Fant 97 publikasjoner. Viser side 1 av 5:
2026
2025
2026
2025
2025
Detection of Body Shaming in Social Media: Traditional Machine Learning vs. Transformer-based Models
2025
2024
2025
Semantic Modeling of Waste Dataflow for Automating Circular Economy Systems
Circular Economy (CE) is a model with a concrete action plan covering the whole life cycle of a product, from production and consumption to waste management (WM). Information technologies considerably contribute to the transition towards CE, e.g., waste tracking using Internet of Things (IoT). This will cause the businesses and organizations to confront a large diversity of data (i.e. waste amount, types, locations, etc.). The generated data is often stored and processed through manual or semi-manual methods by each business or organization. However, an automated method which can also interpret and integrate the diverse data in WM fields across different organizations is still in its infancy. Often, such data is not organized and falls short of reaching its full potential in facilitating coordinated management and enabling Circular Economy initiatives. In this paper, we aim to address this need through automated interpretation and integration of municipal waste data by applying semantic data modeling. Our approach proposes to capture the semantical description of entities in the WM process and their relations, which can appear between waste producers, authorities and consumers. Then, the obtained semantic model will facilitate and automate the required interpretation and integration of waste data, both for intra- and inter-organization scenarios. We realize intelligent semantic-based searching using natural language processing and large language models.
2024
2020
2020
2023
Effect of filter type in ventilation systems on NO2 concentrations in classrooms
This study was conducted to assess how different filter types in the ventilation system affect the indoor NO2 concentrations. Measurements were carried out in two classrooms and air intakes in a primary school located in Oslo, Norway. A regular F7 particle filter and an F7 combination filter with activated charcoal lin-ing were compared. NO2 concentrations were measured for five weeks during winter 2017 in a cross-over study design to compare: 1) NO2-levels in classrooms with regular filter (RF) versus combination filter (CF); 2) indoor/outdoor ratio with regular filter versus combination filter. One-hour average concentrations are reported during operating time of the ventilation system (6:00-23:00) and during hours with high (> 40 μg/m3) outdoor NO2 concentrations. The measured average NO2 concentrations in both classrooms with an RF were significantly higher than with a CF. The median CF/RF ratios for the two class-rooms were 0.50 and 0.81 during hours with high NO2 concentrations, and 0.48 and 1.00 during the period the ventilation system was operational. During hours with high NO2 concentrations, themedian indoor/outdoor ratios for the two class-rooms with an RF were above 1.00, while the corresponding ratios with a CF were 0.78 and 0.75. Our results demonstrate that a combination filter is more efficient than a regular filter in reducing NO2 concentrations in classrooms during hours with high out-door concentrations.
2019
2019
Accurate Lightweight Calibration Methods for Mobile Low-Cost Particulate Matter Sensors
Monitoring air pollution is a critical step towards improving public health, particularly when it comes to identifying the primary air pollutants that can have an impact on human health. Among these pollutants, particulate matter (PM) with a diameter of up to 2.5 μm (or PM2.5) is of particular concern, making it important to continuously and accurately monitor pollution related to PM. The emergence of mobile low-cost PM sensors has made it possible to monitor PM levels continuously in a greater number of locations. However, the accuracy of mobile low-cost PM sensors is often questionable as it depends on geographical factors such as local atmospheric conditions. <p>This paper presents new calibration methods for mobile low-cost PM sensors that can correct inaccurate measurements from the sensors in real-time. Our new methods leverage Neural Architecture Search (NAS) to improve the accuracy and efficiency of calibration models for mobile low-cost PM sensors. The experimental evaluation shows that the new methods reduce accuracy error by more than 26% compared with the state-of-the-art methods. Moreover, the new methods are lightweight, taking less than 2.5 ms to correct each PM measurement on Intel Neural Compute Stick 2, an AI-accelerator for edge devices deployed in air pollution monitoring platforms.
2023
2024
2025
2018