Search

The agricultural sector, in particular viticulture, is highly susceptible to variations in the environment, crop conditions, and operational factors. Effectively managing these variables in the field necessitates observation, measurement, and responsive actions. Leveraging new technologies within the realm of precision agriculture, vineyards can enhance their long-term efficiency, productivity, and profitability. In our work we propose a novel analysis of the impact of pedoclimatic factors on wine, with a case study focusing on the Denomination of Controlled and Guaranteed Origin Chianti Classico (DOCG), a prime wine-producing region located in Tuscany, between the provinces of Siena and Florence. We first collected a novel dataset, where geographic information as well as wine quality information were collected, using publicly available sources. Using such geographic information retrieved and an unsupervised machine learning approach, we conducted an in-depth examination of pedoclimatic and production data. To collect the whole set of possibly relevant features, we first assessed the region's morphological attributes, including altitude, exposure, and slopes, while pinpointing individual wineries. Subsequently we then calculated crucial viticultural indices such as the Winkler, Huglin, Fregoni, and Freshness Index by utilizing daily temperature records from Chianti Classico, and we further related them to an assessment of wine quality. In addition to this, we designed and distributed a survey conducted among a sample of wineries situated in the Chianti Classico area, obtaining valuable insights into local data. The primary goal of this study is to elucidate the interrelationships between various parameters associated with the region, considering influential factors such as the environment, viticulture, and field operations that significantly impact wine production. By doing so, wineries could potentially unlock the full potential of their resources. In fact, through the unsupervised and correlation analysis we could elucidate the relationships existing between the pedoclimatic parameters of the region, considering the most important factors such as viticulture and field operations, and relate them to wine quality as for instance using the survey data collected. This study represents an unprecedent in the literature, and it could pave the path for future studies focusing on the importance of climatic factors into production and quality of wines.

Artificial Intelligence (AI) applications and Machine Learning (ML) methods have gained much attention in recent years for their ability to automatically detect patterns in data without being explicitly taught rules. Specific features characterise the ECGs of patients with Brugada Syndrome (BrS); however, there is still ambiguity regarding the correct diagnosis of BrS and its differentiation from other pathologies.This work presents an application of Echo State Networks (ESN) in the Recurrent Neural Networks (RNN) class for diagnosing BrS from the ECG time series.12-lead ECGs were obtained from patients with a definite clinical diagnosis of spontaneous BrS Type 1 pattern (Group A), patients who underwent provocative pharmacological testing to induce BrS type 1 pattern, which resulted in positive (Group B) or negative (Group C), and control subjects (Group D). One extracted beat in the V2 lead was used as input, and the dataset was used to train and evaluate the ESN model using a double cross-validation approach. ESN performance was compared with that of 4 cardiologists trained in electrophysiology.The model performance was assessed in the dataset, with a correct global diagnosis observed in 91.5 % of cases compared to clinicians (88.0 %). High specificity (94.5 %), sensitivity (87.0 %) and AUC (94.7 %) for BrS recognition by ESN were observed in Groups A + B vs. C + D.Our results show that this ML model can discriminate Type 1 BrS ECGs with high accuracy comparable to expert clinicians. Future availability of larger datasets may improve the model performance and increase the potential of the ESN as a clinical support system tool for daily clinical practice.

Abstract In 2021 almost 300 mm of rain, nearly half of the average annual rainfall, fell near Catania (Sicily Island, Italy). Such events took place in just a few hours, with dramatic consequences on the environmental, social, economic, and health systems of the region. These phenomena are now very common in various countries all around the world: this is the reason why, detecting local extreme rainfall events is a crucial prerequisite for planning actions, able to reverse possibly intensified dramatic future scenarios. In this paper, the Affinity Propagation algorithm, a clustering algorithm grounded on machine learning, was applied, to the best of our knowledge, for the first time, to detect extreme rainfall areas in Sicily. This was possible by using a high-frequency, large dataset we collected, ranging from 2009 to 2021 which we named RSE (the Rainfall Sicily Extreme dataset). Weather indicators were then been employed to validate the results, thus confirming the presence of recent anomalous rainfall events in eastern Sicily. We believe that easy-to-use and multi-modal data science techniques, such as the one proposed in this study, could give rise to significant improvements in policy-making for successfully contrasting climate change.

