Deadline to register is Jun 30, 2019.
Teams can still edit your proposals during judging period.

Category: Sort By:
Regional Final
📁Machine Learning
👤Alexandre Oliveira (Federal Institute of Sao Paulo (IFSP))
📅Oct 06, 2019
The electrocardiogram (ECG) is the record of the cardiac electrical activity, which propitiates a simple and effective heart condition diagnosis. Automatic detection of arrhythmias is an important tool to assist cardiologists in an effective heart diagnosis. The purpose of this project is to implement multiple ECG arrhythmia classifiers implemented in a single-chip FPGA, exploring the architecture flexibility in accommodating concurrent neural network-based classifiers.
details »
Regional Final
📁Machine Learning
👤Galo Sánchez (Escuela Superior Politécnica del Litoral )
📅Oct 09, 2019
It is estimated that over 466 million people suffer from a hearing disease, which can cause partial or total hearing loss. The main impact of hearing loss on individuals, is on the ability to communicate with others. In developing countries, most children with hearing loss, do not have access to education.

Over the last decade, there have been a great improvement on artificial neural networks, which allows developing sophisticated systems for pattern recognition, and classification of data from different types and sources. Our proposal is the implementation of a wearable embedded system of pattern recognition and classification, focused on sign language, using the DE10-nano. This project is focused on improving deaf individuals’ communication with those who do not know sign language.
details »
Regional Final
📁Internet of Things
👤Igor Semenov (The University of Alabama in Huntsville)
📅Oct 09, 2019
Software developers are increasingly using Functional Reactive Programming (FRP) paradigm for writing event-driven applications. Complexity of such applications usually grows fast as new features are added. FRP allows programmers to deal with this growing complexity. In embedded systems and IoT devices reacting on external events and producing corresponding outputs is a common task. That is why, FRP may be useful for embedded software developers as well. Some attempts of using limited versions of FRP in embedded systems have already been made. However, to the best of our knowledge, nobody tried to use FPGA to make use of the parallel nature of FRP. In this project we are going to make such an attempt. We think that our work will allow embedded developers to apply a modern programming paradigm for designing complex and high-performance systems with less effort. At the same time, we assume that our project can help software engineers familiar with FRP to use FPGA technology without knowing hardware description languages.
details »
Regional Final
📁Machine Learning
👤Laís Bandeira (Federal University of Pernambuco)
📅Oct 08, 2019
The project is a smart toy that assists therapists at the activities in the treatment of children with autism performed inside the doctor’s office. This smart toy will use sensors to capture the child’s actions during the activity and analyze them. The doctor receives the acquired data and remotely observe the development of the child at the treatment.

Likewise, the AuT system could be used at home by caregivers to different activities that improve the child’s vocabulary and develop social interaction. The system needs a quick response time, especially the activities that require image processing. For example, emotions activities that teach the child to identify and reproduce the facial expression from another person. Therefore, we decided to choose OpenVINO, which supports neural network algorithms that we will use, provides a faster processing time and an architecture that supports parallelism.
details »
Regional Final
📁Machine Learning
👤Juan Carlos Sernaque Julca (Universidad Nacional de Piura)
📅Oct 10, 2019
The project is mainly focused in join stability algorithms in pendulum robots with self driving algorithms that uses artificial vision. As the robot detects a specific object, it will try to follow it. To get the most out of the DE10 Nano platform, inference engines, DC motor controllers, sensor controllers, image preprocessing modules, object tracking modules, and specialized IP's will be incorporated into a single chip.
details »
Regional Final
📁Machine Learning
👤José Silva (Federal University of Pernambuco)
📅Oct 08, 2019
According to OPAS Brazil: "The delay in detecting and assisting those involved in a traffic accident increases the severity of injuries. in this context injuries are extremely time sensitive: minutes can make the difference between life and death." Our project aims to improve security at roads by analyzing the traffic at a certain piece of a track (street, highway or avenue), in real time, making a journal of that region to give authorities a better understanding of that specific case scenario and alerting authorities directly, when some serious accident occur. To attain a real time constraint with a still reliable system and a lower power consumption, we are going to use FPGA DE10 nano, this would also allows the image processing be made locally what lowers the costs of analyze and store the images in the monitoring's centrals, and allowing a decrease in the delay time from the detecting and assisting of those involved in a serious traffic accident, what could lead to saving lives.
details »
Regional Final
📁Machine Learning
👤Emanuel Ortiz Ortiz (Universidad Nacional de Piura)
📅Oct 09, 2019
The project will try to control the position of an esferical object over an Stewart platform using Fuzzy Logic and computer vision. The system will read the input from a joystick and it’ll measure the position using a camera also and algorithm will be developed to control the platform orientation using Forward and Inverse Kinematics.
details »
Regional Final
📁Machine Learning
👤Víctor Junior Villanueva Fernández (Maelpro)
📅Jul 08, 2019
A system of sensors and actuators will be implemented to make an aeroponic system that can record the values of the most important parameters that must be considered in the crop: humidity, temperature, luminosity, pH concentration, etc. Several random points will be taken in a cultivation area and the values of the mentioned parameters will be measured. These values will be used for the subsequent Monte Carlo simulation, the more random samples of measurements taken, the better approximation results will be obtained. With this the probability distribution will be obtained.
details »
Regional Final
📁Machine Learning
👤Carlos Vazquez Gomez (University of Pittsburgh)
📅Jul 01, 2019
Our innovation aims to assist visually impaired people with their daily walking experience. By combining information captured from camera and GPS, making use of computer vision and machine learning on an FPGA, and navigating by activating vibration motors at different position on a shirt, we can guide a user through a field of obstacles, all without interfering with their auditory sense. The FPGA accelerates the computer vision processing and allows the various hardwares to cooperate.
details »
Regional Final
📁Machine Learning
👤Chris Pasquinelli (University of Pittsburgh)
📅Oct 08, 2019
Real-time translation of American Sign Language into voice. Our approach is unique in that, instead of translating finger spelling alphabet, we focus on a small set of common words to translate simple conversations. We take advantage of a CNN-LSTM network to capture temporal information, and a language model bridges the gap in grammar and styles between English and ASL, and helps to reduce errors.
details »
Regional Final
📁Machine Learning
👤Eduardo Jeremías López Rizo (Instituto Tecnológico y de Estudios Superiores de Occidente (ITESO))
📅Jul 01, 2019
Nowadays digital communications play a primordial rol in our daily lives, and it is invaluable to make them as fast as possible. That is why it is proposed a long short-term memory neural network to improve the bit error rate in digital communications.
When the bit error rate of digital communications is diminished then the transmission can be accelerated even further, so that it is worth to try to implement deep learning in this subject.
details »
Regional Final
📁Machine Learning
👤Dhruvi Bhadiadra (Portland State University)
📅Jul 02, 2019
As the inventions in the field of Deep Neural Network and their corresponding application explodes day-by-day, the size of the deep neural network also increases rapidly for complicated application. There are concepts like averaging or augmenting three deep neural networks to form the desired classification application. Even though the GPU can be used to pace up the training and inference process of the model by using the multiple thread processing available, after training the memory used to store the model is in terms of hundreds of MegaBytes. So, in the past few years, a separate path of research started on how to reduce the memory used in the storage of parameters. We chose to follow one of the papers[1] and implement the design in hardware for the Proof of Concept. The reason we chose the implementation of hardware is to research the scope of deep learning algorithm running on hardware with low power consumption and high parallelism. The resource availability in the hardware is one of the main struggles we face during the design phase. So, we compress the deep learning parameters using the method provided in the paper and in turn implement the compressed model in FPGA.
details »

1 2 3 4