Cristiano Tapparello, research assistant professor of electrical and computer engineering, who also serves as the director of software engineering for the innovative UR Health Lab led by chemical engineering alumnus Dave Mitten ’88 ’92(MD), spent some long hours back in March helping the lab develop the chatbot technology now familiar to many of us as Dr. Chatbot, which enables the University to screen its employees daily for symptoms of COVID-19.

Initially devised to screen incoming calls to the Medical Center’s COVID-19 Hotline, the technology was then adapted to also screen essential Medical Center employees during the lock down. That iteration of Dr. Chatbot is now being extended to non-Medical Center employees and students as well.

The technology now has been further adapted so that citizens throughout our 13-county region can voluntarily respond daily to a brief questionnaire about whether they have symptoms, as part of the ROC Covid-19 project. This will be an important tool to help regional health officials quickly detect any uptick in cases — within individual zip code areas — as the region continues a phased reopening of businesses and other activities. Please consider participating in this daily screening as well; with enough participation, we lessen the chances of having to shut down the entire region again.

Cristiano, the front end designer for the interactive displays you see at these chatbot sites, has also been working with Mt. Hope Family Center research associate Christie Petrenko to create the first mobile phone app for caregivers of children with fetal alcohol spectrum disorders (FASD).

(From Hajim Highlights, published by the University of Rochester, 22 June 2020)

If you need to hold office hours in these days of distancing, and your on-line meeting service has a “waiting room” feature, then you can create a recurring meeting for your office hours and send the access information to your students. Then start the meeting and admit your students one at a time from the waiting room to the office hours meeting, waiting for each to leave before admitting the next.

This same tip could be used if your job requires you to consult with a large number of your colleagues and you need some time for your own work.

George Klimiashvili, a recent University of Rochester graduate, said,

“One of the proudest moments of my college career and my life in general was getting published in the IEEE conference as a first author.”

George is a recipient of The Charles L. Newton Prize, which recognizes engineering students who show a special proficiency in an engineering subject and have conducted research, given a presentation, or published a paper.

Here is the reference to George’s paper: G. Klimiashvili, C. Tapparello and W. Heinzelman, “LoRa vs. WiFi Ad Hoc: A Performance Analysis and Comparison,” 2020 International Conference on Computing, Networking and Communications (ICNC), Big Island, HI, USA, 2020, pp. 654-660, doi: 10.1109/ICNC47757.2020.9049724.

Congratulations to Greg Gdowski, IEEE Region 1 Vice Chair, Director-Elect, and past Rochester Section Chair, on his selection to be a Fellow of the Association for the Advancement of Medical Instrumentation (AAMI).

2020 AAMI Fellows Honored for Achievements, Commitment to AAMI Mission

The Rochester Signal Processing Society hosted a virtual zoom session on Thurs, April 30^th entitled “Fast Deep Learning Prototypes with Tensorflow and Keras Tutorial”, by RIT PhD student Miguel Dominguez. 63 people registered for this hour-long session which included the distribution of iPython notebook sample code and deep learning software installation instructions. This tutorial was very well attended, in spite of being held, non-traditionally, via Zoom.

Deep Neural Networks (DNN) are a powerful tool for computer vision, signal processing, and natural language processing tasks. The last few years have seen the development of a plethora of software tools for the development of DNNs. This tutorial discussed using Tensorflow 2.0 with the Keras API to enable rapid prototyping of DNNs with a minimum of code. All software is free open-source code. The tutorial demonstrated how to get several variants of Convolutional Networks up and running, for training, prediction, and logging.

Miguel Dominguez is a PhD candidate in Engineering at Rochester Institute of Technology, set to graduate in the summer of 2020. His research interests include graph and point cloud neural networks as well as speech processing.

The TensorBoard dashboard pictured here shows the performance of models as they are being trained.