Search

The COVID-19 pandemic has changed the way that society functions. The state governments have chosen different measures to respond to the spread of the virus as there was no clear evidence on what the best way is to respond. In this paper, we gather the evidence of governments’ stringency measures and couple it with countries’ socio-economic data (including the amounting of tests that each country performed) to explore how they influenced the COVID-19 spread. We evaluated how well seven different regression models can predict the spread of the virus. The spread of the virus is expressed through the number of positively identified individuals as well as deaths reported due to the virus. For the prediction of the number of new cases, ElasticNet algorithm was the best performing, followed by Linear Regression and LASSO. LASSO algorithms predicted the best number of new deaths. The metrics used to evaluate were: R-squared score, Adjusted R-squared Score, mean square error (MSE), mean absolute error (MAE), and root mean square error (RMSE). The most effective measure was the stay-at-home measure followed by workplace and school closures. With the availability of new and more accurate data and variables, the models can be further improved.

This article aims to provide a thorough overview of the use of Artificial Intelligence (AI) techniques in studying the gut microbiota and its role in the diagnosis and treatment of some important diseases. The association between microbiota and diseases, together with its clinical relevance, is still difficult to interpret. The advances in AI techniques, such as Machine Learning (ML) and Deep Learning (DL), can help clinicians in processing and interpreting these massive data sets. Two research groups have been involved in this Scoping Review, working in two different areas of Europe: Florence and Sarajevo. The papers included in the review describe the use of ML or DL methods applied to the study of human gut microbiota. In total, 1109 papers were considered in this study. After elimination, a final set of 16 articles was considered in the scoping review. Different AI techniques were applied in the reviewed papers. Some papers applied ML, while others applied DL techniques. 11 papers evaluated just different ML algorithms (ranging from one to eight algorithms applied to one dataset). The remaining five papers examined both ML and DL algorithms. The most applied ML algorithm was Random Forest and it also exhibited the best performances.

The study of microbiome and its relationship with the host organism has recorded rapid increase in popularity over the past decade. The advances in the sequencing techniques used for extraction of microbiome data have stimulated the development of sophisticated bioinformatics tools used to analyze large amounts of data. The gut microbiome, as a network of microorganisms that is the focus of this study, has been implicated in several disorders such as colorectal cancer, obesity, irritable bowel syndrome, diabetes, and metabolic syndrome, and more recently in the study of Parkinsons and Alzheimers diseases as well. This study aims to examine the relationship between multiple sclerosis, autoimmune central nervous system disease, and gut microbial community composition, using the samples obtained 16s rRNA sequencing technique. Healthy control and multiple sclerosis groups of sequences were analyzed. Using the extracted set of statistically significant bacteria, a Random Forest classifier has been developed. The most significant microbiome alterations in multiple sclerosis patients imply increase in Akkermansia and Methanobrevibacter, and decrease in Butyvricimonas bacteria at the genus. The highest accuracy scores obtained by the developed classifier are 84.61% using the genus level bacteria. The presented methods and results define a paradigm that can be used to help guide medical decision making.

The application of machine learning (ML) techniques could facilitate the identification of predictive biomarkers of somatostatin analog (SSA) efficacy in patients with neuroendocrine tumors (NETs). We collected data from 74 patients with a pancreatic or gastrointestinal NET who received SSA as first-line therapy. We developed three classification models to predict whether the patient would experience a progressive disease (PD) after 12 or 18 months based on clinic-pathological factors at the baseline. The dataset included 70 samples and 15 features. We initially developed three classification models with accuracy ranging from 55% to 70%. We then compared ten different ML algorithms. In all but one case, the performance of the Multinomial Naïve Bayes algorithm (80%) was the highest. The support vector machine classifier (SVC) had a higher performance for the recall metric of the progression-free outcome (97% vs. 94%). Overall, for the first time, we documented that the factors that mainly influenced progression-free survival (PFS) included age, the number of metastatic sites and the primary site. In addition, the following factors were also isolated as important: adverse events G3–G4, sex, Ki67, metastatic site (liver), functioning NET, the primary site and the stage. In patients with advanced NETs, ML provides a predictive model that could potentially be used to differentiate prognostic groups and to identify patients for whom SSA therapy as a single agent may not be sufficient to achieve a long-lasting PFS.

