1,721,049 research outputs found
Multiview learning in biomedical applications
No full textMotivation: In the era of big data, the richness and variety of available datasets have opened new horizons for investigators in the biomedical field. The ultimate challenge consists in building an integrated base of knowledge derived from heterogeneous sources. Multiview learning is the branch of machine learning concerned with the analysis of multimodal data, i.e., patterns represented by different sets of features extracted from multiple data sources. In recent years, multiview learning methodologies have become increasingly popular, and a high number of biomedical applications based on multiview data have been recorded in the literature. For example, in bioinformatics, analyses can be based on multiple experiments investigating different facets of the same phenomena, such as gene expression, microRNA expression, protein-protein interactions, genome-wide association, and so on, to capture information regarding different aspects of biological systems. In the same way, neuroscience data analysis can benefit from different imaging modalities that allow to study different features of the nervous system (e.g., structural vs functional organization). Compared to the limited perspective offered by single-view analyses, the integration of multiple views can provide a deeper understanding of the underlying principles governing complex systems. Results: In this work, we review the existing multiview methodologies to discuss their operation modes and principles, with the goal of increasing their further development in the biomedical field. We organized the described methods in three categories, according to the type of data, the statistical problem, and the type of integration. This discussion, which highlights the advantages and disadvantages of different schools of thought, is intended to be a reference for those who want to start working with the integration of biomedical data. We selected a number of representative examples in bioinformatics and neuroinformatics to show the potential of multiview learning applications for cutting-edge research problems. First, we explain how multiview clustering can be used to perform patient subtyping to identify groups of patients that share similar molecular characteristics and possibly similar reactions to treatment. Then, the drug-repositioning problem is introduced and a discussion of the multiview classification methods used in the literature is provided. We then describe an example of how both clustering and classification can be combined in a multiview setting for the automated diagnosis of neurodegenerative disorders and we explain how multiple noninvasive imaging modalities can be exploited together to obtain more accurate brain parcellations. We additionally introduce the emerging fields of single-cell multiomics data analysis and brain imaging genomics. Finally, we discuss how deep learning techniques, which are getting more and more recognition in various fields, can be applied to multimodal data to learn complex representations, and we present a few examples of application
Institutions, social capital and distributive dynamics in development policies in Calabria
No full textAdaptive Neuro-Fuzzy Inference Systems vs Stochastic Models for Mortality data
No full textA comparative analysis is done between stochastic models and Adaptive Neuro–Fuzzy Inference System applied to the projection of the longevity trend. The stochastic models provides the heuristic rule for obtaining projections. In the context of ANFIS models, the fuzzy logic allows for determining the learning algorithm on the basis of the relationship between inputs and outputs. In other words the rule is here deducted by the actual mortality data, because this allows for fuzzy systems to learn from the data they are modelling. This is possible by computing the membership function parameters that best allow the associated fuzzy inference system to track the input/output data. The literature indicates that the self-predicting model of ANFIS is better than other models in a lot of fields. Shortcomings and advantages of both approaches are here highlighted
Exploration and Exploitation in Optimizing a Basic Financial Trading System: A Comparison Between FA and PSO Algorithms
No full textWhen coping with complex global optimization problems, often it is not possible to obtain either analytical or exact solutions. Therefore, one is forced to resort to approximate numerical optimizers. With this aim, several metaheuristics have been proposed in the literature and the primary approaches can be traced back to biology and physics. On one hand, there exist bio-inspired metaheuristics that imitate the Darwinian evolution of species (like, for instance, Genetic Algorithms) or the behaviour of group of social organisms (like, for instance, Ant Colony Optimization). On the other hand, there exist physics-inspired metaheuristics that mimic physical laws (like, for instance, gravitation and electromagnetism). In this work, we take into account the Fireworks Algorithm and the Particle Swarm Optimization in order to compare their exploration and exploitation capabilities. In particular, the investigation is performed considering as complex global optimization problem the estimation of the parameters of the technical analysis indicator Bollinger Bands in order to build effective financial trading systems, similarly to what proposed in (Corazza et al., 2019).When coping with complex global optimization problems, often it is not possible to obtain either analytical or exact solutions. Therefore, one is forced to resort to approximate numerical optimizers. With this aim, several metaheuristics have been proposed in the literature and the primary approaches can be traced back to biology and physics. On one hand, there exist bio-inspired metaheuristics that imitate the Darwinian evolution of species (like, for instance, Genetic Algorithms) or the behaviour of group of social organisms (like, for instance, Ant Colony Optimization). On the other hand, there exist physics-inspired metaheuristics that mimic physical laws (like, for instance, gravitation and electromagnetism). In this work, we take into account the Fireworks Algorithm and the Particle Swarm Optimization in order to compare their exploration and exploitation capabilities. In particular, the investigation is performed considering as complex global optimization problem the estimation of the parameters of the technical analysis indicator Bollinger Bands in order to build effective financial trading systems, similarly to what proposed in[3]
The Ecological Footprint to Measure the Environmental Sustainability of Buildings: A Case Study
No full textRadial Basis Function Interpolation for Referenceless Thermometry Enhancement
No full textMRgFUS (Magnetic Resonance guided Focused UltraSound) is a new and non-invasive technique to treat different diseases in the oncology field, that uses Focused Ultrasound (FUS) to induce necrosis in the lesion.
