(Microelectronics Group, Digital Reconfigurable Devices)
📅Jul 15, 2018
This project presents the development of open source libraries, software tools, and firmware that can emulate the behavior of different conventional laboratory instruments using FPGA boards and a personal computer (PC), thus creating a multiple virtual instrument. The developed system allows the choice of instrument to be used without making a substantial change in the main hardware, the system has been designed in a modular way so that it is easily adaptable and customizable, the PC software and the hardware description language used to code the FPGA are easily extensible to add functionalities or applications.
📁High Performance Computing
📅Jul 13, 2018
Intelligent Vehicle: This electric car has day/night vision and ultrasonic sensor to field the road. Powered by Battery charged with solar panels.
A high performance system controls the vehicle manually or using WiFi. Future human intelligent vehicle. A virtual machine is loaded into the FPGA an assembly language is used to compile the instructions block.
👤Felipe Fernandes Lopes
(Universidade Federal do Rio Grande do Norte)
📅Jul 11, 2018
Melanoma is the least common but deadliest skin cancer, accounting for the majority of skin cancer deaths according to The Skin Cancer Foundation. Moreover, about 132,000 new cases of melanoma are diagnosed worldwide each year, according to the World Health Organization. However, Melanoma presents excellent chances of cure when detected early, according to The Skin Cancer Foundation, the estimated 5-year survival rate for patients whose melanoma is detected first is about 98% in the USA. The survival rate falls to 62% when the disease reaches the lymph nodes and 18% when the disease metastasizes to distant organs. Its detection becomes difficult as it resembles others skin diseases and nevus.
Over the years, several technologies have emerged that seek to improve the detection of melanomas and inside in this context, this project proposes a hardware solution for auxiliary medical diagnosis. The hardware solution uses a technique of pre-processing image with artificial intelligence (AI) technologies to detect skin cancer melanoma. In image processing are used techniques such as image segmentation, morphological operators, statistical parameters, arithmetic and logic operations, and the artificial inteligence technologie employed are artificial neural networks (ANN). The images can come from smartphone camera or another something device.
👤Ânderson Ignacio da Silva
📅Jul 09, 2018
The overall idea of this project is to develop a complete system to detect traffic signs, classify them and inform/help the driver to control speed and movements along the route driving the car using deep learning for the traffic signs and fast segmentation for image processing.
(McGill University, Ecole Polytechnique de Montreal)
📅Jul 08, 2018
This system records the brain activity, predicts the character that the user is thinking and prints it on a screen in real time. So, all the user has to do it is think what they want to type and voila! It is on the screen.
The interaction between humans and computers have changed a lot over the course of time. It started form simple keyboards, to mouse, touch screen and finally gesture recognition. Alongside, rapid advancements in machine learning has opened plethora of possibilities in every field. Through this project we plan to build a system using machine learning predicting techniques, which will make it possible to text just by thinking.
The human brain is a power house of computation. It is a complex system which emits minute radiations. Neuroscientists have been able to record and classify these signals albeit with limited success. Nevertheless, neuromapping systems are advanced enough to observe certain signals emitted from the brain. An custom built EEG cap is used to record the brain waves. It has 14 on board sensors which records the brain waves and transmits the raw EEG signals serially using Bluetooth. An Arduino connected to a Bluetooth receiver (HC - 05), receives the data. This data is arranged in packets by the Arduino and transferred to the INTEL DE-10 FPGA. The EEG data is processed in the FPGA. The need for an FPGA arises as the data needs to be converted and processed in frequency domain an that too in real time. Also, training of Convolution Neural Networks is a computation heavy process. Since FPGA devices offer the unique advantage of parallelism, the data can be processed in almost real time. There are various current implementations of such Brain Computer Interfaces. But, most of it is confined to laboratory environments requiring high power GPUs. As this system comprises of only an EEG cap, FPGA and microcontroller it is standalone and portable. With Elon Musk’s neuralink aiming to link human brains to computers and aid people with brain injuries, the race for building advanced low-power mobile brain-computer interfaces (BCI) is gaining steam.
📁Other: Wearable Devices for Medical Rehabilitation
(LASARRUS Research and Clinic Center)
📅Jul 05, 2018
Each year approximately 795,000 people suffer from stroke which makes it the leading cause of permanent disability in the country. Research have shown that the human brain is capable of self-reorganizing especially after limb stimulation is employed resulting in re-establishment of neural pathways that control volitional movement. Traditional physical therapy which involves one-on-one interaction with a therapist is a conventional method used for stimulating sensorimotor activities, while robotic-assisted rehabilitation can increase the effectiveness of the repetitive exercises used in rehabilitation. Furthermore, to properly quantify the effectiveness of both conventional and robotic-assisted rehabilitation, sensorimotor measurements need to be acquired and analyzed. Thus, the invention of the Flex Force Smart Glove (FFSG) allows for a complete nonintrusive design used to acquire and analyze sensorimotor information obtained from the human hand. The novel nonintrusive FFSG design will be powered by the Intel Altera FPGA and will incorporate all the sensors needed to measure the force and rotation of the human wrist and fingers. The device will provide the individual with a low-cost wearable smart glove to keep track of their rehabilitation process, which they can take home to facilitate further rehabilitation.
