Available master thesis

Available Master Thesis

Thesis
Construction of an in-situ power meter for microscopy illumination quality checks
SupervisorAlessandra Pedrocchi (alessandra.pedrocchi@polimi.it)
Co-SupervisorsAlice Geminiani (alice.geminiani@polimi.it)
CollaborationsAdvanced Light and Electron Microscopy BioImaging Centre – Alembic – San Raffaele Hospital
Dr. Eugenia Cammarota (cammarota.eugenia@hsr.it) , Dr. Valeria Berno (berno.valeria@hsr.it)
 
 
DescriptionBackground:
A Microscopy facility is a service where research scientists can find a team of highly qualified experts that can support in the planning and realization of imaging experiments. Good imaging using advanced fluorescence microscopes requires the microscope to be well maintained and calibrated. Besides checks on the optics resolution and alignment is also fundamental that the intensity of the illumination (source light) is constant over time to ensure the reproducibility of intensity measurements.


Aim:
Construction of a device to measure source light power with the convenient physical support to be placed on the microscope stage on the sample position. The device should operate on an Arduino platform and controlled through a smartphone app.


Requirements:

● Previous experience with Arduino
● Basic experience in programming


Project phases:

● Design of the device project
● Collection of all the materials
● Device assemble
● Software development
● Use of the device for characterization of several microscopes light sources
Thesis
Construction of an in-situ power meter for microscopy illumination quality checks
SupervisorAlessandra Pedrocchi (alessandra.pedrocchi@polimi.it)
Co-SupervisorsAlice Geminiani (alice.geminiani@polimi.it)
CollaborationsAdvanced Light and Electron Microscopy BioImaging Centre – Alembic – San Raffaele Hospital
Dr. Eugenia Cammarota (cammarota.eugenia@hsr.it)
Experimental Imaging Centre – San Raffaele Hospital – Dr. Davide Mazza
 
Description

Background:
Transcription factors (TF) are key proteins for the regulation of cell functionalities. Upon specific stimuli they migrate towards the target gene to initiate DNA transcription. TF trajectories are thought not to follow a simple random walk to reach the target gene, but they seem to follow more efficient searching mechanisms. Highly inclined and laminated optical sheet (HILO) microscopy is an advanced technique used to maximize the contrast and image fluorescent light emitted even from single particles and it is used to image single TFs. The TF tracks recorded are often in practice fragmented and therefore difficult to be analysed by classical methods. Deep learning is a powerful tool that can help in classification tasks like this one where we need to distinguish between Brownian, sub-diffusive and super-diffusive behaviours.

Aim:
Construction of a device to measure source light power with the convenient physical support to be placed on the microscope stage on the sample position. The device should operate on an Arduino platform and controlled through a smartphone app.

Requirements:
● Basic knowledge of Python
● Previous experience in programming

Project phases:
● Literature research on Deep Learning algorithms
● Acquisition of single molecule microscopy data with HILO setup
● Image analysis and trajectories classification with deep learning
● Quantification of trajectories in the different classes in response to external stimuli
● Correlation of motility types with chromatin density landscapes within the nucleus

 

Thesis Large-scale cerebellar Spiking Neural Networks to simulate sensorimotor paradigms
Supervisor Alessandra Pedrocchi (alessandra.pedrocchi@polimi.it)
Co-Supervisors Alberto Antonietti (alberto.antonietti@polimi.it) Alice Geminiani (alice.geminiani@polimi.it)
Collaborations Prof. Egidio D’Angelo and Claudia CasellatoUniversity of Pavia EPFL (Lausanne, Switzerland)
                         
