J48SS: A Novel Decision Tree Approach for the Handling of Sequential and Time Series Data

Abstract

Temporal information plays a very important role in many analysis tasks, and can be encoded in at least two different ways. It can be modeled by discrete sequences of events as, for example, in the business intelligence domain, with the aim of tracking the evolution of customer behaviors over time. Alternatively, it can be represented by time series, as in the stock market to characterize price histories. In some analysis tasks, temporal information is complemented by other kinds of data, which may be represented by static attributes, e.g., categorical or numerical ones. This paper presents J48SS, a novel decision tree inducer capable of natively mixing static (i.e., numerical and categorical), sequential, and time series data for classification purposes. The novel algorithm is based on the popular C4.5 decision tree learner, and it relies on the concepts of frequent pattern extraction and time series shapelet generation. The algorithm is evaluated on a text classification task in a real business setting, as well as on a selection of public UCR time series datasets. Results show that it is capable of providing competitive classification performances, while generating highly interpretable models and effectively reducing the data preparation effort.

A Decision Model to Predict the Selection of Education Streams – A Case Study for Trang Province, Thailand

“…In terms of performance and employment, DT_J48 has high performance regarding sensitivity and gmean, meaning that the model can correctly classify students into the vocational education stream. Although the proposed DT was not superior to the other machine learning methods from all metrics, it has the following advantages when compared to the other models: 1) the ability to depict the connections between variables in a graph with a tree structure, facilitating users' understanding and interpretation of the model [35]; 2) the ability to handle different types of predictor variables [35]; 3) the ability to analyze data without testing parametric assumptions [36]; 4) the ability to handle datasets when the training or testing data has missing values [37]; 5) the ability to reduce data preparation effort [38]. In contrast, LR models entail basic assumptions, including error independence, linearity of logit values for continuous variables, lack of multicollinearity, and lack of very influential outliers.…”

The voice of COVID-19: Breath and cough recording classification with temporal decision trees and random forests

“…Shapelets [64] have been extensively used in the field of learning from time series; this concept has been used in decision trees to classify time series by Brunello et al. [65] . Finally, Brunello et al.…”

Classification of COVID-19 individuals using adaptive neuro-fuzzy inference system

“…Decision Tree (DT): It is a supervised machine learning technique that splits the dataset into two or more classes to solve the classification [ 7 ]. DT represents a tree with internal nodes that denotes a test of an attribute, each branch represents an outcome of the test, and each of the leaf nodes holds the class label.…”