(University of Massachusetts Amherst)
📅Jul 02, 2018
Gene Networks (GNs) attempt to model how genetic information stored in the DNA (Genotype) results in the synthesis of proteins, and consequently, the physical traits of an organism (Phenotype). Deciphering GNs plays an important role in a wide range of applications from genetic studies of the origins of life to personalized healthcare. Probabilistic graphical models such as Bayesian Networks (BNs) are typically used to perform learning and inference of GNs from DNA microarray data. Current techniques of generating BNs of GNs from data involve searching (over space of candidate structures) and scoring (evaluating how well structure agrees with data). However, while search algorithms can be efficiently implemented in software, the same is not true for scoring. The operations involved in the scoring of probabilistic graphical structures are inherently parallel and hence are inefficient when performed sequentially over von-Neumann architectures.
In this project, we utilize the System-on-a-chip (SoC) FPGA development platform to design a dataflow-based Bayesian architecture for structure learning of GNs. While the software running on Hard Processor System (HPS) implements the search over candidate structures, the FPGA architecture performs parallel computations involved in scoring of these structures. We demonstrate structure learning of a GN from synthetically generated DNA microarray data using the proposed architecture. We plan to estimate the performance benefits of the proposed architecture over software-only approaches running on contemporary computers.
Image sources: BYU IDeA Labs, Creative Biolabs.
📁High Performance Computing
(University of Rhode Island)
📅Apr 30, 2018
Our goal is to utilize an FPGA to create a high-speed quantum gate emulator directly in hardware, and couple this with a user-friendly interactive GUI accessible through a web server based application, which will allow the user to create circuits out of the emulated quantum gates using portable devices such as smartphones and laptops. With this project, we will create a viable environment for everyone from experts to students to create new quantum computing applications based on quantum gates, which will accelerate the advancement of quantum computers.
(Maelpro - Mechanical And Electronic Engineering Projects)
📅May 23, 2018
This project demonstrates, with a real-world application, that developing adaptable and reconfigurable systems for industrial machines in our country is possible.
An FPGA is used to implement the control logic for an old offset printer, which counts with 880 LEDs, 88 stepper motors, 8 Bluetooth modules, 4 UART modules and 48 push-buttons, among other peripherals. Even though the machine is very old, its mechanical components are in good condition and, for that reason, only the electronics were replaced.
All the interfaces were developed considering the optimization of resources in order to control all the peripherals contained in the offset printer. This design requirement was met by using shift registers in cascade, which allows us to expand the number of outputs when it is required.
This project has allowed us to apply all our digital design knowledge, and to develop even more our skills to solve real-world problems.
📁Other: FPGA-based fast optical focusing system
(California Institute of Technology)
📅May 11, 2018
Light plays an important role in biomedical applications including imaging, manipulation and therapy. However, direct focusing light deep into biological samples has long been considered impossible due to the scattering nature of typical biological tissue. Recently, a number of optical wavefront shaping techniques have been developed to overcome the scattering in biological samples and have realized optical focusing through scattering media (biological samples). These methods first measure the scattering property of the scattering media, then digitally calculate the corresponding solutions that can compensate the scattering, and finally modulate the light based on the solution by an optical device called spatial light modulator (SLM). However, most of the demonstrations have been limited to static samples since these techniques are very sensitive to the movements of the scatterers. In fact, this problem hinders the translation of the wavefront shaping techniques into practical in vivo applications because in vivo tissue are highly dynamic due to blood flow, muscle movements, etc. Unfortunately, those existed techniques are not fast enough to realize focusing within the time window (decorrelation time) in which the calculated wavefront solutions remain valid. Therefore, a fast optical focusing system is crucial for realizing optical focusing through dynamic scattering media.
Here, we propose and design a new optical focusing system that based on an FPGA board, which uniquely enables high speed optical focusing with our system. Conventional optical focusing systems use a camera as the recording device, a PC to control the system and compute the wavefront and a spatial light modulator to display the wavefront. The operating speed of the optical system is limited by the speed of data transfer between the PC and the optical devices. Here, we develop a new architecture that substitutes the camera with a photodiode, the PC with an FPGA platform, and the SLM with a galvanometer. The FPGA platform can significantly break the bottleneck of the speed of optical system. A commercial galvanometer oscillates at a frequency ~10kHz, and FPGA boards with a 50MHz clock signal can sample ~5000 data points within one galvanometer oscillating period (this is equivalent with a camera with 5000 pixels and 10kfps). An analogue comparator is used to convert the analogue signals from the photodiode to digital signals for the FPGA board.
By using this FPGA-based system, we aim to realize optical focusing through scattering media within 200 microseconds (2 galvanometer oscillating period), an order of magnitude faster than conventional wavefront shaping. This operational speed enables optical focusing deep inside dynamic scattering samples.
📁Internet of Things
(Georgia Institute of Technology)
📅May 11, 2018
The goal of this project is to develop a low power infant sleep apnea monitor.
Infant sleep apnea can have severe consequences. The oxygen level in the infant's blood may become too low, leading to hypoxemia. The infant's heart rate may also slow, causing bradycardia. In some cases, the infant even may lose consciousness and need to be resuscitated.
By leveraging the low power features of the FPGA based design, we hope to make such monitors more portable and less restrictive compared to devices that need to be plugged into a wall power source.
In addition, the flexibility provided by the FPGA will allow for advanced features, such as heart arrhythmia monitoring. By deploying FFT and other signal processing modules to the devices, these features can be added, while preserving low power functionality.
(The University of Maine)
📅May 01, 2018
This design project will be focused on designing a linear motion system for purpose of using in 3D Printer, CNC, robotic or industrial control. It will control one bipolar stepper motor using a built driver board. The driver will be monitoring and control by a signal of the direction and number of steps or microstepping from FBGA. The input signal is received through ethernet communication, direct TTL input port signal or serial signal.