Description Aim: Starting from a scaffold of the cerebellar circuit, to implement a cerebellar Spiking Neural Network in the NEST simulator, embedding detailed single neuron dynamics, plasticity mechanisms and geometry-based connectivity; the network will be exploited to simulate sensorimotor paradigms in physiological and pathological conditions. Project phases: – Literature research on the main properties of the cerebellar circuit. – Integration of new properties in the NEST-based cerebellar Spiking Neural Network – Design and analysis of closed-loop simulations of cerebellum-driven protocols.
Thesis Replicability of Computational Neuroscience studies
Supervisor Alessandra Pedrocchi (alessandra.pedrocchi@polimi.it)
Co-Supervisors Alberto Antonietti (alberto.antonietti@polimi.it) Alice Geminiani (alice.geminiani@polimi.it)
Description Aim: Reproducibility is critical to scientific inquiry, which relies on the independent verification of results. Progress in science also requires that we determine whether conclusions were obtained using a rigorous process, and we must know whether results are robust to small changes in conditions. Computational approaches present unique challenges for these requirements. A foundational research work in the computational neuroscience field, published in the last years, will be replicated by means of up-to-date models, in order to verify the results claimed by the original authors. Project phases: – Literature study about important neuroscience foundational papers. – Identification of the target problem to replicate – Development of the verification pipeline and appropriate codes (e.g. Spiking Neural Networks with NEST simulator) – Analysis of the results and comparison with the original claims
Thesis Sensory-integration in the cerebellum
Supervisor Alessandra Pedrocchi (alessandra.pedrocchi@polimi.it)
Co-Supervisors Alberto Antonietti (alberto.antonietti@polimi.it)
Collaborations Dr. Luca Casartelli and Dr. Ambra Cesareo, Scientific Institute Eugenio Medea Dr. Luca Ronconi, Università Vita-Salute San Raffaele 
Description Aim: It has been proved that the brain is able to integrate information coming from multiple sensory inputs (e.g., visual, auditory, etc.). In particular, the cerebellum is crucially involved in sensory integration, as demonstrated by neuropsychological studies with control subjects and one acerebellar patient. The project aims at utilizing a computational model to understand how the cerebellum is able to perform sensory integration. Project phases: – Literature study about sensory integration and the role of cerebellum. – Familiarization with computational model of the cerebellum in NEST – Development of the protocol to be tested with in-silico simulations – Analysis of the simulation results and the highlights coming from the modeling effort. Requirements: – Knowledge (or intention to acquire) of Python – Strong motivation to solve complex problems
Thesis Interactive mirroring games with the social robot NAO for autism therapy
Supervisor Alessandra Pedrocchi (alessandra.pedrocchi@polimi.it)
Co-Supervisors Alice Geminiani (alice.geminiani@polimi.it) Laura Santos (laura.santos@mail.polimi.it)
Collaborations Dr. Ivana Olivieri, CARELab, Fondazione Don Carlo Gnocchi – Milano Prof. José Santos-Victor, VisLab, Instituto Superior Técnico – Lisboa
                                                                     
