Computer vision in aseptic pharmaceutical manufacturing: a deep learning-based approach to vial inspection and pack formation during a lyophilizer loading cycle

Vision systems are powerful tools playing an increasingly important role in modern industry, to detect errors and maintain product standards. With the enlarged availability of affordable industrial cameras, computer vision algorithms have been increasingly applied in industrial manufacturing processes monitoring. Until a few years ago, industrial computer vision applications relied only on ad-hoc algorithms designed for the specific object and acquisition setup being monitored, with a strong focus on co-designing the acquisition and processing pipeline. Deep learning has overcome these limits providing greater flexibility and faster re-configuration. In this work, the process to be inspected consists in vials’ pack formation entering a freeze-dryer, which is a common scenario in pharmaceutical active ingredient packaging lines. To ensure that the machine produces proper packs, a vision system is installed at the entrance of the freeze-dryer to detect eventual anomalies with execution times compatible with the production specifications. Other constraints come from sterility and safety standards required in pharmaceutical manufacturing. This work presents an overview about the production line, with particular focus on the vision system designed, and about all trials conducted to obtain the final performance. Transfer learning, alleviating the requirement for a large number of training data, combined with data augmentation methods, consisting in the generation of synthetic images, were used to effectively increase the performances while reducing the cost of data acquisition and annotation. The proposed vision algorithm is composed by two main subtasks, designed respectively to vials counting and discrepancy detection. The first one was trained on more than 23k vials (about 300 images) and tested on 5k more (about 75 images), whereas 60 training images and 52 testing images were used for the second one.

Graph-based Vision-Language Model for Multi-Modal Retrieval of Fashion Products

Artificial Intelligence is reshaping the field of fashion industry in different ways. E-commerce retailers exploit their data through AI to enhance their search engines, make outfit suggestions and forecast the success of a specific fashion product. However, it is a challenging endeavour as the data they possess is huge, complex and multi-modal. The most common way to search for fashion products online is by matching keywords with phrases in the product's description which are often cluttered, inadequate and differ across collections and sellers. A customer may also browse an online store's taxonomy, although this is time-consuming and doesn't guarantee relevant items. With the advent of Deep Learning architectures, particularly Vision-Language models, ad-hoc solutions have been proposed to model both the product image and description to solve this problems. However, the suggested solutions do not exploit effectively the semantic or syntactic information of these modalities, and the unique qualities and relations of clothing items. In this work of thesis, a novel approach is proposed to address this issues, which aims to model and process images and text descriptions as graphs in order to exploit the relations inside and between each modality and employs specific techniques to extract syntactic and semantic information. The results obtained show promising performances on different tasks when compared to the present state-of-the-art deep learning architectures.

Tecniche innovative microbiome-based per il recupero della vongola comune nelle aree ad alta mortalità nell’area FLAG dell’Emilia Romagna

Negli ultimi decenni sono state registrate preoccupati fenomeni di mortalità della vongola Chamelea gallina, in particolare nell’area costiera emiliano-romagnola e di cui non sono ancora state chiarite le cause. Il presente studio si è occupato di caratterizzare la comunità microbica associata alla vongola nella ghiandola digestiva, utilizzando il sequenziamento della regione ipervariabile V3-V4 del gene rRNA 16S, al fine di individuare fenomeni di disbiosi in aree ad elevata mortalità. Sono state quindi esplorate le variazioni stagionali (da luglio a novembre) nella struttura del microbiota della vongola e nell'ecosistema microbico dell'acqua di mare circostante, in quattro siti scelti ad hoc, secondo un gradiente di incidenza storica di mortalità, da Nord a Sud, tra le aree di Ravenna e Rimini. Lo stato di salute della vongola e del suo microbiota associato sono stati esplorati tramite, rispettivamente, l’indice di condizione e lo studio mediante NGS della composizione dell’ecosistema microbico intestinale. I nostri dati, sebbene preliminari, dimostrano come tra le aree Nord e Sud ci sia un comportamento differente e reciproco relativamente all’andamento stagionale dei valori di diversità interna (alfa) al microbiota della vongola, che si riduce dall’estate all’autunno nelle aree Nord (Ravenna e Lido di Savio), mentre aumenta - nello stesso periodo di tempo - nelle aree Sud (Rimini e Cesenatico). A conferma dei dati di alfa diversità, l’analisi mediante PCoA delle variazione del microbiota della vongola tra i quattro siti di indagine stratificate per stagione, dimostrano profonde differenze tra i due estremi nord-sud. In particolare, l’analisi integrata dei dati storici di produttività, indice di condizione e dinamica del microbiota della g.d. ci ha consentito di discriminare cinque famiglie microbiche come potenziali Growth Promoting Bacteria, poiché associate ad un picco di indice di condizione che si registra nelle aree a bassa mortalità, nel mese di settembre.