Interpretable Convolutional Neural Networks for Decoding and Analyzing Neural Time Series Data

Machine learning is widely adopted to decode multi-variate neural time series, including electroencephalographic (EEG) and single-cell recordings. Recent solutions based on deep learning (DL) outperformed traditional decoders by automatically extracting relevant discriminative features from raw or minimally pre-processed signals. Convolutional Neural Networks (CNNs) have been successfully applied to EEG and are the most common DL-based EEG decoders in the state-of-the-art (SOA). However, the current research is affected by some limitations. SOA CNNs for EEG decoding usually exploit deep and heavy structures with the risk of overfitting small datasets, and architectures are often defined empirically. Furthermore, CNNs are mainly validated by designing within-subject decoders. Crucially, the automatically learned features mainly remain unexplored; conversely, interpreting these features may be of great value to use decoders also as analysis tools, highlighting neural signatures underlying the different decoded brain or behavioral states in a data-driven way. Lastly, SOA DL-based algorithms used to decode single-cell recordings rely on more complex, slower to train and less interpretable networks than CNNs, and the use of CNNs with these signals has not been investigated. This PhD research addresses the previous limitations, with reference to P300 and motor decoding from EEG, and motor decoding from single-neuron activity. CNNs were designed light, compact, and interpretable. Moreover, multiple training strategies were adopted, including transfer learning, which could reduce training times promoting the application of CNNs in practice. Furthermore, CNN-based EEG analyses were proposed to study neural features in the spatial, temporal and frequency domains, and proved to better highlight and enhance relevant neural features related to P300 and motor states than canonical EEG analyses. Remarkably, these analyses could be used, in perspective, to design novel EEG biomarkers for neurological or neurodevelopmental disorders. Lastly, CNNs were developed to decode single-neuron activity, providing a better compromise between performance and model complexity.

Data assimilation for advanced cross-scale unstructured-grid ocean modeling.

The coastal ocean is a complex environment with extremely dynamic processes that require a high-resolution and cross-scale modeling approach in which all hydrodynamic fields and scales are considered integral parts of the overall system. In the last decade, unstructured-grid models have been used to advance in seamless modeling between scales. On the other hand, the data assimilation methodologies to improve the unstructured-grid models in the coastal seas have been developed only recently and need significant advancements. Here, we link the unstructured-grid ocean modeling to the variational data assimilation methods. In particular, we show results from the modeling system SANIFS based on SHYFEM fully-baroclinic unstructured-grid model interfaced with OceanVar, a state-of-art variational data assimilation scheme adopted for several systems based on a structured grid. OceanVar implements a 3DVar DA scheme. The combination of three linear operators models the background error covariance matrix. The vertical part is represented using multivariate EOFs for temperature, salinity, and sea level anomaly. The horizontal part is assumed to be Gaussian isotropic and is modeled using a first-order recursive filter algorithm designed for structured and regular grids. Here we introduced a novel recursive filter algorithm for unstructured grids. A local hydrostatic adjustment scheme models the rapidly evolving part of the background error covariance. We designed two data assimilation experiments using SANIFS implementation interfaced with OceanVar over the period 2017-2018, one with only temperature and salinity assimilation by Argo profiles and the second also including sea level anomaly. The results showed a successful implementation of the approach and the added value of the assimilation for the active tracer fields. While looking at the broad basin, no significant improvements are highlighted for the sea level, requiring future investigations. Furthermore, a Machine Learning methodology based on an LSTM network has been used to predict the model SST increments.