Description Aim: Autism is a complex neurodevelopmental disorder, whose causes and effective treatments are still unknown. Autistic children show social, emotional and also motor deficits. Social robots have been suggested as potentially powerful tools to enhance traditional therapy, increasing motivation and engagement, while improving interaction and motor skills. To this aim, the current project exploits an interactive mirroring setup based on the social robot NAO, to develop new robot-mediated therapies for autism. Project phases: – Literature study about the use of social robots in autism therapy. – Improvement of the setup, design of a protocol for the interactive game, design of a clinical trial in collaboration with clinicians. – Clinical acquisitions with patients. – Data analysis to validate the setup and evaluate the impact of the interactive mirroring game in autism therapy. Requirements: – Basic knowledge on robotics and motion tracking systems – Good programming skills in Python and MATLAB are a plus – Motivation to take part in clinical acquisitions and interact with therapists – italian language mother tongue/proficiency
Thesis Development of a Board Game for Disabled People
Supervisor Alessandra Pedrocchi (alessandra.pedrocchi@polimi.it)
Co-Supervisors Marta Gandolla (marta.gandolla@polimi.it) Alberto Antonietti (alberto.antonietti@polimi.it) Valeria Longatelli (valeria.longatelli@polimi.it)
Description Aim: Different neuromuscular pathologies can impact the daily life of patients, impeding the execution of simple motor tasks such as feeding, personal hygiene, and entertainment. Usually, patients can only play a limited number of games, that does not imply the movement of their limbs (e.g., computer or smart-phone games), while they cannot perform physical board games, that would be useful also to keep their residual motor capabilities as efficient as possible. This thesis project aims to develop a board game (e.g., chess). Project phases: – Literature study about similar and commercial solutions. – Design of the physical structure of the setup, circuit design, identification of appropriate controllers, sensors, and actuators. – Development of the board game and testing of its mechanical functionality. – Implementation of control intelligence for different kinds of play – Analysis of the performances and test of the prototype with disabled patients. Requirements: – Competence with electronics circuits and 3D printing – Strong motivation to solve complex problems – Programming skills in MATLAB (required) and Python (preferable)
Thesis Development of upper limb IMU-based assessment tests for stroke survivors
Supervisor Emilia Ambrosini (emilia.ambrosini@polimi.it)
Collaborations Serena Maggioni, Hocoma AG – Zurich (Switzerland) (serena.maggioni@hocoma.com) RELab – ETH Zurich
Description Aim: Instrumented assessments of motor function are needed to objectively measure the patient’s progresses and to adjust the therapy accordingly.  Assessment of quality of movement and workspace have been proven to be sensitive to recovery. ArmeoSenso is a sensor-based medical device that provides functional movement therapy for upper extremity rehabilitation and assessments of range of motion, workspace and quality of movement. Assessments of quality of movement and workspace can provide rich information about recovery, which is currently not entirely exploited. Project phases: ArmeoSenso provides continuous offline joint angles and hand position data during training and during 3 assessment tests. Data collected on 24 stroke survivors relative to the 3 already available assessment tests. Next steps include: – Literature research on methods to assess workspace and quality of movement – Development of a new assessment test and definition of new metrics to assess workspace and quality of movementData collection on able-bodied subjects and patients – Data analysis Requirements: – Knowledge of Matlab – Knowledge (or intention to know) Unity – Availability to participate to data acquisition This thesis foresees an internship of 3 months at HOCOMA.
Thesis Effects of a robot-assisted therapy on motor coordination after stroke
Supervisors Emilia Ambrosini (emilia.ambrosini@polimi.it) Simona Ferrante (simona.ferrante@polimi.it)
Collaborations Ing. Monica Parati, Laboratorio di Bioingegneria,  IRCCS Istituti Clinici Scientifici Maugeri, Lissone (MB)
Description Aim: Muscle recruitment process involved in the planning and execution of complex movements seem to be simplified in low-dimensional modules, termed muscle synergies. Multi-muscle activity recorded through surface EMG and quantitatively analyzed in terms of muscle synergies represents a promising tool to examine motor impairments in post-stroke patients. Few studies have already explored the changes of muscle synergies after a rehabilitative intervention. This study aims at investigating the effects of a upper-limb robot-assisted therapy on motor coordination in post-acute stroke survivors. Project phases: A randomized controlled study investigating the effectiveness of a robot-assisted therapy on stroke patients is currently ongoing. Nest steps:
