Designing and maintaining Web applications is one of the major challenges that software industry has to face. Several modeling techniques have been proposed to support this process. In this work we present a methodolo...
详细信息
ISBN:
(纸本)0889864802
Designing and maintaining Web applications is one of the major challenges that software industry has to face. Several modeling techniques have been proposed to support this process. In this work we present a methodology for identifying design patterns within an application modelled using WebML, a modelling language for designing data-intensive Web applications. We extend the set of design patterns supported by WebML and exemplify the application of the methodology using an e-learning scenario.
In this paper, we study some issues on Chinese domain knowledge dictionary and its application to text classification task. First a domain knowledge hierarchy description framework and our Chinese domain knowledge dic...
详细信息
We explore here the application of Gleaner, an Inductive Logic Programming approach to learning in highly-skewed domains, to the learning Language in Logic 2005 biomedical information-extraction challenge task. We cre...
详细信息
We explore here the application of Gleaner, an Inductive Logic Programming approach to learning in highly-skewed domains, to the learning Language in Logic 2005 biomedical information-extraction challenge task. We create and describe a large number of background knowledge predicates suited for this task. We find that Gleaner outperforms standard Aleph theories with respect to recall and that additional linguistic background knowledge improves recall.
Research in protein structure and function is one of the most important subjects in modem bioinformatics and computational biology. It often uses advanced data mining and machinelearning methodologies to perform pred...
详细信息
ISBN:
(纸本)3540269231
Research in protein structure and function is one of the most important subjects in modem bioinformatics and computational biology. It often uses advanced data mining and machinelearning methodologies to perform prediction or pattern recognition tasks. this paper describes a new method for prediction of protein secondary structure content based on feature selection and multiple linear regression. the method develops a novel representation of primary protein sequences based on a large set of 495 features. the feature selection task performed using very large set of nearly 6,000 proteins, and tests performed on standard non-homologues protein sets confirm high quality of the developed solution. the application of feature selection and the novel representation resulted in 14-15% error rate reduction when compared to results achieved when standard representation is used. the prediction tests also show that a small set of 5-25 features is sufficient to achieve accurate prediction for both helix and strand content for non-homologous proteins.
An atmospheric chemical mechanism is a detailed description of a sequence of reactions which summarizes the relevant chemical pathways and gives certain, essentially qualitative, information about the fate of atmosphe...
详细信息
machinelearning can be applied to solve the knowledge acquisition bottleneck in many areas where an expert makes predictions to single cases, such as diagnosis, estimation, etc. the idea is to query the expert with a...
详细信息
this paper is concerned with how multi-agent reinforcement learning algorithms can practically be applied to real-life problems. Recently, a new coordinated multi-agent exploration mechanism, called Exploring Selfish ...
详细信息
this paper is concerned with how multi-agent reinforcement learning algorithms can practically be applied to real-life problems. Recently, a new coordinated multi-agent exploration mechanism, called Exploring Selfish Reinforcement learning (ESRL) was proposed. Withthis mechanism, a group of independent agents can find optimal fair solutions in multi-agent problems, without the need for modeling other agents, without the need of knowing the type of the multiagent problem confronted with and by using only a limited form of communication. In particular, the mechanism allows for using natural reinforcement signals coming from the application itself. We report on how ESRL agents can solve the problem of load-balancing in a natural way, both as a common interest and as a conflicting interest problem. Copyright 2005 ACM.
In this paper, we propose a new routing protocol for mobile ad-hoc networks (MANET), which have attracted considerable attentions in recent years as a tool to realize flexible and robust communication environments in ...
详细信息
ISBN:
(纸本)0769522963
In this paper, we propose a new routing protocol for mobile ad-hoc networks (MANET), which have attracted considerable attentions in recent years as a tool to realize flexible and robust communication environments in many critical application fields. the proposed protocol, called LQ-routing, is a proactive routing protocol based on the Q-routing protocol which was originally proposed for conventional wired networks. In order to reflect the mobility of hosts to the routing decision, which would cause frequent connection and disconnection of communication links between nearby hosts, we introduce the notion of lifetime to represent the stability of routes connecting to the destination. the performance of the proposed routing scheme is experimentally evaluated by using NS-2. the result of simulation indicates that by introducing the notion of lifetime to a simple combination of previous proactive routing scheme DSDV and the Q-routing, we could improve the performance of DSDV in terms of the packet loss rate and the average packet delay.
this paper proposes a conceptual framework for Ubiquitous learning Environment (ULE) construction. ULE is integrated from multi-dimensions, such as physical, social, informational and technical settings, where schools...
详细信息
ISBN:
(纸本)0889864802
this paper proposes a conceptual framework for Ubiquitous learning Environment (ULE) construction. ULE is integrated from multi-dimensions, such as physical, social, informational and technical settings, where schools, communities, and families will be integrated in a smooth context. ULE is established on the combination between Real World and Virtual Space, Personal Space and Shared Space. learning in ULE is conducted in the interactions among three essential communicative elements: Social Human, Object in real world, and Artifact in virtual space. learning process is a social transfer process between tacit and explicit knowledge. Context-Awareness is indispensable to all kinds of interactions in ULE. Especially, this paper gives a discussion to context-awareness supported Interoperability and Adaptability in ULE. Additionally, this paper also gives a simple reminder to related learning terms, Blended learning, Social and Emotional learning, Service-learning, and Situated learning, which are contributive to our deeper understanding to learning in ULE. On practical dimension, this paper presents a design framework for ULE implementation by integrating the application of three kinds of affordable learning devices: networked PC, PDA, and mobile Phone.
In this paper, we describe our approach to the Genic Interaction Extraction Challenge. Our solution combines several elements: 1) a domain theory about the interaction between language, semantics and syntax, 2) a biol...
详细信息
In this paper, we describe our approach to the Genic Interaction Extraction Challenge. Our solution combines several elements: 1) a domain theory about the interaction between language, semantics and syntax, 2) a biological ontology identifying amongst other things biomolecular entities and directed interaction verbs in the lexicon, 3) the notion of lexical-semantic-syntactic unification, 4) the notion of partial unification of lexicalsemantic syntactic trees and 5) the application of the standard RIPPER algorithm to the results. Using this approach on the very limited training and test data from the Challenge we show results that are promising. Our method observes a clear separation between domain-independent and domainspecific components. It can therefore easily be extended to other domains. We briey describe the implementation of the techniques, discuss the results and give suggestions for improvements and further results in the conclusion.
暂无评论