A Ph.D. in Applied AI and a former oil and gas engineer with 4+ years of experience using predictive modeling, data processing, data visualization, machine learning algorithms, and computer vision techniques to solve challenging business problems.
I did three years of AI research and development to create a more efficient business workflow in the oil and gas industry. Having delivered one of the top AI research in the oil and gas operations, I co-founded startup retail, bringing AI to create unmanned stores by utilizing deep learning and computer vision techniques. I also helped to improve the engineering process workflow by using computer vision and deep learning technologies. Currently working for a Japanese IT consultancy company, taking on projects to help various companies implementing machine learning to improve their business.
I have worn many hats in my career--programmer, engineer, analyst, scientist, researcher, manager, marketer and strategist. As a result, I have a unique ability to manage multi-disciplinary projects and able to navigate complex challenges. The ability to talk from the most technical discussion to the highest level of business negotiation is the capability that I am proud of.
Responsible for the development and implementation of machine learning systems for various clients.
Programming languages: Python
Frameworks: TensorFlow, PyTorch, OpenCV, Scikit-Learn
Built document digitization system for engineering drawings (e.g., piping and instrumentation diagram, isometric drawings, etc.) by utilizing computer vision techniques.
Built automated corrosion loop generator for creating more efficient inspection management program.
Programming languages: Python, Javascript
Frameworks: TensorFlow, PyTorch, OpenCV, React, NodeJS, Scikit-Learn
Responsible for the development and implementation of AI products.
Built GetGO Bar, a mini unmanned store, powered by AI and computer vision technologies. We have deployed GetGO Bar to seven different locations. To enable automation, we use a camera and edge-computing to track hand movement and location inside the bar.
Built visual search engine for fashion products. This engine enables customers to search the products they want in e-commerce by uploading their images. The engine will retrieve products with the most similarity to the uploaded images.
Built recommendation engine for fashion products. This engine creates recommendations tailored to every person, and showcase the most relevant items throughout the buyer shopping journey.
GetGO was selected as one of the top 10 direct-to-consumers startups selected in Gojek Xcelerate Batch 4. GetGO was also selected as one of the top startups in GK-Plug & Play Indonesia Accelerator Program Batch 6.
Programming languages: Python, C++, Javascript
Frameworks: TensorFlow, PyTorch, OpenCV, Mediapipe, Flask, React, NodeJS
Performed state-of-the-art analysis for building vehicle detection and classification and face recognition system.
Performed research for deploying edge-computing to the existing technology stack.
Created AI development framework to standardize AI development pipeline in the company.
Programming languages: Python
Frameworks: Scikit-Learn, NumPy, Pandas, TensorFlow, OpenCV, DarkNet
Performed research on the application of AI to improve the effectiveness and efficiency of oil and gas operations.
Utilized machine learning to build predictive models for improving the effectiveness and efficiency of risk-based assessment process.
Published 11 AI-related scientific papers in international journals and conferences.
Programming languages: Python
Frameworks: Scikit-Learn, NumPy, Pandas, TensorFlow, OpenCV
Developed the foundation and framework of technical asset integrity management practices in the organization.
Developed integrity management plan for technical assets.
Developed standard operating procedures for corrosion management. Developed facility integrity database for pressure systems, pipelines, and offshore structures.
Performed and supervised risk-based inspection assessment.
Dissertation title: Artificial Intelligence Approaches to Lean Risk-Based Inspection Assessment. Best Student Paper in 28th International Offshore and Polar Engineering Conference Jul 2018: Artificial Neural Network Model for Risk-Based Inspection Screening Assessment of Oil and Gas Production System.
GPA 3.83/4.00. Key courses include operations and maintenance management, cost engineering and economics, diagnostic and prognostic engineering, safety and risk management, industrial services, decision engineering and performance management.
GPA 3.64/4.00, 2nd Best Student. Material science and engineering program provides knowledge and insights about the materials commonly used in the industry, e.g. metals, ceramics, polymers, and composites. Key courses include material selection, corrosion and its mitigation, welding and manufacturing techniques.
In this project, we use computer vision and deep learning technology to enable automatic detection and recognition of symbols and text from piping & instrumentation (P&ID) and other engineering diagrams. This method is able to label any symbols in tens of drawings in minutes and export the results in Excel or CSV format. The text recognition feature enables the search feature to rapidly find text in drawings.
View ProjectThe fashion visual search turns customer's inspiration into product discovery by removing the barriers of textual search, using AI to understand the context of images and return a list of related results. It consists of three components. First, it detects and classifies clothing items in the image. It uses Mask R-CNN to do this task. Second, it extracts high-level features and representation of detected clothing items using ResNet architecture. Third, the generated features are compared to the database of features (i.e. database of clothing images) for retrieval.
View ProjectUsing deep learning to classify grocery products can be overwhelming, considering the variety of the products and the amount of data needed to train the alogorithm. This project uses OpenCV's feature detection and description (e.g. SHITOMASI, HARRIS, FAST, ORB, BRIEF, FREAK, AKAZE, SIFT, BRISK) to perform classification of grocery products. Using this system, a product image is enough as a reference to recognize the product. The product packaging shall be distinct in order for the system to perform correct classification.
View ProjectThis system is the first iteration used for identifying the direction and location of hand that goes in and out GetGO Bar. This system is one of the components that construct automated transaction system that have the function to recognize customer activities during the transaction with GetGO Bar. This system utilizes two downward-looking cameras that produce video streaming during a transaction. To identify hand direction, we use the Gunnar-Farneback optical flow. To identify the location of the hand (in which shelf the hand is located), we use background subtraction method.
View ProjectThis software implements the paper "Corrosion loop development of oil and gas piping system based on machine learning and group technology method" (see the paper here). The aim is to develop an automated corrosion loop development system based on k-means clustering and group technology method. This system is expected to reduce the man-hours required develop corrosion loops.
View ProjectA computer vision algorithm to detect lane boundaries in a video. This project uses camera calibration, perspective transformation, gradient and color thresholding, and curve fitting to identify road lane boundaries and its radius of curvatures from a stream of videos.
View ProjectThis project develops car collision avoidance system by using Lidar measurements and images from camera. First, we develop a way to match 3D objects over time by using keypoint correspondences. Then, we calculate Compute Time-To-Collision (TTC) based on Lidar measurements. We then proceed to do the same using the camera, which requires to first associate keypoint matches to regions of interest and then to compute the TTC based on those matches.
View ProjectMotion heatmap is useful to see movement patterns over time. For example, it could be used to see the usage of entrances to a factory floor over time, or patterns of shoppers in a store. The application applies background subtraction to create a mask. A threshold is then applied to the mask to remove small amounts of movement, and to set the accumulation value for each iteration. The result of the threshold is added to an accumulation image, which is what records the motion. At the very end, a color map is applied to the accumulated image so it's easier to see the motion. This colored imaged is then combined to accomplish the overlay.
View ProjectSee the certificate here. List of projects:
See the certificate here. List of projects:
See the certificate here. List of projects: