Representation Of Temporal Data Research Articles

A DYNAMIC TEMPORAL NEURO FUZZY INFERENCE SYSTEM FOR MINING MEDICAL DATABASES

The analysis and representation of temporal data ar e becoming increasingly important in many areas of research and application. The existing Fuzzy Cognit ive Maps (FCMs) are efficient modeling method for knowledge representation and fuzzy reasoning in time series analysis. In the past, it was used to repr esent a complex causal system as a collection of concepts a nd causal relationships among concepts. However, most of the FCMs available now are constructed manually and are constrained with human experts’ interventio n for assessing its reliability. This study proposes a new temporal mining system to discover temporal dependencies between the concepts of a complex causal system by building a Fuzzy Temporal Cognitive Map (FTCM) by extending the FCM. For this purpose, a four-layer fuzzy temporal neural network is proposed and implemented by the automatic creation of the conventional FTCMs from the given data. This FTCM is generated from the medical temporal database records of diabetic patients where the medical diagnosis is performed by converting the fuzzy cogn etive maps into a fuzzy temporal rule based inferen ce system using Allen’s temporal relationships and fuz zy temporal rules.

English

There are two paradigms for modelling the varying length temporal data namely, modelling the sequences of feature vectors as in the hidden Markov model-based approaches for speech recognition and modelling the sets of feature vectors as in the Gaussian mixture model (GMM)-based approaches for speech emotion recognition. In this paper, the methods using discrete hidden Markov models (DHMMs) in the kernel feature space and string kernel-based SVM classifier for classification of discretised representation of sequence of feature vectors obtained by clustering and vector quantisation in the kernel feature space are presented. The authors then present continuous density hidden Markov models (CDHMMs) in the explicit kernel feature space that use the continuous valued representation of features extracted from the temporal data. The methods for temporal pattern classification by mapping a varying length sequential pattern to a fixed-length sequential pattern and then using an SVM-based classifier for classification are also presented. The task of recognition of spoken letters in E-set, it is possible to build models that use a discretised representation and string kernel SVM based classification and obtain a classification performance better than that of models using the continuous valued representation is demonstrated. For modelling sets of vectors-based representation of temporal data, two approaches in a hybrid framework namely, the score vector-based approach and the segment modelling based approach are presented. In both approaches, a generative model-based method is used to obtain a fixed length pattern representation for a varying length temporal data and then a discriminative model is used for classification. These two approaches are studied for speech emotion recognition task. The segment modelling based approach gives a better performance than the score vector-based approach and the GMM-based classifiers for speech emotion recognition.Defence Science Journal, 2010, 60(4), pp.348-363, DOI:http://dx.doi.org/10.14429/dsj.60.492

Using temporal constraints for temporal abstraction

The need to provide high level descriptions of the evolution of data is evident in fields like medicine. For being able to perform task such as diagnostic or monitoring, it is very important to facilitate a high level representation and management of temporal data. With this representation two main benefits are obtained: it becomes easier to compare data with generic knowledge, and the volume of data can be reduced. Several models have been proposed for time representation and management. Temporal constraints have been extensively used as a liable model in problems where temporal imprecision or missing data exist. The imprecision is usually present when data are manually collected, or when the data are based on subjective observations. The aim of this paper is to demonstrate how temporal constraints can be used as a formalism in which temporal abstraction of concepts can be performed. To this end, in the first place, we introduce the fuzzy temporal constraint network as the formalism for representing temporal information. Then, we present an algorithm for obtaining a state representation from a sequence of observations. We show the complexity and applicability of the approach.

The Time Wave. A New Method of Visual Exploration of Geo-data in Time–space

Today's data-rich environment creates its own problems since exploring and analysing vast volumes of spatio–temporal data have become increasingly difficult. It is suggested to approach this problem not only via location–space or attribute–space as is traditionally done in GIScience, but also via time–space. This time-visualisation approach considers the data, the user tasks and the visualisation representations, and aims to improve accessibility, exploration and analysis of huge amounts of geo-data to support geovisual analytics. To reach this objective, the time wave as the temporal visual representation is introduced. The time wave combines the strengths of both the timeline and the time wheel and as such is able to represent linear and cyclic time simultaneously, even at different levels of granularity. The time wave can be used in its role as temporal reference system, as temporal data representation tool, and as temporal interaction tool. It functions in combination with other graphic representations that are typical for location–space and attribute–space.

On handling time-varying data in the relational data model

The article addresses the key issues in modeling and querying temporal data within the relational framework. These issues include representation of temporal data, temporal grouping (object) identifiers and primary keys of temporal relations, temporal integrity constraints, and fundamental operations of a temporal query language. The paper develops taxonomy for temporal relational databases and establishes criteria to evaluate various proposed extensions to the relational data model. We expect that it will benefit the researchers and guide the practitioners in choosing the right approach for managing temporal data in their applications.

A logical reconstruction of temporal databases

Traditional approaches to temporal databases are either not formal or deal only with static features, considering mainly a single state of the database. The temporal nature of data in temporal databases, however, is intrinsically dynamic, for it deals with the evolution of data. In this work, a temporal logic framework is proposed to simultaneously cope with both the static and the dynamic aspects of temporal data. The framework consists of a two-dimensional temporal model. One-dimensional temporal models deal with static aspects such as temporal querying and data representation. The second temporal dimension is introduced as a natural extension that captures the dynamics of temporal updates. The resulting twodimensional temporal model is used to formally characterize the differences between valid time and transaction time, to characterize the notion of ‘now’ in a temporal database, and to give a formal model for bitemporal databases.

