Olateju E.

I am a highly motivated and experienced data scientist with a passion for applying machine learning and signal processing techniques to solve real-world problems in the field of brain-computer interfaces (BCIs). I have a strong background in EEG, EMG, BCI and robotics research, and I am proficient in a wide range of data science and machine learning tools and techniques. Skills and Expertise Data analysis and visualization: Proficient in Python and MATLAB for data cleaning, exploratory data analysis, and data visualization. Machine learning: Expertise in supervised and unsupervised learning algorithms, including linear regression, logistic regression, support vector machines, decision trees, random forests, and neural networks. Signal processing: Experience in time-frequency analysis, filtering, feature extraction, and classification of EEG and EMG signals. Neural Data Analysis: Experience in the extraction of temporal, frequency, spatial and combinations features. Experience with complexity and functional connectivity measures. Brain-computer interfaces (BCIs): Familiarity with various BCI paradigms, including motor imagery, steady-state visually evoked potentials (SSVEPs), Mismatch Negativity(MMN) and more. Projects and Accomplishments Creating first African schizophrenia EEG dataset (NSzED) and development of custom EEG data-acquisition software for data acquisition. Developed ANNs (CNN, LSTM, RBFN), linear and non-linear models for predicting schizophrenia based on NSzED, achieving accuracy of 89% and f1-score of 85%. Developed EEG neurofeedback based exoskeleton robot and hand-orthosis for upper-extremities stroke rehabilitation with three confirmed patients recovering full motor function. Developed embedded controllers, measurement systems and gamified therapy software solutions. Developed EEG motor-imagery based neurofeedback hand orthosis device to augment patient grasp and release therapy using common spatial patterns and support vector classifier initially giving 43% accuracy across subjects, while filter-banks common spatial patterns produced 65% accuracy across subjects with best subject accuracy being 81%. Developed STFT spectrogram and CNN based classifier for identifying motor-imagery, motor-action and rest state neural activity. Achieved 85% accuracy across all subjects with least subject performance being 81% Education Bachelors of Science in Electronic and Electrical Engineering, Obafemi Awolowo University, Nigeria. Additional Skills Strong programming skills in Python and MATLAB. Other programming skills and tools include SQL, C, C#, C++, Unity, Git, Microsoft Visual Studio, Jupyter, Docker. Proficient in Microsoft Office Suite and latex. Excellent communication and interpersonal skills Ability to work independently and as part of a team Strong attention to detail Keen interest in the latest developments in data science and machine learning I am eager to apply my skills and knowledge to contribute to innovative projects in the field of data science, machine learning, signal processing, and brain-computer interfaces. Please contact me to discuss your project or research opportunities.