Senior Machine Learning Engineer
2018 - PRESENTTerramera- Researched deep learning models for object detection (Mask-RCNN, U-Net) using Python and TensorFlow to automate pest counting processes.
- Implemented multispectral image processing pipelines for plant health evaluation using Computer Vision and machine learning techniques, including geometric transformation and keypoint descriptor for image alignment and stitching, stereovision for depth estimation, color threshold and watershed for segmentation, and regression and tree-based models for plant trait estimation, in Python, OpenCV, and Scikit-learn.
- Developed a multispectral imaging prototype and implemented machine learning models to estimate grape sugar content based on multispectral reflectance, in Python, OpenCV, and Scikit-learn.
- Implemented machine learning models for drug dose-response modeling, drug synergy analysis and prediction using cheminformatics and machine learning libraries (Scikit-learn, RDKit, PubChemPy) to accelerate the drug discovery process in plant health research.
- Provided advice on experimental design and implemented statistical analysis pipelines with Python, Rpy2, and StatsModels to automate various statistical analyses for plant health research.
Technologies: Python, Scikit-learn, OpenCV, TensorFlow, Keras, RDKitData Scientist
2017 - 2017Phemi Systems- Developed distributed data processing and analytics prototypes using Spark (Scala), Hive and Zeppelin to demonstrate fast query and analytics on terabytes of clinical data.
- Proposed machine learning and deep learning demos using Python, Scikit-learn, and TensorFlow to show how medical imaging data can be analyzed to support diagnosis.
- Researched time-domain/frequency-domain signal processing and machine learning algorithms for fall detection based on biomedical signal data collected from wearable sensors using Python and Scikit-learn.
- Implemented a natural language processing pipeline in Scala and Apache cTAKES - a library with both rule-based and machine learning techniques, to extract clinical information from unstructured medical text.
- Developed term partitioned index mechanism in Java to enable fast document search in Accumulo.
Technologies: Hadoop, Spark, Hive, Zeppelin, Scala, Python, SciPy, Scikit-learnData Analytics Engineer
2012 - 2016DBS Bank- Developed SAS code to extract data from Teradata SQL databases and perform statistical analysis for Card and Unsecured Lending sales and marketing.
- Liaised with the modeling team to deploy predictive models (Recommender System, Location Analytics) for targeted marketing, leading to two times the lift in the customer response rate in digital campaigns.
- Proposed experimental design and hypothesis testing on different content factors to improve customer engagement in email marketing.
- Developed Java analysis reports and QlikView dashboards to provide technology and operations teams with insight on process improvement and risk control.
- Performed process mapping and simulation modeling to optimize business processes, resulting in a 10% reduction in operating costs.
- Led infrastructure design and deployment for an enterprise data management system.
Technologies: Java, SAS, SQL, QlikView
Liam Bui
Deep Learning Developer in Vancouver, BC, Canada
Member since September 15, 2019
Liam is a Certified Analytics Professional (CAP) with over six years of experience in machine learning and data analytics. He has worked with data science, machine learning, deep learning, Computer Vision, and image processing projects from data collection and processing to model training, evaluation, and deployment. He is passionate about building products to help organizations extract insight from data.
Liam is now available for hire
Portfolio
- TerrameraPython, Scikit-learn, OpenCV, TensorFlow, Keras, RDKit
- Phemi SystemsHadoop, Spark, Hive, Zeppelin, Scala, Python, SciPy, Scikit-learn
- DBS BankJava, SAS, SQL, QlikView
Experience
- Python 4 years
- Scikit-learn 4 years
- Computer Vision 3 years
- OpenCV 3 years
- TensorFlow 3 years
- Deep Learning 3 years
- Spark 2 years
- Scala 2 years
Availability
Part-time
Preferred Environment
Windows, Ubuntu, Eclipse, Spyder, Bitbucket, Git
The most amazing...
...project I've worked on used Computer Vision to automatically count dead versus live worms in microscopic images, eliminating the need for manual counting.
Employment
Experience
- Automated Worm Counting with Deep Learning (Development)https://liambll.github.io/blog/portfolio/01_worm_counting/
Built an image processing pipeline and deep learning model to automatically count dead and live worms in microscopic images, reducing the worm counting time from two days (manual counting) to one hour (automated counting with Computer Vision).
- Automated Plant Health Evaluation with Computer Vision (Development)https://liambll.github.io/blog/portfolio/02_plant_health/
Built an image processing pipeline to automatically segment out individual plants in a greenhouse and classify the plants' health.
- Grape Sugar Content Estimation with Multispectral Imaging (Development)https://liambll.github.io/blog/portfolio/06_grape_sugar/
Built a multispectral imaging prototype and machine learning models to predict grape sugar content based on multispectral reflectance.
- Plant Traits Estimation with 3D Imaging (Development)https://liambll.github.io/blog/portfolio/04_plant_3D/
Collaborated with the robotics team to build a 3D imaging prototype and implement an image processing pipeline to perform 3D reconstruction of plants and calculate leaf count and angles.
- Drug Efficacy Prediction (Development)https://liambll.github.io/blog/portfolio/07_drug_discovery/
Built a chemo-informatics pipeline to extract 1D, 2D, and 3D molecular descriptors of chemical molecules and predict their efficacy against certain diseases in plants.
- Fall Detection with Signal Processing (Development)https://liambll.github.io/blog/portfolio/08_fall_detection/
Implemented signal processing algorithms and built machine learning models to detect when an elder falls based on biomedical signal data collected from wearable sensors.
- Skin Lesion Classification (Development)https://liambll.github.io/blog/portfolio/10_skin_lesion_classification/
Implemented a prorotype to demonstrate the use of Computer Vision and Machine Learning to assist diagnosis by classifying whether a skin lesion is malignant vs benign.
- Clinical Text Extraction (Development)https://liambll.github.io/blog/portfolio/12_clinical_text_extraction/
Implemented a prorotype to demonstrate the use of Natural Language Processing to extract relevant clinical information from clinical text.
Skills
Libraries/APIs
Keras, TensorFlow, Scikit-learn, OpenCVOther
Computer Vision, Machine Learning, Deep Learning, Image Processing, Statistics, Big Data, Statistical AnalysisLanguages
Python, Java, SQL, ScalaFrameworks
Spark, Flask, HadoopTools
Scikit-image, TableauPlatforms
Linux, Windows, Amazon Web Services (AWS), QlikViewStorage
MySQL, PostgreSQL, Cassandra, MongoDB
Education
- Master's degree in Computer Science (Big Data, Machine Learning)2016 - 2017Simon Fraser University - Canada
- Master's degree in Technology Management2012 - 2013National University of Singapore - Singapore
- Bachelor's degree in Computer Science, Business Analytics (Dual degree)2008 - 2012Nanyang Technological University - Singapore
Certifications
- HIPPA Business Associate II (Non-Clinical) v11MAY 2017 - PRESENTLitmos
- Certified Analytics Professional (CAP)MAY 2017 - MAY 2020Institute for Operations Research and the Management Sciences
- SAP Certified Business Associate with SAP ERP 6.0APRIL 2010 - PRESENTSAP
