arXiv subjects

Khoa Tran

Publications and source records attributed to Khoa Tran.

21 records · Page 2Linked to original sources

arXiv2020

Deep Learning Framework Applied for Predicting Anomaly of Respiratory Sounds

This paper proposes a robust deep learning framework used for classifying anomaly of respiratory cycles. Initially, our framework starts with front-end feature extraction step. This step aims to transform the respiratory input sound into a two-dimensional spectrogram where both spectral and temporal features are well presented. Next, an ensemble of C- DNN and Autoencoder networks is then applied to classify into four categories of respiratory anomaly cycles. In this work, we conducted experiments over 2017 Internal Conference on Biomedical Health Informatics (ICBHI) benchmark dataset. As a result, we achieve competitive performances with ICBHI average score of 0.49, ICBHI harmonic score of 0.42.

cs.LG↗

arXiv2019

Time-symmetry, symplecticity and stability of Euler-Maclaurin and Lanczos-Dyche integration

Numerical evolution of time-dependent differential equations via explicit Runge-Kutta or Taylor methods typically fails to preserve symmetries of a system. It is known that there exists no numerical integration method that in general preserves both the energy and the symplectic structure of a Hamiltonian system. One is thus normally forced to make a choice. Nevertheless, a symmetric integration formula, obtained by Lanczos-Dyche via two-point Taylor expansion (or Hermite interpolation), is shown here to preserve both energy as well as symplectic structure for linear systems. This formula shares similarities with the Euler-Maclaurin formula, but is superconvergent rather than asymptotically convergent. For partial differential equations, the resulting evolution methods are unconditionally stable, i.e, not subject to a Courant-Friedrichs-Lewy limit. Although generally implicit, these methods become explicit for linear systems.

math.NA↗

arXiv2007

Expected Utility Optimization - Calculus of Variations Approach

In this paper, I'll derive the Hamilton-Jacobi (HJ) equation for Merton's problem in Utility Optimization Theory using a Calculus of Variations (CoV) Approach. For stochastic control problems, Dynamic Programming (DP) has been used as a standard method. To the best of my knowledge, no one has used CoV for this problem. In addition, while the DP approach cannot guarantee that the optimum satisfies the HJ equation, the CoV approach does. Be aware that this is the first draft of this paper and many flaws might be introduced.

math.OC↗