Supporting Scientific Research Through Machine and Deep Learning: Fluorescence Microscopy and Operational Intelligence Use Cases

Although the debate of what data science is has a long history and has not reached a complete consensus yet, Data Science can be summarized as the process of learning from data. Guided by the above vision, this thesis presents two independent data science projects developed in the scope of multidisciplinary applied research. The first part analyzes fluorescence microscopy images typically produced in life science experiments, where the objective is to count how many marked neuronal cells are present in each image. Aiming to automate the task for supporting research in the area, we propose a neural network architecture tuned specifically for this use case, cell ResUnet (c-ResUnet), and discuss the impact of alternative training strategies in overcoming particular challenges of our data. The approach provides good results in terms of both detection and counting, showing performance comparable to the interpretation of human operators. As a meaningful addition, we release the pre-trained model and the Fluorescent Neuronal Cells dataset collecting pixel-level annotations of where neuronal cells are located. In this way, we hope to help future research in the area and foster innovative methodologies for tackling similar problems. The second part deals with the problem of distributed data management in the context of LHC experiments, with a focus on supporting ATLAS operations concerning data transfer failures. In particular, we analyze error messages produced by failed transfers and propose a Machine Learning pipeline that leverages the word2vec language model and K-means clustering. This provides groups of similar errors that are presented to human operators as suggestions of potential issues to investigate. The approach is demonstrated on one full day of data, showing promising ability in understanding the message content and providing meaningful groupings, in line with previously reported incidents by human operators.

On the role of Computational Logic in Data Science: representing, learning, reasoning, and explaining knowledge

In this thesis we discuss in what ways computational logic (CL) and data science (DS) can jointly contribute to the management of knowledge within the scope of modern and future artificial intelligence (AI), and how technically-sound software technologies can be realised along the path. An agent-oriented mindset permeates the whole discussion, by stressing pivotal role of autonomous agents in exploiting both means to reach higher degrees of intelligence. Accordingly, the goals of this thesis are manifold. First, we elicit the analogies and differences among CL and DS, hence looking for possible synergies and complementarities along 4 major knowledge-related dimensions, namely representation, acquisition (a.k.a. learning), inference (a.k.a. reasoning), and explanation. In this regard, we propose a conceptual framework through which bridges these disciplines can be described and designed. We then survey the current state of the art of AI technologies, w.r.t. their capability to support bridging CL and DS in practice. After detecting lacks and opportunities, we propose the notion of logic ecosystem as the new conceptual, architectural, and technological solution supporting the incremental integration of symbolic and sub-symbolic AI. Finally, we discuss how our notion of logic ecosys- tem can be reified into actual software technology and extended towards many DS-related directions.

Temporary teams learning and performance: the case of 3D printing technology in orthopaedic surgery

This dissertation contributes to the scholarly debate on temporary teams by exploring team interactions and boundaries.The fundamental challenge in temporary teams originates from temporary participation in the teams. First, as participants join the team for a short period of time, there is not enough time to build trust, share understanding, and have effective interactions. Consequently, team outputs and practices built on team interactions become vulnerable. Secondly, as team participants move on and off the teams, teams’ boundaries become blurred over time. It leads to uncertainty among team participants and leaders about who is/is not identified as a team member causing collective disagreement within the team. Focusing on the above mentioned challenges, we conducted this research in healthcare organisations since the use of temporary teams in healthcare and hospital setting is prevalent. In particular, we focused on orthopaedic teams that provide personalised treatments for patients using 3D printing technology. Qualitative and quantitative data were collected using interviews, observations, questionnaires and archival data at Rizzoli Orthopaedic Institute, Bologna, Italy. This study provides the following research outputs. The first is a conceptual study that explores temporary teams’ literature using bibliometric analysis and systematic literature review to highlight research gaps. The second paper qualitatively studies temporary relationships within the teams by collecting data using group interviews and observations. The results highlighted the role of short-term dyadic relationships as a ground to share and transfer knowledge at the team level. Moreover, hierarchical structure of the teams facilitates knowledge sharing by supporting dyadic relationships within and beyond the team meetings. The third paper investigates impact of blurred boundaries on temporary teams’ performance. Using quantitative data collected through questionnaires and archival data, we concluded that boundary blurring in terms of fluidity, overlap and dispersion differently impacts team performance at high and low levels of task complexity.

