Possibilistic Similarity Measures for Data Science and Machine Learning Applications

Abstract

Measuring similarity is of a great interest in many research areas such as in data sciences, machine learning, pattern recognition, text analysis and information retrieval to name a few. Literature has shown that possibility is an attractive notion in the context of distinguishability assessment and can lead to very efficient and computationally inexpensive learning schemes. This paper focuses on determining the similarity between two possibility distributions. A review of existing similarity measures within the possibilistic framework is presented first. Then, similarity measures are analyzed with respect to their capacity to satisfy a set of required properties that a similarity measure should own. Most of the existing possibilistic similarity measures produce undesirable outcomes since they generally depend on the application context. A new similarity measure, called InfoSpecificity, is introduced and the similarity measures are categorized into three main methods: morphic-based, amorphic-based and hybrid. Two experiments are being conducted using four benchmark databases. The aim of the experiments is to compare the efficiency of the possibilistic similarity measures when applied to real data. Empirical experiments have shown good results for the hybrid methods, particularly with the InfoSpecificity measure. In general, the hybrid methods outperform the other two categories when evaluated on small-size samples, i.e., poor-data context (or poor-informed environment) where possibility theory can be used at the greatest benefit.

Future trends in mechatronics

“…Hidden Life of Data refers to the use of big data and programming algorithms to understand the processes of human thinking which makes the data more efficient for us to use and, in a way, feels like it has its own mind. Data science [39][40][41] is a valuable skill and a necessary one. Engineers are making amazing inventions every day and the world of data science is filled with possibilities with the fairly recent emergence of robotics.…”

A Redundancy Metric Set within Possibility Theory for Multi-Sensor Systems

“…Consequently, a type II redundancy measure which is set within possibility theory should be based on possibilistic similarity measures. Properties of such similarity measures have been given in [ 61 , 72 , 73 ], which define similarity to be a measure between only two possibility distributions. A definition adapted to sets of possibility distributions is proposed as follows:…”

“…Similarity measures specifically designed towards possibility distributions have rarely been discussed until recently [ 61 , 72 , 73 ]. Before that, similarity of possibility distributions has been predominately determined either based on fuzzy set similarity measures or elementwise distance measurements.…”