Tuesday, September 23, 2014

 

 



Soy un nuevo usuario

Olvidé mi contraseña

Entrada usuarios

Lógica Matemáticas Astronomía y Astrofísica Física Química Ciencias de la Vida
Ciencias de la Tierra y Espacio Ciencias Agrarias Ciencias Médicas Ciencias Tecnológicas Antropología Demografía
Ciencias Económicas Geografía Historia Ciencias Jurídicas y Derecho Lingüística Pedagogía
Ciencia Política Psicología Artes y Letras Sociología Ética Filosofía
 

rss_1.0 Recursos de colección

UPCommons - E-prints UPC Universitat Politècnica de Catalunya (68,235 recursos)
E-prints UPC cobreix dues finalitats: per una banda, és el dipòsit institucional de la UPC que recull els articles de revista, les comunicacions de congrés i els reports de recerca generats en les activitats de recerca del personal docent i investigador de la universitat; per l'altra, és una eina que permet accelerar la producció científica, allotjant versions de documents prèvies a la publicació en una revista o a les actes d’un congrés.

Reports de recerca

Mostrando recursos 1 - 20 de 39

1. Strategies and algorithms for clustering large datasets: a review - Béjar Alonso, Javier
The exploratory nature of data analysis and data mining makes clustering one of the most usual tasks in these kind of projects. More frequently these projects come from many different application areas like biology, text analysis, signal analysis, etc that involve larger and larger datasets in the number of examples and the number of attributes. Classical methods for clustering data like K-means or hierarchical clustering are beginning to reach its maximum capability to cope with this increase of dataset size. The limitation for these algorithms come either from the need of storing all the data in memory or because of...

2. K-means vs Mini Batch K-means: a comparison - Béjar Alonso, Javier
Mini Batch K-means (cite{Sculley2010}) has been proposed as an alternative to the K-means algorithm for clustering massive datasets. The advantage of this algorithm is to reduce the computational cost by not using all the dataset each iteration but a subsample of a fixed size. This strategy reduces the number of distance computations per iteration at the cost of lower cluster quality. The purpose of this paper is to perform empirical experiments using artificial datasets with controlled characteristics to assess how much cluster quality is lost when applying this algorithm. The goal is to obtain some guidelines about what are the...

3. Unsupervised feature selection by means of external validity indices - Béjar Alonso, Javier
Feature selection for unsupervised data is a difficult task because a reference partition is not available to evaluate the relevance of the features. Recently, different proposals of methods for consensus clustering have used external validity indices to assess the agreement among partitions obtained by clustering algorithms with different parameter values. Theses indices are independent of the characteristics of the attributes describing the data, the way the partitions are represented or the shape of the clusters. This independence allows to use these measures to assess the similarity of partitions with different subsets of attributes. As for supervised feature selection, the goal...

4. Event-based real-time decomposed conformance analysis - vanden Broucke, Seppe; Muñoz Gama, Jorge; Carmona Vargas, Josep; Baesens, Bart; Vanthienen, Jan
Process mining deals with the extraction of knowledge from event logs. One important task within this research field is denoted as conformance checking, which aims to diagnose deviations and discrepancies between modeled behavior and real-life, observed behavior. Conformance checking techniques still face some challenges, among which scalability, timeliness and traceability issues. In this paper, we propose a novel conformance analysis methodology to support the real-time monitoring of event-based data streams, which is shown to be more efficient than related approaches and able to localize deviations in a more fine-grained manner. Our developed approach can be directly applied in business process...

5. Deliverable 6.1 Infrastructure for Extractive Summarization - Saggion, Horacio; Padró, Lluís; Fuentes Fort, Maria
SKATER Internal Report: software of infrastructure for extractive Summarization (work carried out until December 2013)

6. Spectral learning of transducers over continuous sequences - Recasens, Adria; Quattoni, Ariadna Julieta
In this paper we present a spectral algorithm for learning weighted nite state transducers (WFSTs) over paired input-output sequences, where the input is continuous and the output discrete. WFSTs are an important tool for modeling paired input-output sequences and have numerous applications in real-world problems. Recently, Balle et al (2011) proposed a spectral method for learning WFSTs that overcomes some of the well known limitations of gradient-based or EM optimizations which can be computationally expensive and su er from local optima issues. Their algorithm can model distributions where both inputs and outputs are sequences from a discrete alphabet. However, many real world...

