Classification confidence weighted majority voting using decision tree classifiers

Abstract

In this paper a novel method is proposed to combine decision tree classifiers using calculated classification confidence values. This confidence in the classification is based on distance calculation to the relevant decision boundary. It is shown that these values-provided by individual classification trees-can be integrated to derive a consensus decision. The proposed combination scheme-confidence weighted majority votingpossesses attractive features compared to other approaches. There is no need for an auxiliary combiner or gating network, like in the Mixture of Experts structure and the method is not limited to decision trees with axis-parallel splits; it is applicable to any kind of classifiers that use hyperplanes to cluster the input space.

Smartphone-Based User Activity Recognition Method for Health Remote Monitoring Applications

“…The simplest windowed decision policy is a majority-rule decision: the window is associated to the class with the most frames in the window. Such decision mechanism is employed in some earlier work on AR, e.g., (Toth, 2008). While it is clearly simple to implement and computationally inexpensive, the majority-rule windowed decision treats all frames within a window in the same way, without considering when the frames occurred or the single frame classifications' reliability.…”

Exploiting context for automatic check-in suggestion and validation

“…Each windowed decision assigns the current window to one of the four considered classes, based on a combination between the Gaussian temporal weighting and the classification scores into a single, joint time-and-score weight. The scoring method used in our implementation is described in [5]. Every windowed decision is sent by the LCB to the Context Broker making the user's motion situation available to applications.…”

A smartphone‐centric platform for remote health monitoring of heart failure

“…The simplest windowed decision policy is a majority‐rule decision: the window is assigned to the class to which the largest number of frames in the window has been associated. Such decision mechanism is employed in some earlier works such as . While it is clearly simple to implement and computationally inexpensive, the majority‐rule windowed decision treats all frames within a window in the same way, without considering when the frames occurred and the single‐frame classification reliability. Time‐weighted decision .…”

“… Score‐weighted decision . A score representing the reliability of the classification is assigned to each frame . The basic idea is that the closer a frame feature vector is to the decision boundary, the more unreliable the frame classification is, under the hypothesis that the majority of badly classified samples lie near the decision boundary.…”