Human Presence Detection: analisi comparativa e caso di studio in Home Manager

La possibilità di monitorare l’attività degli utenti in un sistema domotico, sia considerando le azioni effettuate direttamente sul sistema che le informazioni ricavabili da strumenti esterni come la loro posizione GPS, è un fattore importante per anticipare i bisogni e comprendere le preferenze degli utenti stessi, rendendo sempre più intelligenti ed autonomi i sistemi domotici. Mentre i sistemi attualmente disponibili non includono o non sfruttano appieno queste potenzialità, l'obiettivo di sistemi prototipali sviluppati per fini di ricerca, quali ad esempio Home Manager, è invece quello di utilizzare le informazioni ricavabili dai dispositivi e dal loro utilizzo per abilitare ragionamenti e politiche di ordine superiore. Gli obiettivi di questo lavoro sono: - Classificare ed elencare i diversi sensori disponibili al fine di presentare lo stato attuale della ricerca nel campo dello Human Sensing, ovvero del rilevamento di persone in un ambiente. - Giustificare la scelta della telecamera come sensore per il rilevamento di persone in un ambiente domestico, riportando metodi per l’analisi video in grado di interpretare i fotogrammi e rilevare eventuali figure in movimento al loro interno. - Presentare un’architettura generica per integrare dei sensori in un sistema di sorveglianza, implementando tale architettura ed alcuni algoritmi per l’analisi video all’interno di Home Manager con l’aiuto della libreria OpenCV .

Human Presence Detection in ambiente Home Manager: sperimentazione su piattaforma Raspberry

Home Manager, è una piattaforma sperimentale per la gestione di Smart Space e in particolare di una casa intelligente immersa in uno ambiente, avente l'ambizione di anticipare le necessità dell'utente. Questa tesi ha due obiettivi fondamentali: in primo luogo, implementare su piattaforma Raspberry la parte di Home Manager relativa allo scenario del riconoscimento delle persone negli ambienti della casa, mediante l'utilizzo del modulo telecamera; in secondo luogo, attraverso le informazioni ricavate precedentemente, implementare e simulare una gestione intelligente e automatica delle luci presenti all'interno della casa, sfruttando a tal fine un modulo relè.

Analysis of human posterior EEG alpha frequency as a function of implicit learning of probabilistic lateralized stimuli in a visual detection task

Alpha oscillatory activity has long been associated with perceptual and cognitive processes related to attention control. The aim of this study is to explore the task-dependent role of alpha frequency in a lateralized visuo-spatial detection task. Specifically, the thesis focuses on consolidating the scientific literature's knowledge about the role of alpha frequency in perceptual accuracy, and deepening the understanding of what determines trial-by-trial fluctuations of alpha parameters and how these fluctuations influence overall task performance. The hypotheses, confirmed empirically, were that different implicit strategies are put in place based on the task context, in order to maximize performance with optimal resource distribution (namely alpha frequency, associated positively with performance): “Lateralization” of the attentive resources towards one hemifield should be associated with higher alpha frequency difference between contralateral and ipsilateral hemisphere; “Distribution” of the attentive resources across hemifields should be associated with lower alpha frequency difference between hemispheres; These strategies, used by the participants according to their brain capabilities, have proven themselves adaptive or maladaptive depending on the different tasks to which they have been set: "Distribution" of the attentive resources seemed to be the best strategy when the distribution probability between hemifields was balanced: i.e. the neutral condition task. "Lateralization" of the attentive resources seemed to be more effective when the distribution probability between hemifields was biased towards one hemifield: i.e., the biased condition task.

