1,721,229 research outputs found
A Unified Hierarchical XGBoost model for classifying priorities for COVID-19 vaccination campaign
No full textThe current ML approaches do not fully focus to answer a still unresolved and topical challenge, namely the prediction of priorities of COVID-19 vaccine administration. Thus, our task includes some additional methodological challenges mainly related to avoiding unwanted bias while handling categorical and ordinal data with a highly imbalanced nature. Hence, the main contribution of this study is to propose a machine learning algorithm, namely Hierarchical Priority Classification eXtreme Gradient Boosting for priority classification for COVID-19 vaccine administration using the Italian Federation of General Practitioners dataset that contains Electronic Health Record data of 17k patients. We measured the effectiveness of the proposed methodology for classifying all the priority classes while demonstrating a significant improvement with respect to the state of the art. The proposed ML approach, which is integrated into a clinical decision support system, is currently supporting General Pracitioners in assigning COVID-19 vaccine administration priorities to their assistants
eTourism: ICT and its role for tourism management
No full textPurpose: This paper aims to present innovative information and communication technology (ICT) infrastructure specifically designed and optimized for the tourism sector. The case presented, “La Valle del Pensare lungo il corso del Potenza”, has been conceived with the aim of providing a digital infrastructure to ten municipalities in the Marche Region (Italy), nestled among the valley of the Potenza River. This research project is aimed at developing an important communication system that facilitates the tourist routes of mining attractions and specific thematic routes across the territory, promoting historical centers, cultural heritage, green areas and interesting places. Design/methodology/approach: “La Valle del Pensare” information system has the main feature of being scalable and multi-purpose, as the contents can be managed and conveyed through the website, app mobile, totem touch screen and standard tourist signage. It is integrated and modular and allows to manage multiple information, ensuring an interoperable and multi-channel approach. It is designed for small municipalities in the province of Macerata to connect the territory’s resources and activities through a network. Findings: This work represents an important communication system, i.e. innovative ICT infrastructure that facilitates the tourist routes of mining attractions and specific thematic routes across the territory. Thanks to the collection of user-generated data, the platform allows monitoring of usage statistics and performances. In this way, the municipalities can infer useful information about user’s preferences and needs. The paper also discusses how “La Valle del Pensare” gives identity to the territory, which is not identified as a simple summation of the Common, but as a recognizable system that intends to implement the level of competitiveness through the creation of a real territorial logo able to identify vocations and specificity of the Valley of the Potenza. Originality/value: The value of the project lies in the ICT system, able to convey information at different scales, providing the users with updated contents; at the same time, administrations can constantly monitor its performances, being able to infer useful information about tourists’ needs, habits and preferences. The main contributions are the creation of a single cloud-based architecture for the management of multiple multi- media contents, to be exploited in various platforms; the design of a unique content management system used by several small municipalities of a same territory; the monitoring user’s preferences and needs by collecting users’ generated data; and the analysis of meaningful statistics about the tourists, tested and verified in real scenario with real users
Open-world person re-identification with RGBD camera in top-view configuration for retail applications
Full text linkPerson re-identification (re-ID) is currently a notably topic in the computer vision and pattern recognition communities. However, most of the existing works on re-ID have been designed for closed world scenarios, rather than more realistic open world scenarios, limiting the practical application of these re-ID techniques. In a common real-world application, a watch-list of known people is given as the gallery/target set for searching through a large volume of videos where the people on the watch-list are likely to return. This aspect is fundamental in retail for understanding how customers schedule their shopping. The identification of regular and occasional customers allows to define temporal purchasing profiles, which can put in correlation the customers' temporal habits with other information such as the amount of expenditure and number of purchased items. This paper presents the first attempt to solve a more realistic re-ID setting, designed to face these important issues called Top-View Open-World (TVOW) person re-id. The approach is based on a pretrained Deep Convolutional neural Network (DCNN), finetuned on a dataset acquired by using a top-view configuration. A special loss function called triplet loss was used to train the network. The triplet loss optimizes the embedding space such that data points with the same identity are closer to each other than those with different identities. The TVOW is evaluated on the TVPR2 dataset for people re-ID that is publicly available. The experimental results show that the proposed methods significantly outperform all competitive state-of-the-art methods, bringing to different and significative insights for implicit and extensive shopper behaviour analysis for marketing applications
Mask-R 2 CNN: a distance-field regression version of Mask-RCNN for fetal-head delineation in ultrasound images
