Using Machine Learning to Augment Dynamic Time Warping Based Signal Classification

Overview

Modern applications such as voice recognition rely on the ability to compare signals to pre-recorded ones to classify them. However, this comparison typically needs to ignore differences due to signal noise, temporal offset, signal magnitude, and other external factors. The Dynamic Time Warping (DTW) algorithm quantifies this similarity by finding corresponding regions between the signals and non-linearly warping one signal by stretching and shrinking it. Unfortunately, searching through all “warps” of a signal to find the best corresponding regions is computationally expensive. The FastDTW algorithm improves performance, but sacrifices accuracy by only considering small signal warps. My goal is to improve the speed of DTW while maintaining high accuracy. My key insight is that in any particular application domain, signals exhibit specific types of variation. For example, the accelerometer signal measured for two different people would differ based on their stride length and weight. My system, called Machine Learning DTW (MLDTW), uses machine learning to learn the types of warps that are common in a particular domain. It then uses the learned model to improve DTW performance by limiting the search of potential warps appropriately. My results show that compared to FastDTW, MLDTW is at least as fast and can have up to 25.9 times less error on a real-world data set. These improvements will significantly impact a wide variety of applications (e.g. health monitoring) and enable more scalable processing of multivariate, higher frequency, and longer signal recordings. The Effect of Electrical Stimulation on Ethanol-Induced Paralysis Modeling Parkinsonism in C. elegans Rositsa Tsarnakova State College Area High School, State College, PA Supervisor, D. Rosensteel, State College Area High School Parkinson’s disease and similar neurodegenerative conditions like Parkinsonism, currently affect a large portion of the senior population and in some cases, have limited treatment options. However, methods exploiting applied electrical potential have shown promising results. In order to better understand these methods, this study was designed to model drug-induced parkinsonism in the roundworm organism C. elegans that mimic humans within a neurological scope. Experimental groups received different combinations of ethanol to induce the paralysis and tremor associated with the disease and electrical stimulation via copper electrodes and a basic power station for a duration of 20 minutes. The locomotion of the C. elegans was recorded and quantitatively analyzed for body bends and survival time. ANOVA and Tukey HSD tests revealed p-values less than 0.0001 for both variables of interest and further analysis of means identified prolonged survival in C. elegans receiving electrical stimulation. The findings of this study can be further expanded upon in professional settings using more comprehensive lab techniques to provide greater insight into this method of treatment for Parkinson’s-like diseases.

Competition history

• JSHS 2022 Category not listed

Resources

• National JSHS abstract book ↗

Related projects

Closest projects by meaning, across every fair and year in the corpus.