Machine learning approach as an early warning system to prevent foodborne Salmonella outbreaks in northwestern Italy.

Salmonellosis, one of the most common foodborne infections in Europe, is monitored by food safety surveillance programmes, resulting in the generation of extensive databases. By leveraging tree-based machine learning (ML) algorithms, we exploited data from food safety audits to predict spatiotemporal patterns of salmonellosis in northwestern Italy. Data on human cases confirmed in 2015-2018 (n = 1969) and food surveillance data collected in 2014-2018 were used to develop ML algorithms. We integrated the monthly municipal human incidence with 27 potential predictors, including the observed prevalence of Salmonella in food. We applied the tree regression, random forest and gradient boosting algorithms considering different scenarios and evaluated their predictivity in terms of the mean absolute percentage error (MAPE) and R2. Using a similar dataset from the year 2019, spatiotemporal predictions and their relative sensitivities and specificities were obtained. Random forest and gradient boosting (R2 = 0.55, MAPE = 7.5%) outperformed the tree regression algorithm (R2 = 0.42, MAPE = 8.8%). Salmonella prevalence in food; spatial features; and monitoring efforts in ready-to-eat milk, fruits and vegetables, and pig meat products contributed the most to the models' predictivity, reducing the variance by 90.5%. Conversely, the number of positive samples obtained for specific food matrices minimally influenced the predictions (2.9%). Spatiotemporal predictions for 2019 showed sensitivity and specificity levels of 46.5% (due to the lack of some infection hotspots) and 78.5%, respectively. This study demonstrates the added value of integrating data from human and veterinary health services to develop predictive models of human salmonellosis occurrence, providing early warnings useful for mitigating foodborne disease impacts on public health.

Machine Learning as a Strategic Tool for Helping Cocoa Farmers in Côte D'Ivoire.

Machine learning can be used for social good. The employment of artificial intelligence in smart agriculture has many benefits for the environment: it helps small farmers (at a local scale) and policymakers and cooperatives (at regional scale) to take valid and coordinated countermeasures to combat climate change. This article discusses how artificial intelligence in agriculture can help to reduce costs, especially in developing countries such as Côte d'Ivoire, employing only low-cost or open-source tools, from hardware to software and open data. We developed machine learning models for two tasks: the first is improving agricultural farming cultivation, and the second is water management. For the first task, we used deep neural networks (YOLOv5m) to detect healthy plants and pods of cocoa and damaged ones only using mobile phone images. The results confirm it is possible to distinguish well the healthy from damaged ones. For actions at a larger scale, the second task proposes the analysis of remote sensors, coming from the GRACE NASA Mission and ERA5, produced by the Copernicus climate change service. A new deep neural network architecture (CIWA-net) is proposed with a U-Net-like architecture, aiming to forecast the total water storage anomalies. The model quality is compared to a vanilla convolutional neural network.

Fuel Prediction and Reduction in Public Transportation by Sensor Monitoring and Bayesian Networks.

We exploit the use of a controller area network (CAN-bus) to monitor sensors on the buses of local public transportation in a big European city. The aim is to advise fleet managers and policymakers on how to reduce fuel consumption so that air pollution is controlled and public services are improved. We deploy heuristic algorithms and exhaustive ones to generate Bayesian networks among the monitored variables. The aim is to describe the relevant relationships between the variables, to discover and confirm the possible cause-effect relationships, to predict the fuel consumption dependent on the contextual conditions of traffic, and to enable an intervention analysis to be conducted on the variables so that our goals are achieved. We propose a validation technique using Bayesian networks based on Granger causality: it relies upon observations of the time series formed by successive values of the variables in time. We use the same method based on Granger causality to rank the Bayesian networks obtained as well. A comparison of the Bayesian networks discovered against the ground truth is proposed in a synthetic data set, specifically generated for this study: the results confirm the validity of the Bayesian networks that agree on most of the existing relationships.

A New Genetic Risk Score to Predict the Outcome of Locally Advanced or Metastatic Breast Cancer Patients Treated With First-Line Exemestane: Results From a Prospective Study.

