Gesture Recognition with LSTM Classification of sEmg Signals for Prosthetic ControlDeveloped by Irene Sorianini, Federico Gala Supervised by Nicola Covre, Prof. Mariolino De Cecco and Prof. Davide Brunelli. Conditioning System Development by Ing. Antonio Selmo Supported by Mirolab, Università degli Studi di Trento From zero to hand movement control, the Mirolab presents the ambitious thesis project developed by Engineering Master course students, Irene Sorianini and Federico Gala. The project implements a deep-learning application for gesture classification and control of the prosthetic hand by monitoring the forearm muscles. A sEMG acquisition prototype allows the monitoring of muscle activity with high performance, versatility and low production costs. The results returned a high level of accuracy during test classification, which was followed by an on-line test to assess repeatability. A series of hand crafted dry electrodes applied to the forearm collects the sEMG signals which, after processing, are classified by a machine learning model that returns visual feedback to operate a simple robotic hand. The high accuracy in classification is achieved through data augmentation methods that aims to restrict the unavoidable limitations rasing when dealing with human factors. At the moment the system involved a LSTM machine learning model that has been compared with other deep neural network model, such as CNN and DNN, showing more robustness and accuracy. The mis-classification are minimized with the introduction of parallel LSTM neural networks dedicated to specific gesture recognition. The acquisition system consist of five elements. A neoprene cuff with integrated electrodes, an analog conditioning system for system for signal filtering and amplification, a high-perfomance ADC version system and a raspberry unit for digital dataprocessing. The electrodes are obtained by cutting 16 simple metal plates of size 20x20x1 mm and soldering the copper connector. Wiring is via coaxial cables to reduce noise of the 50 Hz mains voltage. The conditioning system has an amplification gain of 500 while flexing the signal at 500 Hz with a low pass filter, 50 Hz with a notch filter and at 20 Hz with high-pass filter. The ADC samples the 8 channels at approximatly 32 KSPS (4000 Hz per channel). Continue reading →
Laboratorio Pandemico 17 Marzo 2021
Link a Video ed Appunti Lezioni 7 Aprile 2021
2. Statistica ed Incertezza 31 Marzo 2021
Link Lezione 5 Marzo 2021
This thesis proposes the use of image processing and data acquisition to estimate the pose of a subject.
An RGB camera (or a ToF camera) can be used for image acquisition.
The acquisition of joints accelerations through a network of wearable IMU sensors is managed with Raspberry and MQTT communication protocol is used to share the information.
A sensor fusion algorithm allows the union of information and the reduction of uncertainty.
Everything is used in virtual environment for the real-time movement of an avatar displayed with Hololens and a visual feedback of the movement.
Continue reading →
Ingenuity is Art 25 Febbraio 2021
When it is asked for an engineer to design a machine with specific properties, constraints, and performance, he uses not only the laws of physics, analysis, and mathematics but a higher level of skill: Ingenuity.
To solve the most difficult problems, the engineer must use this kind of skill often in original, clever, and inventive ways, which is Art. In particular, this is important nowadays in a world where automation, integration, and optimisation are playing an increasingly important role.
Art as a design philosophy characterises an engineer in all his works from the development of ideas to their implementation and testing.
Alessandro LuchettiContinue reading →
Performed by : Irene Sorianini, Federico Gala and Davide Massella
Supervised by : Nicola Covre
From the development and thesis research of three master’s students we are creating a wearable device to monitor the muscular activity of the human trunk and upper limbs.
The device consists of three components:
- the senrosized shirt;
- the data acquisition and processing system;
- the visual feedback system for the therapist.
1) SENSORIZED T-SHIRT AND SLEEVE
Thanks to the support of an experienced seamstress, the sensorized T-shirt features a reconfigurable allocation of dry electrodes via Velcro.
2) DATA ACQUISITION AND PROCESSING
The data acquisition and processing system is composed of the electrodes, the analog amplification system, the Delta Sigma analog digital conversion system and a raspberry Pi 4 unit.
THE ELECTRODES AND CONNECTION CABLES
Several types of simple dry electrodes were proposed and compared with state-of-the-art disposable electrodes.
Each electrode has been connected with the amplification system by means of shilded cables in order to reduce the 50 Hz noise perturbation. Eight couples of electrodes has been considered and the analog amplification sistem provides to prepare the signal to the ADC conversion.
