Comment

LexiconMD Saves Money and Increases Revenue for National Senior Care Provider

This post is syndicated from Senior Housing News, and was written by Tim Mullaney, an Editor at Aging Media Network.

After being approached earlier this year by LexiconAI CEO Matt Rubashkin, Juniper Communities CEO Lynne Katzmann decided to pilot LexiconMD. She believed that the software might help reduce time spent on documentation at her 22 senior living communities by letting caregivers dictate their notes rather than type them.

Juniper saw this play out in October, the very first full month that LexiconAI was implemented. Though the trial has been brief and involved just nine clinicians, the numbers have been striking.

On average, users have been saving 25 minutes a day on documentation time, according to data gathered by Juniper and LexiconAI. However, this varies quite a bit depending on how much time users were initially spending on documentation—one person was spending more than four hours a day on documentation and now has shaved off more than 30 minutes...

Click here to continue reading

Comment

Comment

TensorFlow RNN Tutorial

Matthew Rubashkin is the CEO of LexicionAI, and was previously a Data Engineer at SVDS. This post is syndicated from Silicon Valley Data Science’s (SVDS) Deep Learning R&D Team. You can find the tutorial code here.

We have investigated Recurrent Neural Networks (RNN) for exploring time series and developing speech recognition capabilities. Many products today rely on deep neural networks that implement recurrent layers, including products made by companies like GoogleBaidu, and Amazon.

However, when developing our own RNN pipelines, we did not find many simple and straightforward examples of using neural networks for sequence learning applications like speech recognition. Many examples were either powerful but quite complex, like the actively developed DeepSpeech project from Mozilla under Mozilla Public License, or were too simple and abstract to be used on real data.

In this post, we’ll provide a short tutorial for training a RNN for speech recognition; we’re including code snippets throughout, and you can find the accompanying GitHub repository here. The software we’re using is a mix of borrowed and inspired code from existing open source projects. Below is a video example of machine speech recognition on a 1906 Edison Phonograph advertisement. The video includes a running trace of sound amplitude, extracted spectrogram, and predicted text...

Click here to continue reading

Comment

Comment

TensorFlow Image Recognition on a Raspberry Pi

Matthew Rubashkin is the CEO of LexicionAI, and was previously a Data Engineer at SVDS. This post is syndicated from Silicon Valley Data Science’s (SVDS) Trainspotting series, a deep dive into the visual and audio detection components of the SVDS Caltrain project. You can find the introduction to the series here, and the code here.

 

SVDS has previously used real-time, publicly available data to improve Caltrain arrival predictions. However, the station-arrival time data from Caltrain was not reliable enough to make accurate predictions. Using a Raspberry PiCamera and USB microphone, we were able to detect trains, their speed, and their direction. When we set up a new Raspberry Pi in our Mountain View office, we ran into a big problem: the Pi was not only detecting Caltrains (true positive), but also detecting Union Pacific freight trains and the VTA light rail (false positive). In order to reliably detect Caltrain delays, we would have to reliably classify the different trains.

Traditional contextual image classification techniques would not suffice, as the Raspberry Pis were placed throughout the Caltrain system at different distances, heights, and orientations from the train tracks. We were also working on a short deadline, and did not have enough time to manually select patterns and features for every Raspberry Pi in our system...

Click here to continue reading

Click here to continue reading

Comment

Getting Started with Deep Learning: a review of available tools

Matthew Rubashkin is the CEO of LexicionAI, and was previously a Data Engineer at SVDS. This post is syndicated from Silicon Valley Data Science (SVDS).

Our R&D team has been investigating different deep learning technologies, from recognizing images of trains to speech recognition. We needed to build a pipeline for ingesting data, creating a model, and evaluating the model performance. However, when we researched what technologies were available, we could not find a concise summary document to reference for starting a new deep learning project...

Click here to continue reading