Smart City
Converter management system connected to the cloud (COMASYC)
AS009 »
Energy is a priority for humanity, in that sense, green energies are a necessity to satisfy the energy shortage and preserve the environment. So electronic converters play a key role.
A converter management system connected to the cloud controlled by a FPGA is proposed for applications in industry 4.0. It has capabilities to integrate panels solar arrays (PVs), batteries, loads at the same time with different converters according to user requirements. That means that the proposed system manages modulation, algorithms, collect information, and distribute energy.
For example, if the user requires a PV, then the P&O MPPPT algorithm is implemented to obtain the maximum energy in the PVs.
On the other hand, parameters such as energy consumption and production of each node are important for the redistribution of energy, for this reason, this model has a single brain that is connected to each node. So, a novel control is proposed based on load balancing managed by the cloud for high-priority requests. The cloud is the single brain that controls the system and organizes the flow power among nodes. The project is focused on the Peruvian reality for places where energy has to be a priority.
Smart City
Innova Qhawaq
AS012 »
Our project has as its main concept, the maximum use of energy through the efficient obtaining of renewable sources within the home, from photovoltaic energy through solar panels that move intelligently through neural networks that seek the maximum use of sunlight, harvesting energy obtained from strategic places such as doors, windows and the floor; and wind energy obtained efficiently through artificial intelligence and adapted to the environment. Through the use of the D10-nano FPGA as a data processing center where the information obtained from the sensors of these energy sources sends signals to actuators so that the energy is obtained more efficiently through the exact orientation where it is collected. as much energy as possible, making the fpga work as a decision-making center to control these actuators, and also by using data storage intelligently in the cloud, neural networks will be used to optimize energy collection from sources and optimize the use of resources.
Smart City
Coprocessor-based Antivirus in Order to Detect Malware Preventively
AS025 »
Distinct metamodels of Smart Cities have been developed in order to solve the problems of cities in relation to different socioeconomic indicators. In view of the foregoing, information security plays an important role in guaranteeing human rights in contemporary society. From an infection by malware (malicious + software), a person or institution can suffer irrecoverable losses. As for a person, bank passwords, social networks, intimate photos or videos can be shared across the world wide web, which will affect finances, dignity and mental health. On the other side, an institution may have its vital data inaccessible and/or information from its respective customers and employees stolen. In synthesis, the theft of intimate information can lead to cases of depression, suicide and other mental disorders.
The proposed work investigates 86 commercial antiviruses. About 17% of the antiviruses did not recognize the existence of the malicious samples analyzed. Commercial antiviruses, which, even with billionaire revenue, have low effectiveness and have been criticized by incident researchers for more than a decade. Commercial antiviruses performance is based on signatures when the suspect executable is compared to a blacklist made from previous reports (and this requires that there have already had victims). Blacklists are assumed to be effectively null by the current worldwide rate of creation of virtual pests, that is 8 (eight) new malwares per second. We concluded that malwares have the ability to deceive antiviruses and other cyber-surveillance mechanisms
In order to overcome the limitations of commercial antiviruses, this project creates a core processor-based antivirus able to identify the modus operandi of a malware application before it is even executed by the user. So, our goal is to propose an antivirus, endowed with artificial intelligence, able to identify malwares through models based on fast training and high-performance neural networks. Our core processor-based antivirus is equipped with an authorial Extreme Learning Machine.
Our processor achieves an average accuracy of 99.80% in the discrimination between benign and malware executables. Preliminary results indicate that the authorial Coprocessor, built on FPGA, can speed up the response time of the proposed antivirus by about 4765 times compared to the CPU implementation employing the same FPGA. Thus, the malicious intent of the malware is preemptively detected even when executed on a slow (low processing power) device. Our antivirus enables high performance, large capacity of parallelism, and simple, low-power architecture with low power consumption. We concluded that our solution assists the main requirements for the proper operation and confection of an antivirus in hardware.