THE ANALOG AMPLIFICATION AND FILTERING
The Analog device amplifies with different reconfigurable stages. A first module with a variable gain of 20 and 50, then it follows a second, third and fourth amplification modules with a variable gain of 1, 2 and 5. Embedded in between the second the third amplification modules a sequence of analog filters is installed. The signal passes through a low pass filter and a high pass filter with recofigurable cut off frequency, respectively 500Hz, 1KHz, 2KHz and 5Hz, 10Hz, 20Hz.
THE ACQUISITION SYSTEM
The Acquisition system consists of an ADS1298 RevB connected via SPI communication system to a Raspberry Pi 4.
The ADS1298 is an analog-to-digital conversion system from the Delta Sigma family and allows the acquisition of 8 channels up to 32KSPS.
Raspberry defines the ADC registers and the acquisition is managed by an interrapt on the GPIO port connected to the DRDY of the conversion board . Whenever a packet of 8 samples is ready it is transferred from ADS1298 and saved in raspberry memory.
The signal acquired and saved on Raspberry is processed to be used in parallel as a sample for classification by Machine Learnign and sent to the visual feedback system. The acquired signal is first interpolated to obtain a sequence with constant step in time. Given the presence of undesired spikes in the system, each channel is cleaned of outliers. Then, the signal is normalized with respect to the other channels by calculating mean and standard deviation.
DEEP NEURAL NETWORK AND LSTM FOR GESSTURE CLASSIFICATION
The signal thus arranged is ready to be classified by an LSTM neural network. The network was previously trained on a generated and tested dataset. As a first test, a limited group of classes was chosen to allow a training dataset to be quickly obtained and electrodes were placed right in the sleeve to monitor the arm muscles. A total of five actions were chosen:
- ch_ Closed Hand
- op_ Open Hand
- i_ Index up
- t_ Thumb up
- 3_ Index, thumb and middle finger raised to dial the number 3
THE VISUAL FEEDBACK SYSTEM FOR THE THERAPIST (WORK IN PROGRESS)
In parallel to the classification system with neural networks, the signal will be sent via bluethoot to a processing unit that will reproduce a virtual model of the muscles activated by the patient. The goal is to repropose the information in augmented reality to the therapist via Hololens. Through RGB image processing techniques such as Open Pose or Open Vino, it will be possible to move the avatar following the actions of the subject.
Continue reading →
Complementary filtering for height estimation and control of a drone 18 Febbraio 2021
STUDENTS : Alessandro Avi, Matteo Zuccatti – SUPERVISOR : Luca Maule
The main focus of this project is the implementation of a key concept belonging to the sensor fusion theory which is Complementary filtering in a Unity game.
In this case the goal is to fuse the measurament coming from an incremental sensor such as an accelerometer with the measurament of a barometer, namely an absolute sensor, to estimate the flying altitude of a drone. The sensor fusion algorithm, as well as the filtering processes of the measurements, are carried out in Matlab, which is connected to Unity through the ZMQ library. The drone is equipped with ideal sensors (e.g. ideal gyroscopes), as well as realistic sensors such as the ones which are used for the sensor fusion. The simulation takes into account multiple aspects of the incremental and absolute sensors, such as drift phenomenas, sampling frequencies, noises and repetabilities, in order to have a more accurate rapresentation of a real sensor.
The game has been further developed by coding additional functions such as stabilization and full control of the drone in space, as well as path-tracking and landing capabilites. The dynamic model of the drone has been manually implemented in C# and every task affecting its dynamics is being carried out through a PD control. The position and attitude of the drone, by design, are not independent each other, thus making the control of its pose not a trivial task.
Multiple dynamical tasks can be executed simultaneously (e.g. landing the drone while stabilizing it along its axis), thus multiple input variable must be controlled at once. This is especially critical when the two tasks are not independant, for example the stabilization and the trajectory tracking.
Once the drone has landed, a series of plots are automatically generated in Matlab, showing few important aspects of the simulation. These plots analyse the raw and filtered measurements coming from the two sensor and the effectiveness of the sensor fusion procedure, as well as showing the motion of the drone in a 3D plot and the tracking errors. The Unity game is also equipped with a dedicated explanatory section, where the theoretical aspects of the project are illustrated and thoroughly explained.
Continue reading →
ISTRUZIONI ESAME DI MISURE 26/01/2021 4 Marzo 2021