GamECAR aims to develop a highly innovative and interactive Serious Games platform that will empower guide users adopt an eco-friendly driving style. This be achieved, without distracting them from safe driving, through multidisciplinary approach aiming at the development of user friendly, unobtrusive multi-player gaming environment, where not only play collaboratively/competitively using their mobile device but also use car itself own bodies, thus turning eco-driving into immersive...

Environment perception constitutes one of the most critical operations performed by semi-and fully- autonomous vehicles. In recent years, Deep Neural Networks (DNNs) have become standard tool for solutions owing to their impressive capabilities in analyzing and modelling complex dynamic scenes, from (often muti-modal) sensory inputs. However, well-established performance DNNs comes at cost increased time storage complexity, which may problematic automotive systems due requirement a short...

Asthma and chronic obstructive pulmonary disease are respiratory diseases that affect negatively the quality of life for patients their families worldwide. Despite significance these diseases, management has been considered suboptimal around world, whereas improper inhaler use underlined as one main causes. Toward this direction, paper presents an integrated mHealth system provides real-time personalized feedback to assessing proper medication educating them helping avoid common mistakes....

Recent advances in 3D scanning technology have enabled the deployment of models various industrial applications like digital twins, remote inspection and reverse engineering. Despite their evolving performance, scanners, still introduce noise artifacts acquired dense models. In this work, we propose a fast robust denoising method for scanned The proposed approach employs conditional variational autoencoders to effectively filter face normals. Training inference are performed sliding patch...

Nowadays, the preservation and maintenance of historical objects is main priority in area heritage culture. The new generation 3D scanning devices assets technological improvements have created a fertile ground for developing tools that could facilitate challenging tasks which traditionally required huge amount human effort specialized knowledge experts (e.g., detailed inspection defects object due to aging). These demand more effort, especially some special cases, such as large-scale or...

Asthma is a common, usually long-term respiratory disease with negative impact on global society and economy. Treatment involves using medical devices (inhalers) that distribute medication to the airways its efficiency depends precision of inhalation technique. There clinical need for objective methods assess technique, during consultation. Integrated health monitoring systems, equipped sensors, enable recognition drug actuation, embedded sound signal detection, analysis identification from...

Obstructive inflammatory pulmonary diseases are life-long conditions of the airways affecting millions worldwide. A crucial step towards effective self-management is adherence patients to their medication. Accurate detection pressurised metered dose inhaler audio events can significantly improve medication facilitating more meaningful interventions by medical personnel. Towards this direction, work presents a data-driven approach for monitoring employing recurrent neural networks with long...

The complexity of BIM software presents significant barriers to the widespread adoption and model-based design within Architecture, Engineering, Construction (AEC) sector. End-users frequently express concerns regarding additional effort required create a sufficiently detailed model when compared with conventional 2D drafting. This study explores potential sequential recommendation systems accelerate modeling process. By treating commands as recommendable items, we introduce novel end-to-end...

Facing increasingly complex BIM authoring software and the accompanying expensive learning costs, designers often seek to interact with in a more intelligent lightweight manner. They aim automate modeling workflows, avoiding obstacles difficulties caused by usage, thereby focusing on design process itself. To address this issue, we proposed an LLM-based autonomous agent framework that can function as copilot tool, answering usage questions, understanding user's intentions from natural...

The conventional BIM authoring process typically requires designers to master complex and tedious modeling commands in order materialize their design intentions within tools. This additional cognitive burden complicates the hinders adoption of model-based AEC (Architecture, Engineering, Construction) industry. To facilitate expression more intuitively, we propose Text2BIM, an LLM-based multi-agent framework that can generate 3D building models from natural language instructions. orchestrates...

Mesh saliency has been widely considered as the measure of visual importance certain parts 3D geometries, distinguishable from their surroundings, with respect to human perception. This work is based on use convolutional neural networks extract maps for large and dense scanned models. The network trained extracted by fusing local global spectral characteristics. Extensive evaluation studies carried out using various models, include perception in simplification compression cases. As a result,...

Delineation approaches provide significant benefits to various domains, including agriculture, environmental and natural disasters monitoring. Most of the work in literature utilize traditional segmentation methods that require a large amount computational storage resources. Deep learning has transformed computer vision dramatically improved machine translation, though it requires massive dataset for training resources inference. More importantly, energy-efficient embedded hardware...

Contemporary sensing devices provide reliable mechanisms for continuous process monitoring, accommodating use cases related to mHealth and smart mobility, by generating real-time data streams of numerous physiological vital parameters. Such can be later utilized machine learning algorithms decision support systems predict critical clinical states motivate users adopt behaviours that improve the quality their life society as a whole. However, in many cases, even when deployed over highly...

This paper presents AVATREE, a computational modelling framework that generates Anatomically Valid Airway tree conformations and provides capabilities for simulation of broncho-constriction apparent in obstructive pulmonary conditions. Such are obtained from the personalized 3D geometry generated computed tomography (CT) data through image segmentation. The patient-specific representation bronchial structure is extended beyond visible airway generation depth using knowledge-based technique...

Chronic respiratory diseases, such as asthma, are very common around the world and have been shown to a significant effect on quality of life patients. A crucial component for effective management asthma is adherence patients their medication prescription, which can be separated into two distinct equally important components, i) time schedule use inhaled ii) competence in using inhaler correctly effectively. Aiming this direction current paper investigates three different algorithmic...

Effective management of chronic constrictive pulmonary conditions lies in proper and timely administration medication. As a series studies indicates, medication adherence can effectively be monitored by successfully identifying actions performed patients during inhaler usage. This study focuses on the recognition audio events usage pressurized metered dose inhalers (pMDI). Aiming at real-time performance, we investigate deep sparse coding techniques including convolutional filter pruning,...

Nowadays, three-dimensional (3D) meshes are widely used in various applications different areas (e.g., industry, education, entertainment and safety). The 3D models captured with multiple RGB-D sensors, the sampled geometric manifolds processed, compressed, simplified, stored, transmitted to be reconstructed a virtual space. These low-level processing require accurate representation of that can achieved through saliency estimation mechanisms identify specific model representing surface...

Automotive Cyber-Physical Systems (ACPS) have attracted a significant amount of interest in the past few decades, while one most critical operations these systems is perception environment. Deep learning and, especially, use Neural Networks (DNNs) provides impressive results analyzing and understanding complex dynamic scenes from visual data. The prediction horizons for those are very short inference must often be performed real time, stressing need transforming original large pre-trained...

Conventional pedestrian simulators are inevitable tools in the design process of a building, as they enable project engineers to prevent overcrowding situations and plan escape routes for evacuation. However, simulation runtime multiple cumbersome steps generating results potential bottlenecks during building process. Data-driven approaches have demonstrated their capability outperform conventional methods speed while delivering similar or even better across many disciplines. In this work,...

Detailed and accurate vehicle-oriented sensor data is considered fundamental for efficient vehicle-to-everything V2X communication applications, especially in the upcoming highly heterogeneous, brisk agile 5G networking era. Information retrieval, transfer manipulation real-time offers a small margin erratic behavior, regardless of its root cause. This paper presents method managing nonuniformities uncertainties found on datasets, based an elaborate Matrix Completion technique, with superior...

Chronic inflammatory conditions are obstructive respiratory diseases that affect negatively the quality of life for patients and their families worldwide. The effective control these is achieved through use pressurized meter dose inhaler (pMDI). However, management has been considered suboptimal, mainly due to improper device. Towards this direction, work presents deep sparse Convolutional Neural Network (CNN) as a classifier provide real-time assessment medication adherence. classification...