3,276 research outputs found
Truck-based drone delivery system: An economic and environmental assessment
No full textInnovative solutions for last-mile delivery have sparked great interest among consumers and logistics operators. The combination of new technologies with existing ones can lead to new possible last-mile delivery configurations, among which truck-drone joint delivery is one of the most promising. This paper evaluates the environmental and economic sustainability of a last-mile delivery solution involving electric trucks equipped with drones, and it provides a comparison with traditional logistics systems. The comparative life cycle assessment methodology is used to quantify the greenhouse gas emissions per parcel delivered. The total cost of ownership methodology is adopted for the economic analysis. Results suggest that the truck-drone alternative leads to significant emissions reductions, while its cost performance is primarily affected by the drone automation level
Deep Deterministic Policy Gradient Control of Type 1 Diabetes
No full textType 1 diabetes is one of the major concerns in current medical studies. Traditional clinical practice involves non-autonomous manual injection of insulin in the blood, while current research in the field of autonomous regulation of blood glucose concentration mostly focuses on model-based control techniques. This paper introduces a novel Reinforcement Learning-based controller for autonomous glycemic regulation in the treatment of type 1 diabetes, building on the Deep Deterministic Policy Gradient algorithm. The proposed control method is validated through in-vitro simulations on the Bergman glucoregulatory model, proving that it successfully preserves healthy values of blood glucose concentration, while overcoming both standard clinical practice and classical model-based control techniques in terms of both control effort and computational efficiency for real-time applications
Behavioural Cloning for Serious Games in Support of Pediatric Neurorehabilitation
No full textBehavioural Cloning is a Machine Learning method concerning how a machine attempts to autonomously mimic the actions of a human, or in general a complex controller, performing a given task. This work innovatively exploits Behavioural Cloning in support of Pediatric Neurorehabilitation. In particular, an Artificial Neural Network Classifier has been implemented to autonomously adapt the difficulty, through a set of tunable parameters, of a Serious Game that was specifically developed to stimulate some relevant cognitive capabilities of the patient. Data augmentation via Behavioural Cloning allows such autonomous difficulty adaptation system to improve its classification performances and, thus, to enforce a control logic that, in turn, improves the effectiveness of the cognitive training. The system is validated through an experimental assessment on a Serious Game that trains motor coordination: experimental results of children gameplay are analyzed and discussed
CADUCEO: A Platform to Support Federated Healthcare Facilities through Artificial Intelligence
No full textData-driven algorithms have proven to be effective for a variety of medical tasks, including disease categorization and prediction, personalized medicine design, and imaging diagnostics. Although their performance is frequently on par with that of clinicians, their widespread use is constrained by a number of obstacles, including the requirement for high-quality data that are typical of the population, the difficulty of explaining how they operate, and ethical and regulatory concerns. The use of data augmentation and synthetic data generation methodologies, such as federated learning and explainable artificial intelligence ones, could provide a viable solution to the current issues, facilitating the widespread application of artificial intelligence algorithms in the clinical application domain and reducing the time needed for prevention, diagnosis, and prognosis by up to 70%. To this end, a novel AI-based functional framework is conceived and presented in this paper
Future Prospects of the Dutch Energy Transition: Analysis of Agents’ Behavior through Energy System Modelling
No full textThe present research takes place at the Environmental Assessment Agency, in the Department of Climate, Air andEnergy. The core objective is to improve the investment module of a national energy system simulation model(Ensysi) that wants to represent actors’ technology-investments in the energy transition context.An initial literature review has revealed the importance of the agents’ rational and non rational behavior in determiningthe future stock evolution, given the high level of uncertainty of some key variables such as future energycarriers prices and ETS prices. With regard to this, Ensysi presents the shortcoming that investment decisions arenot forward looking but just consider the costs and revenues of the year in which the decision takes place. Themodel expansion performed in this research is therefore aimed at re-formulating the investment concept througha discounting calculation so that some exploratory scenarios in terms of actors’ behavior and expectations can bedesigned and analysed.The literature review