Thermal and air quality modeling of an electric vehicle cabin with low-cost sensors and reinforcement learning

The design process of any electric vehicle system has to be oriented towards the best energy efficiency, together with the constraint of maintaining comfort in the vehicle cabin. Main aim of this study is to research the best thermal management solution in terms of HVAC efficiency without compromising occupant’s comfort and internal air quality. An Arduino controlled Low Cost System of Sensors was developed and compared against reference instrumentation (average R-squared of 0.92) and then used to characterise the vehicle cabin in real parking and driving conditions trials. Data on the energy use of the HVAC was retrieved from the car On-Board Diagnostic port. Energy savings using recirculation can reach 30 %, but pollutants concentration in the cabin builds up in this operating mode. Moreover, the temperature profile appeared strongly nonuniform with air temperature differences up to 10° C. Optimisation methods often require a high number of runs to find the optimal configuration of the system. Fast models proved to be beneficial for these task, while CFD-1D model are usually slower despite the higher level of detail provided. In this work, the collected dataset was used to train a fast ML model of both cabin and HVAC using linear regression. Average scaled RMSE over all trials is 0.4 %, while computation time is 0.0077 ms for each second of simulated time on a laptop computer. Finally, a reinforcement learning environment was built in OpenAI and Stable-Baselines3 using the built-in Proximal Policy Optimisation algorithm to update the policy and seek for the best compromise between comfort, air quality and energy reward terms. The learning curves show an oscillating behaviour overall, with only 2 experiments behaving as expected even if too slow. This result leaves large room for improvement, ranging from the reward function engineering to the expansion of the ML model.

Machine learning per la previsione sui prezzi delle case

Negli ultimi anni, a causa della crescente tendenza verso i Big Data, l’apprendimento automatico è diventato un approccio di previsione fondamentale perché può prevedere i prezzi delle case in modo accurato in base agli attributi delle abitazioni. In questo elaborato, verranno messe in pratica alcune tecniche di machine learning con l’obiettivo di effettuare previsioni sui prezzi delle abitazioni. Ad esempio, si può pensare all’acquisto di una nuova casa, saranno tanti i fattori di cui si dovrà preoccuparsi, la posizione, i metri quadrati, l’inquinamento dell’aria, il numero di stanze, il numero dei bagni e così via. Tutti questi fattori possono influire in modo più o meno pesante sul prezzo di quell’abitazione. E’ proprio in casi come questi che può essere applicata l’intelligenza artificiale, nello specifico il machine learning, per riuscire a trovare un modello che approssimi nel miglior modo un prezzo, data una serie di caratteristiche. In questa tesi verrà dimostrato come è possibile utilizzare l’apprendimento automatico per effettuare delle stime il più preciso possibile dei prezzi delle case. La tesi è divisa in 5 capitoli, nel primo capitolo verranno introdotti i concetti di base su cui si basa l’elaborato e alcune spiegazioni dei singoli modelli. Nel secondo capitolo, invece, viene trattato l’ambiente di lavoro utilizzato, il linguaggio e le relative librerie utilizzate. Il terzo capitolo contiene un’analisi esplorativa sul dataset utilizzato e vengono effettuate delle operazioni per preparare i dati agli algoritmi che verranno applicati in seguito. Nel capitolo 4 vengono creati i diversi modelli ed effettuate le previsioni sui prezzi mentre nel capitolo 5 vengono analizzati i risultati ottenuti e riportate le conclusioni.

Progettazione ed implementazione di un'applicazione web di e-learning a supporto della didattica di un corso universitario

Il presente elaborato vuole guidare il lettore lungo l’itinerario che ha previsto la cura e il rilascio di un’applicazione web a tema di e-learning. Greenwich, questo il nome della piattaforma, vuole essere un efficiente strumento di supporto online alla didattica del corso di Basi di Dati dell’Università di Bologna. Lo scopo primario dell’applicazione web è, infatti, quello di fornire agli studenti un mezzo per eseguire query mongoDB in maniera semplice, mirata e su richiesta del docente. Salvo un’approfondita ricerca culturale riguardante il contesto in cui si sviluppa l’applicazione, l’obiettivo primario della trattazione rimane quello di descrivere in modo ordinato i momenti impattanti che hanno segnato, passo dopo passo, le fasi di crescita di Greenwich, raggruppati in tre macro fasi caratteristiche: progettazione, implementazione e validazione.

tecniche di machine learning per la predizione del rating delle applicazioni all’interno di un play store