Monitoring time-dependent deformation patterns through geodetic techniques

In this thesis we focus on the analysis and interpretation of time dependent deformations recorded through different geodetic methods. Firstly, we apply a variational Bayesian Independent Component Analysis (vbICA) technique to GPS daily displacement solutions, to separate the postseismic deformation that followed the mainshocks of the 2016-2017 Central Italy seismic sequence from the other, hydrological, deformation sources. By interpreting the signal associated with the postseismic relaxation, we model an afterslip distribution on the faults involved by the mainshocks consistent with the co-seismic models available in literature. We find evidences of aseismic slip on the Paganica fault, responsible for the Mw 6.1 2009 L’Aquila earthquake, highlighting the importance of aseismic slip and static stress transfer to properly model the recurrence of earthquakes on nearby fault segments. We infer a possible viscoelastic relaxation of the lower crust as a contributing mechanism to the postseismic displacements. We highlight the importance of a proper separation of the hydrological signals for an accurate assessment of the tectonic processes, especially in cases of mm-scale deformations. Contextually, we provide a physical explanation to the ICs associated with the observed hydrological processes. In the second part of the thesis, we focus on strain data from Gladwin Tensor Strainmeters, working on the instruments deployed in Taiwan. We develop a novel approach, completely data driven, to calibrate these strainmeters. We carry out a joint analysis of geodetic (strainmeters, GPS and GRACE products) and hydrological (rain gauges and piezometers) data sets, to characterize the hydrological signals in Southern Taiwan. Lastly, we apply the calibration approach here proposed to the strainmeters recently installed in Central Italy. We provide, as an example, the detection of a storm that hit the Umbria-Marche regions (Italy), demonstrating the potential of strainmeters in following the dynamics of deformation processes with limited spatio-temporal signature

Modelling, simulations and monitoring for sustainable plant and animal production systems through precision technique

Protected crop production is a modern and innovative approach to cultivating plants in a controlled environment to optimize growth, yield, and quality. This method involves using structures such as greenhouses or tunnels to create a sheltered environment. These productive solutions are characterized by a careful regulation of variables like temperature, humidity, light, and ventilation, which collectively contribute to creating an optimal microclimate for plant growth. Heating, cooling, and ventilation systems are used to maintain optimal conditions for plant growth, regardless of external weather fluctuations. Protected crop production plays a crucial role in addressing challenges posed by climate variability, population growth, and food security. Similarly, animal husbandry involves providing adequate nutrition, housing, medical care and environmental conditions to ensure animal welfare. Then, sustainability is a critical consideration in all forms of agriculture, including protected crop and animal production. Sustainability in animal production refers to the practice of producing animal products in a way that minimizes negative impacts on the environment, promotes animal welfare, and ensures the long-term viability of the industry. Then, the research activities performed during the PhD can be inserted exactly in the field of Precision Agriculture and Livestock farming. Here the focus is on the computational fluid dynamic (CFD) approach and environmental assessment applied to improve yield, resource efficiency, environmental sustainability, and cost savings. It represents a significant shift from traditional farming methods to a more technology-driven, data-driven, and environmentally conscious approach to crop and animal production. On one side, CFD is powerful and precise techniques of computer modeling and simulation of airflows and thermo-hygrometric parameters, that has been applied to optimize the growth environment of crops and the efficiency of ventilation in pig barns. On the other side, the sustainability aspect has been investigated and researched in terms of Life Cycle Assessment analyses.

Integrated communication and learning towards autonomous mobile radio networks

The integration of distributed and ubiquitous intelligence has emerged over the last years as the mainspring of transformative advancements in mobile radio networks. As we approach the era of “mobile for intelligence”, next-generation wireless networks are poised to undergo significant and profound changes. Notably, the overarching challenge that lies ahead is the development and implementation of integrated communication and learning mechanisms that will enable the realization of autonomous mobile radio networks. The ultimate pursuit of eliminating human-in-the-loop constitutes an ambitious challenge, necessitating a meticulous delineation of the fundamental characteristics that artificial intelligence (AI) should possess to effectively achieve this objective. This challenge represents a paradigm shift in the design, deployment, and operation of wireless networks, where conventional, static configurations give way to dynamic, adaptive, and AI-native systems capable of self-optimization, self-sustainment, and learning. This thesis aims to provide a comprehensive exploration of the fundamental principles and practical approaches required to create autonomous mobile radio networks that seamlessly integrate communication and learning components. The first chapter of this thesis introduces the notion of Predictive Quality of Service (PQoS) and adaptive optimization and expands upon the challenge to achieve adaptable, reliable, and robust network performance in dynamic and ever-changing environments. The subsequent chapter delves into the revolutionary role of generative AI in shaping next-generation autonomous networks. This chapter emphasizes achieving trustworthy uncertainty-aware generation processes with the use of approximate Bayesian methods and aims to show how generative AI can improve generalization while reducing data communication costs. Finally, the thesis embarks on the topic of distributed learning over wireless networks. Distributed learning and its declinations, including multi-agent reinforcement learning systems and federated learning, have the potential to meet the scalability demands of modern data-driven applications, enabling efficient and collaborative model training across dynamic scenarios while ensuring data privacy and reducing communication overhead.

