Il segnale EEG in un compito di ’center-out reaching’: analisi e decodifica a livello di scalpo e di corteccia

Nellâ analisi del segnale EEG, sono di particolare interesse i potenziali evento correlato (ERP), che descrivono la risposta cerebrale in seguito alla presentazione di stimoli o eventi esterni o interni. Questi potenziali non sono immediatamente visibili sul tracciato EEG grezzo, ed è necessario, oltre ad unâ��accurata fase di preprocessing, mediare (averaging) i segnali di molti trial ripetuti per visualizzare tali risposte nel tempo. Questo studio ha posto l' attenzione sugli ERP visuomotori generati in un compito di center-out reaching, che prevede il raggiungimento di uno tra cinque target, ognuno associato ad un LED, mediante il braccio dominante, con una tempistica scandita dalla presentazione di due stimoli visivi: lo stimolo preparatorio ¸ (che indica il target) e lo stimolo imperativo (che dà il via libera al movimento). I segnali ERP, ottenuti mediante la tecnica dellâ averaging, sono stati analizzati sia a livello di scalpo, considerando i segnali di elettrodo, sia a livello di corteccia, dopo risoluzione del problema inverso, e considerando rappresentazioni prima a livello di singoli dipoli corticali e quindi di intere regioni corticali (ROI). Inoltre, è stata applicato un metodo di deep learning (rete neurale convoluzionale) per decodificare il segnale EEG a livello di singolo trial, ovvero classificare il target coinvolto nello specifico trial. La decodifica è stata applicata sia ai segnali di scalpo sia ai segnali delle ROI corticali. Complessivamente i risultati mostrano ERP ben visibili a livello di scalpo e legati sia a processing visivo che motorio. Gli ERP a livello di ROI corticali sono più rumorosi e sembrano cogliere meno processing motorio rispetto al visivo, presumibilmente anche in conseguenza di alcune scelte metodologiche nella ricostruzione di segnali di ROI. In linea con questo, le performance di decodifica sono migliori a livello di scalpo che di ROI corticali.

Implementazione di banca dati di immagini per lo sviluppo di algoritmi per la navigazione aerea automatica

Lo scopo di questo studio è l’implementazione di un sistema di navigazione autonomo in grado di calcolare la traiettoria di un mezzo aereo, noti che siano a priori dei punti di posizione detti waypoint. A partire da questa traiettoria, è possibile ottenere la sua rappresentazione in un codice che mette a disposizione immagini satellitari e ricavare le viste del terreno sorvolato in una serie di punti calcolati, in modo da garantire in ogni sequenza la presenza di elementi comuni rispetto a quella precedente. Lo scopo della realizzazione di questa banca dati è rendere possibili futuri sviluppi di algoritmi di navigazione basati su deep learning e reti neurali. Le immagini virtuali ottenute del terreno saranno in futuro applicate alla navigazione autonoma per agricoltura di precisione mediante droni. Per lo studio condotto è stato simulato un generico velivolo, con o senza pilota, dotato di una videocamera fissata su una sospensione cardanica a tre assi (gimbal). La tesi, dunque, introduce ai più comuni metodi di determinazione della posizione dei velivoli e alle più recenti soluzioni basate su algoritmi di Deep Learning e sistemi vision-based con reti neurali e segue in un approfondimento sul metodo di conversione degli angoli e sulla teoria matematica che ne sta alla base. Successivamente, analizza nel dettaglio il processo di simulazione della navigazione autonoma e della determinazione della traiettoria in ambiente software Matlab e Simulink, procedendo nell’analisi di alcuni casi di studio in ambienti realistici. L’elaborato si conclude con un breve riepilogo di quanto svolto e con alcune considerazioni sugli sviluppi futuri.

Copy-paste data augmentation for domain transfer on traffic signs

City streets carry a lot of information that can be exploited to improve the quality of the services the citizens receive. For example, autonomous vehicles need to act accordingly to all the element that are nearby the vehicle itself, like pedestrians, traffic signs and other vehicles. It is also possible to use such information for smart city applications, for example to predict and analyze the traffic or pedestrian flows. Among all the objects that it is possible to find in a street, traffic signs are very important because of the information they carry. This information can in fact be exploited both for autonomous driving and for smart city applications. Deep learning and, more generally, machine learning models however need huge quantities to learn. Even though modern models are very good at gener- alizing, the more samples the model has, the better it can generalize between different samples. Creating these datasets organically, namely with real pictures, is a very tedious task because of the wide variety of signs available in the whole world and especially because of all the possible light, orientation conditions and con- ditions in general in which they can appear. In addition to that, it may not be easy to collect enough samples for all the possible traffic signs available, cause some of them may be very rare to find. Instead of collecting pictures manually, it is possible to exploit data aug- mentation techniques to create synthetic datasets containing the signs that are needed. Creating this data synthetically allows to control the distribution and the conditions of the signs in the datasets, improving the quality and quantity of training data that is going to be used. This thesis work is about using copy-paste data augmentation to create synthetic data for the traffic sign recognition task.