Temperature change measurements during ultrasound thermo-therapies can be performed through magnetic resonance monitoring by using Proton Resonance Frequency (PRF) thermometry. It measures the phase variation resulting from the temperature-dependent changes in resonance frequency by subtracting one phase baseline image from actual phase. Referenceless thermometry aims to re-duce artefacts caused by tissue motion and frequency drift, fitting the back-ground phase outside the heated region. The aim of this contribution is to pro-pose a novel background phase reconstruction method using Radial Basis Func-tion (RBF) interpolation. The effectiveness of the method has been demonstrat-ed by comparing it against the classical PRF shift and polynomial referenceless approach. The comparison evaluates temperature rises in uterine fibroids during MRgFUS treatments on a set of 10 patients
The Rural Landscape Is the Backdrop for the Promotion of Outdoor Sports. A Case Study
No full textOverall, rural space represents a common good, beyond ownership structures and forms of management. Attention must increasingly be paid to the multifunctionality of rural and open territory; to its ability to produce a flow of goods and services useful to the community, linked not only to primary production, but also and above all to the recycling and reconstitution of basic resources
(air, water, soil), the maintenance of ecosystems, biodiversity, of the landscape; to tourism, opportunities for recreation and outdoor life. In particular, the contribution highlights the importance of the rural landscape and its recreational potential in outdoor sports. For some time now, the rural landscape has been observed and studied as a fundamental element for sustainable territorial development, espe
cially in the more peripheral territories. The landscape perspective is promoted
globally by all major institutions and through important regional directives and policies. In particular, the rediscovery of the rural landscape as a historical and cultural product has made it an integral part of many initiatives for positive integration between society and the environment. The practical contribution of this study is to highlight how the combination of rural landscape and sport can translate into opportunities for regional development and knowledge of lesser-known tourist destinations
Applicability of Methodological Approaches and Tools for Detecting Preferences in Housing Choice
No full textThe ongoing digital transition profoundly affects people's habits and customs by dislodging them from the place where they have always resided and determining a new demand for housing mobility. The new demand is centered on the choice, conscious and commensurate with one's needs and availability, of the place to live. This phenomenon can significantly affect land-use government activity and requires tools, methodologies and models in order to be understood as the “historicist” approach on which municipalities’ planning activities are based is not deemed sufficient. Based on the above, this paper aims to illustrate some initial results of a Project-to of Significant National Interest referred to in the call No. 1409 of 14-9-2022 (PRIN 2022 PNRR) approved by the Ministry of University and Research (MUR) entitled “Housing mobility and digital transition. Evaluation tools and technologies for understanding current and future people's living needs, supporting territorial governance and regeneration processes.“ This Research project is configured as a prodromal study and investigation activity for understanding, among demographic phenomena, housing mobility, which signi-ficantly affects urbanization phenomena on which land use and protection, urban regeneration, and the protection and enhancement of agricultural activity. These topics are of great interest to the PNRR
- …