  • Literature research on muscle synergies and upper limb robot-assisted therapy in stroke survivors
  • Data collection
  • Analysis of trajectories, force and EMG signals pre- and post- robot-assisted therapy
  • Statistical analysis
  • Interpretation and discussions of the results
Requirements:
  • Knowledge of Matlab
  • Availability to participate to data collection
Thesis Does a hybrid robotic system improve motor recovery in stroke survivors?
Supervisor Alessandra Pedrocchi (alessandra.pedrocchi@polimi.it)
Co-Supervisor Emilia Ambrosini (emilia.ambrosini@polimi.it)
Collaborations RETRAINER consortium
Description Aim: A hybrid robotic system for arm recovery, combining EMG-triggered Functional Electrical Stimulation (FES) with a passive exoskeleton for upper limb suspension, has been developed within the European project RETRAINER. A multi-center clinical study was conducted on 68 stroke survivors and showed the superiority of the RETRAINER system with respect to usual care in improving arm functionalities based on clinical scales. Data collected during training by the system itself might support the definition of the intervention and provide a deeper and more quantitative analysis of motor recovery.  This study aims at analyzing EMG and kinematics data collected on a daily basis by the RETRAINER system in a group of 35 stroke survivors to drive further conclusion on motor recovery and help defining training intensity and duration. Project phases: Starting from EMG and kinematics data collected on 35 stroke survivors longitudinally during the intervention, and pre and post clinical scales: – Literature research – Data analysis in Matlab – Statistical analysis – Interpretation and discusion of the results Requirements:
  • Knowledge of Matlab
  • Software for statistical analysis (R or SPSS)
Thesis Neural Networks for the Decoding of Neural Signals from Behaving Monkeys
Supervisor Alessandra Pedrocchi (alessandra.pedrocchi@polimi.it) Silvestro Micera (silvestro.micera@santannapisa.it)
Collaborations Patrizia Fattori, Department of Biomedical and Neuromotor Sciences (DIBINEM), University of Bologna
Description Aim: Neural decoding is a critical step in BCI technologies. Different machine learning algorithms have been used to guide neural prosthetic limbs but results are far to get close at the natural body performance. In the last years, the availability of multi-electrode array system equipped with more and more recording channels is requiring a big data approach necessary. Together with the rising in computing power, the artificial neural networks (ANN) are a promising tool to address neural decoding problem. We propose to take advantage of modern ANN implementations to decode motor intentions from neural data recorded from behaving monkeys. Exploring different ANN architectures, the aim is to increase decoder robustness and reliability to be effectively implemented in clinical neuroprosthesis. Project phases: – Literature research – Implementation of the ANN architecture – Data analysis – Interpretation and discusion of the results This thesis foresees a development part at Scuola Superiore Sant’Anna in Pisa.
Thesis Wavelet-based Analysis of Neural Population Dynamics in Reaching Tasks
Supervisor Alessandra Pedrocchi (alessandra.pedrocchi@polimi.it) Silvestro Micera (silvestro.micera@santannapisa.it)
Collaborations Patrizia Fattori, Department of Biomedical and Neuromotor Sciences (DIBINEM), University of Bologna
Description Aim: During tasks and actions of humans and animals, neuronal populations communicate using a complex interplay of transient oscillatory rhythms. Neural signals generated by the activity of neuronal populations also display this type of transient behavior. This makes non-stationary spectral analysis of neural signals using wavelet functions a useful tool to investigate neural activity. Wavelet–based techniques are suitable for this type of signals since they possess one key property called multiresolution. Multiresolution allows to accurately determines low frequency components and simultaneously localize time rapidly transient events. Here, we propose to analyze extracellular signals recorded from multi-electrode array implanted in the posterior parietal area of monkeys during reach-to-grasp and reach-to-target task. Specifically, we will consider the low frequency part (< 300 Hz) of the extracellular field, called Local Field Potential (LFP). LFPs will be analyzed using wavelet-based techniques, such as Continuous Wavelet Transform and Wavelet Coherence to determine which type of scales (frequencies) characterizes the different tasks both at single and multi-electrode levels. This is a key step in the decoding of neuronal population dynamics for brain-machine-interfaces and biomedical applications Project phases: – Literature research – Data analysis – Interpretation and discusion of the results This thesis foresees a development part at Scuola Superiore Sant’Anna in Pisa.
Thesis Voice analysis to diagnose neurodegenerative diseases
Supervisor Emilia Ambrosini (emilia.ambrosini@polimi.it)
Co-Supervisor Simona Ferrante (simona.ferrante@polimi.it)
