This paper proposes a method of predicting the formant frequencies of a frame of speech from its mel-frequency cepstral coefficient (MFCC) representation. Prediction is achieved through the creation of a Gaussian mixture model (GMM) which models the joint density of formant frequencies and MFCCs. Using this GMM and an input MFCC vector, a maximum a posteriori (MAP) prediction of the formant fre...

OF THE DISSERTATION Learning and Inference in Latent Variable Graphical Models By Wei Ping Doctor of Philosophy in Computer Science University of California, Irvine, 2016 Professor Alexander Ihler, Chair Probabilistic graphical models such as Markov random fields provide a powerful framework and tools for machine learning, especially for structured output learning. Latent variables naturally ex...

The Differential Evolution (DE) population-based algorithm is an optimal algorithm with powerful global searching capability, but it is usually in low convergence speed and presents bad searching capability in the later evolution stage. A new Chaos Differential Evolution algorithm (CDE) based on the cat map is proposed which combines DE and chaotic searching algorithm. Firstly, the chaotic dist...

A contact map is a 2D derivative of the 3D structure of proteins, containing various residue-residue (RR) contacts within the structure. Contact maps can be used for the reconstruction of structure with high accuracy and can be predicted from the amino acid sequence. Therefore understanding the various properties of contact maps is an important step in protein structure prediction. For investig...

This article describes relationships between selected physical characteristics of urban streets and pedestrianlevel heat. It also identifies conditions that are particularly vulnerable to the summer heat. Field measurements of ambient temperatures 1 m above the ground were collected over sidewalks, green spaces, and parking lots in high density commercial and residential areas. Panel autoregres...

OBJECTIVE To expand the search for preeclampsia (PE) metabolomics biomarkers through the analysis of acylcarnitines in first-trimester maternal serum. METHODS This was a nested case-control study using serum from pregnant women, drawn between 8 and 14 weeks of gestational age. Metabolites were measured using an UPLC-MS/MS based method. Concentrations were compared between controls (n = 500) a...

We investigate the existence of rules (in the form of binary patterns) that allow the short-term prediction of highly complex binary sequences. We also study the extent to which these rules retain their predictive power when the sequence is contaminated with noise. Complex binary sequences are derived by applying two binary transformations on realvalued sequences generated by the well known ten...

We present a simple and efficient method for prediction of transcription factor binding sites from DNA sequence. Our method computes a random approximation of a convolutional kernel feature map from DNA sequence and then learns a linear model from the approximated feature map. Our method outperforms state-ofthe-art deep learning methods on five out of six test datasets from the ENCODE consortiu...

We investigate the moduli theory of Calabi–Yau threefolds, and using Griffiths’ work on the period map, we derive some finiteness results. In particular, we confirm a prediction of Morrison’s Cone Conjecture.