Comparing Posturographic Time Series through Events Detection

Lara, Juan A.; Moreno, G.; Pérez, Aurora Pérez; Valente, Juan Pedro; López-Illescas, África

doi:10.1109/cbms.2008.61

Cited by 9 publications

(17 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Interaction with experts would appear to be crucial for dealing with the above questions, etc. Experience suggests that it is highly advisable to consult a group or panel of experts for multiple gold-standard annotation rather than relying on a single expert [61] , [62] , [63] , [64] , [65] , [66] , [67] , [68] . The premises of this panel-based approach are as follows: There are two or more individuals, each characterized by his or her own perceptions, attitudes, motivations, and personalities, who recognize the existence of a common problem, and attempt to reach a collective decision.…”

Section: Applied Methods and Resultsmentioning

confidence: 99%

Applying data mining techniques to medical time series: an empirical case study in electroencephalography and stabilometry

Anguera

Barreiro

Lara

et al. 2016

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

One of the major challenges in the medical domain today is how to exploit the huge amount of data that this field generates. To do this, approaches are required that are capable of discovering knowledge that is useful for decision making in the medical field. Time series are data types that are common in the medical domain and require specialized analysis techniques and tools, especially if the information of interest to specialists is concentrated within particular time series regions, known as events.This research followed the steps specified by the so-called knowledge discovery in databases (KDD) process to discover knowledge from medical time series derived from stabilometric (396 series) and electroencephalographic (200) patient electronic health records (EHR). The view offered in the paper is based on the experience gathered as part of the VIIP project.1Knowledge discovery in medical time series has a number of difficulties and implications that are highlighted by illustrating the application of several techniques that cover the entire KDD process through two case studies.This paper illustrates the application of different knowledge discovery techniques for the purposes of classification within the above domains. The accuracy of this application for the two classes considered in each case is 99.86% and 98.11% for epilepsy diagnosis in the electroencephalography (EEG) domain and 99.4% and 99.1% for early-age sports talent classification in the stabilometry domain. The KDD techniques achieve better results than other traditional neural network-based classification techniques.

show abstract

Section: Applied Methods and Resultsmentioning

confidence: 99%

Applying data mining techniques to medical time series: an empirical case study in electroencephalography and stabilometry

Anguera

Barreiro

Lara

et al. 2016

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

show abstract

“…To enact the classification process, we have compared each of the ten individuals in the test group against each of the two created models, making use of the stabilometric time series comparison method described in (Lara et al, 2008). All sportspeople have been classified taking into account how similar they are to the two created models, selecting the model most like the patient in question as the class.…”

Section: Results and Conclusionmentioning

confidence: 99%

Modelling Stabilometric Time Series

Lara¹,

Pérez-Pérez²,

Valente³

et al. 2010

Proceedings of the Third International Conference on Health Informatics

View full text Add to dashboard Cite

Abstract:Stabilometry is a branch of medicine that studies balance-related human functions. Stabilometric systems generate time series. The analysis of these time series using data mining techniques can be very useful for domain experts. In the field of stabilometry, as in many other domains, the key nuggets of information in a time series are concentrated within definite time periods known as events. In this paper, we propose a technique for creating reference models for stabilometric time series based on event analysis. After testing the technique on time series recorded by top-competition sportspeople, we conclude that stabilometric models can be used to classify individuals by their balance-related abilities.

show abstract

“…This kind of event is known in the stabilometric domain as an imbalance. To identify and characterise these kinds of events the method proposed in [12] has been used. It is a statistical method that goes through the time series trying to find points where there is an event.…”

Section: Methods For the Identification And Feature Extraction Of Eventsmentioning

confidence: 99%

“…The analysis of stabilometric time series using data mining techniques offers new possibilities. Recently, a new method has been developed for comparison of two stabilometric time-series [12]. This method calculates the level of similarity of two time-series and can be applied to compare either the balance of two patients or to study how the balance of one patient evolves with time.…”

Section: Fig 1 Patient Completing a Test On A Posturographmentioning

confidence: 99%

Classification of Stabilometric Time-Series Using an Adaptive Fuzzy Inference Neural Network System

Lara

Jahankhani

Pérez

et al. 2010

Artificial Intelligence and Soft Computing

Self Cite

View full text Add to dashboard Cite

Abstract. Stabilometry is a branch of medicine that studies balance-related human functions. The analysis of stabilometric-generated time series can be very useful to the diagnosis and treatment balance-related dysfunctions such as dizziness. In stabilometry, the key nuggets of information in a time series signal are concentrated within definite time periods known as events. In this study, a feature extraction scheme has been developed to identify and characterise the events. The proposed scheme utilises a statistical method that goes through the whole time series from the start to the end, looking for the conditions that define events, according to the experts' criteria. Based on these extracted features, an Adaptive Fuzzy Inference Neural Network has been applied for the classification of stabilometric signals. The experimental results validated the proposed methodology.

show abstract

Comparing Posturographic Time Series through Events Detection

Abstract: Abstract

Cited by 9 publications

References 7 publications

Applying data mining techniques to medical time series: an empirical case study in electroencephalography and stabilometry

Applying data mining techniques to medical time series: an empirical case study in electroencephalography and stabilometry

Modelling Stabilometric Time Series

Classification of Stabilometric Time-Series Using an Adaptive Fuzzy Inference Neural Network System

Contact Info

Product

Resources

About