Abstract If understanding sentiments is already a difficult task in human‐human communication, this becomes extremely challenging when a human‐computer interaction happens, as for instance in chatbot conversations. In this work, a machine learning neural network‐based Speech Emotion Recognition system is presented to perform emotion detection in a chatbot virtual assistant whose task was to perform contact tracing during the COVID‐19 pandemic. The system was tested on a novel dataset of audio samples, provided by the company Blu Pantheon, which developed virtual agents capable of autonomously performing contacts tracing for individuals positive to COVID‐19. The dataset provided was unlabelled for the emotions associated to the conversations. Therefore, the work was structured using a sort of transfer learning strategy. First, the model is trained using the labelled and publicly available Italian‐language dataset EMOVO Corpus. The accuracy achieved in testing phase reached 92%. To the best of their knowledge, thiswork represents the first example in the context of chatbot speech emotion recognition for contact tracing, shedding lights towards the importance of the use of such techniques in virtual assistants and chatbot conversational contexts for psychological human status assessment. The code of this work was publicly released at: https://github.com/fp1acm8/SER.

The current image generative models have achieved a remarkably realistic image quality, offering numerous academic and industrial applications. However, to ensure these models are used for benign purposes, it is essential to develop tools that definitively detect whether an image has been synthetically generated. Consequently, several detectors with excellent performance in computer vision applications have been developed. However, these detectors cannot be directly applied as they areto multi-spectral satellite images, necessitating the training of new models. While two-class classifiers generally achieve high detection accuracies, they struggle to generalize to image domains and generative architectures different from those encountered during training. In this paper, we propose a one-class classifier based on Vector Quantized Variational Autoencoder 2 (VQ-VAE 2) features to overcome the limitations of two-class classifiers. We start by highlighting the generalization problem faced by binary classifiers. This was demonstrated by training and testing an EfficientNet-B4 architecture on multiple multi-spectral datasets. We then illustrate that the VQ-VAE 2-based classifier, which was trained exclusively on pristine images, could detect images from different domains and generated by architectures not encountered during training. Finally, we conducted a head-to-head comparison between the two classifiers on the same generated datasets, emphasizing the superior generalization capabilities of the VQ-VAE 2-based detector, wherewe obtained a probability of detection at a 0.05 false alarm rate of 1 for the blue and red channels when using the VQ-VAE 2-based detector, and 0.72 when we used the EfficientNet-B4 classifier.

Abstract Advanced age represents one of the major risk factors for Parkinson’s Disease. Recent biomedical studies posit a role for microRNAs, also known to be remodelled during ageing. However, the relationship between microRNA remodelling and ageing in Parkinson’s Disease, has not been fully elucidated. Therefore, the aim of the present study is to unravel the relevance of microRNAs as biomarkers of Parkinson’s Disease within the ageing framework. We employed Next Generation Sequencing to profile serum microRNAs from samples informative for Parkinson’s Disease (recently diagnosed, drug-naïve) and healthy ageing (centenarians) plus healthy controls, age-matched with Parkinson’s Disease patients. Potential microRNA candidates markers, emerging from the combination of differential expression and network analyses, were further validated in an independent cohort including both drug-naïve and advanced Parkinson’s Disease patients, and healthy siblings of Parkinson’s Disease patients at higher genetic risk for developing the disease. While we did not find evidences of microRNAs co-regulated in Parkinson’s Disease and ageing, we report that hsa-miR-144-3p is consistently down-regulated in early Parkinson’s Disease patients. Moreover, interestingly, functional analysis revealed that hsa-miR-144-3p is involved in the regulation of coagulation, a process known to be altered in Parkinson’s Disease. Our results consistently show the down-regulation of hsa-mir144-3p in early Parkinson’s Disease, robustly confirmed across a variety of analytical and experimental analyses. These promising results ask for further research to unveil the functional details of the involvement of hsa-mir144-3p in Parkinson’s Disease.

The automotive market is experiencing, in recent years, a period of deep transformation. Increasingly stricter rules on pollutant emissions and greater awareness of air quality by consumers are pushing the transport sector towards sustainable mobility. In this historical context, electric cars have been considered the most valid alternative to traditional internal combustion engine cars, thanks to their low polluting potential, with high growth prospects in the coming years. This growth is an important element for companies operating in the electricity sector, since the spread of electric cars is necessarily accompanied by an increasing need of electric charging points, which may impact the electricity distribution network. In this work we proposed a novel application of machine learning methods for the estimation of factors which could impact the distribution of the circulating fleet of electric cars in Italy. We first collected a new dataset from public repository to evaluate the most relevant features impacting the electric cars market. The collected datasets are completely new, and were collected starting from the identification of the main variables that were potentially responsible for the spread of electric cars. Subsequently we distributed a novel designed survey to further investigate such factors on a population sample. Using machine learning models, we could disentangle potentially new interesting information concerning the Italian scenario. We analysed it, in fact, according to different geographical Italian dimensions (national, regional and provincial) and with the final identification of those potential factors that could play a fundamental role in the success and distribution of electric cars mobility. Code and data are available at: https://github.com/GiovannaMariaDimitri/A-machine-learning-approach-to-analyse-and-predict-the-electric-cars-scenario-the-Italian-case.

