Iskanje po repozitoriju

A+ | A- | | SLO | ENG

Povzetek: Sensor-based human activity recognition is becoming ever more prevalent. The increasing importance of distinguishing human movements, particularly in healthcare, coincides with the advent of increasingly compact sensors. A complex sequence of individual steps currently characterizes the activity recognition pipeline. It involves separate data collection, preparation, and processing steps, resulting in a heterogeneous and fragmented process. To address these challenges, we present a comprehensive framework, HARE, which seamlessly integrates all necessary steps. HARE offers synchronized data collection and labeling, integrated pose estimation for data anonymization, a multimodal classification approach, and a novel method for determining optimal sensor placement to enhance classification results. Additionally, our framework incorporates real-time activity recognition with on-device model adaptation capabilities. To validate the effectiveness of our framework, we conducted extensive evaluations using diverse datasets, including our own collected dataset focusing on nursing activities. Our results show that HARE’s multimodal and on-device trained model outperforms conventional single-modal and offline variants. Furthermore, our vision-based approach for optimal sensor placement yields comparable results to the trained model. Our work advances the field of sensor-based human activity recognition by introducing a comprehensive framework that streamlines data collection and classification while offering a novel method for determining optimal sensor placement.
Ključne besede: human activity recognition, multimodal classification, privacy preservation, real-time classification, sensor placement
Objavljeno v DiRROS: 11.12.2023; Ogledov: 205; Prenosov: 79
Celotno besedilo (6,40 MB)
Gradivo ima več datotek! Več...

Povzetek: The surface properties of hydrocarbon polymers are inadequate for numerous applications. Hence, they require alteration via functionalisation with desired functional groups. Hydroxyl groups are often preferred, since they enable appropriate polarity for the irreversible grafting of desired molecules. In this study, the surface kinetics resulting from the treatment of polystyrene with hydroxyl (OH) radicals from the gas phase was fundamentally investigated through a precisely-designed experiment. Polystyrene samples were exposed to various known fluences of OH radicals, and the evolution of surface functional groups versus the OH fluence was monitored using high-resolution X-ray photoelectron spectroscopy (XPS). The fluences of OH radicals varied between 1 × 1018 and 4 × 1023 m−2 in the process of finding a threshold fluence for the formation of specific groups. The surface concentration of carbonyl (C=O) groups could be measured using XPS at a fluence of approximately 5 × 1020 m−2. The C=O groups became measurable at a fluence of approximately 1.5 × 1021 m−2, and carboxyl (COOH)/ester groups at approximately 4 × 1021 m−2. As deduced from the XPS, a concentration of C=O groups at approximately 5 % occurred before the degradation of the aromatic ring. The formation of other oxygen-functional groups required opening of the aromatic ring. The results have been explained using a two-step process, considering available theories vis-a-vis initial stages in the functionalisation of PS with polar functional groups.
Ključne besede: polistiren, kinetika površinske funkcionalizacije, OH radikali, vpliv doze radikalov, časovni razvoj, polystyrene, surface functionalisation kinetics, OH radicals
Objavljeno v DiRROS: 09.11.2023; Ogledov: 252; Prenosov: 108
Povezava na datoteko

Ključne besede: Ions, Layers, Mass spectrometry, Metals, Oxides, SIMS depth profiling H2 C2H2 CO and O2 atmosphere gas flooding cluster secondary ions matrix effect
Objavljeno v DiRROS: 18.10.2023; Ogledov: 320; Prenosov: 143
Celotno besedilo (8,02 MB)
Gradivo ima več datotek! Več...