Predicting corticospinal excitability from pre-TMS EEG using convolutional neural networks

The amplitude of motor evoked potentials (MEPs) elicited by transcranial magnetic stimulation (TMS) of the primary motor cortex (M1) shows a large variability from trial to trial, although MEPs are evoked by the same repeated stimulus. A multitude of factors is believed to influence MEP amplitudes, such as cortical, spinal and motor excitability state. The goal of this work is to explore to which degree the variation in MEP amplitudes can be explained by the cortical state right before the stimulation. Specifically, we analyzed a dataset acquired on eleven healthy subjects comprising, for each subject, 840 single TMS pulses applied to the left M1 during acquisition of electroencephalography (EEG) and electromyography (EMG). An interpretable convolutional neural network, named SincEEGNet, was utilized to discriminate between low- and high-corticospinal excitability trials, defined according to the MEP amplitude, using in input the pre-TMS EEG. This data-driven approach enabled considering multiple brain locations and frequency bands without any a priori selection. Post-hoc interpretation techniques were adopted to enhance interpretation by identifying the more relevant EEG features for the classification. Results show that individualized classifiers successfully discriminated between low and high M1 excitability states in all participants. Outcomes of the interpretation methods suggest the importance of the electrodes situated over the TMS stimulation site, as well as the relevance of the temporal samples of the input EEG closer to the stimulation time. This novel decoding method allows causal investigation of the cortical excitability state, which may be relevant for personalizing and increasing the efficacy of therapeutic brain-state dependent brain stimulation (for example in patients affected by Parkinson’s disease).

Robotic Manipulation of DLOs for Wiring Harness Assembly: a Machine Learning Approach

In recent times, a significant research effort has been focused on how deformable linear objects (DLOs) can be manipulated for real world applications such as assembly of wiring harnesses for the automotive and aerospace sector. This represents an open topic because of the difficulties in modelling accurately the behaviour of these objects and simulate a task involving their manipulation, considering a variety of different scenarios. These problems have led to the development of data-driven techniques in which machine learning techniques are exploited to obtain reliable solutions. However, this approach makes the solution difficult to be extended, since the learning must be replicated almost from scratch as the scenario changes. It follows that some model-based methodology must be introduced to generalize the results and reduce the training effort accordingly. The objective of this thesis is to develop a solution for the DLOs manipulation to assemble a wiring harness for the automotive sector based on adaptation of a base trajectory set by means of reinforcement learning methods. The idea is to create a trajectory planning software capable of solving the proposed task, reducing where possible the learning time, which is done in real time, but at the same time presenting suitable performance and reliability. The solution has been implemented on a collaborative 7-DOFs Panda robot at the Laboratory of Automation and Robotics of the University of Bologna. Experimental results are reported showing how the robot is capable of optimizing the manipulation of the DLOs gaining experience along the task repetition, but showing at the same time a high success rate from the very beginning of the learning phase.

‘Data Augmentation’ per reti neurali profonde per la classificazione del segnale EEG

