Search
Now showing items 1-10 of 38
Capturing the human figure through a wall
(Massachusetts Institute of Technology, 2017)
We present RF-Capture, a system that captures the human figure - i.e., a coarse skeleton - through a wall. RF-Capture tracks the 3D positions of a person's limbs and body parts even when the person is fully occluded from ...
Morphological segmentation : an unsupervised method and application to Keyword Spotting
(Massachusetts Institute of Technology, 2014)
The contributions of this thesis are twofold. First, we present a new unsupervised algorithm for morphological segmentation that utilizes pseudo-semantic information, in addition to orthographic cues. We make use of the ...
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 ...
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 ...
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 ...
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 ...
DGCNN : learning point cloud representations by dynamic graph CNN
(Massachusetts Institute of Technology, 2020)
Point clouds provide a flexible geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices. While hand-designed features on point ...
High fidelity medical image-to-image translation
(Massachusetts Institute of Technology, 2020)
Despite much recent progress in image-to-image translation, it remains challenging to apply such techniques to medical images. We develop a novel parameterization of conditional generative adversarial networks that achieves ...
Adaptive Neural Signal Detection for Massive MIMO
(Massachusetts Institute of Technology, 2019)
Massive Multiple-Input Multiple-Output (MIMO) is a key enabler for fifth generation (5G) cellular communication systems. Massive MIMO gives rise to challenging signal detection problems for which traditional detectors are ...
A software pipeline for converting 3D models into 3D breadboards
(Massachusetts Institute of Technology, 2019)
3D breadboards are a new form of physical prototypes with breadboard functions directly integrated into its surfaces. 3D breadboards offer both the flexibility and re-configurability of breadboards, while also integrating ...