Other: Smart city + food related
Smart garden
EM030 »
It is about how we have a good garden , how we have healthy food, and how we do them in smart manner .
Smart City
NDVI device for building building monitoring
EM031 »
We have developed a platform to measure and visualize Normal Difference Vegetation indices using a low cost Camera and a DE2 board. This device was tested on building facades showing building moisture that can be related to the inhabitant health. In a different project we have studied around 17000 buildings in Beirut to build and energy model, the simulation was run on Azure. In this proposal we try to merge the two concepts/techniques.
Autonomous Vehicles
Gesture Recognition Accelerator
EM032 »
Nowadays, the number of network-based devices (IoT
devices) has been increasing. They can be controlled by
other network-based smart devices such as smartphone,
personal computer or personal assistant robots, and so on.
These systems or devices should have user-friendly interface design. In this project, we propose easy-to-use and
intuitive user interface design for them. We employ gesture controlling UI.
Food Related
Albania: Smart and IoT solutions for agriculture and farming
EM033 »
Summary: Provide smart farming technologies and IoT for all type of greenhouses and farms.
Details: The project will consist in gathering greenhouses and/or farms sensors data into a central device that acts as an IoT gateway. Pest and Plant diseases data will be recorded to Azure storage and insight analysis using Machine Learning techniques will be used to classify the recorded diseases. An inference model will be generated and transmitted to the IoT Gateway (DE10-nano) for local and immediate determination of plants conditions to enable further control actions. The inference model will consist of neural networks parameters from which a neural network IP Core will be reconstructed in the FPGA portion of the cyclone V SoC device found in the DE10 board. The HPS side will handle the communication with the sensors and with the cloud, and the azure cli C libraries will be installed to enable the communication with azure cloud.
The project aims to minimize the time taken to manage the farm or greenhouse operations (data collection, analysis and insight, control actions) as well as to avoid the excessive use of chemicals.
Health
CO2 gas sensor for air quality monitoring
EM034 »
CO2 gas sensors are rapidly gaining interest as a low-cost tool, not only for monitoring air quality inside buildings but also to assess the risk of infection by airborne diseases such as COVID-19.
We will develop a prototype system using the DE10-Nano development kit that will be based on a custom RISC-V microcontroller for the processing of the signals coming from the CO2 sensor. The system will be able to measure the CO2 concentration in the range of 400-5000 ppm.
Food Related
Fpga based aquaponic food production integrated with computer vision
EM036 »
The project will create a smart aquaponics system that uses fpga for fast computation and integration. It will also be supported by computer vision.
Other: Biodiversity
Snow Leopard Detection
EM038 »
Design low-power heterogeneous neural network accelerator for CNN (Convolutional Neural Network) application to identify snow leopards. Internet-connected cameras will be used to collect photos of areas to detect if any snow leopard has passed through that area. These photos will be uploaded to Microsoft Azure Platform and then be processed on an FPGA using CNN.
Smart City
Package deliverance
EM039 »
This system proposes an update in packages deliverance system, improving how couriers deliver their packages optimising the time to deliver it and the number of packages delivered in a day.
Smart City
Fire Detection and Cryptography with FPGA
EM040 »
In response to forest fires, fires that are not noticed within the first 5 minutes and cannot be intervened in 15-20 minutes spread to large areas and become difficult to control. With the system, it is possible to detect forest fires at the initial stage and to inform the firefighting teams, then to respond to the fire immediately and prevent the progression of the fire. "Early" fire detection is possible by closely monitoring the blind spots in forests and habitats all over the world, where watchtowers cannot follow, and by monitoring critical changes in temperature in these areas. Fires, which cannot be detected early and therefore cannot be intervened immediately, cause the destruction of our forests, which take years or even centuries to grow, and impoverish our world in terms of green space. The system in question has been developed to find solutions to these problems.
Method; In the early warning system, using the mesh network topology, thermal cameras and sensors connected to wireless devices take measurements in the forest area, detecting a possible fire threat and informing the center immediately. By sending regular information to the central monitoring software of the devices, statistical information about the weather conditions of the forest area will also be provided. System; It is the most effective alternative to the existing methods such as human eye tracking, telephone notification, aircraft monitoring and camera monitoring, and the operating costs of the system are reduced thanks to the use of "wireless sensor network" technology in fire fighting.
Considering these, we will realize our project.
Smart City
Smart Driving
EM041 »
A system to reduce the consume of fuel driving in the city.
Industrial
SoC design for enhanced keyword spotting applications with eliminated resources
EM042 »
It is aimed to deploy a combined Machine Learning (ML) system based on both FPGA and HPS units of DE10-Nano platform that will be enhancing the capabilities of a keyword spotting (KWS) application. The KWS will be executing at HPS as a low power application targeting limited resources requirements. Together, the required peripherals, such as the microphone input will be handled. The design in the FPGA will be incorporating neural network (NN) models, responsible to enhance the quality of the speech signal by removing environmental noise. Hence, features extraction will be more accurate and the demands in KWS application can be eliminated to reach low power, low size implementation without compromising the performance of the detection.
Marine Related
A smart underwater microbial delivery system for coral reef habitat recovery
EM043 »
In this project, we propose the first underwater and deep-learning-enabled intelligent microbial delivery system for coral reef habitat recovery. The system will be able to deliver coral probiotics and monitor its efficacy. The delivery is precisely regulated by a deep learning network that monitors the color change of corals.