Digital Health Machine Learning Engineer and PhD candidate in Computer Science with experience in machine learning, NLP, and biomedical/healthcare applications. Has worked on prediction and recommendation systems, intent…
Digital Health Machine Learning Engineer and PhD candidate in Computer Science with experience in machine learning, NLP, and biomedical/healthcare applications. Has worked on prediction and recommendation systems, intent prediction, and competition-based forecasting projects using Python, PySpark, Wit.ai, LightGBM, XGBoost, DNN, ARIMA, Random Forest, DeepFM, C, and Matlab.
• Brief: develop a prediction and recommendation system to enhance Healthshare's digital pathway screening tool for Musculoskeletal (MSK) patients using machine learning techniques such as deep neural networks, graph neural networks and Natural Language Processing.
• Contribution: develop BI project to visualise and profile NHS pressure and successfully expand business and win more contracts for the company. Develop initial AI model for the MSK treatment recommendations.
Develop a prediction and recommendation system to enhance Healthshare's digital pathway screening tool for Musculoskeletal (MSK) patients using machine learning techniques such as deep neural networks, graph neural networks and Natural Language Processing.
Develop BI project to visualise and profile NHS pressure and successfully expand business and win more contracts for the company.
Develop initial AI model for the MSK treatment recommendations.
Create biomedical virtual (VR) and augmented (AR) reality content to enhance Higher Education in universities.
Develop the NLP part for the system.
Develop systems to predict the intent of an utterance in English and Korean input by patients.
Set up, deploy and evaluate the performance of Wit.ai and PySpark.
Generate dataset based on collected data via augmentation methods.
Analyse the amount of utterances per intent to obtain good performance.
Achieved 572 out of 10881 (top 5%).
Main technique: Python / Feature extraction / LightGBM / XGBoost / DNN.
Create an AI model for a regression problem in order to predict price of the used cars.
Train the model with multi-dimension data.
Surpassed the official baseline 10%.
Achieved 106 out of 7477 (top 1.4%).
Main technique: Python / LR / ARIMA / LightGBM / Random Forest.
Predict future cash flows based on users' historical purchase and redemption data to help Alibaba improve its funds management abilities.
Achieved 2 out of 70 participants.
Main technique: Python / LR / Feature extraction / LightGBM / DeepFM.
Predict whether users will purchase in the next month based on history purchasing records in the last year.
Implemented pattern recognition algorithms with artificial feature extraction to the images captured by high-frame rate camera.
Surpassed the performance of EyeLink, the best device before ours.
Main technique: Python / C / Matlab / Pattern Recognition / Computer Vision.
Designed, developed, deployed and tested a Pupil Tracking System as an auxiliary diagnostic tool for neurological diseases.
نظام التوظيف التشغيلي المعتمد على الذكاء الاصطناعي أولاً، الذي يوحّد ويؤتمت دورة التوظيف بالكامل للمؤسسات الحديثة حول العالم.
د.جوب منطقة حرة ذ.م.م. 2026 © جميع الحقوق محفوظة