Collaborations Dott. Andrea Arighi, Fondazione IRCCS Ca’ Granda Ospedale Maggiore Policlinico
Description Aim: Voice signals provide important information to measure human behaviors and cognitive functions. Various types of neurodegenerative dementia (Alzheimer’s disease, frontotemporal dementia, primary progressive aphasia, Lewy body dementia) affect human speech in different manners. Disorders or irregularities in language domain, evaluated in terms of temporal features, such as pauses, speech rate, pitch, etc, could be strong predictors of different neurodegenerative pathologies affecting the brain. This thesis aims at the development and validation of a software tool able to automatically extract a set of language features sensitive and to classify neurodegenerative disorders from voice signals. Project phases: Starting from a Matlab-algorithm to automatically extract voice features from recordings and a dataset of recordings on healthy elderly subjects: – Literature review on vocal indicators of cognitive decline – Creation of a database of normal and pathological voice samples from elderly (control subjects, patients with Alzheimer’s disease, frontotemporal dementia, primary progressive aphasia and Lewy body dementia) – Optimization of the algorithm to extract voice features – Development of a classification algorithm to support the diagnosis of neurodegenerative diseases based on voice features and neurodegenerative biomarkers (magnetic resonance atrophy, cerebrospinal fluid proteins concentration) Requirements:
  • Knowledge of Matlab
  • Knowledge (or intention to know) Python
  • Availability to participate to data collection
Thesis Analysis of longitudinal monitoring data in pre-frailty community dwelling elderlies
Supervisor Simona Ferrante (simona.ferrante@polimi.it)
Co-Supervisor Francesca Lunardini (francesca.lunardini@polimi.it Davide Di Febbo (davide.difebbo@polimi.it)
Collaborations Fondazione IRCCS Ca’ Granda Ospedale Maggiore Policlinico Gruppo Korian Consejeria de Sanidad y Politicas Sociales, Junta de Extremadura (RMHS)
Description Aim: The European project MoveCare (H2020-ICT-26b-2016) aims at developing a transparent and heterogeneous long-term home-monitoring system for elderlies living alone. Within the project, sensorized pens and smart stress balls have been developed to acquire intertial and pressure-related data during daily life activities, and instrumented insoles are used to collect gait information. Such non-invasive monitoring system is meant to provide critical information to early predict mental or physicial decline in elderlies. A pilot study, involving healthy subjects belonging to the elderly population, is currently ongoing. This thesis project consists in the MoveCare pilot data elaboration and analysis aimed at defining standards in the available measurements for the healthy elderly population involved, in a completely clinical protocol-free environment. Project phases: – Data collection (from database) – Data preparation and pre-processing – Features and/or meaningful indicator extraction – Data elaboration and statistical analysis
Thesis Analysis of longitudinal monitoring data in pre-frailty community dwelling elderlies
Supervisor Simona Ferrante (simona.ferrante@polimi.it)
Co-Supervisor Francesca Lunardini (francesca.lunardini@polimi.it
Collaborations AISLab – Università degli Studi di Milano Clinical partners
Description Aim: Deficits in the upper extremity, especially in the hand usually affects motor control ability, leading to difficulties in performing the daily life activities. This work aims at developing a digital solution for hand rehabilitation using serious games controlled through a sensorized smart ball to aid patients and older adults in rehabilitating their hand. Project phases:Literature reviewDesign of serious gamesTests on healthy subjects and patients – Data analysis
Thesis A Deep Learning-based decision support system for the Rey-Osterreith complex figure test
Supervisor Simona Ferrante (simona.ferrante@polimi.it)
Co-Supervisors Matteo Matteucci (matteo.matteucci@polimi.it Davide Di Febbo (davide.difebbo@polimi.it) Matteo Luperto (matteo.luperto@unimi.it)
Collaborations AISLab – Università degli studi di Milano Fondazione Don Carlo Gnocchi – Milano
Description Aim: The complex figure of Rey-Osterreith ( ROCF ) is a neuropsychological test largely used for the diagnosis of dementia and Alzheimer’s disease. It requires the subject to copy, by hand, the ROCF and the accuracy of the drawn image provides useful information on the location and severity of a brain damage. However, the scoring methods of the ROCF test are currently performed by clinicians in what tends to be a subjective manner, which is open to interpretation and leads to a poor inter-rater reliability.  This thesis project aims at developing an end-to-end expert system which automates the visual analysis of the ROCF and helps operators in the neurological assessment of patients, by returning the most probable diagnosis from a digitized version of the ROCF drawn by the subject. This is a retrospective study in which data (ROCF drawings) are collected from paper-based patient records, scanned, and labelled according to the respective patient’s diagnosis. Project phases:Creation of a database containing labeled ROCFsDefinition of the expert system’s specs and requirements, according to cliniciansDefinition of the classification problem(s) – Data preparation – Design and implementation of the expert system based on deep learning classificators Requirements:
