The reach of technological innovation continues to grow, changing all industries as it evolves. In healthcare, technology is increasingly playing a role in almost all processes, from patient registration to data monitoring, from lab tests to self-care tools. The increase in the amount and diversity of generated clinical data requires development of new technologies and procedures capable of integrating and analyzing the BIG generated information as well as providing support in their interpretation. To that extent, this dissertation focuses on the analysis and processing of biomedical signals, specifically brain and heart signals, using advanced machine learning techniques. That is, the design and implementation of automatic biomedical signal pre-processing and monitoring algorithms, the design of novel feature extraction methods, and the design of classification techniques for specific decision making processes. In the first part of this dissertation Electroencephalogram (EEG) signals that are recorded in 14 different locations on the scalp are utilized to detect random eye state change in real-time. In summary, cross channel maximum and minimum is used to monitor real-time EEG signals in 14 channels. Upon detection of a possible change, Multivariate Empirical Mode Decomposes the last two seconds of the signal into narrow-band Intrinsic Mode Functions. Common Spatial Pattern is then employed to create discriminating features for classification purpose. Logistic Regression, Artificial Neural Network, and Support Vector Machine classifiers all could detect the eye state change with 83.4% accuracy in less than two seconds. We could increase the detection accuracy to 88.2% by extracting relevant features from Intrinsic Mode Functions and directly feeding it to the classification algorithms. Our approach takes less than 2 seconds to detect an eye state change which provides a significant improvement and promising real-life applications when compared to slow and computationally intensive instance based classification algorithms proposed in literatures. Increasing the training examples could even improve the accuracy of our analytic algorithms. We employ our proposed analytic method in detecting the three different dance moves that honey bees perform to communicate the location of a food source. The results are significantly better than other alternative methods in the literature in terms of both accuracy and run time. The last chapter of the dissertation brings out a collaborative research on Parkinson's disease. As a Parkinson’s Progression Markers Initiative (PPMI) investigator, I had access to the vast database of The Michael J. Fox Foundation for Parkinson's Research. We utilized available data to study the heredity factors leading to Parkinson's disease by using Maximum Likelihood and Bayesian approach. Through sophisticated modeling, we incorporated information from healthy individuals and those diagnosed with Parkinson's disease (PD) to available historical data on their grandparents' family to draw Bayesian estimations for the chances of developing PD in five types of families. That is, families with negative history of PD (type 1) and families with positive history in which estimations provided for the prevalence of developing PD when none of the parents (type 2), one of the parents (type 3 and 4), or both of the parents (type 5) carried the disease. The results in the provided data shows that for the families with negative history of PD the prevalence is estimated to be 20% meaning that a child in this family has 20% chance of developing Parkinson. If there is positive history of PD in the family the chance increases to 33% when none of the parents had PD and to 44% when both of the parents had the disease. The chance of developing PD in a family whose solely mother is diagnosed with the disease is estimated to be 26% in comparison to 31% when only father is diagnosed with Parkinson's.