Industrial
FPGA controlled robot arm
EM028 »
The aim of this project is to build FPGA controlled robotic arm. The robot arm will have higher speed when it is compared to other robot arms which are controlled by the traditional ARM processors
Health
FPGA based Body Area Anomaly Detection System Design for Healthcare
AS036 »
Currently, wireless communication network applications are becoming part of our daily life that cannot be ignored. One of the most important is healthcare application. Physiological and health condition of a person can be detected, processed, transported, and stored easily in (wireless) body area network (W)(BAN). WBANs have several applications including in sports, interactive gaming, military, and security. For instance, aged people show larger dependence on the healthcare system because of age related diseases like cardiac ailments, respiratory problems, arthritis, neurological diseases, and dementia. According to World Health Organization (WHO), by 2047 people 60 and above will be 2 billion, up from 841 million in 2008. According to the US Bureau of the Census, in US alone elderly people are expected to 70 million by 2025, the healthcare expenditure is about $5.4 trillion, which will represent 20% of the GDP. Hence, smart and interactive wireless healthcare system can leverage both the health and economic issues of users.
The three-tier communication architecture of WBAN consists of, (i) BAN node: each node is integrated with biosensors (ECG, SpO2, temperature, etc.) to record patient’s dynamic body parameters and movements; (ii) LPU (Local Processing Unit): to gather data from BSNs and provide to the physicians. It also a router between BAN nodes and the central server using Bluetooth and Wi-Fi for short range and mobile networks for long-range transmission. (iii) back-end infrastructure: which consists of (a) CS (Central Sever), which feeds the patient data to the PD (Patient Database) and (b) Physician Workstation.
The challenges in WBAN are, reliable data transmission, node mobility support and fast event detection, timely delivery of data, power management, and security. Medical data networks are increasingly exposed to external attacks. Safety and privacy of medical data must be guaranteed all the way from the sensor nodes to the back-end services. On the other hand, energy efficiency issue exists at different sensor nodes, and communication and data processing subsystems.
This work focuses on developing a new FPGA based body area anomaly detection system using machine learning techniques by training the behavioral change of body area environment (i.e., indoor and outdoor). Because FPGA is an integrated circuit that contains a large resource of logic gates and memory, it is possible to implement parallel digital computation and executions. This leads to low latency and minimum energy consumption. Hence, we propose system on Chip (SoC) (i.e., Microcontroller Unit (MCU), Central Processing Unit (CPU), and FPGA) at both ends of WBAN system. It enables a wide range of healthcare applications such as ubiquitous health monitoring (UHM), computer assisted rehabilitation, emergency medical response system (EMRS), and promoting healthy living styles.
The objective of this work is to design an energy efficient and secure WBAN for pervasive healthcare system, which reduce patients visit to hospitals. Specifically, to transmit and store medical data securely keeping the privacy, authenticity, availability, and integrity of medical data at the three layers of the WBAN architecture, and to model a power efficient WBAN during data processing and transmission.
Food Related
Herbal plant recognition and monitoring
AP088 »
The project aims to recognize common herbal plant in the Philippine setting, both grown by gardeners and in the wild. Our project also aims to check the viability of the area for growing these herbs by monitoring how many are growing in the area/presence of clustering, plant part status such as checking leaf condition such as drooping and wilting, and presence and absence of invasive plants/animals that can affect the survival of the herb using computer vision. Other parameters such as humidity and sunlight will also be monitored using ADI boards provided. The data collected will be sent to Microsoft Azure platform where partner NGOs and stakeholders can view the data and insights generated to help make sound decisions that will benefit the community they're helping.
Marine Related
Biodiversity
AP092 »
I want to create an IoT based solution for the given SGP project Idea "Mauritius: improving Livelihoods of Communities- Oyster Farming for Jewelry Making in Rodrigues" which will collect all the problem statement mentioned data and share the data as well as specific high swell, theft warning through the azure cloud platform.
