James Dials

Data Scientist & Machine Learning(ML) Specialist

Learn More
James Dials

About Me

Master’s degree in computer science with two years of experience as a data engineer. Used Structured Query Language(SQL)/Python to perform extracting, transforming, and loading data(ETL) on large data sets. Worked towards enhancing surgical simulation in the medical field using data science and ML.

FPU Logo

Education

Master In Computer Science

Florida Polytechnic University

Bachelor In Computer Science

Florida Polytechnic University

Publications

Endoscopic sleeve gastroplasty: stomach location and task classification for evaluation using artificial intelligence

We classified the four different stomach parts manipulated during the ESG procedure with 97% training accuracy and classified two repeated tasks with 99% training accuracy with images. We also classified the four parts of the stomach with a 99% training accuracy and two repeated tasks with a 100% training accuracy with video frames...

Read More

Skill-level classification and performance evaluation for endoscopic sleeve gastroplasty

This paper shows that feature reduction, in combination with classification algorithms such as SVM and KNN, can be used in tandem to classify endoscopists as experts or novices based on their results recorded using our grading metrics. Furthermore, this work introduces a non-linear constraint optimization to separate the two clusters and find the most important tasks using weights.

Read More

Comparison Study of Deep Learning Models for Colorectal Lesions Classification

We had 2 classes: NICE 1 and NICE 2, and a total of 171 high-quality colorectal tumor images. We performed a comparison study about the classification of the colorectal tumor images according to NICE classification by using deep learning models between GoogLeNet, AlexNet, and InceptionV3. Our results show that InceptionV3 has better accuracy with an average of 92.39%...

Read More

Arthroscopic Tool Classification using Deep Learning

Shoulder Arthroscopy is an operation for the treatment of tears on the shoulder. While this surgery is very common, there is no objective assessment for classifying expert surgeons from novice surgeons. Furthermore, cleaning of the tear’s region is the most important phase for the surgery. Therefore, our study focused on two tools which are used to perform this phase...

Read More

Experience

Data Engineer

  • Developed backend API systems and infrastructure.
  • Wrote SQL queries for ingesting, storing & retrieving data.
  • Migrated EC2 instances into Apache Airflow data extracts.
  • Created Scheduled ETL pipelines using Airflow & PostgreSQL.
  • Linked Opsgenie alerting to Google Spaces using Apache Airflow.
  • Created or modified 20+ AWS Lambdas services using Python & Java.
TCS Logo

Skills

Python
Java
SQL
Pandas
Matplotlib
TensorFlow
Scikit-learn
Apache Airflow
Flask
JSON
AWS Lambda
AWS S3
R
Git
Opsgenie
Prometheus

Contact