Analysis of Prevalence of Mental Illnesses and Suicide in Different Countries Using Gower Clustering Based Dimensionality Reduction of Growth Metrics and Simulation-Based Hypothesis Testing

Source code for this research: https://github.com/AnilBattalahalli/Analysis-Of-Mental-Illnesses Introduction In the last two decades, there have been significant developments in understanding the anatomy of the brain on mental illnesses like Major Depressive Disorder, Anxiety Disorder, Bipolar Disorder, Schizophrenia, Personality Disorder, etc. Most of these disorders, along with alcohol and drug abuse are studied together to analyze theContinue reading “Analysis of Prevalence of Mental Illnesses and Suicide in Different Countries Using Gower Clustering Based Dimensionality Reduction of Growth Metrics and Simulation-Based Hypothesis Testing”

Is the Dirichlet Function Riemann-Darboux Integrable?

The Dirichlet Function The Dirichlet function is one of the easiest function to define. It’s literally, $$ \begin{aligned} f(x)=\left\{ \begin{array}{ll} 1, & \text{if $x$ is rational}\\ 0, & \text{if $x$ is irrational} \end{array} \right. \end{aligned} $$ or using the symbols from number theory/set theory that almost no one remembers, $$ \begin{aligned} f(x)=\left\{ \begin{array}{ll} 1, &Continue reading “Is the Dirichlet Function Riemann-Darboux Integrable?”

Infant Cry Classification with Fourier Transform and Support Vector Machine (SVM)

This project deals with classification of an infant’s cry into hungry cry or spasmatic cry. Some infants have an early onset of idiopathic lung muscle spasm which results in improper supply of oxygen to the brain. When the cry of a baby is because of muscular spasms, there are some frequency ‘gaps’ in the spectrogram.Continue reading “Infant Cry Classification with Fourier Transform and Support Vector Machine (SVM)”

Robotic Navigation with Reinforcement Learning (Deep-Q)

This was an original research where reinforcement learning was used with a four-legged robot for its autonomous motion along with computer vision and Deep-Q Neural Network. We chose a 4 legged robot which has three servo motors per leg. We calibrated each servo motor and restricted its degree of freedom to a certain set thresholdContinue reading “Robotic Navigation with Reinforcement Learning (Deep-Q)”

Interictal Spike detection from EEG with stationary waveform classification using Support Vector Machine (SVM)

This was an original Research aimed at devising a deep learning algorithm to learn and diagnose epileptogenic patterns from an EEG which indicate that a person has had an epileptic seizure. The research employed analyzing the nonlinear energy operator (NEO) of the stationary waves and then thresholding with a semi constant calculated from the energyContinue reading “Interictal Spike detection from EEG with stationary waveform classification using Support Vector Machine (SVM)”

Gait Classification with Transfer Learning (ImageNet)

Walking gait is defined as the cyclical pattern in walking. Gait can be used as a basis for biometric classification. The following supervised classifier is a DenseNet classifier which is trained on multiple still frames of labeled walking subjects. Transfer learning demonstrates a very high accuracy ~95% with just 2 epochs for large number ofContinue reading “Gait Classification with Transfer Learning (ImageNet)”

Curvilinear Vector Algebra Toolbox for MATLAB

I have used MATLAB throughout my engineering. I had vector algebra course where we studied multiple vector algebra operations like gradient, curl and divergence in not just cartesian, but also cylindrical and spherical coordinates. One of my friends needed an implementation of vector algebra in curvilinear coordinates for MATLAB. But the same was not availableContinue reading “Curvilinear Vector Algebra Toolbox for MATLAB”

Generation of Power Law Samples with Inverse Transform Sampling (Python, R and Julia)

Implementation of the Inverse Transform Sampling The probability density function of a power law distribution is given by, $$f(x\ | \ x_m,\alpha) = \frac{\alpha-1}{x_m} \left(\frac{x}{x_m}\right)^{-\alpha} \ , x>x_m$$ We can find the cumulative density function by, $$ \begin{aligned} F(x) &= \int_{-\infty}^x f(x\ | \ x_m,\alpha) \ dx\\ \\ &= \int_{-\infty}^x \frac{\alpha-1}{x_m} \left(\frac{x}{x_m}\right)^{-\alpha} I(x>x_m) \ dxContinue reading “Generation of Power Law Samples with Inverse Transform Sampling (Python, R and Julia)”

CryptFather – A chatbot that encrypts your message

I was fascinated about cryptography throughout my childhood. In particular, I was very intrigued about symmetric key encryption systems like One Time Pad (OTP) which theoretically are 100% secure assuming a true random key. I implemented the same to encrypt and decrypt messages for Telegram Messenger. Telegram Messenger has bots which can be programmed asContinue reading “CryptFather – A chatbot that encrypts your message”

People in the US have trouble pronouncing my name. So I over-engineered a Python program

My first name has literally two syllables. And it doesn’t have one of those á, é, í, ó, ú, ü, ñ or any other seizure-inducing accents as well. It is also insanely phonetic. I mean, look at the name “Isla”, it’s pronounced “EYE-la”. Huh?? In spite of my name being so simple to pronounce, hereContinue reading “People in the US have trouble pronouncing my name. So I over-engineered a Python program”