Robotic grasping: State of the art and modular real-world implementation

Robotic Grasping is an important research topic in robotics since for robots to attain more general-purpose utility, grasping is a necessary skill, but very challenging to master. In general the robots may use their perception abilities like an image from a camera to identify grasps for a given object usually unknown. A grasp describes how a robotic end-effector need to be positioned to securely grab an object and successfully lift it without lost it, at the moment state of the arts solutions are still far behind humans. In the last 5–10 years, deep learning methods take the scene to overcome classical problem like the arduous and time-consuming approach to form a task-specific algorithm analytically. In this thesis are present the progress and the approaches in the robotic grasping field and the potential of the deep learning methods in robotic grasping. Based on that, an implementation of a Convolutional Neural Network (CNN) as a starting point for generation of a grasp pose from camera view has been implemented inside a ROS environment. The developed technologies have been integrated into a pick-and-place application for a Panda robot from Franka Emika. The application includes various features related to object detection and selection. Additionally, the features have been kept as generic as possible to allow for easy replacement or removal if needed, without losing time for improvement or new testing.

End-to-end Deep Metric Learning con Vision-Language Model per il Fashion Image Captioning

L'image captioning è un task di machine learning che consiste nella generazione di una didascalia, o caption, che descriva le caratteristiche di un'immagine data in input. Questo può essere applicato, ad esempio, per descrivere in dettaglio i prodotti in vendita su un sito di e-commerce, migliorando l'accessibilità del sito web e permettendo un acquisto più consapevole ai clienti con difficoltà visive. La generazione di descrizioni accurate per gli articoli di moda online è importante non solo per migliorare le esperienze di acquisto dei clienti, ma anche per aumentare le vendite online. Oltre alla necessità di presentare correttamente gli attributi degli articoli, infatti, descrivere i propri prodotti con il giusto linguaggio può contribuire a catturare l'attenzione dei clienti. In questa tesi, ci poniamo l'obiettivo di sviluppare un sistema in grado di generare una caption che descriva in modo dettagliato l'immagine di un prodotto dell'industria della moda dato in input, sia esso un capo di vestiario o un qualche tipo di accessorio. A questo proposito, negli ultimi anni molti studi hanno proposto soluzioni basate su reti convoluzionali e LSTM. In questo progetto proponiamo invece un'architettura encoder-decoder, che utilizza il modello Vision Transformer per la codifica delle immagini e GPT-2 per la generazione dei testi. Studiamo inoltre come tecniche di deep metric learning applicate in end-to-end durante l'addestramento influenzino le metriche e la qualità delle caption generate dal nostro modello.

Seven retinal specializations in the tubular eye of the deep-sea pearleye, Scopelarchus michaelsarsi: A case study in visual optimization

The deep-sea pearleye, Scopelarchus michaelsarsi (Scopelarchidae) is a mesopelagic teleost with asymmetric or tubular eyes. The main retina subtends a large dorsal binocular field, while the accessory retina subtends a restricted monocular field of lateral visual space. Ocular specializations to increase the lateral visual field include an oblique pupil and a corneal lens pad. A detailed morphological and topographic study of the photoreceptors and retinal ganglion cells reveals seven specializations: a centronasal region of the main retina with ungrouped rod-like photoreceptors overlying a retinal tapetum; a region of high ganglion cell density (area centralis of 56.1x10(3) cells per mm(2)) in the centrolateral region of the main retina; a centrotemporal region of the main retina with grouped rod-like photoreceptors; a region (area giganto cellularis) of large (32.2+/-5.6 mu m(2)), alpha-like ganglion cells arranged in a regular array (nearest neighbour distance 53.5+/-9.3 mu m with a conformity ratio of 5.8) in the temporal main retina; an accessory retina with grouped rod-like photoreceptors; a nasotemporal band of a mixture of rod-and cone-like photoreceptors restricted to the ventral accessory retina; and a retinal diverticulum comprised of a ventral region of differentiated accessory retina located medial to the optic nerve head. Retrograde labelling from the optic nerve with DiI shows that approximately 14% of the cells in the ganglion cell layer of the main retina are displaced amacrine cells at 1.5 mm eccentricity. Cryosectioning of the tubular eye confirms Matthiessen's ratio (2.59), and calculations of the spatial resolving power suggests that the function of the area centralis (7.4 cycles per degree/8.1 minutes of are) and the cohort of temporal alpha-like ganglion cells (0.85 cycles per degree/70.6 minutes of are) in the main retina may be different. Low summation ratios in these various retinal zones suggests that each zone may mediate distinct visual tasks in a certain region of the visual field by optimizing sensitivity and/or resolving power.