has covered firstly an overview of energy modeling techniques and categories in order tointroduce Ensysi and categorize it within the existing energy modelling scenario. Secondly, the core object ofthe research was investigated: how investment decisions happen in reality for the actor group of consumers andcompanies. Since Ensysi is not yet provided with a solid theoretical formulation, the main theories for technologyinvestmentdecisions were reviewed in order to find the one appropriate for the theoretical underpinnings of Ensysi.Based on that a conceptual model was formulated, clarifying the nature of the relationships among different variablesand providing a first guide for the subsequent research steps. The formulated conceptual model is based onDiffusion of Innovation theory from Rogers (2003) and some notions from environmental psychology.After the literature review and theoretical validation, a careful analysis of the current module formulation has beendone to reformulate a part of the investment simulation module. More specifically a new parameter connected to anet present value calculation was created to introduce in the model the actors’ perceived time dimension of moneyflows so as to include expectations about future costs.The outputs from the new version were then compared to the ones from the original version to observe whichnew potentialities arise from the model expansion. Two case analysis for different energy subsystems (transportpassenger cars for consumers and electricity generation for companies) were considered to draw research insightsvaluable for energy policy from the new potentiality of the model. The results of these simulations confirm theadded value of defining actor scenarios based on different expectations and long term financial evaluations ratherthan highly uncertain behavioral parameters: more modelling transparency and validation possibilities, as well asrichness of decision-making simulation scope.Management of Technology (MoT
Large-scale sequencing and comparative analysis of oenological Saccharomyces cerevisiae strains supported by nanopore refinement of key genomes
No full textSaccharomyces cerevisiae has long been part of human activities related to the production of food and wine. The industrial demand for fermented beverages with well-defined and stable characteristics boosted the isolation and selection of strains conferring a distinctive aroma profile to the final product. To uncover variants characterizing oenological strains, the sequencing of 65 new S. cerevisiae isolates, and the comparison with other 503 publicly available genomes were performed. A hybrid approach based on short Illumina and long Oxford Nanopore reads allowed the in-depth investigation of eleven genomes and the identification of putative laterally transferred regions and structural variants. A comparative analysis between clusters of strains belonging to different datasets allowed the identification of novel relevant genetic features including single nucleotide polymorphisms, insertions and structural variants. Detection of oenological single nucleotide variants shed light on the existence of different levels of modulation for the mevalonate pathway relevant for the biosynthesis of aromatic compounds
Etude des resonances de basse masse (rho, omega, phi) dans les collisions S-U et O-U a 200 GeV par nucleon
No full textSIGLEINIST T 72937 / INIST-CNRS - Institut de l'Information Scientifique et TechniqueFRFranc
Comemoração do jubileu de prata do pontificado de sua Santidade o Papa João Paulo II
No full textDiscursos do deputado Osmânio Pereira, representando a Câmara dos Deputados; do
senador Marco Maciel, representando o Senado Federal; de Dom Lourenço Baldisseri, Núncio Apostólico no Brasil; do presidente do Congresso Nacional senador José Sarney, e discurso enviado à Mesa pela senadora Serys Slhessarenko, na sessão solene do Congresso Nacional, de 30 de outubro de 2003
Variazione del profilo lipidico nel latte in relazione alla concentrazione di corpi chetonici nel plasma di bovine durante al fase di transizione
No full textDeep Reinforcement Learning Control of Type-1 Diabetes with Cross-Patient Generalization
No full textType 1 diabetes is one of the major concerns in current medical studies, as the World Health Organisation plans to reduce mortality due to such disease by one third by 2030. Standard clinical practice involves self-administered injections of insulin, while current research in the field of automatic control of blood glucose concentration mostly focuses on model-based control techniques. This work presents an application of a Deep Reinforcement Learning-based controller for autonomous treatment of type 1 diabetes, building on the Deep Determin-istic Policy Gradient algorithm. Such control framework is applied for the first time on the Python implementation of the UVA/Padova simulator, named Simglucose. The proposed methodology is validated through in-vitro simulations on an inter-cluster cross-generalization group of virtual adult patients, showing that normoglycemia is successfully preserved while assuring cross-patient generalization and outperforming clinical practice, without the direct knowledge of the amount of ingested carbohydrates
- …
