A5060700137- Conservation, Biodiversity, and Resource Management
- Oil Palm Production and Sustainability
- Advanced Bandit Algorithms Research
- Data Stream Mining Techniques
- Remote Sensing and LiDAR Applications
- Machine Learning and Data Classification
- Advanced Vision and Imaging
- Remote Sensing in Agriculture
- Optical measurement and interference techniques
- Industrial Vision Systems and Defect Detection
- Remote-Sensing Image Classification
Stanford University
2020-2024
Harvard University Press
2023
Characterizing the processes leading to deforestation is critical development and implementation of targeted forest conservation management policies. In this work, we develop a deep learning model called ForestNet classify drivers primary loss in Indonesia, country with one highest rates world. Using satellite imagery, identifies direct patches any size. We curate dataset Landsat 8 images known events paired driver annotations from expert interpreters. use train validate models demonstrate...
While the use of programming problems on exams is a common form summative assessment in CS courses, grading such exam can be difficult and inconsistent process. Through an analysis historical patterns we show that inaccurate free-response widespread CS1 courses. These inconsistencies necessitate development methods to ensure more fairer accurate grading. In subsequent this data demonstrate graders are able accurately assign score student submission when they have previously seen another...
In 2020, maternal mortality in India was estimated to be as high 130 deaths per 100K live births, nearly twice the UN's target. To improve health outcomes, non-profit ARMMAN sends automated voice messages expecting and new mothers across India. However, 38% of stop listening these calls, missing critical preventative care information. engagement, employs workers intervene by making service but can only call a fraction enrolled mothers. Partnering with ARMMAN, we model problem allocating...