Deep learning forecasting of large induced earthquakes via precursory signals.

Precursory phenomena to earthquakes have always attracted researchers' attention. Among the most investigated precursors, foreshocks play a key role. However, their prompt identification with respect to background seismicity still remains an issue. The task is worsened when dealing with low-magnitude earthquakes. Despite that, seismology and, in particular real-time seismology, can nowadays benefit from the use of Artificial Intelligence (AI) to face the challenge of effective precursory signals discrimination. Here, we propose a deep learning method named PreD-Net (precursor detection network) to address precursory signal identification of induced earthquakes. PreD-Net has been trained on data related to three different induced seismicity areas, namely The Geysers, located in California, USA, Cooper Basin, Australia, Hengill in Iceland. The network shows a suitable model generalization, providing considerable results on samples that were not used during the network training phase of all the sites. Tests on related samples of induced large events, with the addition of data collected from the Basel catalogue, Switzerland, assess the possibility of building a real-time warning strategy to be used to avoid adverse consequences during field operations.

Automated Pulmonary Nodule Classification and Detection Using Deep Learning Architectures.

Recent advancement in biomedical imaging technologies has contributed to tremendous opportunities for the health care sector and the biomedical community. However, collecting, measuring, and analyzing large volumes of health-related data like images is a laborious and time-consuming job for medical experts. Thus, in this regard, artificial intelligence applications (including machine and deep learning systems) help in the early diagnosis of various contagious/ cancerous diseases such as lung cancer. As lung or pulmonary cancer may have no apparent or clear initial symptoms, it is essential to develop and promote a Computer Aided Detection (CAD) system that can support medical experts in classifying and detecting lung nodules at early stages. Therefore, in this article, we analyze the problem of lung cancer diagnosis by classification and detecting pulmonary nodules, i.e., benign and malignant, in CT images. To achieve this objective, an automated deep learning based system is introduced for classifying and detecting lung nodules. In addition, we use novel state-of-the-art detection architectures, including, Faster-RCNN, YOLOv3, and SSD, for detection purposes. All deep learning models are evaluated using a publicly available benchmark LIDC-IDRI data set. The experimental outcomes reveal that the False Positive Rate (FPR) is reduced, and the accuracy is enhanced.

A Deep Learning Approach Considering Image Background for Pneumonia Identification Using Explainable AI (XAI).

Pneumonia mainly refers to lung infections caused by pathogens, such as bacteria and viruses. Currently, deep learning methods have been applied to identify pneumonia. However, the traditional deep learning methods for pneumonia identification take less account of the influence of the lung X-ray image background on the model's testing effect, which limits the improvement of the model's accuracy. In this paper, we propose a deep learning method that considers image background factors and analyzes the proposed method with explainable deep learning for explainability. The essential idea is to remove the image background, improve the pneumonia recognition accuracy, and apply the Grad-CAM method to obtain an explainable deep learning model for pneumonia identification. In the proposed approach, (1) preliminary deep learning models for pneumonia X-ray image identification without considering the background are built; (2) deep learning models for pneumonia X-ray image identification with background consideration are built to improve the accuracy of pneumonia identification; (3) Grad-CAM method is employed to analyze the explainability. The proposed approach improves the accuracy of pneumonia identification, and the highest accuracy of VGG16 reaches 95.6%. The proposed approach can be applied to real pneumonia identification for early detection and treatment.

Predictive Medicine for Salivary Gland Tumours Identification Through Deep Learning.

Nowadays, predictive medicine begins to become a reality thanks to Artificial Intelligence (AI) which allows, through the processing of huge amounts of data, to identify correlations not perceptible to the human brain. The application of AI in predictive diagnostics is increasingly pervasive; through the use and interpretation of data, the first signs of some diseases (i.e. tumours) can be detected to help physicians make more accurate diagnoses to reduce the errors and develop methods for individualized medical treatment. In this perspective, salivary gland tumours (SGTs) are rare cancers with variable malignancy representing less than 1% of all cancer diagnoses and about 5% of head and neck cancers. The clinical management of SGTs is complicated by a high rate of preclinical diagnostic errors. Today, fine needle aspiration cytology (FNAC) represents the primary diagnostic tool in the hands of clinicians. However, it provides information that about 25% of cases are dubious or inconclusive, complicating therapeutic choices. Thus, finding new tools supporting clinicians to make the right choices in doubtful cases is necessary. This research work presents and discusses a Deep Learning-based framework for automatic segmentation and classification of salivary gland tumours. Furthermore, we propose an explainable segmentation learning approach supporting the effectiveness of the proposed framework through a per-epoch learning process analysis and the attention map mechanism. The proposed framework was evaluated with a collected CT dataset of patients with salivary gland tumours. Experimental results show that our methodology achieves significant scores on both segmentation and classification tasks.

