Model Selection for Body Temperature Signal Classification Using Both Amplitude and Ordinality-Based Entropy Measures

Abstract

Many entropy-related methods for signal classification have been proposed and exploited successfully in the last several decades. However, it is sometimes difficult to find the optimal measure and the optimal parameter configuration for a specific purpose or context. Suboptimal settings may therefore produce subpar results and not even reach the desired level of significance. In order to increase the signal classification accuracy in these suboptimal situations, this paper proposes statistical models created with uncorrelated measures that exploit the possible synergies between them. The methods employed are permutation entropy (PE), approximate entropy (ApEn), and sample entropy (SampEn). Since PE is based on subpattern ordinal differences, whereas ApEn and SampEn are based on subpattern amplitude differences, we hypothesized that a combination of PE with another method would enhance the individual performance of any of them. The dataset was composed of body temperature records, for which we did not obtain a classification accuracy above 80% with a single measure, in this study or even in previous studies. The results confirmed that the classification accuracy rose up to 90% when combining PE and ApEn with a logistic model.

Influence of Duodenal–Jejunal Implantation on Glucose Dynamics: A Pilot Study Using Different Nonlinear Methods

“…It is important to note that some configuration parameters did not yield significant results, such as = 3 for PE (Table 6) and mPE ( Table 7). As in previous similar studies [37][38][39], it seems the greater the embedded dimension , the better classification performance using PE-based measures.…”

“…In order to better illustrate the differences between the classes studied, a Leave-One-Out (LOO) test [37] 6 Complexity was applied using the data in Table 8. The classification threshold was set at the optimal SampEn value at which the classification accuracy was maximal.…”

Permutation Entropy: Enhancing Discriminating Power by Using Relative Frequencies Vector of Ordinal Patterns Instead of Their Shannon Entropy

“…The discriminating power of PE has been well demonstrated in a number of publications [ 16 , 24 , 60 , 61 , 62 ]. As a single feature, using a threshold, it has been possible to successfully classify a disparity of records of different types.…”

“…The real dataset used in the experiments is composed of body temperature records. This dataset is the same previously used in other works [ 16 ], where additional details can be found. It contains 30 records and two classes.…”

“…Such features exhibit a very high discriminating power, and that is why they have been successfully employed in many applications [ 9 , 10 , 11 ]. However, there are ongoing efforts to further improve this discriminating power with new complexity estimation algorithms or by tweaking current ones [ 12 , 13 , 14 , 15 , 16 , 17 ], as is the case in this paper.…”