Smart City
Reprogrammability Everywhere
AS013 »
FPGAs at the edge enable computationally intensive workloads to be performed with lower latency and lower total energy cost. They also enable custom functionality to be readily swapped and implemented. However, at the moment, FPGA configuration and deployment is not a very smooth and enjoyable as it could be. Compared to deploying a web application, generating and flashing an FPGA bitstream is manually intensive and hard to scale.
Using technologies like Azure IoT for device registration and enrolment, Azure Blob Storage for storing bitstreams, paired with a local Azure IoT client on the cloud connectivity kit and the Remote Update Intel FPGA IP, we will aim to develop a scalable, efficient, and easy-to-use "one click" bitstream deployment solution. With this we hope to enable the pervasive use of FPGAs in IoT deployments, with particular focus on smart cities.
In terms of demonstration, we will build a smart city proof of concept, to show that configuration and deployment of FPGA boards for traffic data collection (as one configuration), and weather and air conditions (as another configuration) can be robust (the system can support many deployments) and targeted (we can select individual boards).
Food Related
TerraMon: Climate Change and Soil Health monitoring
AS014 »
Research has shown that climate change impacts soil PH but long term studies have been challenging to conduct at large scales. Terra-Mon hopes to leverage power efficient edge computing, analog device sensors and the cloud to create a solution that can be deployed in remote regions and relay data back via satellite (SWARM), long range low bandwidth (LORAWAN) terrestrial links as well as faster urban links (WIFI or Cellular) to monitor soil quality. Terra-Mon measures soil PH, moisture and temperature. Once the data is measured, the data is preprocessed at the edge to make sure the data stream is as compact as possible.
A neutral PH of 5.5 to 7.5 is ideal for growing food. Food security over time will be impacted by climate change as USDA zones change and the need to amend soils changes from our standard operational model. Researchers need to start gathering a healthy time series dataset today to create appropriate models for changes in soil health. For Farmers & Hobbyists can use Terra-Mon to monitor real time properties and see the how various soil products impact soil health and yields.
InnovateFPGA allows us to leverage the combination of Intel’s edge compute capabilities, Analog Devices daughter boards and the power of Azure’s IoT stack to create a solution that can be used to gather data that will allow for a comprehensive understanding of soil health and ultimately understand how to improve soil quality for improved harvests and food security.
Food Related
Dregs Reloaded
AS015 »
Good food is the foundation of genuine happiness.But once discarded, its also the source
of 8-10% of greenhouse gas emissions of our earth. According to the latest UNEP (United Nations Environmnet Programme)
food waste index report, the true scale of food waste and the opprotunities related to it largely untapped and under-exploited.
In US restaurants alone,about 33 billion pounds of food is wasted each year. If these discarded food is
collected in an inhouse reservoir, it could be reused to power up via biogas and the produce manure to grow
in-house vegetables.
The Dregs Reloaded project involves setting up an external reservoir/tank outside a restaurant or home
which is used to collect food waste. The tank includes a pulverizing and churning motor which is activated at regular intervals to accelerate the
decomosping process. It also monitors temperature, biogas, food level etc, which could be analyzed making use of cloud storage
and computing. The biogas generated from the tank could be used for restaurant cooking. The decomposed food
waste can be collected and used as fertilizer. Temperature,light & gas sensors can be monitored and analyzed , so that the entire system/feedback controls can be used efficiently.
Marine Related
Waterway cleanup
AS017 »
Using AI to recognize plastic or other waste present in waterways. The location will be recorded and information on the identified waste will be transmitted to a clean up crew.
Food Related
Dregs Reloaded
AS021 »
Good food is the foundation of genuine happiness. But once discarded, its also the source of 8-10% of greenhouse gas emissions of our earth. According to the latest UNEP (United Nations Environment Program ) food waste index report, the true scale of food waste and the opportunities related to it, is largely untapped and under-exploited.
In US restaurants alone, about 33 billion pounds of food is wasted each year. If these discarded food is collected in an inhouse reservoir, it could be reused to power up via biogas and the produce manure to grow in-house vegetables.