Il mio progetto di tesi ha come obiettivo quello di creare un modello in grado di predire il rating delle applicazioni presenti all’interno del Play Store, uno dei più grandi servizi di distribuzione digitale Android. A tale scopo ho utilizzato il linguaggio Python, che grazie alle sue librerie, alla sua semplicità e alla sua versatilità è certamen- te uno dei linguaggi più usati nel campo dell’intelligenza artificiale. Il punto di partenza del mio studio è stato il Dataset (Insieme di dati strutturati in forma relazionale) “Google Play Store Apps” reperibile su Kaggle al seguente indirizzo: https://www.kaggle.com/datasets/lava18/google-play-store-apps, contenente 10841 osservazioni e 13 attributi. Dopo una prima parte relativa al caricamen- to, alla visualizzazione e alla preparazione dei dati su cui lavorare, ho applica- to quattro di↵erenti tecniche di Machine Learning per la stima del rating delle applicazioni. In particolare, sono state utilizzate:https://www.kaggle.com/datasets/lava18/google-play-store-apps, contenente 10841 osservazioni e 13 attributi. Dopo una prima parte relativa al caricamento, alla visualizzazione e alla preparazione dei dati su cui lavorare, ho applicato quattro differenti tecniche di Machine Learning per la stima del rating delle applicazioni: Ridje, Regressione Lineare, Random Forest e SVR. Tali algoritmi sono stati applicati attuando due tipi diversi di trasformazioni (Label Encoding e One Hot Encoding) sulla variabile ‘Category’, con lo scopo di analizzare come le suddette trasformazioni riescano a influire sulla bontà del modello. Ho confrontato poi l’errore quadratico medio (MSE), l’errore medio as- soluto (MAE) e l’errore mediano assoluto (MdAE) con il fine di capire quale sia l’algoritmo più efficiente.

Modelli di Machine Learning per la Valutazione della Qualità del Vino

Descrizione, implementazione in Python e valutazione di modelli di Machine Learning e di tutte le sue fasi di Preprocessing, EDA, Training, Test e Evaluation, per valutare la qualità del vino attraverso le sue caratteristiche fisico-chimiche.

Application of active and transfer learning to wound image segmentation

Wound management is a fundamental task in standard clinical practice. Automated solutions already exist for humans, but there is a lack of applications on wound management for pets. The importance of a precise and efficient wound assessment is helpful to improve diagnosis and to increase the effectiveness of treatment plans for the chronic wounds. The goal of the research was to propose an automated pipeline capable of segmenting natural light-reflected wound images of animals. Two datasets composed by light-reflected images were used in this work: Deepskin dataset, 1564 human wound images obtained during routine dermatological exams, with 145 manual annotated images; Petwound dataset, a set of 290 wound photos of dogs and cats with 0 annotated images. Two implementations of U-Net Convolutioal Neural Network model were proposed for the automated segmentation. Active Semi-Supervised Learning techniques were applied for human-wound images to perform segmentation from 10% of annotated images. Then the same models were trained, via Transfer Learning, adopting an Active Semi- upervised Learning to unlabelled animal-wound images. The combination of the two training strategies proved their effectiveness in generating large amounts of annotated samples (94% of Deepskin, 80% of PetWound) with the minimal human intervention. The correctness of automated segmentation were evaluated by clinical experts at each round of training thus we can assert that the results obtained in this thesis stands as a reliable solution to perform a correct wound image segmentation. The use of Transfer Learning and Active Semi-Supervied Learning allows to minimize labelling effort from clinicians, even requiring no starting manual annotation at all. Moreover the performances of the model with limited number of parameters suggest the implementation of smartphone-based application to this topic, helping the future standardization of light-reflected images as acknowledge medical images.

HBIM to Virtual Reality Workflow for Industrial Archaeology Immovable Assets’ Management: A Case Study

As a witness on the industrialization in Bologna, since its first generation was born in the late 1760, the Battiferro lock has been coping with the innovation that the city experienced throughout the centuries, until it has lost its functionality due to the technological development for which Bologna’s canals were gradually covered starting from the 1950s under Giuseppe Dozza ’s administration, as part of the reconstruction, reclamation and urban requalification that was carried out in the aftermath the World War II and which involved the whole city. The interest of the research carried out on this case study was primarily to reintroduce the landmark that is still intact, to what is considered to be the fourth generation of the industrial revolution, namely in the construction field, which is recognized as Construction 4.0, by means of the Historic (or Heritage) Information Modeling HBIM and Virtual Reality (VR) application. A scan-to-BIM approach was followed to create 3D as-built BIM model, as a first step towards the storytelling of the abandoned industrial built asset in VR environment, or as a seed for future applications such as Digital Twins (DT), heritage digital learning, sustainable impact studies, and/or interface with other interfaces such as GIS. Based on the HBIM product, examples of the primary BIM deliverables such as 2D layouts is given, then a workflow to VR is proposed and investigated the reliability of data and the type of users that may benefit of the VR experience, then the potential future development of the model is investigated, with comparison of a relatively similar experience in the UK.

A Decade Of Malaria During Pregnancy In Brazil: What Has Been Done Concerning Prevention And Management.

