In this project, the performance of speech emotion recognition is compared between two methods (SVM vs Bi-LSTM RNN).Conventional classifiers that uses machine learning algorithms has been used for decades in recognizing emotions from speech. However, in recent years, deep learning methods have taken the center stage and have gained popularity for their ability to perform well without any input hand-crafted features. Speech emotion on sets obtained from RAVDESS corpus is classified using a conventionally used Support Vector Machine (SVM) and its performance is compared to that of a bidirectional long short-term memory (LSTM).
The project aims at building a machine learning model that will be able to classify the various hand gestures used for fingerspelling in sign language. In this user independent model, classification machine learning algorithms are trained using a set of image data and testing is done. Various machine learning algorithms are applied on the datasets, including Convolutional Neural Network (CNN).
Easy to understand classification problem from a highly skewed kaggle dataset. Solved using logistic regression and SVM, code inspired from top contributor.
I developed 2 machine learning software that predict and classify ozone day and non-ozone day. The working principle of the two is similar but there are differences. I got the dataset from ics.icu. Each software has a different mathematical model, Gaussian RBF and Linear Kernel, and classifications are visualized in different ways. I would be happy to present the software to you!
For conceptual understanding you can refer my medium blog which will provide you in-depth knowledge of SVC along with various other factors required in data science.
Code for my paper titled "Online Writer Identification using Sparse Coding and Histogram based descriptors" published as an oral in the 15th International Conference on Frontiers in Handwriting Recognition (ICFHR-2016)