7. Specialization in i* strategic rationale diagrams - López Cuesta, Lidia; Franch Gutiérrez, Javier; Marco Gómez, Jordi
The specialization relationship is offered by the i* modeling language through the is-a construct defined over actors (a subactor is-a superactor). Although the overall meaning of this construct is highly intuitive, its semantics of strategic rationale (SR) diagrams is not defined. In this report we provide a formal definition of the specialization relationship at the level of i* SR diagrams. We root our proposal over existing work in conceptual modeling in general, and object-orientation in particular. Also, we use the results of a survey conducted in the i* community that provides some hints about what i* modelers expect from specialization....

8. Weighted games without a unique minimal representation in integers - Freixas Bosch, Josep; Molinero Albareda, Xavier
Recerca de jocs amb mínim número de jugadors sense representacions enteres mínimes o mínimes normalitzades

9. Non-functional requirements in software architecture practice - Ameller, David; Ayala Martínez, Claudia Patricia; Cabot Sagrera, Jordi; Franch Gutiérrez, Javier
Dealing with non-functional requirements (NFRs) has posed a challenge onto software engineers for many years. Over the years, many methods and techniques have been proposed to improve their elicitation, documentation, and validation. Knowing more about the state of the practice on these topics may benefit both practitioners’ and researchers’ daily work. A few empirical studies have been conducted in the past, but none under the perspective of software architects, in spite of the great influence that NFRs have on daily architects’ practices. This paper presents some of the findings of an empirical study based on 13 interviews with software architects....

10. Unsupervised ensemble minority clustering - González Pellicer, Edgar; Turmo Borras, Jorge
Cluster a alysis lies at the core of most unsupervised learning tasks. However, the majority of clustering algorithms depend on the all-in assumption, in which all objects belong to some cluster, and perform poorly on minority clustering tasks, in which a small fraction of signal data stands against a majority of noise. The approaches proposed so far for minority clustering are supervised: they require the number and distribution of the foreground and background clusters. In supervised learning and all-in clustering, combination methods have been successfully applied to obtain distribution-free learners, even from the output of weak individual algorithms. In this report, we present...

11. WeSSQoS: a configurable SOA system for quality-aware web service selection - Cabrera Bejar, Oscar; Oriol Hilari, Marc; Franch Gutiérrez, Javier; López Cuesta, Lidia; Marco Gómez, Jordi; Fragoso, Olivia; Santaolaya, René
Web Services (WS) have become one the most used technologies nowadays in software systems. Among the challenges when integrating WS in a given system, requirements-driven selection occupies a prominent place. A comprehensive selection process needs to check compliance of Non-Functional Requirements (NFR), which can be assessed by analysing WS Quality of Service (QoS). In this paper, we describe the WeSSQoS system that aims at ranking available WS based on the comparison of their QoS and the stated NFRs. WeSSQoS is designed as an open service-oriented architecture that hosts a configurable portfolio of normalization and ranking algorithms that can be selected by the engineer...

12. Frequent sets, sequences and taxonomies: new efficient algorithmic proposals - Baixeries i Juvillà, Jaume; Casas Garriga, Gemma; Balcázar Navarro, José Luis
We describe efficient algorithmic proposals to approach three fundamental problems in data mining: association rules, episodes in sequences, and generalized association rules over hierarchical taxonomies. The association rule discovery problem aims at identifying frequent itemsets in a database and then forming conditional implication rules among them. For this association task, we will introduce a new algorithmic proposal to reduce substantially the number of processed transactions. The resulting algorithm, called Ready-and-Go, is used to discover frequent sets efficiently. Then, for the discovery of patterns in sequences of events in ordered collections of data, we propose to apply the appropiate variant of...

13. Word sense ranking based on semantic similarity and graph entropy - Sousa Lopes, João; Álvarez Napagao, Sergio; Vázquez Salceda, Javier
In this paper we propose a system for the recommendation of tagged pictures obtained from the Web. The system, driven by user feedback, executes an abductive reasoning (based on WordNet synset semantic relations) that is able to iteratively lead to new concepts which progressively represent the cognitive creative user state. Furthermore we design a selection mechanism to pick the most relevant abductive inferences by mixing a topological graph analysis together with a semantic similitude measure.

14. USE: a multi-agent user-driven recommendation system for semantic knowledge extraction - Lopes, João Sousa; Álvarez Napagao, Sergio; Confalonieri, Roberto; Vázquez Salceda, Javier
Semiotics is a field where research on Computer Science methodologies has focused, mainly concerning Syntax and Semantics. These methodologies, however, are lacking of some flexibility for the continuously evolving web community, in which the knowledge is classified with tags rather than with ontologies. In this paper we propose a multi-agent system for the recommendation of tagged pictures obtained from mainstream Web applications. The agents in this system execute a hybrid reasoning based on WordNet and Markov chains that is able, driven by user feedback, to iteratively disambiguate the semantics of the picture tags and thus to generate knowledge from the,...