In Brazil, malaria remains a disease of major epidemiological importance because of the high number of cases in the Amazonian Region. Plasmodium spp infections during pregnancy are a significant public health problem with substantial risks for the pregnant woman, the foetus and the newborn child. In Brazil, the control of malaria during pregnancy is primarily achieved by prompt and effective treatment of the acute episodes. Thus, to assure rapid diagnosis and treatment for pregnant women with malaria, one of the recommended strategy for low transmission areas by World Health Organization and as part of a strategy by the Ministry of Health, the National Malaria Control Program has focused on integrative measures with woman and reproductive health. Here, we discuss the approach for the prevention and management of malaria during pregnancy in Brazil over the last 10 years (2003-2012) using morbidity data from Malaria Health Information System. Improving the efficiency and quality of healthcare and education and the consolidation of prevention programmes will be challenges in the control of malaria during pregnancy in the next decade.

Management Of Severe Thoracic Impalement Trauma Against Two-wheeled Horse Carriage: A Case Report And Literature Review.

Thoracic injuries in general are of great importance due to their high incidence and high mortality. Thoracic impalement injuries are rare but severe due to the combination of cause, effect and result. This study's primary objective is to report the case of a young man who was impaled by a two-wheeled horse carriage shaft while crashing his motorcycle in a rural zone. An EMT-B ferry was called at the crash scene and a conscious patient was found, sustaining a severe impalement injury to the left hemithorax, suspended over the floor by the axial skeleton with the carriage shaft coming across his left chest. As a secondary objective, a literature review of thoracic impalement injuries is performed. Cases of thoracic impalement injury require unique and individualized care based on injury severity and affected organs. Reported protocols for managing impalement injuries are entirely anecdotal, with no uniformity on impaled patient's approach and management. In penetrating trauma, it is essential not to remove the impaled object, so that possible vascular lesions remain buffered by the object, avoiding major bleeding and exsanguination haemorrhage. Severed impaled thoracic patients should be transferred to a specialist centre for trauma care, as these lesions typically require complex multidisciplinary treatment. High-energy thoracic impalement injuries are rare and hold a high mortality rate, due to the complexity of trauma and associated injuries such as thoracic wall and lung lesions. Modern medicine still seems limited in cases of such seriousness, not always with satisfactory results.

Key Issues In Inhibitor Management In Patients With Haemophilia.

12 Suppl 1

[consensus Of The Brazilian Society Of Rheumatology For The Diagnosis, Management And Treatment Of Lupus Nephritis].

To develop recommendations for the diagnosis, management and treatment of lupus nephritis in Brazil. Extensive literature review with a selection of papers based on the strength of scientific evidence and opinion of the Commission on Systemic Lupus Erythematosus members, Brazilian Society of Rheumatology. 1) Renal biopsy should be performed whenever possible and if this procedure is indicated; and, when the procedure is not possible, the treatment should be guided with the inference of histologic class. 2) Ideally, measures and precautions should be implemented before starting treatment, with emphasis on attention to the risk of infection. 3) Risks and benefits of treatment should be shared with the patient and his/her family. 4) The use of hydroxychloroquine (preferably) or chloroquine diphosphate is recommended for all patients (unless contraindicated) during induction and maintenance phases. 5) The evaluation of the effectiveness of treatment should be made with objective criteria of response (complete remission/partial remission/refractoriness). 6) ACE inhibitors and/or ARBs are recommended as antiproteinuric agents for all patients (unless contraindicated). 7) The identification of clinical and/or laboratory signs suggestive of proliferative or membranous glomerulonephritis should indicate an immediate implementation of specific therapy, including steroids and an immunosuppressive agent, even though histological confirmation is not possible. 8) Immunosuppressives must be used during at least 36 months, but these medications can be kept for longer periods. Its discontinuation should only be done when the patient achieve and maintain a sustained and complete remission. 9) Lupus nephritis should be considered as refractory when a full or partial remission is not achieved after 12 months of an appropriate treatment, when a new renal biopsy should be considered to assist in identifying the cause of refractoriness and in the therapeutic decision.

Conservative Management For Lingual Thyroid Ectopic.

Lingual thyroid gland is a rare clinical entity. The presence of an ectopic thyroid gland located at the base of the tongue may be presented with symptoms like dysphagia, dysphonia, and upper airway obstruction. We are introducing a case of an 8-year-old girl who had lingual thyroid that presented dysphagia and foreign body sensation in the throat. The diagnostic was reached with clinical examination, thyroid scintigraphy with Tc(99m) and ultrasound. A laryngoscopy was performed which confirmed a spherical mass at base of tongue. Investigation should include thyroid function tests. In this case we observed subclinical hypothyroidism. There are different types of surgical approaches for the treatment of this condition; however, the treatment with Levothyroxine Sodium allowed the stabilization of TSH levels and clinical improvement of symptoms in a follow-up of 2 years.