Search
Now showing items 1-10 of 35
Improving clinical risk-stratification tools : instance-transfer for selecting relevant training data
(Massachusetts Institute of Technology, 2014)
One of the primary problems in constructing risk-stratification models for medical applications is that the data are often noisy, incomplete, and suffer from high class-imbalance. This problem becomes more severe when the ...
Approximate k-means clustering through random projections
(Massachusetts Institute of Technology, 2015)
Using random row projections, we show how to approximate a data matrix A with a much smaller sketch à that can be used to solve a general class of constrained k-rank approximation problems to within (1 + [epsilon]) error. ...
Modeling temporally-regulated effects on distributions
(Massachusetts Institute of Technology, 2015)
We present a nonparametric framework for modeling an evolving sequence of (estimated) probability distributions which distinguishes the effects of sequential progression on the observed distribution from extraneous sources ...
Learning articulated motions from visual demonstration
(Massachusetts Institute of Technology, 2014)
Robots operating autonomously in household environments must be capable of interacting with articulated objects on a daily basis. They should be able to infer each object's underlying kinematic linkages purely by observing ...
LEARNSTEM : an interactive and intuitive STEM accessibility system
(Massachusetts Institute of Technology, 2015)
I present an intuitive and interactive platform to make complex STEM (Science Technology Engineering and Mathematics) educational materials accessible to blind and visually impaired people using a mini-hyper-Braille device ...
Simulation of a novel multiprocessor system based on dataflow principles
(Massachusetts Institute of Technology, 2016)
This thesis research is a study of a novel processor architecture for a massively parallel computer system. An existing simulation of the Fresh Breeze architecture has been extended to incorporate a multi-level memory ...
Discrimination of alcoholics from non-alcoholics using supervised learning on resting EEG
(Massachusetts Institute of Technology, 2014)
Alcoholism is a widespread problem that can have serious medical consequences. Alcoholism screening tests are used to identify patients who are at risk for complications from alcohol abuse, but accurate diagnosis of alcohol ...
Wearable-assisted social interaction as assistive technology for the blind
(Massachusetts Institute of Technology, 2014)
This work presents an end-to-end wearable system designed to learn and assist its (potentially blind) wearers with daily social interactions. In particular, it visually identifies nearby acquaintances and provides timely, ...
Learning precise partial semantic mappings via linear algebra
(Massachusetts Institute of Technology, 2016)
In natural language interfaces, having high precision, i.e., abstaining when the system is unsure, is critical for good user experience. However, most NLP systems are trained to maximize accuracy with precision as an ...
BlueCache : a scalable distributed flash-based key-value store
(Massachusetts Institute of Technology, 2016)
Low-latency and high-bandwidth access to a large amount of data is a key requirement for many web applications in data centers. To satisfy such a requirement, a distributed inmemory key-value store (KVS), such as memcached ...