The eyes of deep-sea fish I: Lens pigmentation, tapeta and visual pigments

Deep-sea fish, defined as those living below 200 m, inhabit a most unusual photic environment, being exposed to two sources of visible radiation: very dim downwelling sunlight and bioluminescence, both of which are, in most cases. maximal at wavelengths around 450-500 nm. This paper summarises the reflective properties of the ocular tapeta often found in these animals the pigmentation of their lenses and the absorption characteristics of their visual pigments. Deepsea tapeta usually appear blue to the human observer. reflecting mainly shortwave radiation. However, reflection in other parts of the spectrum is not uncommon and uneven tapetal distribution across the retina is widespread. Perhaps surprisingly, given the fact that they live in a photon limited environment, the lenses of some deep-sea teleosts are bright yellow, absorbing much of the shortwave part of the spectrum. Such lenses contain a variety of biochemically distinct pigments which most likely serve to enhance the visibility of bioluminescent signals. Of the 195 different visual pigments characterised by either detergent extract or microspectrophotometry in the retinae of deep-sea fishes, cn. 87% have peak absorbances within the range 468-494 nm. Modelling shows that this is most likely an adaptation for the detection of bioluminescence. Around 13% of deep-sea fish have retinae containing more than one visual pigment. Of these, we highlight three genera of stomiid dragonfishes, which uniquely produce far red bioluminescence from suborbital photophores. Using a combination of longwave-shifted visual pigments and in one species (Malacosteus niger) a chlorophyll-related photosensitizer. these fish have evolved extreme red sensitivity enabling them to see their own bioluminescence and giving them a private spectral waveband invisible to other inhabitants of the deep-ocean. (C) 1998 Elsevier Science Ltd. All rights reserved.

Implication of the visual system in the regulation of activity cycles in the absence of solar light: 2-[I-125]iodomelatonin binding sites and melatonin receptor gene expression in the brains of demersal deep-sea gadiform fish

Relative eye size, gross brain morphology and central localization of 2-[I-125]iodomelatonin binding sites and melatonin receptor gene expression were compared in six gadiform fish living at different depths in the north-east Atlantic Ocean: Phycis blennoides (capture depth range 265-1260 m), Nezumia aequalis (445-1512 m), Coryphaenoides rupestris (706-1932 m), Trachyrincus murrayi (1010-1884 m), Coryphaenoides guentheri (1030 m) and Coryphaenoides (Nematonurus) armatus (2172-4787 m). Amongst these, the eye size range was 0.15-0.35 of head length with a value of 0.19 for C.(N.) armatus, the deepest species. Brain morphology reflected behavioural differences with well-developed olfactory regions in P.blennoides, T.murrayi and C. (N.) armatus and evidence of olfactory deficit in N. aequalis, C. rupestris and C. guentheri. All species had a clearly defined optic tectum with 2-[I-125] iodomelatonin binding and melatonin receptor gene expression localized to specific brain regions in a similar pattern to that found in shallow-water fish. Melatonin receptors were found throughout the visual structures of the brains of all species. Despite living beyond the depth of penetration of solar light these fish have retained central features associated with the coupling of cycles of growth, behaviour and reproduction to the diel light-dark cycle. How this functions in the deep sea remains enigmatic.

Processing Speed and Working Memory Span: Their Differential Role in Superficial and Deep Memory Processes in Schizophrenia

Previous work has suggested that decrement in both processing speed and working memory span plays a role in the memory impairment observed in patients with schizophrenia. We undertook a study to examine simultaneously the effect of these two factors. A sample of 49 patients with schizophrenia and 43 healthy controls underwent a battery of verbal and visual memory tasks. Superficial and deep encoding memory measures were tallied. We conducted regression analyses on the various memory measures, using processing speed and working memory span as independent variables. In the patient group, processing speed was a significant predictor of superficial and deep memory measures in verbal and visual memory. Working memory span was an additional significant predictor of the deep memory measures only. Regression analyses involving all participants revealed that the effect of diagnosis on all the deep encoding memory measures was reduced to non-significance when processing speed was entered in the regression. Decreased processing speed is involved in verbal and visual memory deficit in patients, whether the task require superficial or deep encoding. Working memory is involved only insofar as the task requires a certain amount of effort. (JINS, 2011, 17, 485-493)