Smart City
Smart off sensor
AS037 »
To be able to determine with a higher likelihood when to be be able to turn off electronics, lights, set air conditioning higher and not to interrupt someone at home simultaneously.
Autonomous Vehicles
Autonomous Pick & Place Robot
AP095 »
The idea of this project is to create an autonomous pick and place robot. This robot will do its movement through line follower robot using IR sensors. The main function of this robot is to pick an object and place it on a desired place; it will select its destination through QR code scanning e.g. there’s a box at X place and a rack at Y place, the robot will scan the QR code of the box at X place. After scanning, next step will be the selection of placing the carried object; robot will select its dropping place after going through the program designed in it using Arduino. Now that our path and dropping place has been selected, object will be placed at Y place as the scanned box belongs to it.
Other
Crisis
AP096 »
One of the major issues that we are facing today is overpopulation which results in food crisis
Other: Warm homes and clean air for everyone.
Smokeless Chimney
AS041 »
There are 10 million existing wood stoves in the USA alone. Each wood stove is a gathering place and source of heat when the power goes out. People who use wood stove are a passionate group. We have 2 issued patents and one pending patent. We have developed the components to measure the opacity of the emitted smoke and control the combustion reaction to adjust for a cleaner burn. This will bring wood stoves into the 21st Century.
Autonomous Vehicles
Autonomous Pick & Place Robot
AP097 »
The idea of this project is to create an autonomous pick and place robot. This robot will do its movement through line follower robot using IR sensors. The main function of this robot is to pick an object and place it on a desired place, it will select its destination through QR code scanning e.g. there’s a box at X place and a rack at Y place, the robot will scan the QR code of the box at X place. After scanning, next step will be the selection of placing the carried object; robot will select its dropping place after going through the program designed in it using Arduino. Now that our path and dropping place has been selected, object will be placed at Y place as the scanned box belongs to it.
Smart City
Environmental Humidity Control System Based on RISC-V
PR040 »
Use Intel's FPGA development platform to design an intelligent environment adjustment system driven by a 32-bit RISC-V architecture processor. The system embeds the RISC-V soft core in the FPGA development platform, drives peripheral sensors, and realizes the shortest path optimization algorithm. Finally, it can control the mobile platform in a specific environment and realize the detection and adjustment of environmental humidity with the optimal path. Real-time obstacle avoidance function is realized by distance sensor during movement. In the process of system development, the system will be tested and improved.
Other: Agriculture
Plant Disease Identification Robot
AP098 »
In order to overcome the major problem, Diseases in plants. A robot is designed that detects the leaf disease using image processing and Machine learning is deployed. The robot is build using a controller known as Raspberry pi 3 and the Raspberry pi 3 is interfaced with motor driver L293D which operates the geared motor. The robot is controlled via IoT using Blynk app an android mobile application which is interfaced with Raspberry pi unique Token. This Blynk app controls the entire operation of the robot which is integrated with machine learning model. We have interfaced Multispectral image sensor integrated with CMOS spectral filter which captures image data at specific frequencies across the electromagnetic spectrum. VNC viewer (Virtual Network Computing) software used to access Raspberry pi 3 operation. By using the IP address of the raspberry pi 3 we can login in any device to access and control the performance. The robot moves towards the plant and captures the RGB image along with raw reflectance NIR (near-infrared) and Rededge images of the leaves. The captured image is stored and also monitor the farm lively via IoT using the camera interfaced in the robot from anywhere on any device and an HTML web page is developed to diagnose plant and check whether the plant leaf is healthy or infected. Once the image is captured the URL is generated and performs to convert NIR and REDEDGE images to NDVI (Normalized Difference Vegetation Index) then it provides the image within the web page which diagnosis the leaf with the given dataset using CNN algorithm and finally it concludes that the plant is healthy or infected with plant name and disease name in VNC viewer.
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.