INTRODUCTION: Approximately 50% of locally advanced or metastatic breast cancer (MBC) patients treated with first-line exemestane do not show objective response and currently there are no reliable biomarkers to predict the outcome of patients using this therapy. The constitutive genetic background might be responsible for differences in the outcome of exemestane-treated patients. We designed a prospective study to investigate the role of germ line polymorphisms as biomarkers of survival. PATIENTS AND METHODS: Three hundred two locally advanced or MBC patients treated with first-line exemestane were genotyped for 74 germ line polymorphisms in 39 candidate genes involved in drug activity, hormone balance, DNA replication and repair, and cell signaling pathways. Associations with progression-free survival (PFS) and overall survival (OS) were tested with multivariate Cox regression. Bootstrap resampling was used as an internal assessment of results reproducibility. RESULTS: Cytochrome P450 19A1-rs10046TC/CC, solute carrier organic anion transporter 1B1-rs4149056TT, adenosine triphosphate binding cassette subfamily G member 2-rs2046134GG, fibroblast growth factor receptor-4-rs351855TT, and X-ray repair cross complementing 3-rs861539TT were significantly associated with PFS and then combined into a risk score (0-1, 2, 3, or 4-6 risk points). Patients with the highest risk score (4-6 risk points) compared with ones with the lowest score (0-1 risk points) had a median PFS of 10 months versus 26.3 months (adjusted hazard ratio [AdjHR], 3.12 [95% confidence interval (CI), 2.18-4.48]; P < .001) and a median OS of 38.9 months versus 63.0 months (AdjHR, 2.41 [95% CI, 1.22-4.79], P = .012), respectively. CONCLUSION: In this study we defined a score including 5 polymorphisms to stratify patients for PFS and OS. This score, if validated, might be translated to personalize locally advanced or MBC patient treatment and management.

The role of the network of matches on predicting success in table tennis.

The influence of training, posture, nutrition or psychological attitudes on an athlete's career is well described in literature. An additional factor of success that is widely recognized as crucial is the network of matches that an athlete plays during a season. The hypothesis is that the quality of a player's opponents affects her long-term ranking and performance. Even though the relevance of these factors is widely recognized as important, a quantitative characterization is missing. In this paper, we try to fill this gap combining network analysis and machine learning to estimate the contribution of the network of matches in predicting an athlete's success. We consider all the official games played by the Italian table tennis players between 2011 and 2016. We observe that the matches network shows scale-free behavior, typical of several real-world systems, and that different structural properties are positively correlated with the athletes' performance (Spearman [Formula: see text], p-value [Formula: see text]). Using these findings, we implement three different tasks, such as talent identification, performance and ranking prediction. Results shows consistently that machine learning approaches are able to predict players' success and that the topological features play an effective role in increasing their predictive power.

A Semisupervised Approach to the Detection and Characterization of Outliers in Categorical Data.

In this paper, we introduce a new approach of semisupervised anomaly detection that deals with categorical data. Given a training set of instances (all belonging to the normal class), we analyze the relationship among features for the extraction of a discriminative characterization of the anomalous instances. Our key idea is to build a model that characterizes the features of the normal instances and then use a set of distance-based techniques for the discrimination between the normal and the anomalous instances. We compare our approach with the state-of-the-art methods for semisupervised anomaly detection. We empirically show that a specifically designed technique for the management of the categorical data outperforms the general-purpose approaches. We also show that, in contrast with other approaches that are opaque because their decision cannot be easily understood, our proposed approach produces a discriminative model that can be easily interpreted and used for the exploration of the data.

The exploitation of data from remote and human sensors for environment monitoring in the SMAT project.

In this paper, we outline the functionalities of a system that integrates and controls a fleet of Unmanned Aircraft Vehicles (UAVs). UAVs have a set of payload sensors employed for territorial surveillance, whose outputs are stored in the system and analysed by the data exploitation functions at different levels. In particular, we detail the second level data exploitation function whose aim is to improve the sensors data interpretation in the post-mission activities. It is concerned with the mosaicking of the aerial images and the cartography enrichment by human sensors--the social media users. We also describe the software architecture for the development of a mash-up (the integration of information and functionalities coming from the Web) and the possibility of using human sensors in the monitoring of the territory, a field in which, traditionally, the involved sensors were only the hardware ones.