Full text linkBackground and objectives: Fetal head-circumference (HC) measurement from ultrasound (US) images provides useful hints for assessing fetal growth. Such measurement is performed manually during the actual clinical practice, posing issues relevant to intra- and inter-clinician variability. This work presents a fully automatic, deep-learning-based approach to HC delineation, which we named Mask-R2CNN. It advances our previous work in the field and performs HC distance-field regression in an end-to-end fashion, without requiring a priori HC localization nor any postprocessing for outlier removal. Methods: Mask-R2CNN follows the Mask-RCNN architecture, with a backbone inspired by feature-pyramid networks, a region-proposal network and the ROI align. The Mask-RCNN segmentation head is here modified to regress the HC distance field. Results: Mask-R2CNN was tested on the HC18 Challenge dataset, which consists of 999 training and 335 testing images. With a comprehensive ablation study, we showed that Mask-R2CNN achieved a mean absolute difference of 1.95 mm (standard deviation = ± 1.92 mm), outperforming other approaches in the literature. Conclusions: With this work, we proposed an end-to-end model for HC distance-field regression. With our experimental results, we showed that Mask-R2CNN may be an effective support for clinicians for assessing fetal growth
An offline parallel architecture for forensic multimedia classification
Full text linkNowadays, the volume of the multimedia heterogeneous evidence presented for digital forensic analysis has significantly increased, thus requiring the application of big data technologies, cloud-based forensics services, as well as Machine Learning (ML) techniques. In digital forensics domain, ML algorithms have been applied for cybercrime investigation such as child abuse investigations, malware classification, and image forensics. This paper addresses this issues and deals with forensic analysis of digital images and videos. In particular, this work aims at proposing a multimedia classification tool with a parallel software architecture for a fast inspection, which is easy to use (to be used by officers during a search), requires limited hardware resources and it is built on an open-source software to limit its costs. Moreover, this tool must be able to quickly inspect multiple devices at a time. When positives are found in a device, such device will be seized for a deeper analysis later in the lab. It will not be seized otherwise, reducing the inconvenience for the suspect as well as the time required for the next analysis phase. As a case study, we focus on the identification of child pornography images. Experimental results show that the proposed architecture is capable of guaranteeing a high recall, a fast process and high performances in real scenarios
SeSAME: Re-identification-based ambient intelligence system for museum environment
Full text linkNowadays, understanding and analysing visitors activities and behaviours is becoming imperative for personalising and improving the user experience in a museum environment. Users' behaviour can provide important statistics, insights and objective information about their interactions, such as attraction, attention and action. These data represent a precious value for the museum curators, and they are one of the parameters that need to be assessed. These information are collected through manual approaches based on questionnaires or visual observations. This procedure is time consuming and can be affected by the subjective interpretation of the evaluator. From such premises, SeSAME (Senseable Self Adapting Museum Environment) a novel system for collecting and analysing the behaviours of visitors inside a museum environment is presented in this paper. SeSAME is based on a multi-modal deep neural network architecture able to extract anthropometric and appearance features from RGB-D videos acquired in crowded environments. Our approach has been tested on four different temporal modelling methods to aggregate a sequence of image-level features into clip-level features. This paper uses as a benchmark TVPR2, a public dataset of acquired videos with an RGB-D camera in a top-view configuration, in the presence of persistent and temporarily heavy occlusion. Moreover, a dataset specifically collected for this work has been acquired in a real museum environment, which is Palazzo Buonaccorsi, an important historical building in Macerata, in Marche Region in the center of Italy. During the experimental phase, the evaluation metrics show the effectiveness and the suitability of the proposed method
Energy Harvesting system for smart shoes
No full textThe aim of Energy Harvesting is to capture free energy, available without costs, from the environment. The development of advanced techniques allowed to capture, to store and to manage amounts of natural energy, transforming them into electrical energy. Moreover, advancements in microprocessor technology have increased power efficiency, effectively reducing power consumption requirements. From the point of view of wearable electronics devices, the most efficient Energy Harvesting system for energy capturing is that to use devices inserted into the shoes. These devices are situated into the soles where, during the movement, a force is exerted. Using piezoelectric elements and electromagnetic induction systems, this force allows recovering a high quantity of electrical energy useful for sensor supply and complex monitoring systems. In this paper, four different solutions of smart shoes that use Energy Harvesting systems are presented, with the aim to recover energy to supply a GPS device. Preliminary comparative results of 4 different solutions are compared on the bases of costs, production feasibility and energy harvesting capabilities.The aim of Energy Harvesting is to capture free energy, available without costs, from the environment. The development of advanced techniques allowed to capture, to store and to manage amounts of natural energy, transforming them into electrical energy. Moreover, advancements in microprocessor technology have increased power efficiency, effectively reducing power consumption requirements. From the point of view of wearable electronics devices, the most efficient Energy Harvesting system for energy capturing is that to use devices inserted into the shoes. These devices are situated into the soles where, during the movement, a force is exerted. Using piezoelectric elements and electromagnetic induction systems, this force allows recovering a high quantity of electrical energy useful for sensor supply and complex monitoring systems. In this paper, four different solutions of smart shoes that use Energy Harvesting systems are presented, with the aim to recover energy to supply a GPS device. Preliminary comparative results of 4 different solutions are compared on the bases of costs, production feasibility and energy harvesting capabilities
- …
