Artificial Human Sensing
UC Berkeley Division of Computing, Data Science, and Society
Independent Researcher | July 2019 - Present
Many artificial intelligence innovations have been inspired by how the human mind and body work. Researchers have created Deep Neural Networks inspired by neurons, computer vision inspired by human vision, cochlear implants that translate sound waves to understandable sound by understanding the ear, and a machine olfactory systems to create an electronic nose. Building upon this, we can continue to understand other innovations that are artificial human senses.
Conducting independent research on the connections between the biological mechanical processes of the human senses and algorithmic processes that mimic these behaviors through artificial intelligence and machine learning. Understanding this can help develop new technology and/or create more efficient algorithms that are inspired by the cognitive processes. This interdisciplinary research connects cognitive science with artificial intelligence.
Language-Independent Automatic Phonetic Transcription
GSI: Emily Grabowski
UC Berkeley Department of Linguistics | D-Lab
Data Science Discovery Researcher | January 2020 - May 2020
Modern technology is not as effective in transcribing audio across multiple languages (especially indigenous ones). Therefore, we utilize Lingustic and Data Science tools to transcribe and understand audio data. Our dataset comes from the UCLA Production and Perception of Linguistic Voice Quality Project which contains audio data from languages (e.g. Bo, Zapotec, Mandarin, etc.) and TextGrid files with labels constants and vowels.
The goals of this project is to using clustering and other machine learning algorithms to answer linguistic questions about audio data. In addition, constructing an algorithm that can transcribe audio data using the International Phonetic Language (IPL) independent of language.
Sensor Fusion and Cross Sensitivity Analysis for Hazardous Potentials in
Sensor Tensegrity Robots
PI: Alice M. Agogino
Department of Mechanical Engineering | Squishy Robotics
Data Analyst Researcher | NSF LSAMP | June 2019 - August 2019
Squishy robots are rapidly deployable mobile sensing robots for disaster rescue, remote monitoring and space exploration. Our emergent technologies are at the fusion of robotics, mobile sensing, machine learning, big data fusion and smart IoT (Internet of Things).
Our first target market is the HazMat and CBRNE (Chemical, biological, radiological, nuclear and explosive) response market, enabling life-saving maneuvers and securing the safety of first responders by providing situational awareness and sensor data in uncharted terrain.
Creating an Intelligent Data Analytics UI Platform that utilizes data from tensegrity sensor robots, builds internal predictive models and provides real-time updates on potential hazards and actionable directives to First Responders.
More Information Here.
Medicare Fraud Detection in Epidemiology
PI: Scott Lee
UC Berkeley School of Public Health
Data Science Discovery Researcher | January 2019 - May 2019
MediCare is the national health care insurance program in the United States that offers quality health care service for Americans at the age of 65 or older. Unfortunately, healthcare costs are increasing due to a large detection of fraud, waste, or abuse. According to Florida Atlantic University, “about $19 billion to $65 billion is lost every year because of Medicare fraud, waste, or abuse.” In order to combat this, the Center for MediCare and Medicaid Services (CMS) have released a database report since 2012 for researchers to investigate and detect fraud.
Analyzing Big Data from the Center of Medicare and Medicaid Services Database with Dr. Scott Lee from the UC Berkeley's School of Public Health. The goal is to find innovative ways to understand clinical decision making in today's healthcare system. Utilizing machine learning to predict fraudulent activity in the field of Epidemiology.
UC Berkeley Division of Equity & Inclusion
Division of Equity & Inclusion | Cal NERDS
Data Analyst Researcher | November 2018 - May 2019
The University of California, Berkeley has demanded a need for a use of data analysis on equity gaps, campus climate, and STEM diversity programs. In addition, there is a need to review campus policies and practices that affect the initiative's goals and suggest revisions.
Therefore, in collaboration with the Division of Equity & Inclusion and as part of the STEM Equity and Inclusion Initiative, the Cal New Experiences for Research and Diversity in Science (NERDS) has given me the opportunity to work as a Data Science Researcher.
In my role, I analyze equity gaps across departments and professional programs on campus using the CalAnswers database and discussing solutions to assist underrepresented minorities in STEM.
Learn more about the STEM Equity and Inclusion Initiative Here.
More Information about Cal NERDS Here.