Luis Selvera
Scan contact card
Graduate Research Assistant with 3 years of research and implementation experience in machine learning models, using predictive data modeling, and analyzing deep learning algorithms to deliver insights and implement data-driven solutions to solve complex and diverse problems. Adept at collecting, processing, analyzing, and interpreting large datasets. Consistently optimized and improved NLP models by evaluation strategies and testing changes in machine learning models. Possessing an extensive analytical skills, strong attention to detail, and a significant ability to work in team environments.
Here is my Resume (last updated May 2021).
Skills
- NLP
- Deep Learning
- Machine Learning
- Data Science
- Data Mining
- Anomaly Detection
- Fraud Detection
- Data Visualization
- NIDS
- IDS
- Pytorch
- Keras
- Tensorflow
- Fastai
- SciKit-Learn
- NLTK
- Spacy
- Pandas
- NumPy
- Matplotlib
- Seaborn
- Jupyter Notebook
- Django
- Flask
- MySQL
- OracleDB
- PostgreSQL
- MongoDB
- OrientDB
- Python
- C
- C++
- Java
- MATLAB
- CLISP
Tracking Covid-19 through Social Media using Sentiment Analysis
Worked in team of 7 implementing data pipeline to process unstructured text data from Twitter and Google. Developed data preprocessing and analytics modules to cleanse and gain insight from collected dataset. Developing text classification sentiment analysis deployed on website using Django web framework.
Text-based Classification of Questions on Q&A Forums using Bi-LSTM
Developed Bidirectional-LSTM model to detect improper questions using datasets from Q&A forums. Deployed model on website using Flask web framework for users to input their questions for classifications. Developed model using Pytorch achieving a 97% classification accuracy.
Trolls Detector using Bidirectional Encoder Representations from Transformers (BERT)
Implemented deep learning solution to detecting trolls online using sequential BERT model for classification. Built website that uses model to detect trolls on forums websites allowing users to input the posts. Developed model using Pytorch and deployed on website using Flask web framework.
Tutor Tools Software
Built a software application for tutoring services using Java and MySQL. Applied software engineering principles, Agile Method, and software design patter model-view-controller (MVC). Allows tutors and students to manage tutoring sessions and give a visual organization of the collected information
Paper - Interpretable Federated Transformer Log Learning for Threat Forensics
Paper - Quantized Spectral Clustering with Seq2Seq Attention Model to Predict Cognitive State from Behavior Variables
Experience
Cyber Security Intern
- Tested machine learning techniques for analysis of malware and extracted firmware
- Performed data collection and transformations from various cyber threat intelligence sources: MISP, Alienvault, Mitre
- Built Structured Threat Intelligence Graphs for analyzing threat intelligence with relational graphs and OrientDB
Graduate Research Assistant
- Constructed NLP Transformer sequential models for classification, anomaly detection, and time series forecasting
- Developed machine learning models to detect abnormal behavior and threats in systems with 90% detection rate
- Analyzed and processed semi-structured real world data using advanced querying, visualization and analytics tools
Teaching Assistant
- Assisted on average 5 students per week by reviewing materials and providing assistance in assignments
- Assisted students in accomplishing established learning objectives, with a 100% passing rate
- Evaluated and supervise student’s assignment
Robotics Intern
- Gained understanding of hardware and software systems for robotics
- Hands on experience and familiarity with robotic systems
- Presented project results at poster session at Savannah River Site National Lab
Academic Tutor
- Courses: C++, Java, Physics, Calculus, Linear Algebra, Probability & Statistics, College Algebra
- Provided students with one-on-one assistance to achieve grade level performance
- Presented five computer science and math workshops on average every semester to academically aid students
Education
The University of Texas at San Antonio
Concentration in Data Science