Smart City
Smart Trashcan
AS034 »
The practice of recycling helps reduce pollution, greenhouse gas emissions, and the amount of waste that is disposed in landfills. The majority of Americans unfortunately does not embrace the three Rs (reduce, reuse, recycle). The lack of adequate knowledge for sorting and recycling materials is one of the biggest barriers to being green. Recycling is a behavior that can be improved through technology. This proposed project is centered around the creation of a smart trash can prototype designed to create awareness among students at Queens University and in its neighboring community on the importance of correctly sorting waste items. The smart-trash can has both a hardware and a software component. The project will specifically focused on developing a working prototype and deep learning (DL) model using the Intel FPGA Cloud Connectivity kit in combination with Microsoft Azure IOT. The model is able to correctly classify different types of disposable and recyclable food service items (paper cups, paper boxes, paper trays, food containers, etc.) commonly found in the Queens University’s cafeteria and around campus. The classification is used by the hardware to provide a visual prompt to indicate the bin for a particular waste item. This can lead to improving the process of pre-sorting recyclable materials once the smart trash can is fully deployed on campus.
Smart City
Blending Tech with TEK
AS047 »
As we move forward into a post-climate-change future, temperature regulation proves to be increasingly important for human survival and comfort, which makes up a significant portion of a building’s energy consumption. As such, our project focuses on improving the energy efficiency of temperature regulation in buildings through the use of Traditional Ecological Knowledge and smart-home design (with the help of the Azure cloud).
Ventilation, cooling, and heating account for 33% of energy use in U.S. commercial buildings, which relies upon conventional systems of cooling down air via refrigerants and pushing the air into rooms. However, there are different methods of cooling that utilize more passive properties of airflow. The Eastgate Centre in Zimbabwe is the biggest example of this.
The Eastgate Centre was designed with biomimicry in mind, to emulate the ability of termites to cool down and ventilate their nests while using less energy than conventional systems. It succeeds in this: despite still using high-powered fans, the Eastgate Centre uses only 10% of the energy compared to similarly-sized buildings using air conditioning, and uses 65% of the energy while actively cooling.
However, the Eastgate Centre’s design leaves some room for improvement, such as the usage of fans. Termites are able to do what they do by selectively opening and closing vents in the nest to maximize the flow of cool air. Our project improves upon the Eastgate design by more closely imitating the termite model and utilizing an FPGA-run system that uses actuator-operated windows to control airflow and further reduce energy consumption. It can accomplish this by sensing the temperature outside and inside of the building at the actuator locations, and opening and closing the windows accordingly. By opening the windows when it is cooler outside, the building takes advantage of cross-ventilation to passively draw in cool air without the use of fans. It will not be the same temperature on every side of the building; thus, the system opens the windows only at the specific sensor, and keeps it closed on the hotter sides.
An additional problem with both conventional AC and with the Eastgate Centre design is that they are reactive rather than predictive systems. Our design connects to the Azure cloud to obtain weather forecasts, which it then uses to pre-cool the building. This not only means the cooling system doesn’t work as hard during a specific period of time, but this also helps reduce energy use during an electric grid’s peak hours. It is also easier for the system to cool the building while it is still relatively cool than to do so when it has already become hot.
Overall, our system improves upon previous designs to reduce energy consumption when cooling buildings in three ways: by utilizing passive cross-ventilation as a cooling method, by taking into account the weather forecast, and by using the FPGA to monitor and manage all of these components together. By using an embedded system (the FPGA and the cloud) we are able to create a more proactive and energy efficient system than conventional AC systems.
Smart City
FPGA Catalyst
AS006 »
Not yet determined
Smart City
Project Watchdog
AS008 »
Project Watchdog is an FPGA-based smart home security camera. Existing solutions such as Google Nest and Amazon Ring require an internet connection and a monthly subscription to operate properly. They send the video to an external server and then perform all processing on that server, increasing bandwidth and latency. Furthermore, these devices are rendered useless without an internet connection. Watchdog will perform all video capture and analysis right on the device, regardless of an internet connection. The device will run inference using an AI model that has been trained to identify people and animals. When any people or animals are detected, that snippet will be uploaded to Azure cloud storage, for easy online access to these clips. The video footage will be stored on a micro-SD card on the FPGA board, which can be accessed if the full video needs to be viewed. Ultimately, Watchdog will perform identically to the state-of-the-art consumer solutions, but will use significantly less bandwidth and latency while not requiring an internet connection. The FPGA solution will be paired with a temperature sensor to provide a complete picture of the environment to the user.
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).
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.