© 2017 Elsevier LtdTo avoid motion artefacts when merging multiple exposures into a high dynamic range image, a number of HDR deghosting algorithms have been proposed. However, these algorithms do not work equally well on all types of scenes, and some may even introduce additional artefacts. As the number of proposed deghosting methods is increasing rapidly, there is an immediate need to evaluate them and compare their results. Even though subjective methods of evaluation provide reliable means of testing, they are often cumbersome and need to be repeated for each new proposed method or even its slight modification. Because of that, there is a need for objective quality metrics that will provide automatic means of evaluation of HDR deghosting algorithms. In this work, we explore several computational approaches of quantitative evaluation of multi-exposure HDR deghosting algorithms and demonstrate their results on five state-of-the-art algorithms. In order to perform a comprehensive evaluation, a new dataset consisting of 36 scenes has been created, where each scene provides a different challenge for a deghosting algorithm. The quality of HDR images produced by deghosting method is measured in a subjective experiment and then evaluated using objective metrics. As this paper is an extension of our conference paper, we add one more objective quality metric, UDQM, as an additional metric in the evaluation. Furthermore, analysis of objective and subjective experiments is performed and explained more extensively in this work. By testing correlation between objective metric and subjective scores, the results show that from the tested metrics, that HDR-VDP-2 is the most reliable metric for evaluating HDR deghosting algorithms. The results also show that for most of the tested scenes, Sen et al.'s deghosting method outperforms other evaluated deghosting methods. The observations based on the obtained results can be used as a vital guide in the development of new HDR deghosting algorithms, which would be robust to a variety of scenes and could produce high quality results.

A major obstacle for real-time rendering of high-fidelity graphics is computational complexity. A key point to consider in the pursuit of “realism in real time” in computer graphics is that the Human Visual System (HVS) is a fundamental part of the rendering pipeline. The human eye is only capable of sensing image detail in a 2 ˆ foveal region, relying on rapid eye movements, or saccades, to jump between points of interest. These points of interest are prioritized based on the saliency of the objects in the scene or the task the user is performing. Such “glimpses” of a scene are then assembled by the HVS into a coherent, but inevitably imperfect, visual perception of the environment. In this process, much detail, that the HVS deems unimportant, may literally go unnoticed. Visual science research has identified that movement in the background of a scene may substantially influence how subjects perceive foreground objects. Furthermore, recent computer graphics work has shown that both fixed viewpoint and dynamic scenes can be selectively rendered without any perceptual loss of quality, in a significantly reduced time, by exploiting knowledge of any high-saliency movement that may be present. A high-saliency movement can be generated in a scene if an otherwise static objects starts moving. In this article, we investigate, through psychophysical experiments, including eye-tracking, the perception of rendering quality in dynamic complex scenes based on the introduction of a moving object in a scene. Two types of object movement are investigated: (i) rotation in place and (ii) rotation combined with translation. These were chosen as the simplest movement types. Future studies may include movement with varied acceleration. The object's geometry and location in the scene are not salient. We then use this information to guide our high-fidelity selective renderer to produce perceptually high-quality images at significantly reduced computation times. We also show how these results can have important implications for virtual environment and computer games applications.

Visual perception is becoming increasingly important in computer graphics. Research on human visual perception has led to the development of perception driven computer graphics techniques, where knowledge of the human visual system and, in particular, its weaknesses are exploited when rendering and displaying 3D graphics. It is well known that many sensory stimuli, including smell, may influence the amount of cognitive resources available to a viewer to perform a visual task. In this paper we investigate the influence smell effects have on the perception of object quality in a rendered image. We show how we can potentially accelerate the rendering of images by directing the viewer's attention towards the source of a smell and selectively rendering at high quality only the smell emitting objects. Other parts of an image can be rendered at a lower quality without the viewer being aware of this quality difference. By doing this, we can significantly reduce rendering time without any loss in the user's perception of delivered quality.

The Human Visual System (HVS) is a key part of the rendering pipeline. The human eye is only capable of sensing image detail in a 2° foveal region, relying on rapid eye movements, or saccades, to jump between points of interest. These points of interest are prioritised based on the saliency of the objects in the scene or the task the user is performing. These "glimpses" of a scene are then assembled by the HVS into a coherent, but inevitably imperfect, visual perception of the environment. In this process, much detail, which the HVS deems unimportant, may literally go unnoticed.The major obstacle for real-time rendering of high fidelity graphics is computational complexity. Visual science research has shown that movement in the background of a scene may influence how subjects perceive foreground objects. In this paper we use knowledge of the HVS to show that we can selectively render walk-throughs without perceptual loss of quality, at significantly reduced time, if high saliency movement is present during the animation.

A cutting-edge method to assess the status of photoreceptors is represented by chromatic pupillometry, which consists in stimulating the eyes of the patients with light of different wavelengths and intensities. The signals of the dynamics of the pupil after the optical stimulations can be approximated by a 2nd-order linear model. Fitting parameters are established by a weighted least-squares algorithm, in order to achieve the correct estimate of the shape of the pupillometric data. Results presented in this work indicate that our model is able to capture the dynamics of pupillometric signals.

The use of chromatic pupil responses may be a novel way to diagnose and monitor diseases affecting either the outer or inner retina. Here we developed a model-based approximation of the dynamics of pupillary diameter after an optical stimulation; we assume the response of the pupil is approximated as the output of a 2nd-order linear model. Model parameters are identified by using a least-squares fitting procedure, thus obtaining an optimal estimate of the activation time and of the shape of the pupil response to the stimulation. Results indicate the model adequately represents the curve shape; despite the presence of artifacts, that hinder the fitting procedure, a significant difference in the time constants of the model of controls and of patients is present.