Temporal relational data model

This paper incorporates a temporal dimension to nested relations. It combines research in temporal databases and nested relations for managing the temporal data in nontraditional database applications. A temporal data value is represented as a temporal atom; a temporal atom consists of two parts: a temporal set and a value. The temporal atom asserts that the value is valid over the time duration represented by its temporal set. The data model allows relations with arbitrary levels of nesting and can represent the histories of objects and their relationships. Temporal relational algebra and calculus languages are formulated and their equivalence is proved. Temporal relational algebra includes operations to manipulate temporal data and to restructure nested temporal relations. Additionally, we define operations to generate a power set of a relation, a set membership test, and a set inclusion test, which are all derived from the other operations of temporal relational algebra. To obtain a concise representation of temporal data (temporal reduction), collapsed versions of the set-theoretic operations are defined. Procedures to express collapsed operations by the regular operations of temporal relational algebra are included. The paper also develops procedures to completely flatten a nested temporal relation into an equivalent 1 NF relation and back to its original form, thus providing a basis for the semantics of the collapsed operations by the traditional operations on 1 NF relations.

The expressive power of temporal relational query languages

The authors consider the representation of temporal data based on tuple and attribute timestamping. They identify the requirements in modeling temporal data and elaborate on their implications in the expressive power of temporal query languages. They introduce a temporal relational data model where N1NF relations and attribute timestamping are used and one level of nesting is allowed. For this model, a nested relational tuple calculus (NTC) is defined. They follow a comparative approach in evaluating the expressive power of temporal query languages, using NTC as a metric and comparing it with the existing temporal query languages. They prove that NTC subsumes the expressive power of these query languages. They also demonstrate how various temporal relational models can be obtained from the temporal relations by NTC and give equivalent NTC expressions for their languages. Furthermore, they show the equivalence of intervals and temporal elements (sets) as timestamps in their model.

Temporal data representation and reasoning in REAKT

The ability of reasoning about temporal data, representing past, current and expected application states is an important function to be accomplished by Real-Time Knowledge-Based Systems (RTKBS). The application of Knowledge-based systems to real-time problems has to deal with dynamic time-constrained environments and assess two of the most important requirements in real-time systems: the ability to react rapidly to changes in the environment and the guarantee of a bound on the response time. This paper presents a temporal framework for reasoning about the future behaviour of a dynamic time-constrained problem. The proposed mechanism is integrated into a multiagent blackboard architecture and will provide a perspective of the temporal functionalities offered in the REAKT tool

Temporal Reasoning in REAKT: An Environment for Real-Time Knowledge-Based Systems

Temporal representation and reasoning, as the ability of reasoning about temporal data, representing past, current and expected application states, is an important function to be accomplished by Real-Time Knowledge-Based Systems RTKBS, since these systems are usually applied in dynamic time-dependent problem domains. However, this feature is not completely nor usually addressed in current RTKBS tools. In this paper, a RTKBS architecture is presented, with special emphasis on its temporal reasoning function, which is integrated in a RTKBS environment with a multi-agent blackboard architecture. Representation and management of temporal data, representing past, current and future problem states and reasoning processes within these contexts are detailed.

A Temporal Query System for Protocol-Directed Decision Support

Chronus is a query system that supports temporal extensions to the Structured Query Language (SQL) for relational databases. Although the relational data model can store time-stamped data and can permit simple temporal-comparison operations, it does not provide either a closed or a sufficient algebra for manipulating temporal data. In this paper, we outline an algebra that maintains a consistent relational representation of temporal data and that allows the type of temporal queries needed for protocol-directed decision support. We also discuss how Chronus can translate between our temporal algebra and the relational algebra used for SQL queries. We have applied our system to the task of screening patients for clinical trials. Our results demonstrate that Chronous can express sufficiently all required temporal queries, and that the search time of such queries is similar to that of standard SQL.

Tracing Temporal Information in an Automated Nautical Charting System

Nautical information is one example of spatial data with a strong temporal component. This paper describes the methods of temporal data representation to be used in a National Ocean Service (NOS) Automated Nautical Charting System (ANCS II). The system will be capable of tracing spatial change over time and of tracking cartographic and data-base procedures within the agency. The discussion describes a method of spatiotemporal representation within traditional geographic information systems (GIS) data structures, draws a distinction between information-oriented and production-oriented temporality, and identifies three fundamental elements of temporal metadata.

Fine detail in body surface potential maps: Accuracy of maps using a limited lead array and spatial and temporal data representation

In order to evaluate the accuracy with which a limited lead array can be used to estimate fine details of the thoracic distribution of cardiac potentials, we compared 192-lead body surface maps and those constructed using a subset of 32 leads. We also evaluated preservation of detail in body surface maps reconstructed following spatial and temporal data representation, a method proposed for quantitative comparison of maps. Maps were analyzed with respect to four previously reported normal map features recorded with extensive lead arrays. The maps constructed from 32 leads accurately reproduced all map features with 92% or greater accuracy. Maps constructed after spatial and temporal data representation had a reproduction accuracy of 93% and 98% respectively for two map features more than 100 μV in amplitude but accuracy with respect to the two map features less than 100 μV in amplitude was 86% and 59% respectively. The study demonstrates that a selected limited lead array permits accurate estimation of the body surface distribution of cardiac potentials even when potentials are low level or occur in regions not directly sampled by a recording electrode. To represent potentials of less than 100 μV, more coefficients would be required to permit accurate spatial and temporal representation.