected, supercharged, horizontal-opposed, air cooled, six cylinder, assembly-2805-528-6015, (Continental model AOSI-895-5 and AOSI-895-5M) : end item application : gun, self-propelled, full tracked, twin 40-mm, M42A1 (TM 9-2350-202), howitzer, self-propelled, full tracked, 105-mm, M52A1 (TM 9-2350-209) ....

Includes index.