  • Fundamentals of image processing
  • Machine learning
  • Basic knowledge on deep learning
Thesis Monitoring of patients with vegetative and minimally conscious state diagnosis
Supervisor Simona Ferrante (simona.ferrante@polimi.it)
Co-Supervisor Francesca Lunardini (francesca.lunardini@polimi.it) Milad Malavolti (milad.malavolti@polimi.it)
Collaborations Fondazione Istituto Neurologico C. Besta – Milano Fondazione IRCCS San Raffaele Centro di Riabilitazione Villa Beretta – Ospedale Valduce Empatica
Description Aim: An ICT system, encompassing inertial, temperature, electrodermal activity, and EMG sensors has been developed to be used in combination with cognitive assessment to achieve longitudinal monitoring of patients with Disorders of Consciousness (DOC), with the final aim of testing the efficacy of tailored interventions. Project phases: – Literature review -Data acquisition on patients -Data analysis and design of algorithms to estimate pain and detect voluntary/unvoluntary contractions during long term acquisitions
Thesis Eye tracking for action observation treatment in neurological patients
Supervisor Simona Ferrante (simona.ferrante@polimi.it)
Co-Supervisor Francesca Lunardini (francesca.lunardini@polimi.it)
Collaborations Dr. Davide Sebastiano RossiFondazione Istituto Neurologico C. Besta, Milano Prof. Giovanni Buccino, Università Vita-Salute San Raffaele and Division of Neuroscience
Description Aim: Studies show that the use of systematic observation of meaningful actions followed by their execution (action observation treatment [AOT]) may become a rehabilitative strategy to accelerate the process of functional recovery in patients with motor impairment. This work aims at developing a home-based system for neurological patients that leverages eye tracking technology during the observation of video clips showing appropriate actions, with the aim of evaluating compliance to the required task.  Project phases: – Literature review -Design of technological solution with definition of requirements and specificationsIntegration of eye tracking with tablet/laptopData acquisition and analysis
Thesis Eye tracking for dysgraphia characterization
Supervisor Simona Ferrante (simona.ferrante@polimi.it) Matteo Matteucci (matteo.matteucci@polimi.it)
Co-Supervisor Linda Greta Dui (lindagreta.dui@polimi.it) Francesca Lunardini (francesca.lunardini@polimi.it)
Description Aim: Learning Disabilities affect an increasing number of students, but their causes are still unclear. In particular, Dysgraphia affects written language production: a big effort is often translated into an illegible product. This work is aimed at investigating the mechanisms underlying normal and pathological handwriting, with a special focus on attentive mechanisms and eye-hand coordination, through serious games for tablet and an eye tracker. Project phases: – Literature review – Design of serious games – Eye tracker integration – Tests on healthy and unhealthy subjects – Data Analysis Requirements:
  • Availability to learn object-oriented programming (C#) 
  • Availability to reach schools for data acquisition (province of Varese)
  • MATLAB and R knowledge
Thesis Machine Learning for digital Dysgraphia diagnosis
Supervisor Simona Ferrante (simona.ferrante@polimi.it) Matteo Matteucci (matteo.matteucci@polimi.it)
Co-Supervisor Linda Greta Dui (lindagreta.dui@polimi.it) Francesca Lunardini (francesca.lunardini@polimi.it)
Collaborations Prof. Cristiano Termine, Università degli Studi dell’Insubria and Fondazione Macchi 
Description Aim: Dysgraphia diagnosis is mainly based on writing speed on paper, but the causes which underlie such slowness are rarely investigated in clinical practice. Besides the evaluation of the overall speed, the digitalization of a Dysgraphia test would provide additional parameters related to gesture production, such as, fluidity, pressure, and tremor, and their variability during the execution. The aim of this work is to validate the digital version of a test for Dysgraphia, to develop an end-to-end expert system which automates the diagnosis, and to leverage Machine Learning techniques to provide additional insights on gesture execution, towards a more targeted diagnosis. Project phases: – Literature review – Data collection on healthy and dysgraphic subjects – Data analysis to extract the score and the features of interest from the acquired data – Statistical analysis – Development of Machine Learning models Requirements:
  • MATLAB, R or Python knowledge
  • Interest in Machine Learning and Deep Learning
  • Availability to reach schools for data acquisition
Thesis Machine Learning to longitudinally monitor graphical abilities, towards the early diagnosis of Dysgraphia
