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: 200; Prenosov: 79
Celotno besedilo (6,40 MB)
Gradivo ima več datotek! Več...

Povzetek: Equipment made of different stainless steels is often used in the hydrometallurgical processing industry. In this study, an electrical resistance sensor was developed for monitoring corrosion in acidic solutions at high temperature. Two types of stainless steel were used as the electrode materials, namely grade 316L stainless steel (EN 1.4404) and grade 2507 duplex stainless steel (EN 1.4410). The materials and sensors were exposed to a 10% H2SO4 solution containing 5000 mg/L of NaCl at various temperatures. Results from the sensors were verified using electrochemical techniques and postexposure examination. Results showed that the microstructure played an important role in the interpretation of corrosion rates, highlighting the importance of using an appropriate stainless steel for the production of sensors. Electrochemical tests and postexposure examination both showed that the grade 2507 had a significantly lower corrosion rate compared to the grade 316L. Under industrial‑process conditions, the results for the grade 2507 sensor were promising with respect to sensor durability and performance, despite the extremely harsh operating environment.
Ključne besede: stainless steel, hydrometallurgical industry, sulphuric acid, electrical resistance sensor, corrosion
Objavljeno v DiRROS: 05.07.2023; Ogledov: 308; Prenosov: 176
Celotno besedilo (5,12 MB)
Gradivo ima več datotek! Več...

Ključne besede: quartz crystal microbalance, mAb, in-line sensor, protein A, continuous multi-column affinity chromatography
Objavljeno v DiRROS: 01.09.2020; Ogledov: 1491; Prenosov: 1053
Celotno besedilo (1,82 MB)
Gradivo ima več datotek! Več...