The Dregs Reloaded project involves setting up two external reservoirs/tanks outside a restaurant/home/community
which is used to collect organic food waste. The tank includes a pulverizing and churning motor which is activated at regular intervals to accelerate the decomposing process. It also monitors and collects data related to temperature, biogas, food level etc.,
which could be analyzed making use of cloud storage and computing. The biogas generated from the tank could be used for cooking or heating. The decomposed food waste can be collected and used as fertilizer. With the help of dual reservoirs, when one gets filled and being decomposed, the other one
can be opened up/enabled for the next collection of food waste.
Most people favor steps to reduce climate impact related to human behavior. Projects like Dregs Reloaded provide a way for every human being to be part of the problem solving method for a sustainable green earth.
Smart City
Energy Waste Monitoring In The Home
AS022 »
Historical, realtime, and predictive measurement of the energy usage and waste within a home given acceptable ranges of temperature, lighting, etc. and correlating with the presence of, movement of, and absence of people and their respective needs for the environmental elements that draws power, uses resources, etc. From this, can determine the level of energy/resource efficiency of a given household. Can then be expanded to community, city, county, etc. scales.
Smart City
Energy efficient mixed-precision algorithm optimization for edge applications
AS024 »
Embedded intelligence applications must optimize the energy efficiency of their computational differentiation. IEEE-754 floating-point has been the workhorse for robust numerical computing, but is notoriously energy inefficient. Next-generation arithmetic solutions, such as posits and cfloats combined with user-defined rounding have demonstrated a 2-4x power benefit over IEEE-754. We have developed a mixed-precision algorithm design and optimization environment to deliver this technology to the marketplace in the form of custom applications and hardware accelerators. We'll use this platform for key SmartCity application such as collective intelligence and congestion optimization.
Smart City
Smart City Traffic Analyzer
AS027 »
A small form factor device for analyzing vehicle and pedestrian traffic using a computer vision workload running on the DE-10 Nano with local sensor data provided by the Analog Device plug-in board. The computer vision workload will be delivered using Azure IoT Edge and allow for extrapolating analytics to the cloud.
Smart City
Solar Follower
AS028 »
A sensor based solar farm that can be installed on top of a house.
Health
Musconnect
AS029 »
Neuromuscular diseases are one of the most common and yet hardest to diagnose anomalies. Most neuromuscular diseases are diagnosed at a very late stage where no cure can help the patient.
But what if this can change? The goal of Musconnect is to monitor almost 100 muscles in a patient simultaneously and in real-time. This mass of data is gathered over a period of time using microelectrodes that are connected to a patient. The electrodes data is transmitted to the FPGA, processed using the MCU and uploaded and stored in Azure. Using data analysis, the device will be able to predict any deterioration in muscle activities far before any doctor or patient can realize.
Moreover, Due to the ability of the device to monitor 100 major muscles across a patient’s body, the diagnostic will be able to pinpoint the exact location of the muscle abnormalities.A doctor can then decide the best treatment option rather than going through several expensive and inaccurate scans.
Since muscle activities are saved on the cloud, a patient/doctor will be able to monitor improvements in the treatments by comparing muscle contractions before and after diagnosis.
This is a major step in the medical field that will help millions of people around the world with a high degree of accuracy.
Other: Monitoring fire in rural areas
Fangorn
AS031 »
Fangorn project aims to develop a drone surveillance system to detect and monitor outbreaks of forest fires.A camera with an infrared sensor and some sensors (temperature, smoke, pressure) will be used to monitor and capture important data, which will be used in conjunction with computer vision techniques and the power of FPGA multiprocessing to classify whether or not there is a focus of fire in the area.
Smart City
Fast Image Deblurring Reconstruction using Generative Adversarial Networks
AS032 »
Deblurring is the process of removing blurring entities from the image. In recent times, with the advent of machine learning there has been tremendous effort from the research community to come up with new deblurring techniques. However, the state-of-the-art deblurring technique still takes hours of time to construct proper deblurring effect. Therefore, in this project the objective is to construct proper deblurring image instantly. In order to accomplish that we will be using Generative Adversarial Networks (GAN). We have come up with a solution to speedup the GAN training. We will be deploying our solution into the cloud connectivity kit and also make use of Microsoft Azure, in order to generate accelerated deblurring image reconstruction.
Our project will have multiple applications starting from Smart City, Autonomous Vehicles, Industrial etc, as it involves creating proper visible images from blurring entities.