Supervisor Simona Ferrante (simona.ferrante@polimi.it) Matteo Matteucci (matteo.matteucci@polimi.it)
Co-Supervisor Linda Greta Dui (lindagreta.dui@polimi.it) Francesca Lunardini (francesca.lunardini@polimi.it)
Collaborations Prof. Cristiano Termine, Università degli Studi dell’Insubria and Fondazione Macchi  Dott. Luigi Macchi, Dott.ssa Simonetta Bralia, Provveditorato, CTI, CTS di Varese
Description Aim: Disentangling transient handwriting difficulties from Dysgraphia is not a trivial task. To facilitate the process, an observational and empowerment study started two years ago. The aim of this work is to longitudinally monitor handwriting-related problems, starting from preschoolers, to leverage Machine Learning techniques to predict the level of risk and evaluate the effectiveness of interventions, towards an early screening of Dysgraphia. Project phases: – Literature review – Data collection – Data Analysis – Machine Learning algorithms implementation Requirements:
  • MATLAB, R, or Python knowledge
  • Interest in machine learning
  • Availability to reach schools for data acquisition (province of Varese)
Thesis A smart scale for premature newborns
Supervisor Simona Ferrante (simona.ferrante@polimi.it)
Co-Supervisor Linda Greta Dui (lindagreta.dui@polimi.it)
Collaborations Link Up S.R.L – www.parenterale.com
Description Aim: Premature babies require special care to overcome their frailty condition. They need a special parenteral nutrition, and their growth must be monitored in time. Even after discharge, parents continue bringing the newborn to the hospital to follow-up weight and length postnatal adaptation. This work is aimed at the introduction of an IoT scale in clinical practice, through the integration with the ParEnt registry, an official Italian registry for neonatology parenteral and enteral nutrition. The final goal is to provide a reliable and usable tool directly to the parents, to facilitate the process of post-discharge follow-up. Project phases: – Literature research – Identify and involve clinicians in the project – Scouting of available technologies for data transmissionIntegration of the data into ParEnt registry – Design of the user interface – Pilot study design and data collection – Data analysis to test reliability, concurrent validity, and user acceptance Requirements:
  • Basic knowledge of microcontrollers
  • Preferred programming languages: PHP, Python
  • R knowledge
Thesis Computer Vision and Deep Learning for children’s problems detection through drawings analysis
Supervisor Simona Ferrante (simona.ferrante@polimi.it) Matteo Matteucci (matteo.matteucci@polimi.it)
Co-Supervisor Linda Greta Dui (lindagreta.dui@polimi.it) Francesca Lunardini (francesca.lunardini@polimi.it)
Collaborations Prof. Cristiano Termine, Università degli Studi dell’Insubria and Fondazione Macchi  Dott. Luigi Macchi, Dott.ssa Simonetta Bralia, Provveditorato, CTI, CTS di Varese
Description Aim: Children free drawings reveal many aspects of their personality, and can potentially uncover the presence of different problems. Judgement about drawings is often performed in a subjective way, taking into account aspects like the presence of details, the use of colors, etc. The aim of this work is to leverage computer vision and/or deep learning techniques to relate children drawings with teacher’s observation about difficulties in various aspects of the learning sphere. Project phases: – Literature review – Data collection – Data analysis – Algorithms implementation Requirements:
  • Basic knowledge of computer vision and deep learning
  • Availability to reach schools for data collection (province of Varese)
Thesis Improving BCI: machine learning to identify visual P300
Supervisor Alessandra Pedrocchi (alessandra.pedrocchi@polimi.it)
Co-Supervisors Alberto Antonietti (alberto.antonietti@polimi.it) Linda Greta Dui (lindagreta.dui@polimi.it)
 
Description Aim: The detection of the P300 signal is the base of a specific type of Brain-Computer Interface (BCI) that explores the fact that paying attention to a specific, rare, stimulus among several others generates a positive peak in the EEG signal around 300ms after the stimulus onset, while the stimuli the user is not paying attention to do not generate such signal. In this thesis, you will explore different machine learning methods to identify the best ones that can be used to identify the presence of P300 reducing the number of trials needed for the training. Project phases: – Literature study about EEG recordings and elaboration methodsDevelopment of pre-processing of EEG recordingsExploration of different machine learning methods that can be used to identify the trials where the P300 is presentCarry out tests using an EEG database recorded from 15 subjects in 7 sessions. Explore robustness and generalizability of the algorithm identified Requirements:
  • Knowledge (or intention to acquire) of Python
  • Interest in machine learning methods
  • Independent problem-solving attitude
  • Strong motivation to solve complex problems
This site uses cookies to enhance your experience. By continuing to the site you accept their use. More info in our cookies policy.     ACCEPT