Milad Yousefi

A passionate researcher at the intersection of mathematics, artificial intelligence, and biological sciences with a strong foundation in Applied Mathematics and expertise in computational approaches to solve complex biological problems.

About Me

I am a computational biology researcher with a foundation in Applied Mathematics from Tabriz University. My work bridges the gap between mathematical modeling, computational methods, and biological applications, with a particular emphasis on neuroscience and medical informatics.

My interdisciplinary approach combines:

• Mathematical Modeling: Developing fuzzy models and computational frameworks for biological systems
• AI Applications: Applying machine learning and deep learning to biological and medical data
• Computational Neuroscience: Modeling neuronal dynamics with a focus on LIF (Leaky Integrate-and-Fire) neuron models
• Bioinformatics: Analyzing genetic and biological data using computational methods

Educational Background

Bachelor of Science in Applied Mathematics
Tabriz University, Iran (2019-2023)
GPA: 17.43/20 (3.58/4.00)
Thesis: "An Investigation into Fuzzy Modeling Techniques for Input Current Conversion in LIF Neuron Models"

My thesis work focused on developing innovative fuzzy logic approaches to model the complex non-linear relationship between input currents and neuronal responses in LIF neuron models, which are fundamental to computational neuroscience.

Computational Biology Research

My research spans several interdisciplinary areas within computational biology, with a primary focus on applying mathematical models and computational methods to understand biological systems and improve healthcare outcomes.

Selected Publications

My research has resulted in several publications and ongoing research projects in peer-reviewed journals, focusing on the application of computational methods in biological and medical contexts:

Skills & Competencies

My interdisciplinary research requires proficiency in various technical skills across mathematics, programming, and data analysis:

Professional Development

I continually enhance my skills through specialized online courses and self-directed learning:

• Advanced Bioinformatics: Specialized course covering genomic data analysis, sequence alignment, and structural bioinformatics
• Computational Neuroscience: Focused study of neural modeling, neural data analysis, and dynamical systems
• Deep Learning Specialization: Completed all 5 courses by Andrew Ng, covering neural networks, CNN, RNN, and optimization techniques
• Machine Learning: Comprehensive training in supervised and unsupervised learning methods, model evaluation, and practical applications

Professional Experience

Major Research Projects

• Brain Stroke Prediction using ML & DL: Developed predictive models incorporating multiple risk factors and biomarkers to assess stroke likelihood, achieving high accuracy in early detection
• Lung Cancer Segmentation & Classification: Created automated tools using convolutional neural networks to process CT scan images, aiding in precise cancer detection and characterization
• Tinnitus Treatment Analysis: Conducted statistical comparison of Gabapentin and Cinnarizine efficacy in patients with sensorineural hearing loss, providing evidence-based treatment recommendations
• Image Compression and Face Recognition: Applied singular value decomposition (SVD) for efficient image compression and feature extraction in facial recognition systems
• Hotel Booking Demand Analysis: Performed comprehensive statistical analysis of hotel booking datasets to identify patterns and factors influencing cancellations and demand fluctuations

Research Vision

Building on my foundation in computational biology and bioinformatics, I aim to pursue several innovative research directions that leverage interdisciplinary approaches:

Integrating AI with Neurological Biomarkers

My ongoing work with retinal imaging and Alzheimer's detection has highlighted the significant potential of using non-invasive biomarkers for neurological disease detection. I plan to expand this research to other neurological conditions, developing more sensitive computational models that can identify subtle changes in various biomarkers.

Advanced Computational Models for Neurological Systems

Building on my work with LIF neuron models, I intend to develop more sophisticated computational frameworks that can better simulate complex neuronal networks and interactions. These models could provide deeper insights into neural functioning and potential therapeutic targets for neurological disorders.

Personalized Medicine through Computational Biology

By combining genetic data, computational models, and machine learning, I aim to contribute to the field of personalized medicine by developing tools that can predict individual responses to treatments based on biological markers and patient characteristics.

Cross-disciplinary Collaboration

I'm particularly interested in forming collaborations across mathematics, computer science, medicine, and biology to tackle complex healthcare challenges that require multidisciplinary approaches. These collaborations could lead to novel computational methods with real-world clinical applications.

Educational Initiatives

Drawing from my experience as a teaching assistant, I'm passionate about developing educational resources that make computational biology more accessible to students from diverse backgrounds, particularly focusing on practical applications and hands-on learning experiences.

Get in Touch

I welcome collaboration opportunities, research discussions, and connections with fellow researchers in computational biology, bioinformatics, and related fields.

Collaboration Areas

I'm particularly interested in collaborating on projects related to:

• Computational approaches to neurodegenerative disease detection and monitoring
• Advanced mathematical modeling of biological systems
• AI applications in medical imaging and diagnostics
• Interdisciplinary research bridging mathematics, biology, and computer science
• Educational initiatives in computational biology and bioinformatics