I recenti sviluppi nel campo dell’intelligenza artificiale hanno permesso una più adeguata classificazione del segnale EEG. Negli ultimi anni è stato dimostrato come sia possibile ottenere ottime performance di classificazione impiegando tecniche di Machine Learning (ML) e di Deep Learning (DL), facendo uso, per quest’ultime, di reti neurali convoluzionali (Convolutional Neural Networks, CNN). In particolare, il Deep Learning richiede molti dati di training mentre spesso i dataset per EEG sono limitati ed è difficile quindi raggiungere prestazioni elevate. I metodi di Data Augmentation possono alleviare questo problema. Partendo da dati reali, questa tecnica permette, la creazione di dati artificiali fondamentali per aumentare le dimensioni del dataset di partenza. L’applicazione più comune è quella di utilizzare i Data Augmentation per aumentare le dimensioni del training set, in modo da addestrare il modello/rete neurale su un numero di campioni più esteso, riducendo gli errori di classificazione. Partendo da questa idea, i Data Augmentation sono stati applicati in molteplici campi e in particolare per la classificazione del segnale EEG. In questo elaborato di tesi, inizialmente, vengono descritti metodi di Data Augmentation implementati nel corso degli anni, utilizzabili anche nell’ambito di applicazioni EEG. Successivamente, si presentano alcuni studi specifici che applicano metodi di Data Augmentation per migliorare le presentazioni di classificatori basati su EEG per l’identificazione dello stato sonno/veglia, per il riconoscimento delle emozioni, e per la classificazione di immaginazione motoria.

Aplicações metodologicas em educação fisica/ciencias do esporte : recortes da experiencia da Saude Coletiva e Atividade Fisica da UNICAMP

Universidade Estadual de Campinas . Faculdade de Educação Física

Kinematic parameters and membership probabilities of open clusters in the Bordeaux PM2000 catalogue

Aims. We derive lists of proper-motions and kinematic membership probabilities for 49 open clusters and possible open clusters in the zone of the Bordeaux PM2000 proper motion catalogue (+ 11 degrees <= delta <= + 18 degrees). We test different parametrisations of the proper motion and position distribution functions and select the most successful one. In the light of those results, we analyse some objects individually. Methods. We differenciate between cluster and field member stars, and assign membership probabilities, by applying a new and fully automated method based on both parametrisations of the proper motion and position distribution functions, and genetic algorithm optimization heuristics associated with a derivative-based hill climbing algorithm for the likelihood optimization. Results. We present a catalogue comprising kinematic parameters and associated membership probability lists for 49 open clusters and possible open clusters in the Bordeaux PM2000 catalogue region. We note that this is the first determination of proper motions for five open clusters. We confirm the non-existence of two kinematic populations in the region of 15 previously suspected non-existent objects.

Sensorless synchronization method for thin-film direct optical broadband monitoring system

Optical monitoring systems are necessary to manufacture multilayer thin-film optical filters with low tolerance on spectrum specification. Furthermore, to have better accuracy on the measurement of film thickness, direct monitoring is a must. Direct monitoring implies acquiring spectrum data from the optical component undergoing the film deposition itself, in real time. In making film depositions on surfaces of optical components, the high vacuum evaporator chamber is the most popular equipment. Inside the evaporator, at the top of the chamber, there is a metallic support with several holes where the optical components are assembled. This metallic support has rotary motion to promote film homogenization. To acquire a measurement of the spectrum of the film in deposition, it is necessary to pass a light beam through a glass witness undergoing the film deposition process, and collect a sample of the light beam using a spectrometer. As both the light beam and the light collector are stationary, a synchronization system is required to identify the moment at which the optical component passes through the light beam.

Comparison of friction models applied to a control valve

Eight different models to represent the effect of friction in control valves are presented: four models based on physical principles and four empirical ones. The physical models, both static and dynamic, have the same structure. The models are implemented in Simulink/Matlab (R) and compared, using different friction coefficients and input signals. Three of the models were able to reproduce the stick-slip phenomenon and passed all the tests, which were applied following ISA standards. (C) 2008 Elsevier Ltd. All rights reserved.

An evaluation of the evidence for linkages between mangroves and fisheries: A synthesis of the literature and identification of research directions

