Repository logo

Browsing by Issue Date, starting with "2025-06-01"

Filter results by year or month
Now showing 1 - 2 of 2
  • Multioccupancy activity recognition based on deep learning models fusing UWB localization heatmaps and nearby-sensor interaction
    Publication . Anguita-Molina, Miguel Ángel; Cardoso, Pedro; Rodrigues, Joao; Medina-Quero, Javier; Polo-Rodríguez, Aurora
    Human activity recognition (HAR) focuses on developing systems and techniques to recognize and categorize human actions automatically based on sensor data. This study combines ultrawideband (UWB) technology and binary sensors to describe and recognize daily activities in real-world environments with multiple occupants, ensuring accurate user localization through noninvasive and privacy-respecting methods. A novel method that combines wearables with UWB technology, which allows the generation of heatmaps for accurate positioning, and binary sensors, which collect nearby interaction with daily activities in naturalistic conditions, is presented. A dataset composed of real-world data collected from three individuals in a real-life environment (house) was compiled. Advanced deep learning models are implemented to effectively fuse spatiotemporal information, leading to an encouraging performance in recognition of daily activities. The promising results suggest that this approach could be viable for large-scale deployments in future smart environments.
    2025-06-01Journal article Open access Show more
  • Plant-based potential in diabetes management: in vitro antioxidant, wound-healing, and enzyme inhibitory activities of southern algarve species
    Publication . Saraiva de Carvalho, Isabel Maria Marques; Mestre Viegas, Cláudia Sofia; Markiewicz, Marta; Galanty, Agnieszka; Paśko, Paweł; Jakupović, Lejsa; Končić, Marijana Zovko
    Type 2 diabetes mellitus (T2DM) is a chronic metabolic disorder characterized by impaired glucose regulation. This study evaluated the antioxidant and antidiabetic potential of aqueous extracts from four plant species from the southern Algarve: Aristolochia baetica, Chelidonium majus, Dittrichia viscosa, and Lavandula viridis, using non-cellular in vitro assays. HPLC/PDA was used to identify active compounds. Antioxidant activity was assessed by using TAA, FRAP, RP, and DPPH assays; antidiabetic potential through alpha-glucosidase and alpha-amylase inhibition; and wound healing relevance through elastase, collagenase, and lipoxygenase inhibition. D. viscosa showed the highest antioxidant activity (FRAP: 1132.99 +/- 19.54 mg TE/g dw; DPPH IC50 = 25.85 +/- 0.75 mu g/mL) and total phenolic/flavonoid content, with a diverse profile including caffeic and chlorogenic acids, isoquercetin, and quercetin. It also exhibited potent alpha-glucosidase inhibition (IC50 = 0.61 +/- 0.06 mg/mL), outperforming acarbose. L. viridis had the highest total phenolic content (39.04 mg/g), while A. baetica demonstrated the strongest anti-elastase, anti-collagenase, and lipoxygenase activity, suggesting wound-healing potential. C. majus showed the weakest effects. A strong correlation was observed between phenolic content and antioxidant/antidiabetic activity. These findings support further in vivo studies on D. viscosa and A. baetica for potential use in T2DM management and diabetic wound healing.
    2025-06-01Journal article Open access Show more