A machine learning-enhanced biosensor for mercury detection based on an hydrophobin chimera.

Marine waters are becoming contaminated by diverse pollutants at a fast rate, and detection of these water pollutants has become a major concern in recent years. Among these, mercury is considered the most toxic element for human health. At present, despite the commonly used methods for its detection are accurate, they often require sophisticated equipments, have relatively high costs, are demanding and time-consuming. Herein a novel solution to detect mercury (II) pollution in sea water is proposed, and an easy and portable detection method has been developed. Indeed, a hydrophobin based chimera able to both adhere to polystyrene multiwell plates and bind mercury (II) with a consequent fluorescent decrease was designed. The chimera was the recognition element in a fluorescence-based biosensor able to detect mercury (II) in the nM range. Indeed, this biosensor specifically measure Hg2+ concentration also in the presence of other metals, reaching a limit of detection of 0.4 nM in tap water and 0.3 nM in sea water. Moreover, the developed biosensor was coupled to machine learning methodologies with the big advantage of predicting mercury concentration levels without the use of classical reader devices, thus allowing in situ monitoring of sea pollution by non-skilled personnel.

General Paradigm of Edge-Based Internet of Things Data Mining for Geohazard Prevention.

Geological hazards (geohazards) are geological processes or phenomena formed under external-induced factors causing losses to human life and property. Geohazards are sudden, cause great harm, and have broad ranges of influence, which bring considerable challenges to geohazard prevention. Monitoring and early warning are the most common strategies to prevent geohazards. With the development of the internet of things (IoT), IoT-based monitoring devices provide rich and fine data, making geohazard monitoring and early warning more accurate and effective. IoT-based monitoring data can be transmitted to a cloud center for processing to provide credible data references for geohazard early warning. However, the massive numbers of IoT devices occupy most resources of the cloud center, which increases the data processing delay. Moreover, limited bandwidth restricts the transmission of large amounts of geohazard monitoring data. Thus, in some cases, cloud computing is not able to meet the real-time requirements of geohazard early warning. Edge computing technology processes data closer to the data source than to the cloud center, which provides the opportunity for the rapid processing of monitoring data. This article presents the general paradigm of edge-based IoT data mining for geohazard prevention, especially monitoring and early warning. The paradigm mainly includes data acquisition, data mining and analysis, and data interpretation. Moreover, a real case is used to illustrate the details of the presented general paradigm. Finally, this article discusses several key problems for the general paradigm of edge-based IoT data mining for geohazard prevention.

The Role of Artificial Intelligence in Fighting the COVID-19 Pandemic.

The first few months of 2020 have profoundly changed the way we live our lives and carry out our daily activities. Although the widespread use of futuristic robotaxis and self-driving commercial vehicles has not yet become a reality, the COVID-19 pandemic has dramatically accelerated the adoption of Artificial Intelligence (AI) in different fields. We have witnessed the equivalent of two years of digital transformation compressed into just a few months. Whether it is in tracing epidemiological peaks or in transacting contactless payments, the impact of these developments has been almost immediate, and a window has opened up on what is to come. Here we analyze and discuss how AI can support us in facing the ongoing pandemic. Despite the numerous and undeniable contributions of AI, clinical trials and human skills are still required. Even if different strategies have been developed in different states worldwide, the fight against the pandemic seems to have found everywhere a valuable ally in AI, a global and open-source tool capable of providing assistance in this health emergency. A careful AI application would enable us to operate within this complex scenario involving healthcare, society and research.

Precision medicine and machine learning towards the prediction of the outcome of potential celiac disease.