High-Content Analysis of Breast Cancer Using Single-Cell Deep Transfer Learning

High-content analysis has revolutionized cancer drug discovery by identifying substances that alter the phenotype of a cell, which prevents tumor growth and metastasis. The high-resolution biofluorescence images from assays allow precise quantitative measures enabling the distinction of small molecules of a host cell from a tumor. In this work, we are particularly interested in the application of deep neural networks (DNNs), a cutting-edge machine learning method, to the classification of compounds in chemical mechanisms of action (MOAs). Compound classification has been performed using image-based profiling methods sometimes combined with feature reduction methods such as principal component analysis or factor analysis. In this article, we map the input features of each cell to a particular MOA class without using any treatment-level profiles or feature reduction methods. To the best of our knowledge, this is the first application of DNN in this domain, leveraging single-cell information. Furthermore, we use deep transfer learning (DTL) to alleviate the intensive and computational demanding effort of searching the huge parameter's space of a DNN. Results show that using this approach, we obtain a 30% speedup and a 2% accuracy improvement.

The Visual and Virtual in Contemporary European Learning Contexts

Special issue of Anthropology in Action originated from the Working Images Conference, a joint meeting of TAN and VAN EASA networks

A multicase study for the evaluation of a pattern-based visual design process for collaborative learning

Collage is a pattern-based visual design authoring tool for the creation of collaborative learning scripts computationally modelled with IMS Learning Design (LD). The pattern-based visual approach aims to provide teachers with design ideas that are based on broadly accepted practices. Besides, it seeks hiding the LD notation so that teachers can easily create their own designs. The use of visual representations supports both the understanding of the design ideas and the usability of the authoring tool. This paper presents a multicase study comprising three different cases that evaluate the approach from different perspectives. The first case includes workshops where teachers use Collage. A second case implies the design of a scenario proposed by a third-party using related approaches. The third case analyzes a situation where students follow a design created with Collage. The cross-case analysis provides a global understanding of the possibilities and limitations of the pattern-based visual design approach.

Learning Robot Motions from Visual Sensing

Learning from demonstration becomes increasingly popular as an efficient way of robot programming. Not only a scientific interest acts as an inspiration in this case but also the possibility of producing the machines that would find application in different areas of life: robots helping with daily routine at home, high performance automata in industries or friendly toys for children. One way to teach a robot to fulfill complex tasks is to start with simple training exercises, combining them to form more difficult behavior. The objective of the Master’s thesis work was to study robot programming with visual input. Dynamic movement primitives (DMPs) were chosen as a tool for motion learning and generation. Assuming a movement to be a spring system influenced by an external force, making this system move, DMPs represent the motion as a set of non-linear differential equations. During the experiments the properties of DMP, such as temporal and spacial invariance, were examined. The effect of the DMP parameters, including spring coefficient, damping factor, temporal scaling, on the trajectory generated were studied.

Signaled two-way avoidance learning using electrical stimulation of the inferior colliculus as negative reinforcement: effects of visual and auditory cues as warning stimuli

The inferior colliculus is a primary relay for the processing of auditory information in the brainstem. The inferior colliculus is also part of the so-called brain aversion system as animals learn to switch off the electrical stimulation of this structure. The purpose of the present study was to determine whether associative learning occurs between aversion induced by electrical stimulation of the inferior colliculus and visual and auditory warning stimuli. Rats implanted with electrodes into the central nucleus of the inferior colliculus were placed inside an open-field and thresholds for the escape response to electrical stimulation of the inferior colliculus were determined. The rats were then placed inside a shuttle-box and submitted to a two-way avoidance paradigm. Electrical stimulation of the inferior colliculus at the escape threshold (98.12 ± 6.15 (A, peak-to-peak) was used as negative reinforcement and light or tone as the warning stimulus. Each session consisted of 50 trials and was divided into two segments of 25 trials in order to determine the learning rate of the animals during the sessions. The rats learned to avoid the inferior colliculus stimulation when light was used as the warning stimulus (13.25 ± 0.60 s and 8.63 ± 0.93 s for latencies and 12.5 ± 2.04 and 19.62 ± 1.65 for frequencies in the first and second halves of the sessions, respectively, P<0.01 in both cases). No significant changes in latencies (14.75 ± 1.63 and 12.75 ± 1.44 s) or frequencies of responses (8.75 ± 1.20 and 11.25 ± 1.13) were seen when tone was used as the warning stimulus (P>0.05 in both cases). Taken together, the present results suggest that rats learn to avoid the inferior colliculus stimulation when light is used as the warning stimulus. However, this learning process does not occur when the neutral stimulus used is an acoustic one. Electrical stimulation of the inferior colliculus may disturb the signal transmission of the stimulus to be conditioned from the inferior colliculus to higher brain structures such as amygdala