15. Reasoning about abductive inferences in BDI agents - Lopes, João Sousa; Álvarez Napagao, Sergio; Reis, Susana; Vázquez Salceda, Javier
The capability of a computational system to deal with unexpected, changing situations and limited perception of the environment is becoming more a more relevant, in oder to make systems flexible and more reliable. Multi-agent Systems offer a computing paradigm where properties such as autonomy, adaptability or flexibility are basic in the construction of agent-based solutions. However most of current implementations are not flexible enough to cope with important changes in the environment or information loss. In this paper we propose to introduce abductive reasoning mechanisms in BDI agents and show how such agents are able to operate with partial models...

16. Metamodelo de la especificación OSID versión 2 de OKI - Rius Gavídia, M. Ángeles; Conesa Caralt, Jordi; García Barriocanal, M. Elena
En las últimas décadas dentro del ámbito del e-Learning, la investigación acerca de especificaciones y estándares relacionados con contenidos digitales ha evolucionado notablemente. Aunque se han multiplicado el número de plataformas de sistemas de aprendizaje, las especificaciones y estándares relacionados con procesos para entornos educativos no han tenido la misma suerte. La especificación Open Service Interface Definition (OSI) de Open Knowledge Initiative (OKI) propone un conjunto de interfaces de servicios web dirigidos a entornos de enseñanza superior con el objetivo de conseguir interoperabilidad entre aplicaciones. Sin embargo esta especificación no ha sido demasiado utilizada, posiblemente por falta de un mapa conceptual...

17. Aprendizaje y asistencia virtual en red - Fuentes Fort, Maria; González Bermúdez, Meritxell; Guardiola Garcia, Marta; Jofre Roca, Lluís; Romeu Robert, Jordi; Vallverdú Bayés, Francesc
Favorecer el uso de las Tecnologías de Información y la Comunicación (TIC) en entornos educativos puede abarcar varios aspectos del proceso de aprendizaje. La incorporación de TICs en las aulas contribuye, por un lado a reducir la brecha digital tanto de profesores como alumnos y por el otro, debiera ayudar a mejorar la metodología educativa. Sin duda las TICs pueden ser de gran ayuda para llegar a alcanzar los objetivos pedagógicos. En concreto, este estudio tenía por objetivo analizar la manera de incorporar tecnologías de la voz y el procesamiento del lenguaje natural para mejorar el proceso de aprendizaje de la...

18. On the proper intervalization of colored caterpillar trees - Álvarez Faura, M. del Carme; Serna Iglesias, María José
This paper studies the computational complexity of the Proper interval colored graph problem (picg), when the input graph is a colored caterpillar, parameterized by hair length. In order prove our result we establish a close relationship between the picg and a graph layout problem the Proper colored layout problem (pclp). We show a dichotomy: the picg and the pclp are NP-complete for colored caterpillars of hair length ≥ 2, while both problems are in P for colored caterpillars of hair length < 2. For the hardness results we provide a reduction from the Multiprocessor Scheduling problem, while the polynomial time...

19. Sensor field: a computational model - Álvarez Faura, M. del Carme; Duch Brown, Amalia; Gabarró Vallès, Joaquim; Serna Iglesias, María José
We introduce a formal model of computation for networks of tiny artifacts, the static synchronous sensor field model (SSSF) which considers that the devices communicate through a fixed communication graph and interact with the environment through input/output data streams. We analyze the performance of SSSFs solving two sensing problems the Average Monitoring and the Alerting problems. For constant memory SSSFs we show that the set of recognized languages is contained in DSPACE(n+m) where n is the number of nodes of the communication graph and m its number of edges. Finally we explore the capabilities of SSSFs having sensing and additional non-sensing...

20. Detecció de fallades en un sistema de piles de combustible - Escobet Canal, Antoni; Nebot Castells, M. Àngela
In this work a fault diagnosis system for non-linear plants based on fuzzy logic, called VisualBlock-FIR, is presented and applied to an energy generation system based on fuel cells. VisualBlock-FIR runs under the Simulink framework and enables early fault detection and identification. During fault detection, the fault diagnosis system should recognize that the system is not working properly. During fault identification, it should conclude which type of failure has occurred. The diagnosis results for some of the most frequent faults in fuel cell systems are presented.

Página de resultados:
 

Busque un recurso