Multiple pathogen detection using nanoplasmonic sensing

Opportunistic diseases caused by Human Immunodeficiency Virus (HIV) and Hepatitis B Virus (HBV) is an omnipresent global challenge. In order to manage these epidemics, we need to have low cost and easily deployable platforms at the point-of-care in high congestions regions like airports and public transit systems. In this dissertation we present our findings in using Localized Surface Plasmon Resonance (LSPR)-based detection of pathogens and other clinically relevant applications using microfluidic platforms at the point-of-care setting in resource constrained environment. The work presented here adopts the novel technique of LSPR to multiplex a lab-on-a-chip device capable of quantitatively detecting various types of intact viruses and its various subtypes, based on the principle of a change in wavelength occurring when metal nano-particle surface is modified with a specific surface chemistry allowing the binding of a desired pathogen to a specific antibody. We demonstrate the ability to detect and quantify subtype A, B, C, D, E, G and panel HIV with a specificity of down to 100 copies/mL using both whole blood sample and HIV-patient blood sample discarded from clinics. These results were compared against the gold standard Reverse Transcriptase Polymerase Chain Reaction (RT-qPCR). This microfluidic device has a total evaluation time for the assays of about 70 minutes, where 60 minutes is needed for the capture and 10 minutes for data acquisition and processing. This LOC platform eliminates the need for any sample preparation before processing. This platform is highly multiplexable as the same surface chemistry can be adapted to capture and detect several other pathogens like dengue virus, E. coli, M. Tuberculosis, etc.

Automatic detection of the inferior alveolar nerve in CT scans with CenterNet

The inferior alveolar nerve (IAN) lies within the mandibular canal, named inferior alveolar canal in literature. The detection of this nerve is important during maxillofacial surgeries or for creating dental implants. The poor quality of cone-beam computed tomography (CBCT) and computed tomography (CT) scans and/or bone gaps within the mandible increase the difficulty of this task, posing a challenge to human experts who are going to manually detect it and resulting in a time-consuming task.Therefore this thesis investigates two methods to automatically detect the IAN: a non-data driven technique and a deep-learning method. The latter tracks the IAN position at each frame leveraging detections obtained with the deep neural network CenterNet, fined-tuned for our task, and temporal and spatial information.

Model-Based validation of Driver Drowsiness Detection System for ADAS

The work described in this Master’s Degree thesis was born after the collaboration with the company Maserati S.p.a, an Italian luxury car maker with its headquarters located in Modena, in the heart of the Italian Motor Valley, where I worked as a stagiaire in the Virtual Engineering team between September 2021 and February 2022. This work proposes the validation using real-world ECUs of a Driver Drowsiness Detection (DDD) system prototype based on different detection methods with the goal to overcome input signal losses and system failures. Detection methods of different categories have been chosen from literature and merged with the goal of utilizing the benefits of each of them, overcoming their limitations and limiting as much as possible their degree of intrusiveness to prevent any kind of driving distraction: an image processing-based technique for human physical signals detection as well as methods based on driver-vehicle interaction are used. A Driver-In-the-Loop simulator is used to gather real data on which a Machine Learning-based algorithm will be trained and validated. These data come from the tests that the company conducts in its daily activities so confidential information about the simulator and the drivers will be omitted. Although the impact of the proposed system is not remarkable and there is still work to do in all its elements, the results indicate the main advantages of the system in terms of robustness against subsystem failures and signal losses.

Production Lot Detection through Synthetic Generated Data

Correctness of information gathered in production environments is an essential part of quality assurance processes in many industries, this task is often performed by human resources who visually take annotations in various steps of the production flow. Depending on the performed task the correlation between where exactly the information is gathered and what it represents is more than often lost in the process. The lack of labeled data places a great boundary on the application of deep neural networks aimed at object detection tasks, moreover supervised training of deep models requires a great amount of data to be available. Reaching an adequate large collection of labeled images through classic techniques of data annotations is an exhausting and costly task to perform, not always suitable for every scenario. A possible solution is to generate synthetic data that replicates the real one and use it to fine-tune a deep neural network trained on one or more source domains to a different target domain. The purpose of this thesis is to show a real case scenario where the provided data were both in great scarcity and missing the required annotations. Sequentially a possible approach is presented where synthetic data has been generated to address those issues while standing as a training base of deep neural networks for object detection, capable of working on images taken in production-like environments. Lastly, it compares performance on different types of synthetic data and convolutional neural networks used as backbones for the model.