Abstract Here, we performed a comprehensive intra-tissue and inter-tissue multilayer network analysis of the human transcriptome. We generated an atlas of communities in gene co-expression networks in 49 tissues (GTEx v8), evaluated their tissue specificity, and investigated their methodological implications. UMAP embeddings of gene expression from the communities (representing nearly 18% of all genes) robustly identified biologically-meaningful clusters. Notably, new gene expression data can be embedded into our algorithmically derived models to accelerate discoveries in high-dimensional molecular datasets and downstream diagnostic or prognostic applications. We demonstrate the generalisability of our approach through systematic testing in external genomic and transcriptomic datasets. Methodologically, prioritisation of the communities in a transcriptome-wide association study of the biomarker C-reactive protein (CRP) in 361,194 individuals in the UK Biobank identified genetically-determined expression changes associated with CRP and led to considerably improved performance. Furthermore, a deep learning framework applied to the communities in nearly 11,000 tumors profiled by The Cancer Genome Atlas across 33 different cancer types learned biologically-meaningful latent spaces, representing metastasis (p

Employee attrition is a major problem that causes many companies to incur in significant costs to find and hire new personnel. The use of machine learning and artificial intelligence methods to predict the likelihood of resignation of an employee, and the quitting causes, can provide HR departments with a valuable decision support system and, as a result, prevent a large waste of time and resources. In this paper, we propose a preliminary exploratory analysis of the application of machine learning methodologies for employee attrition prediction. We compared several classification models with the goal of finding the one that not only performs best, but is also well interpretable, in order to provide companies with the possibility of improving those aspects that have been shown to produce the quitting of their employees. Among the proposed methods, Logistic Regression performs the best, with an accuracy of 88% and an AUC-ROC of 85%.

Deep learning has achieved state-of-the-art performances in several research applications nowadays: from computer vision to bioinformatics, from object detection to image generation. In the context of such newly developed deep-learning approaches, we can define the concept of multimodality. The objective of this research field is to implement methodologies which can use several modalities as input features to perform predictions. In this, there is a strong analogy with respect to what happens with human cognition, since we rely on several different senses to make decisions. In this article, we present a short survey on multimodal integration using deep-learning methods. In a first instance, we comprehensively review the concept of multimodality, describing it from a two-dimensional perspective. First, we provide, in fact, a taxonomical description of the multimodality concept. Secondly, we define the second multimodality dimension as the one describing the fusion approaches in multimodal deep learning. Eventually, we describe four applications of multimodal deep learning to the following fields of research: speech recognition, sentiment analysis, forensic applications and image processing.

Biological aging can be affected by several factors such as drug treatments and pathological conditions. Metabolomics can help in the estimation of biological age by analyzing the differences between predicted and actual chronological age in different subjects. In this paper, we compared three different and well-known machine learning approaches—SVM, ElasticNet, and PLS—to build a model based on the 1H-NMR metabolomic data of serum samples, able to predict chronological age in control individuals. Then, we tested these models in two pathological cohorts of de novo and advanced PD patients. The discrepancies observed between predicted and actual age in patients are interpreted as a sign of a (pathological) biological aging process.

Deep learning is widely applied in bioinformatics and biomedical imaging, due to its ability to perform various clinical tasks automatically and accurately. In particular, the application of deep learning techniques for the automatic identification of glomeruli in histopathological kidney images can play a fundamental role, offering a valid decision support system tool for the automatic evaluation of the Karpinski metric. This will help clinicians in detecting the presence of sclerotic glomeruli in order to decide whether the kidney is transplantable or not. In this work, we implemented a deep learning framework to identify and segment sclerotic and non-sclerotic glomeruli from scanned Whole Slide Images (WSIs) of human kidney biopsies. The experiments were conducted on a new dataset collected by both the Siena and Trieste hospitals. The images were segmented using the DeepLab V2 model, with a pre-trained ResNet101 encoder, applied to 512 × 512 patches extracted from the original WSIs. The results obtained are promising and show a good performance in the segmentation task and a good generalization capacity, despite the different coloring and typology of the histopathological images. Moreover, we present a novel use of the CD10 staining procedure, which gives promising results when applied to the segmentation of sclerotic glomeruli in kidney tissues.