There is a widely held paradigm that mangroves are critical for sustaining production in coastal fisheries through their role as important nursery areas for fisheries species. This paradigm frequently forms the basis for important management decisions on habitat conservation and restoration of mangroves and other coastal wetlands. This paper reviews the current status of the paradigm and synthesises the information on the processes underlying these potential links. In the past, the paradigm has been supported by studies identifying correlations between the areal and linear extent of mangroves and fisheries catch. This paper goes beyond the correlative approach to develop a new framework on which future evaluations can be based. First, the review identifies what type of marine animals are using mangroves and at what life stages. These species can be categorised as estuarine residents, marine-estuarine species and marine stragglers. The marine-estuarine category includes many commercial species that use mangrove habitats as nurseries. The second stage is to determine why these species are using mangroves as nurseries. The three main proposals are that mangroves provide a refuge from predators, high levels of nutrients and shelter from physical disturbances. The recognition of the important attributes of mangrove nurseries then allows an evaluation of how changes in mangroves will affect the associated fauna. Surprisingly few studies have addressed this question. Consequently, it is difficult to predict how changes in any of these mangrove attributes would affect the faunal communities within them and, ultimately, influence the fisheries associated with them. From the information available, it seems likely that reductions in mangrove habitat complexity would reduce the biodiversity and abundance of the associated fauna, and these changes have the potential to cause cascading effects at higher trophic levels with possible consequences for fisheries. Finally, there is a discussion of the data that are currently available on mangrove distribution and fisheries catch, the limitations of these data and how best to use the data to understand mangrove-fisheries links and, ultimately, to optimise habitat and fisheries management. Examples are drawn from two relatively data-rich regions, Moreton Bay (Australia) and Western Peninsular Malaysia, to illustrate the data needs and research requirements for investigating the mangrove-fisheries paradigm. Having reliable and accurate data at appropriate spatial and temporal scales is crucial for mangrove-fisheries investigations. Recommendations are made for improvements to data collection methods that would meet these important criteria. This review provides a framework on which to base future investigations of mangrove-fisheries links, based on an understanding of the underlying processes and the need for rigorous data collection. Without this information, the understanding of the relationship between mangroves and fisheries will remain limited. Future investigations of mangrove-fisheries links must take this into account in order to have a good ecological basis and to provide better information and understanding to both fisheries and conservation managers.

Is PHEEM a multi-dimensional instrument? An international perspective

Aim: To look at the characteristics of Postgraduate Hospital Educational Environment Measure (PHEEM) using data from the UK, Brazil, Chile and the Netherlands, and to examine the reliability and characteristics of PHEEM, especially how the three PHEEM subscales fitted with factors derived statistically from the data sets. Methods: Statistical analysis of PHEEM scores from 1563 sets of data, using reliability analysis, exploratory factor analysis and correlations of factors derived with the three defined PHEEM subscales. Results: PHEEM was very reliable with an overall Cronbach`s alpha of 0.928. Three factors were derived by exploratory factor analysis. Factor One correlated most strongly with the teaching subscale (R=0.802), Factor Two correlated most strongly with the role autonomy subscale (R=0.623) and Factor Three correlated most strongly with the social support subscale (R=0.538). Conclusions: PHEEM is a multi-dimensional instrument. Overall, it is very reliable. There is a good fit of the three defined subscales, derived by qualitative methods, with the three principal factors derived from the data by exploratory factor analysis.

From EEG to BOLD: Brain mapping and estimating transfer functions in simultaneous EEG-fMRI acquisitions

Simultaneous acquisition of electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) aims to disentangle the description of brain processes by exploiting the advantages of each technique. Most studies in this field focus on exploring the relationships between fMRI signals and the power spectrum at some specific frequency bands (alpha, beta, etc.). On the other hand, brain mapping of EEG signals (e.g., interictal spikes in epileptic patients) usually assumes an haemodynamic response function for a parametric analysis applying the GLM, as a rough approximation. The integration of the information provided by the high spatial resolution of MR images and the high temporal resolution of EEG may be improved by referencing them by transfer functions, which allows the identification of neural driven areas without strong assumptions about haemodynamic response shapes or brain haemodynamic`s homogeneity. The difference on sampling rate is the first obstacle for a full integration of EEG and fMRI information. Moreover, a parametric specification of a function representing the commonalities of both signals is not established. In this study, we introduce a new data-driven method for estimating the transfer function from EEG signal to fMRI signal at EEG sampling rate. This approach avoids EEG subsampling to fMRI time resolution and naturally provides a test for EEG predictive power over BOLD signal fluctuations, in a well-established statistical framework. We illustrate this concept in resting state (eyes closed) and visual simultaneous fMRI-EEG experiments. The results point out that it is possible to predict the BOLD fluctuations in occipital cortex by using EEG measurements. (C) 2010 Elsevier Inc. All rights reserved.