Liver disease is characterized by breath exhalation of peculiar volatile organic compounds(VOCs).Thanks to the availability of sensitive technologies for breath analysis,this empiric approach has recently gained incre...Liver disease is characterized by breath exhalation of peculiar volatile organic compounds(VOCs).Thanks to the availability of sensitive technologies for breath analysis,this empiric approach has recently gained increasing attention in the context of hepatology,following the good results obtained in other fields of medicine.After the first studies that led to the identification of selected VOCs for pathophysiological purposes,subsequent research has progressively turned towards the comprehensive assessment of exhaled breath for potential clinical application.Specific VOC patterns were found to discriminate subjects with liver cirrhosis,to rate disease severity,and,eventually,to forecast adverse clinical outcomes even beyond existing scores.Preliminary results suggest that breath analysis could be useful also for detecting and staging hepatic encephalopathy and for predicting steatohepatitis in patients with nonalcoholic fatty liver disease.However,clinical translation is still hampered by a number of methodological limitations,including the lack of standardization and the consequent poor comparability between studies and the absence of external validation of obtained results.Given the low-cost and easy execution at bedside of the new technologies(e-nose),larger and well-structured studies are expected in order to provide the adequate level of evidence to support VOC analysis in clinical practice.展开更多
Mapping hazelnut orchards can facilitate land planning and utilization policies,supporting the development of cooperative precision farming systems.The present work faces the detection of hazelnut crops using optical ...Mapping hazelnut orchards can facilitate land planning and utilization policies,supporting the development of cooperative precision farming systems.The present work faces the detection of hazelnut crops using optical and radar remote sensing data.A comparative study of Machine Learning techniques is presented.The system proposed utilizes multi-temporal data from the Sentinel-1 and Sentinel-2 datasets extracted over several years and processed with cloud tools.We provide a dataset of 62,982 labeled samples,with 16,561 samples belonging to the‘hazelnut’class and 46,421 samples belonging to the‘other’class,collected in 8 heterogeneous geograph-ical areas of the Viterbo province.Two different comparative tests are conducted:firstly,we use a Nested 5-Fold Cross-Validation methodology to train,optimize,and compare different Machine Learning algorithms on a single area.In a second experiment,the algorithms were trained on one area and tested on the remaining seven geo-graphical areas.The developed study demonstrates how AI analysis applied to Sentinel-1 and Sentinel-2 data is a valid technology for hazelnut mapping.From the results,it emerges that Random Forest is the classifier with the highest generalizability,achieving the best performance in the second test with an accuracy of 96%and an F1 score of 91%for the‘hazelnut’class.展开更多
文摘Liver disease is characterized by breath exhalation of peculiar volatile organic compounds(VOCs).Thanks to the availability of sensitive technologies for breath analysis,this empiric approach has recently gained increasing attention in the context of hepatology,following the good results obtained in other fields of medicine.After the first studies that led to the identification of selected VOCs for pathophysiological purposes,subsequent research has progressively turned towards the comprehensive assessment of exhaled breath for potential clinical application.Specific VOC patterns were found to discriminate subjects with liver cirrhosis,to rate disease severity,and,eventually,to forecast adverse clinical outcomes even beyond existing scores.Preliminary results suggest that breath analysis could be useful also for detecting and staging hepatic encephalopathy and for predicting steatohepatitis in patients with nonalcoholic fatty liver disease.However,clinical translation is still hampered by a number of methodological limitations,including the lack of standardization and the consequent poor comparability between studies and the absence of external validation of obtained results.Given the low-cost and easy execution at bedside of the new technologies(e-nose),larger and well-structured studies are expected in order to provide the adequate level of evidence to support VOC analysis in clinical practice.
文摘Mapping hazelnut orchards can facilitate land planning and utilization policies,supporting the development of cooperative precision farming systems.The present work faces the detection of hazelnut crops using optical and radar remote sensing data.A comparative study of Machine Learning techniques is presented.The system proposed utilizes multi-temporal data from the Sentinel-1 and Sentinel-2 datasets extracted over several years and processed with cloud tools.We provide a dataset of 62,982 labeled samples,with 16,561 samples belonging to the‘hazelnut’class and 46,421 samples belonging to the‘other’class,collected in 8 heterogeneous geograph-ical areas of the Viterbo province.Two different comparative tests are conducted:firstly,we use a Nested 5-Fold Cross-Validation methodology to train,optimize,and compare different Machine Learning algorithms on a single area.In a second experiment,the algorithms were trained on one area and tested on the remaining seven geo-graphical areas.The developed study demonstrates how AI analysis applied to Sentinel-1 and Sentinel-2 data is a valid technology for hazelnut mapping.From the results,it emerges that Random Forest is the classifier with the highest generalizability,achieving the best performance in the second test with an accuracy of 96%and an F1 score of 91%for the‘hazelnut’class.
