The Analysis from Nonlinear Distance Metric to Kernel-based Drug Prescription Prediction System

  title={The Analysis from Nonlinear Distance Metric to Kernel-based Drug Prescription Prediction System},
  author={Der Chen Chang and Ophir Frieder and Chi-Feng Hung and Hao-Ren Yao},
. The distance metric and its nonlinear variant play a substantial role in machine learning, particularly yoso in building kernel functions. Often, the Euclidean distance with a radial basis function (RBF) is used to construct a RBF kernel for nonlinear classification. However, domain implications periodically constrain the distance metrics. Specifically, within the domain of drug efficacy prediction, distance measures must account for time that varies based on disease duration, short to chronic… 

Figures and Tables from this paper

Reilly-type inequality for the Φ-Laplace operator on semislant submanifolds of Sasakian space forms

This paper aims to establish new upper bounds for the first positive eigenvalue of the Φ-Laplacian operator on Riemannian manifolds in terms of mean curvature and constant sectional curvature. The



Halting in Random Walk Kernels

This work theoretically shows that halting may occur in geometric random walk kernels, and empirically quantify its impact in simulated datasets and popular graph classification benchmark datasets.

Weisfeiler-Lehman Graph Kernels

A family of efficient kernels for large graphs with discrete node labels based on the Weisfeiler-Lehman test of isomorphism on graphs that outperform state-of-the-art graph kernels on several graph classification benchmark data sets in terms of accuracy and runtime.

Multiple Graph Kernel Fusion Prediction of Drug Prescription

An end-to-end interpretable deep architecture that predicts the success of drug prescription based on multiple graph kernel fusion using a graphical representation of electronic health records that outperforms current start-of-the-art models on accuracy and interpretability is presented.

Sub-Riemannian Geometry: General Theory and Examples

Part I. General Theory: 1. Introductory chapter 2. Basic properties 3. Horizontal connectivity 4. Hamilton-Jacobi theory 5. Hamiltonian formalism 6. Lagrangian formalism 7. Connections on

Graph Kernel Prediction of Drug Prescription

This work proposes an additional such model that uses a graphical representation of an electronic health record with the prescription process formulated as a kernelized binary (success or failure) classification problem.

Cross-Global Attention Graph Kernel Network Prediction of Drug Prescription

An end-to-end, interpretable, deep-learning architecture to learn a graph kernel that predicts the outcome of chronic disease drug prescription that outperforms current start-of-the-art models both in terms of accuracy and interpretability is presented.

Heat kernels for a family of Grushin operators

Geometric Mechanics on Riemannian Manifolds: Applications to Partial Differential Equations

* Preface * Introductory Chapter * Laplace Operator on Riemannian Manifolds * Lagrangian Formalism on Riemannian Manifolds * Harmonic Maps from a Lagrangian Viewpoint * Conservation Theorems *

Heat Kernels for Elliptic and Sub-elliptic Operators: Methods and Techniques

Part I. Traditional Methods for Computing Heat Kernels.- Introduction.- Stochastic Analysis Method.- A Brief Introduction to Calculus of Variations.- The Path Integral Approach.- The Geometric

Untersuchungen über die Grundlagen der Thermodynamik