Dr. Hasan A. Arief - Research and Collaboration
Hasan A. Arief, a machine learning researcher with a complementary skillset in full-stack development and technical project management, is passionate about unlocking the transformative potential of Artificial Intelligence (AI). His interests span diverse fields, from energy and climate to healthcare. If your project aligns with these areas, reach out to explore collaboration!
Hasan brings a unique perspective to problem-solving by combining his expertise in both machine learning research and software development. This allows him to not only design and implement software architecture but also leverage his data science understanding to ensure solutions perfectly align with real-world needs. His adaptability and continuous learning ensure he stays current in these rapidly evolving fields and makes meaningful contributions through collaboration.
Hasan's current projects exemplify this drive. Within the NAIC (Norwegian Artificial Intelligence Cloud), he co-develops machine learning models utilizing high-performance computing to analyze climate data for teleconnection use cases. This involves identifying linkages between seemingly disparate climate phenomena across vast geographical distances. Additionally, he is involved in a project to detect water leakage in drinking pipes using fiber optic data, aiming to improve infrastructure efficiency and sustainability.
Hasan's academic journey has fueled his expertise. Early in his career, he explored how machine learning could be used to detect fraudulent transactions from large amounts of text data. During his PhD, he focused on strengthening his foundational skills in core machine learning concepts, particularly deep learning algorithms and point cloud classification techniques. This involved active participation in research projects that investigated how these techniques could improve and speed up the creation of high-accuracy annotation labels for large point cloud datasets. Notably, his doctoral work addressed a challenge relevant to the remote sensing and computer vision community: balancing the cost and accuracy of annotation in this domain. Traditionally, creating these labels has been a labor-intensive and expensive process. Hasan's research explored how deep learning-based techniques could bridge this gap by providing a faster and more cost-effective solution.
Postdoctoral appointments at NORCE and Northwestern University further broadened Hasan's skillset. He gained experience in creating advanced machine learning algorithms using fiber optic sensors, applying them to diverse areas like sensor data analysis for autonomous vehicles, fiber optic and distributed sensor data modeling, and climate index understanding. Additionally, his work on smart annotation tools for 3D point cloud data at Carnegie Mellon University demonstrates his commitment to building practical solutions across various machine learning domains.
Education
- Ph.D. in Applied Informatics (2020), Norwegian University of Life Sciences, Norway
- Master of Science in Informatics (2016), Bandung Institute of Technology, Indonesia
- Bachelor of Science in Computer Science (2011), Sepuluh Nopember Institute of Technology, Indonesia
Experience
- Research Scientist (2023-Present), NORCE, Norway
- Postdoctoral Researcher (2020-2023), NORCE, Norway and Northwestern University, USA
- Visiting Researcher (2019), Carnegie Mellon University, USA
- Ph.D. Candidate (2017-2020), Norwegian University of Life Sciences, Norway
- Lead Programmer (2014-2016), Bandung Institute of Technology, Indonesia
- Full Stack Developer (2011-2014), Indonesia
Research Expertise
- Deep learning modelling
- Point cloud classification
- Machine learning for sensor data (fiber optic, LiDAR)
- 3D point cloud data annotation
- Fraud detection techniques
- Software development