Eye-tracking can offer a novel clinical practice and a non-invasive tool to detect neuropathological syndromes. In this paper, we show some analysis on data obtained from the visual sequential search test. Indeed, such a test can be used to evaluate the capacity of looking at objects in a specific order, and its successful execution requires the optimization of the perceptual resources of foveal and extrafoveal vision. The main objective of this work is to detect if some patterns can be found within the data, to discern among people with chronic pain, extrapyramidal patients and healthy controls. We employed statistical tests to evaluate differences among groups, considering three novel indicators: blinking rate, average blinking duration and maximum pupil size variation. Additionally, to divide the three patient groups based on scan-path images—which appear very noisy and all similar to each other—we applied deep learning techniques to embed them into a larger transformed space. We then applied a clustering approach to correctly detect and classify the three cohorts. Preliminary experiments show promising results.

Abstract Background We present a multiplex network model for the analysis of Intracranial Pressure (ICP) and Heart Rate (HR) behaviour after severe brain traumatic injuries in pediatric patients. The ICP monitoring is of vital importance for checking life threathening conditions, and understanding the behaviour of these parameters is crucial for a successful intervention of the clinician. Our own observations, exhibit cross-talks interaction events happening between HR and ICP, i.e. transients in which both the ICP and the HR showed an increase of 20% with respect to their baseline value in the window considered. We used a complex event processing methodology, to investigate the relationship between HR and ICP, after traumatic brain injuries (TBI). In particular our goal has been to analyse events of simultaneous increase by HR and ICP (i.e. cross-talks), modelling the two time series as a unique multiplex network system (Lacasa et al., Sci Rep 5:15508-15508, 2014). Methods and data We used a complex network approach based on visibility graphs (Lacasa et al., Sci Rep 5:15508-15508, 2014) to model and study the behaviour of our system and to investigate how and if network topological measures can give information on the possible detection of crosstalks events taking place in the system. Each time series was converted as a layer in a multiplex network. We therefore studied the network structure, focusing on the behaviour of the two time series in the cross-talks events windows detected. We used a dataset of 27 TBI pediatric patients, admitted to Addenbrooke’s Hospital, Cambridge, Pediatric Intensive Care Unit (PICU) between August 2012 and December 2014. Results Following a preliminary statistical exploration of the two time series of ICP and HR, we analysed the multiplex network proposed, focusing on two standard topological network metrics: the mutual interaction, and the average edge overlap (Lacasa et al., Sci Rep 5:15508-15508, 2014). We compared results obtained for these two indicators, considering windows in which a cross talks event between HR and ICP was detected with windows in which cross talks events were not present. The analysis of such metrics gave us interesting insights on the time series behaviour. More specifically we observed an increase in the value of the mutual interaction in the case of cross talk as compared to non cross talk. This seems to suggest that mutual interaction could be a potentially interesting “marker” for cross talks events.

The genetic component of many common traits is associated with the gene expression and several variants act as expression quantitative loci, regulating the gene expression in a tissue specific manner. In this work, we applied tissue-specific cis-eQTL gene expression prediction models on the genotype of 808 samples including controls, subjects with mild cognitive impairment, and patients with Alzheimer's Disease. We then dissected the imputed transcriptomic profiles by means of different unsupervised and supervised machine learning approaches to identify potential biological associations. Our analysis suggests that unsupervised and supervised methods can provide complementary information, which can be integrated for a better characterization of the underlying biological system. In particular, a variational autoencoder representation of the transcriptomic profiles, followed by a support vector machine classification, has been used for tissue-specific gene prioritizations. Interestingly, the achieved gene prioritizations can be efficiently integrated as a feature selection step for improving the accuracy of deep learning classifier networks. The identified gene-tissue information suggests a potential role for inflammatory and regulatory processes in gut-brain axis related tissues. In line with the expected low heritability that can be apportioned to eQTL variants, we were able to achieve only relatively low prediction capability with deep learning classification models. However, our analysis revealed that the classification power strongly depends on the network structure, with recurrent neural networks being the best performing network class. Interestingly, cross-tissue analysis suggests a potentially greater role of models trained in brain tissues also by considering dementia-related endophenotypes. Overall, the present analysis suggests that the combination of supervised and unsupervised machine learning techniques can be used for the evaluation of high dimensional omics data.