Potential Celiac Patients (PCD) bear the Celiac Disease (CD) genetic predisposition, a significant production of antihuman transglutaminase antibodies, but no morphological changes in the small bowel mucosa. A minority of patients (17%) showed clinical symptoms and need a gluten free diet at time of diagnosis, while the majority progress over several years (up to a decade) without any clinical problem neither a progression of the small intestine mucosal damage even when they continued to assume gluten in their diet. Recently we developed a traditional multivariate approach to predict the natural history, on the base of the information at enrolment (time 0) by a discriminant analysis model. Still, the traditional multivariate model requires stringent assumptions that may not be answered in the clinical setting. Starting from a follow-up dataset available for PCD, we propose the application of Machine Learning (ML) methodologies to extend the analysis on available clinical data and to detect most influent features predicting the outcome. These features, collected at time of diagnosis, should be capable to classify patients who will develop duodenal atrophy from those who will remain potential. Four ML methods were adopted to select features predictive of the outcome; the feature selection procedure was indeed capable to reduce the number of overall features from 85 to 19. ML methodologies (Random Forests, Extremely Randomized Trees, and Boosted Trees, Logistic Regression) were adopted, obtaining high values of accuracy: all report an accuracy above 75%. The specificity score was always more than 75% also, with two of the considered methods over 98%, while the best performance of sensitivity was 60%. The best model, optimized Boosted Trees, was able to classify PCD starting from the selected 19 features with an accuracy of 0.80, sensitivity of 0.58 and specificity of 0.84. Finally, with this work, we are able to categorize PCD patients that can more likely develop overt CD using ML. ML techniques appear to be an innovative approach to predict the outcome of PCD, since they provide a step forward in the direction of precision medicine aimed to customize healthcare, medical therapies, decisions, and practices tailoring the clinical management of PCD children.

Advanced Machine-Learning Methods for Brain-Computer Interfacing.

The brain-computer interface (BCI) connects the brain and the external world through an information transmission channel by interpreting the physiological information of the brain during thinking activities. The effective classification of electroencephalogram (EEG) signals is the key to improving the performance of the system. To improve the classification accuracy of EEG signals in the BCI system, the transfer learning algorithm and the improved Common Spatial Pattern (CSP) algorithm are combined to construct a data classification model. Finally, the effectiveness of the proposed algorithm is verified. The results show that in actual and imagined movements, the accuracy of the left- and right-hand movements at different speeds is higher than when the speeds are the same. The proposed Adaptive Composite Common Spatial Pattern (ACCSP) and Self Adaptive Common Spatial Pattern (SACSP) algorithms have good classification effects on 5 subjects, with an average classification accuracy rate of 83.58 percent, which is an increase of 6.96 percent compared with traditional algorithms. When the training sample size is 10, the classification accuracy of the ACCSP algorithm is higher than that of the traditional CSP algorithm. The improved CSP algorithm combined with transfer learning embodies a good classification effect in both ACCSP and SACSP. Especially, the performance of SACSP mode is better. Combining the improved CSP algorithm proposed with the CSP-based transfer learning algorithm can improve the classification accuracy of the BCI classifier.

A deep learning approach for facility patient attendance prediction based on medical booking data.

Nowadays, data-driven methodologies based on the clinical history of patients represent a promising research field in which personalized and intelligent healthcare systems can be opportunely designed and developed. In this perspective, Machine Learning (ML) algorithms can be efficiently adopted to deploy smart services to enhance the overall quality of healthcare systems. In this work, starting from an in-depth analysis of a data set composed of millions of medical booking records collected from the public healthcare organization in the region of Campania, Italy, we have developed a predictive model to extract useful knowledge on patients, medical staff, and related healthcare structures. In more detail, the main contribution is to suggest a Deep Learning (DL) methodology able to predict the access of a patient in one or more medical facilities of a fixed set in the immediate future, the subsequent 2 months. A structured Temporal Convolutional Neural Network (TCNN) is designed to extract temporal patterns from the administrative medical history of a patient. The experiment shows the goodness of the designed methodology. Finally, this work represents a novel application of a TCNN model to a multi-label classification problem not linked to text categorization or image recognition.

3D data denoising via Nonlocal Means filter by using parallel GPU strategies.

Nonlocal Means (NLM) algorithm is widely considered as a state-of-the-art denoising filter in many research fields. Its high computational complexity leads researchers to the development of parallel programming approaches and the use of massively parallel architectures such as the GPUs. In the recent years, the GPU devices had led to achieving reasonable running times by filtering, slice-by-slice, and 3D datasets with a 2D NLM algorithm. In our approach we design and implement a fully 3D NonLocal Means parallel approach, adopting different algorithm mapping strategies on GPU architecture and multi-GPU framework, in order to demonstrate its high applicability and scalability. The experimental results we obtained encourage the usability of our approach in a large spectrum of applicative scenarios such as magnetic resonance imaging (MRI) or video sequence denoising.